Confidential Data Skill Valuation via Encrypted ML

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Users are reluctant to share confidential data, such as salary information, due to privacy concerns, and existing technologies face challenges in ensuring the data remains confidential and is only used for specific purposes, making it difficult to provide accurate recommendations while maintaining user privacy.

Innovation Solution

A system that securely collects, tracks, and utilizes confidential data by using a confidential data frontend and backend architecture, ensuring encryption of user identification and data, and employing machine learning techniques to assign monetary values to skills based on submitted data, allowing for secure and accurate recommendations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If confidential data is collected and utilized for recommendations, then the accuracy and personalization of recommendations improve, but user privacy concerns increase and users become reluctant to share data

Engineering Contradiction:

Improverecommendation accuracyVSAvoiduser privacy concerns

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent introduces multiple intermediary components including encrypted data storage, anonymization processes, and controlled access mechanisms that act as mediators between data collection and recommendation generation. These intermediaries allow the system to utilize confidential data for accurate recommendations while protecting user privacy through encryption and access controls

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system transforms confidential data into different parameter representations through encryption and anonymization. By changing the parameter state of the data (from raw confidential information to encrypted/anonymized forms), the system enables recommendation accuracy while mitigating privacy concerns through parameter transformation

Inventive Principle:

Principle #35Parameter changes

2Reliability

If confidential data is encrypted and securely stored, then user trust and data security improve, but system complexity increases

Engineering Contradiction:

Improvedata securityVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the data storage and processing system into distinct modular components: encrypted data storage modules, anonymization processing modules, and recommendation generation modules. This segmentation allows each component to handle specific security functions independently, improving data security while managing system complexity through modular design

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces intermediary layers including encryption intermediaries and anonymization intermediaries that sit between the user data and the recommendation engine. These intermediaries simplify the overall system architecture by providing standardized security interfaces while maintaining complex security protocols underneath

Inventive Principle:

Principle #24Intermediary (Mediator)

3Loss of information

If confidential data is used for statistical analysis, then broad insights are provided, but the ability to provide personalized recommendations is limited

Engineering Contradiction:

Improvebroad statistical insightsVSAvoidpersonalized recommendation accuracy

Core Design Contradiction:

Loss of informationVSMeasurement precision

Solution Approach 1:

The patent adds another dimension to data utilization by processing confidential data in multiple dimensional forms: aggregated statistical dimensions for broad insights and individualized encrypted dimensions for personalized recommendations. This dimensional approach allows the system to simultaneously provide both broad statistical analysis and personalized recommendations without compromising either function

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS10535018B1Machine learning technique for recommendation of skills in a social networking service based on confidential data

Publication Date: 2020.01.14 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

In an example embodiment, each of a plurality of members of a social networking service is mapped to a weighted skill vector, each weighted skill vector including a list of skills for the member with an associated weight indicating a strength of the skill. Members of the social networking service who belong to an industry are aggregated to obtain a weighted matrix of members and skills along with compensation vectors indicating compensation for each of the members in the matrix. The weighted matrix of members and skills and corresponding compensation vectors are used to train a machine learning skill monetary value prediction model to output a predicted monetary value for a skill contained in a candidate vector fed to the machine learning skill monetary value prediction model. A recommendation is provided to a member of one or more skills to add based on output of the model.