Generation of an insight report and an application programming interface

Abstract

Embodiments of the disclosure describe a method (300) that includes receiving (302) an input API specification from a user. The method (300) further includes validating (304) a compliance of the input API specification to a set of predefined parameters based on correlation using a generative Machine Learning (ML) model (105). The generative ML model (105) implements a Retrieval-Augmented Generation (RAG) technique. Further, the method (300) includes generating (306) an insight report based on the validation, wherein the insight report includes at least one of validated compliance instances and non-validated compliance instances, and wherein the insight report further includes an identification of at least one structural parameter missing or incorrect in the input API specification.

Description

GENERATION OF AN INSIGHT REPORT AND AN APPLICATION PROGRAMMING INTERFACECROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims priority to Indian Application No. 202411057091 filed on July 26, 2024, the disclosure of which is incorporated by reference herein in its entirety.FIELD

[0002] The present disclosure relates to a generation of an insight report and an Application Programming Interface.BACKGROUND

[0003] The information disclosed in this background section is only for the enhancement of understanding of the general background of the disclosure and should not be taken as an acknowledgment or any form of suggestion that this information forms the prior art already known to a person skilled in the art.

[0004] An application programming interface (API) is a way for two or more computer programs or components to communicate with each other. The API is a type of software interface, that offers a service to other pieces of software.

[0005] US Patent Application Publication Number 20240073238 discloses a method and system for analyzing computing devices for properties of at least one computer software in at least one computing system. The method includes loading input data for the at least one computer software. The method further includes determining a result pertaining to vulnerabilities present or expected to be present within the computer software. The method is followed by mapping vulnerabilities to frameworks. Further, the method includes determining a result pertaining to the outcome of the vulnerability-to-framework mapping. Further, the method includes generating, output data describing at least one result. The method is followed by storing the output data pertaining to the result in memory, and determining, if the result satisfies a predetermined condition, and if so, executing an action corresponding to the result on the computing system.

[0006] Further, US Patent Application Publication Number 20230102198 discloses a system that is configured to obtain a compliance document and obtain seed data associated with the compliance document. The seed data includes a plurality of sample text inputs and a plurality of sample computer-readable operations associated with the plurality of sample text inputs. The system is also configured to parse text in the compliance document into one or more text segments, provide one or more text segments and the seed data to an Artificial Intelligence (Al) model, and obtain, from the Al model, one or more computer-readable operations associated with the one or more text segments.SUMMARY

[0007] This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the disclosure. This summary is neither intended to identify key or essential inventive concepts of the disclosure nor is it intended for determining the scope of the disclosure.

[0008] The above-discussed prior art documents do not provide a validation that the API that is built by an organization or a user is in compliant with a set of predefined parameters. The set of predefined parameters are standard operating guidelines for operations of an API specification.

[0009] According to one embodiment of the present disclosure, a method is disclosed. The method includes receiving an input API specification from a user. The method includes validating a compliance of the input API specification to a set of predefined parameters based on correlation using a generative Machine Learning (ML) model. The generative ML model implements a Retrieval-Augmented Generation (RAG) technique. The method further includes generating an insight report based on the validation, wherein the insight report includes at least one of validated compliance instances and non-validated compliance instances, and wherein the insight report further includes an identification of at least one structural parameter missing or incorrect in the input API specification.

[0010] According to another embodiment of the present disclosure, a system is disclosed. The system is configured to receive an input API specification from a user. The system is furtherconfigured to validate a compliance of the input API specification to a set of predefined parameters based on correlation using a generative Machine Learning (ML) model. The generative ML model implements a Retrieval-Augmented Generation (RAG) technique. Further, the system is configured to generate an insight report based on the validation. The insight report includes at least one of validated compliance instances and non-validated compliance instances, and wherein the insight report further includes an identification of at least one structural parameter missing or incorrect in the input API specification.

[0011] According to yet another aspect of the present invention, a non-transitory computer- readable medium for storing instructions is disclosed. The instructions may include one or more instructions that, when executed by a user equipment (UE), cause one or more processors of the UE to receive (302) an input API specification from a user. Further, the instructions may be executed to cause the one or more processors to validate a compliance of the input API specification to a set of predefined parameters based on correlation using a generative Machine Learning (ML) model. The generative ML model implements a Retrieval-Augmented Generation (RAG) technique. The instructions are further executed to cause the one or more processors to generate (306) an insight report based on the validation, wherein the insight report includes at least one of validated compliance instances and non-validated compliance instances, and wherein the insight report further includes an identification of at least one structural parameter missing or incorrect in the input API specification.

