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
METHOD AND SYSTEM FOR SELECTING ONE OR MORE HYPERPARAMETERS VALUES FOR MODEL TRAINING
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 field of Artificial Intelligence (AI) and Machine Learning (ML), more particularly relates to method and system for selecting one or more hyperparameters values for model training.
BACKGROUND OF THE INVENTION
[0002] Artificial Intelligence/Machine Learning (AI/ML) techniques have become increasingly popular for solving complex problems across various domains. However, effectively training these algorithms requires meticulous tuning of hyperparameters, which are critical settings that control the behavior and performance of the algorithms. Hyperparameter tuning involves iteratively adjusting these settings to find the optimal configuration that maximizes performance metrics such as accuracy, precision, or recall.
[0003] Traditionally, hyperparameter tuning has been a manual and time-consuming process. Users need to possess a deep understanding of AI/ML principles and expertise in fine-tuning hyperparameters to achieve desirable results. This often involves trial and error exploration of various hyperparameter combinations, making the algorithm selection process complex and resource intensive.
[0004] There have been attempts in hyperparameter tuning using optimization techniques or grid search techniques. However, these approaches are limited in their ability to efficiently explore the high-dimensional space of hyperparameters and may require significant computational resources.
[0005] Therefore, there is a need for a system that can simplify the hyperparameter tuning process and alleviate the burden on users. Such a system should be capable of intelligently evaluating hyperparameters during the training of AI/ML algorithms, selecting optimal configurations based on user data, and enhancing performance of the system.
SUMMARY OF THE INVENTION
[0006] One or more embodiments of the present disclosure provide a method and a system for selecting one or more hyperparameters values for model training.
[0007] In one aspect of the present invention, the system for selecting one or more hyperparameters values for model training is disclosed. The system includes a receiving unit configured to receive a request from a User Interface (UI) of an at least one User Equipment (UE). The system further includes a retrieving unit configured to retrieve data relevant to the request from a database. The system further includes an identification unit configured to identify one or more hyperparameters required for functioning of a learning model. The system further includes an assessing unit configured to assess performance of the learning model utilizing the one or more hyperparameter values of one or more identified hyperparameters via one or more analytical models. The system further includes a comparison unit configured to compare the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters to a learning model operated utilizing historically used hyperparameter values to determine if the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the learning model operated utilizing the historically used hyperparameter values. The system further includes a selection unit configured to select the one or more hyperparameter values in response to the comparison.
[0008] In an embodiment, the comparison unit is configured to compare the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters to a learning model operated utilizing hyperparameter combination values to determine if the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the learning model operated utilizing the hyperparameter combination values.
[0009] In an embodiment, the hyperparameter combination values are selected within a range of the one or more hyperparameter values of the one or more identified hyperparameters.
[0010] In an embodiment, the request comprises information pertaining to a training period, a test period, one or more features, logical partitioning, and name of a process, wherein the information is required for configuration of the learning model.
[0011] In an embodiment, the system further comprises an execution unit configured to execute the learning model utilizing the selected one or more hyperparameters. The system further comprises a generation unit configured to generate a visual representation of the executed learning model utilizing the selected hyperparameters on the UI of the at least one UE. The visual representation is one of graph and tabular representations. The system further comprises a storing unit configured to store the selected one or more hyperparameters and an output of the learning model achieved utilizing the selected one or more hyperparameters in the database.
[0012] In an embodiment, the one or more analytical models is one of, mean, mode, variance, trend, Auto Correlation Function (ACF), and Partial Auto Correlation Function (PACF).
[0013] In an embodiment, on comparison, the comparison unit is configured to track and measure an improvement achieved by the learning model operated by one of the one or more hyperparameter values of the one or more identified hyperparameters over the historically used hyperparameter values.
[0014] In another aspect of the present invention, the method of selecting one or more hyperparameters values for model training is disclosed. The method includes the step of receiving a request from a User Interface (UI) of an at least one User Equipment (UE). The method further includes the step of retrieving data relevant to the request from a database. The method further includes the step of identifying one or more hyperparameters required for functioning of a learning model The method further includes the step of assessing performance of the learning model utilizing the one or more hyperparameter values of the one or more identified hyperparameters via one or more analytical models. The method further includes the step of comparing the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters to a learning model operated utilizing historically used hyperparameters values to determine if the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the learning model operated utilizing the historically used hyperparameters values. The method further includes the step of selecting the one or more hyperparameters values in response to the comparison.
