Geocoding Multi-Feature Addresses via Confidence Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing geocoding systems struggle with addresses that lack a hierarchical structure, as they often include multiple features with no discernible order, making it impractical to perform table lookups and recognize spatial relationships between objects.
Innovation Solution
A system and method that utilize an address parser to break down non-hierarchical addresses into features, a geocoder to determine geocodes for each feature, and a confidence analyzer to merge the highest confidence geocodes, allowing for the determination of a final geocode by intersecting these results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If table lookup is used for hierarchical addresses, then geocoding is simple and fast, but it cannot handle non-hierarchical addresses with multiple features
Solution Approach 1:
The address parsing process segments the input address string into multiple feature components (e.g., building, store, landmark) separated by delimiters. Each feature is then processed independently through the geocoder, allowing the system to handle non-hierarchical addresses while maintaining manageable complexity through modular processing.
Solution Approach 2:
The geocoding system is designed to handle both hierarchical addresses (using table lookup) and non-hierarchical addresses (using feature-based processing). The confidence analyzer universally processes both address types by collecting geocodes from multiple features and determining the highest confidence match, making the system adaptable to various address formats.
2Adaptability or versatility
If feature-based geocoding is used for multi_feature addresses, then adaptability to non-hierarchical addresses improves, but processing time increases
Solution Approach 1:
The address parser performs preliminary action by pre-splitting the input address into feature components before geocoding begins. This preparation step organizes the unstructured address data into a format ready for parallel processing, reducing the overall time required during the geocoding operation.
Solution Approach 2:
The system geocodes each feature independently and collects multiple geocode results, then uses the confidence analyzer to select the highest confidence match. This partial action approach processes each feature separately (allowing for optimization) while the excessive action of collecting multiple geocodes per feature provides redundancy that improves accuracy without significantly increasing total processing time.
3Measurement precision
If multiple geocodes are collected from feature components, then geocoding accuracy improves, but data processing complexity increases
Solution Approach 1:
The confidence analyzer implements feedback by evaluating the confidence levels of collected geocodes and using this information to select the highest confidence match. This feedback mechanism allows the system to automatically filter and select the most accurate geocode from multiple results, improving precision while managing processing complexity through intelligent selection rather than exhaustive analysis.
Data Source
AI summary
A system and method of parsing natural language descriptions of features to determine an approximate location. An embodiment includes splitting the natural language descriptions into components, geocoding each component, and returning the geocode with the highest confidence level. The geocode references a specific location, and this information may be determined by content from a variety of sources. The system may use an assortment of techniques for determining highest confidence level.