Electronic Device Context Selection for Speech Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for providing high-quality speech recognition services face challenges in accurately identifying user intent from user voice and efficiently processing context information across multiple electronic devices, requiring high-performance servers for real-time analysis and data transmission.
Innovation Solution
An electronic device with a communication interface, processor, and memory that acquires user utterances, identifies context information, selects appropriate external devices, and transmits context information for processing tasks, enabling on-device processing and task execution using context information obtained from external devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If context information is searched and analyzed by a server in real time across multiple electronic devices, then speech recognition service quality is improved, but server performance requirements and system complexity increase
Solution Approach 1:
The system divides the speech recognition functionality into two segments: context information search and analysis is performed by external electronic devices (smartphones, tablets), while the server only performs task execution. This segmentation reduces server complexity while maintaining service quality through distributed processing.
Solution Approach 2:
External electronic devices perform self-service by autonomously searching and analyzing context information using their own resources. The devices independently determine whether to execute tasks locally or transmit to the server, reducing the burden on centralized server infrastructure.
2Measurement precision
If context information is transmitted from server to external electronic devices, then task execution accuracy is improved, but data transmission time and energy consumption increase
Solution Approach 1:
Context information is searched and analyzed in advance by external electronic devices before task execution is needed. This preliminary action ensures that when the server receives the task request, the context is already prepared, eliminating the need for real-time data transmission and reducing latency.
Solution Approach 2:
The external electronic device acts as an intermediary that prepares context information locally before interacting with the server. This intermediary role allows the device to filter and pre-process information, reducing the amount of data that needs to be transmitted and improving overall system efficiency.
3Productivity
If all user utterances are processed by external electronic devices, then on-device processing capability is improved, but context information sharing between devices deteriorates
Solution Approach 1:
The system design allows external electronic devices to perform multiple functions: they can process user utterances locally when capable, or transmit to the server when context sharing is needed. The server also serves dual purposes as both a task execution platform and a context information repository, enabling flexible information sharing across devices.
Data Source
AI summary
An electronic device, according to various embodiments, comprises a communication interface, a processor, and a memory. The memory may store instructions that, when executed, cause the processor to: obtain a user utterance; confirm context information associated with the user utterance; on the basis of the context information, select, as a target device, at least one external electronic device from among a plurality of external electronic devices; and via the communication interface, transmit at least a part of the context information to the at least one external electronic device selected as the target device. Various other embodiments are possible.