US 12,189,697 B2
Informational grounding with respect to a generative model
Zhun Liu, Redmond, WA (US); Saksham Singhal, Redmond, WA (US); Xia Song, Redmond, WA (US); and Rahul Lal, Redmond, WA (US)
Assigned to MICROSOFT TECHNOLOGY LICENSING, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Jun. 15, 2023, as Appl. No. 18/335,983.
Claims priority of provisional application 63/442,447, filed on Jan. 31, 2023.
Prior Publication US 2024/0256615 A1, Aug. 1, 2024
Int. Cl. G06F 16/9532 (2019.01); G06F 16/954 (2019.01)
CPC G06F 16/9532 (2019.01) [G06F 16/954 (2019.01)] 19 Claims
OG exemplary drawing
 
1. A computing system comprising:
a processor; and
memory storing instructions that, when executed by the processor, cause the processor to perform acts comprising:
causing input set forth by a user of a client computing device to be provided to a generative model;
obtaining, from the generative model, a query based upon the input set forth by the user;
providing the query to a search engine;
obtaining, from the search engine, content identified by the search engine, where the search engine identified the content based upon the query;
providing, to the generative model, the content identified by the search engine, where the generative model generates an output based upon the content identified by the search engine;
obtaining, from the generative model, the output;
transmitting the output to the client computing device for presentment to the user;
subsequent to transmitting the output to the client computing device, causing second input set forth by the user of the client computing device to be provided to the generative model, where the generative model generates a second query based upon the input, the query, and the second input;
obtaining, from the generative model, the second query;
providing the second query to the search engine;
obtaining, from the search engine, second content identified by the search engine, where the search engine identified the second content based upon the second query;
providing, to the generative model, the second content identified by the search engine, where the generative model generates a second output based upon the content identified by the search engine and the second content identified by the search engine;
obtaining, from the generative model, the second output; and
transmitting the second output to the client computing device for presentment to the user.