FORM 2
THE PATENTS ACT, 1970
THE PATENTS RULES, 2003
COMPLETE SPECIFICATION
NETWORK
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

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, belong¬ing to Jio Platforms Limited (JPL) 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 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 method for opti-mizing minutes of usage in a wireless network.
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 ‘Call detail records (CDR)’ used hereinafter in the specification refers to information on calls made on telephone systems, including who made the call (name and number), who was called (name if available, and number), the date and time the call was made, the duration of the call, and typically dozens of usages and diagnos¬tic information elements. The CDR includes, but is not limited to, call duration, fre¬quency, user location, minutes of usage, etc., from each cell site.

[0005] “MOU” refers to minutes of usage of a subscriber on call per day. It may also refer to average communication time per one month per one user.
[0006] “Network usage” refers to the amount of data sent back and forth across your network due to applications, servers, devices, and network users.
[0007] “Normalization” refers to a process of organizing data in a database. It includes creating tables and establishing relationships between those tables according to rules designed both to protect the data and to make the database more flexible by eliminating redundancy and inconsistent dependency.
[0008] “Call patterns” refers to parameters such as user relationships, average call du-ration, call frequency and the rate of unsuccessful calls.
[0009] “User characteristics” refers to but not limited to user profile, demographic information, or geographic information, usage of network services by a user.
[0010] “Call duration threshold limit” refers to a call duration limit set by a network operator in minutes or hours after usage, of which the user is not allowed to user the network services for a specific duration of time.
[0011] These definitions are in addition to those expressed in the art.
BACKGROUND OF DISCLOSURE
[0012] The following description of related art is intended to provide background in-formation 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. How¬ever, it should be appreciated that this section be used only to enhance the understand¬ing of the reader with respect to the present disclosure, and not as admissions of prior art.

[0013] Generally, minutes of usage (MOU) refers to minutes of usage of a subscriber on a call per day. The MOU may be a total time measured in minutes used to compute billing and/or statistics for telephone calls or another network use. Generally, some of the subscribers make calls for more than 10 hours a day, and this may even extend to 24 hours a day. When provided with unlimited data and voice services, the users most often allegedly misuse the feature and start to make calls for more than 10 hours a day and or even 24 hours a day. This problem was identified by the applicant after thorough analysis of the call record data of each subscriber. However, there is no known tech¬nique for optimizing MOU in wireless networks.
[0014] There is, therefore, a need in the art to provide a method and a system that can overcome the shortcomings of the existing prior arts.
SUMMARY
[0015] In an exemplary embodiment, a method optimizing minutes of usage in a wire-less network is described. The method includes collecting, by a data collection engine, call detail record (CDR) data associated with network usage from each cell site in the wireless network. The method also includes normalizing and pre-processing, by a com¬putation engine, the collected CDR data for feature extraction and analysis. The method further includes extracting, one or more relevant features from the normalized and pre-processed data to capture one or more call patterns and one or more user char-acteristics. The method further includes analyzing by an analysis module, the one or more call patterns and one or more user characteristics (such as call characteristics and one or more network usage patterns) from the collected data and the extracted features. The method further includes sending, by the ML engine, a notification alert in real¬time to a network operations team upon a call duration exceeding a call duration thresh¬old limit, to take an action such as curating an interim call cut policy.

[0016] In some embodiments, the method further includes training the one or more ML models using the collected data and one or more extracted features to learn the call characteristics and the network usage patterns.
[0017] In some embodiments, analyzing the call characteristics and network usage pat-5 terns includes analyzing one or more ongoing calls and predicting longer than usual call duration leading to excessive minutes of usage (MOU). In aspects, CDR data in¬cludes historical data covering the CDR data over a period of time, and wherein the analysis module is configured to analyze the historical data to identify the one or more call patterns and one or more user characteristics. The method further includes applying 10 a MOU usage mitigation policy, upon the call duration exceeding a call duration thresh¬old limit, for controlling the MOU. The MOU usage mitigation policy comprises ter¬mination of the call when the call duration exceeds the call duration threshold limits.
[0018] In another exemplary embodiment, a system for optimizing minutes of usage in a wireless network is described. The system includes a memory configured to store
15 one or more computer-readable instructions or routines in a non-transitory computer-readable storage medium, fetched and executed to create or share data packets over a network service. The system also includes a processor configured to fetch and execute computer-readable instructions stored in the memory. The system further includes an interface configured to provide a communication pathway for one or more components
20 of the system. The system further includes a data collection engine configured for col-lecting, call detail record (CDR) data associated with network usage from each cell site in the wireless network. A computation engine normalizes and pre-processes, the col¬lected CDR data for feature extraction and analysis. The computation engine further extracts one or more relevant features from the normalized and pre-processed data to
25 capture one or more call patterns and user characteristics (such as one or more call characteristics and network usage patterns). The system further includes an analysis module for analyzing one or more call characteristics and network usage patterns from
5

