Search Result Processing Using Accurate and Semantic Matching Scores
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional search result processing technologies fail to accurately meet diverse user search needs due to inadequate consideration of text similarity calculations, which often ignore word order and context, leading to unsatisfactory top-ranked search results.
Innovation Solution
A method and apparatus that calculate accurate and semantic matching scores for search results by using semantic representation vectors and weight vectors, combining accurate matching with semantic matching to adjust similarities based on user search needs, thereby improving the relevance of top-ranked results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional text similarity algorithms are used for search result sorting, then the sorting process is simple and fast, but the similarity calculation accuracy is insufficient and cannot meet diverse user search needs
Solution Approach 1:
The patent segments the similarity calculation process into two distinct parts: accurate matching (exact word matching with position awareness) and semantic matching (meaning-based matching using word embeddings). This segmentation allows each part to specialize in different aspects of similarity, improving overall accuracy while maintaining manageable complexity through modular design.
Solution Approach 2:
The patent introduces semantic representation vectors (word embeddings) that add a new dimensional layer to the similarity calculation. Instead of only comparing surface-level text features, the system projects words into a high-dimensional semantic space where meaning-based similarity can be captured, effectively adding another dimension to the matching process.
2Measurement precision
If semantic representation vectors and weight vectors are introduced to calculate accurate and semantic matching scores, then the search result ranking accuracy is improved, but the computational complexity increases
Solution Approach 1:
The patent performs preliminary action by pre-training word embedding models and storing semantic representation vectors in advance. During search operations, these pre-computed vectors are directly utilized rather than calculated in real-time, significantly reducing the computational power required during actual search while maintaining high ranking accuracy.
Solution Approach 2:
The patent dynamically adjusts the importance weights of accurate matching versus semantic matching based on different search scenarios. By changing the weight parameters adaptively, the system can optimize computational resource allocation - emphasizing accurate matching when precision is critical and semantic matching when understanding user intent is more important.
Data Source
AI summary
This disclosure relates to a search result processing method and apparatus, and a storage medium. The method may include acquiring a search result according to a search keyword and obtaining an accurate matching score of the search result relative to the search keyword. The method may further include determining a semantic matching weight vector of the search result, a semantic representation vector of the search keyword, and a semantic representation vector of the search result. The method may further include obtaining a semantic matching score of the search result relative to the search keyword according to the semantic representation vectors and the semantic matching weight vector. The method may further include obtaining a similarity between the search result and the search keyword according to the accurate matching score and the semantic matching score.