DESC:
FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENTS RULES, 2003

COMPLETE SPECIFICATION
(See section 10 and rule 13)
1. TITLE OF THE INVENTION
SYSTEM AND METHOD FOR PREDICTING ABNORMALITIES IN A NETWORK
2. APPLICANT(S)
NAME NATIONALITY ADDRESS
JIO PLATFORMS LIMITED INDIAN OFFICE-101, SAFFRON, NR. CENTRE POINT, PANCHWATI 5 RASTA, AMBAWADI, AHMEDABAD 380006, GUJARAT, INDIA
3.PREAMBLE TO THE DESCRIPTION

THE FOLLOWING SPECIFICATION PARTICULARLY DESCRIBES THE NATURE OF THIS INVENTION AND THE MANNER IN WHICH IT IS TO BE PERFORMED.

FIELD OF THE INVENTION
[0001] The present invention relates to the field of wireless communication systems, more particularly relates to a method and a system for predicting abnormalities in a network.
BACKGROUND OF THE INVENTION
[0002] In the communication network, abnormalities may occur due to various network issues such as low signal strength of the network, call drops, communication session failures, etc.
[0003] The NWDAF (Network Data Analytics Function) collects the data from a User Equipment (UE) or a group of UE’s in a certain area of interest and provides analytical information about the network data. The NWDAF also predicts abnormalities in the communication network. Previously, the predictions were not made by the network.
[0004] Generally, the consumers such as network engineers may transmit requests to NWDAF along with the relevant data of user equipment for getting the information about abnormalities. Thereafter the system may perform operations such as predicting abnormalities in order to provide information about the abnormalities present in the communication network to the consumers.
[0005] The process of providing information about the abnormalities present in the communication network to the consumer after requesting for the abnormalities is time consuming task. Due to this method of providing information about the abnormalities present in the communication network to the consumer after requesting for the abnormalities, the network may suffer further issues which can substantially decrease the efficiency of the network.
[0006] In view of the above, there is, a dire need for an efficient system and method for predicting abnormalities in the network based on at least one of, network traffic, and UE location. Further, due to the large number of UEs the system and method enables to extrapolate abnormalities in the future.
SUMMARY OF THE INVENTION
[0007] One or more embodiments of the present disclosure provides a method and a system for predicting abnormalities in a network.
[0008] In one aspect of the present invention, the method for predicting abnormalities in the network is disclosed. The method includes the step of retrieving data pertaining to one or more User Equipment’s (UEs) from a plurality of sources. The method further includes the step of training a AI/ML model with the retrieved data to identify trends/patterns related to the one or more UEs. The method further includes the step of predicting, utilizing the trained model, abnormalities associated with the identified trends/patterns of the one or more UEs in the network. The method further includes the step of generating recommendations pertaining to the predicted.
[0009] In another embodiment, the data pertaining to the one or more UEs includes at least one of, UE identifier, network activity, location, patterns and trends.
[0010] In yet another embodiment, the plurality of sources includes at least one of, but not limited to, an Access and Mobility Management Function (AMF) and a Network Exposure Function (NEF).
[0011] In yet another embodiment, the step of retrieving data pertaining to the one or more UEs from the plurality of sources, further includes the step of, preprocessing, the retrieved data and extracting, one or more features from the retrieved data.
[0012] In yet another embodiment, the step of, predicting, utilizing the trained model, abnormalities associated with the identified trends/patterns of the one or more UEs in the network, includes the step of, determining, utilizing the trained model, whether there is a deviation in the identified trends/patterns in comparison to a learnt historical trends/patterns related to the one or more UEs based on one or more thresholds and in repose to determination, inferring, the deviation as the predicted abnormalities associated with the one or more UEs .
[0013] In yet another embodiment, the model learns the historical trends/patterns related to the one or more UEs based on historical data stored in a storage unit.
[0014] In yet another embodiment, the recommendations are transmitted to the consumer to resolve the predicted abnormalities.
[0015] In yet another embodiment, the generated recommendations are transmitted to the consumer to initiate one or more actions.
[0016] In yet another embodiment, the one or more processors retrieve data pertaining to the one or more UEs from the plurality of sources based on at least one of, receiving a request from the consumer and without receiving a request from the consumer.
[0017] In yet another embodiment, based on the one or more actions initiated by the consumer, the model learns the one or more actions taken and keeps on updating.
[0018] In another aspect of the present invention, the system for predicting abnormalities in a network is disclosed. The system includes a retrieving unit configured to retrieve data pertaining to one or more User Equipment’s (UEs) from a plurality of sources. The system further includes a training unit configured to train a AI/ML model with the retrieved data to identify trends/patterns related to the one or more UEs. The system further includes a predicting unit configured to predict, utilizing the trained model, abnormalities associated with the identified trends/patterns of the one or more UEs in the network. The system further includes a generating unit configured to transmit, recommendations pertaining to the predicted abnormalities.
[0019] In yet another aspect of the present invention, a non-transitory computer-readable medium having stored thereon computer-readable instructions that, when executed by a processor. The processor is configured to retrieve, data pertaining to one or more User Equipment’s (UEs) from a plurality of sources. The processor is further configured to train, a AI/ML model with the retrieved data to identify trends/patterns related to the one or more UEs. The processor is further configured to predict, utilizing the trained model, abnormalities associated with the identified trends/patterns of the one or more UEs in the network. The processor is further configured to generate recommendations pertaining to the predicted abnormalities.
[0020] In another aspect of the present invention, a Consumer Equipment (CE) is disclosed. One or more primary processors are communicatively coupled to one or more processors. The one or more primary processors are further coupled with a memory. The memory stores instructions which when executed by the one or more primary processors cause the CE to receive, recommendations pertaining to the predicted abnormalities form the one or more processors.
[0021] Other features and aspects of this invention will be apparent from the following description and the accompanying drawings. The features and advantages described in this summary and in the following detailed description are not all-inclusive, and particularly, many additional features and advantages will be apparent to one of ordinary skill in the relevant art, in view of the drawings, specification, and claims hereof. Moreover, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes and may not have been selected to delineate or circumscribe the inventive subject matter, resort to the claims being necessary to determine such inventive subject matter.
