Icon-Based Information Presentation for Voice Dialogue Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Natural language dialogue systems struggle to effectively present information to users, particularly in environments like driving or walking, where visual and auditory attention is limited, leading to difficulties in understanding lengthy or complex responses.
Innovation Solution
An information presentation device that combines voice output with visual icons and additional information display, allowing users to intuitively understand topics and options through icon representation, even when spoken information is unexpected or not explicitly mentioned.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If the natural language dialogue system outputs detailed text information as an answer, then the information completeness is improved, but the user understanding difficulty increases
Solution Approach 1:
The patent introduces icons as an intermediary element between the text information and the user's perception. The icon representation unit converts key words from the text answer into visual icons, which serve as a mediator to facilitate user understanding without requiring close viewing of detailed text, thus resolving the contradiction between information completeness and user understanding difficulty
Solution Approach 2:
The patent replaces the traditional text-based information presentation mechanism with a multi-modal mechanism that incorporates visual icons and voice output. This substitution allows users to perceive information through multiple channels simultaneously, improving understanding without increasing the textual information load
2Quantity of substance
If the system displays multiple choices as text on a display, then the information richness is improved, but the driver's attention requirement increases
Solution Approach 1:
The patent uses icons as an intermediary to represent multiple choices and information categories. The icon representation unit generates visual icons that correspond to different information types or choices, allowing drivers to quickly identify and select relevant information without reading extensive text, thus reducing attention requirements while maintaining information richness
Solution Approach 2:
The patent transitions from one-dimensional text display to two-dimensional icon-based visual representation. By organizing information into visual icons with spatial relationships, the system enables faster perception and selection by drivers who can process visual information more efficiently than text, especially in moving vehicles
3Quantity of substance
If the natural language dialogue system provides comprehensive answer information, then the information completeness is improved, but the user's time to process information increases
Solution Approach 1:
The patent segments the comprehensive answer information into discrete key words and represents each as a separate visual icon. This segmentation allows users to quickly scan and identify relevant information without processing large blocks of text, significantly reducing processing time while preserving information completeness through the icon representation of all key concepts
Solution Approach 2:
The icon representation unit performs preliminary processing by pre-converting key words into visual icons before the user needs to access the information. This preliminary action prepares the information in an optimally perceivable format, eliminating the need for users to read and interpret text, thus reducing processing time while maintaining completeness
Data Source
AI summary
There is provision of an information presentation device including a displaying unit, an input receiving unit configured to receive an input from a user, an answer generating unit configured to generate an answer sentence in response to the input received by the input receiving unit, an additional information acquiring unit configured to acquire additional information related to a word contained in the answer sentence generated by the answer generating unit, a voice outputting unit configured to output the answer sentence by sound, and an information outputting unit configured to output the additional information on the displaying unit.