FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
THE PATENTS RULES, 2003
COMPLETE
SPECIFICATION
(See section 10; rule 13)
TITLE OF THE INVENTION
SYSTEM AND METHOD FOR MONITORING SUBSCRIBER EXPERIENCE INDICES
APPLICANT
JIO PLATFORMS LIMITED
of Office-101, Saffron, Nr. Centre Point, Panchwati 5 Rasta, Ambawadi, Ahmedabad -
380006, Gujarat, India; Nationality : India
The following specification particularly describes
the invention and the manner in which
it is to be performed
2
RESERVATION OF RIGHTS
[0001] A portion of the disclosure of this patent document contains material,
which is subject to intellectual property rights such as, but are not limited to,
copyright, design, trademark, Integrated Circuit (IC) layout design, and/or trade
dress protection, belonging to Jio Platforms Limited (JPL) 5 or its affiliates
(hereinafter referred as owner). The owner has no objection to the facsimile
reproduction by anyone of the patent document or the patent disclosure, as it
appears in the Patent and Trademark Office patent files or records, but otherwise
reserves all rights whatsoever. All rights to such intellectual property are fully
10 reserved by the owner.
FIELD OF DISCLOSURE
[0002] The embodiments of the present disclosure generally relate to
communication networks. In particular, the present disclosure relates to a system
and a method for monitoring subscriber experience indices.
15 DEFINITION
[0003] As used in the present disclosure, the following terms are generally
intended to have the meaning as set forth below, except to the extent that the context
in which they are used to indicate otherwise.
[0004] The expression ‘subscriber experience indices’ used hereinafter in
20 the specification refers to a set of metrics used to quantify and improve the overall
satisfaction and quality of service for subscribers (customers) of a particular service
provider, typically in industries such as telecommunications, media, and
subscription-based services. These indices are crucial for understanding how well
a company meets its customers' expectations and where improvements are needed.
25 For example, a mobile network provider might utilize indices such as customer
satisfaction (CSAT) surveys to gauge user satisfaction with network coverage and
customer service, while tracking net promoter score (NPS) to measure customer
3
loyalty and likelihood to recommend services. They might also monitor Churn Rate
to assess subscriber retention, calculate average revenue per user (ARPU) to
understand revenue trends per customer, and track metrics like first call resolution
(FCR) to ensure efficient issue resolution. Service availability metrics help in
measuring uptime and reliability, while adherence to service 5 level agreements
(SLAs) ensures consistent service delivery standards.
[0005] The expression ‘Radio Access Network (RAN) logs’ used
hereinafter in the specification refers to detailed records or data generated by the
components and devices within a Radio Access Network, which is a critical part of
10 a mobile telecommunications system. The RAN logs capture various operational
and performance-related information about the network elements, including base
stations (NodeBs, eNodeBs in LTE/4G, gNodeBs in 5G), antennas, and other
equipment responsible for wireless communication with mobile devices.
[0006] The expression ‘one or more subscribers’ used hereinafter in the
15 specification refers to at least one individual or entity that has subscribed to a
particular service provided by a telecom operator or service provider. The one or
more subscribers indicate that there is at least one user who has signed up for and
is using the telecom service, such as a mobile phone network, internet service, or
cable television service.
20 [0007] These definitions are in addition to those expressed in the art.
BACKGROUND OF DISCLOSURE
[0008] The following description of related art is intended to provide
background information pertaining to the field of the disclosure. This section may
include certain aspects of the art that may be related to various features of the
25 present disclosure. However, it should be appreciated that this section be used only
to enhance the understanding of the reader with respect to the present disclosure,
and not as admissions of prior art.
4
[0009] In the rapidly evolving telecommunications industry, cellular
network operators face the critical challenge of effectively monitoring and
understanding the experience of their subscribers. Traditional methods of gauging
subscriber satisfaction, such as direct interaction or surveys, prove inadequate due
to the vast scale and complexity of modern cellular networks. 5 Consequently,
operators must rely on inferring subscriber experience from various network data,
particularly Radio Access Network (RAN) logs, which contain valuable
information about the performance and behaviour of the network. However,
existing solutions often struggle to derive meaningful insights from this data, failing
10 to establish strong correlations between network attributes and subscriber
experience indices.
[0010] Current monitoring tools for subscriber experience in the market
primarily focus on presenting raw subscriber usage data, such as call volumes or
data consumption. While this information is valuable, it fails to provide a
15 comprehensive understanding of subscribers' satisfaction with the network services.
Some solutions attempt to bridge this gap by employing heuristics or combining
various attributes of usage data to infer subscriber satisfaction. However, these
approaches often fall short in terms of accuracy and meaningful insights, as they
lack the ability to fully grasp the context and nuances of the heuristic functions
20 used. Furthermore, these solutions do not effectively leverage the rich data available
in RAN logs to establish strong correlations between network performance and
subscriber experience.
[0011] Moreover, existing dashboards offer limited flexibility for network
operators to monitor subscribers' experience and happiness index. Queries to extract
25 subscriber-level records are often structured and restrictive, hindering the ability to
gain a holistic view of the subscriber experience. The absence of a unified
dashboard that captures and displays subscriber experience for comprehensive
monitoring and analysis further compounds the challenges faced by network
operators. Additionally, the lack of advanced analytics capabilities, such as machine
30 learning and artificial intelligence, in existing solutions hinders the ability to
5
uncover complex patterns and correlations between network attributes and
subscriber experience indices.
[0012] Prior art, such as TR2021020819A2, addresses the problem of
determining patterns among customer problem solution methods in a call center
setting. The prior art proposes a system that analyzes customer 5 information, call
records, and customer representative expressions to create a problem-solution
dictionary using machine learning models. While the prior art aims to improve the
resolution of customer problems in real-time, it does not specifically address the
challenges of monitoring and understanding subscriber experience in a cellular
10 network context. Moreover, the prior art does not focus on leveraging RAN logs
and establishing correlations between network attributes and subscriber experience
indices.
[0013] It is therefore a need of the present invention to provide a system and
method that enables accurate and meaningful monitoring of subscriber experience
15 indices in cellular networks.
SUMMARY
[0014] The present disclosure discloses a system for monitoring subscriber
experience indices. The system includes a memory and one or more processors. The
one or more processors is communicatively coupled with the memory. The one or
20 more processors are configured to execute instructions stored in the memory to
receive, from a monitoring unit, a request for determining a set of subscriber
experience indices of one or more subscribers. The one or more processors are
configured to retrieve radio access network (RAN) logs from a second database, the
RAN logs comprising one or more attributes. The one or more processors are
25 configured to compute, using an Artificial Intelligence (AI) engine, one or more
correlation values between the one or more attributes of the RAN logs and the set
of subscriber experience indices. The one or more processors are configured to
determine the set of subscriber experience indices by using the one or more
computed correlation values. The one or more processors are configured to transmit
6
the set of determined subscriber experience indices and the one or more computed
correlation values to the monitoring unit.
[0015] In an embodiment, the system includes a request processing engine
configured to determine whether the requested set of subscriber experience indices
is available in a first database. The first database is configured 5 to store a set of
precomputed subscriber experience indices. The request processing engine is
configured to retrieve the precomputed set of subscriber experience indices from
the first database when the requested set of subscriber experience indices is
available. The request processing engine is configured to compute, by a
10 computation engine, the requested set of subscriber experience indices when the
requested set of subscriber experience indices is not available in the first database.
[0016] In an embodiment, for computing the requested set of subscriber
experience indices, the computation engine is configured to retrieve the set of RAN
logs from a second database and derive the requested set of subscriber experience
15 indices from radio frequency (RF) data in the retrieved set of RAN logs.
[0017] In an embodiment, the one or more attributes of the RAN logs
include at least one of a timestamp, a unique identifier of the subscriber, a base
station identifier, an event type, a signal strength, and quality metrics.
[0018] In an embodiment, the AI engine is further configured to analyze the
20 one or more computed correlation values to identify one or more network issues
and generate one or more recommendations for resolving the identified one or more
network issues.
[0019] In an embodiment, the one or more processors are further configured
to transmit the one or more generated recommendations to the monitoring unit and
25 resolve the identified one or more network issues based on generated one or more
recommendations.
7
[0020] In an embodiment, the set of subscriber experience indices includes
at least one of a happiness score, top call release reasons, volume of services used,
time spent by subscribers using services, and subscriber journey with base stations.
[0021] In an embodiment, the monitoring unit is configured to display the
received set of subscriber experience indices on a user interface 5 and provide an
interactive interface for users to analyze and visualize the set of determined
subscriber experience indices.
[0022] The present disclosure discloses a method for monitoring subscriber
experience indices. The method includes receiving, from a monitoring unit, a
10 request for determining a set of subscriber experience indices of one or more
subscribers. The method includes retrieving radio access network (RAN) logs from
a second database, the RAN logs comprising one or more attributes. The method
includes computing, using an Artificial Intelligence (AI) engine, one or more
correlation values between the one or more attributes of the RAN logs and the set
15 of subscriber experience indices. The method includes determining the set of
subscriber experience indices by using the one or more computed correlation
values. The method includes transmitting the set of determined subscriber
experience indices and the one or more computed correlation values to the
monitoring unit.
20 [0023] In an embodiment, a step of retrieving the set of subscriber
experience indices includes steps of determining, by a request processing engine,
whether the requested set of subscriber experience indices is available in a first
database. The first database is configured to store a set of precomputed subscriber
experience indices. The step of retrieving the set of subscriber experience indices
25 includes retrieving the precomputed set of subscriber experience indices from the
first database when the requested set of subscriber experience indices is available.
The step of retrieving the set of subscriber experience indices includes computing,
by a computation engine, the requested set of subscriber experience indices when
8
the requested set of subscriber experience indices is not available in the first
database.
[0024] In an embodiment, a step of computing the requested set of
subscriber experience indices by the computation engine further includes retrieving
a set of RAN logs from a second database and deriving the 5 requested set of
subscriber experience indices from radio frequency (RF) data in the retrieved set of
RAN logs.
[0025] In an embodiment, the method includes analyzing the one or more
computed correlation values to identify one or more network issues and generating
10 recommendations for resolving the identified one or more network issues.
[0026] In an embodiment, the method further includes transmitting the one
or more generated recommendations to the monitoring unit and resolving the
identified one or more network issues based on generated recommendations.
[0027] In an embodiment, the method further includes displaying the
15 received set of subscriber experience indices on a user interface of the monitoring
unit and providing an interactive interface for users to analyze and visualize the set
of determined subscriber experience indices.
[0028] The present disclosure discloses a user equipment communicatively
coupled to a system through a network. The user equipment is configured to monitor
20 subscriber experience indices. The user equipment a memory and one or more
processors coupled with the memory. The one or more processors are configured to
execute instructions stored in the memory to perform steps of a method for
monitoring subscriber experience indices. The method includes receiving, from a
monitoring unit, a request for determining a set of subscriber experience indices of
25 one or more subscribers. The method includes retrieving radio access network
(RAN) logs from a second database, the RAN logs comprising one or more
attributes. The method includes computing, using an Artificial Intelligence (AI)
engine, one or more correlation values between the one or more attributes of the
9
RAN logs and the set of subscriber experience indices. The method includes
determining the set of subscriber experience indices by using the one or more
computed correlation values. The method includes transmitting the set of
determined subscriber experience indices and the one or more computed correlation
values to the 5 monitoring unit.
