Trusted Predictive Analytics Middleware for Secure Cross-Platform Execution

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Predictive analytics services introduce vulnerabilities related to user privacy and intellectual property rights management, and current products are often installed as monolithic, vertical software stacks that require multiple installations across different devices, exacerbating issues due to the proliferation of various networked computing devices with different platform optimizations.

Innovation Solution

The implementation of trusted predictive analytics middleware that uses a model description language to provide a common interface and trusted execution environment, employing cryptographic techniques and digital rights management to protect sensitive data and intellectual property, while allowing a single instance of a predictive analytics service to be optimized across different devices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If predictive analytics services are provided as monolithic vertical software stacks, then the services can be deployed on specific platforms, but multiple installations are required across different devices increasing device complexity

Engineering Contradiction:

Improveplatform compatibilityVSAvoidnumber of software stacks

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements a universal predictive analytics service that can execute on multiple different devices and platforms through a common interface. The service is designed to be platform-agnostic, allowing the same core functionality to operate on diverse hardware architectures without requiring separate monolithic installations for each platform.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent segments the predictive analytics service into modular components that can be independently deployed and executed. By dividing the service into discrete functional units with standardized interfaces, the system can be distributed across multiple devices without requiring complete monolithic stacks on each platform.

Inventive Principle:

Principle #1Segmentation

2Productivity

If predictive analytics services access user data directly, then the services can process information efficiently, but user privacy and intellectual property rights are compromised

Engineering Contradiction:

Improvedata processing efficiencyVSAvoiddata security

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent introduces a trusted execution environment as an intermediary layer between the predictive analytics service and user data. This intermediary provides a secure sandbox that allows data processing to occur without direct access to raw user information, maintaining both processing efficiency and security through controlled data handling within the trusted environment.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent implements a nested architecture where the predictive analytics service executes within a trusted execution environment, which itself runs within the host operating system. This nested structure allows multiple layers of security and abstraction, with the service contained within a secure boundary that protects user data while enabling efficient processing.

Inventive Principle:

Principle #7Nested doll (Nesting)

3Productivity

If different predictive analytics models are optimized for specific platforms, then performance is maximized for each device, but the need for multiple platform-specific versions increases complexity

Engineering Contradiction:

Improvemodel performanceVSAvoidnumber of model versions

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent uses parameter changes to adapt the predictive analytics model to different platforms while maintaining a single core model structure. By adjusting execution parameters, data formats, and optimization settings based on the target platform's characteristics, the system achieves platform-specific performance optimization without requiring separate model versions.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20220147837A1Trusted predictive analytic execution middleware

Publication Date: 2022.05.12 INTEL CORP

AI summary

A disclosed example includes selecting, by a mobile computing device, a model description for a predictive analytics model in response to a user-level application request including input data from an application of the mobile computing device, the model description created with a predictive analytics model description language, the model description received from a predictive analytics provider; comparing, by the mobile computing device, first data associated with the user-level application request with second data indicative of digital rights permissions associated with the model description; and executing, by the mobile computing device, an executable associated with the model description without providing the processor circuitry access to the executable and without providing the input data to the predictive analytics provider.