US 12,423,312 B1
Adaptive data scoring using multi-metric interaction analysis
John Patrick Symborski, Edmonton (CA); Siddharth Jain, Mountain View, CA (US); Rachit Debashish Sengupta, San Diego, CA (US); and Jianzhao Huang, Mountain View, CA (US)
Assigned to Intuit Inc., Mountain View, CA (US)
Filed by Intuit Inc., Mountain View, CA (US)
Filed on Dec. 19, 2024, as Appl. No. 18/987,816.
Int. Cl. G06F 16/22 (2019.01); G06F 16/2457 (2019.01); G06F 16/248 (2019.01); G06F 16/953 (2019.01)
CPC G06F 16/24578 (2019.01) [G06F 16/2237 (2019.01); G06F 16/248 (2019.01); G06F 16/953 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining, as a response to a user query, a plurality of search results and corresponding similarity scores;
obtaining a plurality of data sources corresponding to the plurality of search results;
processing a multi-metric analytic function for a search result of the plurality of search results, and a data source of the plurality of data sources that corresponds to the search result, to obtain a composite score for the search result;
selecting a subset of search results from the plurality of search results based on a composite score threshold to obtain a selected subset of search results;
selecting a corresponding subset of data sources from the plurality of data sources to obtain a selected subset of data sources; and
generating a prompt to a large language model (LLM), including at least the user query, the selected subset of search results, and the selected subset of data sources.