Text Analysis Data Anonymization via Token Mapping

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

There is a security risk when sending data containing personal or sensitive information to cloud services for text analysis, as dictionaries used in these processes may also contain personal or sensitive data, potentially leading to leakage.

Innovation Solution

A method is implemented where a first character string in the analysis logic is replaced with a meaningless second character string using a mapping, ensuring that only the modified logic and target document are sent to the server for analysis, preventing the exposure of sensitive information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If data containing personal or sensitive information is sent to cloud services for text analysis, then text analysis can be performed using cloud computing resources, but security risk increases due to potential leakage of sensitive information

Engineering Contradiction:

Improvetext analysis capabilityVSAvoiddata security

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent applies preliminary action by performing data anonymization before sending data to cloud services. The system replaces personal identifiers (names, addresses, phone numbers) with anonymous tokens in advance, so that when text analysis is performed on cloud services, the sensitive information has already been protected, eliminating the security risk while maintaining analysis capability

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary mechanism - anonymous tokens - that mediate between the original sensitive data and the text analysis process. Instead of directly transmitting personal information to cloud services, the system uses these token intermediaries to represent sensitive data, allowing analysis to proceed while preventing direct exposure of sensitive information

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If dictionaries containing personal or sensitive data are used in text analysis, then analysis accuracy can be improved, but data leakage risk increases

Engineering Contradiction:

Improvetext analysis accuracyVSAvoiddata leakage risk

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent extracts and removes sensitive information from dictionaries before they are used in text analysis. The system identifies and extracts personal identifiers from dictionary data, replaces them with anonymous tokens, and uses these anonymized dictionaries for analysis. This extraction process eliminates the harmful factor (sensitive data) while preserving the functional value of the dictionaries for accurate text analysis

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS10133879B2Technique used in text analysis in a safe manner

Publication Date: 2018.11.20 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A first character string in a logic used for the text analysis with a second character string which is different form the first character string is replaced using a mapping between the first character string and the second character string. The first character string being a character or a combination of characters in a logic. A first character string is searched for in a target document for the text analysis and the first character string, if found, is replaced with the second character string, using the mapping. The logic is sent after the replacement to a server computer. The target document after the replacement is sent to the server computer. A text analysis result for the target document after the replacement is received form the server computer.