Various embodiments disclosed relate to automated docketing of incoming electronic communications and documents. The present disclosure includes methods and systems for identifying omnibus documents containing more than one event, and splitting those omnibus documents into the individual events or documents.

Relating to the field of artificial intelligence, and specifically relating to the field of natural language processing, a data processing method includes and an apparatus performs: determining original text samples, where masking processing is not performed on the original text samples; and performing mask processing on the original text samples to obtain mask training samples, where the mask processing makes mask proportions of the mask training samples unfixed, and the mask training samples each are used to train a pretrained language model PLM. Training the PLM by using the mask training samples whose mask proportions are unfixed can enhance mode diversity of the training samples of the PLM. Therefore, features learned by the PLM are also diversified, a generalization capability of the PLM can be improved, and a natural language understanding capability of the PLM obtained through training can be improved.

Relating to the field of artificial intelligence, and specifically relating to the field of natural language processing, a data processing method includes and an apparatus performs: determining original text samples, where masking processing is not performed on the original text samples; and performing mask processing on the original text samples to obtain mask training samples, where the mask processing makes mask proportions of the mask training samples unfixed, and the mask training samples each are used to train a pretrained language model PLM. Training the PLM by using the mask training samples whose mask proportions are unfixed can enhance mode diversity of the training samples of the PLM. Therefore, features learned by the PLM are also diversified, a generalization capability of the PLM can be improved, and a natural language understanding capability of the PLM obtained through training can be improved.

Cooking recipe display system (100) is provided with database (11), extraction unit (21a), emphasis unit (21b), and output unit (23). Database (11) stores a plurality of cooking recipes each being expressed in natural language sentences. Extraction unit (21a) extracts one or more recipe terms from the natural language sentences constituting one cooking recipe selected from the plurality of cooking recipes. Emphasis unit (21b) determines an emphasis method for the one or more recipe terms. Output unit (23) outputs the one cooking recipe with the one or more recipe terms emphasized according to the emphasis method determined by emphasis unit (21b).

Systems, methods, and applications for mobile intelligent outside sales assistance are provided. Embodiments include receiving speech for recognition of an outside sales call; converting the speech for recognition to text; parsing the converted text into outside sales triples; storing the outside sales triples in an enterprise knowledge graph of a semantic graph database; generating real-time outside sales insights in dependence upon the speech of the outside sales call and the stored outside triples in the enterprise knowledge graph; and presenting the real-time outside sales insights to an outside sales agent.

Systems and methods for implementing a representative support system in a task determination system are provided. The task determination system automatically receives in real-time a set of messages between a member and a representative as these messages are exchanged. The set of messages correspond to a set of proposals associated with a task. The task determination system automatically identifying a selection of a proposal from the set of proposals based on an analysis of the set of messages. Based on the selection, the task determination system generates a set of proposal tasks and processes communications associated with these proposal tasks to monitor performance of these proposal tasks for completion of the task.

Systems and methods for implementing a representative support system in a task determination system are provided. The task determination system automatically receives in real-time a set of messages between a member and a representative as these messages are exchanged. The set of messages correspond to a set of proposals associated with a task. The task determination system automatically identifying a selection of a proposal from the set of proposals based on an analysis of the set of messages. Based on the selection, the task determination system generates a set of proposal tasks and processes communications associated with these proposal tasks to monitor performance of these proposal tasks for completion of the task.

Disambiguating question answering responses by receiving voice command data associated with a first user, determining a first user identity according to the first user voice command data, determining a first user activity context according to the first user voice command data, determining a first response for the first user, receiving voice command data associated with a second user, determining a second user identity according to the second user voice command data, determining a second user activity context according to the second user voice command data, determining a second response for the second user, determining a predicted ambiguity between the first response and the second response, altering the first response according to the predicted ambiguity, and providing the first response and the second response.

Systems as described herein generate an outstanding check alert. An alert generating server may receive transaction records associated with a plurality of checking accounts. The alert generating server may user a first machine learning classifier to determine a transaction pattern indicating a merchant has failed to process outstanding checks for a period of time. The alert generating server may receive sequential check information comprising at least one missing check number associated with a particular checking account. The alert generating server may user a second machine learning classifier to determine at least one outstanding check associated with the particular checking account. The alert generating server may send an alert indicating the at least one outstanding check to a user device.

Methods and systems for artificial intelligence (AI)-assisted document annotation and training of machine learning-based models for document data extraction are described. The methods and systems described herein take advantage of a continuous machine learning approach to create document processing pipelines that provide accurate and efficient data extraction from documents that include structured text, semi-structured text, unstructured text, or any combination thereof.