[0012] To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will be rendered by reference to specific embodiments thereof, which are illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the disclosure and are therefore not to be considered limiting of its scope. The disclosure will be described and explained with additional specificity and detail in the accompanying drawings.BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Features, aspects, and advantages of embodiments of the disclosure will be described below with reference to the accompanying drawings, in which like reference numerals denote like elements, and wherein:FIG. 1 illustrates a block diagram of a system for generating an API specification, according to an embodiment as disclosed herein;FIG. 2 illustrates an exemplary sequence flow diagram depicting one or more operations performed by the system for generating the API specification, according to an embodiment as disclosed herein;FIG. 3A illustrates a flowchart depicting a method for generating a revised API specification, according to an embodiment as disclosed herein;FIG. 3B illustrates a flowchart depicting the method including further steps for generating the revised API specification, according to an embodiment as disclosed herein;FIG. 4 illustrates a flowchart depicting sub-steps of validating a compliance of an input API specification, according to an embodiment as disclosed herein; andFIG. 5 illustrates an embodiment of a device, according to an embodiment as disclosed herein.DETAILED DESCRIPTION

[0014] The following detailed description of example embodiments refers to the accompanying drawings. The present disclosure provides illustrations and descriptions but is not intended to be exhaustive or to limit the implementations to the precise form disclosed. Modifications and variations are possible in light of the present disclosure or may be acquired from practice of the implementations. Further, one or more features or components of one embodiment may be incorporated into or combined with another embodiment (or one or more features of another embodiment). Additionally, the flowchart and description of operations provided below relate to at least one of the embodiments in the present disclosure. It should be noted that it is possible to make other embodiments that do not exactly match the flowchart and its description. It is understood that in other embodiments one or more operations may be omitted, one or moreoperations may be added, and one or more operations may be performed simultaneously (at least in part).

[0015] It will be apparent that systems and / or methods, described herein, may be implemented in different forms of hardware, software, or a combination of hardware and software. The actual specialized control hardware or software code used to implement these systems and / or methods should not limit their implementations. Thus, the operation and behavior of the systems and / or methods are described herein without reference to specific software code. It is understood that software and hardware may be designed to implement the systems and / or methods based on the description herein.

[0016] Even though particular combinations of features are recited in the claims and / or disclosed in the specification, the particular combinations are not intended to limit the disclosure of implementations. In fact, many of these features may be combined in ways not specifically recited in the claims and / or disclosed in the specification. Even if a dependent claim directly depends on only one claim, the present disclosure may indicate that the dependent claim is dependent on other claims in the claim set.

[0017] No element, act, or instruction used herein should be construed as critical or essential unless explicitly described as such. Also, as used herein, the articles “a” and “an” (in other words, nouns not mentioned in the plural) are intended to include one or more items, and may be used interchangeably with “one or more.” Also, as used herein, the terms “has,” “have,” “having,” “include,” “including,” or the like are intended to be open-ended terms. Further, the phrase “based on” is intended to mean “based, at least in part, on” unless explicitly stated otherwise. Furthermore, expressions such as “at least one of [A] and [B],” “[A] and / or [B],” or “at least one of [A] or [B]” are to be understood as including only A, only B, or both A and B.

[0018] The foregoing disclosure provides illustration and description but is not intended to be exhaustive or to limit the implementations to the precise form disclosed. Modifications and variations are possible in light of the above disclosure or may be acquired from the practice of the implementations.

[0019] FIG. 1 illustrates a block diagram of a system 100 for generating an insight report and / or a revised Application Programming Interface (API) specification, according to an embodiment as disclosed herein.

[0020] An Application Programming Interface (API) is a set of rules and protocols that allow two or more computer modules or components to communicate with each other over a network. The API thus provides a software interface that renders services to other software applications. For instance, in the telecommunications industry, the APIs are used to integrate calling, texting, and other telephony functions directly into applications or software services. Additionally, an API specification refers to a document or standard that outlines building or using the software interface effectively. The API specification includes details about the available functions, data formats, protocols, and conventions that developers need to follow to interact with the API.

[0021] In an embodiment, the system 100 may include a memory 102 and a processor 106 in communication with the memory 102 via a communicator 104. The system 100 may further include a generative machine learning (ML) model 105 which is stored in the memory 102 and executed by the processor 106. In an embodiment, the generative ML model 105 is a Large Language Model (LLM) which is a computational model notable for its ability to achieve general- purpose language generation and other natural language processing tasks such as classification. For example, in an embodiment of the present invention, the generative model may generate the revised API specification based on an input API specification explained in conjunction with FIGS. 2-4

[0022] In an embodiment, the system 100 may reside in a user equipment (UE) such as a smartphone, a laptop computer, a desktop computer, a Personal Computer (PC), or the like. In another embodiment, the system 100 may reside in a server.

[0023] In an embodiment, the memory 102 stores instructions to be executed by the processor 106 for generating the API. The memory 102 may include non-volatile storage elements. Examples of such non-volatile storage elements may include magnetic hard discs, optical discs, floppy discs, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories. In addition, the memory 102 may,in some examples, be considered a non-transitory storage medium. The term “non-transitory” may indicate that the storage medium is not embodied in a carrier wave or a propagated signal. However, the term “non-transitory” should not be interpreted as the memory 102 is non-movable. In certain examples, a non-transitory storage medium may store data that can, over time, change (e.g., in Random Access Memory (RAM) or cache).

