Abstract: Systems and methods for responsible AI compliance and governance management in AI Products are disclosed. The system receives a request to assess an enterprise product associated with a specific application. Further, the system may determine a plurality of datasets associated with the AI model of the enterprise product. Furthermore, the system generates a training dataset and a test dataset for the determined plurality of datasets associated with the AI model. The system generates a ranked list of recommended metrics for the enterprise product based on the generated training dataset and the test dataset. The system further determines a mitigation strategy for the enterprise product based on the generated ranked list of recommended metrics. Furthermore, the system creates a feedback loop for continuous training and tuning the AI model and the plurality of datasets based on the determined mitigation strategy.

Abstract: Artificial intelligence (AI)-based systems and methods for AI application development using codeless creation of AI workflows is disclosed. The system receives request for creating an artificial intelligence (AI)-based workflow from the user device. Further, the system obtains input data from data sources and pre-process the obtained data using AI based pre-processing model. Further, the system identifies plurality of AI and Generative AI service nodes to be executed on the pre-processed data. The system further generates an AI-based workflow by connecting AI and Generative AI service nodes. Further, the system generates a metadata for AI and Generative AI service nodes by executing each of the identified plurality of AI and Generative AI service nodes. The system validates the metadata based on AI-based rules. Furthermore, the system determines actions to be performed on the metadata based on results of validation and performs the set of actions on the AI-based workflow.

Abstract: In some examples, machine learning and rule-based identification, anonymization, and de-anonymization of sensitive structured and unstructured data may include receiving input data that is to be masked, and determining, for the input data, at least one type '1 of entity extraction from a plurality of types of entity extractions to be performed on the input data. The at least one determined type of entity extraction may be performed on the input data, and at least one entity may be extracted from the input data. At least one replacement strategy may be determined from a plurality of replacement strategies for the at least one extracted entity. Further, the at least one determined replacement strategy may be applied to the at least one extracted entity to generate masked data.

Abstract: The proposed systems and methods are directed to explainability-augmented AI systems. These systems are configured to automatically identify, based on one or more of metadata associated with labels assigned to sample data and responses to AI-system-related questionnaires, one or more reasons that support the decisions made by an AI model in response to user queries. The proposed systems apply natural language processing (NLP) to transform the explainability data (e.g., metadata and questionnaire data) to generate human reader-friendly output that summarizes the reasoning by which the AI system made a specific decision and offer transparency to the AI-decision-making process.

Abstract: The validity of engineering drawings is automatically determined based on compliance of the specifications of the engineering drawings with automatically generated rules. A document package including images of the engineering drawings and related documents is received. Rules codifying the requirements to be fulfilled by the engineering drawings are automatically generated from the related documents. Data such as specifications of the various parts of the entities in the engineering drawings are automatically extracted. The extracted data is analyzed to determine compliance with the rules to validate the engineering drawings.

Abstract: In some examples, structure-based multi-intent email classification may include receiving an email thread that includes a plurality of emails including an email that is to be classified, and identifying, for the email thread, a process associated with the email thread, Based on the process associated with the email thread and for each sentence of the email that includes a plurality of sentences, a corresponding classifier may be determined from a plurality of classifiers, and applied to each sentence of the email to generate classified sentences. At least one entity may be extracted from each of the classified sentences of the email. Based on the at least one extracted entity, the email may be classified.

Abstract: In some examples, machine learning and rule-based identification, anonymization, and de-anonymization of sensitive structured and unstructured data may include receiving input data that is to be masked, and determining, for the input data, at least one type 1 of entity extraction from a plurality of types of entity extractions to be performed on the input data. The at least one determined type of entity extraction may be performed on the input data, and at least one entity may be extracted from the input data. At least one replacement strategy may be determined from a plurality of replacement strategies for the at least one extracted entity. Further, the at least one determined replacement strategy may be applied to the at least one extracted entity to generate masked data.

Abstract: In some examples, structure-based multi-intent email classification may include receiving an email thread that includes a plurality of emails including an email that is to be classified, and identifying, for the email thread, a process associated with the email thread, Based on the process associated with the email thread and for each sentence of the email that includes a plurality of sentences, a corresponding classifier may be determined from a plurality of classifiers, and applied to each sentence of the email to generate classified sentences. At least one entity may be extracted from each of the classified sentences of the email. Based on the at least one extracted entity, the email may be classified.

Abstract: Examples of artificial intelligence-based reasoning explanation are described. In an example implementation, a knowledge model having a plurality of ontologies and a plurality of inferencing rules is generated. Once the knowledge model is generated, based on a real-world problem, a knowledge model from amongst various knowledge models is selected to be used for resolving a real-world problem. The data procured from the real-world problem is clustered and classified into an ontology of the determined knowledge model. Inferencing rules to be used for deconstructing the real-world problem are identified, and a machine reasoning is generated to provide a hypothesis for the problem and an explanation to accompany the hypothesis.

Abstract: In an example, an ontology analyzer may generate an ontology, based on a claim adjudication request. The claim adjudication request may be processed, based on the ontology to provide an ontology based inference. A rule based analyzer may identify a predefined rule corresponding to the claim adjudication request and process the request, based on the predefined rule. A conflict resolver may resolve a conflict which may occur between the ontology based inference and the rule based inference. When a conflict is detected, a predefined criteria may be selected for resolving the conflict, the predefined criteria comprising rules to select one of the ontology based inference and the rule based inference to maximize a probability of accurately processing the claim adjudication request in case of a conflict.