[0015] In another aspect of the invention, a non-transitory computer-readable medium having stored thereon computer-readable instructions is disclosed. The computer-readable instructions are executed by a processor. The processor is configured to receive a request from a User Interface (UI) of an at least one User Equipment (UE). The processor is further configured to retrieve data relevant to the request from a database. The processor is further configured to identify one or more hyperparameters required for functioning of a learning model. The processor is further configured to assess performance of the learning model utilizing the one or more hyperparameter values of the one or more identified hyperparameters via one or more analytical models. The processor is further configured to compare, the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters to a learning model operated utilizing historically used hyperparameters values to determine if the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the learning model operated utilizing the historically used hyperparameters. The processor is further configured to select the one or more hyperparameters values in response to the comparison.
[0016] In another aspect of invention, User Equipment (UE) is disclosed. The UE includes one or more primary processors communicatively coupled to one or more processors, the one or more primary processors coupled with a memory. The processor causes the UE to transmit a request to the one or more processors. The request comprises information pertaining to a training period, a test period, one or more features, logical partitioning, and name of a process. The information is required for configuration of the learning model.
[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 selecting one or more hyperparameters values for model training, according to one or more embodiments of the present invention;
[0020] FIG. 2 an exemplary block diagram of a system for selecting the one or more hyperparameters values for model training, according to one or more embodiments of the present invention;
[0021] FIG. 3 is a schematic representation of a workflow of the system of FIG. 1, according to the one or more embodiments of the present invention;
[0022] FIG. 4 is an exemplary block diagram of an architecture implemented in the system of the FIG. 2, according to one or more embodiments of the present invention;
[0023] FIG. 5 is a signal flow diagram for selecting the one or more hyperparameters values for model training according to one or more embodiments of the present invention; and
[0024] FIG. 6 is a schematic representation of a method of selecting the one or more hyperparameters values for model training, 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] The present invention provides a hyperparameter tuning system for training Artificial Intelligence/Machine Learning (AI/ML) algorithms using user data. Understanding and tuning hyperparameters can be complex and time-consuming, requiring deep knowledge of machine learning principles. To simplify this process, the disclosed system employs AI/ML techniques for hyperparameter tuning, alleviating the burden on users and streamlining algorithm selection.
[0030] FIG. 1 illustrates an exemplary block diagram of an environment 100 for selecting one or more hyperparameters values for model training, according to one or more embodiments of the present disclosure. In this regard, the environment 100 includes a User Equipment (UE) 102, a server 104, a network 106 and a system 108 communicably coupled to each other for selecting one or more hyperparameters values for model training. The UE 102 aids a user to interact with the system 108 for transmitting the request.
[0031] As per the illustrated embodiment and for the purpose of description and illustration, the UE 102 includes, but not limited 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. In alternate embodiments, the UE 102 may include a plurality of UEs as per the requirement. For ease of reference, each of the first UE 102a, the second UE 102b, and the third UE 102c, will hereinafter be collectively and individually referred to as the “User Equipment (UE) 102”.
[0032] In an embodiment, the UE 102 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 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 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, one or more processors 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.
[0034] 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.
[0035] 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. The network 106 may also include, 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, a VOIP or some combination thereof.
[0036] The environment 100 further includes the system 108 communicably coupled to the server 104 and the UE 102 via the network 106. The system 108 is configured to select one or more hyperparameters values for model training. As per one or more embodiments, the system 108 is adapted to be embedded within the server 104 or embedded as an individual entity.
[0037] Operational and construction features of the system 108 will be explained in detail with respect to the following figures.
[0038] FIG. 2 is an exemplary block diagram of the system 108 for selecting the one or more hyperparameters values for model training, according to one or more embodiments of the present invention.
[0039] As per the illustrated embodiment, the system 108 includes one or more processors 202, a memory 204, and a database 208. For the purpose of description and explanation, the description will be explained with respect to one processor 202 and should nowhere be construed as limiting the scope of the present disclosure. In alternate embodiments, the system 108 may include more than one processors 202 as per the requirement of the network 106. 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.
[0040] As per the illustrated embodiment, the processor 202 is configured to fetch and execute computer-readable instructions stored in the memory 204. The memory 204 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 to create or share data packets over a network service. The memory 204 may include any non-transitory storage device including, for example, volatile memory such as RAM, or non-volatile memory such as disk memory, EPROMs, FLASH memory, unalterable memory, and the like.
