Semantic Analysis System for Ranking Search Results by Document Discrepancy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a need for a computer-based semantic analysis system to effectively rank search results by identifying discrepancies between documents authored by individuals and those authored by others, where the content in the latter may differ significantly from the former.
Innovation Solution
A system comprising an input device, microprocessor, output device, and permanent memory that processes search queries by comparing textual content from first and second documents using indicator terms and weighting factors to determine a semantic ranking score, ranking links to first documents based on the score, and adjusting weighting factors and thresholds for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional search ranking methods are used, then search results can be returned quickly, but the accuracy of identifying content discrepancies between documents authored by the same person deteriorates
Solution Approach 1:
The patent segments the document comparison process into multiple independent components: extracting indicator terms from documents, calculating individual term weights, computing aggregate weights, and determining final discrepancy scores. This segmentation allows the complex discrepancy detection task to be broken down into manageable, modular operations that can be processed systematically.
Solution Approach 2:
The patent employs parameter changes by introducing multiple weighting factors (individual term weights, aggregate weights, and discrepancy scores) that can be adjusted and optimized. The system calculates weights based on term frequency, document frequency, and positional information, allowing dynamic parameter adjustment to improve detection accuracy without requiring complete system redesign.
2Measurement precision
If multiple indicator terms and weighting factors are used to improve discrepancy detection, then measurement precision improves, but computational complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing weights for indicator terms based on their frequency and importance in the document corpus. These pre-computed weights are then reused during discrepancy detection, avoiding redundant calculations and reducing the computational power needed during actual search operations.
Solution Approach 2:
The system uses partial action by focusing computational resources on the most significant indicator terms and weighting factors rather than processing all possible document features equally. The patent identifies and prioritizes key terms that contribute most to discrepancy detection, applying weighted analysis selectively to reduce overall computational burden while maintaining detection accuracy.
3Measurement precision
If the system processes and compares multiple documents with multiple indicator terms, then discrepancy detection accuracy improves, but processing time increases
Solution Approach 1:
The patent applies local quality by assigning different weights to different indicator terms based on their local importance and relevance to discrepancy detection. Rather than treating all terms equally, the system identifies high-weight terms that locally contribute most to detecting content discrepancies, allowing faster processing by focusing on critical local features rather than uniform global analysis.
Data Source
AI summary
A computer-implemented semantic analysis system for ranking search results has instructions including the steps: receive a query about a first document authored by a person; read in data identifying the first document; read in a second document about the person authored after the first document; identify indicator terms in the second document related to whether or not there is a significant discrepancy between the second document and the first document; read in weighting factors for the identified indicator terms; determine an aggregate weighting factor that decreases with an increasing number of indicator terms found; and calculate a score of how much of a discrepancy there is between the second document and the first document using the weighting factors. When multiple first documents are returned for multiple persons, present the links in order from high score to low score.