OBJECTS OF THE PRESENT DISCLOSURE
[0029] Some of the objects of the present disclosure, which at least one
embodiment herein satisfies, are as listed herein below.
[0030] An object of the present disclosure is to provide a system and a
10 method for monitoring subscriber experience indices.
[0031] Another object of the present disclosure is to provide a dashboard
that displays a set of subscriber experience includes happiness score, type of failure
faced, clear codes count, failed procedure, subscriber journey with a base station,
distribution of call release reasons, distribution of services consumed, and the like.
15 [0032] Another object of the present disclosure is to provide a system and a
method that determines subscriber experience indices using Radio Access Network
(RAN) logs.
[0033] Another object of the present disclosure is to provide a system and a
method that allows operators to identify and troubleshoot network issues if
20 subscriber experience indices fall outside a predetermined range.
[0034] Another object of the present disclosure is to provide a system and a
method with a flexible and interactive interface for visualizing and analyzing
subscriber experience indices.
[0035] Another object of the present disclosure is to provide a system and
25 method that computes correlation values between attributes of Radio Access
Network (RAN) logs and subscriber experience indices. By analyzing these
10
correlation values, the system may identify network issues impacting subscriber
experience and generate recommendations for resolving them, enabling network
operators to proactively manage and optimize network performance.
BRIEF DESCRIPTION OF DRAWINGS
[0036] The accompanying drawings, which are incorporated 5 herein, and
constitute a part of this disclosure, illustrate exemplary embodiments of the
disclosed methods and systems in which like reference numerals refer to the same
parts throughout the different drawings. Components in the drawings are not
necessarily to scale, emphasis instead being placed upon clearly illustrating the
10 principles of the present disclosure. Some drawings may indicate the components
using block diagrams and may not represent the internal circuitry of each
component. It will be appreciated by those skilled in the art that disclosure of such
drawings includes the disclosure of electrical components, electronic components
or circuitry commonly used to implement such components.
15 [0037] FIG. 1 illustrates an exemplary network architecture for
implementing a system for monitoring subscriber experience indices, in accordance
with embodiments of the present disclosure.
[0038] FIG. 2 illustrates an exemplary block diagram of the system, in
accordance with embodiments of the present disclosure.
20 [0039] FIG. 3 illustrates an exemplary implementation of the system, in
accordance with embodiments of the present disclosure.
[0040] FIG. 4 illustrates an exemplary flowchart of a method for monitoring
subscriber experience indices, in accordance with embodiments of the present
disclosure.
25 [0041] FIG. 5 illustrates an exemplary computer system in which or with
which embodiments of the present disclosure may be implemented.
11
[0042] FIG. 6 illustrates another exemplary flowchart of the method for
monitoring subscriber experience indices, in accordance with embodiments of the
present disclosure.
[0043] The foregoing shall be more apparent from the following more
detailed description 5 of the disclosure.
LIST OF REFERENCE NUMERALS
100 – Network Architecture
102-1, 102-2, 102-3 – User (s)
104-1, 104-2, 104-3 – User Equipment (s)
10 106 –Network
108 – System
110-1– Network entity 1
110-2– Network entity 2
112-1– Base station-1
15 112-2– Base station-2
114– Monitoring unit
202 – One or more processor(s)
204 – Memory
206 –Interface(s)
20 210 –Database
210-1– First Database
210-2– Second Database
212 – Request Processing engine
214 – Computation engine
25 216 – AI engine
218 – Other unit(s)
220– Distributed file system
400 – Method flowchart
510 – External Storage Device
12
520 – Bus
530 – Main Memory
540 – Read Only Memory
550 – Mass Storage Device
560 – 5 Communication Port
570 – Processor
BRIEF DESCRIPTION OF THE INVENTION
[0044] In the following description, for the purposes of explanation, various
specific details are set forth in order to provide a thorough understanding of
10 embodiments of the present disclosure. It will be apparent, however, that
embodiments of the present disclosure may be practiced without these specific
details. Several features described hereafter can each be used independently of one
another or with any combination of other features. An individual feature may not
address any of the problems discussed above or might address only some of the
15 problems discussed above. Some of the problems discussed above might not be
fully addressed by any of the features described herein. Example embodiments of
the present disclosure are described below, as illustrated in various drawings in
which like reference numerals refer to the same parts throughout the different
drawings.
20 [0045] The ensuing description provides exemplary embodiments only, and
is not intended to limit the scope, applicability, or configuration of the disclosure.
Rather, the ensuing description of the exemplary embodiments will provide those
skilled in the art with an enabling description for implementing an exemplary
embodiment. It should be understood that various changes may be made in the
25 function and arrangement of elements without departing from the spirit and scope
of the disclosure as set forth.
[0046] Specific details are given in the following description to provide a
thorough understanding of the embodiments. However, it will be understood by one
of ordinary skill in the art that the embodiments may be practiced without these
13
specific details. For example, circuits, systems, networks, processes, and other
components may be shown as components in block diagram form in order not to
obscure the embodiments in unnecessary detail. In other instances, well-known
circuits, processes, algorithms, structures, and techniques may be shown without
unnecessary detail in order to avoid obscuring 5 the embodiments.
[0047] Also, it is noted that individual embodiments may be described as a
process that is depicted as a flowchart, a flow diagram, a data flow diagram, a
structure diagram, or a block diagram. Although a flowchart may describe the
operations as a sequential process, many of the operations can be performed in
10 parallel or concurrently. In addition, the order of the operations may be re-arranged.
A process is terminated when its operations are completed but could have additional
steps not included in a figure. A process may correspond to a method, a function, a
procedure, a subroutine, a subprogram, etc. When a process corresponds to a
function, its termination can correspond to a return of the function to the calling
15 function or the main function.
[0048] The word “exemplary” and/or “demonstrative” is used herein to
mean serving as an example, instance, or illustration. For the avoidance of doubt,
the subject matter disclosed herein is not limited by such examples. In addition, any
aspect or design described herein as “exemplary” and/or “demonstrative” is not
20 necessarily to be construed as preferred or advantageous over other aspects or
designs, nor is it meant to preclude equivalent exemplary structures and techniques
known to those of ordinary skill in the art. Furthermore, to the extent that the terms
“includes,” “has,” “contains,” and other similar words are used in either the detailed
description or the claims, such terms are intended to be inclusive like the term
25 “comprising” as an open transition word without precluding any additional or other
elements.
[0049] Reference throughout this specification to “one embodiment” or “an
embodiment” or “an instance” or “one instance” means that a particular feature,
structure, or characteristic described in connection with the embodiment is included
14
in at least one embodiment of the present disclosure. Thus, the appearances of the
phrases “in one embodiment” or “in an embodiment” in various places throughout
this specification are not necessarily all referring to the same embodiment.
Furthermore, the particular features, structures, or characteristics may be combined
in any suitable manner in one or 5 more embodiments.
[0050] The terminology used herein is to describe particular embodiments
only and is not intended to be limiting the disclosure. As used herein, the singular
forms “a”, “an”, and “the” are intended to include the plural forms as well, unless
the context indicates otherwise. It will be further understood that the terms
10 “comprises” and/or “comprising,” when used in this specification, specify the
presence of stated features, integers, steps, operations, elements, and/or
components, but do not preclude the presence or addition of one or more other
features, integers, steps, operations, elements, components, and/or groups thereof.
As used herein, the term “and/or” includes any combinations of one or more of the
15 associated listed items. It should be noted that the terms “mobile device”, “user
equipment”, “user device”, “communication device”, “device” and similar terms
are used interchangeably for the purpose of describing the invention. These terms
are not intended to limit the scope of the invention or imply any specific
functionality or limitations on the described embodiments. The use of these terms
20 is solely for convenience and clarity of description. The invention is not limited to
any particular type of device or equipment, and it should be understood that other
equivalent terms or variations thereof may be used interchangeably without
departing from the scope of the invention as defined herein.
[0051] As used herein, an “electronic device”, or “portable electronic
25 device”, or “user device”, or “communication device”, or “user equipment”, or
“device” refers to any electrical, electronic, electromechanical, and computing
device. The user device is capable of receiving and/or transmitting one or
parameters, performing function/s, communicating with other user devices, and
transmitting data to the other user devices. The user equipment may have a
30 processor, a display, a memory, a battery, and an input-means such as a hard keypad
15
and/or a soft keypad. The user equipment may be capable of operating on any radio
access technology including but not limited to IP-enabled communication, Zig Bee,
Bluetooth, Bluetooth Low Energy, Near Field Communication, Z-Wave, Wi-Fi,
Wi-Fi direct, etc. For instance, the user equipment may include, but not limited to,
a mobile phone, smartphone, virtual reality (VR) devices, augmented 5 reality (AR)
devices, laptop, a general-purpose computer, desktop, personal digital assistant,
tablet computer, mainframe computer, or any other device as may be obvious to a
person skilled in the art for implementation of the features of the present disclosure.
[0052] Further, the user device may also comprise a “processor” or
10 “processing unit” includes processing unit, wherein processor refers to any logic
circuitry for processing instructions. The processor may be a general-purpose
processor, a special purpose processor, a conventional processor, a digital signal
processor, a plurality of microprocessors, one or more microprocessors in
association with a DSP core, a controller, a microcontroller, Application Specific
15 Integrated Circuits, Field Programmable Gate Array circuits, any other type of
integrated circuits, etc. The processor may perform signal coding data processing,
input/output processing, and/or any other functionality that enables the working of
the system according to the present disclosure. More specifically, the processor is
a hardware processor.
20 [0053] As portable electronic devices and wireless technologies continue to
improve and grow in popularity, the advancing wireless technologies for data
transfer are also expected to evolve and replace the older generations of
technologies. In the field of wireless data communications, the dynamic
advancement of various generations of cellular technology are also seen. The
25 development, in this respect, has been incremental in the order of second generation
(2G), third generation (3G), fourth generation (4G), and now fifth generation (5G),
and more such generations are expected to continue in the forthcoming time.
[0054] While considerable emphasis has been placed herein on the
components and component parts of the preferred embodiments, it will be
16
appreciated that many embodiments can be made and that many changes can be
made in the preferred embodiments without departing from the principles of the
disclosure. These and other changes in the preferred embodiment as well as other
embodiments of the disclosure will be apparent to those skilled in the art from the
disclosure herein, whereby it is to be distinctly understood 5 that the foregoing
descriptive matter is to be interpreted merely as illustrative of the disclosure and
not as a limitation.
[0055] In the rapidly evolving telecommunications industry, cellular
network operators face the critical challenge of effectively monitoring and
10 understanding the experience of their subscribers. Modern cellular networks'
increasing complexity and scale have made it difficult for operators to gauge
subscriber satisfaction using traditional methods such as surveys or direct
interaction. Consequently, operators must infer subscriber experience from vast
amounts of network data, particularly Radio Access Network (RAN) logs.
15 However, existing solutions often struggle to derive meaningful insights from this
data, providing only a superficial understanding of subscriber experience. The
present disclosure addresses these challenges by introducing a comprehensive
system and method for monitoring subscriber experience indices, leveraging
advanced techniques such as Artificial Intelligence (AI) and correlation analysis to
20 derive actionable insights from RAN logs and subscriber usage data. In an example,
the RAN logs may include:
 Call Detail Records (CDRs): Information about calls made and received,
including call duration, location, and quality metrics.
