User Behavior Recommendation Using Affinity-Based Habit Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing life habits improvement support devices do not provide support information that can be easily executed by users, hindering effective behavioral changes.
Innovation Solution
A user behavior proposal device that calculates user affinity and risk contribution for various behaviors using terminal logs, user attributes, and questionnaire results to recommend executable behaviors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If support information for life habits improvement is provided to users, then health improvement potential is enhanced, but the information is not easily executable by users
Solution Approach 1:
The patent applies local quality by calculating individual affinity values for each behavior type specific to each user, rather than providing generic health advice. The affinity calculation unit computes user-specific affinity based on terminal logs, user attributes, and questionnaire results, enabling personalized behavior recommendations that match each user's characteristics and likelihood of execution.
Solution Approach 2:
The patent uses parameter changes by transforming raw user data (terminal logs, attributes, questionnaire results) into an affinity parameter that quantifies user-behavior compatibility. This affinity parameter serves as a decision criterion for selecting recommended behaviors, changing the approach from generic health advice to parameter-driven personalized recommendations.
2Measurement precision
If personalized behavior recommendations are generated using multiple data sources, then behavior accuracy is improved, but system complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the recommendation system into distinct functional units: an affinity calculation unit that processes multiple data sources (terminal logs, user attributes, questionnaire results) separately, and a recommendation generation unit that synthesizes the affinity results. This modular segmentation manages complexity while maintaining comprehensive data analysis for accurate recommendations.
Solution Approach 2:
The patent introduces an affinity value as an intermediary parameter that mediates between multiple input data sources and the final behavior recommendation. Instead of directly processing complex multi-source data, the system first computes affinity values that capture user-behavior compatibility, then uses these affinity values to generate recommendations, simplifying the overall system architecture.
Data Source
AI summary
A user behavior proposal device that can enable a user to carry out an executable behavioral change is provided. In the user behavior proposal device 100, an affinity calculating unit 102 calculates an affinity of one user with each life habits entry on the basis of a terminal log of the user. An information transmitting unit 105 transmits the calculated affinity to the user. The information transmitting unit 105 may notify one user of a behavior based on an affinity satisfying a predetermined condition as a recommended behavior as information based on the affinity.