FORM 2
THE PATENTS ACT, 1970
(39 OF 1970)
&
THE PATENT RULES, 2003
COMPLETE SPECIFICATION
(See section 10 and rule 13)
“METHOD AND SYSTEM FOR IDENTIFYING NETWORK
ANOMALIES”
We, Jio Platforms Limited, an Indian National, of Office - 101, Saffron, Nr. Centre Point, Panchwati 5 Rasta, Ambawadi, Ahmedabad - 380006, Gujarat, India.
The following specification particularly describes the invention and the manner in which it is to be performed.

METHOD AND SYSTEM FOR IDENTIFYING NETWORK ANOMALIES
FIELD OF DISCLOSURE
[0001] Embodiments of the present disclosure generally relate to network performance management systems. More particularly, embodiments of the present disclosure relate to identifying network anomalies.
BACKGROUND
[0002] The following description of the 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 present disclosure. However, it should be appreciated that this section is used only to enhance the understanding of the reader with respect to the present disclosure, and not as admissions of the prior art.
[0003] Wireless communication technology has rapidly evolved over the past few decades, with each generation bringing significant improvements and advancements. The first generation of wireless communication technology was based on analog technology and offered only voice services. However, with the advent of the second generation (2G) technology, digital communication and data services became possible, and text messaging was introduced. 3G technology marked the introduction of high-speed internet access, mobile video calling, and location-based services. The fourth generation (4G) technology revolutionized wireless communication with faster data speeds, better network coverage, and improved security. Currently, the fifth generation (5G) technology is being deployed, promising even faster data speeds, low latency, and the ability to connect multiple devices simultaneously. With each generation, wireless communication technology has become more advanced, sophisticated, and capable of delivering more services to its users.

[0004] In telecommunication network, it is extremely important to identify areas where user experience is poor. There may be various reasons for such poor user experience. The signal strength of a wireless network decreases as it travels through various materials such as walls, ceilings, and floors. The signal strength of the wireless network decreases in areas with poor signal coverage or even complete dead zones. Further, the wireless signals may also reflect off surfaces and create multipath interference, which may result in signal distortion, signal cancellation, and reduced coverage. Furthermore, high density environments such as large buildings or crowded public areas can strain network capacity and lead to congestion, resulting in reduced coverage and slower data transfer speeds. It is also possible that limited budget has limited the number of antennae, resulting in areas with poor coverage. Coverage hole planning is done after network roll out based on field inputs i.e. drive test data and customer complaints and/or field optimization. This data for coverage planning is inadequate and often used without checking the consistency of issues. Therefore, it is pertinent to identify areas of poor user experience for pinpointing the issue in that area and taking targeted actions to mitigate poor user experience and improving customer satisfaction.
[0005] Thus, there exists a need in the art of a method and a system for identification of poor user experience polygon on a map, which addresses the above-mentioned problems.
SUMMARY
[0006] This section is provided to introduce certain aspects of the present disclosure in a simplified form that are further described below in the detailed description. This summary is not intended to identify the key features or the scope of the claimed subject matter.

[0007] An aspect of the present disclosure may relate to a method for identifying network anomalies. The method comprises determining, by a processing unit, a health index for each user of a plurality of users in one or more polygons of a wireless network. The method further comprises identifying, by an identification unit, a set of users of the plurality of users. Furthermore, the method comprises aggregating, by an aggregation unit, location-specific ratio signal report (LSR) samples for the identified set of users from a predefined period of time onto one or more grids. Hereinafter, the method comprises applying, by the processing unit, a first trained model to the one or more grids to identify clusters of the one or more grids with high density of the LSR samples. The method further comprises generating, by the processing unit, closed polygons using a second trained model around the identified clusters for visualization and analysis to identify the network anomalies.
[0008] In an exemplary aspect of the present disclosure, the one or more KPIs comprises at least one of a call quality, a signal strength, a data speed, and a reliability factor.
[0009] In an exemplary aspect of the present disclosure, the closed polygons refer to areas or zones within the network where wireless signal strength is weak.
[0010] In an exemplary aspect of the present disclosure, the health index is calculated using one or more key performance indicators (KPIs).
[0011] In an exemplary aspect of the present disclosure, each of the one or more grids has a predefined dimension.
[0012] In an exemplary aspect of the present disclosure, the first trained model corresponds to a density-based clustering algorithm.

[0013] In an exemplary aspect of the present disclosure, the second trained model corresponds to a convex hull algorithm.
[0014] In an exemplary aspect of the present disclosure, the calculation of health index by the processing unit comprises collecting the one or more KPIs for each user of the plurality of users for all call sessions over the predefined period of time. The method further comprises scaling the one or more KPIs on a scale from one to five, with one indicating a worst range of values and five indicating a best range of values, wherein each range of values is given a score. Furthermore, the method comprises calculating an average score for each of the one or more KPIs. The method further comprises calculating the health index for each user of the plurality of users by taking the calculated average score for each of the one or more KPIs and scaling by a factor of twenty.
[0015] In an exemplary aspect of the present disclosure, the method further comprises eliminating, by the processing unit, a subset of grids from the one or more grids that contain noise data before applying the first trained model.
[0016] In an exemplary aspect of the present disclosure, the visualization and analysis of identified clusters, further comprises calculating additional metrics for each of the identified clusters, wherein the additional metrics comprises number of complaints, call drops, call mutes, unique users, and session counts in association with serving cells.
[0017] Another aspect of the present disclosure may relate to a system for identifying network anomalies. The system comprises a processing unit. The processing unit is configured to determine a health index for each user of a plurality of users in one or more polygons of a wireless network. The system further includes an identification unit. The identification unit is configured to identify, a set of users of the plurality of users. The system further comprises an aggregation unit. The aggregation unit is configured to aggregate location-specific radio signal report

