Context-Aware Natural Language Expression for Electronic Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Electronic devices face challenges in providing natural language expressions when a specific application is not executed or when user utterances are absent, leading to vulnerabilities in reflecting the current context.
Innovation Solution
An electronic device with a touch screen display, communication circuit, microphone, speaker, and processor stores instructions to display a user interface, receive user inputs, transmit identifiers to an external server, and display text-based information on the received utterances, enabling natural language expression based on current context information through an accessible user interface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If natural language expression is provided based on specific application execution, then speech recognition service can be supported, but the system cannot provide context-relevant expressions when no application is executed or user utterance is absent
Solution Approach 1:
The electronic device provides natural language expressions through multiple pathways: when a specific application is executed, expressions are provided based on the application context; when no application is executed, expressions are provided based on the home screen context. This multi-functionality ensures reliable natural language expression provision across different operational states, resolving the contradiction between reliability and adaptability.
Solution Approach 2:
The system dynamically adapts its natural language expression provision based on the current operational context. When a user utterance is present, the system processes it through speech recognition; when no utterance is present but an application is executing, it provides context-relevant expressions; when neither condition is met, it provides home screen-based expressions. This dynamic adaptation resolves the contradiction by making the system responsive to different contextual states.
2Ease of operation
If speech recognition service is supported through application execution, then user interaction is enhanced, but the system becomes vulnerable when user utterance does not occur
Solution Approach 1:
The system performs preliminary actions by providing natural language expressions based on the current context before a user utterance occurs. When an application is executing, the system prepares context-relevant expressions in advance, so that when the user does provide an utterance, the system can respond more effectively. This preliminary preparation enhances both ease of operation and service availability.
Solution Approach 2:
The system continuously monitors the operational context (application execution state, home screen state) and provides feedback in the form of natural language expressions that reflect the current state. This feedback mechanism ensures that even when no user utterance occurs, the system maintains service availability by providing context-appropriate expressions, thereby resolving the contradiction between ease of operation and reliability.
3Reliability
If natural language expression is provided only when specific application is executed, then speech recognition service can be supported, but the system cannot reflect current context in home screen environment
Solution Approach 1:
The system segments the operational context into distinct states: application execution state and home screen state. For each state, it provides tailored natural language expressions - application-specific expressions when an application is running, and home screen-based expressions when no application is executing. This segmentation allows the system to maintain reliable speech recognition service while adapting to different environmental contexts.
Solution Approach 2:
The system changes the contextual parameters based on the operational state. When transitioning from home screen to application execution, the system switches from providing home screen-based expressions to providing application-specific expressions. This parameter change approach enables the system to maintain reliability across different states while adapting to the specific environmental context of each state.
Data Source
AI summary
An embodiment of the present invention comprises a touch screen display, a communication circuit, a microphone, a speaker, a processor, and a memory. Wherein: the memory stores a first application program that includes a first user interface, and an intelligent application program that includes a second user interface; and the memory can cause the processor to display the first user interface at the time of execution and to receive a first user input for displaying the second user interface while displaying the first user interface.