[0041] The database 208 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 database 208 types are non-limiting and may not be mutually exclusive e.g., a database can be both commercial and cloud-based, or both relational and open-source, etc.
[0042] In order for the system 108 for selecting the one or more hyperparameters values for model training, the processor 202 includes one or more modules. In one embodiment, the one or more modules includes, but not limited to, a receiving unit 210, a retrieving unit 212, an identification unit 214, an assessing unit 216, a comparison unit 218, a selection unit 220, an execution unit 222, a generation unit 224 and a storing unit 226 communicably coupled to each other for selecting the one or more hyperparameters values for model training.
[0043] In one embodiment, the one or more modules includes, but not limited to, the receiving unit 210, the retrieving unit 212, the identification unit 214, the assessing unit 216, the comparison unit 218, the selection unit 220, the execution unit 222, the generation unit 224 and the storing unit 226 can be used in combination or interchangeably for selecting the one or more hyperparameters values for model training.
[0044] The receiving unit 210, the retrieving unit 212, the identification unit 214, the assessing unit 216, the comparison unit 218, the selection unit 220, the execution unit 222, the generation unit 224 and the storing unit 226 in an embodiment, may be 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. 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.
[0045] In one embodiment, the receiving unit 210 is configured to receive a request from a User Interface (UI) 306 (shown in FIG. 3) of an at least one UE 102. The request comprises information pertaining to a training period, a test period, one or more features, logical partitioning, and name of a process. The information is required for configuration of the learning model. The UI 306 is the point of communication between the user and the UE 102.
[0046] Upon receiving the request from the UI 306 of the at least one UE 102, the data relevant to the request is retrieved from the database 208 by the retrieving unit 212. For example, the user can select/enter a training period via the UE 102 to request the relevant data such as UE data, voice data, image data. Based on which, the data pertaining to the training period (for example-1 month selected/entered by the user via the UE) will be fetched from the database 208.
[0047] The data relevant to the training period includes, but not limited to, the start and end date of the training period, historical data specific to the training period, relevant statistics and metrics for the training period. The data relevant to the test period includes, but not limited to, the start and end date for the test period, historical data specific to the test period, relevant statistics and metrics for the test period. The data relevant to the one or more features includes, but not limited to, a list of features used for model training, description of data types of the features, statistical summaries of each feature (mean, median, standard deviation etc.). The data relevant to the logical partitioning includes, but not limited to, information on how the data is logically partitioned, partitioning rules and parameters, identifiers for data partitions. For example, the partitioning can be based on region, network function types, error codes, vendor etc. The data relevant to the name of the machine learning process/algorithms includes, but not limited to, name and description of the training process, process-specific parameters and settings, previous results and configurations for the process, documentation and notes related to the process. The process refers to a mathematical procedure or a sequence of computational steps that processes input data to produce a desired output.
[0048] Upon retrieving the data relevant to the request from the database 208, the identification unit 214 is configured to identify one or more hyperparameters required for functioning of a learning model. The one or more hyperparameters is a parameter whose value is set before the learning process begins and controls the learning process. The one or more hyperparameters includes, but not limited to, learning rate, batch size, epochs, number of layers, number of nodes per layer, architecture, activation function. The learning model is at least one of Artificial Intelligence/ Machine Learning (AI/ML) model. The AI/ML model is at least one of supervised learning models, unsupervised learning models, reinforcement learning models, deep learning models, and Natural Language Processing (NLP) models. In an embodiment, to identify the one or more hyperparameters for functioning of the learning model, all the combination of one or more hyperparameters are evaluated for an algorithm and dataset. Thereafter, checking which combination provides good result and then finalizes the final set of one or more hyperparameters.
[0049] Upon identifying the one or more hyperparameters, the assessing unit 216 is configured to assess the performance of the learning model utilizing the one or more hyperparameter values of the one or more identified hyperparameters via one or more analytical models. The one or more analytical models is one of, mean, mode, variance, trend, Auto Correlation Function (ACF), and Partial Auto Correlation Function (PACF).
[0050] Upon assessing the performance of the learning model, the comparison unit 218 is configured to compare the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters to a learning model operated utilizing historically used hyperparameters values. The learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters is compared with the learning model operated utilizing historically used hyperparameters values to determine if the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the learning model operated utilizing the historically used hyperparameters values. The improvement over the learning model operated utilizing the historically used hyperparameters values referred as the improvements in the results of learning model such as learning model accuracy percentages when tested on some sample test data.
