Abstract: A system and method for upgrading an executable chatbot is disclosed. The system may include a processor including a fallout utterance analyzer, a response identifier, a deviation identifier, a flow generator and enhancer. The fallout utterance analyzer may receive chats logs comprising a plurality of utterances and corresponding bot responses. The fallout utterance analyzer may classify the plurality of utterances into multiple buckets pertaining to at least one of an out-of-scope intent, a newly identified intent, and a new variation of an existing intent. The response identifier may generate auto-generated responses corresponding to new intents for upgrading the executable chatbot. The deviation identifier may overlay corresponding intent in the chat logs with the prestored flow dialog network to designate an extent of deviation with respect to flow prediction performance by the executable chatbot.

Abstract: In some implementations, a device may receive extensibility data related to one or more custom code objects installed in a current environment. The device may classify the one or more custom code objects in one or more respective categories and determine one or more respective complexities associated with the one or more custom code objects based on the extensibility data. The device may generate an extensibility recommendation for deploying the one or more custom code objects to a target environment based on the one or more respective categories and the one or more respective complexities associated with the one or more custom code objects. The extensibility recommendation may be generated based on the one or more custom code objects satisfying extensibility conditions associated with the target environment. The device may provide an output relating to the extensibility recommendation.

Abstract: In some examples, policy-based application architecture generation may include generating, based on a knowledge model schema, data residency policies, and a data classification ontology, a knowledge model, and determining, based on the knowledge model, whether an application includes regulated data. Based on an analysis of application data and user data, user location and regulated data insights may be generated to determine location specific data residency policies. Location specific regulated data in-flow and data source hosted location insights may be analyzed to determine a location compliance assessment that includes an indication of whether a location associated with the application is compliant or not compliant with the location specific data residency policies.

Abstract: A device may receive demand data associated with a product or a service, multiple forecasting models, and multiple cost functions, and may identify primary parameters for the multiple models based on the demand data. The device may utilize a model to rank the multiple forecasting models and the multiple cost functions based on the primary parameters, and may select optimum primary parameters based on ranking the multiple forecasting models and the multiple cost functions. The device may identify secondary parameters for the multiple forecasting models based on the demand data and the optimum primary parameters. The device may select optimum secondary parameters based on ranking the multiple forecasting models and the multiple cost functions, and may select a forecasting model, from the multiple forecasting models, based on the optimum primary parameters and the optimum secondary parameters. The device may perform one or more actions based on selecting the forecasting model.

Abstract: In some implementations, a device may receive project management data including information related to project elements associated with one or more projects and associations among the project elements associated with the one or more projects. The device may generate one or more data structures representing the project elements associated with the one or more projects and the associations among the project elements associated with the one or more projects. The device may receive a request to visualize project data, wherein the request may indicate a view to use in order to visualize the project data and/or specify criteria related to the project data to be visualized in the view. The device may search the one or more data structures to obtain the project data to be visualized based on the criteria specified in the request. The device may render the project data using the view indicated in the request.

Abstract: This disclosure describes example implementations for generating context-dependent embedding vectors of words in the multi-dimensional embedding space based on a generic and non-domain-specific pretrained word embeddings. Such an implementation requires no domain specific training corpus and is capable of generating context-dependent embedding vectors of multi-semantic words using a few contextual texts. Such an implementation thus provides an efficient way to generate a library of multiple domain specific embedding vectors for multi-semantic words without any domain-specific training process. Other example embodiments further apply the principles of the context-dependent word embedding generation to a text-to-image application.

Abstract: In some examples, energy efficient collaboration for environmental social and governance (ESG) data consolidation and validation may include identifying, based on a global correlation graph, correlated ESG dimensions for each ESG data analyzer of a plurality of ESG data analyzers with respect to a set of ESG dimensions on which an ESG data analyzer of the plurality of ESG data analyzers collects data for at least one organization avatar entity (OAE) of a plurality of OAEs. In this regard, decentralized groups of collaborating ESG data analyzers may be generated based on a collaboration potential between the plurality of ESG data analyzers. For an ESG data analyzer that is collecting data and based on an associated updated data model, a potential anomalous ESG event may be identified at a specific ESG dimension. Further, operation of an OAE associated with the ESG data analyzer that is collecting data may be controlled.

Abstract: A device may receive work item data identifying work items associated with requirements from different tools of a project and may perform data cleansing to remove and/or modify particular words from the work item data and to generate cleansed work item data. The device may perform natural language processing on the cleansed work item data to identify synonyms for words in the cleansed work item data and may replace abbreviations in the cleansed work item data with full form text to generate final work item data. The device may identify keywords in the final work item data and may process the final work item data, the synonyms, and the keywords, with a machine learning model, to identify mappings between work items of the final work item data and to determine a confidence score for the mappings. The device may perform actions based on the mappings and the confidence score.

Abstract: A device may process, using a first model and based on an entity-specific task description that is included in entity role data and that is associated with a role, the entity role data to identify a task associated with the role. The device may determine, using a second model and based on the entity-specific task description and standardized descriptions of automation-capable tasks, a task automation score associated with the task. The device may determine, using a third model and based on a characteristic of the task and mappings of standardized characteristics to a plurality of automation categories, a set of automation category scores for the task. The device may classify, based on the set of automation category scores, the task as being associated with a particular automation category, and may perform an action associated with the task automation score and the particular automation category.