(LSR) samples for the identified set of users from a predefined period of time onto
one or more grids. The processing unit is further configured to apply, a first trained
model to the one or more grids to identify clusters of the one or more grids with
high density of the LSR samples. Furthermore, the processing unit is configured to
5 generate closed polygons using a second trained model around the identified
clusters for visualization and analysis.
[0018] Yet another aspect of the present disclosure may relate to a non-transitory computer readable storage medium, storing instructions for identifying network
10 anomalies, the instructions include executable code which, when executed by one
or more units of a system cause a processing unit to determine a health index for each user of a plurality of users in the one or more polygons of the wireless network. The instructions when executed by the system further cause an identification unit to identify, a set of users of the plurality of users. The instructions when executed
15 by the system further cause an aggregation unit to aggregate location-specific radio
signal report (LSR) samples for the identified set of users from a predefined period of time onto one or more grids. The instructions when executed by the system further cause the processing unit to apply, a first trained model to the one or more grids to identify clusters of the one or more grids with high density of the LSR
20 samples. The instructions when executed by the system further cause the processing
unit to generate closed polygons using a second trained model around the identified clusters for visualization and analysis.
OBJECTS OF THE DISCLOSURE
25
[0019] Some of the objects of the present disclosure, which at least one embodiment disclosed herein satisfies are listed herein below.
[0020] It is an object of the present disclosure to provide a system and a method for
30 identification of poor user experience polygons on a map.
6

[0021] It is another object of the present disclosure to provide a solution that actively monitors and tracks problems and allows for timely intervention and prevents the problem from becoming more complex or causing more damage by identifying poor user experience polygons on a map. 5
[0022] It is yet another object of the present disclosure to provide a solution that recognizes recurring problems or patterns and enables development of preventive measures, improved processes and implementation of corrective actions to avoid future occurrence by identifying poor user experience polygons on a map.
10
[0023] It is yet another object of the present disclosure to provide a solution that enables tracking and categorization of problems and enables efficient allocation of resources, focusing on high-priority problems that have the most significant impact on your goals or objectives, by identifying poor user experience polygons on a map.
15
[0024] It is yet another object of the present disclosure to provide a solution enables provides valuable data and metrics for analysis, thereby enabling identification of trends, root causes and underlying systemic issues by identifying poor user experience polygons on a map.
20
DESCRIPTION OF THE DRAWINGS
[0025] The accompanying drawings, which are incorporated herein, and constitute a part of this disclosure, illustrate exemplary embodiments of the disclosed methods
25 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 principles of the present disclosure. Also, the embodiments shown in the figures are not to be construed as limiting the disclosure, but the possible variants of the method and system
30 according to the disclosure are illustrated herein to highlight the advantages of the
disclosure. It will be appreciated by those skilled in the art that disclosure of such
7

drawings includes disclosure of electrical components or circuitry commonly used to implement such components.
[0026] FIG. 1 illustrates an exemplary block diagram representation of 5th
5 generation core (5GC) network architecture, in accordance with exemplary
implementations of the present disclosure.
[0027] FIG. 2 illustrates an exemplary block diagram of a computing device upon
which the features of the present disclosure may be implemented in accordance with
10 exemplary implementations of the present disclosure.
[0028] FIG. 3 illustrates an exemplary block diagram of a system for identifying network anomalies, in accordance with exemplary implementations of the present disclosure. 15
[0029] FIG. 4 illustrates an implementation of the system for identifying network anomalies, in accordance with exemplary implementations of the present disclosure.
20 [0030] FIG. 5 illustrates a method flow diagram for identifying network anomalies,
in accordance with exemplary implementations of the present disclosure.
[0031] FIG. 6, illustrates a method for identifying network anomalies, in accordance with exemplary implementations of the present disclosure. 25
[0032] FIG. 7 illustrates an implementation of the KPIs that may be measured to calculate the health index, in accordance with exemplary implementations of the present disclosure.
30 [0033] The foregoing shall be more apparent from the following more detailed
description of the disclosure.
8

DETAILED DESCRIPTION
[0034] In the following description, for the purposes of explanation, various
specific details are set forth in order to provide a thorough understanding of
5 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 may 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
10 problems discussed above.
[0035] 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
15 the art with an enabling description for implementing an exemplary embodiment.
It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the disclosure as set forth.
20 [0036] 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 specific details. For example, circuits, systems, processes, and other components may be shown as components in block diagram form in order not to obscure the
25 embodiments in unnecessary detail.
[0037] Also, it is noted that individual embodiments may be described as a process
which 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
30 a sequential process, many of the operations may be performed in parallel or
concurrently. In addition, the order of the operations may be re-arranged. A process
9

is terminated when its operations are completed but could have additional steps not included in a figure.
[0038] The word “exemplary” and/or “demonstrative” is used herein to mean
5 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 necessarily to be construed as preferred or advantageous over other aspects or designs, nor is it meant to preclude equivalent exemplary structures and techniques
10 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—in a manner similar to the term “comprising” as an open transition word—without precluding any additional or other elements.
15
[0039] As used herein, a “processing unit” or “processor” or “operating processor” includes one or more processors, wherein processor refers to any logic circuitry for processing instructions. A processor may be a general-purpose processor, a special purpose processor, a conventional processor, a digital signal processor, a plurality
20 of microprocessors, one or more microprocessors in association with a (Digital
Signal Processing) DSP core, a controller, a microcontroller, Application Specific 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
25 the system according to the present disclosure. More specifically, the processor or
processing unit is a hardware processor.
[0040] As used herein, “a user equipment”, “a user device”, “a smart-user-device”,
“a smart-device”, “an electronic device”, “a mobile device”, “a handheld device”,
30 “a wireless communication device”, “a mobile communication device”, “a
communication device” may be any electrical, electronic and/or computing device
10

or equipment, capable of implementing the features of the present disclosure. The
user equipment/device may include, but is not limited to, a mobile phone, smart
phone, laptop, a general-purpose computer, desktop, personal digital assistant,
tablet computer, wearable device or any other computing device which is capable
5 of implementing the features of the present disclosure. Also, the user device may
contain at least one input means configured to receive an input from at least one of a transceiver unit, a processing unit, a storage unit, a detection unit and any other such unit(s) which are required to implement the features of the present disclosure.
10 [0041] As used herein, “storage unit” or “memory unit” refers to a machine or
computer-readable medium including any mechanism for storing information in a form readable by a computer or similar machine. For example, a computer-readable medium includes read-only memory (“ROM”), random access memory (“RAM”), magnetic disk storage media, optical storage media, flash memory devices or other
15 types of machine-accessible storage media. The storage unit stores at least the data
that may be required by one or more units of the system to perform their respective functions.
[0042] As used herein “interface” or “user interface” refers to a shared boundary
20 across which two or more separate components of a system exchange information
or data. The interface may also be referred to a set of rules or protocols that define communication or interaction of one or more modules or one or more units with each other, which also includes the methods, functions, or procedures that may be called. 25
[0043] All modules, units, components used herein, unless explicitly excluded
herein, may be software modules or hardware processors, the processors being a
general-purpose processor, a special purpose processor, a conventional processor,
a digital signal processor (DSP), a plurality of microprocessors, one or more
30 microprocessors in association with a DSP core, a controller, a microcontroller,
11

