Digital Object Ranking System Using Quality Metric Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing e-commerce search engines face issues where filtering by secondary characteristics leads to top results becoming less relevant to the user's request, resulting in a low overall ranking quality metric, causing user dissatisfaction.
Innovation Solution
A method and system for re-ranking digital objects based on a secondary characteristic while ensuring the selected objects are relevant to the user's request, using a machine learning algorithm to determine object parameters that increase the quality metric of the re-ranked set, thereby maintaining relevance and improving user experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If digital objects are filtered and re-ranked based on a secondary characteristic (e.g., price), then the user can find objects with desired secondary attributes, but the top results become less relevant to the user's original search request, reducing overall ranking quality
Solution Approach 1:
The patent applies composite ranking by combining multiple characteristics (objective relevance and secondary attributes) into a unified ranking system. Instead of purely filtering based on secondary characteristics, the system creates a composite score that integrates both relevance metrics and secondary attribute values, producing a re-ranked list that maintains quality while satisfying user filtering preferences
Solution Approach 2:
The system dynamically adjusts ranking parameters by introducing a quality metric threshold that adapts based on the filtering operation. When re-ranking based on secondary characteristics, the system modifies the ranking parameters to balance between maintaining relevance quality and satisfying the secondary characteristic sorting requirement
2Reliability
If digital objects are strictly ranked by relevance to the search request, then the top results are highly relevant, but users cannot easily find objects with specific secondary characteristics (e.g., lowest price)
Solution Approach 1:
The patent implements dynamic re-ranking that adapts to user needs. The system provides a mechanism where users can trigger re-ranking operations based on secondary characteristics while the system dynamically adjusts the ranking algorithm to maintain quality thresholds, creating a flexible system that responds to user control requirements without sacrificing relevance
3Quantity of substance
If the system provides all digital objects ranked by relevance, then completeness is maintained, but the user must manually filter through results to find objects with desired secondary characteristics, increasing time and effort
Solution Approach 1:
The system performs preliminary re-ranking operations automatically when a user applies a secondary characteristic filter. Instead of requiring users to manually examine and filter through all results, the system pre-processes the ranking in advance by computing the re-ranked list based on secondary characteristics while maintaining quality metrics, saving user time and effort
Data Source
AI summary
A method and system for ranking digital object based on an objective characteristic associated therewith are provided. The method comprising: generating a set of digital objects based on a user request, the set of digital objects being rankable according to an objective characteristic thereof; receiving a filter request from the user, the filter request being based on a secondary characteristic of digital objects in the set of digital objects; determining object parameters for the digital objects in the set of digital objects, a given object parameter being indicative of a likelihood that an inclusion of a respective digital object in a re-ranked set of digital objects will increase a quality metric of the re-ranked set of digital objects; selecting digital objects based on object parameters; ranking digital objects based on respective values of the secondary characteristic, thereby generating the re-ranked set of digital objects.