Abstract: A system and method for video authentication may apply machine learning to analyze whether a person's face captured by live video matches a face in a photo ID captured by live video and to analyze other features based on a video session with the person. For example, machine learning may be applied to analyze a set of features indicating whether the person is a real, live person (as opposed to a photo image held up over the person's face in the video, etc.). Finally, the machine learning may be applied to analyze a set of features to determine whether a lower probability prediction that the person's face captured by live video matches a face in a photo ID captured by live video should be either pass authentication (due to one or more features/circumstances mitigating the lower probability) or fail authentication (due to one or more features not mitigating the lower probability). In such a situation, the set of features may indicate that mitigating factors/conditions exist that can offset the lower probability.

Abstract: In some implementations, a device may receive data associated with a set of taxonomies, wherein a taxonomy, of the set of taxonomies, represents a classification of a set of relationships of data entries of the data. The device may integrate the set of taxonomies to generate a meta-taxonomy of the data. The device may generate a data graph of the data based on integrating the set of taxonomies to generate the meta-taxonomy, wherein the data graph is based on a graph-based search model that is associated with at least one of: taxonomy-based filtering, metadata attribute prioritization, or semantic matching. The device may store the data graph.

Abstract: Customer relationship management (“CRM”) implemented in a computer system, including parsing, by a parsing engine of the computer system into parsed triples of a description logic, words of a CRM event from an incoming stream of CRM events, the CRM event characterized by an event type, the stream implemented in a CRM application of the computer system; and inferring, by an inference engine from the parsed triples according to inference rules specific to the event type, inferred triples.

Abstract: A system for providing automated and domain specific contextual processing for context based verification may classify a plurality of extracted parameters from a set of digitized training document to assign a document similarity score with respect to a set of reference documents. The system may automatically detect a domain for the set of digitized training documents based on the document similarity score. The system may load a domain based neural model for the detected domain to generate a plurality of pre-defined contextual parameters. The system may receive a set of input documents and perform a contextual processing of the received set of documents based on the pre-defined contextual parameters to obtain an output in form of a plurality of filtered snippets, each bearing a corresponding rank. The context based verification may be performed based on the plurality of filtered snippets and the corresponding rank.

Abstract: A method and system for emotion recognition and forecasting are disclosed. The method may include obtaining an audio data of a conversation involving a plurality of speakers and identifying a plurality of turns of the conversation from the plurality of utterances. The method may further include extracting audio embedding features from the plurality of turns, obtaining a plurality of text segments associated with the audio data, extracting text embedding features from the plurality of text segments, obtaining and concatenating speaker embedding features associated with the audio data, obtaining and concatenating a plurality of emotion features corresponding to the plurality of turns. The method further comprises executing a tree-based prediction model to predict emotion features of the plurality of speakers for a subsequent turn of the ongoing conversation based on the audio embedding features, text embedding features, the concatenated speaker embedding features, and the concatenated emotion features.

Abstract: A system and method of offering task-specific guidance to users of software. The system and method can intelligently determine which task the user is likely performing and what sequence of steps (data journey) will offer the user the most efficient route in completing the task. In some embodiments, the proposed system collects data representing in-app behavior for a large group of users in order to train a model that will predict what the user's next actions are likely to be. Furthermore, in some cases, current data for a user may include screen captures or other image data that can be compared with stored image data in order to help identify the user's current task.

Abstract: A system and method for managing access by end-users to features of an application through a policy management service is disclosed. Specifically, the method and system enable an application provider to utilize tools made available by the policy management service for creation of policies, such as terms and conditions and/or consent to data usage. In addition, the policy management service can provide an interface from which application administrators can link subset(s) of an API to specific policies, as well as the manage the presentation of these policies to end-users of the API that offer options to review and accept or reject the policies. The service further allows users to revoke an acceptance to a policy and to review their privacy settings. In addition, the policy management service can regulate the access of user data by external entities based on the policy limits.

Abstract: A device may identify unique segments within data objects, of an object corpus stored in a data structure, as elements, and may generate an embedding space based on unique elements and mappings of the data objects to embeddings. The device may estimate semantic proximities among the data objects based on the mappings, and may build a semantic cohesion network among the data objects based on the semantic proximities. The device may identify semantically cohesive data clusters in the semantic cohesion network, and may sort the data objects in the semantically cohesive data clusters. The device may determine, from the semantically cohesive and sorted data clusters, a home data cluster for a new data object, and may store bookkeeping details of the new data object in the data structure based on the new data object being semantically similar to the data object in the home data cluster.

Abstract: Methods, systems, and apparatuses, including computer programs encoded on computer-storage media, for prioritizing test cases. Processes may include obtaining test artifacts that were generated based on testing one or more legacy versions of a software application using multiple test cases, generating a risk index based at least on the test artifacts that were generated based on testing the one or more legacy versions of the software application using the multiple test cases, and training an ensemble model that is configured to identify likely unnecessary or redundant test cases in connection with in testing an updated version of the software application, based at least on the risk index.

Abstract: In some implementations, a system may receive a submission associated with an innovation associated with an entity. The system may analyze, using a first machine learning model, the submission to identify a classification associated with the innovation. The system may analyze, using a second machine learning model in association with the classification, content of the submission to identify a characteristic of the innovation. The system may determine, using a third machine learning model and based on the characteristic, a ranking of the innovation relative to individual innovations in the subset of innovations. The system may determine, using a fourth machine learning model, an impact score associated with the innovation. The system may perform, based on the impact score satisfying a threshold, an action associated with a project involving the innovation.

Abstract: A document processing system processes a document image to identify document image regions including floating images, structured data units, and unstructured floating text. A first masked image is generated by deleting any floating images from the document image and a second masked image is generated by deleting any structured data units from the first masked image. The structured data units and the unstructured floating text are thus identified serially one after another. Textual data is extracted from the structured data units and the unstructured floating text by processing the corresponding document image regions via optical character recognition (OCR). Entities are extracted from the textual data using natural language processing (NLP) techniques.