Application Specific Integrated Circuits (ASIC), Field Programmable Gate Array circuits (FPGA), any other type of integrated circuits, etc.
[0044] As used herein the transceiver unit include at least one receiver and at least
5 one transmitter configured respectively for receiving and transmitting data, signals,
information or a combination thereof between units/components within the system and/or connected with the system.
[0045] As discussed in the background section, the current known solutions have
10 several shortcomings. The present disclosure aims to overcome the problems
mentioned in the background and other existing problems in this field of technology by providing method and system of identifying network anomalies.
[0046] FIG. 1 illustrates an exemplary block diagram representation of 5th
15 generation core (5GC) network architecture [100], in accordance with exemplary
implementations of the present disclosure. As shown in FIG. 1, the 5GC network
architecture [100] includes a user equipment (UE) [102], a radio access network
(RAN) [104], an access and mobility management function (AMF) [106], a Session
Management Function (SMF) [108], a Service Communication Proxy (SCP) [110],
20 an Authentication Server Function (AUSF) [112], a Network Slice Specific
Authentication and Authorization Function (NSSAAF) [114], a Network Slice
Selection Function (NSSF) [116], a Network Exposure Function (NEF) [118], a
Network Repository Function (NRF) [120], a Policy Control Function (PCF) [122],
a Unified Data Management (UDM) [124], an application function (AF) [126], a
25 User Plane Function (UPF) [128], a data network (DN) [130], wherein all the
components are assumed to be connected to each other in a manner as obvious to
the person skilled in the art for implementing features of the present disclosure.
[0047] The Radio Access Network (RAN) [104] is the part of a mobile
30 telecommunications system that connects user equipment (UE) [102] to the core
network (CN) and provides access to different types of networks (e.g., 5G network).
12

It consists of radio base stations and the radio access technologies that enable wireless communication.
[0048] The Access and Mobility Management Function (AMF) [106] is a 5G core
5 network function responsible for managing access and mobility aspects, such as UE
registration, connection, and reachability. It also handles mobility management procedures like handovers and paging.
[0049] The Session Management Function (SMF) [108] is a 5G core network
10 function responsible for managing session-related aspects, such as establishing,
modifying, and releasing sessions. It coordinates with the User Plane Function
(UPF) for data forwarding and handles IP address allocation and QoS enforcement.
[0050] The Service Communication Proxy (SCP) [110] is a network function in the
15 5G core network that facilitates communication between other network functions
by providing a secure and efficient messaging service. It acts as a mediator for service-based interfaces.
[0051] The Authentication Server Function (AUSF) [112] is a network function in
20 the 5G core responsible for authenticating UEs during registration and providing
security services. It generates and verifies authentication vectors and tokens.
[0052] The Network Slice Specific Authentication and Authorization Function
(NSSAAF) [114] is a network function that provides authentication and
25 authorization services specific to network slices. It ensures that UEs can access only
the slices for which they are authorized.
[0053] The Network Slice Selection Function (NSSF) [116] is a network function
responsible for selecting the appropriate network slice for a UE based on factors
30 such as subscription, requested services, and network policies.
13

[0054] The Network Exposure Function (NEF) [118] is a network function that exposes capabilities and services of the 5G network to external applications, enabling integration with third-party services and applications.
5 [0055] The Network Repository Function (NRF) [120] is a network function that
acts as a central repository for information about available network functions and services. It facilitates the discovery and dynamic registration of network functions.
[0056] The Policy Control Function (PCF) [122] is a network function responsible
10 for policy control decisions, such as QoS, charging, and access control, based on
subscriber information and network policies.
[0057] The Unified Data Management (UDM) [124] is a network function that
centralizes the management of subscriber data, including authentication,
15 authorization, and subscription information.
[0058] The Application Function (AF) [126] is a network function that represents external applications interfacing with the 5G core network to access network capabilities and services. 20
[0059] The User Plane Function (UPF) [128] is a network function responsible for handling user data traffic, including packet routing, forwarding, and QoS enforcement.
25 [0060] The Data Network (DN) [130] refers to a network that provides data
services to user equipment (UE) in a telecommunications system. The data services may include but are not limited to Internet services, private data network related services.
30 [0061] FIG. 2 illustrates an exemplary block diagram of a computing device [200]
upon which the features of the present disclosure may be implemented in
14

accordance with exemplary implementation of the present disclosure. In an
implementation, the computing device [200] may also implement a method for
identifying network anomalies, utilising the system. In another implementation, the
computing device [200] itself implements the method for identifying network
5 anomalies, using one or more units configured within the computing device [200],
wherein said one or more units are capable of implementing the features as disclosed in the present disclosure.
[0062] The computing device [200] may include a bus [202] or other
10 communication mechanism for communicating information, and a hardware
processor [204] coupled with bus [202] for processing information. The hardware
processor [204] may be, for example, a general-purpose microprocessor. The
computing device [200] may also include a main memory [206], such as a random-
access memory (RAM), or other dynamic storage device, coupled to the bus [202]
15 for storing information and instructions to be executed by the processor [204]. The
main memory [206] also may be used for storing temporary variables or other
intermediate information during execution of the instructions to be executed by the
processor [204]. Such instructions, when stored in non-transitory storage media
accessible to the processor [204], render the computing device [200] into a special-
20 purpose machine that is customized to perform the operations specified in the
instructions. The computing device [200] further includes a read only memory
(ROM) [208] or other static storage device coupled to the bus [202] for storing static
information and instructions for the processor [204].
25 [0063] A storage device [210], such as a magnetic disk, optical disk, or solid-state
drive is provided and coupled to the bus [202] for storing information and instructions. The computing device [200] may be coupled via the bus [202] to a display [212], such as a cathode ray tube (CRT), Liquid crystal Display (LCD), Light Emitting Diode (LED) display, Organic LED (OLED) display, etc. for
30 displaying information to a computer user. An input device [214], including
alphanumeric and other keys, touch screen input means, etc. may be coupled to the
15

