Geographical Information Scoring Using Positional Weights
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies fail to accurately extract core geographical information from documents, leading to inaccurate results in services that rely on geographical data, as they extract all geographical information without differentiation, misrepresenting the true core information.
Innovation Solution
A method and system that compute scores for geographical names based on frequency and positional weights, and aggregate scores for geographical regions, using a geographical information database to determine the core geographical information by identifying the highest scoring geographical region and name.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If all geographical information is extracted from a document without differentiation, then the quantity of extracted geographical information increases, but the accuracy of identifying core geographical information deteriorates
Solution Approach 1:
The patent applies local quality by assigning different weights to geographical names based on their positional characteristics within the document. Core geographical information (appearing in titles, first paragraphs, or standalone) receives higher weights, while non-core geographical information (appearing in body text only) receives lower weights. This differential weighting resolves the contradiction by maintaining high quantity of extraction while improving accuracy through position-based differentiation.
2Device complexity
If simple extraction methods are used, then the complexity of the system is reduced, but the reliability of geographical information identification deteriorates
Solution Approach 1:
The patent changes parameters by introducing multiple weighting factors (position weight, frequency weight, aggregation weight) to evaluate geographical names. Instead of simple extraction, the system computes composite scores by combining these parameters. This resolves the contradiction by systematically increasing reliability through multi-parameter evaluation while keeping the overall approach computationally manageable.
3Measurement precision
If positional weights and frequency analysis are applied, then the accuracy of core geographical information determination improves, but the computational complexity increases
Solution Approach 1:
The patent segments the evaluation process into distinct computational stages: (1) identifying geographical names, (2) assigning position weights, (3) counting frequencies, (4) computing individual scores, and (5) aggregating regional scores. This segmentation resolves the contradiction by breaking down complex computation into manageable steps, improving accuracy through systematic evaluation while controlling computational complexity through structured processing.
Data Source
AI summary
A method determines core geographical information in a document by computing a score for each geographical name found in the document. The computation of the score uses the appearance frequency of the respective geographical name and positional weights assigned to various types of appearance positions of the geographical name in the document. The system determines the core geographical information in the document based on the scores of the geographical names found in the document. The method may further compute aggregated scores of geographical regions related to the geographical names and determine the core geographical information using both the aggregated scores of geographical regions and the scores of individual geographical names to increase accuracy.