针对上下文数据选择性地使用传感器
By performing semantic analysis on spoken input, it can determine whether sensors need to be enabled, thus solving the problem of digital assistants' difficulty in responding to ambiguous requests and achieving efficient sensor activation and privacy protection.
CN116686044BActive Publication Date: 2026-07-17APPLE INC
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- APPLE INC
- Filing Date
- 2021-08-20
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
In computer-generated real-world technologies, digital assistants struggle to determine appropriate responses to ambiguous user requests, especially when users use unclear terminology, leading to improper sensor activation and impacting device efficiency and privacy.
Method used
By receiving spoken input and performing semantic analysis, it determines whether additional contextual data is needed to satisfy the request. If the threshold is exceeded, sensors such as cameras are activated, and the response is determined based on the captured data.
Benefits of technology
It improves the selective activation of sensors, reduces power consumption, extends device battery life, and provides privacy protection by capturing only helpful activity.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116686044B_ABST
Abstract
提供了用于操作数字助理的系统和方法。用于确定响应的示例性方法包括：在具有一个或多个处理器以及存储器的电子设备处，接收包括请求的口语输入，对该口语输入执行语义分析，基于该语义分析确定该电子设备需要附加上下文数据来满足该请求的可能性，以及根据所确定的可能性超过阈值，启用该电子设备的相机并且基于由该电子设备的该相机捕获的数据来确定对该请求的响应。
Need to check novelty before this filing date? Find Prior Art