BRIEF DESCRIPTION OF THE DRAWINGS
[0022] 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 different drawings. Components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. Some drawings may indicate the components using block diagrams and may not represent the internal circuitry of each component. It will be appreciated by those skilled in the art that disclosure of such drawings includes disclosure of electrical components, electronic components or circuitry commonly used to implement such components.
[0023] FIG. 1 is an exemplary block diagram of an environment for predicting abnormalities in a network, according to one or more embodiments of the present invention;
[0024] FIG. 2 is an exemplary block diagram of a system for predicting abnormalities in the network, according to one or more embodiments of the present invention;
[0025] FIG. 3 is an exemplary architecture of the system of FIG. 2, according to one or more embodiments of the present invention;
[0026] FIG. 4 is an exemplary architecture for predicting abnormalities in the network, according to one or more embodiments of the present disclosure;
[0027] FIG. 5 is an exemplary signal flow diagram illustrating the flow for predicting abnormalities in the network, according to one or more embodiments of the present disclosure; and
[0028] FIG. 6 is a flow diagram of a method for predicting abnormalities in the network, according to one or more embodiments of the present invention.
[0029] The foregoing shall be more apparent from the following detailed description of the invention.
DETAILED DESCRIPTION OF THE INVENTION
[0030] Some embodiments of the present disclosure, illustrating all its features, will now be discussed in detail. It must also be noted that as used herein and in the appended claims, the singular forms "a", "an" and "the" include plural references unless the context clearly dictates otherwise.
[0031] Various modifications to the embodiment will be readily apparent to those skilled in the art and the generic principles herein may be applied to other embodiments. However, one of ordinary skill in the art will readily recognize that the present disclosure including the definitions listed here below are not intended to be limited to the embodiments illustrated but is to be accorded the widest scope consistent with the principles and features described herein.
[0032] A person of ordinary skill in the art will readily ascertain that the illustrated steps detailed in the figures and here below are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments.
[0033] Various embodiments of the present invention provide a system and a method for predicting abnormalities in a network. The disclosed system and method aim at providing information of the abnormalities present in the network even before consumers request the same. In other words, the present invention provides a unique approach of predicting abnormalities present in the network based on historical data before the consumers requests for the same. Advantageously, this ensures that the consumer may take precautionary measures in a timely manner in response to the predicted abnormalities thereby preventing abnormalities which may occur in the future.
[0034] Referring to FIG. 1, FIG. 1 illustrates an exemplary block diagram of an environment 100 for predicting abnormalities in a network 106 according to one or more embodiments of the present invention. The environment 100 includes one or more User Equipment (UE) 102, a server 104, the network 106, a system 108, a plurality of sources 110 and a Consumer Equipment (CE) 112. In an embodiment, predicting abnormalities in the network 106 pertains to predicting abnormalities present in the network 106 before a customer requesting the system 108 for predicting abnormalities. Herein, the consumers are the users associated with network providers.
[0035] For the purpose of description and explanation, the description will be explained with respect to one or more user equipment’s (UEs) 102, or to be more specific will be explained with respect to a first UE 102a, a second UE 102b, and a third UE 102c, and should nowhere be construed as limiting the scope of the present disclosure. Each of the at least one UE 102 namely the first UE 102a, the second UE 102b, and the third UE 102c is configured to connect to the server 104 via the network 106.
[0036] In an embodiment, each of the first UE 102a, the second UE 102b, and the third UE 102c is one of, but not limited to, any electrical, electronic, electro-mechanical or an equipment and a combination of one or more of the above devices such as smartphones, Internet Of Things (IOT) devices, Virtual Reality (VR) devices, Augmented Reality (AR) devices, laptop, a general-purpose computer, desktop, personal digital assistant, tablet computer, mainframe computer, or any other computing device.
[0037] In an embodiment, the CE 112 is one of, but not limited to, any electrical, electronic, electro-mechanical or an equipment and a combination of one or more of the above devices such as smartphones, Internet Of Things (IOT) devices, Virtual Reality (VR) devices, Augmented Reality (AR) devices, laptop, a general-purpose computer, desktop, personal digital assistant, tablet computer, mainframe computer, or any other computing device.
[0038] The network 106 includes, by way of example but not limitation, one or more of a wireless network, a wired network, an internet, an intranet, a public network, a private network, a packet-switched network, a circuit-switched network, an ad hoc network, an infrastructure network, a Public-Switched Telephone Network (PSTN), a cable network, a cellular network, a satellite network, a fiber optic network, or some combination thereof. The network 106 may include, but is not limited to, a Third Generation (3G), a Fourth Generation (4G), a Fifth Generation (5G), a Sixth Generation (6G), a New Radio (NR), a Narrow Band Internet of Things (NB-IoT), an Open Radio Access Network (O-RAN), and the like.
[0039] The network 106 may also include, by way of example but not limitation, at least a portion of one or more networks having one or more nodes that transmit, receive, forward, generate, buffer, store, route, switch, process, or a combination thereof, etc. one or more messages, packets, signals, waves, voltage or current levels, some combination thereof, or so forth.
[0040] The environment 100 includes the server 104 accessible via the network 106. The server 104 may include by way of example but not limitation, one or more of a standalone server, a server blade, a server rack, a bank of servers, a server farm, hardware supporting a part of a cloud service or system, a home server, hardware running a virtualized server, a processor executing code to function as a server, one or more machines performing server-side functionality as described herein, at least a portion of any of the above, some combination thereof. In an embodiment, the entity may include, but is not limited to, a vendor, a network operator, a company, an organization, a university, a lab facility, a business enterprise side, a defense facility side, or any other facility that provides service.
