Link-Based Content Retrieval via Knowledge Graph
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional search engines require users to convert web page content into keywords and iteratively search for related content, which is time-consuming and inefficient.
Innovation Solution
The system uses link-based searches, where a server receives a hyperlink from a user and determines if it exists in a database. If it does, the server provides related content; if not, it analyzes the content to generate search parameters and provides search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users convert web page content into keywords and perform iterative searches, then search results can be obtained, but the process becomes time-consuming and inefficient
Solution Approach 1:
The system pre-processes web page content to extract entities, relationships, and concepts, storing them in a knowledge graph before search is needed. This preliminary structuring of information allows the system to immediately retrieve related content when a URL is provided, eliminating the need for users to iteratively convert content to keywords and perform multiple searches.
Solution Approach 2:
The patent introduces a URL-based search interface as an intermediary between the user and the search system. Instead of requiring users to directly convert content to keywords, the URL serves as a mediator that the system automatically processes to extract meaningful search parameters, thereby simplifying the user's task while maintaining search accuracy.
2Ease of operation
If users manually synthesize information and reduce it to keywords, then search queries can be formulated, but the process becomes complex and skill-dependent
Solution Approach 1:
The system performs the information synthesis and keyword extraction tasks automatically without requiring user intervention. When a user provides a URL, the system self-services by automatically accessing the web page, extracting relevant content, converting it to search parameters, and executing the search, thereby eliminating the need for users to manually synthesize information or possess specialized search skills.
Solution Approach 2:
The URL acts as an intermediary that the system automatically processes. Instead of requiring users to manually reduce content to keywords, the system uses the URL as a starting point and automatically performs the complex tasks of content access, analysis, and parameter extraction, thereby simplifying the user interface while handling the complexity internally.
3Adaptability or versatility
If conventional keyword-based search is used, then search functionality is provided, but the ability to find related content is limited
Solution Approach 1:
The patent transitions from traditional keyword-based search to URL-based search, adding a new dimension to the search interface. This dimensional change allows the system to leverage the structured information inherently present in URLs and their corresponding web pages, enabling more effective discovery of related content through entity extraction, relationship analysis, and concept identification that goes beyond simple keyword matching.
Solution Approach 2:
The system pre-processes web pages to extract entities, relationships, and concepts, building a knowledge graph that captures the semantic structure of content. This preliminary action enables the system to understand and retrieve related content more effectively by leveraging pre-extracted semantic information rather than relying solely on keyword matching, thereby improving adaptability and reducing information loss.
Data Source
AI summary
Described herein are techniques and systems for retrieval of content using link-based searches. Embodiments herein include receiving, by a server, a request including a hyperlink directed to a source content. The server may determine whether a database associated with the server comprises the hyperlink. The database stores information of multiple entities each corresponding to one or more hyperlinks. In response to a determination that the database includes the hyperlink, the server may identify an entity corresponding to the hyperlink and provide information of the entity to the computing device. In some embodiments, in response to a determination that the database does not include the hyperlink, the server may identify related web content and return results to user.