Keyword Query Filter Scoring via Popularity Tables
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for identifying and presenting filters in keyword queries on network-based marketplaces face challenges in accurately interpreting user intent and efficiently generating relevant search results, as they struggle to differentiate between competing interpretations of attribute-value pairs and prioritize results based on popularity.
Innovation Solution
The system employs a popularity table to score filter sets in keyword queries by analyzing the probabilities of attribute-value pairs and their co-occurrences in completed listings, allowing it to identify the most popular filter sets and present them in an ordered manner on user interfaces, thereby enhancing search result relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the system analyzes multiple interpretations of attribute-value pairs in keyword queries, then the accuracy of search results improves, but the complexity of the system increases
Solution Approach 1:
The system segments the query processing into distinct components: extracting attribute-value pairs from keywords, generating multiple filter set interpretations, scoring each interpretation, and selecting the highest-scoring filter set. This segmentation allows the system to handle complexity systematically while maintaining accuracy.
Solution Approach 2:
The system performs preliminary actions by pre-processing completed listings to build a popularity table that stores pre-calculated scores for attribute-value pairs and filter sets. This pre-computation reduces the complexity of real-time query processing while maintaining high accuracy in search results.
2Measurement precision
If the system prioritizes filter sets based on popularity from historical data, then the relevance of search results improves, but the time required to process queries increases
Solution Approach 1:
The system pre-computes popularity scores for attribute-value pairs and filter sets by analyzing completed listings beforehand and storing them in a popularity table. During query processing, the system simply retrieves these pre-calculated scores, significantly reducing query processing time while maintaining high relevance of results.
Solution Approach 2:
The system creates a simplified copy of the complex popularity analysis in the form of a popularity table with pre-calculated scores. This copy allows rapid query processing without requiring full re-analysis of historical data for each query, thus reducing processing time while preserving relevance.
3Quantity of substance
If the system generates multiple filter sets from keyword queries, then the completeness of search results improves, but the difficulty of interpreting user intent increases
Solution Approach 1:
The system uses popularity scores from historical data as feedback to evaluate and rank multiple filter set interpretations. By comparing the scores of different interpretations, the system can objectively determine which interpretation best matches user intent, reducing the difficulty of interpretation while maintaining completeness.
Solution Approach 2:
The system changes the parameter of filter set selection from subjective interpretation to objective scoring based on popularity metrics. By transforming user intent detection into a parameter-based scoring system, the system can handle multiple interpretations systematically and select the most relevant one, improving completeness while reducing interpretation difficulty.
Data Source
AI summary
Systems and methods to identify a filter set in a keyword query are described. The system receives a query from a client machine. The system identifies filter sets based on the query and a based on rules. The filter sets include a first filter set that includes a first filter. The rules are utilized to associate at the least one keyword from the query to the first filter. The system further scores the filter sets based on probabilities to generate scores. The probabilities describe occurrences of attribute-value pairs in listings that respectively describe items that were previously transacted on a network-based marketplace. The system further identifies the first filter set from the filter sets based on the scores, generates a user interface including search results that are identified based on the identified first filter set, and communicates the user interface, over the network, to the client machine.