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 TRAINING A MODEL USING DATA IN A CENTRALIZED DATA STORAGE UNIT
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 training a model using data in a centralized data storage unit.
BACKGROUND OF THE INVENTION
[0002] In traditional telecommunications networks, the models are trained using the various data in order to perform may be any analysis, predictions, detect anomaly, etc.
[0003] However, the data required for model training may be stored across different databases and storage systems. Further, in order to access relevant and diverse data from the different databases and storage systems for training models is a challenging and time-consuming task. This may lead to delays in model updates and decision-making.
[0004] There is, therefore, a dire need for a system and a method for a centralized data storage that ensures enhanced consumer’s experience.
SUMMARY OF THE INVENTION
[0005] One or more embodiments of the present disclosure provides a method and a system for training a model using data in a centralized data storage unit.
[0006] In one aspect of the present invention, the method for training the model using data in the centralized data storage unit is disclosed. The method includes the step of establishing, by one or more processors, one or more connections with one or more data sources. The method further includes the step of retrieving, by the one or more processors, data from the one or more data sources based on the established one or more connections. The method further includes the step of formatting, by the one or more processors, the data to align with an acceptable format. The method further includes the step of storing, by the one or more processors, the formatted data in a centralized data storage unit. The method further includes the step of preprocessing, by the one or more processors, the formatted data stored in the centralized data storage unit. The method further includes the step of training, by the one or more processors, a model with the pre-processed data.
[0007] In another embodiment, the one or more processors, establishes one or more connections with the one or more data sources using one or more Application Programming Interfaces (APIs).
[0008] In yet another embodiment, the one or more data sources include at least one of, cell towers, network functions, network elements, network performance data, subscriber data, device data, competitor data, social media data, customer feedback and surveys.
[0009] In yet another embodiment, the acceptable format is the format which is suitable for training the model.
[0010] In yet another embodiment, the one or more processors, formats the data to align with the acceptable format using the one or more APIs.
[0011] In yet another embodiment, the centralized data storage is at least one of, a Network Attached Storage (NAS).
[0012] In yet another embodiment, the preprocessing the formatted data, includes operations performed on the formatted data including at least one of, data cleaning, correcting data errors, data transformation and data normalization.
[0013] In yet another embodiment, the step of training, the model with the pre-processed data includes the step of identifying, one or more patterns/trends from the pre-processed data, wherein the one or more patterns/trends pertain to ideal patterns/trends in a network environment without an anomaly.
[0014] In yet another embodiment, the subsequent to performing the step of, training, a model with the pre-processed data, the method further includes the steps of determining, by the one or more processors, utilizing the trained model, one or more anomalies when current data deviates from the patterns/trends of the pre-processed data. Further, generating, by the one or more processors, alerts and/or notifications pertaining to the determined one or more anomalies. Thereafter, recommending, by the one or more processors, one or more actions to address the determined one or more anomalies.
[0015] In another aspect of the present invention, the system for training a model using data in a centralized data storage unit is disclosed. The system includes a connection establishing unit, configured to, establish, one or more connections with one or more data sources. The system further includes a retrieving unit, configured to, retrieve, data from the one or more data sources based on the established one or more connections. The system further includes a formatting unit, configured to, format, the data to align with an acceptable format. Further, the formatting unit is configured to store the formatted data in a centralized data storage unit. The system further includes a preprocessing unit, configured to, preprocess, the formatted data stored in the centralized data storage unit. The system further includes a training unit, configured to, train a model with the pre-processed data.
[0016] 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 establish, one or more connections with one or more data sources. The processor is further configured to retrieve, data from the one or more data sources based on the established one or more connections. The processor is further configured to format, the data to align with an acceptable format. The processor is further configured to store the formatted data in a centralized data storage unit. The processor is further configured to preprocess, the formatted data stored in the centralized data storage unit. The processor is further configured to train a model with the pre-processed data.
[0017] 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
[0018] 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.
[0019] FIG. 1 is an exemplary block diagram of an environment for training a model using data in a centralized data storage unit, according to one or more embodiments of the present invention;
[0020] FIG. 2 is an exemplary block diagram of a system for training the model using data in the centralized data storage unit, according to one or more embodiments of the present invention;
[0021] FIG. 3 is an exemplary architecture of the system of FIG. 2, according to one or more embodiments of the present invention;
[0022] FIG. 4 is an exemplary architecture for training the model using data in the centralized data storage unit, according to one or more embodiments of the present disclosure;
[0023] FIG. 5 is an exemplary signal flow diagram illustrating the flow for training the model using data in the centralized data storage unit, according to one or more embodiments of the present disclosure; and
[0024] FIG. 6 is a flow diagram of a method for training the model using data in the centralized data storage unit, according to one or more embodiments of the present invention.
[0025] The foregoing shall be more apparent from the following detailed description of the invention.
DETAILED DESCRIPTION OF THE INVENTION
[0026] 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.
[0027] 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.
[0028] 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.
