Information Providing Device for Hierarchical Customer Intent Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods fail to accurately quantify the contribution of evaluation factors to customer revisit, repurchase, or recommendation intentions, limiting the effectiveness of service improvements.
Innovation Solution
An information providing device and method that conducts multivariate analysis on customer evaluation data to calculate contribution degrees of explanatory variables, using a hierarchical structure to enhance accuracy, and displays results on a network-capable terminal.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional survey results are simply aggregated and displayed, then the implementation is simple and quick, but the accuracy of determining contribution degrees of evaluation factors is insufficient
Solution Approach 1:
The patent segments the evaluation factors into a hierarchical structure with multiple levels (first-level factors like revisit intention, second-level factors like service quality, third-level factors like specific service aspects). This segmentation allows the complex analysis to be broken down into manageable multivariate analysis steps, where each level contributes to understanding the overall contribution degrees without overwhelming complexity.
Solution Approach 2:
The patent introduces multivariate analysis as an intermediary computational method between the raw survey data and the final contribution degree results. This intermediary process uses statistical algorithms to process the hierarchical evaluation factors and produce accurate contribution degree quantifications, bridging the gap between simple data collection and precise measurement.
2Measurement precision
If multivariate analysis with hierarchical structure is conducted, then the accuracy of contribution degree quantification is improved, but the computational complexity and processing time increase
Solution Approach 1:
The hierarchical segmentation of evaluation factors into multiple levels allows the multivariate analysis to be conducted in a structured manner, processing factors level by level rather than all at once. This reduces the computational burden at each step while maintaining overall accuracy, thereby reducing processing time compared to analyzing all factors simultaneously.
Solution Approach 2:
The patent performs preliminary organization of evaluation factors into a hierarchical structure before conducting the multivariate analysis. This preliminary action prepares the data in an optimized format that facilitates faster computational processing during the actual analysis phase, reducing the overall processing time while maintaining measurement precision.
3Measurement precision
If hierarchical evaluation items with multiple levels are used, then the depth of analysis and accuracy are improved, but the complexity of data collection and processing increases
Solution Approach 1:
The patent segments the evaluation data collection process into hierarchical levels, where each level corresponds to specific evaluation items. This segmentation allows the complex data collection to be organized systematically, with each level building upon the previous one, making the overall complex structure manageable and processable through structured multivariate analysis.
Solution Approach 2:
The patent introduces a hierarchical dimension to the evaluation data structure, organizing factors into multiple levels (first-level, second-level, third-level factors). This dimensional organization transforms the complex flat data structure into a layered hierarchy, enabling deeper analysis while providing a systematic framework that simplifies data processing through the multivariate analysis method.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
Problem: provided is an information providing device, a method, and a program capable of quantifying a contribution degree of an evaluation factor with respect to a revisit intention or a recommendation intention of a customer with high accuracy. Solution: An information providing device includes a survey data acquisition means configured to acquire evaluation data including evaluation values for evaluation items related to a revisit intention, repurchase intention, or recommendation intention for others from customers, a multivariate analysis means configured to calculate contribution degrees of explanatory variables with respect to an objective variable by conducting a multivariate analysis using an evaluation value for the revisit intention, repurchase intention, or recommendation intention for others as the objective variable, and evaluation values for evaluation items in the evaluation data as the explanatory variables, and an analysis result output means configured to display an analysis result from the multivariate analysis means on an information terminal. The evaluation data includes an evaluation item of a first level corresponding to the objective variable, evaluation items of a second level that explain the objective variable, and evaluation items of a third level that explain evaluation items of the second level. The multivariate analysis means is configured to execute a first multivariate analysis using an evaluation value for an evaluation item of the second level as an intermediate objective variable, and evaluation items of the third level as explanatory variables, and execute a second multivariate analysis using an evaluation item of the first level as an objective variable and evaluation items of the second level as explanatory variables.