Abstract: Systems, methods, and computer-readable media for generating responses to natural-language queries regarding items in unstructured documents are disclosed. An application instance that includes one or more machine learning models receives, from a subscriber computing system, a query and document comprising unstructured data. Based on the unstructured data, the application instance generates a searchable data structure using a machine learning model. A query response is generated by performing a semantic search on the searchable data structure. The query response is provided to a target application.

Abstract: A smart data signals platform for artificial intelligence/machine learning (AI/ML)-based modeling and simulation is structured to pre-process input data by structuring previously unstructured data that relates to a structured data item and linking the structured data to the data item to generate a validated enriched dataset. The validated enriched dataset is used to generate a trigger signal by evaluating at least an aspect to the enriched dataset against at least one criterion that corresponds to a loss hypothesis. The trigger signal is used to automatically monitor subsequently received structured data, access corresponding unstructured data and generate an analysis dataset for one or more machine learning models. The one or more machine learning models generate a computer-based prediction based on the analysis dataset. The prediction can include a resource degradation indicator.

Abstract: A text recognition system receives a prompt and, based on the prompt, causes a trained region encoder to determine a first region of interest of an image file. The system modifies a first image associated with the first region of interest (e.g., parsed out from the first region) to generate a data augmentation entity that includes a modified image. Using a trained instance encoder, the system generates a first set of visual instances corresponding to the first region of interest image and a second set of visual instances corresponding to the data augmentation entity. The system generates the corresponding first and second sequences. By executing a self-supervised contrastive loss function on the first and second sequences, the system automatically updates a continual knowledge distillation model of the trained region encoder. The system provides the first sequence to an instance decoder to generate output text in response to the prompt.

Abstract: An application instance that includes one or more machine learning models receives, from a subscriber computing system, a document comprising unstructured data. Based on the unstructured data, the application instance generates an optimized model input that includes a plurality of parsed document sections. For each parsed document section, the application instance generates an output set by performing, by a machine learning model, at least one key information extraction operation. The machine learning model transmits the output in structured form to a target application operated or hosted at least in part by a subscriber entity associated with the subscriber computing system.

Abstract: A settlement evaluation tool includes a settlement evaluation module having a statistical model, and an inquiry portal module. The inquiry portal module is configured to perform operations that include electronically receiving data related to an insurance liability dispute between a first insurance carrier and a second insurance carrier, and transferring the data to the settlement evaluation module. The settlement evaluation module is configured to perform operations that include applying the statistical model to the data to obtain an outcome probability associated with a strategy for resolving the dispute, and outputting the outcome probability.