bus [202] for communicating information and command selections to the processor
[204]. Another type of user input device may be a cursor controller [216], such as
a mouse, a trackball, or cursor direction keys, for communicating direction
information and command selections to the processor [204], and for controlling
5 cursor movement on the display [212]. The input device typically has two degrees
of freedom in two axes, a first axis (e.g., x) and a second axis (e.g., y), that allow the device to specify positions in a plane.
[0064] The computing device [200] may implement the techniques described
10 herein using customized hard-wired logic, one or more ASICs or FPGAs, firmware
and/or program logic which in combination with the computing device [200] causes
or programs the computing device [200] to be a special-purpose machine.
According to one implementation, the techniques herein are performed by the
computing device [200] in response to the processor [204] executing one or more
15 sequences of one or more instructions contained in the main memory [206]. Such
instructions may be read into the main memory [206] from another storage medium,
such as the storage device [210]. Execution of the sequences of instructions
contained in the main memory [206] causes the processor [204] to perform the
process steps described herein. In alternative implementations of the present
20 disclosure, hard-wired circuitry may be used in place of or in combination with
software instructions.
[0065] The computing device [200] also may include a communication interface
[218] coupled to the bus [202]. The communication interface [218] provides a two-
25 way data communication coupling to a network link [220] that is connected to a
local network [222]. For example, the communication interface [218] may be an
integrated services digital network (ISDN) card, cable modem, satellite modem, or
a modem to provide a data communication connection to a corresponding type of
telephone line. As another example, the communication interface [218] may be a
30 local area network (LAN) card to provide a data communication connection to a
compatible LAN. Wireless links may also be implemented. In any such
16

implementation, the communication interface [218] sends and receives electrical, electromagnetic or optical signals that carry digital data streams representing various types of information.
5 [0066] The computing device [200] can send messages and receive data, including
program code, through the network(s), the network link [220] and the
communication interface [218]. In the Internet example, a server [230] might
transmit a requested code for an application program through the Internet [228], the
ISP [226], the local network [222], the host [224] and the communication interface
10 [218]. The received code may be executed by the processor [204] as it is received,
and/or stored in the storage device [210], or other non-volatile storage for later execution.
[0067] The present disclosure is implemented by a system [300] (as shown in FIG.
15 3). In an implementation, the system [300] may include the computing device [200]
(as shown in FIG. 2). It is further noted that the computing device [200] is able to perform the steps of a method [400] (as shown in FIG. 4).
[0068] Referring to FIG. 3, an exemplary block diagram of a system [300] for
20 identifying network anomalies, is shown, in accordance with the exemplary
implementations of the present disclosure. The system [300] comprises at least one
processing unit [302], at least one identification unit [304] and at least one
aggregation unit [306]. Also, all of the components/ units of the system [300] are
assumed to be connected to each other unless otherwise indicated below. As shown
25 in the figures all units shown within the system should also be assumed to be
connected to each other. Also, in FIG. 3 only a few units are shown, however, the
system [300] may comprise multiple such units or the system [300] may comprise
any such numbers of said units, as required to implement the features of the present
disclosure. Further, in an implementation, the system [300] may be present in a user
30 device to implement the features of the present disclosure. The system [300] may
be a part of the user device / or may be independent of but in communication with
17

the user device (may also referred herein as a UE). In another implementation, the system [300] may reside in a server or a network entity. In yet another implementation, the system [300] may reside partly in the server/ network entity and partly in the user device. 5
[0069] The system [300] is configured for identifying network anomalies, with the
help of the interconnection between the components/units of the system [300]. In
an implementation of the present disclosure, the network is the 5th generation core
network. The network may be one of a 4th generation network, a 6th generation
10 network, or any other future generations of the network. The network anomalies
may be one of an unauthorised access given to a system [300] to the network, unusual traffic at the network, a sudden change in configuration, and the like.
[0070] The processing unit [302] is configured to determine a health index for each
15 user of a plurality of users in the one or more polygons of the wireless network. In
one example, the health index provides a measure of level of service and satisfaction of experience a user of the network. The one or more polygons of the network refers to a region or a zone of the network. Each user may be one of a network consumer, a system consumer, a network administrator, a system administrator, and the like.
20
[0071] The health index is calculated using one or more key performance indicators (KPIs). The KPIs refers to a measurement to indicate performance of the indicator in the network. For instance, for a network utilization KPI, the measurement of the network utilization may indicate if the network is highly utilized or lower than an
25 average required utilization. In one example, the one or more KPIs to calculate the
health index includes but may not be limited to at least one of a call quality, a signal strength, a data speed, and a reliability factor. The reliability factor is a measure to assess the dependability of the network. The reliability factor indicates the likelihood of the system or network to perform without failure.
30
18

[0072] To calculate the health index, the processing unit [302] is configured to
collect the one or more KPIs for each user of the plurality of users. The KPIs may
be collected for all call sessions over the predefined period. The predefined period
may be defined by the network operator or the system operator. For instance, the
5 predefined period is 120 minutes, the processing unit [302] may collect the one or
more KPIs from the network after every 120 minutes.
[0073] To calculate, the processing unit [302] is further configured to scale the one
or more KPIs on a scale from one to five. In the scale, one indicates a worst range
10 of values and five indicates a best range of values. In one example, the KPI for the
call quality may be scaled as two if the call quality measure is lower than expected, whereas the KPI for the data speed may be scaled as five if it higher than expected.
[0074] Furthermore, the processing unit [302] is configured to calculate an average
15 score for each of the one or more KPIs. Further, the processing unit [302] is
configured to calculate the health index for each user of the plurality of users by
taking the calculated average score for each of the one or more KPIs and scaling by
a factor of twenty. For instance, if the calculated average score for each of the one
or more KPIs is 4, it will be scaled by a factor of 20. The health index will be 80.
20 (4 X 20 = 80) The health index will be in the range of 0-100.
[0075] In one example, based on the calculated health index for each user of the
plurality of users, the identification unit [304] may receive a list of the calculated
health index. The identification unit [304] is configured to identify a set of users of
25 the plurality of users. Each user from the set of users has a health index less than or
equal to bottom ten percentiles from the list.
[0076] The aggregation unit [306] is configured to aggregate location-specific radio
signal report (LSR) samples for the identified set of users for a predefined period
30 of time onto one or more grids. The set of users may be a subset of the total users
in the network, chosen for the purpose of aggregating and analysing location-
19

