Dynamic Search Result Repositioning for Relevance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Search engines often provide users with irrelevant results, leading to frustration and increased system burden due to repeated queries, as existing query suggestion systems can further complicate the process and reduce efficiency.
Innovation Solution
A system that analyzes user search queries and ranked product lists to determine if products within a 'boost category' should be repositioned, using content model prediction scores and discounted cumulative gain (DCG) scores to dynamically modify the graphical user interface and re-rank products, thereby improving the relevance and efficiency of search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional search engines provide ranked results based on standard algorithms, then the system maintains operational simplicity, but the relevance of search results deteriorates leading to user frustration and repeated queries
Solution Approach 1:
The patent implements dynamic repositioning of search results based on real-time user interactions. The system continuously monitors user behavior (clicks, views, time spent) and dynamically adjusts the ranking of search results, allowing previously hidden relevant results to move to more prominent positions without requiring complex manual intervention or complete system redesign
Solution Approach 2:
The patent segments the search result display into different zones with varying visibility weights. By dividing the result set and applying different repositioning strategies to different segments, the system can improve relevance for specific query types or user profiles without overwhelming the entire system with complex changes
2Ease of operation
If query suggestion systems are implemented to help users find relevant results, then the ease of operation improves, but the device complexity increases and may further frustrate users
Solution Approach 1:
The system performs self-service by automatically analyzing user interactions and adjusting result rankings without requiring users to manually provide feedback or navigate complex suggestion interfaces. The repositioning mechanism operates autonomously based on observed user behavior patterns
Solution Approach 2:
The patent implements a feedback loop where user interactions with search results are continuously monitored and fed back into the ranking system. This feedback drives automatic repositioning of results, improving ease of operation by making the system responsive to user needs without adding complex manual controls
3Loss of time
If the system displays all search results in standard ranking order, then the device complexity remains low, but the loss of time increases as users must scroll through irrelevant results
Solution Approach 1:
The system performs preliminary action by pre-positioning potentially relevant results in optimized locations based on initial analysis of user behavior patterns. Before users even search, the system has prepared repositioning strategies that will automatically activate when relevant interaction patterns are detected
Solution Approach 2:
The patent implements dynamic repositioning that automatically adjusts result rankings based on real-time user interactions, reducing the time users spend scrolling through irrelevant results by bringing relevant content to more visible positions as they interact with the page
Data Source
AI summary
A method includes receiving in-session user activity information comprising a user search query from a user and a ranked list of products to be displayed to the user based on the user search query, where a product within the ranked list of the products is in a boost category, and where the user search query is received via a graphical user interface that is in a first display state. The method also includes analyzing the product in the boost category to determine if the product is to be repositioned within the ranked list of the products. The method further includes, in response to determining that the product that in the boost category is to be repositioned within the ranked list of the products, transmitting instructions to modify the graphical user interface to display the ranked list of the products with the product repositioned within the ranked list of the products, where the ranked list of the products is displayed via the graphical user interface in a second display state, the second display state being different than the first display state. Other embodiments are described.