[0029] Various embodiments of the present invention provide a system and a method for training a model using data in a centralized data storage unit. The present invention integrates Network-Attached Storage (NAS) as the centralized data storage unit for training the model. The integration of the centralized data storage unit with the system allows for real-time or near-real-time analytics and model training, which is critical for proactively addressing network issues, optimizing resource allocation, and ensuring a high-quality consumers experience. The centralized data storage unit simplifies data management and reduces the complexity of maintaining data across multiple sources.
[0030] Referring to FIG. 1, FIG. 1 illustrates an exemplary block diagram of an environment 100 for training a model 220 using data in a centralized data storage unit 112, according to one or more embodiments of the present invention. The environment 100 includes a User Equipment (UE) 102, a server 104, a network 106, a system 108, one or more data sources 110 and the centralized data storage unit 112.
[0031] 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.
[0032] 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, 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.
[0033] 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.
[0034] 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.
[0035] 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.
[0036] The environment 100 further includes the one or more data sources 110. In one embodiment, the data sources are origins from which the data is collected and utilized for at least one of, but not limited to, analysis, research, and decision-making. In one embodiment, the one or more data sources 110 is at least one of, but not limited to, cell towers, network functions, network elements, network performance data, subscriber data, UE 102 data, competitor data, social media data, customer feedback and surveys. In particular, the one or more data sources 110 is associated with the sources included within the network 106 and outside the network 106.
[0037] The environment 100 further includes the centralized data storage unit 112. As per the illustrated embodiment, the centralized data storage unit 112 is configured to store data retrieved from the one or more data sources 110. In an embodiment, the centralized data storage unit 112 is a dedicated device or storage server that is connected to the network 106 which provides a centralized data storage and file sharing services to multiple consumers within the network 106. In one embodiment, the centralized data storage unit 112 is configured to store ingested data or formatted data. The centralized data storage unit 112 also stores an output generated by the model 220.
[0038] The centralized data storage unit 112 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 centralized data storage unit 112 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.
[0039] The environment 100 further includes the system 108 communicably coupled to the server 104, the UE 102, the one or more data sources 110 and the centralized data storage unit 112 is via the network 106. The system 108 is adapted to be embedded within the server 104 or is embedded as the individual entity.
[0040] Operational and construction features of the system 108 will be explained in detail with respect to the following figures.
[0041] FIG. 2 is an exemplary block diagram of the system 108 for training the model 220 using data in the centralized data storage unit 112, according to one or more embodiments of the present invention.
[0042] As per the illustrated and preferred embodiment, the system 108 for training the model 220 using data in the centralized data storage unit 112, includes one or more processors 202, a memory 204, and the 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.
[0043] 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 training the model 220 using data in the centralized data storage unit 112. 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.
[0044] As per the illustrated embodiment, the system 108 includes the model 220. Herein, the model 220 is at least one of, but not limited to, an Artificial Intelligence/Machine Leaning (AI/ML) model. In an alternate embodiment, the system 108 includes a plurality of models 220. The model 220 is a machine learning model that performs tasks such as recognizing patterns, making predictions, and solving problems, enhance decision-making, and provide insights across various fields. For example, the model 220 facilitates in solving real-world problems without extensive manual intervention.
[0045] As per the illustrated embodiment, the system 108 includes the processor 202 for training the model 220 using data in the centralized data storage unit 112. The processor 202 includes a connection establishing unit 208, a retrieving unit 210, a formatting unit 212, a preprocessing unit 214, a training unit 216, and a determining unit 218. The processor 202 is communicably coupled to the one or more components of the system 108 such as the memory 204, and the model 220. In an embodiment, operations and functionalities of the connection establishing unit 208, the retrieving unit 210, the formatting unit 212, the preprocessing unit 214, the training unit 216, the determining unit 218 and the one or more components of the system 108 can be used in combination or interchangeably.
[0046] In one embodiment, initially the connection establishing unit 208 of the processor 202 is configured to establish one or more connections with the one or more data sources 110. The one or more connections between the processor 202 and the one or more data sources 110 includes at least one of, but not limited to, a Transmission Control Protocol (TCP) connection. In an embodiment, the TCP is a connection-oriented protocol for communications that facilitates the exchange of data or messages between the processor 202 of the system 108 and the one or more data sources 110 in the network 106.
[0047] In one embodiment, the connection establishing unit 208 establishes one or more connections with the one or more data sources 110 using at least one of, but not limited to, a TCP 3-Way Handshake process. In particular, the TCP 3-Way Handshake process used in the TCP to establish a reliable connection between the processor 202 and the one or more data sources 110 before data transmission begins. The TCP 3-Way Handshake process ensures that both parties are synchronized and ready for communication.
[0048] For example, when the system 108 wants to establish the one or more connections with the one or more data sources 110, the connection establishing unit 208 transmits a synchronize (SYN) packet/request to the one or more data sources 110 to initiate the one or more connections establishment process. The SYN packet includes a sequence number. Further, the one or more data sources 110 responds with a synchronize-acknowledge (SYN-ACK) packet, acknowledging the SYN packet/request of the connection establishing unit 208. The connection establishing unit 208 transmits an acknowledge (ACK) packet back to the one or more data sources 110, confirming receipt of the server’s SYN-ACK which completes the handshake. Herein, the one or more connections are established between the system 108 and the one or more data sources 110 via which the communication takes place.