[0041] The environment 100 further includes the plurality of sources 110. In one embodiment, the plurality of sources 110 are origins from which the data is retrieved and utilized for at least one of, but not limited to, analysis, research, and decision-making. In one embodiment, the plurality of sources 110 is at least one of, but not limited to, sensors, applications, network functions and one or more databases. In one embodiment, the plurality of sources 110 are associated with the sources included within the network 106 and outside the network 106. In one embodiment, the plurality of sources includes at least one of, but not limited to, an Access and Mobility Management Function (AMF) and a Network Exposure Function (NEF).
[0042] In one embodiment, the AMF is a key component in the 5G core network architecture. The primary role of the AMF is to manage UE 102 access to the network 106, including handling registration, connection management, and mobility management. In one embodiment, the NEF is a functional element in the 5G network architecture that provides a set of Application Programming Interfaces (APIs) to expose network capabilities and services to external applications and service providers. The NEF facilitates the controlled access to various network resources, enabling third-party developers to create applications that leverage unique features of the 5G network, such as quality of service (QoS), location services, and network slicing.
[0043] The environment 100 further includes the system 108 communicably coupled to the server 104, the UE 102, the plurality of sources 110 and the CE 112 via the network 106. The system 108 is adapted to be embedded within the server 104 or is embedded as the individual entity.
[0044] Operational and construction features of the system 108 will be explained in detail with respect to the following figures.
[0045] FIG. 2 is an exemplary block diagram of the system 108 for predicting abnormalities in the network 106, according to one or more embodiments of the present invention.
[0046] As per the illustrated and preferred embodiment, the system 108 for predicting abnormalities in the network 106, includes one or more processors 202, a memory 204, a storage unit 206 and a model 220. Herein, an Artificial Intelligence/Machine Learning (AI/ML) model 220. The one or more processors 202, hereinafter referred to as the processor 202, may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, single board computers, and/or any devices that manipulate signals based on operational instructions. However, it is to be noted that the system 108 may include multiple processors as per the requirement and without deviating from the scope of the present disclosure. Among other capabilities, the processor 202 is configured to fetch and execute computer-readable instructions stored in the memory 204.
[0047] As per the illustrated embodiment, the processor 202 is configured to fetch and execute computer-readable instructions stored in the memory 204 as the memory 204 is communicably connected to the processor 202. The memory 204 is configured to store one or more computer-readable instructions or routines in a non-transitory computer-readable storage medium, which may be fetched and executed for predicting abnormalities in the network 106. The memory 204 may include any non-transitory storage device including, for example, volatile memory such as RAM, or non-volatile memory such as disk memory, EPROMs, FLASH memory, unalterable memory, and the like.
[0048] The environment 100 further includes the storage unit 206. As per the illustrated embodiment, the storage unit 206 is configured to store data retrieved from the plurality of sources 110. The storage unit 206 is further configured to store historical data pertaining to the one or more UEs 102. The storage unit 206 is one of, but not limited to, a centralized database, a cloud-based database, a commercial database, an open-source database, a distributed database, an end-user database, a graphical database, a No-Structured Query Language (NoSQL) database, an object-oriented database, a personal database, an in-memory database, a document-based database, a time series database, a wide column database, a key value database, a search database, a cache databases, and so forth. The foregoing examples of the storage unit 206 types are non-limiting and may not be mutually exclusive e.g., the database can be both commercial and cloud-based, or both relational and open-source, etc.
[0049] As per the illustrated embodiment, the system 108 includes the AI/ML model 220. In an alternate embodiment, the system 108 includes a plurality of AI/ML models 220. The AI/ML model 220 facilitates system 108 in performing tasks such as predicting abnormalities, detecting anomalies, recognizing patterns, making predictions, solving problems, enhancing decision-making, and providing insights across various fields. For example, the plurality of AI/ML models 220 facilitates solving real-world problems without extensive manual intervention. The AI/ML models 220 includes at least one of, a linear regression model, decision trees model, and K-Means Clustering model.
[0050] As per the illustrated embodiment, the system 108 includes the processor 202 for predicting abnormalities in the network 106. The processor 202 includes a retrieving unit 208, a training unit 210, a predicting unit 212, and a generating unit 214, a transceiver unit 216 and a handling unit 222. The processor 202 is communicably coupled to the one or more components of the system 108 such as the memory 204, the storage unit 206 and the AI/ML model 220. In an embodiment, operations and functionalities of the retrieving unit 208, the training unit 210, the predicting unit 212, the generating unit 214, the transceiver unit 216 and the handling unit 222 and the one or more components of the system 108 can be used in combination or interchangeably.
[0051] In one embodiment, the system 108 initiates a process of predicting abnormalities in the network 106 without receiving any request pertaining to predicting abnormalities in the network 106 from the consumer. In one embodiment, initially the retrieving unit 208 of the processor 202 is configured to retrieve data pertaining to the one or more UEs 102 from the plurality of sources 110. In one embodiment, retrieving unit 208 is configured to check whether any request pertaining to predicting abnormalities in the network 106 is received from the consumer within a predefined time period. Based on checking, if the retrieving unit 208 identifies that the request is not received from the consumer for predicting abnormalities in the network 106, then the retrieving unit 208 retrieves data pertaining to the one or more UEs 102 from the plurality of sources 110.
[0052] In one embodiment, the plurality of data sources 110 stores data pertaining to the one or more UEs 102 which includes at least one of, but not limited to, location information of the one or more UEs 102, unique identity of the one or more UEs 102, and credentials for authenticating one or more UEs 102. Herein, the plurality of data sources 110 facilities in understanding behavior of the one or more UEs 102. In an alternate embodiment, the plurality of data sources 110 includes at least one of, but not limited to, Radio Access Network (RAN), server 104 and core network nodes such as at least one of, Serving Gateway (SGW) and Packet Data Network Gateway (PGW). In one embodiment, the retrieving unit 208 retrieves data pertaining to the one or more UEs 102 from the plurality of data sources 110 which is further utilized for predicting abnormalities.
