Presentation Slide Selection Using Conversation Keyword Conversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing presentation systems fail to accurately select the next slide based on conversation content, as voice recognition often misinterprets spoken terms, leading to inappropriate slide transitions.
Innovation Solution
A display device that extracts conversation-derived terms, converts them into search keywords, and uses these keywords to identify relevant presentation material pages, displaying selection terms for slide selection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If voice recognition is used to recognize conversation and select slides, then the system can automatically transition between presentation slides, but the recognized terms may not match search terms associated with slides, leading to inappropriate slide selection
Solution Approach 1:
The patent introduces an intermediary term conversion process between voice recognition output and slide search terms. A conversion table stores multiple alternative terms for each slide search term, allowing the system to match recognized conversation terms with appropriate slides even when exact matches don't exist. This intermediary layer resolves the mismatch between colloquial speech and formal slide terminology.
Solution Approach 2:
The system changes the parameter of term representation by storing multiple alternative terms (synonyms, related terms, different formulations) for each slide search term in the conversion table. This allows flexible matching where a recognized term can match any of the stored alternatives, significantly improving term matching accuracy while maintaining automatic slide transition capability.
2Measurement precision
If multiple alternative terms are stored for each search term to improve matching accuracy, then slide selection accuracy improves, but the system complexity and data storage requirements increase
Solution Approach 1:
The conversion table is prepared in advance during system setup or presentation material creation. All alternative terms and their corresponding slide search terms are pre-defined and stored. During actual presentation, the system only needs to perform simple lookup operations in the pre-prepared conversion table, avoiding complex real-time analysis and reducing computational complexity while maintaining high accuracy.
3Measurement precision
If the system displays selection terms for user confirmation, then slide selection accuracy improves, but the presentation flow is interrupted and time is lost
Solution Approach 1:
The system displays only a limited number of candidate slides (e.g., top 3 matches) rather than all possible slides, and only when confidence is not sufficiently high. In many cases where the recognized term clearly matches a single slide, the system automatically selects without displaying candidates, thus minimizing interruption to the presentation flow while maintaining accuracy when needed.
Data Source
AI summary
A display device comprises a voice recognition unit performing voice recognition, a conversation-derived term extraction unit extracting conversation-derived terms from conversation information derived from the voice recognitions, a search keyword storage storing the conversation-derived terms and search keyword in an associated manner, a search keyword extraction unit extracting search keywords from the search keyword storage using the conversation-derived terms, a material storage unit storing each page of a plurality of presentation materials, a search term of each page, and a score of the search term in an associated manner, a relevant page information extraction unit extracting a page of presentation material associated with the search keyword, a selection term extraction unit extracting the search keywords, and a selection term display unit causing the selection terms to be displayed on a display unit.