[0051] On comparison, the comparison unit 218 is configured to track and measure the improvement achieved by the learning model operated by one of the one or more hyperparameter values of the one or more identified hyperparameters over the historically used hyperparameter values.
[0052] In particular, the output of the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters is compared with the output of the learning model operated utilizing historically used hyperparameters values. The output of the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters is compared with the output of the learning model operated utilizing historically used hyperparameters values to determine if the output of the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the output of the learning model operated utilizing the historically used hyperparameters values.
[0053] Further, the comparison unit 218 is configured to compare the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters to a learning model operated utilizing hyperparameter combination value. The learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters are compared with the learning model operated utilizing hyperparameter combination values to determine if the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the learning model operated utilizing the hyperparameter combination values. The hyperparameter combination values are selected within a range of the one or more hyperparameter values of the one or more identified hyperparameters. In an embodiment, the range of the one or more hyperparameter values is at least one of trend such as ( ‘n’ is the trend is none (no increasing or decreasing), ‘c’ is the constant (increasing or decreasing constantly), ‘ct’ is the cyclical (if trend repeating then is used)), order selections, ‘q’ is the size of the moving average window such as (‘q_max’ is the max number of non-zero values, ‘q_min’ is the min number of non-zero values ), ‘d’ is the parameter used refers to the order of differencing the number of times the data needs to be differenced to make it stationary, such as mean and variance, remain constant over time, ‘p’ is the value which lies outside the blue area is taken as parameter p for PACF. In an embodiment, the data values of the hyperparameter values is at least one of range, Boolean, string, integer, float etc.
[0054] In particular, the output of the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters is compared with the output of the learning model operated utilizing hyperparameter combination value. The output of the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters are compared with the output of the learning model operated utilizing hyperparameter combination values to determine if the output of the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the output of the learning model operated utilizing the hyperparameter combination values.
[0055] In response to comparison, the selection unit 220 is configured to select the one or more hyperparameter values. Upon selecting the one or more hyperparameter values, the execution unit 222 is configured to execute the learning model utilizing the selected one or more hyperparameters. In an embodiment, the parameter value selections can be done via UI 306, where UI 306 represents form type interface (radio, choice, text, dropdown) for various parameters.
[0056] In an embodiment, users are provided the flexibility to configure their own parameter values. This flexibility allows them to have greater control over the training process and adapt it to their specific needs. Users can experiment with different parameter settings and fine-tune them based on their domain knowledge or preferences.
[0057] Upon executing the learning model, the storing unit 226 is configured to store the selected one or more hyperparameter and an output of the learning model achieved utilizing the selected one or more hyperparameters in the database 208.
[0058] Subsequently, the generation unit 224 is configured to generate a visual representation of the executed learning model utilizing the selected hyperparameters on the UI 306 of the at least one UE 102. The visual representation is one of graph and tabular representations. Therefore, the system 108 is configured to reduce the time required for configuring the best-suited hyperparameters. Further, the system 108 automates the evaluation of various hyperparameters within a specified value range, enabling to efficiently optimize algorithm performance and enhance the accuracy of the analysis results.
[0059] FIG. 3 describes a preferred embodiment of the system 108 of FIG. 2, according to various embodiments of the present invention. It is to be noted that the embodiment with respect to FIG. 3 will be explained with respect to the first UE 102a and the system 108 for the purpose of description and illustration and should nowhere be construed as limited to the scope of the present disclosure.
[0060] As mentioned earlier in FIG. 1, each of the first UE 102a the second UE 102b, and the third UE 102c may include an external storage device, a bus, a main memory, a read-only memory, a mass storage device, communication port(s), and a processor. The exemplary embodiment as illustrated in FIG. 3 will be explained with respect to the first UE 102a without deviating from the scope of the present disclosure and the limiting the scope of the present disclosure. The first UE 102a includes one or more primary processors 302 communicably coupled to the one or more processors 202 of the system 108.
[0061] The one or more primary processors 302 are coupled with a memory 304 for storing instructions which are executed by the one or more primary processors 302 and a user interface 306. In an embodiment, the user interface 306 includes a variety of interfaces, for example, interfaces for a graphical user interface, a web user interface, a Command Line Interface (CLI), and the like.
[0062] Execution of the stored instructions by the one or more primary processors 302 enables the first UE 102a to transmit the request to the one or mor processors 202. The request comprises information pertaining to the training period, the test period, the one or more features, the logical partitioning, and the name of the process. The information is required for configuration of the learning model.