 Signal Strength and Quality: Measurements of radio signal strength, Signal25
to-Noise Ratio (SNR), and other RF (Radio Frequency) parameters.
 Handover Events: Records of when a mobile device switches from one base
station to another to maintain connectivity as it moves.
17
 Alarms and Events: Notifications and alerts generated by network equipment
for anomalies, faults, or performance issues.
 Performance Metrics: Data on throughput, latency, packet loss, and other
network performance indicators.
 Subscriber Activity: Information on subscriber connections, 5 session durations,
and data usage patterns
[0056] The present disclosure aims to empower network operators with a
powerful tool for monitoring and analyzing subscriber experience indices, enabling
them to proactively manage and optimize network performance. By computing
10 correlation values between attributes of RAN logs and subscriber experience
indices using an AI engine, the system can identify network issues impacting
subscriber satisfaction and generate recommendations for resolving them. This
proactive approach to network management can lead to improved subscriber
experience, reduced churn rates, and increased customer loyalty in the highly
15 competitive telecommunications market. The system also provides a
comprehensive dashboard that displays a range of metrics used for determining
subscriber experience indices, offering network operators a holistic view of
subscriber satisfaction and network performance.
[0057] The present disclosure relates to a system and method for monitoring
20 subscriber experience indices in a cellular network. The system comprises a
memory and one or more processors configured to execute instructions stored in
the memory. The processors receive requests from a monitoring unit to determine
subscriber experience indices, retrieve the indices and RAN logs from databases,
and compute correlation values between attributes of the RAN logs and the indices
25 using an AI engine. The computed subscriber experience indices and correlation
values are then transmitted to the monitoring unit for display and analysis. The
system and method may leverage various components such as a request processing
18
engine, a computation engine, and databases storing precomputed indices and RAN
logs to efficiently process and analyze the data.
[0058] The various embodiments throughout the disclosure will be
explained in more detail with reference to FIG. 1- FIG. 6.
[0059] FIG. 1 illustrates an exemplary network architecture 5 (100) for
implementing a system (108) for monitoring subscriber experience indices in a
network (106), in accordance with embodiments of the present disclosure.
[0060] Referring to FIG. 1, the network architecture (100) may include one
or more computing devices or user equipments (104-1, 104-2, 104-3) associated
10 with one or more users (102-1, 102-2, 102-3) in an environment. A person of
ordinary skill in the art will understand that one or more users (102-1, 102-2, 102-
3) may be individually referred to as the user (102) and collectively referred to as
the users (102). Similarly, a person of ordinary skill in the art will understand that
one or more user equipments (104-1, 104-2, 104-3) may be individually referred to
15 as the user equipment (104) and collectively referred to as the user equipment (104).
A person of ordinary skill in the art will appreciate that the terms “computing
device(s)” and “user equipment” may be used interchangeably throughout the
disclosure. Although three user equipments (104) are depicted in FIG. 1, however
any number of the user equipment’s (104) may be included without departing from
20 the scope of the ongoing description.
[0061] In an embodiment, the user equipment (104) may include, but is not
limited to, a handheld wireless communication device (e.g., a mobile phone, a smart
phone, a phablet device, and so on), a wearable computer device(e.g., a headmounted
display computer device, a head-mounted camera device, a wristwatch
25 computer device, and so on), a Global Positioning System (GPS) device, a laptop
computer, a tablet computer, or another type of portable computer, a media playing
device, a portable gaming system, and/or any other type of computer device with
wireless communication capabilities, and the like. In an embodiment, the user
equipment (104) may include, but is not limited to, any electrical, electronic,
19
electro-mechanical, or an equipment, or a combination of one or more of the above
devices such as virtual reality (VR) devices, augmented reality (AR) devices,
laptop, a general-purpose computer, desktop, personal digital assistant, tablet
computer, mainframe computer, or any other computing device, where the user
equipment (104) may include one or more in-built or externally coupled 5 accessories
including, but not limited to, a visual aid device such as a camera, an audio aid, a
microphone, a keyboard, and input devices for receiving input from the user (102)
or the entity such as touch pad, touch enabled screen, electronic pen, and the like.
A person of ordinary skill in the art will appreciate that the user equipment (104)
10 may not be restricted to the mentioned devices and various other devices may be
used. The architecture may include a monitoring unit (114) having a user interface
that provides audio-visual indications to the user based on a set of signals
transmitted by the system (108). In an embodiment, the monitoring unit (114) may
be implemented on a UE (104) and may be used by operators of the network (106).
15 [0062] Referring to FIG. 1, the user equipment (104) may communicate
with the system (108) through the network (106). In an embodiment, the network
(106) may include at least one of a Fifth Generation (5G) network, 6G network, or
the like. The network (106) may enable the user equipment (104) to communicate
with other devices in the network architecture (100) and/or with the system (108).
20 The network (106) may include a wireless card or some other transceiver
connection to facilitate this communication. In another embodiment, the network
(106) may be implemented as, or include any of a variety of different
communication technologies such as a wide area network (WAN), a local area
network (LAN), a wireless network, a mobile network, a Virtual Private Network
25 (VPN), the Internet, the Public Switched Telephone Network (PSTN), or the like.
In an embodiment, each of the UE (104) may have a unique identifier attribute
associated therewith. In an embodiment, the unique identifier attribute may be
indicative of Mobile Station International Subscriber Directory Number
(MSISDN), International Mobile Equipment Identity (IMEI) number, International
20
Mobile Subscriber Identity (IMSI), Subscriber Permanent Identifier (SUPI) and the
like.
[0063] In an embodiment, the network (106) may include one or more base
stations (112-1, 112-2), with which the UEs (104) may connect to and request
services from. The base station (112-1, 112-2) may be a network infrastructure 5 that
provides wireless access to one or more terminals associated therewith. The base
station (112-1, 112-2) may have coverage defined to be a predetermined geographic
area based on the distance over which a signal may be transmitted. The base station
(112-1, 112-2) may include, but not be limited to, wireless access point, evolved
10 NodeB (eNodeB), 5G node or next generation NodeB (gNB), wireless point,
transmission/reception point (TRP), and the like. In an embodiment, the base station
(112-1, 112-2) may include one or more operational units that enable
telecommunication between two or more UEs (104). In an embodiment, the one or
more operational units may include, but not be limited to, transceivers, baseband
15 unit (BBU), remote radio unit (RRU), antennae, mobile switching centres, radio
network control units, one or more processors associated thereto, and a plurality of
network entities (110-1, 110-2) such as Access and Mobility Management Function
(AMF) unit, Session Management Function (SMF) unit, Network Exposure
Function (NEF) units, or any custom built functions executing one or more
20 processor-executable instructions, but not limited thereto.
[0064] In an embodiment, RAN logs may be generated as the operational
units or network entities (110-1, 110-2) interact with each other and the UE (104)
to provide services thereto. RAN logs refer to the records or data generated by
various components of the radio access network, such as base stations, radio
25 network controllers, or other network elements. These logs may contain detailed
information about the performance and behaviour of the network, including
timestamps, unique identifiers of subscribers, base station identifiers, event types,
signal strengths, and quality metrics. RAN logs may serve as a valuable source of
data for analyzing and deriving insights into the subscriber experience. RAN logs
30 are essential for network monitoring, troubleshooting, optimization, and
21
performance analysis. The RAN logs are used by network operators, engineers, and
analysts to maintain network quality, identify and resolve issues promptly, optimize
network resources, and improve the overall subscriber experience. In an
embodiment, the RAN logs may include one or more attributes that may be used to
derive performance and health metrics of the network (106). In 5 an embodiment, the
one or more attributes may include, but not be limited to, radio summary logs,
timestamps, UE (104) information such as unique identifier attributes,
configurations details, device type, etc., call event details, signal strength metrics,
throughput metrics, unique attributes associated with the base stations (112), alarms
10 and fault details, error codes, and the like. In an embodiment, the RAN logs may be
used to compute the subscriber experience indices.
[0065] In an embodiment, the system (108) may be coupled to a monitoring
unit (114) that may provide an audio-visual interface to the user (102) for
monitoring and analyzing data. In an embodiment, the monitoring unit (114) may
15 provide an interface, including, but not limited to, a Graphical User Interface (GUI),
an Application Programming Interface (API) or a Command Line Interface (CLI).
In an embodiment, the monitoring unit (114) may provide a dashboard for
visualizing and monitoring the subscriber experience indices in real time. In an
embodiment, the monitoring unit (114) may be used by users (102) or operators of
20 the network (106).
[0066] In an embodiment, a user (102) or operator of the network (106) may
use the monitoring unit (114) to transmit a request for determining a set of
subscriber experience indices of one or more subscribers. In an example, the
received request may be a query request (requesting specific information or metrics
25 about subscriber experience), an analysis request (asking for an analysis of current
subscriber experience indices), a report request (requesting a report on the latest
subscriber experience metrics), a comparison request (requesting a comparison of
subscriber experience indices over different time periods or between different
subscriber groups), or a trend analysis request (requesting an analysis of trends in
30 subscriber experience metrics). The request may be transmitted in the form of
22
including, but not limited to, signals, data packets, and the like. In an embodiment,
the system (108) may allow operators to analyze subscriber experience indices of
one or more subscribers and identify factors that improve or reduce the same. In an
embodiment, the system (108) may allow for monitoring the subscriber experience
indices and take pre-emptive actions to ensure the indices remain 5 in a predetermined
range. In an embodiment, when the subscriber experience indices fall below the
predetermined range, it may indicate that the network (106) is underperforming or
malfunctioning. In an embodiment, when the subscriber experience indices exceed
the predetermined range, it may indicate that the network (106) is operating with
10 substantial costs. The system (108) may determine the subscriber experience
indices based on whether a precomputed set of subscriber experience indices is
stored in a first database. In an example, the precomputed set of subscriber
experience indices is defined as a collection of the subscriber experience indices
that have already been calculated or determined beforehand. In an example, the
15 precomputed set of subscriber experience indices includes the subscriber
experience indices that are recently generated. If the precomputed set of subscriber
experience indices for the one or more subscribers is available in the first database,
the system (108) retrieves and transmits the indices to the monitoring unit (114).
[0067] In an embodiment, if the precomputed set of subscriber experience
20 indices is unavailable in the first database, the system (108) may retrieve the set of
RAN logs from a second database and determine the set of subscriber experience
indices therewith. In an aspect, for retrieval of the set of subscriber experience
indices, the system (108) may be configured to transmit a query specific to the first
database to extract the set of subscriber experience indices. In an aspect, the query
25 may include various subscriber experience indices that are needed, or a number of
filters (for example, specific time range, geographical area, network conditions). In
an aspect, the system may be configured to retrieve the data via a server, where the
server is configured to receive the query from the system and provide a response by
processing the query and retrieving the requested data from the first database. If the
30 set of requested subscriber experience indices is not available in the first database,
23
then the system may be configured to send a data retrieval request to the second
database via the server. In an aspect, the data retrieval request may include various
attributes of the RAN logs that are needed, or a number of filters (for example,
specific time range, geographical area, network conditions). The system may be
configured to determine a location and access method for the second 5 database where
the RAN logs are stored. The data retrieval request may include authentication
credentials or permissions granted by an administrator. The system may be
configured to execute the query against the second database using an application
programming interface (API).