[0053] In one embodiment, the data is at least one of, but not limited to a UE identifier, a network activity, a location, usage patterns and trends related to one or more UEs 102. In one embodiment, the UE identifier is used to uniquely identify devices within the network 106. The UE identifier includes at least one of, an International Mobile Equipment Identity (IMEI), an International Mobile Subscriber Identity (IMSI) and a Mobile Station International Subscriber Directory Number (MSISDN). In one embodiment, the network activity of the one or more UEs102 refers to the various actions and interactions performed by the one or more UEs 102 while connected to the network 106. The network activity includes at least one of, but not limited to, data transmission, voice calls and messaging.
[0054] In one embodiment, the location of the one or more UEs 102 relates to at least one of, but not limited to, cell ID and Global Positioning System (GPS). For example, a base station has a unique cell ID that facilitates identifying the one or more UEs 102 location. In one embodiment, the usage patterns refer to the behaviors and of the one or more UEs 102 when interacting with at least one of, devices, applications, and services. In one embodiment, the usage patterns relate to at least one of, frequency of the one or more UEs 102 engaged in the network 106 and duration of the one or more UEs 102 relates to average time spent by the one or more UEs 102 during each session. In another embodiment, the usage patterns relates to power consumption of a cell tower which is monitored by the one or more UEs 102. For example, the usage patterns of the one or more UEs 102 include notifying power consumption of the cell tower during specific times of day, such as during evening hours. In one embodiment, the trends related to one or more UEs 102 are general directions in which the one or more UEs 102 developing or changing.
[0055] For example, the data pertaining to the one or more UEs 102 is retrieved from at least one of, but not limited to, the AMF and the NEF. Herein the one or more UEs 102 refers to devices used by subscribers. Herein, the subscribers are users utilizing services provided by network providers. The services include at least one of, but not limited to, a telephony service, a video conferencing service, and an anomaly prediction service. In an alternate embodiment the retrieving unit 208 retrieves the data from the plurality of sources 110 which are present within the network 106 and outside the network 106. In one embodiment, the plurality of sources 110 periodically transmits the data to the system 108.
[0056] In an alternate embodiment, the consumer transmits the request to the system 108 for predicting abnormalities in the network 106. Further, the retrieving unit 208 determines whether the request is received from the consumer for predicting abnormalities in the network 106. If the request is received at the retrieving unit 208, then based on the request received by the consumer, the retrieving unit 208 initiates a process for predicting abnormalities in the network 106. For example, the retrieving unit 208 periodically checks whether the request for predicting abnormalities in the network 106 is received is not. Advantageously, the system 108 is capable of predicting abnormalities in the network 106 without requesting for the same.
[0057] In one embodiment, the CE 112 is at least one of, but not limited to, a microservice, and an application that transmits the request to the system 108 for predicting abnormalities in the network 106. The microservice is a small, independent service that performs a specific function within a larger application. An application is a software program designed to perform specific tasks or functions for the consumers. Further, the retrieving unit 208 determines whether the request is received from at least one of, but not limited to, the microservice, and the application for predicting abnormalities in the network 106. If the request is received at the retrieving unit 208, then based on the request received by the consumer, the retrieving unit 208 initiates the process for predicting abnormalities in the network 106.
[0058] In one embodiment, the retrieving unit 208 retrieves the data from the plurality of sources 110 via an interface. In one embodiment, the interface includes at least one of, but not limited to, one or more Application Programming Interfaces (APIs) which are used for retrieving the data from the plurality of sources 110. The one or more APIs are sets of rules and protocols that allow different entities to communicate with each other. The one or more APIs define the methods and data formats that entities can use to request and exchange information, enabling integration and functionality across various platforms. In particular, the APIs are essential for integrating different systems, accessing services, and extending functionality.
[0059] In one embodiment, the retrieving unit 208 is at least one of, but not limited to, a Network Data Analytics Function (NWDAF). The NWDAF is a standardized function in 5G network architecture which is designed to collect, analyze, and utilize data from various network elements to improve overall network performance.
[0060] Upon retrieving the data from the plurality of sources 110, the retrieving unit 208 is further configured to preprocess the retrieved data. In particular, the retrieving unit 208 is configured to preprocess the retrieved data to ensure the data consistency and quality of the data within the system 108. The retrieving unit 208 performs at least one of, but not limited to, data normalization, data definition and data cleaning procedures.
[0061] While preprocessing, the retrieving unit 208 performs at least one of, but not limited to, reorganizing the data, removing the redundant data, formatting the data, removing null values from the data, cleaning the data, and handling missing values. The main goal of the preprocessing is to achieve a standardized data format across the system 108. While preprocessing, the duplicate data and inconsistencies are eliminated from the retrieved data. The retrieving unit 208 is further configured to store the pre-processed data in at least one of, the storage unit 206 for subsequent retrieval and analysis.
[0062] For example, let us assume that the one or more UEs 102 monitors and records power consumption values of the one or more cell towers such as at least one of, a first tower with 150 kilowatt (kW), a second tower with NaN value, a third tower with 200 kW and a forth tower with 180 kW. Based on the recorded data, the retrieving unit 208 preprocesses the record of the second tower by replacing the NAN value with the mean of the power consumption values of the first tower, the third tower and the forth tower.
[0063] Upon storing the pre-processed data in the storage unit 206, the retrieving unit 208 is further configured to extract one or more features from the pre-processed data for training the AI/ML model 220. For example, let us consider that the pre-processed data is related to the UEs 102 in the network 106. Then in order to train the AI/ML model 220, the retrieving unit 208 extracts the one or more features such as at least one of, but not limited to, the UE identifier and the UE location from the pre-processed data.
[0064] Upon preprocessing the retrieved data and extracting the one or more features from the pre-processed data, the training unit 210 of the processor 202 is configured to train the AI/ML model 220 with at least one of, the retrieved data to identify trends/patterns related to the one or more UEs 102. In one embodiment, the trend refers to the general direction in which data points move over time.