[0024] The non-transitory storage medium may be interchangeably referred to as a non- transitory computer-readable medium for storing the instructions. The instructions may include one or more instructions that, when executed by the UE, cause one or more processors of the UE to perform steps disclosed in FIGS. 3A-4. The one or more processors may interchangeably be referred to as the processor 106 within the scope of the present invention.

[0025] The processor 106 communicates with the memory 102 via the communicator 104. The processor 106 may be configured to execute instructions stored in the memory 102 and to perform various processes for generating the API specification, as discussed throughout the disclosure. The processor 106 may include one or a plurality of processors, may be a general- purpose processor, such as a Central Processing Unit (CPU), an Application Processor (AP), or the like, a graphics-only processing unit such as a Graphics Processing Unit (GPU), a Visual Processing Unit (VPU), and / or an Artificial intelligence (Al) dedicated processor such as a Neural Processing Unit (NPU).

[0026] In one or more embodiments, the processor 106 may include a user interface module 108 and an API module 110. The API module 110 may be implemented by processing circuitry such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like. The user interface module 108 and the API module 110 may execute multiple operations to generate the insight report and the revised API, which is explained in conjunction with FIG. 2.

[0027] FIG. 2 illustrates an exemplary sequence flow diagram depicting one or more operations performed by the system 100 for generating the insight report and / or revised the API specification, according to an embodiment as disclosed herein.

[0028] In one or more embodiments, a user interface may be configured to enable a user to input requests, associated with the generation of the insight report and / or the revised API specification. In an exemplary embodiment, at block 202a, the user interface module 108 of the system 100 may be configured to receive the input API specification provided by the user to the user interface, along with the request to ensure compliance of the input API specification with a set of predefined parameters. In an embodiment, the set of predefined parameters indicates standard operating guidelines for the operations of the API specification which are stored in a database of the memory 102. Preferably, the set of predefined parameters are standard parameters for one or more APIs, which enable the generation of the revised API specification by modifying the input API specification which is discussed in the below paragraphs.

[0029] In another exemplary embodiment, at block 202b, the user interface module 108 may be configured to receive the request for generating the revised API specification that may comply with the predefined set of parameters. In yet another exemplary embodiment, the user interface module 108 may be configured to receive other requests provided by the user to the user interface. For example, the user may provide a request as “What are the predefined set of parameters, and how does an open API work?”

[0030] In various embodiments, the present disclosure is explained in reference to the validation of the input API specification and the set of predefined parameters for the generation of the API specification.

[0031] At block 204, the user interface module 108 may further be configured to share the user requests with the API module 110 to enable identification of a user-intent of the user. At block 206, the API module 110 may be further configured to verify the user-intent of the user based on the identification of the user intent. The user-intent herein refers to a query intent or search intent, which may be an identification of what the user wants to get in response based on the user requests. Preferably, the API module 110 may be configured to identify the user-intent based on a user input and the input API specification. Preferably, at block 208, the API module 110 may be configuredto validate compliance of the input API specification to the set of predefined parameters. In an embodiment, the API module 110 may be configured to validate the compliance based on correlation using a Retrieval-Augmented Generation (RAG) technique in response to the user request received at block 202a. In an embodiment, the set of predefined parameters may be stored in the database of the memory 102 to ensure the compliance of the input API specification received from the user which is discussed in the below paragraphs.

[0032] In various embodiments, at block 208a, the set of predefined parameters may be obtained from an open API architecture and stored in the database of the memory 102. Further, at step 208b, the API module 110 may be configured to receive the set of predefined parameters from the database of the memory 102. The open API architecture herein refers to an architecture that includes documentation with the set of predefined parameters based on the user request.

[0033] In an embodiment, at block 208b, the API module 110 may be configured to retrieve the set of predefined parameters from the database of the memory 102 based on the user input and the input API specification to validate the compliance of the input API specification using the RAG technique. In an embodiment, the compliance indicates a contextual association of the input API specification with the set of predefined parameters.

[0034] In the embodiment, the set of predefined parameters is correlated with each of one or more corresponding sections of the input API specification using the RAG technique. The RAG technique merges the capabilities of two distinct types of models, i.e., a retriever and a generator. In essence, the retriever scans the input API specification and the set of predefined parameters to identify text of relevancy based on the user input, which the generator then uses to construct a detailed and coherent response.

