Blockchain Supervised Learning via Smart Contracts and TEE

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current supervised learning-based data analytics on blockchain platforms require data extraction and processing on external intermediary platforms, which is inefficient, time-consuming, and counter to the decentralized spirit of blockchain, eliminating its security and cost advantages.

Innovation Solution

A system and method that enables supervised learning-based data analytics directly on the blockchain by using smart contracts to receive and execute analysis transactions, train algorithms, and generate insights without extracting data records from the blockchain, allowing for user-customized analysis and off-chain data storage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If data records are extracted from blockchain and processed on external intermediary platforms, then data analytics can be performed, but security and decentralization advantages of blockchain are eliminated

Engineering Contradiction:

Improvedata analytics capabilityVSAvoidsecurity and decentralization

Core Design Contradiction:

Ease of manufactureVSReliability

Solution Approach 1:

The patent introduces a trusted execution environment (TEE) as an intermediary layer between the blockchain and external analytics platforms. This TEE acts as a secure mediator that allows data processing to occur outside the blockchain while maintaining security through hardware-based isolation and cryptographic verification, thus enabling analytics without completely eliminating blockchain's security advantages

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system segments the data processing workflow into distinct components: data remains on-chain for security, selective data extraction occurs through controlled interfaces, processing happens in isolated TEE environments, and results are verified and returned to the blockchain. This segmentation allows each component to optimize for its specific function while maintaining overall system security

Inventive Principle:

Principle #1Segmentation

2Measurement precision

If all data records are fetched from blockchain blocks for training supervised learning algorithms, then comprehensive analysis is achieved, but time consumption and processing inefficiency increase

Engineering Contradiction:

Improveanalysis comprehensivenessVSAvoiddata extraction and processing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

Instead of extracting and processing all data records from the blockchain, the system applies partial action by selectively extracting only the subset of data records that are relevant to the specific analytics task or model training requirements. This reduces the volume of data transferred and processed externally, significantly decreasing time consumption while maintaining sufficient analysis comprehensiveness for the intended purpose

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system performs preliminary actions by pre-processing and filtering data on-chain before extraction, organizing data into accessible formats and identifying relevant records in advance. This preliminary preparation reduces the complexity and time required for external processing, as the data is already structured and ready for targeted analysis

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If data records are stored and processed on traditional databases external to blockchain, then supervised learning can be implemented, but cost and intermediary dependency increase

Engineering Contradiction:

Improvesupervised learning implementationVSAvoidintermediary platform dependency

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system implements a universal smart contract-based framework that can accommodate multiple supervised learning algorithms and various data analytics tasks within a single blockchain-integrated platform. This multi-functional approach eliminates the need for separate intermediary systems for different algorithms, reducing overall system complexity and intermediary dependency while maintaining adaptability across different machine learning use cases

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11263484B2System and method for supervised learning-based prediction and classification on blockchain

Publication Date: 2022.03.01 INNOPLEXUS AG

AI summary

Disclosed herein is a system and method for performing on-demand supervised learning-based data analytics directly on blockchain without the need to extract data from the blockchain to an external intermediary platform. The system and method disclosed herein enable supervised learning-based analysis directly on the blockchain, for data records stored on the blockchain. Furthermore, the system and methods disclosed herein allows a training and validation of supervised learning-based algorithms using data records from the transaction blocks of the blockchain without the need of an intermediary platform external to the blockchain.