Search Query Related Question Generation via Topic Sets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search systems do not effectively provide users with relevant questions related to their search queries, making it difficult for users to explore topics comprehensively and identify commonly used keywords.
Innovation Solution
A method that involves receiving a search query, determining topic sets for search results, selecting related questions from a question database, ranking them, and transmitting these questions to the user device, which includes generating a graph to identify equivalent questions and replacing lower-ranked questions with their best variants.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If search systems provide only traditional search results, then the system complexity remains low, but users cannot effectively explore topics comprehensively or identify commonly used keywords
Solution Approach 1:
The system pre-generates question sets from previously submitted search queries and stores them in a question database before users need them. When a user submits a search query, the system retrieves pre-generated questions related to the query topics rather than generating questions in real-time, thus enhancing topic exploration capability while avoiding real-time generation complexity
Solution Approach 2:
The patent introduces a question database as an intermediary component between the search engine and users. This database stores pre-generated questions derived from historical search queries and serves as a mediator that provides users with relevant questions without requiring the search system to generate questions on-the-fly, thus resolving the complexity issue
2Loss of information
If the system generates and displays multiple related questions for each search query, then user understanding of topics improves, but the processing time and computational resources increase
Solution Approach 1:
Questions are generated in advance from historical search query data and stored in a pre-built question database. When users submit search queries, the system performs quick retrieval of relevant pre-generated questions based on topic matching rather than generating new questions during the search process, thus improving topic understanding while minimizing processing time
Solution Approach 2:
The system generates a comprehensive question database that may contain more questions than any single user will need, and stores them all in advance. This excessive pre-generation approach ensures that when users search, they receive relevant questions immediately without waiting for real-time generation, trading off storage space for reduced processing time
3Reliability
If the system uses a comprehensive question database with many questions, then the quality of related questions improves, but the time to select and rank relevant questions increases
Solution Approach 1:
The system determines topic sets for each search result resource and uses these local topic identifiers to filter and select questions from the comprehensive database. Instead of processing all questions in the database for every search, the system only retrieves questions matching the specific topic sets of the current search results, thus maintaining high question quality while improving selection efficiency
Solution Approach 2:
Questions in the database are pre-tagged or associated with topic sets during the database construction phase. This preliminary organization allows for efficient filtering and retrieval during actual search operations, as the system can quickly identify relevant questions by matching topic sets without performing complex analysis on the entire question database each time
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying related questions for a search query is described. One of the methods includes receiving a search query from a user device; obtaining a plurality of search results for the search query provided by a search engine, wherein each of the search results identifies a respective search result resource; determining one or more respective topic sets for each search result resource, wherein the topic sets for the search result resource are selected from previously submitted search queries that have resulted in users selecting search results identifying the search result resource; selecting related questions from a question database using the topic sets; and transmitting data identifying the related questions to the user device as part of a response to the search query.