[0035] Preferably, the RAG technique may include a step of retrieving data associated with the set of predefined parameters. The data is converted into numerical representations and stored in a vector database. A next step is to perform a relevancy search in which the input API specification is converted to a vector representation and matched with the vector database. In an embodiment, the relevancy is calculated and established using mathematical vector calculations and representations. Thereafter, the RAG technique augments the one or more corresponding sections of the input API specification by adding the text of relevancy, thereby enabling thegenerative ML model 105 to validate the compliance the one or more corresponding sections of the input API specification with the set of predefined parameters.

[0036] At block 210, the API module 110 may be further configured to implement the RAG technique to generate a prompt for executing the generation of the insight report based on the validation. Preferably, at block 212a, the API module 110 may be configured to generate the insight report based on the validation. The insight report includes at least one of validated compliance instances and non-validated compliance instances. The insight report further includes an identification of at least one structural parameter missing or incorrect in the input API specification. In the embodiment, the insight report may include detailed descriptions of the validated compliance instances and the non-validated compliance instances for each of the correlated sections of the input API specification. In an embodiment, the insight report may be published in the user interface for the user via the user interface module 108. This may enable the user to view differences between the input API specification and the set of predefined parameters.

[0037] Preferably, the “validated compliance instances” herein refer to attributes that are in compliance with at least some attributes of the input API specification. For example, the input API specification may include the attributes in a text form that matches the attributes of the predefined set of parameters, thereby enabling the validation of the attributes of the input API specification as the validated compliance instances.

[0038] Preferably, the “non-validated compliance instances” herein refer to features that are not in compliance with at least some features of the input API specification. For example, the input API specification may include the attributes in a text form that does not match with the attributes of the predefined set of parameters, thereby enabling the validation of the attributes of the input API specification as the non-validated compliance instances.

[0039] In various embodiments, the validated compliance instances and the non-validated compliance instances are highlighted in the insight report. For example, the validated compliance instances are highlighted with a blue color, and non-validated compliances are highlighted with a red color.

[0040] In one embodiment, the insight report may further include suggestions for corrections or improvements to the input API specification to ensure compliance with the set of predefined parameters.

[0041] At block 214, the API module 110 may be configured to generate the revised API specification for Create, Read, Update, and Delete (CRUD) operations based on the insight report. Preferably, the API module 110 modifies the input API specification based on the generated insight report to generate the revised API specification.

[0042] The CRUD operations may be performed on persistent data structures like files. For example, the user may create a Microsoft Word document, update it, read it, and even delete it from the file explorer.

[0043] Preferably, the API module 110 may be configured to retrieve the set of predefined parameters corresponding to the user request and the input API specification. In an embodiment, the API module 110 may be configured to correlate the insight report with the input API specification using the generative ML model 105. Preferably, the generative ML model 105 identifies at least one of the non-validated compliance instances, incorrect or missing parameters from the insight report, and based on identification, the generative ML model 105 may add the least one of the non-validated compliance instances, incorrect or missing parameters in the input API specification to generate the revised API specification such that the revised API specification is compliant with the set of predefined parameters.

[0044] In another embodiment of the present disclosure, the revised API specification may be generated based on the user request. In an embodiment, the user request herein indicates a request that is input by the user for directly generating the API specification without the generation of the insight report. The revised API specification may be in compliance with the set of predefined parameters. The user request indicates instructions for the generation of the revised API specification corresponding to at least one of, custom parameters and configurations for the revised API specification.

[0045] In an embodiment, to generate the revised API specification, at block 212b, the API module 110 may be configured to correlate the input API specification and the set of predefined parameters. In an embodiment, the input API specification and the set of predefined parametersare retrieved from the database. Thereafter, the input API specification is compared with the set of predefined parameters, thereby providing dissimilarity between the input API specification and the set of predefined parameters.

[0046] Further, at block 214, the API module 110 may be configured to generate the revised API specification for the Create, Read, Update, and Delete (CRUD) operations based on the correlation illustrated in block 212b. More specifically, the revised API specification enables the user to interact with the database or a data storage system for the CRUD operations.

[0047] Preferably, at block 216, the API module 110 may be configured to transmit the revised API specification to the user interface module 108 to publish the revised specification in the user interface.

[0048] Further, at block 218, a conformity certificate may be generated based on receiving the revised API specification from the API module 110. In an embodiment, the conformity certificate may be generated based on assessing the revised API specification corresponding to the set of predefined parameters via the open API architecture and stored in the database of the memory 102. The conformity certificate herein refers to a certificate of authorization that the revised specification is in compliance with the set of predefined parameters.

[0049] Further, at block 220, the user interface module 108 may be configured to publish the conformity certificate on the user interface based on receiving the conformity certificate. In an advantageous aspect, the conformity certificate is published for the user to provide a verification that the revised API specification complies with the set of predefined parameters.

[0050] In various embodiments, at block 222, the API module 110 may generate a response based on the insight report, which is shared with the user via the user interface module 108 in the user interface. The response herein refers to a reply which is generated after processing the user requests. For example, an Excel sheet may be generated which may include a list of the missing parameters.

