Abstract: Systems and methods that offer significant improvements to current virtual agent (VA) conversational experiences are disclosed. The proposed systems and methods are configured to manage conversations in real-time with human customers while accommodating a dynamic goal. The VA includes a goal-driven module with a reinforcement learning-based dialogue manager. The VA is an interactive tool that utilizes both task-specific rewards and sentiment-based rewards to respond to a dynamic goal. The VA is capable of handling dynamic goals with a significantly high success rate. As the system is trained primarily with a user simulator, it can be readily extended for applications across other domains.

Abstract: A device may receive multimodal content that includes two or more of text data, image data, or video data, and may process the two or more of the text data, the image data, or the video data, with a binary classifier model, to determine whether the two or more of the text data, the image data, or the video data is biased or unbiased. The device may process the two or more of the text data, the image data, or the video data, with a multilabel classifier model and based on the two or more of the text data, the image data, or the video data being biased, to determine an implicit bias in at least one of the two or more of the text data, the image data, or the video data, and may perform one or more actions based on the implicit bias.

Abstract: A device may receive text data, audio data, and video data associated with a user, and may process the received data, with a first model, to determine a stress level of the user. The device may process the received data, with second models, to determine depression levels of the user, and may combine the depression levels to identify an overall depression level. The device may process the received data, with a third model, to determine a continuous affect prediction, and may process the received data, with a fourth model, to determine an emotion of the user. The device may process the received data, with a fifth model, to determine a response to the user, and may utilize a sixth model to determine a context for the response. The device may utilize seventh models to generate contextual conversation data, and may perform actions based on the contextual conversational data.

Abstract: Systems and methods that offer significant improvements to current virtual agent (VA) conversational experiences are disclosed. The proposed systems and methods are configured to manage conversations in real-time with human customers while accommodating a dynamic goal. The VA includes a goal-driven module with a reinforcement learning-based dialogue manager. The VA is an interactive tool that utilizes both task-specific rewards and sentiment-based rewards to respond to a dynamic goal. The VA is capable of handling dynamic goals with a significantly high success rate. As the system is trained primarily with a user simulator, it can be readily extended for applications across other domains.

Abstract: A device may receive text data, audio data, and video data associated with a user, and may process the received data, with a first model, to determine a stress level of the user. The device may process the received data, with second models, to determine depression levels of the user, and may combine the depression levels to identify an overall depression level. The device may process the received data, with a third model, to determine a continuous affect prediction, and may process the received data, with a fourth model, to determine an emotion of the user. The device may process the received data, with a fifth model, to determine a response to the user, and may utilize a sixth model to determine a context for the response. The device may utilize seventh models to generate contextual conversation data, and may perform actions based on the contextual conversational data.

Abstract: Techniques for building knowledge graphs from conversational data are disclosed. The systems include a high-performance relation classifier developed with active learning and requiring minimal supervision. The classifier is used to classify relation triples extracted from conversational text, which are then used to populate the knowledge graph. A heuristic for constructing the knowledge graph is also disclosed. The proposed embodiments provide a way to efficiently build and/or augment knowledge graphs and improve the quality of the generated responses by a dialogue agent despite a sparsity of data.

Abstract: An intelligent question and answer (Q&A) system and method for interactively guiding users through a procedure is disclosed. The intelligent Q&A system can dynamically generate process trees (or procedural trees) from the content or procedures presented in a raw document, such as a reference manual. The intelligent Q&A system can include a virtual agent that uses the dynamically generated process trees for interactive conversation with a user. Using the system, the virtual agent can interactively guide users through completing tasks such as updating software or connecting an IoT device to an existing system.

Abstract: An intelligent question and answer (Q&A) system and method for interactively guiding users through a procedure is disclosed. The intelligent Q&A system can dynamically generate process trees (or procedural trees) from the content or procedures presented in a raw document, such as a reference manual. The intelligent Q&A system can include a virtual agent that uses the dynamically generated process trees for interactive conversation with a user. Using the system, the virtual agent can interactively guide users through completing tasks such as updating software or connecting an IoT device to an existing system.

Abstract: A device may determine a behavioral pattern of an account over a past time period based on data relating to one or more transactions associated with the account. The device may identify one or more quantitative features of the behavioral pattern and one or more spatial features of the behavioral pattern. The device may determine an account type cluster to which the account belongs, based on the one or more quantitative features and the one or more spatial features identified. The device may determine, based on the account type cluster that is determined, a model for processing the behavioral pattern. The device may predict, using the model that is determined, an amount of funds that is likely to remain in the account during a future time period. The device may perform one or more actions based on the amount of funds that is predicted.

Abstract: A device may receive human-related data associated with a surveyor and a surveyed person participating in an interview, and may receive environmental data. The device may determine, based on rules, that first portions of the human-related data and environmental data are more reliable than second portions, and may process the first portions of the human-related data and the environmental data, with a first model, to determine high-reliability context data. The device may process the second portions of the human-related data and the environmental data, with a second model, to determine low-reliability context data, and may process the high-reliability context data and the low-reliability context data, with a third model, to generate weighted context data. The device may process the weighted context data, with a fourth model, to calculate a total stress factor, and may perform actions based on the total stress factor.

