Universal Concept Phrase Graph for E-book Similarity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying relevant additional information, such as video or audio content, for e-books is difficult due to the complexity of matching user context with available resources.
Innovation Solution
A system that extracts concept phrases from an e-book being read, uses a universal concept phrase graph to determine core concepts, and generates queries to search engines to provide indicators of similar documents to the user, enhancing the user experience by presenting relevant information without user input.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If concept phrases are extracted and matched with a universal concept phrase graph to identify similar documents, then the relevance of additional information is improved, but the computational complexity and processing time increase
Solution Approach 1:
The universal concept phrase graph is pre-computed and stored before the actual document matching process. Concept phrases from the e-book are extracted and matched against this pre-built graph structure, allowing efficient retrieval of related documents without performing complex graph computations in real-time.
Solution Approach 2:
The universal concept phrase graph serves as an intermediary data structure that bridges the e-book content and the database of available documents. Instead of directly comparing e-book text with all available documents, the system uses concept phrases as intermediaries to facilitate efficient and accurate matching.
2Measurement precision
If concept phrases are extracted and matched with a universal concept phrase graph to identify similar documents, then the relevance of additional information is improved, but the processing time increases
Solution Approach 1:
The universal concept phrase graph is pre-computed and stored before the actual document matching process. Concept phrases from the e-book are extracted and matched against this pre-built graph structure, allowing efficient retrieval of related documents without performing complex graph computations in real-time.
Solution Approach 2:
Only the necessary concept phrases are extracted from the e-book content and used for matching, rather than processing the entire document text. This extraction approach reduces the amount of data that needs to be processed while maintaining matching accuracy.
3Ease of operation
If the system automatically presents additional information without user input, then the ease of operation is improved, but the device complexity increases
Solution Approach 1:
The system automatically extracts concept phrases from the e-book, queries the universal concept phrase graph, retrieves related documents, and presents them to the user without requiring any manual input. The system serves itself by autonomously performing all steps of the information retrieval process.
Solution Approach 2:
The universal concept phrase graph serves multiple functions: it stores knowledge about concept relationships, enables efficient querying for related documents, and supports various types of additional information retrieval. This multi-functional data structure reduces the need for separate systems for each function.
Data Source
AI summary
While a document, such as an e-book, is read by a user on a computing device such as an e-reader, concept phrases are extracted from the document. The extracted concept phrases may be words or phrases that match known concept phrases such as headings. Based on a universal concept phrase graph that includes nodes for each known concept phrase, core concept phrases are determined for the document. These core concept phrases are associated with nodes of the universal concept phrase graph that are located within a predetermined distance of nodes that represent the concept phrases extracted from the document. Each core concept phrase is combined with one or more of the concept phrases to generate multiple queries. These queries are submitted to search engines, and indicators of documents from the corresponding search results are presented to the user with the original document that is being read.