[0051] At block 224, the API module 110 may be configured to check the accuracy of the validation based on the user feedback. In an embodiment, the API module 110 may be configured to determine an accuracy score associated with validation. The API module 110 may be further configured to compare the accuracy score with a predefined threshold score. In an embodiment, atblock 226, the API module 110 may be configured to train the generative ML model 105 when the accuracy score is below the predefined threshold score.

[0052] In an embodiment, the generative ML model 105 may be trained for predicting or determining the revised API specification based on the user feedback and the accuracy of the ML model. Preferably, a loss function is computed for measuring the dissimilarity between the generative ML model 105’s predictions and the actual data obtained. Thereafter, one or more parameters of the generative ML are optimized via one or more optimization techniques such as Grid search, Random search, Bayesian search, etc.

[0053] In another aspect of the present disclosure, a method 300 for generating the insight report and the revised API specification is disclosed which is explained in conjunction with FIGS. 3A-4

[0054] FIG. 3A illustrates a flowchart depicting an exemplary method 300 generating the insight report, according to an embodiment as disclosed herein. The method 300 begins with step 302 which may include receiving the input API specification from the user.

[0055] At step 304, the method 300 may include validating the compliance of the input API specification to the set of predefined parameters based on correlation using the generative Machine Learning (ML) model which is discussed in conjunction with FIG. 4.

[0056] FIG. 4 illustrates a flowchart depicting sub-steps of validating the compliance of the input API specification, according to an embodiment as disclosed herein. At sub-step 304a, the step 304 may include identifying the user-intent based on the user input and the input API specification.

[0057] Further, at sub-step 304b, the step 304 may include retrieving the set of predefined parameters from a database based on the user input and the input API specification. Thereafter, at sub- step 304c, the step 304 may include correlating the set of predefined parameters with each of the one or more corresponding sections of the input API specification using the RAG technique.

[0058] At step 304d, the step 304 may include validating the compliance of the input API specification based on the correlation. The compliance indicates the contextual association of the input API specification with the set of predefined parameters.

[0059] Referring back to FIG. 3 A, at step 306, the method 300 may include generating the insight report based on the validation. The insight report includes at least one of the validated compliance instances, the non-validated compliance instances, and further includes an identification of at least one structural parameter missing or incorrect in the input API specification.

[0060] In an embodiment, the insight report includes the detailed descriptions of the validated compliance instances and the non-validated compliance instances for each of the correlated section of the input API specification. The insight report may further include suggestions for corrections or improvements to the input API specification to ensure compliance with the set of predefined parameters.

[0061] FIG. 3B illustrates a flowchart depicting the method 300 including further steps for generating the revised API specification, according to an embodiment as disclosed herein.

[0062] At step 308, the method 300 may include retrieving the set of predefined parameters corresponding to the user request and the input API specification. The set of predefined parameters indicates standard operating guidelines for the operations of the revised API specification.

[0063] At step 310, the method 300 may include correlating the insight report with the input API specification using the generative ML model 105.

[0064] At step 312, the method 300 may include generating the revised API specification based on the correlation, such that the revised API specification is compliant with the set of predefined parameters.

[0065] In another embodiment, the revised API specification is generated based on the user request. In an embodiment, the user request indicates instructions for the generation of the revised API specification corresponding to at least one of the custom parameters and the configurations for the revised API specification.

[0066] Further, at step 314, the method 300 may include publishing the revised API specification on the user interface.

[0067] At step 316, the method 300 may include publishing the conformity certificate based on assessing the revised API specification corresponding to the set of predefined parameters. Further, at step 318, the method 300 may include training the generative ML model 105 based on a corpus of set of predefined parameters.

[0068] The various actions, acts, blocks, steps, or the like in the flow diagrams or sequence flow diagrams may be performed in the order presented, in a different order, or simultaneously. Further, in some embodiments, some of the actions, acts, blocks, steps, or the like may be omitted, added, modified, skipped, or the like without departing from the scope of the present disclosure.

[0069] The present disclosure has several advantages over the existing technologies, for example, which are stated below, a. Accurate validation of the input API specification with the set of predefined parameters. The present disclosure enables the implementation of the RAG technique to identify the at least one structural parameter missing or incorrect in the input API specification, thereby enabling accurate validation. b. Generation of the insight report. The present disclosure enables the generation of the insight report based on the validation of the input API specification, thereby enabling the user to view the generated insight report and share user feedback. c. Accurate generation of the API specification: The present disclosure enables automatic generation of the revised API specification in compliance with the set of predefined parameters. d. Pre-trained generative ML model: The present disclosure uses the generative ML model, which is pre-trained for various APIs, thereby enabling the accurate validation of the input API specification. e. No human intervention during the generation of the API specification: The present disclosure eliminates the need for human intervention, resulting in cost cost- effective and efficient way of generating the revised API specification.