specific ratio signal (LSR) samples. The set of users may be one or more persons
present at a particular location for the predefined period of time. In one example,
the predefined period may be 7 days. The predefined period may be configured by
the system administrator or the network administrator. Each of the one or more
5 grids has a predefined dimension. The one or more grids to division of a
geographical area into smaller areas. In one example, the predefined dimension of the each of the one or more grids is 10m X 10m.
[0077] The LSR samples refers to a data that provide information about the radio
10 signal strength and quality at the one or more grids. The LSR sample includes but
may not be limited to metrics such as signal strength, signal-to-noise ratio, and other relevant parameters.
[0078] If a subset of grids from the one or more grids includes a noise data, the
15 processing unit [302] is further configured to eliminate the subset of grids from the
one or more grids. The noise data refers to irrelevant data that can interfere with accurate measurement of the cluster data. The subset of grids from the one or more grids may be identified based on the LSR samples aggregated by the aggregation unit [306]. 20
[0079] The processing unit [302] is further configured to apply, a first trained
model to the one or more grids to identify clusters of the one or more grids with
high density of the LSR samples. The first trained model corresponds to a density-
based clustering algorithm. In one example, the first trained model may be a density
25 based spatial clustering of applications with noise (DBSCAN) that operates to
identify clusters in a dataset. The DBSCAN involves calculating a maximum distance between two points of data. Further, including data from the data sets in a cluster based on the maximum distance.
30 [0080] Furthermore, the processing unit [302] is configured to generate closed
polygons using a second trained model around the identified clusters for
20

visualization and analysis. The closed polygons refer to areas or zones within the
network where wireless signal strength is weak. In one example, the second trained
model corresponds to a convex hull algorithm. The convex hull refers to smallest
convex polygon that can be formed covering all the points in the cluster. The convex
5 hull algorithm is run atop these clusters to form closed polygons for better
visualization and analysis of these clusters.
[0081] Based on the formation of closed polygons, the visualization and analysis of identified clusters by the processing unit [302], further includes calculating
10 additional metrics for each of the identified clusters. The additional metrics that
may be calculate includes number of complaints, call drops, call mutes, unique users, and session counts in association with serving cells, and the like. Based on the calculation, the processing unit [302] may develop preventive measures and implement corrective actions to avoid future occurrence of the identified issues.
15
[0082] Referring to FIG. 4, an implementation of the system [400] for identifying network anomalies, in accordance with exemplary implementations of the present disclosure is shown.
20 [0083] The system [400] comprises of a network platform (NP) [402]. The NP
[402] is connected to a fault management (FM) system [404], a master database (MD) system [406], a configuration management (CM) system [408] and a performance management (PM) system [410], wherein all the components are assumed to be connected to each other in a manner as obvious to the person skilled
25 in the art for implementing features of the present disclosure.
[0084] The NP [402] sends and receives data from various servers such as FM server, PM server, CM server and database server and manages various operations of the network. 30
21

[0085] The FM system [404] monitors alarms, failures or other issues that occur in
various other components that are part of a network. In an implementation of the
present disclosure, the network is the 5th generation core network. The FM system
[404] may detect faults in the network by constantly monitoring the network or
5 system for abnormal conditions, errors, or deviations from normal operation. These
anomalies could include hardware failures, software glitches, network congestion, or other issues.
[0086] Based on the detection of the fault, the FM system [404] is configured to
10 isolate the issue to determine its cause and location in the system. To determine the
cause, the FM system [404] is configured to identify the specific device or component that is experiencing the problem.
[0087] The FM system [404] is configured to generate an alarm once a fault is
15 detected and isolated. The FM system [404] generates the alarm to notify a network
or a system administrator about the issue. These alarms can be displayed on management consoles, sent via an email or text message.
[0088] After receiving the alarm, the system or the network administrator use tools
20 and techniques to diagnose the problem. The diagnosis may involve reviewing logs,
conducting tests, and performing other investigative tasks to determine the root cause of the fault.
[0089] After the cause of the fault is identified, the network or system administrator
25 may take steps to resolve it. The steps may involve repairing or replacing faulty
hardware, applying updates, reconfiguring network settings, or taking other corrective actions. Fault Documentation: The fault may be stored in the MD system [406]. The fault may include details of the fault, including a cause of the fault, resolution steps, and preventive measures taken to avoid similar faults in the future. 30
22

[0090] The FM system [404] interacts with the NP [402] via a NP-FM interface. The NP-FM interface provides a communication channel for interaction.
[0091] The MD system [406] refers to a database to store physical all the network
5 data and provides the stored data to other components of the NP [402], as may be
re quired. The MD system [406] interacts with the NP [402] via a NP- MD
interface. The NP-MD interface provides a communication channel for the MD system [406].
10 [0092] The configuration management (CM) system [408] configures all devices
of the network. The CM system [408] maintains a comprehensive database that stores configuration information for all network elements. The network elements whose configuration information may be stored includes routers, switches, base stations, and other components. The CM system [408] contains detailed records of
15 device configurations, network topology, and other pertinent information. The CM
system [408] facilitates controlled and organized change management by providing a centralized platform for tracking, approving, and implementing configuration changes. Further, the CM system [408] keeps an up-to-date inventory of all network assets, including their physical location, serial numbers, firmware versions, and
20 configurations. This inventory management helps operators keep track of network
resources, plan for maintenance, and efficiently allocate resources. The CM system [408] plays a role in provisioning services and resources within the network.
[0093] In case of network issues, the CM system [408] provides a historical record
25 of configurations, making it easier to identify potential causes of problems and
revert to known, stable configurations if needed.
[0094] The CM system [408] interacts with the NP [402] via a NP-CM interface. The NP-CM interface provides a communication channel for the CM system [408]. 30
23