10 [0068] The set of subscriber experience indices may be derived from radio
frequency (RF) data in RAN logs. In an embodiment, the system (108) may
compute the subscriber experience indices based on the one or more attributes in
the RAN logs. In an embodiment, the subscriber experience indices may be
determined by an AI engine. In such embodiments, the AI engine may include a
15 pre-trained ML model configured to take the one or more attributes of the RAN
logs as input and provide the subscriber experience indices as output. The system
(108) may store the subscriber experience indices in the first database so that
subsequent requests for substantially similar subscriber experience indices may be
retrieved from the first database instead of being recomputed.
20 [0069] In an embodiment, the subscriber experience indices may include
one or more computed values that indicate the health and performance of the
network, as well as a set of values indicating the satisfaction of the subscribers. In
an example, the one or more computed values may include, but not be limited to, a
happiness score, top call release reason (CRR) encountered, volume of services
25 used, and time spent by subscribers using the services, subscriber journey maps
with a plurality of base stations (112), and the like, which may be computed based
on the one or more attributes of the RAN logs. In an embodiment, the network
operators may use the subscriber experience indices to identify network issues
causing the indices to fall outside the predetermined range.
24
[0070] In an embodiment, the system (108) may compute one or more
correlation values between one or more attributes of the RAN logs and the
subscriber experience indices. In an embodiment, the system (108) may use the AI
engine to compute the correlation values. The one or more correlation values refer
to a statistical measure that quantifies the degree to which two 5 or more variables
are related or move together in a linear fashion. It indicates the strength and
direction of a linear relationship between variables. In an embodiment, the
correlation values may allow network operators to identify the cause of the network
issue. To compute correlation values between attributes of RAN logs and the set of
10 subscriber experience indices, the AI engine, may configured to follow the given
steps:
o Collecting RAN logs, which may include information such as signal
strength, network congestion, handover events, etc.
o Calculating data on selected indices (for example CSAT, NPS, churn
15 rate, etc.), which represent subscriber satisfaction and engagement.
o preprocessing the data to handle missing values, outliers, and ensure
consistency across datasets (RAN logs and subscriber indices).
o Integrating the RAN log attributes with the subscriber experience
indices in a format suitable for analysis.
20 o Determining which attributes from the RAN logs are potentially
correlated with the subscriber experience indices. This might
involve domain expertise and initial exploratory data analysis.
o Using one or many statistical methods such as Pearson correlation
coefficient, Spearman rank correlation, or others to compute
25 correlation values.
o Utilizing machine learning models, particularly regression models
or correlation-based feature selection methods, to identify
significant relationships between RAN log attributes and subscriber
indices.
25
[0071] For instance, if a location attribute in the RAN log has a negative
correlation with the subscriber experience indices, then the network issue may be
associated with underperformance or malfunctioning of base stations (112) in a
location. In an embodiment, the system (108) may also generate one or more
recommendations for performing preventative maintenance or pre-5 emptive network
expansion. In an embodiment, the subscriber experience indices may be used to
resolve network issues and appropriately upgrade specifications or configurations
of the network (106). The system (108) may transmit the subscriber experience
indices to the monitoring unit (114), where the indices may be displayed.
10 [0072] In accordance with embodiments of the present disclosure, the
system (108) may be configured to provide monitoring subscriber experience
indices. In an embodiment, the system (108) may also be configured to provide a
real-time dashboard for monitoring subscriber experience indices.
[0073] FIG. 2 illustrates a block diagram (200) of the system (108), in
15 accordance with embodiments of the present disclosure.
[0074] In an aspect, the system (108) may include one or more processor(s)
(202). The one or more processor(s) (202) may be implemented as one or more
microprocessors, microcomputers, microcontrollers, edge or fog microcontrollers,
digital signal processors, central processing units, logic circuitries, and/or any
20 devices that process data based on operational instructions. Among other
capabilities, the one or more processor(s) (202) may be configured to fetch and
execute computer-readable instructions stored in a memory (204) of the system
(108). The memory (204) may be configured to store one or more computerreadable
instructions or routines in a non-transitory computer readable storage
25 medium, which may be fetched and executed to create or share data packets over a
network service. The memory (204) may include any non-transitory storage device
including, for example, volatile memory such as Random Access Memory (RAM),
or non-volatile memory such as Erasable Programmable Read-Only Memory
(EPROM), flash memory, and the like.
26
[0075] Referring to FIG. 2, the system (108) may include an interface(s)
(206). The interface(s) (206) may include a variety of interfaces, for example,
interfaces for data input and output devices, referred to as I/O devices, storage
devices, and the like. The interface(s) (206) may facilitate communication to/from
the system (108). The interface(s) (206) may also provide 5 a communication
pathway for one or more components of the system (108). Examples of such
components include, but are not limited to, processing unit/engine(s) and a database
(210).
[0076] In an embodiment, the one or more processors (202) may be
10 implemented as a combination of hardware and programming (for example,
programmable instructions) to implement one or more functionalities of the one or
more processors (202). In the examples described herein, such combinations of
hardware and programming may be implemented in several different ways. For
example, the programming for the one or more processors (202) may be processor15
executable instructions stored on a non-transitory machine-readable storage
medium, and the hardware for the one or more processors (202) may include a
processing resource (for example, one or more processors), to execute such
instructions. In the present examples, the machine-readable storage medium may
store instructions that, when executed by the processing resource, implement the
20 one or more processors (202). In such examples, the system (108) may include the
machine-readable storage medium storing the instructions and the processing
resource to execute the instructions, or the machine-readable storage medium may
be separate but accessible to the system (108) and the processing resource. In other
examples, the one or more processors (202) may be implemented by electronic
25 circuitry.
[0077] In an embodiment, the system (108) may include one or more
databases, such as the first database (210-1) and the second database (210-2)
(collectively referred to as a database or databases (210)). In an embodiment, the
database (210) includes data that may be either stored or generated as a result of
30 functionalities implemented by any of the components of the processor (202). In an
27
embodiment, the database (210) may be separate from the system (108). In an
embodiment, the database (210) may be indicative of including, but not limited to,
a relational database, a distributed database, a distributed file sharing system, a
cloud-based database, or the like.
[0078] In an embodiment, the first database (210-1) may 5 be configured to
store a set of precomputed subscriber experience indices. The set of precomputed
subscriber experience indices typically refers to a predefined collection of metrics
or measures that are systematically calculated or prepared to assess the satisfaction,
behaviour, and interaction patterns of subscribers with a service or product. These
10 indices are often used by companies to quickly evaluate and monitor subscriber
experience without having to calculate them from raw data each time. In an
embodiment, the subscriber experience indices may be associated with requests
received from the monitoring unit (114). In an embodiment, the precomputed
subscriber experience indices may be stored such that requests for substantially
15 similar subscriber experience indices may be retrieved from the first database (210-
1) instead of being recomputed. In an embodiment, the RAN logs may be stored in
the second database (210-2). The RAN logs may be retrieved by the system (108)
to process the requests received from the monitoring unit (114). In an embodiment,
the first database (210-1) and the second database (210-2) may be implemented in
20 a single database.
[0079] In an exemplary embodiment, the one or more processors (202) may
include one or more engines selected from any of a request processing engine (212),
a computation engine (214), an AI engine (216), and other engines (218) having
functions that may include, but are not limited to, testing, storage, and peripheral
25 functions, such as wireless communication unit for remote operation, audio unit for
alerts and the like.
[0080] The system (108) may comprise the memory (204) and one or more
processors (202) communicatively coupled with the memory (204). The one or
more processors (202) may be configured to execute instructions stored in the
28
memory (204) to perform various functions associated with monitoring subscriber
experience indices.
[0081] In one embodiment, the system (108) may receive, from the
monitoring unit (114), the request for determining the set of subscriber experience
indices of one or more subscribers. The set of subscriber 5 experience indices
typically includes a variety of metrics that collectively gauge the satisfaction,
engagement, and overall experience of subscribers with a service or product. For
example, the set of subscriber experience indices may include a Customer
Satisfaction Score (CSAT), a Net Promoter Score (NPS), a Customer Effort Score
10 (CES), a Retention Rate, a Churn Rate, an Average Resolution Time and Usage
Metrics.
[0082] The CSAT measures overall satisfaction with a specific interaction,
transaction, or experience. The NPS measures the likelihood of customers
recommending the product or service to others, indicating loyalty and satisfaction.
15 The CES measures the ease of which customers can interact with a service or
complete a task. The churn rate refers to a percentage of subscribers who cancel or
leave the service within a given period, indicating dissatisfaction or disengagement.
The Retention Rate measures the percentage of customers who continue to use the
service over a specified period, indicating satisfaction and loyalty. The Average
20 Resolution Time measures how quickly customer issues or inquiries are resolved,
indicating responsiveness and service efficiency. The usage metrics include metrics
such as frequency of use, duration of use, and feature adoption rates, which reflect
how actively subscribers are engaging with the service. These indices collectively
provide a comprehensive view of subscriber experience, helping organizations
25 identify strengths, weaknesses, and opportunities for improvement to enhance
overall customer satisfaction and loyalty. Subscriber experience indices may refer
to various metrics or indicators that quantify the quality of experience (QoE) of
subscribers using the cellular network. These indices may provide valuable insights
into the performance of the network from the perspective of the subscribers and
30 may help network operators identify areas for improvement.
29
[0083] To determine the set of subscriber experience indices, the system
may be configured to identify the goals of a network operator (marketing, customer
service, product development, and management who are involved or impacted by
subscriber experience). The goals of the network operator clarify the objectives of
measuring subscriber experience indices. For example, 5 improving customer
satisfaction, reducing churn, increasing referrals, etc. Based on the goals, the system
may be configured to define key metrics or review existing metrics. Further, the
system may be configured to select one or more core metrics that directly align with
the goals defined. In an example, the one or more core indices include CSAT, NPS,
10 CES, churn rate, etc. Further, the system may be configured to identify critical
touchpoints where subscriber experience can be measured, such as onboarding,
support interactions, renewal processes, etc. The system is further configured to
gather input and feedback. The system analyzes existing customer feedback,
surveys, and reviews to understand what matters most to subscribers. The system
15 may be configured to prioritize metrics based on their importance to achieving the
goals set. In an aspect, the system establishes benchmarks or targets for each
selected metric and defines specific quantitative goals for improving each metric
over time.
[0084] In an aspect, upon receiving the request, the system (108) may
20 retrieve the set of subscriber experience indices. The retrieval process may involve
accessing one or more databases or data sources that store precomputed or real-time
data related to subscriber experience. The system (108) may also retrieve RAN logs,
which may contain valuable information about the performance of the network at
the radio access level. RAN logs may include various attributes such as timestamps,
25 unique identifiers of subscribers, base station identifiers, event types, signal
strengths, and quality metrics.
