Search Ranking Adjustment via User-Seller Trust Levels
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current e-commerce search engines fail to consider individual user differences in search result rankings, leading to suboptimal results for users with unique preferences and trust levels towards sellers.
Innovation Solution
A two-part search results ranking technique that preliminarily ranks product information based on known methods and then adjusts the ranking sequence using user-specific trust level values associated with sellers, limiting computations by focusing on a predetermined number of intermediate ranked results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If search results are ranked based on traditional factors (keywords, price, transaction quantity, seller scores), then search accuracy is improved, but individual user differences and preferences are not considered
Solution Approach 1:
The system pre-calculates and stores trust level values between users and sellers in advance, so that when a search is performed, the ranking can be quickly adjusted based on these pre-computed values without adding significant computation time to the search process
Solution Approach 2:
The patent introduces a new parameter 'trust level value' that quantifies the relationship between users and sellers. This parameter is integrated into the search ranking formula, transforming the ranking from a static process to a dynamic one that adapts to individual user preferences while maintaining traditional ranking factors
2Ease of operation
If search results are adjusted based on user-specific trust level values, then user experience is improved, but computation burden increases
Solution Approach 1:
Trust level values are pre-calculated and stored in a database before searches are executed. This preliminary computation avoids the need to calculate trust levels in real-time during each search, significantly reducing the computation burden during actual search operations
Solution Approach 2:
The system automatically maintains and updates trust level values based on user interactions and seller performance data, eliminating the need for manual input or complex real-time calculations. The trust level system serves itself by automatically updating based on transaction data and user feedback
3Adaptability or versatility
If all search results are re-ranked considering user trust levels, then personalized results are achieved, but processing time increases
Solution Approach 1:
By pre-computing and storing trust level values, the system enables rapid re-ranking during search operations. The pre-stored values are simply retrieved and applied to adjust rankings, avoiding time-consuming calculations during the actual search process
Solution Approach 2:
The system applies trust level adjustments selectively to enhance personalization without completely re-ranking all search results from scratch. The adjustment is made as a modification to existing rankings rather than a complete recalculation, reducing processing time
Data Source
AI summary
Adjusting search results ranking is disclosed, including: receiving a search query comprising one or more keywords submitted by a user; determining intermediate ranked results comprising a plurality of sets of product information matching the one or more keywords; determining a trust level value associated with the user with respect to a first seller of a plurality of sellers associated with the intermediate ranked results, wherein the trust level value is determined based at least in part on one or more historical user product information evaluation records associated with the first seller submitted by the user; and adjusting ranking associated with the intermediate ranked results based at least in part on the determined trust level value associated with the user with respect to the first seller to determine final ranked results.