[0049] In one embodiment, the connection establishing unit 208 establishes the one or more connections with the one or more data sources 110 using one or more Application Programming Interfaces (APIs). 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.
[0050] Upon establishing the one or more connections with the one or more data sources 110, the retrieving unit 210 of the processor 202 is configured to retrieve data from the one or more data sources 110 based on the established one or more connections. In one embodiment, the retrieving unit 210 retrieves data from the one or more data sources 110 via the one or more APIs which are used for establishing the one or more connections with the one or more data sources 110. In particular, the data from the one or more data sources 110 is retrieved to train the model 220. Herein, the retrieving unit 210 retrieves data from the one or more data sources 110 which are present within the network 106 and outside the network 106. In one embodiment, the retrieved data include at least one of, but not limited to, network performance data, historical data related to the model 220, subscriber data, UE 102 data, competitor data, social media data, customer feedback and surveys.
[0051] Upon retrieving the data from the one or more data sources 110, the formatting unit 212 of the processor 202 is configured to format the retrieved data to align with an acceptable format. Herein the acceptable format is the format which is suitable for training the model 220. In one embodiment, the data retrieved from the one or more data sources 110 are in different formats such as at least one of, but not limited to, plain text, Hyper Text Markup Language (HTML), binary, Comma-Separated Values (CSV), eXtensible Markup Language (XML), JavaScript Object Notation (JSON) and images. In one embodiment, the acceptable format for training the model 220 includes at least one of, but not limited to, the HTML, the XML, the CSV and the JSON. Herein, the formatting unit 212 includes at least one of, a data ingestion layer that converts and structures the data retrieved from the one or more sources 110 into the acceptable format using the one or more APIs which ensures that retrieved data is consistent, standardized, and ready to be used effectively.
[0052] In one embodiment, formatting the retrieved data using the one or more APIs typically involves structuring and preparing data for transmission or storage in such a way that the formatted data is easily understandable by both a sender and a receiver. Initially, the one or more APIs identifies the different formats of the retrieved data from the one or more data sources 110. Thereafter, the one or more APIs performs the data serialization process, which converts the data into the acceptable format. In particular, the data serialization process is the process of converting the data from one format into another format. Herein, the one or more APIs includes functions or libraries to handle the data serialization process. In particular, the functions or libraries for handling the data serialization process refer to the tools and methods used to convert complex data structures (like objects, arrays, or lists) into the format that can be easily stored or transmitted, and then reconstructed later.
[0053] For example, let us assume that the retrieved data is in XML format and the acceptable format is in the JSON format. So, in order to convert the retrieved data from the XML data into the JSON format, the retrieved data is parsed which involves reading the retrieved data and breaking the retrieved data into at least one of, but not limited to, elements and attributes. The attributes are data objects containing one or more key-value pairs and arrays and the elements are used as a container to store text, elements, and attributes. Herein, if the XML data is , Alice then the id and the gender are attributes and the name is element. Further, the XML elements and attributes are mapped with the JSON elements and attributes. Thereafter, using the libraries, the XML format is converted in the JSON format.
[0054] Upon formatting the retrieved data, the formatting unit 212 of the processor 202 is further configured to store the formatted data in the centralized data storage unit 112. Herein, the centralized data storage unit 112 is at least one of, but not limited to, a Network Attached Storage (NAS). In one embodiment, the system 108 communicates with the centralized data storage unit 112 using at least one of, but not limited to, a File Transfer Protocol (FTP) and a file Access and file operations methods. Once the system 108 establishes connection with the centralized data storage unit 112, the system 108 may read and write data to and from the centralized data storage unit 112. In one embodiment, the centralized data storage unit 112 acts as a central data source for training the model 220. In particular, the centralized data storage unit 112 serves as a repository for storing diverse data types, historical records, and real-time data streams.
[0055] Upon storing the formatted data in the centralized data storage unit 112, the preprocessing unit 214 of the processor 202 is further configured to preprocess the formatted data which is stored in the centralized data storage unit 112. In one embodiment, the preprocessing unit 214 is configured to preprocess the formatted data to ensure the data consistency and quality within the system 108. Herein, the preprocessing includes operations performed on the formatted data such as at least one of, but not limited to, data cleaning, correcting data errors, data transformation and data normalization.
[0056] In one embodiment, while preprocessing the preprocessing unit 214 performs at least one of, but not limited to, reorganizing the formatted data, removing the redundant data within the formatted data, removing null values from the formatted data, handling missing values from the formatted data. The main goal of the the preprocessing unit 214 is to achieve a standardized data format of the formatted data with no errors. The preprocessing unit 214 eliminates duplicate data from the formatted data and inconsistencies which reduces manual efforts. The preprocessing unit 214 ensures that the pre-processed data is stored appropriately in at least one of, the centralized data storage unit 112 and the pre-processed data is ready for subsequent retrieval and model 220 training.