[0095] The performance management (PM) system [410] evaluates and manages
all the key performance indicators that are relevant for functioning of the network
and delivering best user experience. The PM system [410] continuously collects
and stores performance data from various network elements, such as switches,
5 routers, base stations, and transmission equipment. The PM system [410] monitors
parameters like network latency, packet loss, bandwidth utilization, and device health to understand how the network is performing and to identify potential issues.
[0096] Further, the PM system [410] assesses the quality of voice calls, data
10 transfers, video, and the like to measure metrics like call setup time, call drop rates,
data throughput, and the quality of voice and video calls.
[0097] Furthermore, the PM system [410] tracks and manages Key Performance Indicators (KPIs) that reflect the overall health and performance of the telecom
15 network. The PM system [410] detects and diagnoses network faults and
anomalies. Based on the diagnosis, the PM system [410] is configured to perform a root cause analysis. The root cause analysis identifies underlying causes of problems, and the system where the issue is located. The PM system [410] provides solutions for the issues. To provide the solutions, the PM system [410] comprises
20 visualization tools to present performance data in graphical dashboards and reports
to interpret and support decision-making.
[0098] The PM system [410] interacts with the NP [402] via a NP-PM interface. The NP-PM interface refers to a communication channel for the PM system [410].
25
[0099] In order to identify poor user experience polygons on a map, the network platform [402] is configured to determine a user health index, using one or more key performance indicators determined using data from the one or more of FM system [404], the PM system [406], the CM system [408] and the MD system [410]
30 over a predefined period of time, for quantifying experience of each user. The NP
[402] is further configured to identify users with worst experience by comparing
24

user health index of each user with a predefined value. The NP [402] is also
configured to map a location of call summary logs from a predefined number of
previous days of users with worst experience. Further, the NP [402] is configured
to identify clusters of points using the first algorithm. The first algorithm is a
5 density-based clustering algorithm. Furthermore, the NP [402] is configured to
form closed polygons from clusters identified by the density-based clustering
algorithm by the second algorithm. The second algorithm is using the convex hull
algorithm. Finally, the cognitive platform server [104] is configured to extract from
one or more of PM server [106] or FM server [102], number of bad users experience
10 instances and corresponding antenna information.
[0100] In an embodiment, the predefined value used for identifying worst user is determined such that users with worst experience form a bottom 10% percentile users. The predefined period is 7 days.
15
[0101] Referring to FIG. 5, an exemplary method flow diagram [500] for identifying network anomalies, in accordance with exemplary implementations of the present disclosure is shown. In an implementation the method [500] is performed by the system [300]. Further, in an implementation, the system [300]
20 may be present in a server device to implement the features of the present
disclosure. Also, as shown in FIG. 5, the method [500] starts at step [502].
[0102] At step [504], the method comprises determining, by a processing unit [302], a health index for each user of a plurality of users in the one or more polygons
25 of the wireless network. In one example, the health index provides a measure of
level of service and satisfaction of experience a user of the network. The one or more polygons of the network refers to a region or a zone of the network. Each user may be one of a network consumer, a system consumer, a network administrator, a system administrator, and the like.
30
25

[0103] The health index is calculated using one or more key performance indicators
(KPIs). In one example, the one or more KPIs to calculate the health index includes
but may not be limited to at least one of a call quality, a signal strength, a data speed,
and a reliability factor. The reliability factor is a measure to assess the dependability
5 of the network. The reliability factor indicates the likelihood of the system or
network to perform without failure.
[0104] To calculate the health index, the one or more KPIs may be collected by the
processing unit [302] for each user of the plurality of users. The KPIs may be
10 collected for all call sessions over the predefined period. The predefined period may
be defined by the network operator or the system operator. For instance, the predefined period is 120 minutes, the processing unit [302] may collect the one or more KPIs from the network after every 120 minutes.
15 [0105] To calculate, the one or more KPIs may be scaled on a scale from one to
five by the processing unit [302]. In the scale, one indicates a worst range of values and five indicates a best range of values. In one example, the KPI for the call quality may be scaled as two if the call quality measure is lower than expected, whereas the KPI for the data speed may be scaled as five if it higher than expected.
20
[0106] Furthermore, an average score for each of the one or more KPIs may be calculated by the processing unit [302]. Further, the processing unit [302] calculates the health index for each user of the plurality of users by taking the calculated average score for each of the one or more KPIs and scaling by a factor of twenty.
25 For instance, if the calculated average score for each of the one or more KPIs is 3,
it will be scaled by a factor of 20. The health index will be 60. (3 X 20 = 60) The health index will be in the range of 0-100.
[0107] At step [506], the method comprises identifying, by an identification unit
30 [304], a set of users of the plurality of users. In one example, based on the calculated
health index for each user of the plurality of users, the identification unit [304] may
26

receive a list of the calculated health index. A set of users of the plurality of users may be identified by the identification unit [304] from the list. Each user from the set of users has a health index less than or equal to bottom ten percentiles from the list. 5
[0108] At step [508], the method comprises aggregating, by an aggregation unit [306], location-specific ratio signal report (LSR) samples for the identified set of users from a predefined period onto one or more grids. In one example, the predefined period may be 7 days. The predefined period may be configured by the
10 system administrator or the network administrator. Each of the one or more grids
has a predefined dimension. The one or more grids to division of a geographical area into smaller areas. In one example, the predefined dimension of the each of the one or more grids is 15m X 15m. The LSR sample includes but may not be limited to metrics such as signal strength, signal-to-noise ratio, and other relevant
15 parameters.
[0109] If a subset of grids from the one or more grids include a noise data, the
subset of grids comprising the noise data may be eliminated from the one or more
grids by the processing unit [302]. The noise data refers to irrelevant data points
20 that can interfere with accurate measurement of the radio signal quality. The subset
of grids from the one or more grids may be identified based on the LSR samples aggregated by the aggregation unit [306].
[0110] At step [510], the method comprises applying, by the processing unit [302],
25 a first trained model to the one or more grids to identify clusters of the one or more
grids with high density of the LSR samples. The first trained model corresponds to a density-based clustering algorithm.
[0111] At step [512], the method comprises generating, by the processing unit
30 [302], closed polygons using a second trained model around the identified clusters
for visualization and analysis to identify the network anomalies. The closed
27

