Place Data Accuracy Estimation From Crowdsourced Correction Patterns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Crowdsourced data for points of interest (POIs) often contains errors, leading to unreliable information and reduced user engagement, as correcting these errors through expert investigation is time-consuming and costly.
Innovation Solution
A depletion model is applied to crowdsourced field reports to predict the total number of errors in a region, generating an estimated level of accuracy for POI attributes, thereby improving data reliability and reducing resource waste.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If crowdsourced field reports are used to gather POI data, then data coverage and real-time updates are improved, but data accuracy and reliability deteriorate due to inherent errors in user-submitted content
Solution Approach 1:
The system implements feedback mechanisms by analyzing correction patterns from multiple users and using depletion models to identify persistent errors. The feedback loop continuously refines data accuracy by incorporating user corrections and predicting remaining errors based on correction rates, transforming raw crowdsourced data into reliable information.
Solution Approach 2:
The system enables self-service by allowing users to automatically correct errors in POI data through the field report feature. Users can identify and fix inaccuracies in place names, addresses, and other attributes without expert intervention, enabling the system to self-correct and improve data quality over time through community participation.
2Reliability
If expert investigators are deployed to verify and correct POI data errors, then data accuracy is improved, but time consumption and operational costs increase
Solution Approach 1:
The system creates a virtual model of data accuracy by applying depletion models to simulate and predict the total number of errors and their correction rates. This virtual modeling allows the system to estimate accuracy levels and prioritize verification efforts without requiring physical expert investigation of every potential error, significantly reducing time and resource requirements.
Solution Approach 2:
The system changes the parameter of verification from manual expert review to automated statistical analysis. By transforming the verification process into a computational task that analyzes correction patterns and predicts error rates, the system achieves accurate assessments without the time and resource costs of human investigation.
3Measurement precision
If comprehensive error verification is performed on all POI data, then measurement precision of data quality is improved, but device complexity and computational resources increase
Solution Approach 1:
The system applies partial verification by focusing computational resources on regions and attributes with the highest error rates. Rather than verifying all POI data uniformly, the depletion model identifies areas where verification would be most beneficial, performing comprehensive analysis only where needed to achieve acceptable overall accuracy with reduced computational complexity.
Data Source
AI summary
Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and a method for performing operations comprising: receiving a plurality of records associated with a first geographical area; identifying a plurality of corrections to a first attribute in the first geographical area in the plurality of records for a particular time period; based on identifying the plurality of corrections to the first attribute, computing a first metric representing a quantity of the plurality of corrections to the first attribute per effort during the particular time period; accumulating a first value representing a total number of errors across a plurality of time periods up to and including the particular time period based on the identified plurality of corrections; and generating a first model that predicts accuracy of the first attribute in the first geographical area based on the metric and the accumulated first value.