[0065] In particular, the training unit 210 trains the AI/ML model 220 with the one or more features extracted from the pre-processed data. In order to train the AI/ML model 220, the training unit 210 configures one or more hyperparameters of the AI/ML model 220. In one embodiment, the one or more hyperparameters of the AI/ML model 220 includes at least one of, but not limited to, a learning rate, a batch size, and a number of epochs.
[0066] Upon configuring the one or more hyperparameters of the AI/ML model 220, the training unit 210 trains the AI/ML model 220. For training the AI/ML model 220, the training unit 210 splits the at least one of, pre-processed data and the one or more features into at least one of, but not limited to, training data and testing data. Further, the training unit 210 feeds the training data to the AI/ML model 220 based on which the AI/ML model 220 are trained by the training unit 210.
[0067] In one embodiment, the training unit 210 trains the AI/ML model 220 by applying one or more logics for identifying trends/patterns of the one or more UEs 102 in the network 106. In one embodiment, the one or more logics may include at least one of, but not limited to, a k-means clustering, a hierarchical clustering, a Principal Component Analysis (PCA), an Independent Component Analysis (ICA), a deep learning logics such as Artificial Neural Networks (ANNs), a Convolutional Neural Networks (CNNs), a Recurrent Neural Networks (RNNs), a Long Short-Term Memory Networks (LSTMs), a Generative Adversarial Networks (GANs), a Q-Learning, a Deep Q-Networks (DQN), a Reinforcement Learning Logics, etc. In one embodiment, subsequent to training, the trained AI/ML model 220 is fed with the testing data in order to evaluate performance of the AI/ML models 220. In alternate one embodiment, the AI/ML model 220 learns the historical trends/patterns related to the one or more UEs 102 based on historical data stored in a storage unit 206.
[0068] Upon training the AI/ML model 220, the predicting unit 212 of the processor 202 is configured to predict abnormalities associated with the identified trends/patterns of the one or more UEs 102 utilizing the trained AI/ML model 220. For prediction, the predicting unit 212 utilizes the trained AI/ML model 220 to determine whether there is a deviation in the identified trends/patterns in comparison to the learnt historical trends/patterns related to the one or more UEs 102 based on one or more thresholds. Based on comparison if determined that the identified trends/patterns related to the one or more UEs 102 are deviating from the learnt historical trends/patterns related to the one or more UEs 102, then in response to determination the predicting unit 212 infers the deviation as the predicted abnormalities associated with the one or more UEs 102.
[0069] For example, let us assume that usually traffic pertaining to the one or more UEs 102 flows from location A to location B. In one scenario, let us assume due to low network, the traffic flow deviates from the location A to a location C, due to the deviation the predicting unit 212 infers the deviation as the predicted abnormalities associated with the one or more UEs 102.
[0070] In another example, let us assume that the UE 102 is the IOT device which is connected to a cell tower in order to monitor the power consumption of the cell tower. Depending on the pre-defined or pre-configured parameters such as threshold of response time of the IOT device set by the consumer, the IOT device required to provide the report of the power consumption of the cell tower to the consumers (in one hour). Herein, the consumer sets the threshold based on the learnt historical trends/patterns related to the one or more UEs based on historical data. In one situation when the IOT device takes more time than 1 hour (predefined threshold) then the predicting unit 212 detect the abnormalities or abnormal behavior of the IOT device.
[0071] Upon predicting the abnormalities, the generating unit 214 of the processor 202 is configured to generate recommendations related to the predicted abnormalities. For example, let us assume that ideally the traffic flow from the location A to the location B. Due to the low network, the traffic flow deviates from the location A to the location C. Herein, based on historical one or more actions taken by the consumer to resolve the predicted abnormality, the generating unit 214 generates recommendations such as increase the network strength which enables the traffic to flow from the location A to the location B. In one embodiment, the CE 112 may be the UE 102 where the consumer can check for the abnormalities related to the CE 112. For example, if the UE 102 is IOT device then, the consumer can perform prediction process using the UI of the IOT device.
[0072] Upon predicting the abnormalities, the transceiver unit 216 of the processor 202 is configured to transmit recommendations pertaining to the predicted abnormalities to the consumer to initiate one or more actions. In particular, the transceiver unit 214 transmits recommendations pertaining to the predicted abnormalities to the CE 112 of the consumer to initiate the one or more actions. Herein, the recommendations are transmitted to the consumer to resolve the predicted abnormalities. In one embodiment, the one or more actions includes at least one of, but not limited to, redirect traffic to another path, and adjust network setting such as improving network strength.
[0073] In one embodiment, based on the one or more actions initiated by the consumer, the AI/ML model 220 learns the one or more actions taken by the consumer to resolve the predicted abnormalities and keeps on updating. For example, based on a current one or more actions taken by the consumer to resolve the predicted abnormalities, the AI/ML model 220 learns the one or more actions taken by the consumer so that whenever in future such kind of abnormalities are predicted, the generating unit 214 can to generate recommendations utilizing the AI/ML model 220.
[0074] In an alternate embodiment, the generating unit 214 is configured to generate the recommendations regarding the predicted abnormalities and transceiver unit 216 is configured to notify at least one of, the service, the microservice, and the application. For example, the transceiver unit 216 is configured to notify the predicted abnormalities by transmitting an acknowledgment to one of, the service, the microservice, the application using a handling unit 222. The handling unit 222 is configured to keep a record of mappings of interaction of the entities (such as the service, microservice, application, component) with the system 108. Mappings of the interaction of the entities with the system 108 pertains to at least one of, the entities transmitting commands and/or requests to the system 108 to predict abnormalities. Based on the mapping, the handling unit 222 informs the transceiver unit 216 to which entity the acknowledgment has to be transmitted pertaining to the predicted abnormalities. For example, let us consider that the microservice 1 had transmitted the request at the system 108 to predict abnormalities, the handling unit 222 keeps a track of this event. Basis which, the handling unit 222 informs the transceiver unit 216 to transmit the acknowledgment (response) to the microservice 1 pertaining to the predicted abnormalities.