polygons refer to areas or zones within the network where wireless signal strength is weak. The second trained model corresponds to a convex hull algorithm.
[0112] Based on the formation of closed polygons, the visualization and analysis
5 of identified clusters by the processing unit [302], further includes calculating
additional metrics for each of the identified clusters. The additional metrics that
may be calculate includes number of complaints, call drops, call mutes, unique
users, and session counts in association with serving cells, and the like. Based on
the calculation, the processing unit [302] may develop preventive measures and
10 implement corrective actions to avoid future occurrence of the identified issues.
[0113] The method terminates at step [514].
[0114] Referring to FIG. 6, an implementation of a method [600] for identifying
15 network anomalies, in accordance with exemplary implementations of the present
disclosure is shown.
[0115] At step [602], the health index is determined for each user of the plurality of users in the one or more polygons of the wireless network. The health index is
20 calculated using one or more key performance indicators (KPIs). For instance, for
a network utilization KPI, the measurement of the network utilization may indicate if the network is highly utilized, or the network utilization is lower than an average required utilization. In one example, the one or more KPIs to calculate the health index includes but may not be limited to at least one of a call quality, a signal
25 strength, a data speed, and a reliability factor.
[0116] The calculation of the health index is performed by collecting the one or
more KPIs for each user of the plurality of users. The KPIs may be collected for all
call sessions over the predefined period. The predefined period may be defined by
30 the network administrator or the system administrator. For instance, the predefined
28

period is 120 minutes, the KPI may be collect the from the network after every 120 minutes.
[0117] Further, at step [604], the LSR samples are aggregated for the identified set
5 of users for the predefined period onto one or more grids. In one example, the
predefined period is 7 days. The predefined period may be configured by the system administrator or the network administrator. Each of the one or more grids has a predefined dimension. In one example, the predefined dimension of the each of the one or more grids is 10m X 10m.
10
[0118] Furthermore, at step [606], if the subset of grids from the one or more grids includes the noise data, the method [600] includes eliminating the subset of grids from the one or more grids. The subset of grids from the one or more grids may be identified based on the LSR samples aggregated by the aggregation unit [306].
15
[0119] Furthermore, at step [608], the first trained model is applied to the one or more grids to identify clusters with high density of the LSR samples. The first trained model corresponds to a density-based clustering algorithm. In one example, the first trained model is a density based spatial clustering of applications with noise
20 (DBSCAN).
[0120] Furthermore, at step [610], once the clusters with high density of the LSR
samples are identified, the second trained model is configured to be applied to the
identified clusters. The convex hull refers to smallest convex polygon that can be
25 formed covering all the points in the cluster. The convex hull algorithm is run atop
these clusters to form closed polygons for better visualization and analysis of these clusters. The visualization and analysis include but may not be limited to calculating total number of complaints, call drops, call mutes, unique users and session counts.
30 [0121] Referring to FIG. 7, an implementation of the KPIs [700] that may be
measured to calculate a health index [714] is shown, in accordance with exemplary
29

implementations of the present disclosure. The health index [714] is same as explained above.
[0122] In an exemplary embodiment, for each call session, measured KPIs includes
5 but not limited to a Reference Signal Received Power (RSRP) [702], a Reference
Signal Received Quality (RSRQ) [704], a Signal-to-Noise Ratio (SINR) [706], a Channel Quality Indicator (CQI) [708], an Internet Protocol (IP) throughput [710] and mutes and drops [712].
10 [0123] The RSRP [702] is a measure of the power level of reference signals
transmitted by a base station as received by a user equipment (UE). The base station may be the gNB if the network is the 5th GC network. The RSRP [702] is used to assess the signal strength and coverage of a cellular network.
15 [0124] The RSRQ [704] is a metric that provides information about quality of
received reference signals relative to interference and noise level. The RSRQ [704] is calculated as ratio of RSRP to a Received Signal Strength Indicator (RSSI).
[0125] The SINR [706] measures a ratio of power of a specific signal to sum of the
20 power of interference signals and background noise. The SINR [706] evaluates
quality of a wireless communication link.
[0126] The CQI [708] metric to indicate quality of the communication channel. The
CQI [708] may be based on factors including signal strength, interference, noise,
25 and the like. Also, the IP throughput [710] refers to rate at which data packets are
successfully delivered over an IP network.
[0127] The mutes and drops [712]- Mutes refer to periods when audio signal is
temporarily lost or silenced during a call due to network issues, signal interference,
30 or other factors affecting the transmission quality and drops refers to instances
where a call or data session is unexpectedly terminated.
30

[0128] The measured KPIs are compressed into a single quantitative indicator of a
user’s overall experience – the user’s health index [714]. In an exemplary
embodiment, the health index [714] is calculated over a given hour and the health
5 index [714] may be compressed to indicate user’s overall experience for that given
hour. Likewise, the health data may be calculated for a given day by compressing the health index [714] of every hour.
[0129] Each of the KPI is scaled on a scale of 1 to 5. The KPI may be scaled at 1 if
10 the measure is worse than expected and 5 being the best possible range of values
that KPI can take.
[0130] The average scores for each KPI, for all sessions in the defined duration are
calculated. Further, the health index [714] is calculated by taking an average score
15 of each KPI and scaled by a factor of 20. The resultant health index [714] is in the
range of 0 – 100.
[0131] The present disclosure further discloses a non-transitory computer readable storage medium, storing instructions for identifying network anomalies, the
20 instructions include executable code which, when executed by one or more units of
a system, cause a processing unit [302] to determine a health index for each user of a plurality of users in the one or more polygons of the wireless network. The instructions when executed by the system further cause an identification unit [304] to identify, a set of users of the plurality of users. The instructions when executed
25 by the system further cause an aggregation unit [306] to aggregate location-specific
radio signal report (LSR) samples for the identified set of users from a predefined period of time onto one or more grids. The instructions when executed by the system further cause the processing unit [302] to apply, a first trained model to the one or more grids to identify clusters of the one or more grids with high density of
30 the LSR samples. The instructions when executed by the system further cause the
31

