Personal Information Detection in Free Text via NLP
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated text analytics tools lack effective methods for detecting personal information in digital text documents, particularly in identifying and quantifying personal data that may violate regulations like GDPR, which is crucial for compliance and data protection.
Innovation Solution
A method and system utilizing named-entity recognition (NER) algorithms, parts-of-speech tagging, and dependency parsing to automatically detect named entities and their relations in digital text, estimating the presence of personal information, and calculating a privacy score, while also inferring full names from partial mentions using knowledge graphs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional data classification techniques are used to scan databases, then vulnerability scanning and risk assessment can be performed, but personal information in free text documents cannot be effectively detected
Solution Approach 1:
The patent replaces traditional mechanical database scanning methods with natural language processing techniques including named-entity recognition, parts-of-speech tagging, and dependency parsing algorithms to detect personal information in free text documents, enabling effective detection where traditional methods fail
Solution Approach 2:
The patent changes the detection parameters from database-specific field scanning to linguistic feature analysis by applying NLP algorithms that identify personal entities, relationships, and privacy indicators based on text structure, syntax, and semantic dependencies
2Measurement precision
If multiple NLP algorithms are applied to detect named entities and relations, then personal information detection accuracy is improved, but system complexity increases
Solution Approach 1:
The patent segments the personal information detection process into distinct modular stages: named-entity recognition for identifying personal entities, parts-of-speech tagging for grammatical analysis, dependency parsing for relationship detection, and privacy estimation for final assessment, allowing each component to be optimized independently
Solution Approach 2:
The patent creates a multi-functional NLP system where the same processing pipeline handles multiple detection tasks including entity identification, relationship extraction, pronoun resolution, and privacy scoring, reducing overall system complexity through unified architecture
3Measurement precision
If pronoun replacement with full names is performed, then personal information identification is enhanced, but processing time increases
Solution Approach 1:
The patent performs preliminary named-entity recognition and relationship detection before pronoun replacement, establishing entity references and contextual understanding in advance, so that pronoun resolution can quickly map to already-identified entities without re-processing the entire text
Data Source
AI summary
Automated detection of personal information in free text, which includes: automatically applying a named-entity recognition (NER) algorithm to a digital text document, to detect named entities appearing in the digital text document, wherein the named entities are selected from the group consisting of: at least one person-type entity, and at least one non-person-type entity; automatically detecting at least one relation between the named entities, by applying a parts-of-speech (POS) tagging algorithm and a dependency parsing algorithm to sentences of the digital text document which contain the detected named entities; automatically estimating whether the at least one relation between the named entities is indicative of personal information; and automatically issuing a notification of a result of the estimation.