Context-Aware Query Selection for Web Pages
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing question answering systems do not effectively utilize web page context to improve the relevance of search query suggestions, relying solely on query detail without considering the context in which the query is submitted.
Innovation Solution
A method that retrieves and processes web page context data to identify relevant queries by correlating client queries with contextual information from the web page, including textual data and user history, to provide more accurate and context-aware query suggestions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If search query suggestions are generated based solely on query detail and frequency, then the system is simple to operate, but the relevance and quality of query suggestions deteriorates
Solution Approach 1:
The system segments the query suggestion generation process into multiple independent components: web page context extraction module, query processing module, and suggestion generation module. Each component handles specific tasks separately, allowing the system to incorporate context awareness without requiring complete redesign of the entire system architecture.
Solution Approach 2:
The patent introduces web page context data as an intermediary element that mediates between the user's query and the suggested queries. This context data acts as a bridge, enriching the query with additional semantic information from the web page without directly modifying the query structure itself.
2Measurement precision
If multiple queries are retrieved from database without context filtering, then the retrieval process is fast and simple, but the quality and relevance of returned queries deteriorates
Solution Approach 1:
The system performs preliminary action by pre-extracting and storing web page context data before query processing occurs. This allows the context information to be ready for immediate use when a query is received, avoiding the need for time-consuming context extraction during the query processing phase.
Solution Approach 2:
The patent applies local quality by filtering and selecting queries based on their specific correlation with the current web page context. Instead of treating all queries uniformly, the system identifies and prioritizes queries that are locally relevant to the specific web page being displayed, thereby improving relevance without processing all retrieved queries equally.
3Adaptability or versatility
If query suggestions are based only on frequent searches, then the system is easy to implement, but the adaptability to current web page context deteriorates
Solution Approach 1:
The system achieves universality by designing a multi-functional query processing system that can handle multiple types of input data (query text, web page context, user history) and generate appropriate suggestions accordingly. The same core system structure serves both traditional frequency-based suggestions and context-aware suggestions, eliminating the need for separate systems.
Solution Approach 2:
The patent adds another dimension to the query suggestion problem by incorporating web page context as an additional feature space. Instead of only considering query frequency and text, the system now operates in a multi-dimensional space that includes context information, allowing for more nuanced and adaptable query suggestions.
Data Source
AI summary
Context data is determined for a web page. The context data includes textual data that describes subject matter displayed on the web page. A client query is retrieved from a client-retrieved instance of the web page. An identifier associated with the web page capable of distinguishing the web page from other web pages is determined. In response to receiving the client query, a plurality of queries are retrieved from a database. Whether one or more of the retrieved queries correlate the determined web page context and the received client query is determined. A set of one or more queries from the plurality of queries is selected based on the selected set of queries each having been determined to correlate the web page context data and the client query. The selected set of the plurality of the queries is sent to the client-retrieved instance of the web page.