The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Mar. 31, 2026

Filed:

Jan. 30, 2025
Applicant:

Salesforce, Inc., San Francisco, CA (US);

Inventors:

Nan Zhang, Palo Alto, CA (US);

Prafulla Kumar Choubey, San Jose, CA (US);

Alexander R. Fabbri, New York, NY (US);

Gabriel Bernadett-Shapiro, Palo Alto, CA (US);

Chien-Sheng Wu, Mountain View, CA (US);

Assignee:

Salesforce, Inc., San Francisco, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 16/00 (2019.01); G06F 16/22 (2019.01); G06F 40/35 (2020.01); G06N 3/0475 (2023.01); G06F 40/284 (2020.01);
U.S. Cl.
CPC ...
G06F 16/2246 (2019.01); G06F 40/35 (2020.01); G06N 3/0475 (2023.01); G06F 40/284 (2020.01);
Abstract

A method of retrieval-augmented text generation is provided to generate a response to by an artificial intelligence (AI) agent. The method incudes constructing an indexing tree reflecting sematic relationship among textual contexts of one or more documents. The indexing tree includes at least a first level of nodes representing a plurality of propositions indicating facts about at least one entity from the documents, a second level of nodes representing a plurality of proposition aggregates that aggregate one or more first-level propositions mentioning a same entity, and a third level of nodes representing a plurality of summaries that summarize one or more second-level proposition aggregates. The method also includes receiving the user query; retrieving, from the indexing tree, one or more nodes across multiple levels based on similarity comparison with the user query based at least on a similarity between embeddings of the nodes and an embedding of the user query.


Find Patent Forward Citations

Loading…