AI Document Analysis for Sensitive Data Access Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing computer systems are unable to effectively identify and control access to restricted information within documents, relying on inefficient keyword searches that consume significant memory and processing resources, limiting system throughput.
Innovation Solution
A document analysis system utilizing artificial intelligence and machine learning to analyze text, classify sentences, identify similarities, and tag outlier sentences, thereby improving the accuracy and efficiency of information access control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If keyword searches are used for controlling data access, then data access control can be implemented, but memory resources and processing resources are consumed significantly
Solution Approach 1:
The patent replaces the mechanical keyword search system with a machine learning-based semantic analysis system. Instead of using traditional keyword matching algorithms that require storing and searching through large keyword sets, the system uses trained machine learning models to understand document content and identify sensitive information through semantic analysis, thereby reducing memory and processing resource consumption
Solution Approach 2:
The patent changes the fundamental parameters of the search approach from exact keyword matching to semantic similarity scoring. By transforming the problem from discrete keyword matching to continuous semantic space comparison, the system can identify sensitive information without requiring extensive keyword databases, thus reducing memory resources while maintaining control reliability
2Reliability
If keyword searches are used for controlling data access, then data access control can be implemented, but processing resources are consumed significantly
Solution Approach 1:
The patent applies preliminary action by pre-training machine learning models on large datasets before deployment. The models are trained offline to learn semantic representations and sensitivity patterns, so that during actual document analysis, the pre-trained models can quickly classify content without requiring extensive real-time processing resources. This shifts the computational burden from runtime to training time
Solution Approach 2:
The patent substitutes the computationally intensive keyword search mechanism with a more efficient machine learning inference process. Once models are trained, they can perform semantic analysis with lower processing requirements compared to searching through large keyword sets for each document, thus reducing ongoing processing resource consumption
3Measurement precision
If a large set of keywords is used to describe a term or concept, then data access control accuracy can be improved, but memory resources are consumed significantly
Solution Approach 1:
The patent merges multiple keywords that describe the same term or concept into a single unified semantic representation. Instead of storing and managing separate keyword sets for each synonym or related term, the machine learning model learns to represent them as equivalent or related vectors in semantic space, consolidating memory requirements while maintaining the ability to accurately identify sensitive information through semantic similarity
4Reliability
If a large set of keywords is used to search documents, then data access control coverage can be improved, but processing resources are consumed significantly
Solution Approach 1:
The patent replaces the exhaustive keyword search mechanism with semantic similarity-based matching. Instead of checking each document against every keyword in the database, the system uses pre-trained models to compute semantic representations and compare them efficiently, achieving comprehensive coverage with reduced processing overhead
Solution Approach 2:
The patent changes the search parameter from exact keyword matching to semantic similarity thresholding. By transforming the discrete keyword match problem into a continuous similarity scoring problem, the system can efficiently determine document sensitivity without iterating through all keywords, thus reducing processing resources while maintaining coverage
Data Source
AI summary
A document analysis device that includes an artificial intelligence (AI) processing engine configured to receive a set of input sentences, to select a first sentence from the set of input sentences, and to compare the first sentence to previously classified sentences. The AI processing engine is further configured to compute similarity scores between the first sentence and the previously classified sentences, to identify a second sentence from the previously classified sentences with a similarity score greater than or equal to a similarity score threshold value, to identify a sentence type that is associated with the second sentence, and to associate the first sentence with the sentence type. The AI processing engine is further configured to add the first sentence to the set of training data for the machine learning model and to train the machine learning model using the set of training data.