the collected data and the one or more extracted relevant features. A notification alert is sent in real-time to a network operations team upon a call duration exceeding a call duration threshold limit, to curate an interim call cut policy.
[0019] In some embodiments, the analysis module is further configured to analyze one 5 or more ongoing calls and predicting longer than usual call duration leading to exces¬sive minutes of usage (MOU).
[0020] In yet another exemplary embodiment, a user equipment (UE) configured for optimizing minutes of usage in a wireless network is described. The user equipment includes a processor and a computer readable storage medium storing programming for
10 execution by the processor. The programming includes instructions to collect, call de¬tail record (CDR) data associated with network usage from each cell site in the wireless network, normalize and pre-process the collected CDR data for feature extraction and analysis, extract one or more relevant features from the normalized and pre-processed data to capture one or more call patterns and one or more user characteristics, analyze
15 call characteristics and one or more network usage patterns from the collected data and the extracted features and send a notification alert in real-time to a network operations team upon a call duration exceeding a call duration threshold limit, to curate an interim call cut policy.
[0021] In yet another exemplary embodiment, a computer program product comprising 20 a non-transitory computer-readable medium is described. The non-transitory com-puter-readable medium comprises instructions that, when executed by one or more pro-cessors, cause the one or more processors to perform a method. The method includes collecting, by a data collection engine, call detail record (CDR) data associated with network usage from each cell site in the wireless network. The method also includes 25 normalizing and pre-processing, by the processing engine, the collected CDR data for feature extraction and analysis. The method further includes extracting, one or more relevant features from the normalized and pre-processed data to capture one or more
6

call patterns and one or more user characteristics. The method further includes analyz¬ing by an analysis module, call characteristics and one or more network usage patterns from the collected data and the extracted features The method further includes sending, by the ML engine, a notification alert in real-time to a network operations team upon a 5 call duration exceeding a call duration threshold limit, to curate an interim call cut pol¬icy.
[0022] The foregoing general description of the illustrative embodiments and the fol-lowing detailed description thereof are merely exemplary aspects of the teachings of this disclosure and are not restrictive.
10 OBJECTS OF THE PRESENT DISCLOSURE
[0023] Some of the objects of the present disclosure, which at least one embodiment herein satisfies are as listed herein below.
[0024] An object of the present disclosure is to provide a system and a method for monitoring call detail records.
15 [0025] An object of the present disclosure is to provide a system and a method to detect alleged misuse of network services in advance by analyzing customer behaviour data using optimized Artificial Intelligence/Machine Learning (AI/ML) techniques.
[0026] An object of the present disclosure is to provide a system and a method that uses AI and ML techniques to constantly monitor real time MOU patterns of all the 20 users, thereby predicting and curbing any further misuse of the network services.
[0027] An object of the present disclosure is to provide a system and a method that ensures fair utilization of network services among all the users, thereby building an optimized network for better customer experience, and enhancing revenue optimiza-tion.
7

[0028] An object of the present disclosure is to provide a system and a method that prevents revenue loss of a service provider by detecting the alleged misuse of the net-work services in advance.
BRIEF DESCRIPTION OF DRAWINGS
5 [0029] The accompanying drawings, which are incorporated 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 differ¬ent drawings. Components in the drawings are not necessarily to scale, emphasis in¬stead being placed upon clearly illustrating the principles of the present disclosure. 10 Some drawings may indicate the components using block diagrams and may not rep¬resent 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 compo¬nents, electronic components or circuitry commonly used to implement such compo¬nents.
15 [0030] FIG. 1 illustrates an exemplary network architecture for implementing a system for optimizing minutes of usage in a wireless network, in accordance with an embodiment of the present disclosure.
[0031] FIG. 2 illustrates an exemplary block diagram of the system for optimizing minutes of usage in a wireless network, in accordance with an embodiment of the 20 present disclosure.
[0032] FIG. 3 illustrates an exemplary architecture of the system for optimizing minutes of usage in a wireless network, in accordance with an embodiment of the present disclosure.
[0033] FIG. 4 illustrates an exemplary process flow for implementing a method of 25 optimizing minutes of usage in a wireless network, in accordance with an embodiment
8

of the present disclosure.
[0034] FIG. 5 illustrates an exemplary flow diagram for implementing a method of optimizing minutes of usage in a wireless network, in accordance with an embodiment of the present disclosure.
5 [0035] FIG. 6 illustrates an exemplary computer system in which or with which the embodiments of the present disclosure may be implemented.
[0036] The foregoing shall be more apparent from the following more detailed description of the disclosure.
IST OF REFERENCE NUMERALS 10 100 – Network architecture
102-1, 102-2…102-N – Users
104-1, 104-2…104-N – User equipment
106 - Network
108 - System 15 202 – Processor
204 – Memory
206 – Interface
208 – Processing Engine
210 – Database
20 212 – Data Collection Engine
9

214 – ML Engine
216 – Other Engines
218 - Computation Engine
300 -Implementation of the system 5 400 - Method
500 - Method
600 - Computer system
610 - External storage device
620 - Bus 10 630 - Main memory
640 - Read only memory
650 - Mass Storage Device
660 - Communication Port
670 - Computer System Processor
15 DETAILED DESCRIPTION OF THE DISLCOSURE
[0037] In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of 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 20 hereafter can each be used independently of one another or with any combination of
10

other features. An individual feature may not address all of the problems discussed above or might address only some of the problems discussed above. Some of the prob¬lems discussed above might not be fully addressed by any of the features described herein.
5 [0038] The ensuing description provides exemplary embodiments only, and is not in-tended 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 function and arrangement of ele-10 ments without departing from the spirit and scope of the disclosure as set forth.
[0039] 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, networks, processes, and other components may be 15 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 the embodiments.
[0040] Also, it is noted that individual embodiments may be described as a process 20 which is depicted as a flowchart, a flow diagram, a data flow diagram, a structure dia¬gram, or a block diagram. Although a flowchart may describe the operations as a se¬quential process, many of the operations can be performed in 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 25 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 corre¬spond to a return of the function to the calling function or the main function.
11

