Systems and methods for retrieving patient information using large language models

Inventors

SINHA, Purushottam • Vij, Anurag • Tomar, Jatin Kumar • Anand, Akash

Assignees

Nference Inc

Abstract

A system for retrieving patient information using large language models including a computing device configured to receive a natural language query as a function of a user input, input the natural language query into a large language model communicatively connected to the least a processor, receive a computer language query comprising a plurality of nodes from the large language model, map the plurality of nodes to one or more entries in a patient database, receive a database response from the patient database as a function of the mapping, generate a final database query as a function of the database response. query the patient database using the final database query, receive a user response as a function of the final database query, and transmit the user response to a graphical user interface as a function of the final database query.

Core Innovation

A system for retrieving patient information uses large language models to convert a natural language query into a computer language query comprising a plurality of nodes. The system receives the natural language query as a function of a user input, inputs the natural language query into a large language model, and maps the plurality of nodes to one or more entries in a patient database, from which a database response is received.

The system generates a final database query as a function of the database response and queries the patient database using the final database query. After querying, the system receives a user response as a function of the final database query and transmits the user response to a graphical user interface, including transmitting the user response to the large language model and generating a natural language response using the large language model.

The generation of the natural language response comprises receiving a user profile comprising previously received natural language queries associated with the user, iteratively training a classifier as a function of training data comprising exemplary natural language query inputs correlated to at least one exemplary language grouping output, and classifying the user profile to one or more language groupings as a function of the trained classifier and the previously received natural language queries. The described processing is further refined by using atomic elements to form the node-based computer language query and by constructing logical relationships between nodes, including temporal relationships.

Claims Coverage

The document includes two independent claims, covering a system and a method for retrieving patient information using large language models. The claims center on generating and executing a final database query, producing a natural language response using a user profile-based classifier trained to assign language groupings, and using node-based computer language queries mapped to patient database entries.

Across the independent claims, the core inventive coverage centers on generating a node-based computer language query from a natural language query using a large language model, mapping nodes to patient database entries, and using the database response to generate and execute a final database query. The resulting user response is provided via a graphical user interface, while a natural language response is generated using the large language model and a user profile classified into language groupings by an iteratively trained classifier.

Stated Advantages

Documented Applications