Text Relevance Determination Using Temporal Similarity Assignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods fail to effectively determine the relevance of a text, particularly in online publications and news, as they lack criteria to distinguish original from derived content and struggle with plagiarism detection due to the absence of citation or linking.
Innovation Solution
A method and computer system that compare a text with a portfolio of texts to calculate a relevance value based on similarity, considering the publication time of each text, allowing for ranking and identification of original content by assigning higher relevance to earlier published texts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If text relevance is determined by citation frequency, then original texts are identified, but derived texts without citations cannot be distinguished
Solution Approach 1:
The patent segments the text comparison process into individual comparisons between the text under consideration and each text in the portfolio, calculating separate similarity values for each comparison. This segmentation enables the system to handle multiple texts independently and aggregate their contributions to the overall relevance determination.
Solution Approach 2:
The patent introduces a temporal dimension by considering the publication time of texts. By assigning similarity values to texts based on their publication timestamps, the system creates a new dimension for evaluating relevance that goes beyond simple citation frequency, allowing distinction between original and derived content through temporal analysis.
2Measurement precision
If similarity comparison is performed with all texts in portfolio, then comprehensive relevance assessment is achieved, but computational complexity increases
Solution Approach 1:
The patent performs preliminary actions by pre-storing texts in a portfolio with their publication time information before the relevance determination process. This preparation allows the system to efficiently retrieve and compare texts without requiring complex real-time processing, reducing computational complexity while maintaining assessment completeness.
3Ease of operation
If similarity values are assigned to all texts in comparison, then symmetric treatment is applied, but temporal development and originality are not emphasized
Solution Approach 1:
The patent applies asymmetry by treating texts differently based on their publication time. Similarity values are assigned asymmetrically: texts published earlier receive higher weight or are identified as more relevant, while later texts are considered derived. This asymmetric treatment enables the system to distinguish original content from derivative content while maintaining consistent comparison procedures.
Data Source
AI summary
A method and a computer system for determining the relevance of a text. The method includes: determining the similarity of the text to texts in a portfolio, where the text is compared with each of the texts in the portfolio as part of an individual comparison while determining a similarity value which indicates the similarity between the two texts in each case; assigning the similarity value to one of the two texts in the respectively performed individual comparison which was published at an earlier time or was first captured by a capture system at an earlier time; calculating a relevance value from the similarity values which were determined in the individual comparisons and were assigned to the text, and storing the calculated relevance value and/or transmitting the calculated relevance value to a communication end system via a computer network.