[0070] FIG. 5 illustrates an embodiment of a device 500 associated with generation of the insight report and the revised API specification. As shown in FIG. 5, the device 500 includes a processor 510, a memory 520, a storage component 530, an input component 540, an output component 550, a communication interface 560, and a bus 570.

[0071] The processor 510, as used herein, means any type of computational circuit that may comprise hardware elements and software elements. The processor 510 may be embodied asa multi-core processor, a single core processor, or a combination of one or more multi-core processors and / or one or more single core processors, a distributed processing system, or the like. The processor 510 may be a Central Processing Unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), an application-specific integrated circuit (ASIC), or another type of processing component.

[0072] Memory 520 includes a non-transitory computer readable medium. Memory 520 includes a random-access memory (RAM), a read only memory (ROM), and / or another type of dynamic or static storage device (e.g., a flash memory, a magnetic memory, and / or an optical memory) that stores information and / or instructions for use by processor 510. The memory 520 comprises machine-readable instructions which are executable by the processor 510. These machine-readable instructions when executed by the processor 510 cause the processor 510 to perform one or more method steps of an embodiment described above.

[0073] Storage component 530 stores information and / or software related to the operation and use of the device 500. For example, storage component 530 may include a hard disk (e.g., a magnetic disk, an optical disk, a magneto-optic disk, and / or a solid-state disk), a compact disc (CD), a digital versatile disc (DVD), a floppy disk, a cartridge, a magnetic tape, and / or another type of non-transitory computer-readable medium, along with a corresponding drive.

[0074] Input component 540 is configured to receive information, such as user input. For example, the input component 540 may include, but not be limited to, a touch screen display, a keyboard, a keypad, a mouse, a button, a switch, and / or a microphone. Additionally, or alternatively, the input component 540 may include a sensor for sensing information (e.g., a global positioning system (GPS), an accelerometer, a gyroscope, and / or an actuator).

[0075] Output component 550 is configured to provide output information from the device 500. For example, the output component 550 may be, but not limited to, a display, a speaker, instructions to an external device, and / or one or more light-emitting diodes (LEDs).

[0076] Communication interface 560 is an interface that provides a communication connection to other devices, such as external devices and internal devices. The connection by the communication interface 560 can be a wired connection, a wireless connection, or a combination of wired and wireless connections, and can be a direct connection or an indirect connection via acommunication network that exists between the device 500 and other devices. In other words, the standard of the communication interface 560 is not limited.

[0077] The bus 570 acts as an interconnect between the processor 510, the memory 520, the storage component 530, the input component 540, the output component 550, and the communication interface 560 of the device 500. The bus 570 may include a wired interconnection or a wireless interconnection.

[0078] The number and arrangement of components shown in FIG. 5 are provided as an example. In practice, device 500 may include additional components, fewer components, different components, or differently arranged components than those shown in FIG. 5. Additionally, or alternatively, a set of components (e.g., one or more components) of device 500 may perform one or more functions described as being performed by another set of components of device 500. Further, one or more method steps described in any of the embodiments may be performed utilizing a plurality of devices 500 in communication with one another.[1], A method (300) comprising: receiving (302) an input API specification from a user; validating (304) a compliance of the input API specification to a set of predefined parameters based on correlation using a generative Machine Learning (ML) model (105), wherein the generative ML model (105) implements a Retrieval -Augmented Generation (RAG) technique; and generating (306) an insight report based on the validation, wherein the insight report includes at least one of validated compliance instances and non-validated compliance instances, and wherein the insight report further includes an identification of at least one structural parameter missing or incorrect in the input API specification.[2], The method (300) described in [1], comprising: generating a revised API specification for Create, Read, Update, and Delete (CRUD) operations based on at least one of, a user request and the insight report.[3], The method (300) described in any one of [1] or [2], wherein generating the revised API specification comprises: retrieving (308) the set of predefined parameters corresponding to the user request and the input API specification, wherein the set of predefined parameters indicate standard operating guidelines for the operations of the revised API specification; correlating (310) the insight report with the input API specification using the generative ML model (105); and generating (312) the revised API specification based on the correlation, such that the revised API specification is compliant with the set of predefined parameters.[4], The method (300) described in any one of [1] to [3], comprising: publishing (314) the revised API specification on a user interface; and publishing (316) a conformity certificate based on assessing the revised API specification corresponding to the set of predefined parameters.[5], The method (300) described in any one of [1] to [4], wherein the user request indicates instructions for generation of the revised API specification corresponding to at least one of, custom parameters and configurations for the revised API specification.[6], The method (300) described in any one of [1] to [5], comprising: training (318) the generative ML model (105) based on a corpus of set of predefined parameters indicating standard operating guidelines for the operations of the API specification.[7], The method (300) described in any one of [1] to [6], wherein validating the compliance comprises: identifying (304a) a user-intent based on a user input and the input API specification;retrieving (304b) the set of predefined parameters from a database based on the user input and the input API specification, wherein the set of predefined parameters indicate standard operating guidelines for the operations of the API specification; correlating (304c) the set of predefined parameters with each of one or more corresponding sections of the input API specification using the RAG technique; and validating (304d) the compliance of the input API specification based on the correlation, wherein the compliance indicates contextual association of the input API specification with the set of predefined parameters.[8], The method (300) described in any one of [1] to [7], wherein the insight report comprises: detailed descriptions of the validated compliance instances and the non-validated compliance instances for each of the correlated section of the input API specification; and suggestions for corrections or improvements to the input API specification to ensure compliance with the set of predefined parameters.[9], A system (100) configured to: receive an input API specification from a user; validate a compliance of the input API specification to a set of predefined parameters based on correlation using a generative Machine Learning (ML) model, wherein the generative ML model (105) implements a Retrieval-Augmented Generation (RAG) technique; and generate an insight report based on the validation, wherein the insight report includes at least one of validated compliance instances and non-validated compliance instances, and wherein the insight report further includes an identification of at least one structural parameter missing or incorrect in the input API specification.