[0085] To derive meaningful insights from the RAN logs and subscriber
experience indices, the system (108) may use an Artificial Intelligence (AI) engine
(216). The AI engine (216) refers to a platform that utilizes various algorithms,
30 techniques, and data to simulate human intelligence and perform tasks traditionally
30
requiring human cognition. The AI engine (216) is designed to analyze large
volumes of data, make decisions, learn from patterns, and adapt to changing
circumstances without explicit programming for each scenario. They typically
incorporate machine learning models, natural language processing (NLP),
computer vision, and other AI techniques to achieve tasks such 5 as data analysis,
pattern recognition, automation, and decision-making. The AI engine (216) may be
configured to compute the one or more correlation values between the attributes of
the RAN logs and the subscriber experience indices. Correlation values may
indicate the strength and direction of the relationship between the attributes and the
10 indices, helping to identify which network factors significantly impact subscriber
experience.
[0086] After computing the correlation values, the system (108) may
transmit the set of subscriber experience indices and the correlation values to the
monitoring unit (114). The monitoring unit (114) may be a centralized entity
15 responsible for overseeing the performance of the cellular network and making
data-driven decisions to optimize network operations. By receiving the subscriber
experience indices and correlation values, the monitoring unit (114) may gain
valuable insights into the current state of the network and identify areas that require
attention or improvement.
20 [0087] In one embodiment, the process of retrieving the set of subscriber
experience indices may involve several steps. The system (108) may include a
request processing engine (212) that determines whether the requested set of
subscriber experience indices is available in a first database (210-1). The first
database (210-1) may be a dedicated storage that contains precomputed subscriber
25 experience indices, which may be regularly updated based on historical data or realtime
network measurements.
[0088] If the requested set of subscriber experience indices is available in
the first database (210-1), the request processing engine (212) may retrieve the
precomputed indices directly from the database. This approach may be efficient and
31
time-saving, as it eliminates the need for real-time computation of the indices.
However, if the requested set of indices is not available in the first database (210-
1), the system (108) may use a computation engine (214) to calculate the indices on
demand.
[0089] The computation engine (214) may derive the 5 requested set of
subscriber experience indices when they are not readily available in the first
database (210-1). The computation engine (214) may retrieve the set of RAN logs
from the second database (210-2) to perform this computation. The second database
(210-2) may be a separate storage entity that specifically stores RAN logs collected
10 from various elements of the cellular network, such as base stations, radio network
controllers, or other network nodes.
[0090] Once the relevant RAN logs are retrieved from the second database
(210-2), the computation engine (214) may process and analyze the logs to derive
the requested set of subscriber experience indices. This derivation process may
15 involve extracting relevant information from the RAN logs, such as radio frequency
(RF) data, and applying various algorithms or models to calculate the indices. The
specific algorithms or models used may depend on the nature of the subscriber
experience indices being computed and the available data in the RAN logs.
[0091] After the computation engine (214) derives the requested set of
20 subscriber experience indices, the system (108) may store the computed indices in
the first database (210-1) for future retrieval. This storage mechanism may optimize
the system's performance by allowing quick access to previously computed indices,
reducing the need for redundant computations. The stored indices may be updated
periodically or whenever new data becomes available to ensure the accuracy and
25 relevance of the information.
[0092] The RAN logs used by the system (108) may contain various
attributes that provide valuable information about the performance of the cellular
network. These attributes may include timestamps, which indicate the specific time
at which certain events or measurements occurred. Timestamps may be crucial for
32
understanding the temporal dynamics of network performance and identifying
patterns or trends over time.
[0093] Another important attribute of the RAN logs may be the unique
identifier of the subscriber. This identifier may be used to track the experience of
individual subscribers as they interact with the network. By analyzing 5 subscriberspecific
data, the system (108) may identify any issues or anomalies that affect
particular users and take targeted actions to resolve them.
[0094] The RAN logs may also include base station identifiers, which
specify the specific base station or cell site associated with each log entry. This
10 information may be valuable for understanding the geographic distribution of
network performance and identifying any location-specific issues. By correlating
subscriber experience indices with base station identifiers, the system (108) may
pinpoint areas of the network that require optimization or capacity enhancements.
[0095] Event types may be another crucial attribute captured in the RAN
15 logs. These event types may indicate specific occurrences or conditions in the
network, such as call drops, handover failures, or quality of service degradations.
The system (108) may identify the most common or impactful issues affecting
subscriber experience by analyzing the frequency and distribution of different event
types.
20 [0096] Signal strength and quality metrics may also be included in the RAN
logs. These metrics may provide information about the strength and quality of the
radio signals received by subscribers' devices. Poor signal strength or quality may
lead to dropped calls, slow data speeds, or other issues that negatively impact
subscriber experience. By monitoring these metrics, the system (108) may identify
25 areas of the network that require coverage optimization or interference mitigation.
[0097] The AI engine (216) may compute the correlation values between
the attributes of the RAN logs and the subscriber experience indices. By leveraging
advanced machine learning algorithms and statistical techniques, the AI engine
33
(216) may identify patterns, anomalies, and insights that may not be apparent
through manual analysis.
[0098] One of the key functions of the AI engine (216) may be to identify
network issues based on the computed correlation values. By examining the
strength and direction of the correlations, the AI engine (216) may 5 determine which
attributes of the RAN logs have the most significant impact on subscriber
experience indices. This analysis may reveal specific network issues, such as
congested cells, faulty equipment, or suboptimal network configurations.
[0099] In addition to identifying network issues, the AI engine (216) may
10 also generate one or more recommendations for resolving the identified issues.
These one or more recommendations may be based on best practices, historical data,
or machine learning models that predict the most effective actions to improve
subscriber experience. For example, the AI engine (216) may suggest network
parameter optimizations, capacity expansions, or maintenance activities to address
15 the identified issues.
[00100] Once the AI engine (216) generates one or more recommendations,
the system (108) may transmit these recommendations to the monitoring unit (114).
The monitoring unit (114) may then review the recommendations and take
appropriate actions to resolve the identified network issues. This may involve
20 coordinating with network operations teams, dispatching field technicians, or
making configuration changes to network elements.
[00101] By implementing the recommendations generated by the AI engine
(216), the system (108) may proactively address network issues and improve
subscriber experience. This proactive approach may help prevent or mitigate
25 service disruptions, reduce customer complaints, and enhance overall network
performance. The system (108) may continuously monitor the impact of the
implemented recommendations and adjust its strategies based on the observed
results.
34
[00102] The set of subscriber experience indices monitored by the system
(108) may include various metrics that provide a comprehensive view of the quality
of experience for subscribers. One such metric may be the happiness score, which
may be a composite indicator that quantifies the overall satisfaction of subscribers
with the network services. The happiness score may consider 5 factors such as
network availability, call quality, data speeds, and customer support interactions.
The happiness score metric is used to quantify and evaluate the subjective wellbeing
or satisfaction levels of individuals or groups. It typically involves asking
respondents to rate their happiness or satisfaction on a numerical scale or through
10 qualitative feedback. For example, in a customer satisfaction survey, a
telecommunications company might ask subscribers to rate their overall happiness
with the service received on a scale from 1 to 10. Another important subscriber
experience indices may be the top call release reasons. This metric may identify the
most frequent causes of call drops or disconnections, such as network congestion,
15 coverage issues, or equipment failures. “Top call release reasons” are the primary
reasons or causes for calls being disconnected or released by a telecommunications
network or customer service center. These reasons are identified through analysis
of call logs and may include technical issues, customer actions, or network-related
problems. For example, the common top call release reasons could include network
20 congestion, dropped calls due to poor signal strength, customer hang-ups, or issues
with billing inquiries. By analyzing the top call release reasons, the system (108)
may prioritize network improvements and troubleshooting efforts to address the
most prevalent issues affecting subscriber experience.
[00103] The “volume of services” used by subscribers may also be a relevant
25 subscriber experience index. This metric may track the usage patterns of various
network services, such as voice calls, text messages, and data consumption. The
system (108) may identify trends, preferences, and potential capacity constraints by
monitoring service usage. This information may help network operators optimize
their service offerings and ensure adequate resources are available to meet
30 subscriber demands. The volume of services used may be defined as an amount or
35
extent of services consumed or utilized by subscribers within a specified timeframe.
This metric can encompass various services offered by a provider, such as data
usage, voice calls, text messages, or additional features like streaming
subscriptions. In an example, a mobile service provider measures the volume of
services used by each subscriber monthly, including data usage 5 in gigabytes,
minutes of voice calls, and number of text messages sent.
[00104] The time spent by subscribers using different services may be
another important subscriber experience index. This metric may provide insights
into the engagement and satisfaction of subscribers with specific network services.
10 For example, if subscribers spend a significant amount of time using data services,
it may indicate a high level of satisfaction with the network's data performance.
Conversely, if subscribers frequently experience long call setup times or interrupted
sessions, it may suggest issues with network reliability or capacity. Time spent by
subscribers using services may be defined as a duration or amount of time that
15 subscribers engage with or utilize services provided by a company. This can include
time spent actively using digital services, watching content, or interacting with
customer support. In an example, a streaming platform tracks the average time
subscribers spend watching videos or accessing content daily to gauge engagement
levels and user behaviour patterns.
20 [00105] The subscriber journey with base stations may also be a valuable
subscriber experience index. This metric may track the movement and interactions
of subscribers across different base stations or cell sites. By analyzing subscriber
journeys, the system (108) may identify coverage gaps, handover issues, or other
network anomalies that impact subscriber experience. This information may help
25 network operators optimize cell site placements, adjust network parameters, and
ensure seamless connectivity for subscribers as they move within the network.
Subscriber Journey with Base Stations may be defined as a path or sequence of
interactions and connectivity experiences that subscribers undergo when
connecting to and utilizing base stations within a telecommunications network. It
30 includes aspects such as signal strength, handoff between base stations, and overall
36
network performance. In an example, a mobile network operator maps the
subscriber journey with base stations to analyze coverage gaps, optimize network
efficiency, and improve service reliability for seamless connectivity across different
geographical areas.
[00106] To facilitate the analysis and interpretation of subscriber 5 experience
indices, the monitoring unit (114) may provide a user interface that displays the
received indices in a clear and intuitive manner. This user interface may include
various visualizations, such as charts, graphs, and heatmaps, to help network
operators quickly identify trends, patterns, and anomalies in the data.
10 [00107] In addition to displaying the subscriber experience indices, the
monitoring unit (114) may also provide an interactive interface for users to analyze
and visualize the data. This interactive interface may allow users to drill down into
specific metrics, filter the data based on various criteria, and perform comparative
analyses across different time periods or geographic regions. The monitoring unit
15 (114) may empower network operators to gain deeper insights into subscriber
experience and make data-driven decisions to optimize network performance by
providing these interactive capabilities. Providing the interactive interface for users
to analyze and visualize the set of determined subscriber experience indices
involves creating a user-friendly platform that allows stakeholders to explore and
20 derive insights from the data. To provide the interactive interface, the system may
be configured to integrate the determined set of subscriber experience indices into
a centralized data repository. The system may be configured to provide the userfriendly
interface for data visualization and interactivity. In an example, the userfriendly
interface is configured to provide:
25  various types of visualizations such as line charts, bar charts, heatmaps,
scatter plots, and geographical maps.
 Allow users to filter data based on different criteria (e.g., time period,
geographic region, customer segment) and drill down into specific
details.
37
 Incorporate interactive elements (such as selection tools) for exploring
data points in detail.
 Offer customization options for users to adjust visualizations according
to their preferences and specific analytical needs.
