Temporal Graph Document Retrieval System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for searching documents based on temporal similarity are limited, as they either ignore temporal information or focus solely on timestamps without considering the overall structure and concepts of documents.
Innovation Solution
A computer system and method that uses natural language processing to extract entities and temporal information from documents, creating a graph structure representing temporal semantics, and linking multiple documents into a knowledgebase for searching documents with similar temporal structures based on a similarity threshold.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If current search methods focus on keywords or timestamps, then search speed is improved, but temporal structure analysis accuracy deteriorates
Solution Approach 1:
The patent segments documents into temporal events with specific temporal relations, creating a structured representation that preserves temporal information while enabling efficient processing. Each event is extracted with its temporal attributes, allowing the system to analyze temporal structure without processing entire documents sequentially.
Solution Approach 2:
The patent introduces temporal graphs as an intermediary representation between raw documents and search queries. These graphs capture temporal structures and relations, serving as a mediator that enables both accurate temporal analysis and efficient similarity computation through graph matching algorithms.
2Measurement precision
If documents are analyzed in detail for temporal semantics, then search accuracy is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary extraction of temporal events and construction of temporal graphs during document indexing, before search queries are executed. This advance processing creates ready-to-use temporal representations that enable fast similarity searches without re-analyzing full document content during query processing.
Solution Approach 2:
The patent transforms documents from unstructured text into structured temporal graphs with specific parameters (events, temporal relations, time points). This parameter transformation enables efficient computational operations on temporal structures, reducing processing time for similarity comparisons while maintaining high accuracy.
3Reliability
If temporal information is extracted and structured, then temporal similarity retrieval is improved, but system complexity increases
Solution Approach 1:
The patent creates a universal temporal graph representation that can handle various temporal queries and similarity retrieval tasks through a single unified framework. This multi-functional approach reduces the need for separate processing systems for different temporal analysis tasks, managing complexity while maintaining retrieval reliability.
Data Source
AI summary
Entities and temporal information associated with the entities can be extracted from the documents using natural language processing. A graph structure can be created representing the document's temporal semantics, nodes of the graph structure including the entities and edges of the graph structure representing temporal relationships between the nodes. The graph structure can be linked with the document. Multiple documents can be received and a knowledgebase can be created including multiple graph structures representing the multiple documents according to the multiple documents' temporal semantics. An input document for query can be received and transformed into a graph structure for query, the graph structure for query representing the input document's temporal semantics. The knowledgebase can be searched for a matching document having a graph structure similar to the graph structure for query based on a similarity threshold. The matching document can be output.