Satisfaction Estimation Model for Collaborative Performance Agents
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional performance evaluation technologies struggle to estimate a performer's degree of satisfaction in collaborative performances, as the second performance by another performer often differs from the first, making it difficult to assess satisfaction accurately.
Innovation Solution
A trained model establishment method using machine learning to estimate satisfaction by acquiring datasets of first and second performance data along with satisfaction labels, allowing for the generation of a satisfaction estimation model that matches the indicated degree of satisfaction, and applying this model to recommend and adjust performance agents.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional performance evaluation methods are used to assess accuracy of individual performances, then measurement precision is improved, but the ability to estimate performer satisfaction in collaborative performances deteriorates
Solution Approach 1:
The satisfaction estimation model serves multiple functions: it evaluates individual performance accuracy while simultaneously assessing collaborative performance satisfaction. The model processes both first performance data and second performance data to generate comprehensive satisfaction estimates, making the evaluation system versatile for different performance contexts.
Solution Approach 2:
The system changes evaluation parameters from solely accuracy-based metrics to include satisfaction-based metrics. By training the model with satisfaction labels and using it to estimate performer satisfaction alongside accuracy, the system adapts its evaluation parameters to capture both individual and collaborative performance aspects.
2Adaptability or versatility
If machine learning is applied to train a satisfaction estimation model using multiple datasets, then the ability to estimate performer satisfaction is improved, but device complexity increases
Solution Approach 1:
The satisfaction estimation model is trained in advance using multiple datasets containing first performance data, second performance data, and satisfaction labels. This preliminary training action prepares the model before actual use, allowing it to estimate performer satisfaction without adding complexity to the real-time evaluation process.
Solution Approach 2:
The trained satisfaction estimation model acts as an intermediary between raw performance data and satisfaction assessment. It mediates the complex task of estimating performer satisfaction by processing first and second performance data through learned patterns, simplifying the overall system architecture.
3Measurement precision
If the satisfaction estimation model is trained to match satisfaction labels from datasets, then measurement precision of satisfaction estimation is improved, but loss of time during model training increases
Solution Approach 1:
The model training is performed as a preliminary action before deployment. Multiple datasets with satisfaction labels are processed in advance to train the satisfaction estimation model, achieving high precision satisfaction estimation without time loss during actual performance evaluation.
Solution Approach 2:
The trained model enables continuous satisfaction estimation without interruption. Once training is complete, the model can continuously process first and second performance data to estimate performer satisfaction in real-time, maintaining precision without recurring time loss.
Data Source
AI summary
A trained model establishment method realized by a computer includes acquiring a plurality of datasets each of which is formed by a combination of first performance data of a first performance by a performer, second performance data of a second performance performed together with the first performance, and a satisfaction label indicating a degree of satisfaction of the performer, and executing machine learning of a satisfaction estimation model by using the plurality of datasets. In the machine learning, the satisfaction estimation model is trained such that, for each of the datasets, a result of estimating a degree of satisfaction the performer from the first performance data and the second performance data matches the degree of the satisfaction indicated by the satisfaction label.