Abstract: A method and system for evidencing skills of a developer are disclosed. The method includes extracting, from various databases, a list of terms and definitions for identifying skills, and grouping the identified skills for forming at least one ontology based on similarity. The method further includes acquiring raw data and performing data cleaning on the raw data for identifying at least one domain-specific skill. Subsequently, skill matching is performed by comparing the at least one domain-specific skill against the at least one ontology for determining that the at least one ontology is evidenced for the developer. The method further includes performing analytics to display the evidenced at least ontology and corresponding level, and automatically assigning the at least one task based on the performed analytics.

Abstract: Various methods and processes, apparatuses or systems, and media for using a semantic search approach for identifying and recommending testing software artefacts for reuse for testing new software functionality are disclosed. The method includes: receiving stories that include natural language textual descriptions of sets of user requirements; converting, by using a predetermined text vectorization technique, each story into a respective embedding that includes a respective vector representation thereof; receiving a new story, and converting the new story into a new embedding; comparing the new embedding to each respective embedding, and generating a respective similarity score that relates to a respective semantic similarity between the respective embedding and the new embedding; for each respective embedding having a high similarity score, identifying testing artefact(s) that are associated with the respective story; and generating a list of recommendations based on the identified testing artefact(s).

Abstract: A method and system for determining and mitigating a potential delay in task completion are disclosed. The method includes extracting previously resolved tasks and changes occurred to each of the previously resolved tasks, and calculating features for training a machine learning model. The method further includes dividing the tasks into different groups and training the machine learning model using the calculated features associated with the different groups. The method then starts a task and partially processes the respective task until reaching a cutoff time, and based on change history of the task up to the cutoff time and using the trained machine learning model, determines whether a delay is expected or not for the task.

Abstract: A method for using a graph neural network framework to improve learning and predicting in a multiplex network environment is provided. The method includes: identifying a plurality of layers of a multiplex network; estimating, for each layer, a corresponding probability of selecting the layer as being a relevant layer for training with respect to an application; estimating, for each layer, a corresponding loss associated with selecting the layer as being relevant; calculating, for each layer based on the corresponding probability and the corresponding loss, a corresponding regret associated with selecting the layer as being relevant; determining, for each layer based on the calculated corresponding regret, whether to select the layer as being relevant; and training the multiplex network with respect to the application by aggregating information obtained from layers that have been determined as being relevant layers.

Abstract: A method and a system for performing domain adaptations of social media text by using lexical data transformations are provided. The method includes: receiving a first data set that is usable for training a machine learning (ML) model that is designed to perform natural language processing tasks; training the ML model by using the first data set; receiving a second data set that relates to a social media platform; transforming a subset of the first data set into a third data set that is suitable for the social media platform; and retraining the ML model by using a combination of the first data set, the second data set, and the third data set. The transformations may include injecting emojis, emoticons, user mention indicators, hashtags, retransmission indicators, URLs, and/or inverse lexical normalizations that are often used in social media posts.

Abstract: A method and system for automatically converting a software rule code specifying a policy rule into a human comprehensible document are disclosed. The method includes receiving the software rule code; obfuscating the software rule code prior to submission to a machine learning (ML) model; decomposing the obfuscated software rule code into at least one then block and at least one when block; performing code logic simplification on the at least one then block for separating the at least one then block into at least one logic and at least one action; creating a truth table using the at least one logic; constructing a decision table by combining the truth table, the at least one when block and the at least one action; and outputting the human comprehensible document for display on the display screen.

Abstract: A method and a system for preparing a response to a subpoena by using an automated subpoena processing and handling model is provided. The method includes: receiving a first subpoena; extracting a set of informational requests from the first subpoena; retrieving a data set from a memory; analyzing the first data set with respect to the set of informational requests in order to identify items from within the data set that are responsive to items included within the set of informational requests; and generating a report that includes a result of the analysis. The analysis is performed by providing the first subpoena as an input to a Robustly optimized Bidirectional Encoder Representations from Transformers pre-training approach (RoBERTa) model that uses a sub-word approach to modeling words in a sequential format.

Abstract: A method and system for reducing context length in processing a codebase using large language model (LLM) are disclosed. The method includes receiving the codebase including multiple files for processing, generating, via the LLM, summaries based on the multiple files, and subsequently organizing the summaries based on a structure of the codebase. The method further includes determining a downstream task, determining whether the downstream task requires a summary of a code or the code itself, and transmitting the summary or the code to the downstream task for executing the downstream task.

Abstract: A system for correcting a Structured Query Language (SQL) dialect conversion error. The system may include a processor and memory that stores instructions that, when executed by the processor, cause the processor to perform operations. The operations may include: receiving a first partially converted SQL file that has been partially converted from a first SQL dialect into a second SQL dialect; extracting, from the first partially converted SQL file, at least one first unconverted SQL snippet; deriving at least one first transformation; determining whether the at least one first transformation includes an appropriate set of at least one transformation for correcting a corresponding SQL conversion error; and associating the appropriate set of at least one transformation with the at least one first unconverted SQL snippet.

Abstract: A method and a system for automatically performing specialized due diligence for politically exposed persons in order to evaluate risk levels associated therewith are provided. The method includes: receiving a first data set that includes a name of a person and a list of positions associated with the person; extracting, from the first data set, first additional information that relates to the person; identifying, for each respective position included in the list of positions, a corresponding category from among a set of positional categories; retrieving, from at least one publicly accessible information source, second additional information that relates to the person; analyzing each of the first data set, the first additional information, and the second additional information in order to obtain answers to questions from among a predefined set of questions; and generating a due diligence report based on a result of the analysis.