[0041] 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 de¬scribed herein as “exemplary” and/or “demonstrative” is not necessarily to be con-5 strued 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 in a manner similar to the term “comprising” as an 10 open transition word without precluding any additional or other elements.
[0042] Reference throughout this specification to “one embodiment” or “an embodi¬ment” or “an instance” or “one instance” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, the appearances of the phrases “in one 15 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 more embodiments.
[0043] The terminology used herein is for the purpose of describing particular embod-20 iments only and is not intended to be limiting of the disclosure. As used herein, the singular forms “a,” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises” and/or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, 25 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 all combinations of one or more of the associated listed items.
12

[0044] The aspects of the present disclosure are directed to a method and system for optimizing minutes of usage in a wireless network.
[0045] The system of the present disclosure collects call detail record (CDR) which includes, but not limited to, call duration, frequency, user location, minutes of usage, 5 etc. from each cell site. The system of the present disclosure normalizes and pre-pro¬cesses the collected data for feature extraction and further analysis. The system of the present disclosure extracts relevant features from the pre-processed data to capture call patterns and user characteristics. The collected data and the extracted features are fed to suitable ML models. The ML model may be trained using the collected data and the
10 extracted features to learn the call characteristics and the network usage patterns. The trained ML model may analyze the ongoing calls and predict longer than usual call duration leading to excessive minutes of usage (MOU). The system of the present dis-closure sends an immediate notification alert to the network operations team who then ensures that the call duration goes more than the call duration threshold limit and curate
15 an interim call cut policy, when the call duration goes more than the call duration threshold limit.
[0046] The various embodiments throughout the disclosure will be explained in more detail with reference to FIGs. 1-6.
[0047] Referring to FIG. 1, a network architecture (100) may include one or more com-20 puting devices or user equipment (104-1, 104-2…104-N) (used interchangeably with the term “user device”) associated with one or more users (102-1, 102-2…102-N) in an environment. A person of ordinary skill in the art will understand that one or more users (102-1, 102-2…102-N) may be individually referred to as the user (102) and col¬lectively referred to as the users (102). Similarly, a person of ordinary skill in the art 25 will understand that one or more user equipment (104-1, 104-2…104-N) may be indi¬vidually referred to 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
13

“computing device(s)” and “user equipment” may be used interchangeably throughout the disclosure. Although two user equipment (104) are depicted in FIG. 1, however any number of the user equipment (104) may be included without departing from the scope of the ongoing description.
5 [0048] 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 pha-blet device, and so on), a wearable computer device (e.g., a head-mounted display com¬puter device, a head-mounted camera device, a wristwatch computer device, and so on), a global positioning system (GPS) device, a laptop computer, a tablet computer, 10 or another type of portable computer, a media playing device, a portable gaming sys¬tem, and/or any other type of computer device with wireless communication capabili¬ties, and the like. In an embodiment, the user equipment (104) may include, but is not limited to, any electrical, electronic, electro-mechanical, or an equipment, or a combi¬nation of one or more of the above devices such as virtual reality (VR) devices, aug-15 mented 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 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) 20 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) may not be restricted to the mentioned devices and various other devices may be used. The net¬work architecture (100) may include a monitoring unit (114) having a user interface that provides audio-visual indications to the user (102) based on a set of signals trans-25 mitted by a system (108). In an embodiment, the monitoring unit (114) may be imple¬mented on the UE (104) and may be used by operators of the system (108).
14

[0049] In an embodiment, the user equipment (104) may include smart devices oper¬ating in a smart environment, for example, an Internet of Things (IoT) system. In such an embodiment, the user equipment (104) may include, but is not limited to, smart phones, smart watches, smart sensors (e.g., mechanical, thermal, electrical, magnetic, 5 etc.), networked appliances, networked peripheral devices, networked lighting system, communication devices, networked vehicle accessories, networked vehicular devices, smart accessories, tablets, smart television (TV), computers, smart security system, smart home system, other devices for monitoring or interacting with or for the users (102) and/or entities, or any combination thereof. A person of ordinary skill in the art 10 will appreciate that the user equipment (104) may include, but is not limited to, intelli¬gent, multi-sensing, network-connected devices, that can integrate seamlessly with each other and/or with a central server or a cloud-computing system or any other device that is network-connected.
[0050] Referring to FIG. 1, the user equipment (104) may communicate with the sys-15 tem (108) through a 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). The network (106) may in¬clude a wireless card or some other transceiver connection to facilitate this communi-20 cation. 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 (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 at-25 tribute associated therewith. In an embodiment, the unique identifier attribute may be indicative of mobile station international subscriber directory number (MSISDN), in¬ternational mobile equipment identity (IMEI) number, international mobile subscriber identity (IMSI), subscriber permanent identifier (SUPI) and the like.
15

