Database Query Entity Prediction via User Selection Scaling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Database systems face inaccuracies in predicting intended entities for search queries and require significant time and resources to process search index data, limiting their efficiency in generating query results.
Innovation Solution
The system uses previous users' selections to associate query terms with entities, scaling and normalizing this information to predict subsequent user intentions, thereby improving query result ordering and reducing reliance on search index data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the system uses search index data to predict entity intentions, then query results can be generated, but the prediction accuracy is insufficient and system resources are consumed
Solution Approach 1:
The system performs preliminary actions by collecting and analyzing user selection patterns before query execution. It pre-processes user behavior data to build prediction models that estimate entity intentions based on historical selections, preparing the groundwork for accurate predictions without requiring extensive search index processing during actual queries
Solution Approach 2:
The system introduces user selection patterns as an intermediary between the query and search index data. Instead of directly relying on search index data for entity prediction, the system uses user behavior patterns as a mediating factor that guides which search index data to retrieve and how to interpret it, improving prediction accuracy while reducing unnecessary resource consumption
2Productivity
If the system requests and processes search index data from search servers, then query results can be generated, but it requires relatively large amounts of time and system resources
Solution Approach 1:
The system applies partial action by selectively requesting only the necessary search index data based on user selection patterns rather than processing all available index data. It uses user behavior predictions to determine which entities are most likely intended, thereby requesting and processing only a subset of search index data that is relevant to the predicted entity intentions
Solution Approach 2:
The system performs preliminary analysis of user selection patterns before executing queries, pre-determining which entities are most likely intended based on historical data. This preliminary action allows the system to prepare optimized query execution plans in advance, reducing the time and resources needed during actual query processing
Data Source
AI summary
Predicting entities for database query results are described. A system receives a query that includes a query term. The system outputs a query result that identifies at least one record that includes the query term. The system identifies a selection of a record that is identified by the query result and that includes the query term. The system stores information that associates the query term with an entity that corresponds to the selected record. The system scales the information that associates the query term with the entity. The system receives another query that includes the query term. The system outputs another query result in response to the other query, the other query result being based on the scaled information that associates the query term with the entity.