Microsoft technology licensing, llc (20240346255). CONTEXTUAL KNOWLEDGE SUMMARIZATION WITH LARGE LANGUAGE MODELS simplified abstract

From WikiPatents
Revision as of 03:00, 18 October 2024 by Wikipatents (talk | contribs) (Creating a new page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

CONTEXTUAL KNOWLEDGE SUMMARIZATION WITH LARGE LANGUAGE MODELS

Organization Name

microsoft technology licensing, llc

Inventor(s)

Sebastian Johannes Blohm of Munich (DE)

Dmitriy Meyerzon of Bellevue WA (US)

Aaron Lee Halfaker of Seattle WA (US)

James John Hensman of Cambridge (GB)

CONTEXTUAL KNOWLEDGE SUMMARIZATION WITH LARGE LANGUAGE MODELS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240346255 titled 'CONTEXTUAL KNOWLEDGE SUMMARIZATION WITH LARGE LANGUAGE MODELS

The techniques disclosed in this patent application aim to improve the efficiency and functionality of knowledge base systems by automating the generation of knowledge base content, such as topic definitions, using a large language model. This is achieved through a summarization module that processes requests related to a knowledge base topic and generates instructions for the large language model to produce natural language outputs.

  • Summarization module processes requests for knowledge base topics
  • Generates instructions for large language model to create natural language outputs
  • Ensures consistency and relevance of outputs by contextualizing instructions
  • Maintains information security by applying access controls to privileged information
  • Allows for review and editing of large language model outputs for accuracy

Potential Applications: - Enhancing the efficiency of knowledge base systems - Improving the quality of generated content in various industries such as customer support, education, and research

Problems Solved: - Automating the generation of knowledge base content - Ensuring consistency and relevance of outputs from large language models - Maintaining information security for privileged information

Benefits: - Increased efficiency in generating knowledge base content - Improved accuracy and relevance of generated content - Enhanced information security for privileged information

Commercial Applications: Title: Automated Knowledge Base Content Generation Technology This technology can be applied in industries such as customer support, education, and research to streamline the process of generating knowledge base content, leading to improved efficiency and accuracy. Companies can benefit from more consistent and relevant content, ultimately enhancing customer satisfaction and operational effectiveness.

Questions about Automated Knowledge Base Content Generation Technology: 1. How does this technology improve the efficiency of knowledge base systems? - This technology automates the generation of knowledge base content, such as topic definitions, using a large language model, which streamlines the process and ensures consistency and relevance in the outputs. 2. What are the potential applications of this technology in different industries? - This technology can be applied in various industries such as customer support, education, and research to enhance the quality of generated content and improve operational efficiency.


Original Abstract Submitted

the techniques disclosed herein enable systems to enhance the efficiency and functionality of knowledge base systems through automated generation of knowledge base content such as topic definitions using a large language model. this is accomplished by utilizing a summarization module that processes incoming requests pertaining to a knowledge base topic. in response to a request, the summarization module can retrieve information related to the topic and generate an instruction directing a large language model to generate a natural language output. by generating the instruction from the specific context of the knowledge base, the disclosed techniques can ensure that outputs received from the large language model are consistent and relevant. in addition, content that was generated based on privileged information such as an access-controlled document can receive the same access controls to maintain information security. furthermore, large language model outputs can undergo a review and editing process to ensure accuracy.