[0051] In an embodiment, the system (108) may receive and analyze call record data from each cell site. The call record data may include, but not limited to, call records, call duration, frequency, user location, minutes of usage, etc. The system (108) may normalize and pre-process the call record data. The system (108) may extract one or 5 more relevant features such as network load, time of day, user behaviour from the pre-processed call record data to capture call patterns and user characteristics. The system (108) may feed the call record data and the extracted features to an artificial intelligence (AI)/machine learning (ML) model, and the AI/ML model may be trained based on the call record data and the extracted features. The AI/ML model may be trained to analyze
10 ongoing calls and predict longer than usual call duration leading to excessive MOU. The trained AI/ML model may send an immediate notification alert to a network oper-ations team, when the call duration goes more than a call duration threshold limit. Upon receiving the immediate notification alert, the network operations team may ensure that the call duration goes more than the call duration threshold limit and curate an interim
15 call cut policy.
[0052] Although FIG. 1 shows exemplary components of the network architecture (100), in other embodiments, the network architecture (100) may include fewer com¬ponents, different components, differently arranged components, or additional func¬tional components than depicted in FIG. 1. Additionally, or alternatively, one or more 20 components of the network architecture (100) may perform functions described as be¬ing performed by one or more other components of the network architecture (100).
[0053] FIG. 2 illustrates a block diagram of the system (108) for optimizing minutes of usage in a wireless network, in accordance with embodiments of the present disclo¬sure. In an aspect, the system (108) may include one or more processor(s) (202) and a 25 memory (204). The one or more processor(s) (202) may be implemented as one or more microprocessors, microcomputers, microcontrollers, edge or fog microcontrollers, dig¬ital signal processors, central processing units, logic circuitries, and/or any devices that
16

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 computer-readable instructions or routines in a non-5 transitory computer readable storage 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 ran¬dom-access memory (RAM), or non-volatile memory such as erasable programmable read-only memory (EPROM), flash memory, and the like.
10 [0054] The memory (204) may include, for example, a hard disk drive and/or a remov-able storage drive, representing a floppy disk drive, a magnetic tape drive, a compact disk drive, a program cartridge and cartridge interface (such as that found in video game devices), a removable memory chip (such as EPROM or PROM), and the like, which is read by and written to by removable storage unit. As will be appreciated, the
15 removable storage unit includes a computer usable storage medium having stored therein computer software and/or data. The removable storage drive reads from and/or writes to a removable storage unit in a well-known manner. The removable storage unit, also called a program storage device or a computer program product, represents a floppy disk, magnetic tape, compact disk, etc. The computer programs (also called
20 computer control logic) are stored in main memory (204). Such computer programs, when executed, enable the system (108) to perform the functions of the present disclo¬sure as discussed herein. In particular, the computer programs, when executed, enable the one or more processor (102) to perform the functions of the present disclosure. Accordingly, such computer programs represent controllers of the system (108).
25 [0055] Referring to FIG. 2, the system (108) may also 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.
17

The interface(s) (206) may facilitate communication to/from the system (108). The in-terface(s) (206) may also provide a communication pathway for one or more compo¬nents of the system (108). Examples of such components include, but are not limited to, processing unit/engine(s) (208) and a database (210).
5 [0056] In an embodiment, the processing unit/engine(s) (208) may be implemented as a combination of hardware and programming (for example, programmable instruc¬tions) to implement one or more functionalities of the processing engine(s) (208). In examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the pro-10 cessing engine(s) (208) may be processor-executable instructions stored on a non-tran¬sitory machine-readable storage medium and the hardware for the processing engine(s) (208) may include a processing resource (for example, one or more processors), to ex¬ecute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the 15 processing engine(s) (208). In such examples, the system (108) may include the ma¬chine-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 pro¬cessing engine(s) (208) may be implemented by electronic circuitry.
20 [0057] In an embodiment, the system (108) may include one or more databases such as databases (210). In an embodiment, the database (210) includes data that may be either stored or generated because of functionalities implemented by any of the com-ponents of the processor (202) or the processing engines (208). In an embodiment, the database (210) may be separate from the system (108). In an embodiment, the database
25 (210) may be indicative of including, but not limited to, a relational database, a distrib-uted database, distributed file sharing system, a cloud-based database, or the like.
18

[0058] In an exemplary embodiment, the processing engine (208) may include one or more engines selected from any of a data collection engine (212), an analysis module, a machine learning (ML) engine (214), and other engines (216), a computation engine (218) having functions that may include, but are not limited to, testing, storage, and 5 peripheral functions, such as wireless communication unit for remote operation, audio unit for alerts and the like, as described in FIG. 3.
[0059] The data collection engine (212) is configured for collecting call detail record (CDR) data associated with network usage from each cell site in the wireless network. The CDR captures information on calls made on telephone systems, including who 10 made the call (name and number), who was called (name if available, and number), the date and time the call was made, the duration of the call, and typically dozens of usages and diagnostic information elements. The CDR includes, but is not limited to, call duration, frequency, user location, minutes of usage, etc., from each cell site. In exam¬ples, the CDR data includes historical data covering the CDR data over a period of 15 time. The period of time may be 24 months to 1 month. A cell site, also known as a cell tower or base station, is a fixed-location structure that facilitates wireless commu¬nication between a mobile device and a network. In examples, the CDR data may be collected from each cell sites. In implementations, the CDR data may be collected by accessing CDR data storage through an application program interface (API), file trans-20 fers, and/or database access. The CDR data may be collected periodically, or on de¬mand. The computation engine (218) is configured for normalizing and pre-pro¬cessing, the collected CDR data for feature extraction and analysis. In examples, the CDR data may be stored in a structured format that includes details such as call start time, call duration, caller's number, callee's number, call type (e.g., voice call, SMS), 25 and possibly additional information depending on the telecom services. In some ex¬amples, the CDR data may not be stored in structured format. In either of the cases, the CDR data may normalize the data by processing the data in a uniform format, han¬dling missing, outliers or anomalies, removing duplicates, and correcting errors. In
19

