用户意图澄清方法、装置、设备、介质及车辆
By constructing an event graph and utilizing in-vehicle device status information to remove erroneous samples, the problem of inaccurate user intent in existing technologies is solved, and the accuracy of dialogue clarification is improved.
CN118733720BActive Publication Date: 2026-07-17BEIJING CO WHEELS TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING CO WHEELS TECH CO LTD
- Filing Date
- 2023-03-30
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing dialogue clarification methods based on deep learning models ignore contextual information at the current moment, resulting in inaccurate user intent and poor clarification effectiveness.
Method used
By statistically analyzing user vehicle usage events within a preset time period, an event graph is constructed. Current control commands are received, and prefix feature sample groups and complete feature sample groups are constructed. Combined with in-vehicle device status information, erroneous samples are removed to obtain a target user intent probability table.
Benefits of technology
The accuracy of dialogue clarification has been improved by combining event graphs with different event attributes and in-vehicle device status information.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN118733720B_ABST
Abstract
本公开涉及一种用户意图澄清方法、装置、设备、介质及车辆，通过构造事件图谱，接收当前控制指令，分别为当前控制指令构造前缀特征样本组、完整特征样本组，从事件图谱中统计出每条前缀特征样本对应的概率值、每条完整特征样本对应的概率值，进一步得到用户意图概率表，利用车内设备的状态信息去除用户意图概率表中的错误样本，得到目标用户意图概率表，将目标用户意图概率表中最大概率值对应的特征样本作为澄清后的用户真实意图。本公开通过统计用车事件得到事件图谱，事件图谱对不同事件兼容不同属性，具有很好的扩展性，为当前控制指令构造特征样本，结合车内设备状态，去除错误样本，可以提高对话澄清的准确率，从而提升对话澄清效果。
Need to check novelty before this filing date? Find Prior Art