Data analysis method based on atlas and large model and ChatBI system

CN119622055AInactive Publication Date: 2025-03-14TIANJIN HUIZHI XINGYUAN INFORMATION TECH CO LTD
View PDF 7 Cites 7 Cited by

Patent Information

Application Number
CN202411520985.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-29
Publication Date
2025-03-14
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Intelligent BI systems have problems such as poor flexibility and unfriendly user, which cannot meet the diverse needs of different users and business scenarios, and the needs of complex queries and real-time analysis are becoming increasingly urgent.

Method used

Using a data analysis method based on graphs and large models, we obtain natural language query statements input by users, use large language models to parse query statements, determine the query keywords and intent, and map target nodes and edges in the data relationship graph to generate target graph structure query statements, and finally query in the graph database to determine the query result set.

Benefits of technology

It significantly improves the flexibility and efficiency of data query, reduces the threshold for user operation, can handle large-scale data sets and complex data associations, and provides high-quality chart generation and real-time analysis capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119622055A_ABST
    Figure CN119622055A_ABST
Patent Text Reader

Abstract

The invention provides a data analysis method based on a graph and a large model, which is applied to a ChatBI system and comprises the following steps: acquiring a natural language query statement input by a user, analyzing the natural language query statement by using a large language model, and determining a query keyword and a query intention. And according to the query keyword, mapping in a pre-constructed data relation graph to obtain a target node and a target edge. And based on the target node, the target edge and the query intention, determining a high-quality target graph structure query statement by adopting the large language model. And querying in a graph database in which the data relation graph is stored based on the target graph structure query statement, and determining a query result set. Through accurate data matching, the graph database can ensure that only the query result set which completely conforms to the requirement of the target graph structure query statement is returned, and the accuracy of the query process is improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Knowledge graph storage and search method and system

    CN116467291A

  • Data retrieval method, device and equipment

    CN117271754A

  • Question and answer method and device

    CN117370494A

  • Auxiliary retrieval method fusing knowledge graph and large language model

    CN117633252A

  • Knowledge graph construction method and knowledge graph application method

    CN118069856A

Cited By

  • SQL statement generation method and device, electronic equipment and storage medium

    CN119961363A

  • Chart generation method and device based on natural language, equipment and storage medium

    CN120523933A

  • Degradable dialogue analysis method and system based on large model arbitration and electronic equipment

    CN120743940A

  • ChatBI business semantic unified retrieval method and system based on knowledge base

    CN121144454A

  • Professional domain knowledge question answering method and device, electronic equipment and storage medium

    CN121166728A