examples, the processed CDR data may be converted to a standardized format and scale to ensure balance in comparison. In some examples, min-max scaling or z-score nor¬malization may be used for standardized format and scaling. The computation engine (212) is also configured for extracting one or more relevant features from the normal-5 ized and pre-processed data to capture one or more call patterns and user characteris¬tics. In examples, the feature extraction from CDR data involves deriving meaningful attributes or characteristics that can be used to analyze patterns, behaviors, and trends. Some examples of basic features include, but are not limited to call duration, call type, and timestamp features. Advanced features may include, but are not limited to, fre-10 quency of calls, geographical features, network features, usage patterns such as time-based patterns and seasonality calling patterns, call recurrence, and call intensity among the contacts.
[0060] The processing engine (208) may include an analysis module. The analysis module may include a machine learning (ML) engine (214). The ML engine (214) is
15 configured to analyze the one or more call patterns and the user characteristics from the collected data and the one or more extracted relevant features using one or more ML models. For example, a review of the CDR data may indicate call-related activity of the user, call recurrences, and user characteristics such as user behavior, including how the user calls specific contacts, time of call, frequency, and duration of calls, etc.
20 The call patterns may include trends of the user time of call, period of call, length of call, etc. The call patterns and the user characteristics may be obtained by analysis of historical data. The relevant features may be extracted by selecting features for extrac¬tion and using feature extracting techniques such as statistical measures, time-series features, etc. The statistical measures include computing statistical summaries such as
25 mean, median, standard deviation or variance for numeric features. The time-series features may include temporal patterns such as seasonality, trends, periodicity in call activities, etc. In examples, the ML models include one or more of classification mod-els, clustering models, time series analysis models, regression models, support vector
20

machine (SVM), k-nearest Neighbors (KNN), graph-based models, ensemble models, etc. The ML engine (214) analyzes one or more ongoing calls and predicts longer than usual call duration leading to excessive MOU. As used herein the term “MOU” refers to minutes of usage of a subscriber on call per day. The MOU may include information 5 such as date/time, caller ID, callee ID, call start time, call end time, duration, call type (local, international, landline, etc.), network, location, call charges, total minutes, usage breakdown (type of usage, network, time of the day), etc. When unlimited data and voice services are provided to all the subscribers, in some instances, the subscribers allegedly misuse the feature and start to make calls for long durations, such as beyond
10 10 hours a day, which constitutes a high MOU. A fair utilization of network services among all the users enables building an optimized network for better customer experi-ence and therefore helps in revenue optimization by the telecom service providers. Op¬timizing MOU may refer to strategies and practices aimed at efficiently managing and utilizing the allocated talk time or usage limits within a service plan. Optimizing the
15 MOU supports both consumers and service providers to ensure effective communica¬tion while maximizing value and minimizing costs. The ML engine (214) detects the alleged misuse of the services in advance by analyzing the user behavior data using optimized AI/ML techniques, thereby helping prevent revenue loss to the telecom ser-vice providers. For example, the ML engine (214) may identify and predict, based on
20 seasonality, contact details, call patterns, etc., that the user may likely to longer than usual call duration leading to excessive MOU. For example, the user may be making long calls for one or more contacts, leading to hours, which can possibly lead to exces¬sive MOU. In another example, the user may be making several calls to some contacts in a span of few hours leading to excessive MOU. These aspects may be identified as
25 relevant features and used by ML to predict longer than usual call duration leading to excessive MOU.
[0061] The machine learning (ML) engine (214) is also configured to send a notifica-tion alert in real-time to a network operations team upon a call duration exceeding a
21

call duration threshold limit, to curate an interim call cut policy. In an example, a telecom usage plan may be provided to a user that allows unlimited calling. However, the telecom usage plan may also define a call duration threshold limit of one hour or sixty minutes for a call. The call duration threshold limit may be defined based on, for 5 example, usage pattern of the user. When the user crosses the call duration threshold limit of sixty minutes, then an send a notification alert indicating that the MOU has exceeded the call duration threshold limit. The notification alert may include a short message service (SMS), an automated voice call alert, and the like. The notification alert may include message indicating the user that the calls are leading to excessive 10 MOU and appropriate policy may be applied. The curating an interim call cut policy may refer to application of a MOU usage mitigation policy. The MOU usage mitiga¬tion policy comprises disconnecting the call when the call duration goes more than the call duration threshold limit for controlling the MOU.
[0062] Although FIG. 2 shows exemplary components of the system (108), in other 15 embodiments, the system (108) may include fewer components, different components, differently arranged components, or additional functional components than depicted in FIG. 2. Additionally, or alternatively, one or more components of the system (108) may perform functions described as being performed by one or more other components of the system (108).
20 [0063] FIG. 3 illustrates an example architecture (300) of the proposed system (108), in accordance with an embodiment of the present disclosure.
[0064] As illustrated in FIG. 3, in an embodiment, the system (108) may include an ingestion layer, a compute or computation layer, and an AI/ML layer. The ingestion layer may include, but not limited to, a data collection module or the data collection 25 engine (212). The compute layer may include, but not limited to, a computation engine (218). The AI/ML layer may include, but not limited to, a ML model or the ML engine (214).
22

