US 12,265,570 B2
Generative artificial intelligence enterprise search
Thomas M. Siebel, Woodside, CA (US); Nikhil Krishnan, Los Altos, CA (US); Louis Poirier, Paris (FR); Michael Haines, San Francisco, CA (US); and Romain Juban, San Francisco, CA (US)
Assigned to C3.ai, Inc., Redwood City, CA (US)
Filed by C3.ai, Inc., Redwood City, CA (US)
Filed on Dec. 15, 2023, as Appl. No. 18/542,481.
Claims priority of provisional application 63/492,133, filed on Mar. 24, 2023.
Claims priority of provisional application 63/446,792, filed on Feb. 17, 2023.
Claims priority of provisional application 63/433,124, filed on Dec. 16, 2022.
Prior Publication US 2024/0202221 A1, Jun. 20, 2024
Int. Cl. G06F 16/34 (2019.01); G06F 16/33 (2019.01); G06F 16/332 (2019.01); G06F 16/334 (2025.01); G06F 16/335 (2019.01); G06F 16/338 (2019.01); G06F 40/20 (2020.01); G06F 40/40 (2020.01); G06N 3/092 (2023.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01)
CPC G06F 16/345 (2019.01) [G06F 16/3326 (2019.01); G06F 16/334 (2019.01); G06F 16/3347 (2019.01); G06F 16/335 (2019.01); G06F 16/338 (2019.01); G06F 40/20 (2020.01); G06F 40/40 (2020.01); G06N 3/092 (2023.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01)] 24 Claims
OG exemplary drawing
 
1. A method comprising:
generating a set of potential responses to a prompt using one or more data models with data from at least a plurality of data domains of an enterprise information environment that includes access controls, wherein generating the set of potential responses uses at least one large language model trained on the at least the plurality of data domains of the enterprise information environment to determine data object semantics, and wherein the at least one large language model includes vectorized data from the data from the at least the plurality of data domains with embeddings;
determining validation data for the set of potential responses, wherein the validation data is from the at least the plurality of data domains of the enterprise information environment, wherein determining the validation data comprises retrieving the embeddings from the vectorized data;
selecting a deterministic response from the set of potential responses based on scoring of the validation data and restricting the deterministic response based on the access controls in view of profile information associated with the prompt, wherein selecting the deterministic response from the set of potential responses comprises using the embeddings from the vectorized data to determine relevance evaluations; and
outputting the selected deterministic response with the validation data corresponding to the selected deterministic response.