Geocoding Text Phrases Using Administrative Level and Population Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Ambiguities in geographic data within textual information make it challenging to accurately map text phrases to geographical locations, as words can represent multiple locations or entities, leading to incorrect geocoding.
Innovation Solution
A method that identifies entities in documents, assigns initial scores to candidate locations based on administrative level and relative population, adjusts scores using heuristics and context, and selects the highest-scoring location to resolve ambiguities, applying the identified label to all occurrences, thereby determining accurate geographical coordinates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If natural language flexibility is used to represent geographic locations, then text can be more versatile and adaptable, but geographic data becomes ambiguous and cannot be accurately geocoded
Solution Approach 1:
The patent introduces an intermediary disambiguation system that mediates between the flexible natural language representation and the precise geographic location. This system uses multiple heuristics including geographic context analysis, administrative level prioritization, and population-based scoring to resolve ambiguities and map text phrases to accurate geographic coordinates.
2Device complexity
If a single location name is used without additional context, then text is simpler and more concise, but multiple locations with the same name create ambiguity
Solution Approach 1:
The patent changes the parameters used to evaluate location candidates by assigning scores based on administrative level (prioritizing higher levels like countries over cities) and population size. This transforms the simple location name into a ranked list of candidates with differentiated probabilities, resolving ambiguity without requiring additional contextual text.
3Measurement precision
If heuristics and context analysis are applied to resolve ambiguities, then geocoding accuracy improves, but processing complexity and time increase
Solution Approach 1:
The patent segments the disambiguation process into independent heuristic modules that can be applied sequentially: geographic context analysis, administrative level evaluation, and population-based scoring. This segmentation allows the system to handle complexity systematically and can prioritize or skip certain heuristics based on the specific text input, balancing accuracy with processing efficiency.
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
A system and method for mapping text phrases to geographical locations is provided. Entities, each comprising one of a location, person, and place, are identified in one or more documents. Possible candidate locations associated with each entity are determined. An initial score is assigned to each location. The initial scores are adjusted and the candidate location with the highest adjusted score is selected for each entity. The selected candidate location is applied to all occurrences of the entity in the documents.