[0065] At step 304, the data collection engine (212) may be used for collecting call data records (CDRs) (302) from each cell site. The CDR captures information on calls made on telephone systems, including who made the call (name and number), who was called (name if available, and number), the date and time the call was made, the dura-5 tion of the call, and typically dozens of usages and diagnostic information elements. The CDR includes, but not limited to, call duration, frequency, user location, minutes of usage, etc. from each cell site. CDRs may be collected every time a call is made over a given time interval, e.g., five minutes. As an alternative, a sliding window or sliding timing interval may be used, e.g., five minutes, ten minutes, etc., to collect 10 CDRs. The CDRs may be from different servers for different network elements for a given call within a given time interval.
[0066] At step 306, the compute layer or the computation engine (218) may normalize and pre-process the collected CDR data. Normalization is the process of organizing data in a database. It includes creating tables and establishing relationships between
15 those tables according to rules designed both to protect the data and to make the data-base more flexible by eliminating redundancy and inconsistent dependency. The nor-malization cleans up the CDRs of unnecessary or inconsistent information or format the destinations based on a consistent numbering plan. The normalization of CDR in-cludes caller Id normalization, Destination normalization, and Disconnection Code
20 normalization.
[0067] n an exemplary embodiment, SIP caller Id “blue” is normalized to sip: 999600003@ag-projects.com which cor¬responds to a billable entity in Provider database. 0235468104@gateway.com for calls in the Netherlands might have the first 0 removed and 0031 appended. After normali-25 zation the destination becomes 0031235468104@gateway.com. 0031 has a corre¬sponding rate which can be calculated based on a consolidated international destina¬tions table (00 + Country code + Subscriber number). In an example for disconnection
23

code normalization, Cisco release codes are stored in hexadecimal values correspond-ing to Q931 Integrated Services Digital Network (ISDN) release codes defined by In¬ternational Telecommunication Union (ITU).
[0068] At step 308, the compute layer or the computation engine (218) may perform 5 feature extraction and further analysis on the normalized data. The compute layer or the computation engine (218) (212) may extract relevant features from the normalized and pre-processed data to capture call patterns and user characteristics.
[0069] At step 310, the ML engine (314) may perform ML model selection. In model selection a machine learning model is selected from among a collection of candidate 10 machine learning models (e.g., regression models, support vector machine (SVM), k-nearest Neighbors (KNN), etc.) for training a dataset. Multiple techniques, such as but not limited to, resampling methods and cross-validation are used for model selection.
[0070] At step 312, one or more ML models may be trained. The ML model may be trained using the pre-processed data and the computed features to understand the call 15 characteristics and the network usage patterns. The trained model may analyze the on¬going calls and predict longer than usual call duration leading to excessive MOU.
[0071] At step 314, the MOU may be predicted by the ML models.
[0072] At step 316, the excessive MOU may be detected. Generally, some of the sub-scribers make calls for more than 10 hours a day and this may even extend till 24 hours 20 a day. When provided with unlimited data and voice services, the users most often allegedly misuse the feature and start to make calls for more than 10 hours a day and or even 24 hours a day. This excessive MOU is detecting by the company after thor¬ough analysis of the call record data of each subscriber.
[0073] At step 318, the ML engine (214) may send an immediate notification alert to 25 the network operations team who then ensures that the call duration goes more than the
24

call duration threshold limit and curate the interim call cut policy, when the call dura-tion goes more than the call duration threshold limit. The curating may include the blockage of the service usage by service provider. The notification can be provided by email, message or provided on a GUI of a device associated with the service provider.
5 [0074] FIG. 4 illustrates an example process flow (400) for implementing for opti¬mizing minutes of usage in a wireless network, in accordance with an embodiment of the present disclosure. As illustrated in FIG. 4, at step 402, the method may include collecting CDR data which includes, but not limited to, call duration, frequency, user location, minutes of usage, etc. from each cell site.
10 [0075] At step 404 (compute layer), the method may include normalizing and pre-processing the collected data for feature extraction and further analysis.
[0076] At step 406 (compute layer), the method may include extracting relevant fea-tures from the pre-processed data to capture call patterns and user characteristics.
[0077] At step 408 (AI/ML layer), the method may include feeding the collected data 15 and the extracted features to suitable ML models. The ML model may be trained using the collected data and the extracted features to learn the call characteristics and the network usage patterns. The trained ML model may analyze the ongoing calls and pre¬dict longer than usual call duration leading to excessive MOU.
[0078] At step 410, the method includes predicting the MOU base on the analysis by 20 the ML models.
[0079] At step 412, the method includes determining if an excessive MOU is detected.
[0080] At step 414, the method includes sending an immediate notification alert to the network operations team who then ensures that the call duration goes more than the call duration threshold limit and curate the interim call cut policy.
25

