Deep Neural Net Classification for Intelligence Pattern Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Intelligence and law enforcement agencies face challenges in sorting through vast amounts of data to identify linked activities indicative of criminal or enemy elements, such as clandestine meetings, using traditional methods.
Innovation Solution
A deep neural net classification system that analyzes previous queries and patterns stored in an intelligence data store, compares them with current queries and knowledge graphs, and classifies potential dispositions by identifying patterns indicative of illicit activities using a feature identifier and comparison engine.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional data sorting methods are used, then data processing is simple and straightforward, but the ability to identify linked activities indicative of criminal or enemy elements is insufficient
Solution Approach 1:
The patent replaces traditional mechanical data sorting methods with a deep neural network-based automated classification system. The comparison engine uses machine learning algorithms to automatically analyze patterns in intelligence data, substituting manual or rule-based processing with intelligent automated systems that can identify complex relationships and dispositions in data objects.
2Measurement precision
If deep neural net classification is implemented, then identification of suspicious activities is improved, but computational resources and processing time increase
Solution Approach 1:
The system performs preliminary actions by pre-processing intelligence data objects and storing them in the intelligence data store before actual analysis is needed. The comparison engine is pre-configured with deep neural network models and pattern recognition capabilities, so when queries are executed, the heavy computational lifting has already been prepared in advance, reducing real-time processing requirements.
3Measurement precision
If deep neural net classification is implemented, then identification of suspicious activities is improved, but computational resources and processing time increase
Solution Approach 1:
The comparison engine applies partial action by selectively analyzing only relevant features and patterns in data objects rather than processing entire datasets. The system identifies and focuses computational resources on specific dispositions and pattern types that are most indicative of criminal or enemy activities, avoiding unnecessary computational expenditure on irrelevant data.
Data Source
AI summary
The present invention provides a method, computer program product, and system of generating predicted reactions of a user. In some embodiments, the method, computer program product, and system include receiving an intelligence data store, receiving a current data object with a current query and at least one knowledge graph, identifying one or more patterns in the at least one knowledge graph, comparing using a deep neural net, the previous queries and associated one or more patterns with the current query and identified one or more patterns of the current data object, classifying the plurality data objects from the intelligence data store based on a closeness of the current query and identified one or more patterns with each of the previous queries and associated one or more patterns in the intelligence data store, and identifying, by the classification engine, potential dispositions based on the classification of the plurality of data objects.