一种面向未来数据预测的开放域表格问答方法、系统、终端及存储介质
By using a large language model to generate SQL statements in a table-based question-and-answer system and combining it with a time series prediction model to extend historical data sequences, the problem of insufficient modeling of dynamic time series data in existing technologies is solved, and the accuracy of numerical prediction is improved.
CN122152862BActive Publication Date: 2026-07-17BEIJING NORMAL UNIV AT ZHUHAI
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING NORMAL UNIV AT ZHUHAI
- Filing Date
- 2026-05-11
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing table-based question-answering methods mainly focus on retrieval and reasoning based on static historical data, lacking a modeling mechanism for dynamic time series data, resulting in poor numerical prediction performance.
Method used
The system filters tabular databases using a large language model, generates SQL queries, expands historical data sequences using a time series prediction model, and transforms the data using the large language model to generate query answers.
Benefits of technology
It improves the accuracy of data prediction in the form-based question-and-answer system, especially in the prediction of dynamic time series data.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN122152862B_ABST
Abstract
本发明涉及数据处理技术领域，公开了一种面向未来数据预测的开放域表格问答方法、系统、终端及存储介质，所述方法包括：获取用户查询语句和数据库，根据用户查询语句对数据库进行筛选处理，得到目标表格；通过大语言模型根据用户查询语句和目标表格进行SQL语句生成处理，得到SQL语句；根据SQL语句在数据库中进行查询，得到历史数据序列，并通过时间序列预测模型进行扩展，得到目标数据序列；对目标数据序列进行数据转换，得到查询回答。本发明根据用户查询语句生成SQL语句，并在数据库中进行查询，得到历史数据序列，对历史数据序列进行扩展得到目标数据序列，并进行数据转换，得到查询回答，提高了表格问答系统的预测准确性。
Need to check novelty before this filing date? Find Prior Art