Abstract: A device may determine a behavioral pattern of an account over a past time period based on data relating to one or more transactions associated with the account. The device may identify one or more quantitative features of the behavioral pattern and one or more spatial features of the behavioral pattern. The device may determine an account type cluster to which the account belongs, based on the one or more quantitative features and the one or more spatial features identified. The device may determine, based on the account type cluster that is determined, a model for processing the behavioral pattern. The device may predict, using the model that is determined, an amount of funds that is likely to remain in the account during a future time period. The device may perform one or more actions based on the amount of funds that is predicted.

Abstract: A device may receive human-related data associated with a surveyor and a surveyed person participating in an interview, and may receive environmental data. The device may determine, based on rules, that first portions of the human-related data and environmental data are more reliable than second portions, and may process the first portions of the human-related data and the environmental data, with a first model, to determine high-reliability context data. The device may process the second portions of the human-related data and the environmental data, with a second model, to determine low-reliability context data, and may process the high-reliability context data and the low-reliability context data, with a third model, to generate weighted context data. The device may process the weighted context data, with a fourth model, to calculate a total stress factor, and may perform actions based on the total stress factor.

Abstract: In some examples, incident prediction and prevention may include ascertaining a plurality of past incidents, clustering the plurality of past incidents to generate a plurality of incidents clusters, and identifying, for each past incident of the plurality of past incidents that is in a respective incidents cluster of the plurality of incidents clusters, a time of occurrence. Incident prediction and prevention may include ascertaining a new incident, assigning the new incident to an incidents cluster of the plurality of incidents clusters, and determining, for the assigned incidents cluster, at least one further predicted incident associated with at least one further corresponding incidents cluster. Further, incident prediction and prevention may include determining a resolution to the at least one further predicted incident, and preventing occurrence of the at least one further predicted incident by executing the determined resolution to the at least one further predicted incident.

Abstract: A device may receive sensor data from one or more sensor devices. The device may detect a trigger condition, that triggers an update to a model used to analyze the sensor data, based on receiving the sensor data. The trigger condition may include at least one of: a change in a type of data included in the sensor data, a change in an entity being monitored in association with the sensor data, or a change in a frequency with which the sensor data is received from the one or more sensor devices. The device may transmit a request to update the model based on detecting the trigger condition. The device may receive an updated model based on transmitting the request to update the model. The device may apply the updated model to the sensor data and/or subsequent sensor data received from the one or more sensor devices.

Abstract: In the pharmaceutical research and development process, it may be necessary to process large amounts of medical records or clinical literature, to ensure safety of patients consuming a drug. A pharmacovigilance system may assist in this process by efficiently and automatically processing medical records to extract information and relationships contained therein and may also form a preliminary assessment regarding a medical or clinical judgment. The pharmacovigilance system may automatically generate reports based on this information, which may be validated by trained clinicians and medical experts.

Abstract: A device may receive, from a user device, an implicit search request identifying a resource accessed by a user of the user device. Based on properties defined in a user role and a rule identified in context configuration information, the device may determine an intent associated with the user and a context associated with the intent and the resource accessed by the user. The device may send, based on query options identified in search configuration information, a search query identifying search criteria associated with the context, and may receive a search response identifying available resources that satisfy the search criteria. The device may determine a probability, for each of the available resources, that the available resource matches the context, identify a portion of the search response based on the probabilities, and send the portion to the user device.

Abstract: A device may receive a first textual document and a set of second textual documents. The first textual document may identify parameters. The device may process the first textual document, based on a natural language processing algorithm, to identify first values corresponding to the parameters. The device may process the plurality of second textual documents, based on the natural language processing algorithm, to identify second values corresponding to the parameters. Each of the plurality of second textual documents may be associated with one or more respective second values of the second values. The device may determine scores for the plurality of second textual documents. A score may be determined based on comparing one or more of the first values to one or more of the second values associated with a second textual document. The device may provide information identifying the plurality of second textual documents and the scores.

Abstract: In some examples, incident prediction and prevention may include ascertaining a plurality of past incidents, clustering the plurality of past incidents to generate a plurality of incidents clusters, and identifying, for each past incident of the plurality of past incidents that is in a respective incidents cluster of the plurality of incidents clusters, a time of occurrence. Incident prediction and prevention may include ascertaining a new incident, assigning the new incident to an incidents cluster of the plurality of incidents clusters, and determining, for the assigned incidents cluster, at least one further predicted incident associated with at least one further corresponding incidents cluster. Further, incident prediction and prevention may include determining a resolution to the at least one further predicted incident, and preventing occurrence of the at least one further predicted incident by executing the determined resolution to the at least one further predicted incident.

Abstract: A device receives documents and previously answered questions associated with a restricted domain, and processes the documents and the previously answered questions to generate a corpus of searchable information. The device receives a question associated with the restricted domain, and processes the question, with a machine learning model or a rule-based classifier model, to determine a classification type for the question. The device manipulates the question to generate a query from the question, and processes the query, with an expansion technique, to generate an expanded query. The device utilizes the expanded query, with the corpus of searchable information, to identify candidate answers to the question, and processes the candidate answers and the classification type for the question, with a deep learning model, to generate scored and ranked candidate answers to the question. The device selects an answer from the scored and ranked candidate answers, and provides information indicating the answer.

Abstract: A transportation system may store a standard time of arrival table including standard time of arrivals for fixed stops and waypoints or geo-sections. Delay of a vehicle reaching a fixed stop is determined and may be used to determine an estimated time of arrival to a destination on the route. Delay may be determined in response to traversing the waypoints or geo-sections on the route, and the estimated time of arrival may be updated according to the delay at each waypoint or geo-section.