[0010] , The system (100) described in [9], wherein the system is configured to: generate a revised API specification for Create, Read, Update, and Delete (CRUD) operations based on at least one of, a user request and the insight report.

[0011] , The system (100) described in any one of [9] or

[0010] , wherein the system is configured to: retrieve the set of predefined parameters corresponding to the user request and the input API specification, wherein the set of predefined parameters indicates standard operating guidelines for the operations of the revised API specification; correlate the insight report with the input API specification using the generative ML model (105); and generate the revised API specification based on the correlation, such that the revised API specification is compliant with the set of predefined parameters.

[0012] , The system (100) described in any one of [9] to

[0011] , wherein the system is configured to: publish the revised API specification on a user interface; and publish a conformity certificate based on assessing the revised API specification corresponding to the set of predefined parameters.

[0013] , The system (100) described in any one of [9] to

[0012] , wherein the user request indicates instructions for generation of the revised API specification corresponding to at least one of, custom parameters and configurations for the revised API specification.

[0014] , The system (100) described in any one of [9] to

[0013] , wherein the system is configured to: train the generative ML model (105) based on a corpus of set of predefined parameters indicating standard operating guidelines for the operations of the API specification.

[0015] , The system (100) described in any one of [9] to

[0014] , wherein the system is configured to:identify a user-intent based on a user input and the input API specification; retrieve the set of predefined parameters from a database based on the user input and the input API specification, wherein the set of predefined parameters indicate standard operating guidelines for the operations of the API specification; correlate the set of predefined parameters with each of one or more corresponding sections of the input API specification using the RAG technique; and validate the compliance of the input API specification based on the correlation, wherein the compliance indicates contextual association of the input API specification with the set of predefined parameters.

[0016] , The system (100) described in any one of [9] to

[0015] , wherein the insight report comprises: detailed descriptions of the validated compliance instances and the non-validated compliance instances for each of the correlated section of the input API specification; and suggestions for corrections or improvements to the input API specification to ensure compliance with the set of predefined parameters.

[0017] , A non-transitory computer-readable medium storing instructions, the instructions comprising: one or more instructions that, when executed by a user equipment (UE), cause one or more processors of the UE to: receive (302) an input API specification from a user; validate (304) a compliance of the input API specification to a set of predefined parameters based on correlation using a generative Machine Learning (ML) model, wherein the generative ML model (105) implements a Retrieval-Augmented Generation (RAG) technique; and generate (306) an insight report based on the validation, wherein the insight report includes at least one of validated compliance instances and non-validated compliance instances, and wherein the insight report further includes an identification of at least one structural parameter missing or incorrect in the input API specification.

[0079] The embodiments disclosed herein can be implemented through at least one software program running on at least one hardware device and performing network management functions to control the elements. The elements can be at least one of a hardware device or a combination of hardware devices and software modules.

[0080] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.

[0081] The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein.

[0082] Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. Numerous variations, whether explicitly given in the specification or not, such as differences in structure, dimension, and use of material, are possible. The scope of embodiments is at least as broad as given by the following claims.

[0083] Benefits, other advantages, and solutions to problems have been described above with regard to specific embodiments. However, the benefits, advantages, solutions to problems, and any component(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential feature or component of any or all the claims.

[0084] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and / or adapt for various applications such specific embodiments without departing fromthe generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of at least one embodiment, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.

Claims

CLAIMSWe Claim:

1. A method comprising: receiving an input API specification from a user; validating a compliance of the input API specification to a set of predefined parameters based on correlation using a generative Machine Learning (ML) model, wherein the generative ML model implements a Retrieval-Augmented Generation (RAG) technique; and generating an insight report based on the validation, wherein the insight report includes at least one of validated compliance instances and non-validated compliance instances, and wherein the insight report further includes an identification of at least one structural parameter missing or incorrect in the input API specification.