[0057] Upon preprocessing the formatted data, the training unit 216 of the processor 202 is configured to train the model 220 with the pre-processed data stored in the centralized data storage unit 112. In one embodiment, for training the model 220, instead of retrieving the data from the one or more sources 110, the training unit 216 retrieves the pre-processed data from the centralized data storage unit 112 which leads to reduction in the time consumption for retrieving data or data transferring for training the model 220. Due to the retrieval of the pre-processed data from the centralized data storage unit 112 and utilization of the pre-processed data for training the model 220, the time consumption for training the model 220 is reduced.
[0058] In an alternate embodiment, the system 108 includes a plurality of models 220 from which the training unit 216 selects an appropriate model 220 for training. Thereafter, the selected model 220 is trained using the pre-processed data stored in the centralized data storage unit 112.
[0059] In one embodiment, for training the model 220, the training unit 216 splits the pre-processed data into at least one of, but not limited to, training data and testing data. Further, the training unit 216 feeds the training data to the model 220. Based on the fed training data, the model 220 learns one or more trends/patterns in the fed training data. Subsequent to training, the trained model 220 is fed with the testing data to evaluate performance of the trained model 220. When the trained model 220 generates an output based on the testing data, the training unit 216 evaluates the performance of the trained model 220. In one embodiment, the output generated by the trained model 220 is again fed back to the trained model 220 by the training unit 216, so that based on the output generated, the trained model 220 is trained again. In particular, after generating the output, the model 220 keeps on training and updating itself in order to achieve better output.
[0060] In one embodiment, based on the evaluation of the performance of the trained model 220, the training unit 216 may tune one or more hyperparameters of the trained model 220 to optimize the performance of the trained model 220. Herein, the one or more hyperparameters of the trained model 220 includes at least one of, but not limited to, a learning rate, a batch size, and a number of epochs. In one embodiment, when the performance of the trained model 220 is optimized, then the trained model 220 is used for one or more use cases such as at least one of, but not limited to, a network performance prediction, a subscriber behavior analysis, issue detection or one or more anomalies detection.
[0061] In one embodiment, based on training, the trained model 220 identifies at least one of, but not limited to, one or more patterns/trends, and behavior in the network 106 by applying one or more logics. 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.
[0062] Herein, the identified one or more patterns/trends, and behavior pertains to ideal one or more patterns/trends in the network 106 environment without an anomaly. In one embodiment, the trends refer to a general direction or pattern of change observed over time within a specific dataset (pre-processed data) or network environment. For example, trends facilities in identifying increase or decrease in a traffic over time in the network 106.
[0063] Herein, the patterns are recurring regularities observed in network data. For example, a number of Hyper Text Transfer Protocol (HTTP) requests received in the network 106 are more as compared to the other requests received in the network 106. In one embodiment, the behavior refers to how users and one or more components such as the system 108, the one or more data sources 110 and the centralized data storage unit 112 interacts within the network 106. For example, when the at least one source among the one or more sources 110 suddenly transmits multiple requests to the system 108 then the behavior of the at least one source among the one or more sources 110 is indicated as security threats. In one embodiment, the identified one or more patterns/trends, and behavior aid in identifying one or more anomalies or potential issues.
[0064] Upon training the model 220 with the pre-processed data, the trained model 220 is utilized for determining at least one of, but not limited to, one or more anomalies in the network 106. In one embodiment the determining unit 218 is configured to determine at least one of, but not limited to, the one or more anomalies in the network 106. In order to determine the one or more anomalies, the determining unit 218 utilizes the trained model 220 to identify patterns/trends of current data which is continuously received at the system 108 from the centralized data storage unit 112. Herein, the current data is associated with the one or more data sources 110. Further, the determining unit 218 compares the identified patterns/trends of the current data with the ideal patterns/trends associated with the one or more data sources 110 which are set by the trained model 220. Based on the comparison, if the determining unit 218 determines that current data deviates from the ideal patterns/trends associated with the data, then the determining unit 218 infers the deviation as the one or more anomalies.
[0065] Upon determining the one or more anomalies, the determining unit 218 is further configured to generate alerts and/or notifications pertaining to the determined one or more anomalies for notifying the user in a real time regarding the determined one or more anomalies. In one embodiment, the user is notified on the UI 306 of the UE 102 in the real time. Further, the determining unit 218 recommends the user one or more actions to address the determined one or more anomalies. For example, the determining unit 218 recommends user to perform a Root Cause Analysis (RCA) in order to resolve the determined one or more anomalies, or to perform at least one of but not limited to, troubleshooting techniques to resolve the determined one or more anomalies without impacting the performance of the system 108 in the network 106.
[0066] The connection establishing unit 208, the retrieving unit 210, the formatting unit 212, the preprocessing unit 214, the training unit 216, and the determining unit 218 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.
[0067] 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 training the model 220 using data in the centralized data storage unit 112. It is to be noted that the embodiment with respect to FIG. 3 will be explained with respect to the UE 102 for the purpose of description and illustration and should nowhere be construed as limited to the scope of the present disclosure.
[0068] FIG. 3 shows communication between the UE 102, the system 108, the one or more data sources 110 and the centralized data storage unit 112. For the purpose of description of the exemplary embodiment as illustrated in FIG. 3, the UE 102, uses network protocol connection to communicate with the system 108, the one or more data sources 110 and the centralized data storage unit 112. In an embodiment, the network protocol connection is the establishment and management of communication between the UE 102, the system 108, the one or more data sources 110 and the centralized data storage unit 112 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).
