Document Summarization Graphs Using Semantic Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for summarizing trouble reports with natural language processing present users with numerous linguistic representations and semantic relationships, making it difficult to understand the information at a glance.
Innovation Solution
A document summarization apparatus that performs natural language processing to extract linguistic representations and semantic relationships, classifies them into clusters based on semantic similarity, determines relationships between clusters, and generates a graph to concisely summarize the information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If all linguistic representations and semantic relationships are extracted and presented to the user, then the completeness of information is improved, but the understandability and ease of operation deteriorates
Solution Approach 1:
The patent segments the extracted linguistic representations into multiple clusters based on semantic similarity. Each cluster groups related concepts together, allowing the system to present organized, manageable groups of information rather than overwhelming the user with all individual representations. This segmentation maintains information completeness while improving understandability through structured presentation.
Solution Approach 2:
The patent merges similar linguistic representations into clustered groups. By combining semantically related representations into single clusters, the system reduces the total number of items presented to the user while preserving the underlying semantic relationships. This merging approach directly addresses the contradiction by maintaining information completeness through cluster organization while significantly improving ease of operation through reduced cognitive load.
2Measurement precision
If natural language processing extracts all linguistic representations from the trouble report, then the accuracy of information extraction is improved, but the device complexity and information overload increases
Solution Approach 1:
The system segments the complex task of processing all linguistic representations by organizing them into semantic clusters. This segmentation allows the NLP extraction to maintain high accuracy by capturing all relevant representations, while the subsequent clustering process manages system complexity by structuring the output in an organized, hierarchical manner that is easier to process and present.
3Loss of information
If numerous linguistic representations are presented to the user, then the completeness of the summary is improved, but the time required to understand the information increases
Solution Approach 1:
The patent segments linguistic representations into semantic clusters, allowing users to quickly grasp the organizational structure and navigate to relevant information. This segmentation maintains the completeness of the summary by preserving all extracted representations within their respective clusters, while significantly reducing understanding time through the intuitive clustered organization that presents information in manageable groups rather than exhaustive lists.
Solution Approach 2:
The patent merges semantically related linguistic representations into clustered groups, reducing the visual and cognitive burden on users. This merging maintains summary completeness by preserving all original representations within their clusters while reducing understanding time through consolidated, organized presentation that allows users to quickly comprehend relationships between concepts without being overwhelmed by individual items.
Data Source
AI summary
According to one embodiment, a document summarization apparatus includes a processor. The processor performs natural language processing on text included in a document to extract a plurality of linguistic representations and a first semantic relationship between the linguistic representations from the text. The processor classifies the linguistic representations into a plurality of clusters by semantic similarity. The processor determines a second semantic relationship between the clusters based on the first semantic relationship. The processor generates a graph representing the clusters and the second semantic relationship.