Human-computer interaction methods, apparatus, electronic devices, and storage media

The method automates plugin selection and optimizes input text length in large-scale language models, addressing inefficiencies and improving user experience and model accuracy.

JP7864847B2Active Publication Date: 2026-05-25BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
BEIJING BAIDU NETCOM SCI & TECH CO LTD
Filing Date
2024-06-14
Publication Date
2026-05-25

AI Technical Summary

Technical Problem

Large-scale language models struggle with accurately responding to new data outside their training dataset, and the manual selection of plugins becomes cumbersome as the number of plugins increases, leading to inefficiencies and reduced accuracy due to excessive input text length exceeding token limits.

Method used

A method to automatically identify a target plugin based on dialogue text, generate a second dialogue text by combining the original text with the plugin's description, and input this into the model, reducing the need for manual plugin selection and minimizing excessive text input.

Benefits of technology

Improves user experience by automating plugin selection, reducing processing time, and enhancing the accuracy and efficiency of large-scale language models by optimizing input text length.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007864847000001
    Figure 0007864847000001
  • Figure 0007864847000002
    Figure 0007864847000002
  • Figure 0007864847000003
    Figure 0007864847000003
Patent Text Reader

Abstract

The present invention provides a human-computer interaction method, device, electronic device, and storage medium, which relate to the fields of artificial intelligence technology, particularly deep learning, natural language processing, and large-scale model technology. A specific implementation method is to respond to a human-computer interaction request by identifying a first target plugin related to the first dialogue text from multiple plugins registered in a large-scale language model based on a first dialogue text included in the human-computer interaction request, obtaining a second dialogue text based on the first dialogue text and the description text of the first target plugin, and inputting the second dialogue text into the large-scale language model to obtain an answer text.
Need to check novelty before this filing date? Find Prior Art