[0069] In an embodiment, the UE 102 includes a primary processor 302, and a memory 304 and a User Interface (UI) 306. In alternate embodiments, the UE 102 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.
[0070] 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 training the model 220 using data in the centralized data storage unit 112. 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.
[0071] 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 UE 102 allows the user to transmit data to the system 108 which is stored in the centralized data storage unit 112 for training the model 220. Herein, the UE 102 act as at least one data source 110. In one embodiment, the user receives the at least one of, but not limited to, alerts and/or notifications pertaining to the determined one or more anomalies from the system 108. Further, the user receives recommendations to perform one or more actions to address the determined one or more anomalies. In one embodiment, the user may be at least one of, but not limited to, a network operator.
[0072] As mentioned earlier in FIG.2, the system 108 includes the processors 202, the memory 204, for training the model 220 using data in the centralized data storage unit 112, 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.
[0073] Further, as mentioned earlier the processor 202 includes the connection establishing unit 208, the retrieving unit 210, the formatting unit 212, the preprocessing unit 214, the training unit 216, and the determining unit 218 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.
[0074] FIG. 4 is an exemplary the system 108 architecture 400 for training the model 220 using data in the centralized data storage unit 112, according to one or more embodiments of the present disclosure.
[0075] The architecture 400 includes the one or more data sources 110, a data ingestion layer 402, a data pre-processing unit 404, a model training unit 406, a model output unit 408, an alerting and response unit 410, a user 412, the centralized data storage unit 112 and the UI 306 communicably coupled to each other via the network 106.
[0076] In one embodiment, the one or more data sources 110 are various origins from which the data is collected which are used for at least one of, analysis, model 220 training, or other purposes. In one embodiment, the data ingestion layer 402 is responsible for connecting and ingesting data from the one or more data sources 110. The data ingestion layer 402 includes connectors, data ingestion pipelines, and mechanisms for handling real-time data streams. The data ingestion involves collection of data from the one or more data sources 110 both within and outside the network 106.
[0077] In one embodiment, the data pre-processing unit 404 preprocesses the data received from the one or more data sources 110. 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.
[0078] In one embodiment, centralized data storage unit 112 includes a structured collection of pre-processed data that is managed and organized in a way that allows system 108 for easy access, retrieval, and manipulation. The centralized data storage unit 112 are used to store, manage, and retrieve large amounts of information efficiently. The centralized data storage unit 112 is the dedicated device or storage server that is connected to the network 106 and provides centralized data storage and file sharing services to multiple clients and users within the network 106.
[0079] In one embodiment, the model training unit 406 trains the model 220 using the pre-processed data stored in the centralized data storage unit 112. Due to training, the trained model 220 is used for various purposes such as making predictions, identifying the one or more anomalies, pattern recognition and issue detection etc. In one embodiment, the model output unit 408 refers to the component of the architecture responsible for generating and managing the predictions made by the trained model 220.
[0080] In one embodiment, the alerting and response unit 410 generates alerts and notifications when significant issues/patterns/one or more anomalies are identified. the alerting and response unit 410 provides the notification to the user 412 via the UI 306. Herein, the users are the network operators who analyses the data to resolve the significant issues/one or more anomalies.
[0081] FIG. 5 is a signal flow diagram illustrating the flow for training the model 220 using data in the centralized data storage unit 112, according to one or more embodiments of the present disclosure.
[0082] At step 502, the system 108 retrieves data from at least one of, the one or more data sources 110 present within the network 106 and the one or more data sources 110 present outside the network 106 for training the model 220 by transmitting at least one of, but not limited to, a HTTP request. Herein, the connection between the system 108 and the one or more data sources 110 is established before retrieving the data.
[0083] At step 504, the system 108 formats the data retrieved from the one or more data sources 110 to align with the acceptable format which is suitable for training the model 220. For example, the system 108 converts the data retrieved from the one or more data sources 110 into at least one format such as the JSON format which is suitable for training the model 220.
[0084] At step 506, the system 108 stores the formatted data in the centralized data storage unit 112. For example, when the data retrieved from the one or more data sources 110 is converted into the JSON format, the data formatted in the JSON is stored in the centralized data storage unit 112.
[0085] At step 508, the system 108 preprocess the formatted data. For example, when the model 220 is to be trained, the system 108 fetches the formatted data from the centralized data storage unit 112 by transmitting at least one of, but not limited to, the HTTP request. Further the system 108 preprocess the fetched data by at least one of, cleaning and normalizing. Herein, the system 108 makes the preprocessed ready for training the model 220.
[0086] At step 510, the system 108 trains the model 220 using the pre-processed data. In particular, the model 220 is trained to teach the model 220 to make predictions or decisions based on data.
[0087] FIG. 6 is a flow diagram of a method 600 for training the model 220 using data in the centralized data storage unit 112, 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.
[0088] At step 602, the method 600 includes the step of establishing the one or more connections with the one or more data sources 110. In one embodiment, the connection establishing unit 208 establishes the one or more connections between the system 108 and the one or more data sources 110 using the one or more APIs. For example, let us consider in order to train the model 220 the system 108 requires the data. So, based on the requirement, the system 108 establishes the one or more connections with the one or more data sources 110.