[00108] Overall, the system (108) for monitoring the subscriber 5 experience
indices may provide a comprehensive and proactive approach to ensuring highquality
network services for subscribers. By leveraging the power of AI and data
analytics, the system (108) may identify network issues, generate actionable
recommendations, and enable network operators to make informed decisions to
10 enhance subscriber experience. The system's ability to process and analyze vast
amounts of RAN logs and correlate them with subscriber experience indices may
provide a deep understanding of the factors influencing network performance and
subscriber satisfaction.
[00109] The potential benefits of the system (108) are numerous. By
15 proactively monitoring and addressing network issues, the system (108) may help
reduce the frequency and duration of service disruptions, leading to improved
network reliability and availability. This, in turn, may result in higher subscriber
satisfaction, reduced churn rates, and increased customer loyalty.
[00110] Moreover, the insights provided by the system (108) may enable
20 network operators to optimize their network investments and resource allocation.
By identifying the most critical areas for improvement and prioritizing network
upgrades or expansions based on subscriber experience indices, operators may
achieve a higher return on investment and maximize the impact of their network
enhancements.
25 [00111] FIG. 3 illustrates an exemplary implementation (300) of the system
(108) for monitoring the subscriber experience indices, in accordance with
embodiments of the present disclosure. The implementation (300) may involve
various components of the system (108), such as the monitoring unit (114), the first
38
database (210-1), the second database (210-2), the request processing engine (212),
the computation engine (214), and the AI engine (216), working together to provide
a comprehensive solution for monitoring and analyzing subscriber experience
indices.
[00112] In one embodiment, the user (102) or an operator 5 of the network
(106) may initiate the process by using the monitoring unit (114) to transmit the
request for determining the set of subscriber experience indices for one or more
subscribers (at step 302). Upon receiving the request, the system (108) may first
check whether the precomputed set of subscriber experience indices is already
10 available in the first database (210-1) (at step 304). If the requested indices are
found in the first database (210-1), the system (108) may retrieve them and transmit
them directly to the monitoring unit (114), thereby providing a quick response to
the user's request (at step 312).
[00113] However, if the requested subscriber experience indices are not
15 available in the first database (210-1), the system (108) may invoke the computation
engine (214) to calculate the indices in real time (at step 306). The computation
engine (214) may be a separate component external to the system (108), as shown
in FIG. 3, or it may be integrated within the one or more processors (202) of the
system (108), as depicted in FIG. 2. Regardless of its location, the computation
20 engine (214) may play a crucial role in deriving the subscriber experience indices
when they are not readily available in the first database (210-1).
[00114] To compute the subscriber experience indices, the computation
engine (214) may retrieve the set of RAN logs from the second database (210-2) (at
step 308). The second database (210-2) may serve as the repository for storing RAN
25 logs, which contain valuable information about the performance and behaviour of
the radio access network. These RAN logs may include various attributes such as
timestamps, unique identifiers of subscribers, base station identifiers, event types,
signal strengths, and quality metrics. The computation engine (214) may derive
meaningful insights into the subscriber experience by analyzing these attributes.
39
[00115] In some embodiments, the computation engine (214) may leverage
the capabilities of the AI engine (216) to determine the subscriber experience
indices based on the RAN logs. The AI engine (216) may employ advanced
machine learning algorithms and statistical techniques to extract relevant patterns
and correlations from the RAN data. By applying sophisticated 5 data analytics and
AI models, the AI engine (216) may accurately infer the subscriber experience
indices, considering multiple factors and their complex interactions.
[00116] The AI engine (216) may utilize various machine learning and deep
learning techniques to compute correlation values between the attributes of the
10 RAN logs and the subscriber experience indices. The AI engine (216) may employ
machine learning models such as linear regression, decision trees, random forests,
or support vector machines to establish relationships between the input features
(RAN log attributes) and the output variable (subscriber experience indices).
Additionally, deep learning architectures such as feedforward neural networks,
15 convolutional neural networks (CNNs), or recurrent neural networks (RNNs) may
be used to capture complex patterns and dependencies in the RAN log data. The AI
engine (216) may also involve data preprocessing techniques, including feature
selection, data normalization, and handling of missing or noisy data, to ensure the
quality and relevance of the input data. The training process of the AI models may
20 involve collecting and labelling a dataset of RAN logs and corresponding subscriber
experience indices, using techniques such as cross-validation and evaluation
metrics to assess model performance. Furthermore, the AI engine (216) may
incorporate methods for model interpretation and explainability, such as feature
importance analysis and model visualization, to provide insights into the learned
25 patterns and relationships between the RAN log attributes and the subscriber
experience indices.
[00117] At step (310), the computation engine is configured to transmit the
computed data to the system. Once the computation engine (214) has derived the
requested set of subscriber experience indices, it may transmit them to the
30 monitoring unit (114) for display and further analysis (at step 312). The monitoring
40
unit (114) may provide a user-friendly interface that allows network operators to
visualize the subscriber experience indices in various formats, such as charts,
graphs, and heatmaps. This visual representation may enable operators to quickly
identify trends, anomalies, and areas of concern, facilitating data-driven decisionmaking
and proactive network 5 management.
[00118] In addition to computing the subscriber experience indices, the AI
engine (216) may also be configured to calculate correlation values between the
attributes of the RAN logs and the subscriber experience indices. These correlation
values may indicate the strength and direction of the relationships between specific
10 network parameters and the overall subscriber experience. By examining these
correlations, the system (108) may uncover key factors that have a significant
impact on subscriber satisfaction and network performance.
[00119] The correlation values computed by the AI engine (216) may serve
as valuable inputs for identifying and resolving network issues. The system (108)
15 may continuously monitor the subscriber experience indices and compare them
against predefined thresholds or ranges. If the indices fall outside the acceptable
range, it may trigger an alert to the network operators, prompting them to
investigate and address the underlying issues. By proactively detecting and
resolving network problems based on the insights derived from the correlation
20 analysis, the system (108) may help maintain a high level of subscriber satisfaction
and prevent potential service disruptions.
[00120] To further enhance the efficiency and responsiveness of the system
(108), the computed set of subscriber experience indices may be stored in the first
database (210-1) for future retrieval. This caching mechanism may allow the system
25 (108) to quickly serve subsequent requests for the same indices without the need
for redundant computations. The system (108) may optimize its performance and
reduce the response time for user queries by maintaining a repository of
precomputed indices.
41
[00121] FIG. 4 illustrates an exemplary flowchart of a method (400) for
monitoring subscriber experience indices, in accordance with embodiments of the
present disclosure. The method (400) may encompass various steps and procedures
that enable the system (108) to effectively monitor and analyze subscriber
experience indices, leveraging the capabilities of its components such 5 as the request
processing engine (212), the computation engine (214), and the AI engine (216).
[00122] The method (400) may commence with the step of receiving (402) a
request for determining the set of subscriber experience indices for one or more
subscribers from the monitoring unit (114). This request may be initiated by the
10 user (102) or the operator of the network (106) who seeks to gain insights into the
quality of experience perceived by the subscribers. The request may specify the
particular subscribers or groups of subscribers for whom the experience indices are
to be determined.
[00123] Upon receiving the request, the method (400) may proceed to
15 retrieve the requested set of subscriber experience indices. The retrieval process
may involve a determination (404) by the request processing engine (212) regarding
the availability of the requested indices in the first database (210-1). The first
database (210-1) may serve as the repository for storing precomputed subscriber
experience indices, which can be readily accessed and returned to the monitoring
20 unit (114) if available. In an example, the first database (210-1) and the second
database may be a MySQL Database, or a MongoDB. MySQL is a widely used
open-source relational database management system (RDBMS). It can store
structured data efficiently and support fast retrieval of precomputed subscriber
experience indices. The MongoDB is a popular NoSQL database known for its
25 flexibility and scalability. It is suitable for storing semi-structured or unstructured
data, which can include subscriber experience indices in various formats.
[00124] If the requested set of subscriber experience indices is found in the
first database (210-1), the method (400) may proceed to retrieve the precomputed
indices and transmit them to the monitoring unit (114). This approach may provide
42
a quick and efficient response to the user's request, as the indices are already
calculated and stored in the database. By leveraging precomputed indices, the
system (108) may reduce the computation overhead and improve the
responsiveness of the monitoring process.
[00125] However, if the requested set of subscriber experience 5 indices is not
available in the first database (210-1), the method (400) may invoke the
computation engine (214) to calculate the indices in real-time. The computation
engine (214) may be responsible for deriving the subscriber experience indices
based on the available data and the specific requirements of the request. This
10 computation step (406) may involve various algorithms, models, and techniques to
process the relevant data and generate meaningful insights into the subscriber
experience.
[00126] To compute the requested set of subscriber experience indices, the
computation engine (214) may retrieve the set of RAN logs from the second
15 database (210-2). The second database (210-2) may serve as the repository for
storing RAN logs, which capture detailed information about the performance and
behaviour of the radio access network. These RAN logs may contain a wide range
of attributes, such as timestamps, unique identifiers of subscribers, base station
identifiers, event types, signal strengths, and quality metrics.
20 [00127] The computation engine (214) may analyze the retrieved RAN logs
and derive the requested set of subscriber experience indices based on the radio
frequency (RF) data contained within the logs. This derivation process may involve
extracting relevant features, applying statistical methods, and utilizing machine
learning algorithms to identify patterns and correlations that indicate the quality of
25 the subscriber experience. By examining the RF data, the computation engine (214)
may gain valuable insights into factors such as network coverage, signal quality,
and service availability, which directly impact the subscriber experience.
[00128] Once the computation engine (214) has derived the requested set of
subscriber experience indices, the method (400) may proceed to store (408) the
43
computed indices in the first database (210-1) for future retrieval. This storage step
may optimize the efficiency of the system (108) by allowing subsequent requests
for the same indices to be served from the database without the need for redundant
computations. By maintaining a cache of precomputed indices, the system (108)
may improve its responsiveness and reduce the latency in providing 5 results to the
monitoring unit (114).
[00129] In addition to computing the subscriber experience indices, the
method (400) may involve the use of the Artificial Intelligence (AI) engine (216)
to calculate correlation values between the attributes of the RAN logs and the
10 subscriber experience indices. This computation step (410) may leverage machine
learning techniques and statistical analysis to uncover meaningful relationships and
dependencies between specific network parameters and the overall subscriber
experience.
[00130] The AI engine (216) may examine the RAN logs and the derived
15 subscriber experience indices to identify patterns and correlations that provide
insights into the factors influencing the quality of experience. For example, the AI
engine (216) may discover that certain signal strength thresholds or network
congestion levels have a significant impact on subscriber satisfaction. By
calculating these correlation values, the AI engine (216) may help network
20 operators understand the key drivers of subscriber experience and prioritize their
efforts accordingly.
[00131] The correlation values computed by the AI engine (216) may be
utilized to identify potential network issues and generate recommendations for
resolving them. By analyzing the correlations, the system (108) may detect
25 anomalies, performance degradations, or other problems that negatively impact the
subscriber experience. The AI engine (216) may employ predictive models and
intelligent algorithms to suggest appropriate actions or interventions that can
address the identified issues and improve the overall network quality.
44
[00132] Once the subscriber experience indices and the correlation values
have been computed, the method (400) may proceed to transmit (414) these results
to the monitoring unit (114). The monitoring unit (114) may serve as the interface
between the system (108) and the users (102) or network operators. It may provide
a user-friendly dashboard or visualization tools that allow the users 5 to explore and
analyze the subscriber experience indices and the associated correlation values.
