意图理解方法、装置、电子设备和存储介质
By constructing a semantic tag tree and enhancing semantic features, the problem of poor intent understanding in long and complex sentences and sentences with multiple intents is solved, achieving greater comprehensiveness and accuracy.
CN115879478BActive Publication Date: 2026-07-17IFLYTEK CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- IFLYTEK CO LTD
- Filing Date
- 2022-12-26
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing technologies are not effective at understanding intent when dealing with long, complex sentences and sentences with multiple intents.
Method used
By constructing a semantic label tree, based on the correlation between the semantic features of the text and the graph coding features of the semantic label tree, the semantic features are enhanced to obtain enhanced semantic features that highlight feature representations related to the text intent.
Benefits of technology
It improves the comprehensiveness and accuracy of understanding the intent of long, complex, and multi-intent sentences.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN115879478B_ABST
Abstract
本发明提供一种意图理解方法、装置、电子设备和存储介质，其中方法包括：获取待理解的文本，以及文本的语义标签树；基于文本的语义特征与语义标签树的图编码特征之间的相关性，对语义特征进行特征增强，得到文本的增强语义特征；基于文本的增强语义特征，对文本进行意图理解。本发明提供的方法、装置、电子设备和存储介质，通过构建待理解的文本的语义标签树，并基于文本的语义特征与语义标签树的图编码特征之间的相关性，对语义特征进行特征增强，达到凸显语义特征中与文本意图相关的特征表示的效果；基于由此得到的增强语义特征进行意图理解，能够保证意图理解的可靠性，尤其能够提高对长难句和多意图句子的意图理解的全面性和精确性。
Need to check novelty before this filing date? Find Prior Art