Personalized Search Filtering for E-Commerce
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
E-commerce websites return the same search results to all users using similar search keywords, which may not satisfy individual user preferences, leading to inefficient and ineffective product searches due to inclusion of unwanted products or sellers based on past experiences.
Innovation Solution
Implementing a system that allows users to configure screening information to exclude specific products or sellers from search results, enabling personalized search outcomes by storing user preferences and applying them to subsequent searches.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the e-commerce website assigns products sold by different sellers with the same probability of being found and presented among search results, then fairness is ensured, but user satisfaction deteriorates because the same search results are returned to all users regardless of individual preferences
Solution Approach 1:
The patent segments search results by user identity, creating personalized search result sets for different users based on their historical behavior, preferences, and feedback. This allows the system to maintain fairness (each user gets relevant results) while enabling personalization (different users get different results based on their individual characteristics).
Solution Approach 2:
The system performs preliminary actions by collecting and analyzing user feedback, click-through rates, and browsing behavior in advance to pre-compute personalized search result rankings. This preliminary analysis enables the system to quickly deliver personalized results without compromising fairness, as the personalization is based on objective user preference data collected beforehand.
2Device complexity
If the e-commerce website returns the same search results to all users using similar search keywords, then system complexity is reduced, but search efficiency deteriorates because users must manually filter out unwanted products
Solution Approach 1:
The system implements self-service by automatically analyzing user behavior patterns, preferences, and feedback to generate personalized search results without requiring manual user configuration. The system serves itself by using its own collected data to improve search results, eliminating the need for complex user setup while significantly improving search efficiency through automated personalization.
Solution Approach 2:
The system incorporates feedback mechanisms where user interactions (clicks, purchases, complaints, browsing time) are continuously collected and used to refine personalized search results. This feedback loop enables the system to automatically adapt to user preferences over time, improving search efficiency without increasing system complexity, as the feedback is processed through automated algorithms.
3Quantity of substance
If the e-commerce website includes all relevant products in search results, then completeness of information is improved, but information quality deteriorates because unwanted products from disliked sellers appear among the results
Solution Approach 1:
The system changes the parameter of result selection from static (same for all users) to dynamic (personalized per user) based on user preference parameters. By adjusting the selection criteria according to individual user profiles, the system maintains a comprehensive set of results while filtering out unwanted items, thus preserving quantity while improving precision through parameter-based personalization.
Data Source
AI summary
Applying screening information to search results is disclosed, including: receiving a search request for products, wherein the search request comprises one or more search conditions and a set of user information; retrieving screening information associated with the set of user information, wherein the screening information indicates one or both of seller information and product information to exclude from search results; determining a plurality of search results based at least in part on the one or more search conditions and determining a search result from the plurality of search results to be excluded based at least in part on the screening information; and returning one or more search results from the plurality of search results other than the search result determined to be excluded.