[0063] As mentioned earlier in FIG. 2, the one or more processors 202 of the system 108 is configured for selecting the one or more hyperparameters values for model training. As per the illustrated embodiment, the system 108 includes the one or more processors 202, the memory 204, and the database 208. The operations and functions of the one or more processors 202, the memory 204, and the database 208 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.
[0064] Further, the processor 202 includes the receiving unit 210, the retrieving unit 212, the identification unit 214, the assessing unit 216, the comparison unit 218, the selection unit 220, the execution unit 222, the generation unit 224 and the storing unit 226. The operations and functions of the receiving unit 210, the retrieving unit 212, the identification unit 214, the assessing unit 216, the comparison unit 218, the selection unit 220, the execution unit 222, the generation unit 224 and the storing unit 226 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 as provided for the system 108 in the FIG. 2 above, and should not be construed as limiting the scope of the present disclosure.
[0065] FIG. 4 is an exemplary block diagram of an architecture 400 implemented in the system 108 for selecting the one or more hyperparameters values for model training, according to one or more embodiments of the present invention.
[0066] The architecture 400 includes the UI 306, a load balancer 402, the database 208, a cache 404, AI/ML model (406-1, 406-2) communicably coupled to each other for selecting the one or more hyperparameters values for model training.
[0067] In an embodiment, the request is received from the UI 306 of the at least one UE 102. The request comprises information pertaining to the training period, the test period, the one or more features, the logical partitioning, and the name of the process. The information is required for configuration of the AI/ML model (406-1, 406-2). Thereafter, the load balancer 402 distributes the received request to the available computing and storage resources.
[0068] Upon receiving the request, the data relevant to the received request is retrieved from the database 208. Upon retrieving the relevant data, at least one of the mathematical computations such as mean, median, variance is performed on retrieved data to evaluate the one or more hyperparameters. Further, all the combinations of mathematical computation are performed iteratively to evaluate the one or more hyperparameters until the best configuration is identified.
[0069] Further, the auto tune uses the retrieved data and best mathematical computations for tuning the one or more hyperparameters. The tuning is performed by comparing the output of the AI/ML model (406-1, 406-2) operated utilizing one or more hyperparameters values with the output of the AI/ML model (406-1, 406-2) operated utilizing the historically used hyperparameters values. The comparison between the output of the AI/ML model (406-1, 406-2) operated utilizing the one or more hyperparameters values with the output of the AI/ML model (406-1, 406-2) operated utilizing the historically used hyperparameters values is performed to determine if the output of the AI/ML model (406-1, 406-2) operated utilizing the one or more hyperparameters values shows improvement over the output of the AI/ML model (406-1, 406-2) operated utilizing the historically used hyperparameters values. Upon comparison, the tuned one or more hyperparameters are selected.
[0070] Thereafter the AI/ML model (406-1, 406-2) is executed using the tuned one or more hyperparameters. Upon execution of the AI/ML model (406-1, 406-2), the tuned one or more hyperparameters and the output of the AI/ML model (406-1, 406-2) achieved utilizing the tuned one or more hyperparameters are stored in the cache 404. The cache 404 is a temporary storage for quick access to intermediate results and frequently accessed data. Subsequently the tuned one or more hyperparameters and the output of the AI/ML model (406-1, 406-2) achieved utilizing the tuned one or more hyperparameters are stored in the database 208. Further, the visual representation of the executed AI/ML model (406-1, 406-2) on the UI 306 of the at least one UE 102. The visual representation is one of graphical and tabular representations.
[0071] FIG. 5 is a signal flow diagram for selecting the one or more hyperparameters values for model training according to one or more embodiments of the present invention.
[0072] At step 502, the request is received from the UI 306 of the at least one UE 102.
[0073] At step 504, upon receiving the request from the UI 306, the data relevant to the request is retrieved from the database 208.
[0074] At step 506, upon retrieving the relevant data, the one or more hyperparameters required for functioning of the learning model is identified. The one or more hyperparameters are identified based on evaluating all the combination of one or more hyperparameters. Thereafter, checking which combination provides good result and then finalizes the final set of one or more hyperparameters.
[0075] At step 508, upon identifying the one or more hyperparameters, the performance of the learning model utilizing the one or more hyperparameter values of the one or more identified hyperparameters is assessed via the one or more analytical models. The one or more analytical models is one of, mean, mode, variance, trend, Auto Correlation Function (ACF), and Partial Auto Correlation Function (PACF).
[0076] At step 510, upon assessing the performance of the learning model, the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters is compared with the learning model operated utilizing historically used hyperparameters values to determine if the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the learning model operated utilizing the historically used hyperparameters values.
[0077] On comparison, the improvement achieved by the learning model operated by one of the one or more hyperparameter values of the one or more identified hyperparameters are tracked and measured over the historically used hyperparameter values. Further, the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters is compared with the learning model operated utilizing hyperparameter combination value to determine if the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the learning model operated utilizing the hyperparameter combination values. The hyperparameter combination values are selected within a range of the one or more hyperparameter values of the one or more identified hyperparameters.
