Voice Recognition Help Generation for Smart TVs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Image display apparatuses, such as smart TVs, face challenges in providing users with intuitive guidance for using voice recognition features, as existing voice recognition functions may not be familiar to users and lack effective assistance for operations like channel changing or application execution.
Innovation Solution
An image display apparatus that includes a controller to extract keywords from user sentences, assign them to help categories, and generate help information based on these categories, allowing for the display of a use guide that includes familiar phrases for operations like searching, channel changing, or executing applications, using a storage unit to store recently used keywords for personalized assistance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If voice recognition functions are added to image display apparatuses, then functionality and user interaction capabilities are improved, but user understanding and ease of operation deteriorate due to lack of familiar guidance
Solution Approach 1:
The system performs preliminary actions by extracting keywords from user speech and proactively generating help information before the user encounters difficulties. The controller extracts keywords from spoken sentences, categorizes them, and prepares context-specific help information in advance, making guidance available when users need it most.
Solution Approach 2:
The patent introduces an intermediary mechanism - the help information generation system - that mediates between the voice recognition function and the user. This intermediary extracts meaningful keywords from user speech, categorizes them, and provides contextual guidance, bridging the gap between advanced functionality and user comprehension.
2Loss of information
If generic help information is provided for voice recognition operations, then information coverage is improved, but relevance and usefulness deteriorate due to lack of personalization
Solution Approach 1:
The system applies local quality by providing customized help information tailored to each user's specific speech patterns and intent. Rather than uniform generic help, the controller analyzes individual user sentences, extracts relevant keywords, and generates context-specific guidance that matches the user's actual needs and language style.
Solution Approach 2:
The patent implements parameter changes by dynamically adjusting help information based on extracted keywords from user speech. The system changes the content, category, and specificity of help information according to the analyzed sentence, transforming static generic help into dynamic personalized guidance that adapts to each interaction.
3Loss of information
If comprehensive help information is generated for all possible operations, then information completeness is improved, but system complexity and processing requirements worsen
Solution Approach 1:
The system applies the extraction principle by isolating and focusing on key elements from user speech - specifically extracting keywords from spoken sentences. Rather than processing entire sentences or generating help for all possible operations, the controller extracts essential keywords and generates targeted help information only for relevant operations, reducing unnecessary processing complexity.
Solution Approach 2:
The patent implements partial action by generating help information for only the most relevant operations based on extracted keywords, rather than providing exhaustive help for all possible voice recognition operations. This selective approach provides sufficient guidance for current user needs without the overhead of comprehensive but unnecessary help content.
Data Source
AI summary
Provided are an image display apparatus and an image display method. The image display apparatus includes a display configured to display a use guide comprising help information, and a controller configured to extract a keyword from a sentence spoken by a user, assign the keyword to a help category, and generate the help information based on the help category and the keyword.