[0089] At step 604, the method 600 includes the step of retrieving the data from the one or more data sources 110 based on the established one or more connections. In one embodiment, the retrieving unit 210 retrieves the data from the one or more data sources 110. In particular, the retrieving unit 210 utilizes the APIs for retrieving the data received from the one or more data sources 110. For example, the retrieving unit 210 retrieves data from at least one of, but not limited to, the cell towers, and network functions. Herein, the data is at least one of, but not limited to, the network performance data, the subscriber data, the UE 102 data.
[0090] data received from the data sources 110 is combined by the retrieving unit 210. Thereafter, the integrated data is preprocessed by the the preprocessing unit 214 to ensure the data consistency and quality within the system 108. Herein, preprocessing of the integrated data includes at least one of, but not limited to, data cleaning, normalization, and handling missing values.
[0091] At step 606, the method 600 includes the step of formatting the data to align with the acceptable format. In one embodiment, the formatting unit 212 formats the retrieved data from the one or more data sources 110 to align with the acceptable format. For example, let us consider that the acceptable format for training the model 220 is the JSON format. Herein, the data retrieved from the one or more data sources 110 are in various formats such as at least one of, the XML and the CSV. So, the formatting unit 212 converts the data format such as XML and the CSV into the JSON format.
[0092] At step 608, the method 600 includes the step of storing, the formatted data in the centralized data storage unit 112. In one embodiment, the formatting unit 212 stores the formatted data in the centralized data storage unit 112. For example, the converted JSON format data is stored in the centralized data storage unit 112 for subsequent usage and analysis. In particular, the real time data associated with the one or more data sources 110 is stored in the centralized data storage unit 112. Advantageously, the data retrieved from the one or more data sources 110 are available in one place, due to which there is no need for the system 108 to connect with one or more data sources 110 for the data which is required for training the model 220. Due to the centralized data storage unit 112 the time required for retrieving the data from the one or more data sources 110 is reduced.
[0093] At step 610, the method 600 includes the step of preprocessing, the formatted data stored in the centralized data storage unit 112. In one embodiment, the preprocessing unit 214 preprocesses the formatted data stored in the centralized data storage unit 112. While preprocessing, the preprocessing unit 214 ensures that the data formats are consistent. In particular, the preprocessing is performed to prepare the data with no inconsistencies and errors so that the pre-processed data is utilized for the model 220 training. For example, let us assume that the preprocessing unit 214 preprocesses text data. While preprocessing, the preprocessing unit 214 converts the text into all lowercase and removes the duplicate text. Further, the preprocessing unit 214 stores the pre-processed data in the centralized data storage unit 112.
[0094] At step 612, the method 600 includes the step of training the model 220 with the pre-processed data. In one embodiment, the training unit 216 trains the model 220 with the pre-processed data. Based on training, the trained model 220 identifies at least one of, but not limited to, one or more patterns/trends associated with the preprocessed data. Herein, the training unit 216 infers the identified one or more patterns/trends as the ideal one or more patterns/trends in the network environment without an anomaly.
[0095] Subsequent to training the model 220 with the pre-processed data, the trained model 220 is utilized to determine at least one of, but not limited to, the one or more anomalies in the network 106. In one embodiment, the determining unit 218 utilizes the trained model 220 to determine the one or more anomalies in the network 106. For example, let us assume the real time data associated with the one or more data sources 110 is continuously updated in the centralized data storage unit 112 and based on training, the trained model 220 had set ideal patterns/trends associated with the one or more data sources 110. Herein, the determining unit 218 determines the one or more anomalies using the trained model 220 when the real time data or current data associated with the one or more data sources 110 deviates from the ideal patterns/trends associated with the data of the one or more data sources 110.
[0096] Based on the determined one or more anomalies, the determining unit 218 generates alerts and/or notifications pertaining to the determined one or more anomalies and notifies the user regarding the determined one or more anomalies on the UI 306. The notification provided to the user also includes the recommendation to perform the one or more actions to address the determined one or more anomalies.
[0097] 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 establish one or more connections with one or more data sources 110. The processor 202 is further configured to retrieve data from the one or more data sources 110 based on the established one or more connections. The processor 202 is further configured to format the data to align with an acceptable format. The processor 202 is further configured to store the formatted data in the centralized data storage unit 112. The processor 202 is further configured to preprocess the formatted data stored in the centralized data storage unit 112. The processor 202 is further configured to configured to train the model 220 with the pre-processed data.
[0098] 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.
[0099] The present disclosure provides technical advancements of centralized data management as the centralized storage unit provides a centralized and easily accessible location for storing training data. The centralization simplifies data management and reduces the complexity of maintaining data across multiple sources. The data consistency is ensured as data is stored in one place such as the centralized storage unit. In the centralized storage unit, all network performance metrics from different regions and time periods are organized uniformly, reducing the chances of inconsistencies due to data formatting or naming variations. The centralized storage unit enables efficient and rapid access to training data. Models retrieves data directly from the centralized storage unit, reducing data transfer times and improving overall model training efficiency. The centralized storage unit supports real-time data integration for timely insights. Network performance data is continuously streamed to the centralized storage unit, allowing the model to incorporate real-time network performance updates into its predictions.
[00100] 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