[0078] At step 512, in response to comparison, the one or more hyperparameter values are selected.
[0079] At step 514, upon selecting the one or more hyperparameter values, the learning model utilizing the selected one or more hyperparameters is executed.
[0080] At step 516, upon executing the learning model, the selected one or more hyperparameter and an output of the learning model achieved utilizing the selected one or more hyperparameters are stored in the database 208.
[0081] At step 518, subsequently, the visual representation of the executed learning model utilizing the selected hyperparameters is generated on the UI 306 of the at least one UE 102. The visual representation is one of graph and tabular representations.
[0082] FIG. 6 is a flow diagram of a method 600 for selecting the one or more hyperparameters values for model training, 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.
[0083] At step 602, the method 600 includes the step of receiving the request from the UI 306 of the at least UE 102 by the receiving unit 210. The request comprises information pertaining to a training period, a test period, one or more features, logical partitioning, and name of a process, wherein the information is required for configuration of the learning model.
[0084] At step 604, the method 600 includes the step of retrieving the data relevant to the request from the database 208 by the retrieving unit 212.
[0085] At step 606, the method 600 includes the step of identifying the one or more hyperparameters required for functioning of the learning model by the identification unit 214.
[0086] At step 608, the method 600 includes the step of assessing performance of the learning model utilizing the one or more hyperparameter values of the one or more identified hyperparameters via the one or more analytical models by the assessing unit 216. the one or more analytical models is one of, mean, mode, variance, trend, Auto Correlation Function (ACF), and Partial Auto Correlation Function (PACF).
[0087] At step 610, the method 600 includes the step of comparing the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters to the learning model operated utilizing historically used hyperparameters values by the comparison unit 218 to determine if the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the learning model operated utilizing the historically used hyperparameters values. On comparison, the improvement achieved by the learning model operated by one of the one or more hyperparameter values of the one or more identified hyperparameters are tracked and measured over the historically used hyperparameter values.
[0088] Further, the learning model operated utilizing one or more hyperparameter values of the one or more identified hyperparameters compared with the learning model operated utilizing hyperparameter combination values by the comparison unit 218 to determine if the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the learning model operated utilizing the hyperparameter combination values. The hyperparameter combination values are selected within a range of the one or more hyperparameter values of the one or more identified hyperparameters.
[0089] At step 612, the method 600 includes the step of selecting the one or more hyperparameter values by the selection unit 220 in response to the comparison. Further, upon selecting the one or more hyperparameter values, the learning model is executed by the execution unit 222 utilizing the selected one or more hyperparameter values. Thereafter, the selected one or more hyperparameters values and an output of the learning model achieved utilizing the selected one or more hyperparameters values are stored by the storing unit 226 in the database 208. Subsequently, the visual representation of the executed learning model is generated by the generation unit 224 utilizing the selected one or more hyperparameter values on the UI of the at least one UE 102. The visual representation is one of graphical and tabular representations.
[0090] The present invention further discloses a non-transitory computer-readable medium having stored thereon computer-readable instructions. The computer-readable instructions are executed by the processor 202. The processor 202 is configured to receive the request from the UI 306 of the at least one UE 102. The processor 202 is further configured to retrieve the data relevant to the request from the database 208. The processor 202 is further configured to identify the one or more hyperparameters required for functioning of the learning model. The processor 202 is further configured to assess the performance of the learning model utilizing the one or more hyperparameter values of the one or more identified hyperparameters via the one or more analytical models. The processor 202 is further configured to compare the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters to the learning model operated utilizing historically used hyperparameters values to determine if the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the learning model operated utilizing the historically used hyperparameters. The processor 202 is further configured to select the one or more hyperparameters values in response to the comparison.
[0091] 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.
[0092] The present disclosure incorporates technical advancement reducing the time required for configuring the best-suited hyperparameters for different algorithms. In particular, the system eliminates manual exploration of hyperparameter combinations, saving time and improving algorithm performance.
[0093] Further, the system allows users to tailor the training process to their specific needs. Users can experiment with different parameter settings based on their domain knowledge or preferences, enhancing their control over the training process. The system enhances the efficiency and effectiveness of model training. By fine-tuning the hyperparameters, better accuracy, robustness, and adaptability to different datasets or use cases are achieved.
[0094] 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

