CNIPA.AI
검색으로 돌아가기
기록

SYSTEMS AND METHODS FOR GENERATIVE ARTIFICIAL INTELLIGENCE-ENABLED INTENT RESOLUTION

발명심사 중
1조회수
21청구항 · 3 독립항
§ Ⅰ

개요

발명자

Kenneth Hashimoto; Becca Williams; Jennifer Cantor; Jeremy Mack; Jordan H. Taler

IPC 분류

G6F 16/334G6F 40/30H4L 51/2

CPC 분류

G6F16/334G6F40/30H4L51/2

Systems and methods provide a framework through which generative artificial intelligence-enabled systems are implemented to provide real-time intent analysis and resolution. In response to user queries communicated by different users, the user queries are converted into different sets of embeddings that are evaluated according to different data sources made available through a Retrieval Augmented Generation (RAG) processor. Based on these different data sources and the different sets of embeddings, the RAG processor and one or more Large Language Models (LLMs) and/or generative artificial intelligence processes dynamically generate relevant responses to these different user queries.

원문 (중국어)

Systems and methods provide a framework through which generative artificial intelligence-enabled systems are implemented to provide real-time intent analysis and resolution. In response to user queries communicated by different users, the user queries are converted into different sets of embeddings that are evaluated according to different data sources made available through a Retrieval Augmented Generation (RAG) processor. Based on these different data sources and the different sets of embeddings, the RAG processor and one or more Large Language Models (LLMs) and/or generative artificial intelligence processes dynamically generate relevant responses to these different user queries.