[00133] The transmitted results may be displayed on the user interface of the
monitoring unit (114) in various formats, such as charts, graphs, heat maps, or
tabular representations. These visualizations may help users quickly identify trends,
10 patterns, and areas of concern within the subscriber experience data. The
monitoring unit (114) may also provide interactive features that allow users to drill
down into specific metrics, filter the data based on various criteria, and perform
comparative analyses across different time periods or geographic regions.
[00134] In addition to displaying the subscriber experience indices, the
15 monitoring unit (114) may present the generated recommendations for resolving
network issues. These recommendations may be based on the correlation values and
the insights derived from the AI engine (216). By providing actionable suggestions,
the monitoring unit (114) may assist network operators in making informed
decisions and taking proactive measures to enhance the subscriber experience.
20 [00135] The method (400) may further include the step of resolving (412) the
identified network issues based on the generated recommendations. Network
operators may review the recommendations provided by the system (108) and take
appropriate actions to address the underlying problems. This may involve
optimizing network parameters, reallocating resources, upgrading infrastructure, or
25 implementing targeted solutions to improve the quality of service delivered to
subscribers.
[00136] By continuously monitoring the subscriber experience indices and
taking prompt actions based on the insights and recommendations provided by the
system (108), network operators may proactively manage the network and ensure a
45
high level of subscriber satisfaction. The method (400) may enable operators to
identify and resolve issues before they escalate into major problems, thereby
reducing the impact on subscribers and minimizing service disruptions.
[00137] The set of subscriber experience indices monitored by the system
(108) may encompass a wide range of metrics that provide a 5 comprehensive view
of the subscriber experience. These indices may include but are not limited to, a
happiness score, top call release reasons, volume of services used, time spent by
subscribers using services, and subscriber journey with base stations. Each of these
indices may offer unique insights into different aspects of the subscriber experience,
10 allowing network operators to gain a holistic understanding of the quality of service
provided.
[00138] The happiness score may serve as an overall indicator of subscriber
satisfaction, considering various factors such as network performance, service
reliability, and customer support. By tracking the happiness score over time,
15 network operators may gauge the general sentiment of subscribers and identify
trends or fluctuations that warrant attention. A declining happiness score may signal
the need for proactive measures to address underlying issues and improve the
subscriber experience.
[00139] The top call release reasons may provide valuable information about
20 the most common causes of call drops or disconnections experienced by
subscribers. By analyzing these reasons, network operators may identify specific
network issues or areas of weakness that require focus and optimization. For
example, if a high percentage of call releases are attributed to poor signal quality or
network congestion, operators may take steps to enhance coverage, upgrade
25 infrastructure, or optimize resource allocation in affected areas.
[00140] The volume of services used by subscribers may offer insights into
the usage patterns and preferences of different subscriber segments. By monitoring
the usage of various services, such as voice calls, data services, and value-added
offerings, network operators may gain a better understanding of the demand and
46
popularity of specific services. This information may guide marketing strategies,
service provisioning, and capacity planning to ensure that the network is equipped
to meet the evolving needs of subscribers.
[00141] The time spent by subscribers using different services may provide
an indication of the engagement and satisfaction levels associated 5 with each service.
By analyzing the duration and frequency of service usage, network operators may
identify services that are highly valued by subscribers and allocate resources
accordingly. Conversely, services with low usage or short engagement times may
require further investigation to understand the reasons behind their lack of
10 popularity and take corrective measures.
[00142] The subscriber journey with base stations may offer valuable
insights into the mobility patterns and network performance experienced by
subscribers as they move across different geographic areas. By tracking the
handover processes, signal strengths, and quality metrics associated with different
15 base stations, network operators may identify coverage gaps, capacity constraints,
or other issues that impact the seamless connectivity and quality of service. This
information may guide network planning, optimization, and expansion strategies to
ensure a consistent and reliable subscriber experience across the network.
[00143] The method (400) may also involve providing an interactive
20 interface within the monitoring unit (114) to enable users to analyze and visualize
the subscriber experience indices. This interface may offer advanced features such
as data exploration, filtering, and drill-down capabilities, allowing users to delve
deeper into specific metrics, time periods, or subscriber segments. By providing
intuitive and user-friendly tools for data analysis, the monitoring unit (114) may
25 empower network operators to derive actionable insights and make data-driven
decisions to enhance the subscriber experience.
[00144] The method (400) may enable network operators to proactively
monitor and manage the subscriber experience, taking timely actions to address
problems and optimize network performance. By providing a data-driven approach
47
to understanding the factors influencing subscriber satisfaction, the method (400)
may help operators prioritize their efforts, allocate resources efficiently, and deliver
a superior quality of service to their customers.
[00145] By continuously monitoring subscriber experience indices, network
operators may gain real-time visibility into the performance of 5 their network and
the satisfaction levels of their subscribers. This proactive monitoring approach may
allow operators to detect and resolve issues promptly, minimizing the impact on
subscribers and preventing potential churn.
[00146] Moreover, the method (400) may provide valuable insights into the
10 key drivers of subscriber experience, enabling operators to focus their efforts on the
areas that matter most to their customers. By analyzing the correlation values
between network attributes and subscriber experience indices, operators may
identify the critical factors that influence subscriber satisfaction and take targeted
actions to optimize those aspects of the network.
15 [00147] The AI-powered analysis and recommendation capabilities of the
method (400) may further enhance the efficiency and effectiveness of network
management. By leveraging advanced machine learning algorithms and intelligent
automation, the system (108) may provide accurate and timely recommendations
for resolving network issues, reducing the reliance on manual troubleshooting and
20 enabling operators to take proactive measures to prevent future problems.
[00148] Furthermore, the interactive interface provided by the monitoring
unit (114) may empower network operators with the tools and insights they need to
make informed decisions and drive continuous improvement. By providing a userfriendly
platform for data exploration and visualization, the method (400) may
25 facilitate collaboration, knowledge sharing, and data-driven decision-making
across different teams and departments within the organization.
[00149] FIG. 5 illustrates an exemplary computer system (500) in which or
with which embodiments of the present disclosure may be implemented. As shown
48
in FIG. 5, the computer system (500) may include an external storage device (510),
a bus (520), a main memory (530), a read only memory (540), a mass storage device
(550), a communication port (560), and a processor (570). A person skilled in the
art will appreciate that the computer system (500) may include more than one
processor (570) and communication ports (560). Processor 5 (570) may include
various modules associated with embodiments of the present disclosure.
[00150] In an embodiment, the communication port (560) may be any of an
RS-232 port for use with a modem-based dialup connection, a 10/100 Ethernet port,
a Gigabit or 10 Gigabit port using copper or fiber, a serial port, a parallel port, or
10 other existing or future ports. The communication port (560) may be chosen
depending on a network, such a Local Area Network (LAN), Wide Area Network
(WAN), or any network to which the computer system (500) connects.
[00151] In an embodiment, the memory (530) may be Random Access
Memory (RAM), or any other dynamic storage device commonly known in the art.
15 Read-only memory (540) may be any static storage device(s) e.g., but not limited
to, a Programmable Read Only Memory (PROM) chips for storing static
information e.g., start-up or Basic Input/Output System (BIOS) instructions for the
processor (570).
[00152] In an embodiment, the mass storage (550) may be any current or
20 future mass storage solution, which may be used to store information and/or
instructions. Exemplary mass storage solutions include, but are not limited to,
Parallel Advanced Technology Attachment (PATA) or Serial Advanced
Technology Attachment (SATA) hard disk drives or solid-state drives (internal or
external, e.g., having Universal Serial Bus (USB) and/or Firewire interfaces), one
25 or more optical discs, Redundant Array of Independent Disks (RAID) storage, e.g.,
an array of disks (e.g., SATA arrays).
[00153] In an embodiment, the bus (520) communicatively couples the
processor(s) (570) with the other memory, storage and communication blocks. The
bus (520) may be, e.g., a Peripheral Component Interconnect (PCI)/PCI Extended
49
(PCI-X) bus, Small Computer System Interface (SCSI), Universal Serial Bus (USB)
or the like, for connecting expansion cards, drives and other subsystems as well as
other buses, such a front side bus (FSB), which connects the processor (570) to the
computer system (500).
[00154] Optionally, operator and administrative interfaces, 5 e.g., a display,
keyboard, joystick, and a cursor control device, may also be coupled to the bus
(520) to support direct operator interaction with the computer system (500). Other
operator and administrative interfaces may be provided through network
connections connected through the communication port (560). Components
10 described above are meant only to exemplify various possibilities. In no way should
the aforementioned exemplary computer system (500) limit the scope of the present
disclosure.
[00155] The method and system of the present disclosure may be
implemented in a number of ways. For example, the methods and systems of the
15 present disclosure may be implemented by software, hardware, firmware, or any
combination of software, hardware, and firmware. The above-described order for
the steps of the method is for illustration only, and the steps of the method of the
present disclosure are not limited to the order specifically described above unless
specifically stated otherwise. Further, in some embodiments, the present disclosure
20 may also be embodied as programs recorded in a recording medium, the programs
including machine-readable instructions for implementing the methods according
to the present disclosure. Thus, the present disclosure also covers a recording
medium storing a program for executing the method according to the present
disclosure. The programs for executing the method according to the present
25 disclosure can be recorded on various types of recording media, including, but not
limited to, magnetic storage media (e.g., hard disks, floppy disks, magnetic tapes),
optical storage media (e.g., CD-ROMs, DVDs, Blu-ray discs), solid-state storage
media (e.g., USB flash drives, SD cards, solid-state drives), and any other nontransitory
computer-readable storage media. These recording media can store the
30 programs in the form of machine-readable instructions, which can be executed by
50
a computer or other processing device to implement the methods described in the
present disclosure.
[00156] FIG. 6 illustrates another exemplary flowchart of the method (600)
for monitoring subscriber experience indices, in accordance with embodiments of
the present 5 disclosure.
[00157] Step (602) involves receiving the request from the monitoring unit
to determine the set of subscriber experience indices for one or more subscribers.
In an example, the received request may be a query request (requesting specific
information or metrics about subscriber experience), an analysis request (asking for
10 an analysis of current subscriber experience indices), a report request (requesting a
report on the latest subscriber experience metrics), a comparison request (requesting
a comparison of subscriber experience indices over different time periods or
between different subscriber groups), or a trend analysis request (requesting an
analysis of trends in subscriber experience metrics).
15 [00158] In an aspect, step (602) involves processing, which typically
includes gathering, processing, and analyzing relevant data to generate meaningful
metrics that reflect the quality of service and customer satisfaction.
[00159] Step (604) involves retrieving radio access network (RAN) logs
from a secondary database. In an example, the RAN logs contain various attributes
20 that are crucial for understanding and analyzing the performance of the radio access
network within a telecommunications system. At step (604), the system initiates a
query to the secondary database where RAN logs are stored. This database typically
stores detailed operational data from the network elements involved in radio access,
such as base stations (NodeBs, eNodeBs in LTE/4G, gNodeBs in 5G), antennas,
25 and related equipment. The system processes the retrieved RAN logs, potentially
aggregating, filtering, or analyzing them to extract relevant insights and prepare
them for further analysis.