[0095] Environment- 100
[0096] User Equipment (UE)- 102
[0097] Server- 104
[0098] Network- 106
[0099] System -108
[00100] Processor- 202
[00101] Memory- 204
[00102] Database- 208
[00103] Receiving Unit- 210
[00104] Retrieving Unit- 212
[00105] Identification Unit- 214
[00106] Assessing Unit- 216
[00107] Comparison Unit- 218
[00108] Selection Unit- 220
[00109] Execution Unit- 222
[00110] Generation Unit- 224
[00111] Storing Unit- 226
[00112] Primary processor- 302
[00113] Memory- 304
[00114] User Interface- 306
[00115] Load balancer- 402
[00116] Cache- 404
[00117] AI/ML model- 406-1, 406-2
,CLAIMS:CLAIMS:

We Claim:
1. A method (600) of selecting one or more hyperparameters values for model training, the method (600) comprising the steps of:
receiving, by one or more processors (202), a request from a User Interface (UI) (306) of an at least one User Equipment (UE) (102);
retrieving, by the one or more processors (202), data relevant to the request from a database (208);
identifying, by the one or more processors (202), one or more hyperparameters required for functioning of a learning model;
assessing, by the one or more processors (202), performance of the learning model utilizing the one or more hyperparameter values of the one or more identified hyperparameters via one or more analytical models;
comparing, by the one or more processors (202), the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters to a learning model operated utilizing historically used hyperparameters values to determine if the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the learning model operated utilizing the historically used hyperparameters values; and
selecting, by the one or more processors (202), the one or more hyperparameters values in response to the comparison.