[00101] Environment - 100;
[00102] User Equipment (UE) - 102;
[00103] Server - 104;
[00104] Network- 106;
[00105] System -108;
[00106] One or more data sources – 110;
[00107] Centralized data storage unit – 112;
[00108] Processor - 202;
[00109] Memory - 204;
[00110] Connection establishing unit – 208;
[00111] Retrieving unit – 210;
[00112] Formatting unit – 212;
[00113] Preprocessing unit – 214;
[00114] Training unit – 216;
[00115] Determining unit -218;
[00116] Model – 220;
[00117] Primary Processor – 302;
[00118] Memory – 304;
[00119] User Interface (UI) – 306;
[00120] Data ingestion layer– 402;
[00121] Data Preprocessing unit – 404;
[00122] Model training unit – 406;
[00123] Model output unit – 408;
[00124] Alert and response unit – 410;
[00125] User – 412
,CLAIMS:CLAIMS
We Claim:
1. A method (600) for training a model (220) using data in a centralized data storage unit (112), the method (600) comprising the steps of:
establishing, by one or more processors, one or more connections with one or more data sources (110);
retrieving, by the one or more processors (202), data from the one or more data sources (110) based on the established one or more connections;
formatting, by the one or more processors (202), the data to align with an acceptable format;
storing, by the one or more processors (202), the formatted data in a centralized data storage unit (112);
preprocessing, by the one or more processors (202), the formatted data stored in the centralized data storage unit (112); and
training, by the one or more processors (202), a model (220) with the pre-processed data.

