召回方法、装置、电子设备及计算机可读存储介质

By acquiring and transforming feature values ​​from different databases, and using interface statements and transformation protocols, simultaneous retrieval of multiple feature elements and combined weight setting were achieved. This solved the problem of low recall efficiency in different databases and improved recall efficiency and versatility.

CN116303647BActive Publication Date: 2026-07-17BEIJING BAIDU NETCOM SCI & TECH CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING BAIDU NETCOM SCI & TECH CO LTD
Filing Date
2023-03-14
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

In different types of databases, users need to learn different search syntaxes to obtain recall results, which leads to inefficiency and makes it difficult to simultaneously retrieve multiple features and set the importance of features.

Method used

By acquiring the feature elements and their values ​​of the target to be analyzed, and using pre-generated interface statements and conversion protocols, the system converts them into retrieval statements that match the target database, executes retrieval operations to obtain recall results, and supports simultaneous retrieval of multiple feature elements and setting combined weights.

Benefits of technology

It improved recall efficiency, achieved universal recall across different databases, reduced the cost of manual searching, and provided interpretability for case consolidation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116303647B_ABST
    Figure CN116303647B_ABST
Patent Text Reader

Abstract

本公开提供了召回方法、装置、电子设备及可读存储介质,涉及人工智能技术领域,具体涉及自然语言处理、深度学习、智能推荐技术,可应用在智慧城市、智慧政务场景下。具体实现方案为:获取待分析目标的目标特征要素以及所述目标特征要素对应的要素值;将所述目标特征要素对应的要素值填入预先生成的接口语句,所述接口语句为根据召回策略基于预先设定的转换协议生成的语句,所述召回策略包括至少一个特征要素对应的检索需求;将所述接口语句转换为与目标数据库匹配的检索语句;基于所述检索语句在所述目标数据库中执行检索操作,获取与所述待分析目标对应的召回结果。
Need to check novelty before this filing date? Find Prior Art