Privacy-Preserving Customer Data Combination via Feature Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Companies are reluctant to share customer data due to concerns about personal information protection and potential disadvantages, limiting the provision of fine-grained customer data.
Innovation Solution
An information processing system that acquires and combines feature data from different groups of constituents while implementing information protection measures, using identification information and clustering techniques to effectively combine data while maintaining privacy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If customer data is provided externally in detailed form, then data analysis accuracy is improved, but personal information protection is compromised
Solution Approach 1:
The patent segments customer data into multiple feature dimensions (demographic features, purchase behavior features, browsing behavior features, etc.) and organizes them into structured data groups. This segmentation allows selective combination of features while maintaining privacy protection, as individual detailed records are not directly exposed.
Solution Approach 2:
The patent introduces a data combination system that acts as an intermediary between data holders and data users. This system combines features from multiple sources according to predetermined rules and generates aggregated data groups, preventing direct access to individual customer records while still enabling analytical insights.
2Loss of information
If fine-grained customer data is shared, then commercial analysis value is improved, but data holder's potential disadvantages increase
Solution Approach 1:
The patent merges data from multiple holders through a standardized combination process. Multiple data groups containing overlapping customer features are combined according to predetermined rules, creating comprehensive data aggregates that preserve analytical value while distributing risk across multiple participants rather than exposing individual detailed records.
Solution Approach 2:
The patent changes the parameter representation from individual customer records to aggregated feature combinations. Data is transformed from detailed personal information to statistical aggregates and pattern descriptions, maintaining commercial analysis value while reducing the harm potential of any single data exposure.
3Object-affected harmful factors
If customer data is provided in encrypted or modified form, then personal information protection is improved, but data combination effectiveness deteriorates
Solution Approach 1:
The patent creates standardized data group templates that replicate the essential structure and relationships of customer data without containing actual personal information. These template structures enable effective data combination and analysis while the absence of real personal identifiers maintains privacy protection.
Solution Approach 2:
The patent develops a universal data combination framework that can process multiple types of customer data (demographic, purchase, browsing) through a single standardized process. This multi-functional approach maintains data combination effectiveness across different data sources while the standardized aggregation process inherently protects privacy by design.
Data Source
AI summary
A method according to an aspect of the present disclosure includes combining pieces of first feature data and pieces of second feature data. Each of the pieces of first feature data is associated with first identification information related to a corresponding one or more of first constituents included in a first group and indicates a feature of the corresponding one or more of the first constituents. Each of the pieces of the second feature data corresponds to one of clusters in the second group. The second feature data includes statistic data associated with second identification information related to two or more of the second constituents included in a corresponding cluster. The statistic data has a statistic indicating a feature of two or more of the second constituents included in the corresponding cluster. The combining is performed based on the first identification information and the second identification information.