Online Map Edit Moderation With Reliability-Based Correctness Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge of determining the accuracy of user-provided information on online platforms, particularly in online maps, is exacerbated by malicious users intentionally providing incorrect data, leading to unreliable information that can mislead others and is difficult to update efficiently.
Innovation Solution
A system and method that uses a consensus engine, accuracy engine, and reliability engine to determine a correctness score for proposed map feature attributes, automating the moderation of edits based on user reliability and value probability, thereby automatically accepting or rejecting submitted information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If expert reviewers manually assess user-provided information, then information accuracy is improved, but time consumption and labor costs increase significantly
Solution Approach 1:
The system performs preliminary automated assessment of user-submitted information using multiple engines (spam detection, consensus, accuracy, reliability) before human review. This pre-filtering process identifies and flags potentially inaccurate information, allowing reviewers to focus only on cases that require human judgment, thereby reducing overall review time while maintaining accuracy standards
Solution Approach 2:
The patent introduces automated assessment engines as intermediary components between users and expert reviewers. These engines act as mediators that preliminarily evaluate information quality, generate confidence scores, and prioritize reviews, thus reducing the time burden on human reviewers while preserving the reliability benefits of expert assessment
2Reliability
If manual review processes are used to verify information, then information reliability is improved, but productivity decreases due to labor-intensive processes
Solution Approach 1:
The system performs preliminary automated verification using consensus engines that compare user-submitted information against existing data, reliability engines that assess user trustworthiness, and accuracy engines that evaluate historical precision. This preliminary filtering automatically validates reliable information, allowing only uncertain cases to proceed to manual review, thereby maintaining reliability while significantly improving productivity
Solution Approach 2:
The patent enables information to undergo self-verification through automated engines that assess consistency, user reliability, and historical accuracy. This self-service mechanism handles routine verification tasks autonomously, freeing human reviewers to focus on complex cases and thereby increasing overall information update speed without compromising reliability
3Productivity
If automated systems are used to moderate content, then processing speed is improved, but measurement precision of information accuracy deteriorates
Solution Approach 1:
The patent segments the accuracy assessment process into multiple specialized automated engines, each focusing on specific aspects: spam detection engines identify malicious content, consensus engines verify information against multiple sources, reliability engines assess user trustworthiness, and accuracy engines evaluate historical precision. This segmentation allows each engine to specialize in its domain, improving overall measurement precision while maintaining high processing speed through parallel operation
Solution Approach 2:
The system employs multi-functional automated engines that perform multiple assessment functions simultaneously. For example, the reliability engine both assesses user trustworthiness and predicts future information quality, while the consensus engine both verifies current information and learns from historical patterns. This multi-functionality increases measurement precision without requiring additional processing resources, thereby maintaining high productivity
Data Source
AI summary
A system and method for updating and correcting facts that receives proposed values for facts from users and determines a correctness score which is used to automatically accept or reject the proposed values.