Entertainment Robot User Identification with Matching-Degree Action Modes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional user identification methods require high authentication accuracy and expensive sensors, which are not suitable for entertainment robots that need a more relaxed identification process.
Innovation Solution
An information processing device that acquires feature data from users using various sensors, derives a matching degree with registered user data, and sets an action mode based on this matching degree to improve authentication accuracy without requiring high precision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional user identification methods are used, then authentication accuracy is improved, but system cost and complexity increase
Solution Approach 1:
The patent applies dynamics by making the identification system adaptable through multiple action modes (first, second, and third modes) that dynamically adjust the identification process based on matching degree results. The system transitions between different operational states depending on whether the matching degree exceeds thresholds, allowing flexible response to varying identification confidence levels without requiring always-high-cost components.
Solution Approach 2:
The patent changes parameters by introducing multiple threshold values (first threshold, second threshold) for matching degree comparison. Instead of using a single fixed threshold for user identification, the system compares the matching degree against multiple parameter levels to determine appropriate action modes, enabling accurate identification while accommodating varying sensor quality and computational resources.
2Reliability
If high authentication accuracy is required, then reliable user identification is achieved, but the system becomes unsuitable for entertainment robots
Solution Approach 1:
The system dynamically adapts its behavior based on the entertainment context by implementing multiple action modes. When the matching degree is high (exceeds first threshold), the system confidently identifies the user. When the matching degree is intermediate (between first and second thresholds), the system enters a second mode that may involve additional verification or probabilistic identification. When the matching degree is low (below second threshold), the system enters a third mode appropriate for non-identification scenarios. This dynamic adaptation makes the system suitable for entertainment robots that need flexibility rather than absolute precision.
Solution Approach 2:
The patent applies partial action by not always requiring complete certainty for user identification. In the second action mode, the system operates with intermediate confidence levels, performing partial identification actions that are sufficient for entertainment purposes but would not meet strict authentication requirements. This allows the system to function effectively in entertainment contexts where perfect accuracy is unnecessary and may even be counterproductive to user experience.
3Measurement precision
If expensive sensors are used, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent changes the parameter of threshold values to compensate for varying sensor quality. By using multiple thresholds (first threshold, second threshold) for matching degree comparison, the system can achieve reliable identification results even with less precise sensors. The multi-threshold approach allows the system to adjust its decision criteria based on the quality of input data, maintaining effectiveness without requiring expensive high-precision sensors.
Solution Approach 2:
The patent employs a software-based identification approach that uses inexpensive feature extraction and comparison algorithms instead of expensive specialized sensors. The system processes feature data through computational matching against stored user profiles, using software intelligence to compensate for the limitations of simpler, cheaper hardware sensors. This replaces the need for costly dedicated authentication sensors with more affordable general-purpose sensing combined with sophisticated processing.
Data Source
AI summary
A feature acquiring section 100 obtains feature data of a target person. A matching degree deriving section 110 derives a matching degree between the feature data and feature data of a registered user stored in a feature amount database 120. An identifying section 130 determines that the target person is the registered user in a case where the matching degree is greater than or equal to a first threshold, and determines that the target person is not the registered user in a case where the matching degree is less than a second threshold smaller than the first threshold. An action management section 140 sets an action mode of an acting subject according to the matching degree.