US 12,111,858 B1
Database system interaction embedding and indexing for text retrieval and generation
Regunathan Radhakrishnan, Dublin, CA (US); Zachary Alexander, Berkeley, CA (US); Yuanxin Wang, Mountain View, CA (US); Sitaram Asur, Fremont, CA (US); and Aron Kale, Huntington Beach, CA (US)
Assigned to Salesforce, Inc., San Francisco, CA (US)
Filed by Salesforce, Inc., San Francisco, CA (US)
Filed on Oct. 4, 2023, as Appl. No. 18/481,036.
Int. Cl. G06F 16/33 (2019.01); G06F 16/31 (2019.01); G06N 3/0455 (2023.01)
CPC G06F 16/3347 (2019.01) [G06F 16/31 (2019.01); G06N 3/0455 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving a text interaction record at a database system, the text interaction record including interaction text from one or more messages between a client machine and a service provider;
determining a search vector based on the interaction text via a processor at the database system, the search vector including a text embedding representing the interaction text in a multi-dimensional vector space;
retrieving a reference interaction record from the database system based on the search vector, the reference interaction record including reference interaction text, the reference interaction record including a reference vector representing the reference interaction text in the multi-dimensional vector space;
determining recommended reply text based on the interaction text and the reference interaction text, the recommended reply text being determined by a large language model configured to generate the recommended reply text in response to a prompt that includes one or more natural language instructions; and
transmitting a response message from the database system to the client machine, the response message including some or all of the recommended reply text.