Abstract: A method for automating a loan origination process by optimizing parameters used for routing loan origination applications to underwriters and prioritizing the handling of the applications is provided. The method includes: receiving first information that relates to a loan origination application; obtaining parameter values from the first information; retrieving second information that relates to candidate underwriters; generating, based on the parameter values and the second information, a task procedure for processing the loan origination application, including an identification of a target underwriter and requirements for completion of the processing of the loan origination application; transmitting, to the target underwriter, a request message that includes the first information and the task procedure; and receiving a confirmation message indicating that the task procedure is acceptable.

Abstract: A system for providing responses to natural language queries or commands is disclosed. The system comprises a server comprising a processor and non-transitory memory storing instructions that cause the processor to: retrieve a stored data structure comprising a plurality of named entities; receive a natural language query or command from a human user; extract one or more named entities from the query or command, wherein the extraction comprises iteratively: dividing the query or command into overlapping sets of tokens, determining whether a set of tokens corresponds to a named entity from the plurality of named entities, extracting any corresponding set of tokens from the query, and if no corresponding sets remain, decreasing the set size and repeating; and based at least in part on the query or command and on the extracted one or more named entities, act to fulfill a user intent expressed by the query or command.

Abstract: A system for providing responses to natural language queries or commands is disclosed. The system comprises a server comprising a processor and non-transitory memory storing instructions that cause the processor to: retrieve a stored data structure comprising a plurality of named entities; receive a natural language query or command from a human user; extract one or more named entities from the query or command, wherein the extraction comprises iteratively: dividing the query or command into overlapping sets of tokens, determining whether a set of tokens corresponds to a named entity from the plurality of named entities, extracting any corresponding set of tokens from the query, and if no corresponding sets remain, decreasing the set size and repeating; and based at least in part on the query or command and on the extracted one or more named entities, act to fulfill a user intent expressed by the query or command.