2. The method as claimed in claim 1, comprising: generating a revised API specification for Create, Read, Update, and Delete (CRUD) operations based on at least one of, a user request and the insight report.

3. The method as claimed in claim 2, wherein generating the revised API specification comprises: retrieving the set of predefined parameters corresponding to the user request and the input API specification, wherein the set of predefined parameters indicate standard operating guidelines for the operations of the revised API specification; correlating the insight report with the input API specification using the generative ML model; and generating the revised API specification based on the correlation, such that the revised API specification is compliant with the set of predefined parameters.

4. The method as claimed in claim 3, comprising: publishing the revised API specification on a user interface; andpublishing a conformity certificate based on assessing the revised API specification corresponding to the set of predefined parameters.

5. The method as claimed in claim 2, wherein the user request indicates instructions for generation of the revised API specification corresponding to at least one of, custom parameters and configurations for the revised API specification.

6. The method as claimed in claim 1, comprising: training the generative ML model based on a corpus of set of predefined parameters indicating standard operating guidelines for the operations of the API specification.

7. The method as claimed in claim 1, wherein validating the compliance comprises: identifying a user-intent based on a user input and the input API specification; retrieving the set of predefined parameters from a database based on the user input and the input API specification, wherein the set of predefined parameters indicate standard operating guidelines for the operations of the API specification; correlating the set of predefined parameters with each of one or more corresponding sections of the input API specification using the RAG technique; and validating the compliance of the input API specification based on the correlation, wherein the compliance indicates contextual association of the input API specification with the set of predefined parameters.

8. The method as claimed in claim 1, wherein the insight report comprises: detailed descriptions of the validated compliance instances and the non-validated compliance instances for each of the correlated section of the input API specification; and suggestions for corrections or improvements to the input API specification to ensure compliance with the set of predefined parameters.

9. A system configured to:receive an input API specification from a user; validate a compliance of the input API specification to a set of predefined parameters based on correlation using a generative Machine Learning (ML) model, wherein the generative ML model implements a Retrieval-Augmented Generation (RAG) technique; and generate an insight report based on the validation, wherein the insight report includes at least one of validated compliance instances and non-validated compliance instances, and wherein the insight report further includes an identification of at least one structural parameter missing or incorrect in the input API specification.

10. The system as claimed in claim 9, wherein the system is configured to: generate a revised API specification for Create, Read, Update, and Delete (CRUD) operations based on at least one of, a user request and the insight report.

11. The system as claimed in claim 10, wherein the system is configured to: retrieve the set of predefined parameters corresponding to the user request and the input API specification, wherein the set of predefined parameters indicates standard operating guidelines for the operations of the revised API specification; correlate the insight report with the input API specification using the generative ML model; and generate the revised API specification based on the correlation, such that the revised API specification is compliant with the set of predefined parameters.

12. The system as claimed in claim 11, wherein the system is configured to: publish the revised API specification on a user interface; and publish a conformity certificate based on assessing the revised API specification corresponding to the set of predefined parameters.

13. The system as claimed in claim 10, wherein the user request indicates instructions for generation of the revised API specification corresponding to at least one of, custom parameters and configurations for the revised API specification.

14. The system as claimed in claim 9, wherein the system is configured to: train the generative ML model based on a corpus of set of predefined parameters indicating standard operating guidelines for the operations of the API specification.

15. The system as claimed in claim 1, wherein the system is configured to: identify a user-intent based on a user input and the input API specification; retrieve the set of predefined parameters from a database based on the user input and the input API specification, wherein the set of predefined parameters indicate standard operating guidelines for the operations of the API specification; correlate the set of predefined parameters with each of one or more corresponding sections of the input API specification using the RAG technique; and validate the compliance of the input API specification based on the correlation, wherein the compliance indicates contextual association of the input API specification with the set of predefined parameters.

16. The system as claimed in claim 9, wherein the insight report comprises: detailed descriptions of the validated compliance instances and the non-validated compliance instances for each of the correlated section of the input API specification; and suggestions for corrections or improvements to the input API specification to ensure compliance with the set of predefined parameters.

17. A non-transitory computer-readable medium storing instructions, the instructions comprising: one or more instructions that, when executed by a user equipment (UE), cause one or more processors of the UE to: receive an input API specification from a user;validate a compliance of the input API specification to a set of predefined parameters based on correlation using a generative Machine Learning (ML) model, wherein the generative ML model implements a Retrieval-Augmented Generation (RAG) technique; and generate an insight report based on the validation, wherein the insight report includes at least one of validated compliance instances and non-validated compliance instances, and wherein the insight report further includes an identification of at least one structural parameter missing or incorrect in the input API specification.

Images