Patent · US Active

Using intent-based rankings to generate large language model responses

US12222992B1 · kind B1 · utility

1Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 21, 2024
Grant dateFeb 11, 2025
Priority date
Expiry dateOct 21, 2044

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F16/93
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The systems and methods disclosed herein generates responses generated by artificial intelligence (AI) models such as large language models (LLM) using intent-based rankings of retrieved information. The systems and methods disclosed herein receives an output generation request for the generation of an output using a set of AI models. Using a first AI model, a set of documents are retrieved using the received output generation request. The set of documents are partitioned into chunks. The chunks are ranked using a distance between the vector representation of the received output generation request and the vector representation of each chunk. A second AI model classifies the output generation request and chunks using an intent of the respective output generation request or chunk, and generates a second set of rankings using the intents. The set of AI models generate a response using the second set of rankings.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.