[0075] The retrieving unit 208, the training unit 210, the predicting unit 212, the generating unit 214, the transceiver unit 216, and the handling unit 222 in an exemplary embodiment, are implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processor 202. In the examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the processor 202 may be processor-executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the processor may comprise a processing resource (for example, one or more processors), to execute such instructions. In the present examples, the memory 204 may store instructions that, when executed by the processing resource, implement the processor 202. In such examples, the system 108 may comprise the memory 204 storing the instructions and the processing resource to execute the instructions, or the memory 204 may be separate but accessible to the system 108 and the processing resource. In other examples, the processor 202 may be implemented by electronic circuitry.
[0076] FIG. 3 illustrates an exemplary architecture for the system 108, according to one or more embodiments of the present invention. More specifically, FIG. 3 illustrates the system 108 for predicting abnormalities in the network 106. It is to be noted that the embodiment with respect to FIG. 3 will be explained with respect to CE 112 for the purpose of description and illustration and should nowhere be construed as limited to the scope of the present disclosure.
[0077] FIG. 3 shows communication between the CE 112, the system 108, and the plurality of sources 110. For the purpose of description of the exemplary embodiment as illustrated in FIG. 3, the CE 112, uses network protocol connection to communicate with the system 108, and the plurality of sources 110. In an embodiment, the network protocol connection is the establishment and management of communication between the CE 112, the system 108, and the plurality of sources 110 over the network 106 (as shown in FIG. 1) using a specific protocol or set of protocols. The network protocol connection includes, but not limited to, Session Initiation Protocol (SIP), System Information Block (SIB) protocol, Transmission Control Protocol (TCP), User Datagram Protocol (UDP), File Transfer Protocol (FTP), Hypertext Transfer Protocol (HTTP), Simple Network Management Protocol (SNMP), Internet Control Message Protocol (ICMP), Hypertext Transfer Protocol Secure (HTTPS) and Terminal Network (TELNET).
[0078] In an embodiment, the CE 112 includes a primary processor 302, and a memory 304 and a User Interface (UI) 306. In alternate embodiments, the CE 112 may include more than one primary processor 302 as per the requirement of the network 106. The primary processor 302, may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, single board computers, and/or any devices that manipulate signals based on operational instructions.
[0079] In an embodiment, the primary processor 302 is configured to fetch and execute computer-readable instructions stored in the memory 304. The memory 304 may be configured to store one or more computer-readable instructions or routines in a non-transitory computer-readable storage medium, which may be fetched and executed for predicting abnormalities in the network 106. The memory 304 may include any non-transitory storage device including, for example, volatile memory such as RAM, or non-volatile memory such as disk memory, EPROMs, FLASH memory, unalterable memory, and the like.
[0080] In an embodiment, the User Interface (UI) 306 includes a variety of interfaces, for example, a graphical user interface, a web user interface, a Command Line Interface (CLI), and the like. The UI 306 of the CE 112 allows the consumer to transmit requests to the one or more processors 202 to predict abnormalities in the network 106 and receive recommendations from the one or more processors 202 pertaining to the predicted abnormalities. In one embodiment, the consumer may be at least one of, but not limited to, a network operator.
[0081] As mentioned earlier in FIG.2, the system 108 includes the processors 202, the memory 204 and the storage unit 206, for predicting abnormalities in the network 106, which are already explained in FIG. 2. For the sake of brevity, a similar description related to the working and operation of the system 108 as illustrated in FIG. 2 has been omitted to avoid repetition.
[0082] Further, as mentioned earlier the processor 202 includes the retrieving unit 208, the training unit 210, the predicting unit 212, the generating unit 214, the transceiver unit 214, and the handling unit 222 which are already explained in FIG. 2. Hence, for the sake of brevity, a similar description related to the working and operation of the system 108 as illustrated in FIG. 2 has been omitted to avoid repetition. The limited description provided for the system 108 in FIG. 3, should be read with the description provided for the system 108 in the FIG. 2 above, and should not be construed as limiting the scope of the present disclosure.
[0083] FIG. 4 is an exemplary the system 108 architecture 400 for predicting abnormalities in the network 106, according to one or more embodiments of the present disclosure.
[0084] The architecture 400 includes a 5G core Network Function (NF) 402 which is at least one of the AMF and the NEF. The architecture 400 further includes a NWDAF 404, a data pre-processing unit 406, a feature extraction unit 408, the training unit 210, the predicting unit 212, an altering and response unit 410, the storage unit 206, a Graphical User Interface (GUI) 412 and data consumers 414 communicably coupled to each other via the network 106.
[0085] In one embodiment, the NWDAF 404 is the component in 5G network 106 that analyzes data received from the 5G core Network Function (NF) 402 to improve performance and provide insights. In particular, the NWDAF 404 receives the UE information from the 5G core NF 402. In one embodiment, the NWDAF 404 is inserts and receives data from the storage unit 206.
[0086] In one embodiment, the data pre-processing unit 406 receives the NWDAF 404 and preprocesses the data. For example, the data undergoes preprocessing to ensure data consistency within the system 108. In particular, the preprocessing involves tasks like data cleaning, normalization, removing unwanted data like outliers, duplicate records and handling missing values.
[0087] In one embodiment, the feature extraction unit 408 extracts data from the preprocessed data that facilitates predicting abnormalities in the network 106. For example, the features include at least one of, but not limited to, traffic patterns, latency and packet loss.
[0088] In one embodiment, the training unit 210 periodically receives the features from the feature extraction unit 408. The features act as the input stream which is crucial for training the AI/ML model 220. Subsequent to training, the trained AI/ML model 220 is utilized by the predicting unit 212 for predicting abnormalities in the network 106. Herein the predicting unit 212 generates output pertaining to the predicted abnormalities.
[0089] In one embodiment, the alerting and response unit 410 transmits alerts and response related to the outputs generated by the predicting unit 216 to the GUI. In one embodiment, the alerts and response further includes recommendations pertaining to the predicted abnormalities to initiate one or more actions for resolving the predicted abnormalities.
