Search Query Identification Using Semantic Association and Keyword Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional search methods for identifying time-effective search queries face challenges in balancing identification accuracy and recall rate, as raising thresholds to improve accuracy reduces the recall rate of search results closer to the present time.
Innovation Solution
A search method and apparatus that identifies first time-effective search queries from a search log, selects candidate queries based on semantic association and preset keywords, processes these queries to remove those with low semantic similarity or relevance, and uses the resulting second time-effective search queries to improve recall rate while maintaining accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If thresholds are raised to improve identification accuracy of time-effective search queries, then accuracy is improved, but recall rate is reduced
Solution Approach 1:
The patent segments the identification process into multiple stages: first identifying high-frequency search queries above a first threshold, then further filtering these results using a second threshold to identify time-effective queries. This multi-stage segmentation allows the system to maintain higher recall in the first stage while achieving high precision in the final identification, resolving the contradiction between accuracy and recall rate.
Solution Approach 2:
The patent performs preliminary identification of candidate time-effective search queries using a lower first threshold before applying the stricter second threshold. This preliminary action expands the candidate pool to maintain high recall, while the subsequent filtering ensures high accuracy in the final results, thus resolving the contradiction between recall rate and identification accuracy.
2Ease of manufacture
If conventional identification methods are used, then implementation is simple, but identification recall rate is reduced
Solution Approach 1:
The patent dynamically adjusts identification strategies by first identifying high-frequency queries using a relaxed threshold, then applying semantic analysis and time-based filtering only to these candidates. This dynamic approach maintains implementation simplicity while significantly improving recall rate compared to applying strict thresholds to all queries from the beginning.
Data Source
AI summary
A search method and apparatus. A specific embodiment of the search method includes: finding a set of first time-effective search queries from a search log; selecting search queries meeting one of the following selection requirements as candidate time-effective search queries: included in the search log and semantically associated with the first time-effective search queries in the set of first time-effective search queries; included in the search log and containing a combination of preset keywords; processing the candidate time-effective search queries to obtain second time-effective search queries; performing search with a second time-effective search query, when a search query entered by the user matches the second time-effective search query. The present disclosure achieves obtaining the second time-effective search queries from the search queries of the search log based on the identified first time-effective search queries, thus raising the identification recall rate and further improving the identification effect of the time-effective search queries, on the condition that the identification accuracy is ensured in the identification process of the time-effective search queries.