US 12,339,875 B1
Machine learning architecture for contextual data retrieval
David Veillon, Longmont, CO (US); Talha Jubair Siam, Dacca (BD); and Eyal Leeder, San Diego, CA (US)
Assigned to AskTuring.AI Inc., La Jolla, CA (US)
Filed by AskTuring.AI Inc., La Jolla, CA (US)
Filed on Mar. 17, 2025, as Appl. No. 19/082,105.
Application 19/082,105 is a continuation of application No. 18/916,406, filed on Oct. 15, 2024, granted, now 12,254,029.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/242 (2019.01); G06F 16/248 (2019.01); G06F 16/28 (2019.01)
CPC G06F 16/285 (2019.01) [G06F 16/243 (2019.01); G06F 16/248 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, by one or more processors from a client device via a first query form presented on a user interface at the client device, a natural language query, the natural language query comprising a request for data regarding one or more of sets of data stored in a database;
parsing, by the one or more processors, the natural language query to generate one or more parsed tags each indicating a context of the natural language query;
updating, by the one or more processors, a second query form on the user interface with the one or more parsed tags;
responsive to a selection of a submit button on the user interface, retrieving, by the one or more processors using one or more generative language models, a subset of the sets of data based on each set of data of the subset corresponding to an assigned category tag that corresponds to at least one of the one or more parsed tags indicated in the second query form on the user interface;
querying, by the one or more processors using the one or more generative language models, the retrieved subset of the sets of data based on the natural language query to generate a response to the natural language query;
presenting, by the one or more processors, the generated response at the client device.