Mobile Recommendation System Using User Preference Pattern Mining
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional recommendation techniques, such as content-based and collaborative filtering, are impractical for real exhibitions or megastores due to the time-consuming process of gathering quantification values from a large number of objects, making them unsuitable for providing personalized recommendations in such environments.
Innovation Solution
A mobile recommendation system that utilizes a User Preference Pattern (UPP) mining method to analyze user behavior by tracking location data in exhibition or store spaces, generating personalized recommendations through a wireless communication module, tracking module, and recommendation module, which classifies users into correlated groups based on visit patterns and preferences, and applies a Profile-to-Preference-Rule (PPR) mining method to derive profile features for generating recommendations when insufficient data is available.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional content-based or collaborative recommendation techniques are used, then personalized recommendations can be generated, but the process becomes time-consuming and impractical due to the large number of objects to be evaluated
Solution Approach 1:
The patent segments the recommendation process into two phases: an offline phase where user preferences are pre-analyzed and stored in a database, and an online phase where pre-computed recommendation lists are quickly retrieved and presented. This segmentation allows complex analysis to be done in advance without affecting real-time performance.
Solution Approach 2:
The system performs preliminary analysis of user preferences and object characteristics offline before the actual recommendation is needed. User profiles are pre-built by analyzing their interactions with objects, and recommendation lists are pre-computed based on these profiles, enabling fast delivery when users actually request recommendations.
2Adaptability or versatility
If users provide quantification values for each object in collaborative recommendation, then personalized preferences can be determined, but the process becomes impractical due to the large number of objects
Solution Approach 1:
The system automatically analyzes user interactions with objects (such as viewing, clicking, or purchasing behavior) to infer preferences without requiring users to manually provide quantification values. The system self-serve by extracting preference information from observable user behaviors, eliminating the burden of manual input while maintaining personalization capability.
Data Source
AI summary
A mobile recommendation system for an exhibition space is provided. The mobile recommendation system includes a wireless communication module, a tracking module, a preference correlation module, and a recommendation module. The wireless communication module receives location information corresponding to a plurality of users. The tracking module stores the location information and generates a plurality of track records corresponding to the users according to the location information. The preference correlation module generates track correlation information between the users and the track records according to the track records. The recommendation module generates a recommendation list according to the track correlation information.