Query Suggestion Filter Using Ban Markers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing search engines face challenges in generating relevant search query completion suggestions while filtering out potentially offensive or inappropriate content, which can lead to user exposure to undesirable information.
Innovation Solution
A method that parses search queries to determine if they match potentially banned words associated with ban or unban markers, generating suggestions only if they match unban markers and excluding those that match ban markers, using a server-based system with a suggestion module and database to filter and suggest query completions based on past search data and user preferences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the search engine presents a large set of query suggestions to assist users, then the user experience is improved and search efficiency is enhanced, but the risk of exposing users to offensive or inappropriate content increases
Solution Approach 1:
The patent applies preliminary action by pre-classifying query suggestions into safe and unsafe categories before presenting them to users. The system proactively identifies and filters inappropriate content using classification models and safety checks, ensuring that only approved suggestions are displayed. This prevents harmful content from reaching users while maintaining efficient search assistance.
Solution Approach 2:
The patent introduces an intermediary classification system that acts as a mediator between the query suggestion generation and user presentation. This intermediary layer classifies suggestions based on safety criteria and selectively passes only appropriate suggestions to users, effectively filtering out offensive or inappropriate content while preserving useful search assistance.
2Reliability
If the search engine filters out potentially offensive content from suggestions, then user safety is improved, but the number of available suggestions decreases
Solution Approach 1:
The patent applies local quality by implementing differential filtering based on the specific characteristics of each query suggestion. Instead of uniformly blocking all suggestions containing certain keywords, the system classifies each suggestion individually, allowing contextually appropriate suggestions to pass through while blocking only those that are genuinely inappropriate. This preserves the quantity of useful suggestions while ensuring safety.
Solution Approach 2:
The patent changes the parameter of suggestion presentation by introducing classification-based filtering. The system transforms the binary choice of showing or hiding suggestions into a multi-level classification system that evaluates safety parameters, relevance, and user context. This allows the system to maintain a high number of safe, relevant suggestions while filtering out only the inappropriate ones.
3Manufacturing precision
If the search engine processes and classifies each query suggestion, then the quality and safety of suggestions is improved, but the processing time and computational resources increase
Solution Approach 1:
The patent applies preliminary action by pre-computing and caching classification results for common query patterns and suggestions. The system performs initial classification during off-peak times or uses historical data to pre-approve frequently used suggestions, reducing the need for real-time processing. This maintains high suggestion quality while minimizing processing delays during user searches.
Solution Approach 2:
The patent applies partial action by implementing a two-stage filtering process: a fast, lightweight filter that quickly eliminates obviously inappropriate suggestions, followed by more thorough classification only for suggestions that pass the initial filter. This reduces the overall processing time by avoiding exhaustive analysis of all suggestions while still maintaining high quality control.
Data Source
AI summary
There is disclosed a method and a system for generating a search query completion suggestion. The method comprises receiving at least a portion of a search query and determining a first query component therein. A suggested second query component related to the first query component is generated, the search query completion suggestion containing the first query component and the suggested second query component. A list of potentially banned words is accessed to determine if the first query component matches any of the potentially banned words maintained therein. It is then determined if the potentially banned word is associated with a ban marker or an unban marker. A list of ban or unban markers respectively is accessed to determine if the suggested second query component matches any of the ban or unban markers maintained therein, the search query completion suggestion being generated or not generated accordingly.