2. The method (600) as claimed in claim 1, wherein the method (600) includes the step of comparing, by the one or more processors (202), the learning model operated utilizing one or more hyperparameter values of the one or more identified hyperparameters to a learning model operated utilizing hyperparameter combination values to determine if the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the learning model operated utilizing the hyperparameter combination values.

3. The method (600) as claimed in claim 2, wherein the hyperparameter combination values are selected within a range of the one or more hyperparameter values of the one or more identified hyperparameters.

4. The method (600) as claimed in claim 1, wherein the request comprises information pertaining to a training period, a test period, one or more features, logical partitioning , and name of a process, wherein the information is required for configuration of the learning model.

5. The method (600) as claimed claim 1, wherein the one or more analytical models is one of, mean, mode, variance, trend, Auto Correlation Function (ACF), and Partial Auto Correlation Function (PACF).

6. The method (600) as claimed in claim 1, wherein on comparison, the one or more processors (202) is configured to track and measure an improvement achieved by the learning model operated by one of the one or more hyperparameter values of the one or more identified hyperparameters over the historically used hyperparameter values.

7. The method (600) as claimed in claim 1, further comprising,
executing, by the one or more processor (202), the learning model utilizing the selected one or more hyperparameter values; and
generating, by the one or more processor (202), a visual representation of the executed learning model utilizing the selected one or more hyperparameter values on the UI (306) of the at least one UE (102), wherein the visual representation is one of graphical and tabular representations.

8. The method (600) as claimed in claim 1, wherein the method (600) further comprises the step of, storing, by the one or more processors (202), the selected one or more hyperparameters values and an output of the learning model achieved utilizing the selected one or more hyperparameters values in the database.

9. A system (108) for selecting one or more hyperparameters values for model training, the system (108) comprising:
a receiving unit (210) configured to receive, a request from a User Interface (UI) (306) of an at least one User Equipment (UE) (102);
a retrieving unit (212) configured to retrieve, data relevant to the request from a database (208);
an identification unit (214) configured to identify, one or more hyperparameters required for functioning of a learning model;
an assessing unit (216) configured to assess, performance of the learning model utilizing the one or more hyperparameter values of one or more identified hyperparameters via one or more analytical models;
a comparison unit (218) configured to compare, the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters to a learning model operated utilizing historically used hyperparameter values to determine if the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the learning model operated utilizing the historically used hyperparameter values; and
a selection unit (220) configured to select, the one or more hyperparameter values in response to the comparison.

10. The system (108) as claimed in claim 9, wherein the comparison unit (218) is configured to compare the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters to a learning model operated utilizing hyperparameter combination values to determine if the learning model operated utilizing the one or more hyperparameter values of the one or more identified hyperparameters shows improvement over the learning model operated utilizing the hyperparameter combination values.

11. The system (108) as claimed in claim 10, wherein the wherein the hyperparameter combination values are selected within a range of the one or more hyperparameter values of the one or more identified hyperparameters.

12. The system (108) as claimed in claim 9, wherein the request comprises information pertaining to a training period, a test period, one or more features, logical partitioning, and name of a process, wherein the information is required for configuration of the learning model.

13. The system (108) as claimed in claim 9, wherein the system (108) further comprises:
an execution unit (222) configured to execute, the learning model utilizing the selected one or more hyperparameters;
a generation unit (224) configured to generate, a visual representation of the executed learning model utilizing the selected hyperparameters on the UI of the at least one UE, wherein the visual representation is one of graph and tabular representations; and
a storing unit (226) configured to store, the selected one or more hyperparameters and an output of the learning model achieved utilizing the selected one or more hyperparameters in the database.

14. The system (108) as claimed in claim 9, wherein the one or more analytical models is one of, mean, mode, variance, trend, Auto Correlation Function (ACF), and Partial Auto Correlation Function (PACF).

15. The system (108) as claimed in claim 9, wherein on comparison, the comparison unit (218) is configured to track and measure an improvement achieved by the learning model operated by one of the one or more hyperparameter values of the one or more identified hyperparameters over the historically used hyperparameter values.

16. A User Equipment (UE) (102), 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 UE (102) to:
transmit, a request to the one or more processors (202), wherein the request comprises information pertaining to a training period, a test period, one or more features, logical partitioning, and name of a process, wherein the information is required for configuration of the learning model;
wherein the one or more processors (202) is configured to perform the steps as claimed in claim 1.