Abstract: Systems and methods for extracting information from a resume of an applicant are provided. The method includes: receiving a resume that relates to an applicant; extracting information that relates to applicant attributes from the resume; comparing the extracted information with a predetermined list of job-specific skills and with a predetermined list of characteristics that relate to soft skills; using the extracted information to determine applicant achievements; and determining at least one skill that corresponds to the applicant. The method may be implemented by using a deep learning technique and/or a natural language processing technique.

Abstract: A method for automating a process of generating messages that are responsive to client inquiries by using an AI algorithm that implements a machine learning technique to ensure accuracy and timeliness in the responses is provided. The method includes: receiving a first message that includes an inquiry that relates to an account associated with a user; applying an AI algorithm for analyzing the first message in order to extract information that relates to the inquiry; determining, based on a result of the analysis, whether generating a response to the inquiry requires human intervention; when human intervention is not required, retrieving information that is responsive to the inquiry from a memory; generating a second message that includes the information that is responsive to the inquiry; and transmitting the second message to the user.

Abstract: A method and system for evidencing skills of a developer are disclosed. The method includes extracting, from various databases, a list of terms and definitions for identifying skills, and grouping the identified skills for forming at least one ontology based on similarity. The method further includes acquiring raw data and performing data cleaning on the raw data for identifying at least one domain-specific skill. Subsequently, skill matching is performed by comparing the at least one domain-specific skill against the at least one ontology for determining that the at least one ontology is evidenced for the developer. The method further includes performing analytics to display the evidenced at least ontology and corresponding level, and automatically assigning the at least one task based on the performed analytics.

Abstract: A method and a system for automatically processing financial documents to generate knowledge graphs that convey information relating to entities of interest and relationships between those entities are provided. The method includes: receiving a document; extracting raw text included in the document; identifying, based on the extracted raw text, a set of entities that are named in the document; determining respective relationship information that corresponds to respective pairs of entities; constructing a knowledge graph that illustrates respective relationships among the respective pairs of entities; and outputting the knowledge graph. The determination of the respective relationship information may be performed by applying an artificial intelligence (AI) algorithm that is trained by using historical data that relates to the set of entities.

Abstract: A method for automating a process of generating messages that are responsive to client inquiries by using an AI algorithm that implements a machine learning technique to ensure accuracy and timeliness in the responses is provided. The method includes: receiving a first message that includes an inquiry that relates to an account associated with a user; applying an AI algorithm for analyzing the first message in order to extract information that relates to the inquiry; determining, based on a result of the analysis, whether generating a response to the inquiry requires human intervention; when human intervention is not required, retrieving information that is responsive to the inquiry from a memory; generating a second message that includes the information that is responsive to the inquiry; and transmitting the second message to the user.

Abstract: A method and system for reducing context length in processing a codebase using large language model (LLM) are disclosed. The method includes receiving the codebase including multiple files for processing, generating, via the LLM, summaries based on the multiple files, and subsequently organizing the summaries based on a structure of the codebase. The method further includes determining a downstream task, determining whether the downstream task requires a summary of a code or the code itself, and transmitting the summary or the code to the downstream task for executing the downstream task.

Abstract: A method and system for determining and mitigating a potential delay in task completion are disclosed. The method includes extracting previously resolved tasks and changes occurred to each of the previously resolved tasks, and calculating features for training a machine learning model. The method further includes dividing the tasks into different groups and training the machine learning model using the calculated features associated with the different groups. The method then starts a task and partially processes the respective task until reaching a cutoff time, and based on change history of the task up to the cutoff time and using the trained machine learning model, determines whether a delay is expected or not for the task.

Abstract: A method and system for providing a video query are disclosed. The method includes acquiring context information, training a first machine learning (ML) model using historical data of the software life cycle tool, and removing, by the first ML model, noise from the context information for generating a query including at least one keyword. Once the query is generated, executing, by a second ML model, the query to retrieve at least one video segment from a learning repository. Scoring and ranking is then performed on the at least one video segment. The ranked video segment is then transmitted, to the user interface of the software life cycle tool, and displayed in an ad-hoc manner.

Abstract: A method and system for automatically converting a software rule code specifying a policy rule into a human comprehensible document are disclosed. The method includes receiving the software rule code; obfuscating the software rule code prior to submission to a machine learning (ML) model; decomposing the obfuscated software rule code into at least one then block and at least one when block; performing code logic simplification on the at least one then block for separating the at least one then block into at least one logic and at least one action; creating a truth table using the at least one logic; constructing a decision table by combining the truth table, the at least one when block and the at least one action; and outputting the human comprehensible document for display on the display screen.

Abstract: A method for providing action-based modeling to facilitate predictive analytics is disclosed. The method includes aggregating raw data from various sources, the raw data including application metadata; structuring the raw data to generate a primary data set; partitioning the primary data set to generate an action data set for predetermined actions, the action data set including a status label for each data point; generating a model for each of the predetermined actions; training the model based on the corresponding action data set; and determining an explanation for each of the predetermined actions based on the corresponding trained model, the explanation including a rule-based description in a natural language format.