Autocomplete Query Recommendation Using Domain Properties
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search systems struggle to provide effective autocomplete recommendations for long tail queries that lack query logs, as they rely solely on user input and existing query logs, failing to guide users with insufficient knowledge on suitable query words.
Innovation Solution
A method and system that utilize domain properties to generate recommendation query words by combining objects and properties within specific domains, providing autocomplete suggestions even when traditional query logs are absent, and emphasizing these recommendations for improved user recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If autocomplete recommendations are provided based solely on existing query logs, then recommendations for common queries are accurate, but recommendations for long tail queries without query logs cannot be provided
Solution Approach 1:
The patent introduces domain properties as an intermediary element between query logs and recommendation generation. When query logs are unavailable for long tail queries, the system uses domain properties (such as category information, object attributes, and semantic relationships) as a mediator to generate recommendations. This allows the system to extend coverage to queries without historical data while maintaining reasonable accuracy through domain knowledge guidance.
Solution Approach 2:
The system performs preliminary action by pre-establishing domain property databases that contain structured knowledge about various domains, objects, and their relationships before query processing. This pre-prepared domain knowledge structure enables the system to quickly generate recommendations for long tail queries by leveraging pre-defined domain properties rather than relying solely on historical query logs.
2Ease of operation
If the system emphasizes recommendation query words to improve user recognition, then user convenience is enhanced, but the complexity of the recommendation system increases
Solution Approach 1:
The patent applies local quality by differentiating the display treatment of different recommendation query words based on their source and relevance. Recommendation words derived from domain properties are emphasized with distinct visual styling (such as bold formatting or highlighting) compared to those from query logs. This localized differentiation enhances user recognition and guides attention to the most relevant recommendations without requiring complete system redesign.
Data Source
AI summary
A method of recommending a query word using a domain property includes receiving a search keyword from a terminal of a user, the search keyword being input by the user; generating at least one recommendation query word concerned with the search keyword by using a property of an object of a domain when the search keyword belongs to the object of the domain; and providing the recommendation query word to the terminal of the user as an autocomplete query word for the search keyword.