Local AI Module Aggregation for Latency and Security

Solution Overview

Problem

Conventional AI systems face performance and security challenges due to data latency and privacy risks associated with cloud-based processing, where sensitive data is transmitted over external networks, exposing it to unauthorized interception.

Innovation Solution

Implementing a local AI module aggregation system within a local computing environment, such as a LAN, where AI modules are managed by a server and executed on client devices, limiting data exposure and enhancing security by processing data locally, thus reducing latency and improving performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Power

If cloud-based AI systems are used for processing, then computational power and processing speed are improved, but data latency and security risks increase

Engineering Contradiction:

Improvecomputational powerVSAvoiddata latency

Core Design Contradiction:

PowerVSLoss of time

Solution Approach 1:

The system segments AI processing into modular AI modules that can be selectively deployed and executed on edge devices or local systems. This allows dividing the computational workload between cloud-based modules (for heavy lifting) and local modules (for low-latency operations), resolving the contradiction between accessing powerful cloud computing and avoiding data latency.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary AI module execution environment that acts as a mediator between the user's local system and the cloud-based AI services. This intermediary layer processes data locally when needed to reduce latency, while still having access to cloud-based computational resources through the modular architecture, thus balancing both requirements.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Power

If cloud-based AI systems are used for processing, then processing capabilities are improved, but data security and privacy risks worsen

Engineering Contradiction:

Improveprocessing capabilitiesVSAvoiddata security risks

Core Design Contradiction:

PowerVSObject-affected harmful factors

Solution Approach 1:

The system segments AI processing into modular AI modules that can be selectively deployed and executed on edge devices or local systems. This allows dividing the computational workload between cloud-based modules (for heavy lifting) and local modules (for low-latency operations), resolving the contradiction between accessing powerful cloud computing and avoiding data latency.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent implements local quality by allowing AI modules to be executed locally on user devices or within private networks rather than requiring all processing to occur in the cloud. This enables sensitive data to remain local while still benefiting from the processing capabilities provided by the modular AI architecture, thus reducing security risks associated with data transmission and storage in cloud environments.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS11836640B2Artificial intelligence modules for computation tasks

Publication Date: 2023.12.05 MOTOROLA MOBILITY LLC

AI summary

Techniques for artificial intelligence (AI) modules for computation tasks are described, and may be implemented to enable multiple AI modules to be aggregated to form an execution structure (e.g., an execution chain) for performing a computation task. Generally, the described techniques aggregate AI modules based on their respective functions to perform an overall computation task.