Cross-library question answering system and method based on natural language

By using a cross-database question-and-answer system that intelligently matches the core layer and a two-layer knowledge base, the problem of retrieval efficiency and accuracy for cross-regional policy consultations has been solved. This system enables efficient and accurate answer returns for multi-terminal access, thereby improving the flexibility of government services and the responsiveness of service delivery.

CN121412352APending Publication Date: 2026-01-27CHONGQING VISION INFORMATION IND GRP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202511777018.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-28
Publication Date
2026-01-27

AI Technical Summary

Technical Problem

Existing natural language question answering systems suffer from low retrieval efficiency when handling cross-regional and multi-level policy consultations. They are unable to automatically identify regional attributes, resulting in low information retrieval efficiency and poor answer accuracy. Furthermore, they lack multi-terminal access capabilities, which limits the work flexibility of call center staff.

Method used

It adopts a cross-database question-answering system based on natural language. It automatically identifies regional information through intelligent matching core layer, performs semantic parsing and intent recognition in combination with two-layer knowledge base, generates search instructions, and returns the final answer through multi-terminal access layer. It supports access from multiple clients such as government WeChat mini-program, PC web terminal, and mobile H5 terminal.

Benefits of technology

It enables efficient and accurate retrieval of cross-regional policy consultations, improves information acquisition efficiency and the relevance and authority of answers, provides a unified multi-terminal access experience, and enhances the system's usability and service response capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121412352A_ABST
    Figure CN121412352A_ABST
Patent Text Reader

Abstract

The invention belongs to the field of customer service, and particularly relates to a cross-library question answering system and method based on natural language, and the system comprises a multi-terminal access layer which is used for receiving natural language questions inputted by different types of clients; the intelligent matching core layer is used for performing semantic analysis and intention recognition on an input natural language question, outputting a retrieval instruction containing a region tag and a user intention, and obtaining corresponding knowledge entries from the double-layer knowledge base layer according to the retrieval instruction; the double-layer knowledge base layer comprises a nationwide universal knowledge base and a regional localization database, the nationwide universal knowledge base is used for storing nationwide universal rules, and the regional localization database is used for storing local rules in different regions; and the result output layer is used for integrating the retrieved knowledge entries and returning a final answer to the user through the multi-terminal access layer.
Need to check novelty before this filing date? Find Prior Art