US 12,254,005 B1
Systems and methods for retrieving patient information using large language models
Purushottam Sinha, Gaya (IN); Anurag Vij, Bangalore (IN); Jatin Kumar Tomar, Bangalore (IN); and Akash Anand, Bhagalpur (IN)
Assigned to nference, Inc., Cambridge, MA (US)
Filed by nference, Inc., Cambridge, MA (US)
Filed on Mar. 29, 2024, as Appl. No. 18/622,750.
Int. Cl. G06F 40/40 (2020.01); G06F 16/242 (2019.01); G16H 10/60 (2018.01); G16H 50/70 (2018.01)
CPC G06F 16/243 (2019.01) [G16H 10/60 (2018.01); G16H 50/70 (2018.01)] 14 Claims
OG exemplary drawing
 
1. A system for retrieving patient information using large language models, the system comprising:
at least a processor; and
a memory communicatively connected to the at least a processor, the memory containing instructions configuring the at least a processor 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, wherein transmitting the user response to the graphical user interface comprises:
transmitting the user response to the large language model;
generating a natural language response using the large language model, wherein generating 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 training data comprising exemplary natural language query inputs correlated to at least one exemplary language grouping output;
classifying the user profile to one or more language groupings as a function of the trained classifier and the previously received natural language queries; and
generating the natural language response as a function of as a function of the user response and the one or more language groupings; and
transmitting the natural language response to the graphical user interface.