Methods and systems for training an intent classifier. For example, a question-intent tuple dataset comprising data samples is received. Each data sample has a question, an intent, and a task. A pre-trained language model is also received and fine-tuned by adjusting values of learnable parameters. Parameter adjustment is performed by generating a plurality of neural network models. Each neural network model is trained to predict at least one intent of the respective question having a same task value of the tasks of the question-intent tuple dataset. Each task represents a source of the question and the respective intent. The fine-tuned language model generates embeddings for training input data, the training input data comprising a plurality of data samples having questions and intents. Further, feature vectors for the data samples of the training input data are generated and used to train an intent classification model for predicting intents.

An improved search engine is disclosed. The search engine receives search queries from client devices and inputs these queries into a first neural network (an action understanding model) that includes an action embedding layer. The action embedding layer can be a word embedding layer constructed using action terms. The action understanding model outputs a filter match associated with a type of filter and, in some scenarios, an action-condition pair. The action-condition pair includes an action associated with the type of filter and a condition comprising an adaptive value associated with the action. Based on the filter and, if present, action-condition pair(s), the embodiments generate a structured query and issue the structured query to a data repository (e.g., database). The search engine then returns a search results page responsive to the search query that includes the results returned by the data repository in response to the structured query.

The invention relates to computer-implemented systems and methods for analyzing and standardizing various types of input data such as structured data, semi-structured data, unstructured data, and images and voice. Embodiments of the systems and the methods further provide for generating responses to specific questions based on the standardized input data.

An artificial intelligence device mounted on a vehicle is provided. A sensing unit acquires a gyroscope sensor value, an acceleration sensor value, a GPS sensor value, and a proximity sensor value. If the acquired data satisfies a predetermined reference value, a processor inputs the acquired sensor values to an artificial intelligence model, acquires whether an impact requiring self-diagnosis occurs and impact direction information as a result value, selects an ECU module to perform self-diagnosis according to the acquired result value, and performs self-diagnosis.

A device trains a classification model with defect classifier training data to generate a trained classification model and processes information indicating priorities and rework efforts for defects, with a Pareto analysis model, to select a set of classes for the defects. The device calculates defect scores for the set of the classes and selects a particular class, from the set of the classes, based on the defect scores. The device processes a historical data set for the particular class to identify a root cause corrective action (RCCA) recommendation and processes information indicating a defect associated with the particular class, with the trained classification model, to generate a predicted RCCA recommendation for the defect. The device processes the predicted RCCA recommendation and the RCCA recommendation, with a linear regression model, to determine an effectiveness score for the predicted RCCA recommendation and retrains the classification model based on the effectiveness score.

A mechanism is provided in a data processing system comprising at least one processor and at least one memory, the at least one memory comprising instructions that are executed by the at least one processor and configure the at least one processor to implement a medical record to illustrative medical image translation engine. The medical record to illustrative medical image translation engine receives a medical record batch from storage for a patient and generates one or more predicted prognosis records based on the medical record batch using a neural network. The medical record to illustrative medical image translation engine converts the one or more predicted prognosis records to illustrative medical images using a first agent. The medical record to illustrative medical image translation engine generates a presentation of disease progression using the illustrative medical images and outputs the presentation to a user.

A computer-implemented method and system for enrichment of responses in a multimodal conversation environment are disclosed. A Question Answer (QA) engine, such as a reinforcement document transformer exploits a document template structure or layout, adapts the information extraction using a domain ontology, stores the enriched contents in a hierarchical form, and learns context and query patterns based on the intent and utterances of one or more queries. The region of enriched content for preparing a response to a given query is expanded or collapsed by navigating upwards or downwards in the hierarchy. The QA engine returns the most relevant answer with the proper context for one or more questions. The responses are provided to the user in one or more modalities.

A computer-implemented method is provided that includes accessing candidate text and a candidate pair including first and second phrases, substituting the first and second phrases into cause-effect patterns to generate variant sentences. An artificial intelligence model is leveraged to determine respective probabilities that the variant sentences are inferred from the candidate text, calculate a statistical measure of the respective probabilities, and assess the calculated statistical measure to ascertain whether the first and second phrases possess a causal relationship or non-causal relationship to one another. A knowledge base including one or more pairs of cause-effect phrase pairs is populated with the first and second phrases possessing the causal relationship. A computer system and a computer program product are also provided.

The present disclosure is directed toward systems, methods, and non-transitory computer readable media for generating conversational survey questions. The systems and methods analyze a received survey question response to identify characteristics of a survey response, including topics and other response features. For example, the systems can determine a sentiment associated with a given product or service that a respondent expresses within a response. Based on the determined sentiment, and further based on a set of logic rules received from a survey administrator, the systems and methods generate provide conversational follow-up questions associated with the identified product or service.

A system, method and computer program product, which given in input a question in natural language format, delivers personalized insights related to the answer. Personalized insights are selected among candidate insights mined from the data and ranked based on closeness to (mined) user-preference, relevance to the question, and surprise factor. Two core components include: Question analysis and meaningful insight look up and Multi-dimensional insight ranking. The Question analysis and meaningful insights lookup module performs a semantic analysis of the questions and, uses techniques including “templates” to build new questions which could uncover insights from the data. The Multi-dimensional insight ranking module takes in input a list of insights returned from Question analysis and meaningful insights lookup and rank such insights based on such factors as: relevance to the query, surprise factor, and user preferences.