Name Segmentation for Denied Party Access Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for reviewing Denied Parties Lists (DPL) are inefficient, as they rely on single-source lists and lack effective methods to identify new suspect entities or variations in names that evade detection.
Innovation Solution
A computer-implemented method that decomposes names into parts and uses a neural network model to analyze these parts against a periodically updated database of entities, improving the identification of restricted entities by considering variations and characteristics of names on denial lists.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If exact match queries are used to check against denial lists, then the system is simple to operate, but the measurement precision of identifying restricted entities deteriorates because variations in names evade detection
Solution Approach 1:
The patent segments entity names into multiple components (e.g., prefix, root, suffix) and checks each segment independently against the denial list. This allows the system to identify restricted entities even when the complete name doesn't match exactly, as long as significant segments match. The name segmentation module divides the input name into meaningful parts that can be separately analyzed for matches.
Solution Approach 2:
The patent introduces a neural network model as an intermediary between the exact match query and the final determination. This intermediary processes the segmented name components and determines whether they represent a restricted entity, bridging the gap between simple exact matching and complex pattern recognition.
2Device complexity
If single-source denial lists are used, then the device complexity is reduced, but the reliability of access control deteriorates because entities on one list may not appear on multiple lists
Solution Approach 1:
The patent merges multiple denial lists from different sources into a unified checking system. The system maintains connections to multiple external denial list sources and integrates their data, allowing comprehensive checking against all lists simultaneously. This combination approach ensures that entities appearing on any single list are detected, significantly improving the reliability of access control.
3Measurement precision
If manual review of denial lists is performed, then the measurement precision of identifying suspect entities is improved, but the productivity of the system deteriorates due to heavy manual task requirements
Solution Approach 1:
The patent implements self-service through automated neural network analysis that performs the identification work without human intervention. The system automatically segments names, queries multiple denial lists, analyzes results through the neural network model, and determines access status. This automation maintains high precision in identifying suspect entities while dramatically improving productivity by eliminating manual review requirements.
Solution Approach 2:
The patent replaces the mechanical process of manual review with an electronic neural network-based analysis system. Instead of human operators manually examining denial lists, the system uses automated computational methods including name segmentation, database querying, and neural network classification to identify restricted entities, achieving both precision and efficiency.
4Measurement precision
If fuzzy queries are used instead of exact matches, then the measurement precision of identifying variations improves, but the loss of information increases due to unreliable query results
Solution Approach 1:
The patent applies segmentation to break down names into meaningful components before comparison, allowing the system to identify variations while maintaining reliability. By analyzing segments rather than treating names as unstructured strings, the system can distinguish between legitimate variations and false matches, reducing information loss.
Solution Approach 2:
The patent incorporates feedback mechanisms where the neural network model learns from query results and adjusts its analysis accordingly. The system uses the outcomes of segment comparisons to refine its determination process, providing feedback that improves the reliability of results while maintaining the ability to detect name variations.
Data Source
AI summary
A method and system determine network based access to restricted systems. The method includes receiving a request for a permission access status of a party seeking access to one of the restricted systems. A database of periodically updated lists of entities is accessed. A name of the party is extracted from the request. A determination is made whether the name does not match one of the entities. The name is decomposed into parts if the name not matching one of the entities. A determination is made whether any of the parts of the name matches one of the entities. A denial of access status is forwarded from the computer server to an external computing device if any of the parts of the name matches one of the entities.