Voice Interaction Device Topic Selection via Activity Database
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing voice interaction systems fail to provide topics that are relevant to a child's activities and easy for them to discuss, as they rely on keyword extraction and random topic generation, which do not accurately reflect the child's engagement or activity level.
Innovation Solution
A device that uses image and audio data to identify adults and children, extracts voice features, and determines when to introduce new topics by analyzing activity names stored in a database, selecting topics based on movement and audio levels to ensure engagement and relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If keyword extraction and random topic generation are used, then the system is simple to operate, but the topic relevance to child's activity deteriorates
Solution Approach 1:
The system performs preliminary actions by capturing image data and audio data before the conversation occurs, extracting activity names and movement amounts in advance, and storing them in databases. This preliminary data collection enables the system to select relevant topics based on the child's actual activity without requiring complex real-time analysis during conversation.
Solution Approach 2:
The system uses feedback mechanisms by continuously monitoring the child's activity through image and audio data, extracting activity names and movement amounts, and using this information to select appropriate topics for conversation. The system adjusts topic selection based on the extracted activity information, creating a feedback loop that improves topic relevance.
2Loss of information
If activity-based topic selection is implemented, then topic relevance to child's activity is improved, but device complexity increases
Solution Approach 1:
The system segments the complex task of activity recognition and topic selection into separate functional modules: image data acquisition, audio data acquisition, activity name extraction, movement amount calculation, and topic selection. Each module handles a specific aspect of the process, making the overall system more manageable and maintainable despite the increased functionality.
Solution Approach 2:
The system introduces intermediary components including databases for storing activity data and movement information, as well as processing units that act as mediators between data acquisition and topic selection. These intermediary elements organize and facilitate the flow of information between different system components, reducing direct complexity in the main processing path.
3Reliability
If movement amount and audio level analysis is added, then conversation engagement is improved, but measurement precision requirements increase
Solution Approach 1:
The system applies partial action by focusing measurement on specific aspects of child activity such as movement amount and audio level, rather than attempting to measure all possible activity parameters. This selective measurement approach provides sufficient information for topic selection without requiring overly precise or comprehensive measurement systems.
Data Source
AI summary
A topic providing device includes a candidate topic extractor, a provided topic determiner, a voice synthesizer, and a speaker. When a determination is made that a parent and child are conversing and that there is a need to provide a new topic to the parent and child, based on a conversation history database and a child activity database storing at least one activity name indicating an activity the child was engaged in for a first predetermined period of time, the candidate topic extractor extracts at least one candidate topic that corresponds to the at least one activity name in the child activity database and does not correspond to an activity name included in text data recorded in a first database. From the at least one candidate topic, the provided topic determiner selects one topic to provide to the parent and the child. The voice synthesizer generates voice data containing the one topic. The speaker outputs the voice data.