[0081] FIG. 5 illustrates an exemplary flow diagram of a method (500) for optimizing minutes of usage in a wireless network, in accordance with embodiments of the present disclosure.
[0082] At step (502), call detail record (CDR) data associated with network usage 5 from each cell site in the wireless network is collected by a data collection engine (212). The CDR captures information on calls made on telephone systems, including who made the call (name and number), who was called (name if available, and number), the date and time the call was made, the duration of the call, and typically dozens of usages and diagnostic information elements. The CDR includes, but not limited to, call dura-10 tion, frequency, user location, minutes of usage, etc. from each cell site. The CDR may collect at regular intervals or at predetermined time duration.
[0083] At step (504), a computation engine (218), normalizes and pre-processes the collected CDR data for feature extraction and analysis.
[0084] At step (506), the computation engine (218) extracts one or more relevant fea-15 tures from the normalized and pre-processed data to capture one or more call patterns and one or more user characteristics.
[0085] At step (508), the ML engine (214) analyzes the one or more call patterns and one or more user characteristics from the collected data and the extracted features using one or more ML models. The one or more ML models are trained using the collected
20 CDR data and one or more extracted features to learn the call characteristics and the network usage patterns. The ML engine (214) analyzes one or more ongoing calls and predicts longer than usual call duration leading to MOU. As used herein the term “MOU” refers to minutes of usage of a subscriber on call per day. When unlimited data and voice services are provided to all the subscribers, in some instances the subscribers
25 allegedly misuse the feature and start to make calls for long durations, such as for be-yond 10 hours a day, that constitutes a high MOU. A fair utilization of network services
26

among all the users enables building an optimized network for better customer experi¬ence and therefore helps in revenue optimization by the telecom service providers. The ML engine (214) detects the alleged misuse of the services in advance by analyzing the customer behaviour data using optimized AI/ML techniques, thereby helping in pre-5 venting revenue loss of the telecom service providers.
[0086] At step (510), the ML engine (214) sends a notification alert in real-time to a network operations team upon a call duration exceeding a call duration threshold limit, to curate an interim call cut policy. The call duration threshold limit may be for exam¬ple, 90 minutes or in a range of 100-500 minutes.
10 [0087] In an exemplary embodiment, the present disclosure discloses a user equip¬ment (UE) (104) configured for monitoring minutes of usage in a wireless network. The user equipment includes the processor (202) and a computer readable storage me¬dium storing programming for execution by the processor (202). The programming includes instructions to collect, call detail record (CDR) data associated with network
15 usage from each cell site in the wireless network. The collected CDR data is normalized and pre-processed for feature extraction and analysis. One or more relevant features are extracted from the normalized and pre-processed data to capture one or more call patterns and one or more user characteristics. The programming also includes instruc-tions to analyze the one or more call patterns and the one or more user characteristics
20 from the collected data and the extracted features using one or more ML models. Based on this, a notification alert is sent in real-time to a network operations team upon a call duration exceeding a call duration threshold limit, to curate an interim call cut policy.
[0088] FIG. 6 illustrates an exemplary computer system (600) in which or with which embodiments of the present disclosure may be implemented. As shown in FIG. 5, the 25 computer system (600) may include an external storage device (610), a bus (620), a main memory (630), a read-only memory (640), a mass storage device (650), a com¬munication port (660), and a processor (670). A person skilled in the art will appreciate
27

that the computer system (600) may include more than one processor (670) and com-munication ports (660). The processor (670) may include various modules associated with embodiments of the present disclosure.
[0089] In an embodiment, the communication port (660) may be any of an RS-232 5 port for use with a modem-based dialup connection, a 10/100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fibre, a serial port, a parallel port, or other existing or future ports. The communication port (660) may be chosen depending on the net¬work (106), such a Local Area Network (LAN), Wide Area Network (WAN), or any network to which the computer system (600) connects.
10 [0090] In an embodiment, the memory (630) may be Random Access Memory (RAM), or any other dynamic storage device commonly known in the art. Read-only memory (640) may be any static storage device(s) e.g., but not limited to, a Program¬mable Read Only Memory (PROM) chips for storing static information e.g., start-up or Basic Input/Output System (BIOS) instructions for the processor (670).
15 [0091] In an embodiment, the mass storage (650) may be any current or future mass storage solution, which may be used to store information and/or instructions. Exem-plary mass storage solutions include, but are not limited to, Parallel Advanced Tech-nology Attachment (PATA) or Serial Advanced Technology Attachment (SATA) hard disk drives or solid-state drives (internal or external, e.g., having Universal Serial Bus
20 (USB) and/or Firewire interfaces), one or more optical discs, Redundant Array of In-dependent Disks (RAID) storage, e.g., an array of disks (e.g., SATA arrays).
[0092] In an embodiment, the bus (620) communicatively couples the processor(s) (670) with the other memory, storage, and communication blocks. The bus (620) may be, e.g., a Peripheral Component Interconnect (PCI)/PCI Extended (PCI-X) bus, Small
28

