Query Autocompletion via Prefix Removal and Quality Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Search engines often fail to provide query autocompletions for partially entered queries that do not produce any or very few results, leading to an incomplete user experience.
Innovation Solution
The system modifies the query by removing initial terms and submits the shortened query to an autocompletion module to determine if any query autocompletions are available, using a language model to verify the quality of suggested completions based on their frequency and relevance in user queries.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the search engine only provides autocompletions for queries with many results, then the quality of autocompletions is maintained, but the coverage of queries receiving autocompletions is limited
Solution Approach 1:
The system performs preliminary processing by removing prefixes from queries before submitting to the autocompletion module. This allows the system to proactively prepare and provide autocompletions for queries that initially appear to have few results, by transforming them into different query forms that may yield better autocompletion results.
Solution Approach 2:
The system changes the parameters of the query by removing different lengths of prefixes (e.g., first prefix, second prefix) to transform the original query into multiple alternative forms. This parameter transformation enables the autocompletion module to find relevant completions that would not be apparent from the original query form.
2Adaptability or versatility
If the system processes multiple prefix removals to find autocompletions, then query coverage is improved, but the processing complexity increases
Solution Approach 1:
The system segments the query processing into distinct stages: removing a first prefix to generate a first modified query, then removing a second prefix to generate a second modified query. This segmentation allows complex processing to be broken down into manageable steps, each handled by the same autocompletion module with different input parameters.
Solution Approach 2:
The same autocompletion module handles multiple types of queries (original queries, first modified queries, second modified queries) through a universal interface. This multi-functionality approach allows the system to increase query coverage without proportionally increasing system complexity, as the core module remains the same while handling diverse query forms.
3Ease of operation
If autocompletions are provided for queries with few results, then user experience is enhanced, but the precision of result matching may decrease
Solution Approach 1:
The system uses quality tests as feedback mechanisms to evaluate whether retrieved autocompletions are appropriate for the modified queries. The quality test analyzes whether the autocompletion results satisfy certain criteria, and only autocompletions passing this feedback evaluation are presented to the user, ensuring precision is maintained even when processing modified queries.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining query completions. In one aspect, a method includes receiving a query input in a search engine query input field in a user interface. The method also includes submitting the query input as a first query stem to an autocompletion module. The method also includes receiving a first response from the autocompletion module, the first response providing no first query autocompletions. The method also includes submitting a second query stem to the autocompletion module, the second query stem being the first query stem with a first prefix removed. The method also includes receiving a second response from the autocompletion module including one or more second autocompletions satisfying a second quality test. The method also includes providing second autocompletions for presentation on the user interface.