[0090] In one embodiment, the storage unit 206 includes a structured collection of the preprocessed data, and the output generated by predicting unit 212, which are managed and organized in a way that allows system 108 for easy access, retrieval, and manipulation. Herein, the system 108 inserts and receives data from the storage unit 206. The storage unit 206 is used to store, manage, and retrieve large amounts of information efficiently.
[0091] In one embodiment, the GUI 412 provides a visual representation of the outputs generated from the predicting unit 216. The GUI 412 provides a unified view to the consumer that enables comprehensive analysis. The visual representation includes at least one of, but not limited to, a tabular format and a graphical format.
[0092] In one embodiment, the data consumers 414 are the network operators which has subscribed to the NWDAF 404 in order to predict abnormalities.
[0093] FIG. 5 is a signal flow diagram illustrating the flow for predicting abnormalities in the network 106, according to one or more embodiments of the present disclosure.
[0094] At step 502, the system 108 retrieves data from the plurality of sources 110. For example, the data associated with the one or more UEs 102 is retrieved by the system 108 from the AMF. In one embodiment, the system 108 transmits at least one of, but not limited to, a Hyper Text Transfer Protocol (HTTP) request to the plurality of sources 110 to retrieve the data. In one embodiment, a connection is established between the system 108 and the plurality of sources 110 before retrieving data. Further, the retrieved data is preprocessed and the one or more features from the preprocessed data by the system 108.
[0095] At step 504, the system 108 trains the AI/ML model 220 with the retrieved data to identify trends/patterns related to the one or more UEs 102.
[0096] At step 506, the system 108 predicts abnormalities associated with the identified trends/patterns of the one or more UEs 102 in the network 106 utilizing the trained AI/ML model 220. Herein, the system 108 generates output related to the prediction of abnormalities when the identified trends/patterns deviate in comparison to the learnt historical trends/patterns related to the one or more UEs 102.
[0097] At step 508, the system 108 transmits the recommendations pertaining to the predicted abnormalities to the consumer to initiate one or more actions. Herein, the system 108 transmits the recommendations to the user by at least one of, but not limited to, the HTTP request. The recommendations are transmitted to the consumer to resolve the predicted abnormalities. Further, the user can view the recommendations, and the output generated by system 108 pertaining to the predicted abnormalities on the UI 306 of the one or more UEs 102.
[0098] FIG. 6 is a flow diagram of a method 600 for predicting abnormalities in the network 106, according to one or more embodiments of the present invention. For the purpose of description, the method 600 is described with the embodiments as illustrated in FIG. 2 and should nowhere be construed as limiting the scope of the present disclosure.
[0099] At step 602, the method 600 includes the step of retrieving data pertaining to one or more UEs 102 from a plurality of sources 110. In one embodiment, the retrieving unit 208 retrieves the data from the plurality of sources 110. In particular, the retrieving unit 208 utilizes the one or more APIs for retrieving the data from the plurality of sources 110. Further, the retrieved data is preprocessed by the retrieving unit 208 to ensure the data consistency and quality within the system 108.
[00100] At step 604, the method 600 includes the step of training the AI/ML model 220 with the retrieved data to identify trends/patterns related to the one or more UEs 102. For example, let us consider the retrieved data as the dataset which includes data related to the one or more UEs 102. Then, the training unit 210 splits the dataset into the training data and the testing data such as 75% of the dataset is considered as the training data and the 25% of the dataset is considered as the testing data. Thereafter, the training data is fed to each of the AI/ML model 220 for training. Based on training the AI/ML model 220 learns the trends/patterns related to the one or more UEs 102.
[00101] At step 606, the method 600 includes the step of predicting, utilizing the trained AI/ML model 220, abnormalities associated with the identified trends/patterns of the one or more UEs 102 in the network 106. In one embodiment, the predicting unit 212 predicts abnormalities associated with the identified trends/patterns of the one or more UEs 102 in the network 106. In one embodiment, the predicting unit 212 predicts abnormalities by determining whether there is a deviation in the identified trends/patterns in comparison to the learnt historical trends/patterns related to the one or more UEs 102. Based on determination, the predicting unit 212 infers the deviation as the predicted abnormalities associated with the one or more UEs 102.
[00102] At step 608, the method 600 includes the step of generating recommendations pertaining to the predicted abnormalities. In one embodiment, the generating unit 214 generates the recommendations pertaining to the predicted abnormalities based on historical one or more actions taken for resolving abnormalities.
[00103] In one embodiment, the transceiver unit 216 transmits recommendations pertaining to the predicted abnormalities to the consumer to initiate one or more actions. For example, let us assume that usually traffic pertaining to the one or more UEs 102 flows from location A to location B and due to low network, the traffic flow deviates from the location A to a location C which is considered as the predicted abnormalities associated with the one or more UEs 102. Based on the predicted abnormalities, the system 108 recommends to at least one of, but not limited to, upgrade the network 106, improve coverage of cells, and improve load balancing. In one embodiment, the recommendations are represented to the consumer on the UI 306.
[00104] In yet another aspect of the present invention, a non-transitory computer-readable medium having stored thereon computer-readable instructions that, when executed by a processor 202. The processor 202 is configured to retrieve data pertaining to one or more User Equipment’s (UEs) 102 from a plurality of sources 110. The processor 202 is further configured to train a model 220 with the retrieved data to identify trends/patterns related to the one or more UEs 102. The processor 202 is further configured to predict, utilizing the trained model 220, abnormalities associated with the identified trends/patterns of the one or more UEs 102 in the network 106. The processor 202 is further configured to generate recommendations pertaining to the predicted abnormalities.
[00105] A person of ordinary skill in the art will readily ascertain that the illustrated embodiments and steps in description and drawings (FIG.1-6) are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments.
[00106] The present disclosure provides technical advancements where the system predicts abnormalities in the network spontaneously without the consumer request. The system predicts abnormalities based on historical trends that have occurred in one or more UEs. The system takes precautions measures before the occurrence of the issues due to which the system performance is enhanced.
[00107] The present invention offers multiple advantages over the prior art and the above listed are a few examples to emphasize on some of the advantageous features. The listed advantages are to be read in a non-limiting manner.

