Search Result Ranking by User Intent Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing search engine ranking techniques fail to accurately differentiate between multiple intents behind a query, assuming all users have the same intent, leading to suboptimal result satisfaction for users with diverse needs.
Innovation Solution
A method that identifies user types based on the number and type of results selected, determines user profiles, and re-ranks results to optimize user satisfaction by prioritizing results relevant to the majority of users, using a user satisfaction metric to position results for quicker user satisfaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional keyword-based ranking is used, then results are returned quickly, but user satisfaction is low because multiple intents are not differentiated
Solution Approach 1:
The patent segments users into different user types based on their query intent and behavior patterns. By dividing the homogeneous user group into heterogeneous segments with distinct intents, the system can apply different ranking strategies to satisfy diverse user needs, thereby improving intent differentiation accuracy without overwhelming complexity
Solution Approach 2:
The patent dynamically adjusts ranking based on identified user types. Instead of using a static ranking approach, the system adapts the ranking methodology according to the specific user type detected, allowing the ranking system to be flexible and responsive to different user intents while maintaining manageable complexity through structured adaptation
2Reliability
If results are re-ranked to satisfy majority users, then overall user satisfaction improves, but time to scan and find relevant results increases
Solution Approach 1:
The patent performs preliminary user type identification and intent classification before final result ranking. By pre-segmenting users and pre-determining their intent categories, the system can quickly apply the appropriate ranking strategy without requiring users to scan through results, thereby reducing scanning time while maintaining high satisfaction consistency
Solution Approach 2:
The patent changes the ranking parameters based on user type classification. Different user types have different ranking parameters optimized for their specific intents, allowing the system to quickly present relevant results without requiring users to scan through irrelevant content, thus reducing time loss while maintaining reliable satisfaction
Data Source
AI summary
Techniques and systems are disclosed providing improved ranking of results to an online search-based query. One or more user types are identified for a search-based query, and may correspond to a number of user relevant results, and which user results are selected. A user profile can be determined for the respective user types for the search-based query, which may identify a proportion of the users that belong to that type, and how many results are relevant to that type. A set of relevant results can be identified for the respective user types for the search-based query, based on a number of results used by the user type. An improved ranking of the results can be determined for the search-based query, from the one or more sets of relevant results, based on user profiles and a desired user satisfaction metric for a desired number of users.