Assistant Device Selection Using Scenario-Based Context Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Determining which device within an ecosystem of connected devices should provide a response to a user's request is challenging, as multiple devices may be capable of responding, leading to inefficiencies and suboptimal user experiences.
Innovation Solution
A user specifies a device to handle responses based on a scenario, generating and storing scenario features from sensor data, and comparing current contextual features to determine the appropriate device for response, ensuring the specified device is used when the scenario occurs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple devices are configured to respond to user requests, then device versatility and user choice are improved, but device selection complexity and response accuracy deteriorate
Solution Approach 1:
The system changes parameters by comparing current contextual features (from sensors) with stored scenario features to determine device selection. This parameter-based matching approach resolves the contradiction by providing automatic, accurate device selection based on contextual parameters rather than manual configuration complexity
Solution Approach 2:
The system performs self-service by automatically selecting the appropriate device based on contextual feature matching without requiring user intervention. The automated assistant client autonomously determines which device should respond by comparing current context with stored scenario associations, eliminating manual device selection complexity
2Measurement precision
If contextual features are transmitted to the cloud for processing, then scenario recognition accuracy is improved, but data transmission overhead and processing time increase
Solution Approach 1:
The system segments the processing by performing local feature extraction and comparison on the device, rather than transmitting all raw sensor data to the cloud. Only essential contextual features are processed locally and compared with stored scenario features, reducing transmission overhead while maintaining recognition accuracy
Solution Approach 2:
The system performs preliminary action by pre-storing scenario features and associations in the automated assistant client before runtime. This allows rapid local comparison with current contextual features without requiring cloud processing for each query, significantly reducing processing time while maintaining accuracy
3Measurement precision
If sensor data is collected and transmitted for scenario detection, then scenario identification accuracy is improved, but security risks and data privacy concerns increase
Solution Approach 1:
The system extracts only the essential contextual features from sensor data that are necessary for scenario identification, rather than transmitting or storing complete raw sensor datasets. This extraction approach maintains scenario identification accuracy while minimizing security risks by reducing the amount of sensitive data handled
Solution Approach 2:
The system creates local copies of scenario features and associations within the automated assistant client, eliminating the need to transmit sensitive sensor data to the cloud for processing. This copying approach maintains identification accuracy while improving security by keeping data local
Data Source
AI summary
Implementations relate to selecting a particular device, from an ecosystem of devices, to provide responses to a device-agnostic request of the user while a scenario is occurring. The user specifies a scenario and contextual features are identified from one or more devices of the ecosystem to generate scenario features indicative of the scenario occurring. The scenario features are stored with a correlation to a device that is specified by the user to handle responses while the scenario is occurring. When a subsequent device-agnostic request is received, current contextual features are identified and compared to the scenario features. Based on the comparison, the specified assistant device is selected to respond to the device-agnostic request.