Decision Making Analysis Engine for Identity Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current identity verification systems are limited by the quantity of credentials and facts collected, rather than the quality of the data, and struggle with accurately assessing the trustworthiness of identities and detecting fraudulent activities due to issues like diffuse, duplicative, diverse, decorated, delusional, deceptive, and dishonest information on the web, which existing AI techniques fail to adequately address.
Innovation Solution
The system employs the DUPES algorithm for advanced web searches, the CORRAL algorithm to identify causation rather than correlation in topic modeling, and the ONTO algorithm for nuanced sentiment analysis to enhance data classification and trustworthiness assessment, using machine learning and natural language processing to improve data quality and relevance in identity verification processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If comprehensive web searches are conducted to collect identity verification data, then the quantity of credentials and facts increases, but the quality of data deteriorates due to diffuse, duplicative, diverse, decorated, delusional, deceptive, and dishonest information
Solution Approach 1:
The patent introduces an intermediary layer of AI-based analysis between raw web data collection and identity verification decisions. This intermediary systematically processes collected information to distinguish reliable credentials from unreliable data, resolving the contradiction between collecting comprehensive data and maintaining data quality.
Solution Approach 2:
The patent replaces manual evaluation of collected credentials with automated AI-based analysis systems. This substitution enables efficient processing of large volumes of data while applying sophisticated judgment criteria to assess data quality, thereby maintaining reliability despite increased quantity of collected information.
2Productivity
If AI techniques are used to analyze collected data, then processing efficiency improves, but accuracy in detecting fraudulent activities deteriorates due to inability to differentiate correlation from causation
Solution Approach 1:
The patent changes the analytical parameters used by AI systems, moving from simple correlation-based metrics to causation-based analysis. By modifying how AI processes and interprets data relationships, the system maintains high processing efficiency while improving fraud detection accuracy through better differentiation of causal relationships.
3Adaptability or versatility
If sentiment analysis is performed to assess trustworthiness, then decision-making capability improves, but differentiation between neutral and positive/negative sentiments deteriorates
Solution Approach 1:
The patent applies local quality by implementing specialized sentiment analysis capabilities tailored to specific contexts and data types. Rather than using a single generic sentiment analysis approach, the system employs context-aware analysis that adapts to different situations, thereby improving both decision-making capability and sentiment differentiation accuracy.
Data Source
AI summary
The automated collection of online data is enhanced by generating and saving a context between a document and a related named entity, as well as a credibility level of the online source. The context, credibility level, and quality and quantity of collected data are used to enhance the use of the collected data in automated decision-making. Both the quality and the quantity may be continuously updated and honed through machine learning. Three new algorithms—DUPES, CORRAL, and ONTO—have been introduced to support the above, improving current state-of-the-art engineering practice by sharpening the strategy for named-entity searching, for ensuring that topic modeling produces relevant topic tags, and for handling sentiment which may be NEGATIVE, POSITIVE, and NEUTRAL (which includes MISSING and INCONCLUSIVE).