Vehicle-Mounted Pictogram Selection via Mood Context
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems cannot send distinct pictograms based on user mood via email, as they convert the same text utterance into the same pictogram, limiting user expression.
Innovation Solution
An information processing system with a vehicle-mounted device that includes a sound pickup unit and a control unit, which uses pictogram correspondence information to select appropriate pictograms based on speech recognition data, allowing for mood-based pictogram selection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the same text is converted into the same pictogram, then the conversion is simple and consistent, but the user cannot express different moods or nuances through pictogram selection
Solution Approach 1:
The system introduces additional selection parameters beyond simple text-to-pictogram conversion. By incorporating mood information and contextual data as selection criteria, the system enables multiple pictograms to correspond to the same text input, allowing users to express different nuances and moods while maintaining consistent conversion functionality.
2Adaptability or versatility
If multiple pictograms correspond to the same keyword, then user expression is enhanced, but the selection process becomes more complex
Solution Approach 1:
The system automatically performs pictogram selection based on predefined criteria such as mood information and contextual data. Instead of requiring users to manually select from multiple pictograms, the system autonomously determines the appropriate pictogram, maintaining ease of operation while providing pictogram variety.
Solution Approach 2:
The system incorporates feedback mechanisms where user input (such as mood indicators or contextual information) is processed to determine the appropriate pictogram selection. This feedback loop enables the system to adapt to user intentions and select the most suitable pictogram from multiple options.
3Adaptability or versatility
If speech recognition converts speech to text, then communication is enabled, but mood nuance and contextual information are lost
Solution Approach 1:
The system introduces mood information and contextual data as intermediary elements between speech recognition and pictogram selection. These intermediaries preserve and transmit mood nuance and contextual information that would otherwise be lost in the speech-to-text conversion process, enabling more expressive communication.
Data Source
AI summary
This invention can enhance the convenience of a user. An information processing system 1 includes: a vehicle-mounted device 3 which has a sound pickup unit 36 that picks up a speech sound, and a transmitting unit that transmits speech data that is generated based on the speech sound that is picked up to a control server 8; and the control server 8 which has a server storage unit 82 that stores a pictogram correspondence table 82a in which recognition keywords and pictogram IDs indicating a plurality of pictograms that correspond to the recognition keywords are associated, and a server control unit 81 which executes pictogram processing that selects a recognition keyword that corresponds to text representing a speech sound that is generated by speech recognition based on speech data from among the recognition keywords included in the pictogram correspondence table 82a, and in accordance with a predetermined condition, selects a single pictogram ID from among a plurality of pictogram IDs that are associated with the selected recognition keyword.