REFERENCE NUMERALS

[00108] Environment - 100;
[00109] User Equipment (UE) - 102;
[00110] Server - 104;
[00111] Network- 106;
[00112] System -108;
[00113] Plurality of sources – 110;
[00114] Consumer Equipment (CE) – 112;
[00115] Processor - 202;
[00116] Memory - 204;
[00117] Storage unit – 206;
[00118] Retrieving unit – 208;
[00119] Training unit – 210;
[00120] Predicting unit – 212;
[00121] Generating unit – 214;
[00122] Transceiver unit – 216;
[00123] AI/ML Model – 220;
[00124] Handling unit – 222;
[00125] Primary Processor – 302;
[00126] Memory – 304;
[00127] User Interface (UI) – 306;
[00128] 5G core network function (NF) – 402;
[00129] NWDAF – 404;
[00130] Data pre-processing unit - 406;
[00131] Feature extraction unit – 408;
[00132] Alerting and response unit – 410;
[00133] Graphical User Interface – 412;
[00134] Data consumers - 414.
,CLAIMS:CLAIMS
We Claim:
1. A method (600) for predicting abnormalities in a network (106), the method (600) comprising the steps of:
retrieving, by one or more processors (202), data pertaining to one or more User Equipment’s (UEs) (102) from a plurality of sources (110);
training, by the one or more processors (202), a model (220) with the retrieved data to identify trends/patterns related to the one or more UEs (102);
predicting, by the one or more processors (202), utilizing the trained model (220), abnormalities associated with the identified trends/patterns of the one or more UEs (102) in the network (106); and
generating, by the one or more processors (202), recommendations pertaining to the predicted abnormalities.

2. The method (600) as claimed in claim 1, wherein the data pertaining to the one or more UEs (102) includes at least one of, UE identifier, network activity, location, usage patterns and trends related to one or more UEs.

3. The method (600) as claimed in claim 1, wherein the plurality of sources (110) includes at least one of, but not limited to, an Access and Mobility Management Function (AMF) and a Network Exposure Function (NEF).

4. The method (600) as claimed in claim 1, wherein the step of retrieving, data pertaining to the one or more UEs (102) from the plurality of sources (110), further includes the step of:
preprocessing, by the one or more processors (202), the retrieved data; and
extracting, by the one or more processors (202), one or more features from the retrieved data.

5. The method (600) as claimed in claim 1, wherein the step of, predicting, by the one or more processors (202), utilizing the trained model (220), abnormalities associated with the identified trends/patterns of the one or more UEs (102) in the network (106), includes the step of:
determining, by the one or more processors (202), utilizing the trained model (220), whether there is a deviation in the identified trends/patterns in comparison to a learnt historical trends/patterns related to the one or more UEs (102) based on one or more thresholds; and
in repose to determination, inferring, by the one or more processors (202), the deviation as the predicted abnormalities associated with the one or more UEs (102).

6. The method (600) as claimed in claim 5, wherein the model (220) learns the historical trends/patterns related to the one or more UEs (102) based on historical data stored in a storage unit (206).

7. The method (600) as claimed in claim 1, wherein the recommendations are transmitted to the consumer to resolve the predicted abnormalities.

8. The method (600) as claimed in claim 1, wherein the generated recommendations are transmitted to the consumer to initiate one or more actions.

9. The method (600) as claimed in claim 1, wherein the one or more processors (202) retrieve data pertaining to the one or more UEs (102) from the plurality of sources (110) based on at least one of, receiving a request from the consumer and without receiving a request from the consumer.

10. The method (600) as claimed in claim 1, wherein based on the one or more actions initiated by the consumer, the model (220) learns the one or more actions taken and keeps on updating.

11. A system (108) for predicting abnormalities in a network (106), the system (108) comprising:
a retrieving unit (208), configured to, retrieve, data pertaining to one or more User Equipment’s (UEs) (102) from a plurality of sources (110);
a training unit (210), configured to, train, a AI/ML model (220) with the retrieved data to identify trends/patterns related to the one or more UEs (102);
a predicting unit (212), configured to, predict, utilizing the trained model (220), abnormalities associated with the identified trends/patterns of the one or more UEs (102) in the network (106); and
a generating unit (214), configured to, transmit recommendations pertaining to the predicted abnormalities.

12. The system (108) as claimed in claim 11, wherein the data pertaining to the one or more UEs (102) includes at least one of, UE identifier, network activity, location, usage patterns and trends related to one or more UEs.

13. The system (108) as claimed in claim 11, wherein the plurality of sources (110) includes at least one of, but not limited to, an Access and Mobility Management Function (AMF) and a Network Exposure Function (NEF).

14. The system (108) as claimed in claim 11, wherein the retrieving unit (208) is further configured to:
preprocess, the retrieved data; and
extract, one or more features from the retrieved data.

15. The system (108) as claimed in claim 11, wherein the predicting unit predicts, utilizing the trained model (220), abnormalities associated with the identified trends/patterns of the one or more UEs (220) in the network (106), by:
determining, utilizing the trained model (220), whether there is a deviation in the identified trends/patterns in comparison to a learnt historical trends/patterns related to the one or more UEs (102) based on one or more thresholds; and
in repose to determination, inferring, the deviation as the predicted abnormalities associated with the one or more UEs (102).

16. The system (108) as claimed in claim 15, wherein the model (220) learns the historical trends/patterns related to the one or more UEs (110) based on historical data stored in a storage unit (206).

17. The system (108) as claimed in claim 11, wherein the recommendations are transmitted to the consumer by a transceiver unit (216) to resolve the predicted abnormalities.

18. The system (108) as claimed in claim 11, wherein the generated recommendations are transmitted to the consumer to initiate one or more actions.

19. The system (108) as claimed in claim 11, wherein the retrieving unit (208) retrieve data pertaining to the one or more UEs (102) from the plurality of sources (110) based on at least one of, receiving a request form the consumer and without receiving a request from the consumer.

20. The system (108) as claimed in claim 11, wherein based on the one or more actions initiated by the consumer, the model (220) learns the one or more actions taken and keeps on updating.

21. A Consumer Equipment (CE) (112), comprising:
one or more primary processors (302) communicatively coupled to one or more processors (202), the one or more primary processors (302) coupled with a memory (304), wherein said memory (304) stores instructions which when executed by the one or more primary processors (302) causes the CE (112) to:
receive, recommendations pertaining to the predicted abnormalities form the one or more processors (202);
wherein the one or more processors (202) is configured to perform the steps as claimed in claim 1.