51
[00160] At step (606), the method involves using the Artificial Intelligence
(AI) engine to compute one or more correlation values between the attributes of the
RAN logs and the set of subscriber experience indices. The AI engine is employed
to analyze the relationship between the attributes of the RAN logs and the
subscriber experience indices. In an example, the AI engine 5 is configured to:
 Identify which attributes of the RAN logs are most relevant or influential in
predicting or explaining variations in the subscriber experience indices.
 Compute correlation values (e.g., Pearson correlation coefficient, Spearman's
rank correlation) between pairs of attributes from RAN logs and subscriber
10 indices. These correlation values quantify the strength and direction of
relationships.
 Employ machine learning techniques to discover patterns, dependencies, or
causal relationships between RAN attributes and subscriber indices. This may
include regression models, classification models, or clustering algorithms,
15 depending on the nature of the analysis.
[00161] At step (608), the system is configured to determine the set of
subscriber experience indices by using the one or more computed correlation values
obtained from the previous step (606). Based on the computed correlation values,
the system sets thresholds or criteria to determine which RAN attributes
20 significantly impact subscriber experience indices. The system is configured to
identify correlation values that exceed predefined thresholds, indicating a
meaningful relationship (e.g., correlation coefficient above a certain value). The
system is configured to consider both positive and negative correlations to
understand how variations in RAN performance affect subscriber behaviours or
25 perceptions. Using the established thresholds or criteria, the system determines a
subset of RAN attributes that most strongly correlate with the set of subscriber
experience indices.
52
[00162] At step (610), the system transmits the set of determined subscriber
experience indices and the one or more computed correlation values to the
monitoring unit. The transmission may occur in real-time or at scheduled intervals,
depending on the monitoring unit's requirements and capabilities. Real-time
updates allow for immediate monitoring and responsiveness to 5 changing network
conditions or subscriber feedback. Upon receiving the transmitted data, the
monitoring unit displays the subscriber experience indices and correlation values in
the user-friendly interface.
[00163] The present disclosure discloses a user equipment that is
10 communicatively coupled to a system through a network. The user equipment is
configured to monitor subscriber experience indices. The user equipment a memory
and one or more processors coupled with the memory. The one or more processors
are configured to execute instructions stored in the memory to perform steps of a
method for monitoring subscriber experience indices. The method includes
15 receiving, from the monitoring unit, the request to determine the set of subscriber
experience indices of one or more subscribers. The method includes retrieving radio
access network (RAN) logs from a second database, the RAN logs comprising one
or more attributes. The method includes computing, using the Artificial Intelligence
(AI) engine, one or more correlation values between the one or more attributes of
20 the RAN logs and the set of subscriber experience indices. The method includes
determining the set of subscriber experience indices by using the one or more
computed correlation values. The method includes transmitting the set of
determined subscriber experience indices and the one or more computed correlation
values to the monitoring unit.
25 [00164] The present disclosure introduces a significant technological
advancement by consolidating subscriber experience metrics into a single
dashboard. The present disclosure addresses existing limitations in analyzing
subscriber experience and happiness scores within telecommunications services.
Previously, end-users lacked the flexibility to readily assess subscriber experiences
30 and happiness indices, only being able to extract subscriber-level data through
53
specific UI queries. One potential advantage of the present system and method is
the ability to derive actionable insights from subscriber usage data and RAN logs,
empowering network operators with a comprehensive view of subscriber
experience. This may facilitate proactive management and enhancement of network
services, ultimately leading to improved subscriber satisfaction 5 in the dynamic
telecommunications landscape.
[00165] While considerable emphasis has been placed herein on the preferred
embodiments, it will be appreciated that many embodiments can be made and that
many changes can be made in the preferred embodiments without departing from
10 the principles of the disclosure. These and other changes in the preferred
embodiments of the disclosure will be apparent to those skilled in the art from the
disclosure herein, whereby it is to be distinctly understood that the foregoing
descriptive matter to be implemented merely as illustrative of the disclosure and not
as limitation.
15 ADVANTAGES OF THE PRESENT DISCLOSURE
[00166] The present disclosure provides a system and a method for
monitoring subscriber experience indices.
[00167] The present disclosure provides a dashboard that displays a plurality
of metrics used for determining subscriber experience indices such as happiness
20 score, type of failure faced, clear codes count, failed procedure, subscriber journey
with a base station, distribution of call release reasons, distribution of services
consumed, and the like.
[00168] The present disclosure provides a system and a method that
determines subscriber experience indices using Radio Access Network (RAN) logs.
25 [00169] The present disclosure provides a system and a method that allows
operators to identify and troubleshoot network issues if subscriber experience
indices fall outside a predetermined range.
54
[00170] The present disclosure provides a system and a method with a
flexible and interactive interface for visualizing and analyzing subscriber
experience indices.
[00171] The present disclosure is to provide a system and method that
computes correlation values between attributes of Radio Access 5 Network (RAN)
logs and subscriber experience indices. By analyzing these correlation values, the
system may identify network issues impacting subscriber experience and generate
recommendations for resolving them, enabling network operators to proactively
manage and optimize network performance.
10
55
We Claim:
1. A system (108) for monitoring subscriber experience indices, comprising:
a memory (204); and
one or more processors (202) communicatively coupled with the
memory (204), wherein the one or more processors (202) 5 are configured to
execute instructions stored in the memory (204) to:
receive, from a monitoring unit (114), a request for
determining a set of subscriber experience indices of one or more
subscribers;
10 retrieve radio access network (RAN) logs from a second
database, the RAN logs comprising one or more attributes;
compute one or more correlation values between the one or
more attributes of the RAN logs and the set of subscriber experience
indices;
15 determine the set of subscriber experience indices by using
the one or more computed correlation values; and
transmit the set of determined subscriber experience indices
and the one or more computed correlation values to the monitoring
unit (114).
20 2. The system (108) of claim 1, includes a request processing engine (212)
configured to:
determine whether the requested set of subscriber experience indices
is available in a first database (210-1), the first database (210-1) is
configured to store a set of precomputed subscriber experience indices;
56
retrieve the precomputed set of subscriber experience indices from
the first database (210-1) when the requested set of subscriber experience
indices is available; and
compute, by a computation engine (214), the requested set of
subscriber experience indices when the requested 5 set of subscriber
experience indices is not available in the first database (210-1).
3. The system (108) of claim 2, wherein for computing the requested set of
subscriber experience indices, the computation engine (214) is configured
to:
10 retrieve the set of RAN logs from the second database (210-2); and
derive the requested set of subscriber experience indices from radio
frequency (RF) data in the retrieved set of RAN logs.
4. The system (108) of claim 1, wherein the one or more attributes of the RAN
logs include at least one of a timestamp, a unique identifier of the subscriber,
15 a base station identifier, an event type, a signal strength, and quality metrics.
5. The system (108) of claim 1, wherein an Artificial Intelligence (AI) engine
(216) is further configured to:
analyze the one or more computed correlation values to identify one
or more network issues; and
20 generate one or more recommendations for resolving the identified
one or more network issues.
6. The system (108) of claim 5, wherein the one or more processors (202) are
further configured to:
transmit the one or more generated recommendations to the
25 monitoring unit (114); and
57
resolve the identified one or more network issues based on generated
one or more recommendations.
7. The system (108) of claim 1, wherein the set of subscriber experience
indices includes at least one of a happiness score, top call release reasons,
volume of services used, time spent by subscribers using 5 services, and
subscriber journey with base stations.
8. The system (108) of claim 1, wherein the monitoring unit (114) is
configured to:
display the received set of subscriber experience indices on a user
10 interface; and
provide an interactive interface for users to analyze and visualize the
set of determined subscriber experience indices.
9. A method (600) for monitoring subscriber experience indices, the method
comprising:
15 receiving (602), from a monitoring unit (114), a request for
determining a set of subscriber experience indices of one or more
subscribers;
retrieving (604) radio access network (RAN) logs from a second
database, the RAN logs comprising one or more attributes;
20 computing (606), using one or more processors (202), one or more
correlation values between the one or more attributes of the RAN logs and
the set of subscriber experience indices;
determining (608) the set of subscriber experience indices by using
the one or more computed correlation values; and
58
transmitting (610) the set of determined subscriber experience
indices and the one or more computed correlation values to the monitoring
unit (114).
10. The method (600) of claim 9, further comprising retrieving the set of
subscriber experience indices including 5 steps of:
determining, by a request processing engine (212), whether the
requested set of subscriber experience indices is available in a first database
(210-1), the first database (210-1) is configured to store a set of
precomputed subscriber experience indices;
10 retrieving the precomputed set of subscriber experience indices from
the first database (210-1) when the requested set of subscriber experience
indices is available; and
computing, by a computation engine (214), the requested set of
subscriber experience indices when the requested set of subscriber
15 experience indices is not available in the first database (210-1).
11. The method (600) of claim 9, wherein computing the requested set of
subscriber experience indices by the computation engine (214) further
comprises:
retrieving a set of RAN logs from a second database (210-2); and
20 deriving the requested set of subscriber experience indices from
radio frequency (RF) data in the retrieved set of RAN logs.
12. The method (600) of claim 9, wherein the one or more attributes of the RAN
logs include at least one of a timestamp, a unique identifier of the subscriber,
a base station identifier, an event type, a signal strength, and quality metrics.
25 13. The method (600) of claim 9, further comprising:
59
analyzing the one or more computed correlation values to identify
one or more network issues; and
generating recommendations for resolving the identified one or
more network issues.
14. The method 5 (600) of claim 13, further comprising:
transmitting the one or more generated recommendations to the
monitoring unit (114); and
resolving the identified one or more network issues based on
generated recommendations.
10 15. The method (600) of claim 9, wherein the set of subscriber experience
indices includes at least one of a happiness score, top call release reasons,
volume of services used, time spent by subscribers using services, and
subscriber journey with base stations.
16. The method (600) of claim 9, further comprising:
15 displaying the received set of subscriber experience indices on a user
interface of the monitoring unit (114); and
providing an interactive interface for users to analyze and visualize
the set of determined subscriber experience indices.
17. A user equipment (104) communicatively coupled to a system (108) through
20 a network (106), wherein the system (108) for monitoring subscriber
experience indices, comprising:
a memory; and
one or more processors coupled with the memory, wherein the one
or more processors are configured to execute instructions stored in the
25 memory to perform steps of a method (400) as claimed in claim 9.
Dated this 08 day of July 2024
~Digitally signed~
Anandan S
REG.NO:IN/PA-1717
of De Penning & De Penning
Agent for the Applicants
60
ABSTRACT
SYSTEM AND METHOD FOR MONITORING SUBSCRIBER
EXPERIENCE INDICES
The present disclosure relates to a system (108) for monitoring subscriber
experience indices in a cellular network. The system 5 (108) may comprise a memory
(204) and one or more processors (202) communicatively coupled with the memory
(204). The one or more processors (202) may be configured to receive, from a
monitoring unit (114), a request for determining a set of subscriber experience
indices of one or more subscribers. The one or more processors (202) may retrieve
10 the set of subscriber experience indices and radio access network (RAN) logs
comprising one or more attributes. An Artificial Intelligence (AI) engine (216) may
compute correlation values between the one or more attributes of the RAN logs and
the set of subscriber experience indices. The one or more processors (202) may
transmit the set of subscriber experience indices and the correlation values to the
15 monitoring unit (114) for further analysis and visualization.