Computer System Interface (SCSI), Universal Serial Bus (USB) or the like, for con-necting expansion cards, drives and other subsystems as well as other buses, such a front side bus (FSB), which connects the processor (670) to the computer system (600).
[0093] Optionally, operator and administrative interfaces, e.g., a display, keyboard, 5 joystick, and cursor control device, may also be coupled to the bus (620) to support direct operator interaction with the computer system (600). Other operator and admin¬istrative interfaces may be provided through network connections connected through the communication port (660). The components described above are meant only to ex¬emplify various possibilities. In no way should the aforementioned exemplary com-10 puter system (600) limit the scope of the present disclosure.
[0094] While considerable emphasis has been placed herein on the preferred embod¬iments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the princi¬ples of the disclosure. These and other changes in the preferred embodiments of the 15 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.
[0095] The present disclosure provides technical advancement related to optimizing minutes of usage in a wireless network. Conventional or state of art do not have any 20 solutions for optimizing MOU as many players ignore the MOU related issues. The disclosure focusses not only on identifying the users causing MOU issues, but also alert them to avoid prospective MOU issues.
ADVANTAGES OF THE PRESENT DISCLOSURE
[0096] The present disclosure provides a system and a method for minutes of usage 25 (MOU) optimization in a wireless network.
29

[0097] The present disclosure detects alleged misuse of network services in advance by analysing customer behaviour data using optimized Artificial Intelligence/Machine Learning (AI/ML) techniques.
[0098] The present disclosure provides a system and a method that uses AI/ML tech-5 niques to constantly monitor real time MOU patterns of all the users, thereby predicting and curbing any further misuse of the network services.
[0099] The present disclosure provides a system and a method that sends an immedi-ate notification alert to the network operations team, and curates an interim call-cut policy when the call duration goes more than the call duration threshold limit.
10 [00100] The present disclosure provides a system and a method that ensures fair utili-zation of network services among all the users, thereby building an optimized network for better customer experience, and enhancing revenue optimization.
[00101] The present disclosure provides a system and a method that prevents revenue loss of a service provider by detecting the alleged misuse of the network services in 15 advance.
30

We Claim:
1. A method (500) for optimizing minutes of usage (MOU) in a wireless network,
the method (500) comprising:
collecting (502), by a data collection engine (212), call detail record (CDR) data associated with network usage from each cell site in the wireless network;
normalizing and pre-processing (504), by a computation engine (218), the col-lected CDR data for feature extraction and analysis;
extracting (506), by the computation engine (218) one or more relevant features from the normalized and pre-processed data to capture one or more call patterns and one or more user characteristics;
analyzing (508), by an analysis module, the one or more call patterns and the one or more user characteristics; and
sending (510), by the analysis module, a notification alert in real-time to a user upon a call duration exceeding a call duration threshold limit, to take an action.
2. The method (500) of claim 1, further comprising:
training the analysis module using the collected CDR data and the one or more extracted features to learn the one or more call patterns and the one or more user char¬acteristics.
3. The method (500) of claim 1, wherein analyzing the one or more call patterns
and the one or more user characteristics comprises:
analyzing one or more ongoing calls and predicting longer than usual call dura-tion leading to excessive minutes of usage (MOU).

4. The method (500) of claim 1, wherein the CDR data comprises historical data covering the CDR data over a period of time, and wherein the analysis module is con-figured to analyze the historical data to identify the one or more call patterns and one or more user characteristics.
5. The method (500) of claim 3, further comprising applying a MOU usage miti-gation policy, upon the call duration exceeding a call duration threshold limit, for con-trolling the MOU.
6. The method (500) of claim 5, wherein the MOU usage mitigation policy com-prises termination of the call when the call duration exceeds the call duration threshold limits.
7. A system (108) for optimizing minutes of usage in a wireless network, the sys-tem (108) comprising:
a memory (204) configured to store one or more computer-readable instructions or routines in a non-transitory computer-readable storage medium, fetched and exe¬cuted to create or share data packets over a network service;
a processor (202) configured to fetch and execute computer-readable instruc-tions stored in the memory (204);
an interface (206) configured to provide a communication pathway for one or more components of the system (108);
a data collection engine (212) configured to collect, call detail record (CDR) data associated with network usage from each cell site in the wireless network; a computation engine (218) configured to
normalize and pre-process, the collected CDR data for feature extrac-tion and analysis; and

extract one or more relevant features from the normalized and pre-pro-cessed data to capture one or more call patterns and one or more user charac-teristics; and an analysis module to:
analyze the one or more call patterns and one or more user characteris-tics; and
sending, a notification alert in real-time to a user upon a call duration exceeding a call duration threshold limit, to perform an action.
8. The system (108) of claim 7, wherein the analysis module is further configured to analyze one or more ongoing calls and predict longer than usual call duration leading to excessive minutes of usage (MOU).
9. A user equipment (UE) (104) configured for optimizing minutes of usage in a wireless network, the user equipment (104) comprising:
a processor (202); and
a computer readable storage medium storing programming for execution by the processor (202), the programming including instructions to:
collect, call detail record (CDR) data associated with network usage from each cell site in the wireless network;
normalize and pre-process the collected CDR data for feature extraction and analysis;
extract one or more relevant features from the normalized and pre-pro-cessed data to capture one or more call patterns and one or more user character-istics;
analyze the one or more call patterns and the one or more user character-istics; and

send a notification alert in real-time to a user upon a call duration exceed¬ing a call duration threshold limit, to perform an action.