2. The method (600) as claimed in claim 1, wherein the one or more processors (202), establishes one or more connections with the one or more data sources (110) using one or more Application Programming Interfaces (APIs).

3. The method (600) as claimed in claim 1, wherein the one or more data sources (110) include at least one of, cell towers, network functions, network elements, network performance data, subscriber data, device data, competitor data, social media data, customer feedback and surveys.

4. The method (600) as claimed in claim 1, wherein the acceptable format is the format which is suitable for training the model (220).

5. The method (600) as claimed in claim 1, wherein the one or more processors (202), formats the data to align with the acceptable format using the one or more APIs.

6. The method (600) as claimed in claim 1, wherein the centralized data storage unit (112) is at least one of, a Network Attached Storage (NAS).

7. The method (600) as claimed in claim 1, wherein preprocessing the formatted data, includes operations performed on the formatted data including at least one of, data cleaning, correcting data errors, data transformation and data normalization.

8. The method (600) as claimed in claim 1, wherein the step of, training, the model (220) with the pre-processed data includes the step of:
identifying, one or more patterns/trends from the pre-processed data, wherein the one or more patterns/trends pertain to ideal patterns/trends in a network environment without an anomaly.

9. The method (600) as claimed in claim 1, wherein subsequent to performing the step of, training, a model (220) with the pre-processed data, the method (600) further includes the steps of:
determining, by the one or more processors (202), utilizing the trained model (220), one or more anomalies when current data deviates from the patterns/trends of the pre-processed data;
generating, by the one or more processors (202), alerts and/or notifications pertaining to the determined one or more anomalies; and
recommending, by the one or more processors (202), one or more actions to address the determined one or more anomalies.

10. A system (108) for training a model (220) using data in a centralized data storage unit (112), the system (108) comprising:
a connection establishing unit (208), configured to, establish, one or more connections with one or more data sources (110);
a retrieving unit (210), configured to, retrieve, data from the one or more data sources (110) based on the established one or more connections;
a formatting unit (212), configured to, format, the data to align with an acceptable format;
the formatting unit (212), configured to, store, the formatted data in a centralized data storage unit (112);
a preprocessing unit (214), configured to, preprocess, the formatted data stored in the centralized data storage unit (112); and
a training unit (216), configured to, train a model (220) with the pre-processed data.

11. The system (108) as claimed in claim 10, wherein the connection establishing unit (208), establishes one or more connections with the one or more data sources (110) using one or more Application Programming Interfaces (APIs).

12. The system (108) as claimed in claim 10, wherein the one or more data sources (110) include at least one of, cell towers, network functions, network elements, network performance data, subscriber data, device data, competitor data, social media data, customer feedback and surveys.

13. The system (108) as claimed in claim 10, wherein the acceptable format is the format which is suitable for training the model (220).

14. The system (108) as claimed in claim 10, wherein the formatting unit (212), formats the data to align with the acceptable format using the one or more APIs.

15. The system (108) as claimed in claim 10, wherein the centralized data storage unit (112) is at least one of, a Network Attached Storage (NAS).

16. The system (108) as claimed in claim 10, wherein preprocessing the formatted data, includes operations performed on the formatted data including at least one of, data cleaning, correcting data errors, data transformation and data normalization.

17. The system (108) as claimed in claim 10, wherein the training unit (216), trains the model (220) with the pre-processed data by:
identifying, one or more patterns/trends from the pre-processed data, wherein the one or more patterns/trends pertain to ideal patterns/trends in a network environment without an anomaly.

18. The system (108) as claimed in claim 10, wherein a determining unit (218) is configured to:
determine, utilizing the trained model (220) one or more anomalies when current data deviates from the patterns/trends of the pre-processed data;
generate, alerts and/or notifications pertaining to the determined one or more anomalies; and
recommend, one or more actions to address the determined one or more anomalies.