ML Model Prioritization Using Telemetry and Application Capabilities
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information handling systems face inefficiencies in executing machine learning model algorithms due to the lack of timely and relevant data for prioritization, leading to delayed execution and resource overconsumption.
Innovation Solution
A method and system for prioritizing machine learning model algorithms by gathering user-specific and use-specific information before execution, using an AI productivity tool module and subagent to select and prioritize ML model calls based on collected telemetry data and application capabilities, ensuring efficient resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If machine learning model algorithms are executed without prioritization on information handling systems, then all applications can access ML models, but execution latency increases and hardware resources are overconsumed
Solution Approach 1:
The system performs preliminary actions by gathering application capabilities and telemetry data before ML model execution requests are processed. The AI productivity tool subagent uses this pre-collected information to prioritize and specialize ML model calls, avoiding the need to collect data during execution and reducing overall latency.
Solution Approach 2:
An AI productivity tool subagent is introduced as an intermediary component between applications and ML model execution infrastructure. This subagent specializes and prioritizes ML model calls by analyzing application capabilities and telemetry data, enabling intelligent resource allocation without requiring changes to the underlying ML execution infrastructure.
2Productivity
If machine learning model algorithms are executed without prioritization, then system simplicity is maintained, but hardware resource consumption increases
Solution Approach 1:
The system implements feedback mechanisms by continuously collecting telemetry data from applications and using this information to dynamically prioritize and specialize ML model execution. The AI productivity tool subagent adjusts resource allocation based on real-time system state and application performance data, optimizing hardware resource utilization.
Solution Approach 2:
The system changes execution parameters by gathering application-specific information (capabilities, telemetry data) before ML model execution. These parameter changes enable the AI productivity tool subagent to make informed decisions about prioritization and specialization, matching resource allocation to actual application needs rather than using uniform allocation.
3Measurement precision
If application capabilities and telemetry data are gathered before ML execution, then prioritization accuracy improves, but system complexity increases
Solution Approach 1:
The AI productivity tool subagent serves multiple functions: it gathers application capabilities, collects telemetry data, prioritizes ML model calls, and specializes execution parameters. By consolidating these diverse functions into a single multi-functional component, the system achieves high prioritization accuracy without proportionally increasing overall system complexity.
Data Source
AI summary
A system and method of prioritizing invoking machine learning (ML) model algorithms during execution of a first AI productivity tool-enablable software applications on an information handling system includes a hardware processor executing code instructions to receive registerable capabilities from the first AI productivity tool-enablable software application, executing program code instructions to initiate a request for an ML model algorithm and to instantiate the ML model algorithm to receive input from the first AI productivity tool-enablable software application to execute a capability, and executing code instructions to determine priority of execution of the ML model algorithm with the first AI productivity tool-enablable software application relative to execution of a second ML model algorithm with a second AI productivity tool-enablable software application based on an ML model execution system policy and received telemetry data relating to execution of the ML model algorithm by the first AI productivity tool-enablable software application.