Abstract: 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.

Abstract: A system and method for using, training, building, and managing a question and answer engine to automatically generate responses to an end-user is disclosed. Specifically, the method and system make use of a topic builder that uses cluster predictions to generate and identify a list of topics and subtopics. A question and answer database may then be sorted by topic and subtopic using a similarity scorer. New user utterances may be analyzed to identify questions, with a cluster predictor identifying the corresponding topic and subtopics for each question, and a similarity scorer may identify the closest known question for the user's question to a recommender as an answer. Analytics of new user utterances are tracked to update the historical utterance database and question and answer database, thus allowing continuous improvement of the engine.

Abstract: The present disclosure relates to a system, a method, and a product for an artificial intelligence based virtual agent trainer. The system includes a processor in communication with a memory storing instructions. When the processor executes the instructions, the instructions are configured to cause the processor to obtain input data and generate a preliminary set of utterances based on the input data, process the preliminary set of utterances to generate a set of utterance training data, generate a set of conversations based on the set of utterance training data, simulate the set of conversations on a virtual agent to obtain a conversation result, verify an intent and a response based on the conversation result, verify a use case flow and flow hops based on the conversation result, and generate recommendation information and maturity report based on verification results.

Abstract: A device may receive user input data identifying a canvas, API documents, or tagged assets for an application to be generated, a requirements document for the application, and asset data identifying reusable assets and components for the application. The device may process the user input data, the requirements document, and the asset data, with a first model, to extract entity data and intent classification data. The device may parse the API documents to generate structured data identifying API endpoints, a request API model, and a response API model. The device may process the structured data to generate an API layer. The device may process the canvas to identify UI objects and to map the UI objects to UI elements. The device may generate code for the application based on the asset data, the entity data, the intent classification data, the API layer, and the UI elements.

Abstract: A device may receive user input data identifying a canvas, API documents, or tagged assets for an application to be generated, a requirements document for the application, and asset data identifying reusable assets and components for the application. The device may process the user input data, the requirements document, and the asset data, with a first model, to extract entity data and intent classification data. The device may parse the API documents to generate structured data identifying API endpoints, a request API model, and a response API model. The device may process the structured data to generate an API layer. The device may process the canvas to identify UI objects and to map the UI objects to UI elements. The device may generate code for the application based on the asset data, the entity data, the intent classification data, the API layer, and the UI elements.

Abstract: The present disclosure relates to a system, a method, and a product for an artificial intelligence based virtual agent trainer. The system includes a processor in communication with a memory storing instructions. When the processor executes the instructions, the instructions are configured to cause the processor to obtain input data and generate a preliminary set of utterances based on the input data, process the preliminary set of utterances to generate a set of utterance training data, generate a set of conversations based on the set of utterance training data, simulate the set of conversations on a virtual agent to obtain a conversation result, verify an intent and a response based on the conversation result, verify a use case flow and flow hops based on the conversation result, and generate recommendation information and maturity report based on verification results.

Abstract: A system and method for intelligently and automatically generating deployable code for target platforms and frameworks based on images or other graphical inputs is disclosed. The system and method leverage artificial intelligence to automatically identify and classify elements of a design as feature patterns. Identification is performed using convolutional neural networks, while classification is done using a Softmax classifier. The intelligent system can then automatically generate code for target platforms and frameworks that reproduce the feature patterns. Target platforms may include web platforms, mobile platforms (such as mobile phones), wearable platforms (such as smart watches), and extended reality platforms (which includes augmented reality (AR), virtual reality (VR), and/or combinations of AR/VR).

Abstract: Examples of a multisource augmented reality model are defined. In an example, the system receives a query from a user. The system obtains representative data corresponding to an environment associated with the query and identifies at least one context therein. The system obtains product parameter data and identifies a parameter set therein to process the query. The system implements an artificial intelligence component to sort the product parameter data, the representative data, and the context for identifying pertinent data domains associated with the query. The system may establish a product augmented reality model corresponding to the product by performing a first cognitive learning operation on a domain from the updated pertinent data domains and the identified parameter set. The system may a list of related products for guided selling facilitating a shopping decision of the user. The system may generate an augmented reality result for the user.

Abstract: A system and method for using, training, building, and managing a question and answer engine to automatically generate responses to an end-user is disclosed. Specifically, the method and system make use of a topic builder that uses cluster predictions to generate and identify a list of topics and subtopics. A question and answer database may then be sorted by topic and subtopic using a similarity scorer. New user utterances may be analyzed to identify questions, with a cluster predictor identifying the corresponding topic and subtopics for each question, and a similarity scorer may identify the closest known question for the user's question to a recommender as an answer. Analytics of new user utterances are tracked to update the historical utterance database and question and answer database, thus allowing continuous improvement of the engine.

Abstract: 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.

Abstract: The present disclosure relates to a system, a method, and a product for an artificial intelligence based virtual agent trainer. The system includes a processor in communication with a memory storing instructions. When the processor executes the instructions, the instructions are configured to cause the processor to obtain input data and generate a preliminary set of utterances based on the input data, process the preliminary set of utterances to generate a set of utterance training data, generate a set of conversations based on the set of utterance training data, simulate the set of conversations on a virtual agent to obtain a conversation result, verify an intent and a response based on the conversation result, verify a use case flow and flow hops based on the conversation result, and generate recommendation information and maturity report based on verification results.