Query Suggestion Engine Using Relevancy and Obviousness Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users may not be aware of entities related to their query searches, leading to incomplete results, as existing systems do not effectively suggest relevant but non-obvious entities, potentially missing important information.
Innovation Solution
A method that analyzes user queries and their results to calculate relevancy and informativity scores for related entities, ranking them and suggesting those that are relevant but not obvious to the user, using natural language processing and cognitive analysis to identify and rank related entities based on user profiles and search history.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If the system provides only explicit search results based on user queries, then the search results are precise to the user's intent, but the completeness of information is reduced because users may be unaware of related entities
Solution Approach 1:
The system performs preliminary analysis of query results to identify related entities before the user completes their search. By proactively analyzing the initial search results and pre-identifying relevant entities that the user might not know about, the system prepares suggestion lists in advance, thereby improving information completeness without waiting for user feedback or additional queries.
Solution Approach 2:
The system uses feedback from the initial query results to generate suggestions for related entities. By analyzing the documents and entities returned from the user's query, the system feeds back a curated list of related entities that are likely relevant but not obvious, helping users discover additional information they might have missed in their original search intent.
2Loss of information
If the system suggests many related entities to users, then the completeness of information improves, but the complexity of the system increases due to scoring and ranking mechanisms
Solution Approach 1:
The system changes parameters by introducing two distinct scoring dimensions: relevancy score (based on document frequency and entity relationships) and obviousness score (based on user profile matching). By transforming the entity selection problem into a multi-parameter scoring and filtering process, the system manages complexity through structured parameter evaluation rather than unstructured analysis.
Solution Approach 2:
The system segments the entity suggestion process into distinct stages: first calculating relevancy scores based on document analysis, then calculating obviousness scores based on user profiles, and finally filtering and ranking entities by combining these scores. This segmentation breaks down the complex task of entity suggestion into manageable, independent scoring components that can be processed separately and then integrated.
Data Source
AI summary
Embodiments for identifying entities relevant to queries are provided. At least one query is received from a user. The at least one query is associated with at least one entity. Results of the at least one query are analyzed to identify related entities. The related entities are analyzed based on a relevancy score and an information enhancement score for each of the related entities to generate a ranking of the related entities. At least one of the related entities is provided to the user based on the ranking of the related entities.