Context-Aware Emotion Estimation Using Attention Objects and Appearance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing emotion estimation technologies fail to accurately account for the varying emotions of a user when they are paying attention to different objects, leading to inconsistent and inaccurate emotion assessments.
Innovation Solution
An information processing device that includes an acquisition unit, an identification unit, and an emotion estimation unit, which identifies the object a user is paying attention to and the user's appearance, using various input information types to estimate emotion based on object and appearance information, employing methods such as algebraic expressions, learned models, and classifiers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If emotion estimation is performed based on general user state information, then the estimation process is simple, but the estimation accuracy is low because it does not account for variations in emotion based on different attention objects
Solution Approach 1:
The emotion estimation process is segmented into multiple stages: first identifying the attention object using sight line data, then selecting appropriate estimation methods based on the identified object. This segmentation allows the system to apply different levels of complexity only when necessary, improving accuracy without uniformly increasing system complexity across all scenarios.
Solution Approach 2:
The system performs preliminary identification of the attention object before conducting emotion estimation. By using sight line data to determine what the user is looking at first, the system prepares the appropriate estimation method in advance, which improves the accuracy of subsequent emotion analysis without adding significant real-time processing complexity.
2Measurement precision
If the system considers multiple factors including attention objects and user appearance, then emotion estimation accuracy improves, but the amount of information processing increases
Solution Approach 1:
The system applies different processing qualities to different aspects of user data. High-precision processing is applied specifically to sight line data for attention object identification, while appearance information is processed at an appropriate level of detail. This local quality approach ensures accurate emotion estimation without uniformly processing all information at maximum detail, reducing overall information processing load.
Solution Approach 2:
The attention object identification serves as an intermediary step that bridges raw input data and emotion estimation. By first determining what the user is looking at, the system creates a contextual framework that guides subsequent emotion analysis, reducing the need to process all possible information variables simultaneously and thereby reducing information processing load.
3Ease of operation
If emotion estimation assumes constant emotion when user is paying attention, then processing is simplified, but estimation accuracy deteriorates because user emotion varies based on different attention targets
Solution Approach 1:
The system transitions from a static assumption of constant emotion to a dynamic approach where emotion estimation varies based on the identified attention object. The estimation method is dynamically selected according to what the user is looking at, allowing the system to maintain processing simplicity through automated selection while achieving higher accuracy through context-aware estimation.
Solution Approach 2:
The system changes the parameters of emotion estimation based on the identified attention object. Different objects or contexts trigger different estimation parameters and methods, allowing the system to adapt to varying user emotions without requiring complex manual configuration. This parameter-based adaptation maintains ease of operation while significantly improving estimation accuracy.
Data Source
AI summary
An information processing device includes an acquisition unit, an identification unit and an emotion estimation unit. The acquisition unit acquires input information as information regarding a user in a certain situation. The identification unit identifies an object to which the user is paying attention and the user's appearance when the user is paying attention to the object based on the input information. The emotion estimation unit estimates emotion of the user based on object information indicating the identified object, appearance information indicating the identified appearance, and a predetermined method of estimating the emotion.