Abstract: Examples of cognitive procurement are described. In an example embodiment, procurement-specific data sources associated with at least one of a process, an organization, and an industry relevant for procurement operations are monitored. From the monitored procurement-specific data, an operation behavioral pattern is identified. Subsequently, a behavior model of an order is constructed using the operation behavioral pattern and a pre-existing behavior model library. A procurement interaction indicating a query for processing the order is received from a user. The order is tracked by the cognitive order concierge. Using the behavior model, a potential event relating to the order is predicted, the potential event being indicative of an issue affecting the order. Accordingly, the issue affecting the order is proactively remediated to automatically troubleshoot the order. In an example, the user is notified as per the remediation requirement.

Abstract: The validity of engineering drawings is automatically determined based on compliance of the specifications of the engineering drawings with automatically generated rules. A document package including images of the engineering drawings and related documents is received. Rules codifying the requirements to be fulfilled by the engineering drawings are automatically generated from the related documents. Data such as specifications of the various parts of the entities in the engineering drawings are automatically extracted. The extracted data is analyzed to determine compliance with the rules to validate the engineering drawings.

Abstract: Examples of employee concierge are provided. In an example, an issue may be determined for an employee. The issue may be determined based on a query shared by the employee or upon occurrence of an unusual event. The unusual event may be indicative of a deviation in behaviour and routine of the employee. A session may be initiated and the issue may be parsed to determine a context. A bot may be selected from multiple bots for the issue where each bot includes information relating to a solution to address the issue. Data associated with the issue may be collected from a central database and other bots. The data may then be analyzed to determine a solution. The solution comprises a response to the query and a suggestion to mitigate the unusual event.

Abstract: Examples of automated order troubleshooting are described. In an example embodiment, sales-specific data sources associated with at least one of a process, an organization, and an industry relevant for sales operations are monitored. From the monitored sales-specific data, an operation behavioral pattern is identified, based on predefined rules. Subsequently, a behavior model capturing the operation behavioral pattern is constructed using a pre-existing behavior model library. Using the behavior model, a potential event relating to an order received to be fulfilled using the sales operation is predicted, the potential event being indicative of an issue affecting the order. Accordingly, the issue affecting the order is proactively remediated to automatically troubleshoot the order.

Abstract: Systems and methods for orchestrating a process are disclosed. In an implementation, a system is configured to extract process information associated with the process. Based on the process information, the system is configured to determine a current model of performing the process based on the process information. The system is further configured to retrieve regulatory information associated with the process, wherein the regulatory information is indicative of at least one of a predefined policy, a predefined rule, and a predefined regulation associated with the process. Further, the system is configured to update the current model based on at least one of the process information and the regulatory information for obtaining a predefined outcome of the process.

Abstract: A model optimization system monitors a model deployed to an external system to determine the performance of the model and to replace the model with one of a plurality of models stored to a model repository if degradation of model performance is detected or if one of the models in the plurality of models is evaluated as having better performance than the model deploy the external system. A model evaluation trigger can be generated based on dates or data criteria. Various metrics are used in the model evaluation to calculate values of a model optimization function for each of the plurality of models. If a model that is better optimized than the deployed model is identified from the model evaluation, then the deployed model is replaced with the identified model and the external system continues to use the deployed model.

Abstract: A data extraction and expansion system receives documents with data to be processed, extracts a set of a specific type of entities from the received documents, expands the set of entities by retrieving additional entities of the specific type from an ontology and other external data sources to improve the match between the received documents. The ontology includes data regarding entities and relationships between entities. The ontology is built by extracting the entity and relationship information from external data sources and can be constantly updated. If the additional entities to expand the set of entities cannot be retrieved from the ontology then a real-time search of the external data sources is executed to retrieve the additional entities from the external data sources.

Abstract: Examples of medical concierge are provided. In an example, an claim may be received. The claim may include data relating to service provided, by a provider, to multiple patients. The claim may be parsed to determine the provider, the multiple patients and the service provided. Additional information may then be fetched. The additional information may include one of a number of claims filed in the past, status of each claim, number of appeals filed, status of the appeals, and complaints registered by the provider. Thereafter, the claim and the additional information may be analyzed and a category may be determined for the provider. The category may be determined based on a behaviour model that may be computed based on the claim and the additional information. The category may be indicative of an issue in behaviour of the provider.

Abstract: Data from multiple sources may be gathered continuously to perform reconciliation operations. The data items in a first data set may be matched with those in the second data set using a data matching technique. Based on the matching, a confidence score indicative of an extent of match between the data items in the data sets may be generated. Based on the confidence score and predefined thresholds, it may be ascertained if the data items are reconciled. The non-reconciled items in at least one of the first data set and the second data set may be classified in a classification category, based on an artificial intelligence based technique, the classification category being indicative of an explanation of a non-reconciled data item being non-reconcilable. When the data item is not reconciled and classified, the data item is identified as an open item for further analysis.

Abstract: A system for determining a response to a query includes a receiver to receive a query along with a plurality of potential responses to the query. A detector detects a topic and a type of the query based on information extracted from text and structure. Further, a selector selects at least one of a plurality of techniques for processing the query and the plurality of potential responses, based on the topic and the type of the query. An obtainer obtains an answer by execution of each of the selected techniques for processing the query and the plurality of potential responses along with an associated confidence score. A determinator determines one of obtained answers as a correct response to the query, based on a comparison between confidence scores associated with the answers.