processing unit [302] to generate closed polygons using a second trained model around the identified clusters for visualization and analysis.
[0132] As is evident from the above, the present disclosure provides a technically
5 advanced solution for identifying network anomalies. The present disclosure is
implemented in the 5G network, but may further be implemented in a 6th generation network or any other future generations of network. The present solution provides early detection by actively monitoring and tracking problems to allow for timely intervention and prevention of the problem from becoming more complex. The
10 present solution further provides proactive problem-solving by recognizing
recurring problems or patterns and implement corrective actions to avoid future occurrences. The present solution further provides continuous improvement by reviewing and analyzing problem data over time to identify trends and root causes and make informed decisions and implement improvements to enhance
15 performance, productivity, and quality.
[0133] While considerable emphasis has been placed herein on the disclosed
implementations, it will be appreciated that many implementations can be made and
that many changes can be made to the implementations without departing from the
20 principles of the present disclosure. These and other changes in the implementations
of the present disclosure will be apparent to those skilled in the art, whereby it is to be understood that the foregoing descriptive matter to be implemented is illustrative and non-limiting.
25 [0134] Further, in accordance with the present disclosure, it is to be acknowledged
that the functionality described for the various components/units can be implemented interchangeably. While specific embodiments may disclose a particular functionality of these units for clarity, it is recognized that various configurations and combinations thereof are within the scope of the disclosure. The
30 functionality of specific units as disclosed in the disclosure should not be construed
as limiting the scope of the present disclosure. Consequently, alternative
32

arrangements and substitutions of units, provided they achieve the intended functionality described herein, are considered to be encompassed within the scope of the present disclosure.

We Claim:
1. A method for identifying network anomalies, the method comprising:
determining, by a processing unit [302], a health index for each user of a plurality of users in one or more polygons of a wireless network;
identifying, by an identification unit [304], a set of users of the plurality of users;
aggregating, by an aggregation unit [306], location-specific ratio signal report (LSR) samples for the identified set of users from a predefined period of time onto one or more grids;
applying, by the processing unit [302], a first trained model to the one or more grids to identify clusters of the one or more grids with high density of the LSR samples; and
generating, by the processing unit [302], closed polygons using a second trained model around the identified clusters for visualization and analysis to identify the network anomalies.
2. The method as claimed in claim 1, wherein the closed polygons refer to areas or zones within the network where wireless signal strength is weak.
3. The method as claimed in claim 1, wherein the health index is calculated using one or more key performance indicators (KPIs).
4. The method as claimed in claim 3, wherein the one or more KPIs comprises at least one of a call quality, a signal strength, a data speed, and a reliability factor.
5. The method as claimed in claim 1, wherein each of the one or more grids has a predefined dimension.
6. The method as claimed in claim 1, wherein the first trained model corresponds to a density-based clustering algorithm.

7. The method as claimed in claim 1, wherein the second trained model corresponds to a convex hull algorithm.
8. The method as claimed in claim 1, wherein calculation of the health index by the processing unit [302] comprises:
collecting the one or more KPIs for each user of the plurality of users for all call sessions over the predefined period of time;
scaling the one or more KPIs on a scale from one to five, with one indicating a worst range of values and five indicating a best range of values, wherein each range of values is given a score;
calculating an average score for each of the one or more KPIs; and
calculating the health index for each user of the plurality of users by taking the calculated average score for each of the one or more KPIs and scaling by a factor of twenty.
9. The method as claimed in claim 1, further comprising eliminating, by the processing unit [302], a subset of grids from the one or more grids that contain noise data before applying the first trained model.
10. The method, as claimed in claim 1, wherein visualization and analysis of identified clusters, further comprises calculating additional metrics for each of the identified clusters, wherein the additional metrics comprises number of complaints, call drops, call mutes, unique users, and session counts in association with serving cells.
11. A system for identifying network anomalies, the system comprising:
- a processing unit [302], configured to:
determine a health index for each user of a plurality of users in one or more polygons of a wireless network; - an identification unit [304], configured to:
identify, a set of users of the plurality of users;

- an aggregation unit [306], configured to:
aggregate location-specific radio signal report (LSR) samples for the identified set of users from a predefined period of time onto one or more grids;
- the processing unit [302] further configured to:
apply, a first trained model to the one or more grids to identify clusters of the one or more grids with high density of the LSR samples; and
generate closed polygons using a second trained model around the identified clusters for visualization and analysis.
12. The system as claimed in claim 11, wherein the closed polygons refer to areas or zones within the network where wireless signal strength is weak.
13. The system as claimed in claim 11, wherein the health index is calculated using one or more key performance indicators (KPIs).
14. The system as claimed in claim 13, wherein the one or more KPIs comprises at least one of a call quality, a signal strength, a data speed, and a reliability factor.
15. The system as claimed in claim 11, wherein each of the one or more grids has a predefined dimension.
16. The system as claimed in claim 11, wherein the first trained model corresponds to a density-based clustering algorithm.
17. The system as claimed in claim 11, wherein the second trained model corresponds to a convex hull algorithm.
18. The system as claimed in claim 11, wherein to calculate the health index, the processing unit [302] is configured to:
collect the one or more KPIs for each user of the plurality of users for all call sessions over the predefined period of time;

scale the one or more KPIs on a scale from one to five, with one indicating a worst range of values and five indicating a best range of values, wherein each range of values is given a score;
calculate an average score for each of the one or more KPIs; and
calculating the health index for each user of the plurality of users by taking the calculated average score for each of the one or more KPIs and scaling by a factor of twenty.
19. The system as claimed in claim 11, wherein the processing unit [302] is further configured to eliminate a subset of grids from the one or more grids, wherein the subset of grids contains noise data, wherein the elimination of the subset of grids takes place before applying the first trained model.
20. The system, as claimed in claim 11, wherein visualization and analysis of identified clusters by the processing unit [302], further comprises calculating additional metrics for each of the identified clusters, wherein the additional metrics comprises number of complaints, call drops, call mutes, unique users, and session counts in association with serving cells.