ML Protocol Selection for System State Data Collection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for collecting system state information in information processing systems often fail to gather all necessary attributes when using multiple protocols simultaneously, leading to incomplete data and unnecessary delays in troubleshooting, as they halt collection once one protocol succeeds, missing attributes that other protocols can provide.

Innovation Solution

A machine learning-based methodology that uses fuzzy decision trees to predict and rank protocols for collecting system state information, ensuring that relevant attributes are collected by automatically determining the most appropriate protocol based on historical data, alerts, and technical support tickets, and providing fallback protocols for incomplete collections.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If multiple collection protocols are used simultaneously to collect system state information, then the completeness of collected attributes is improved, but the complexity of managing and coordinating multiple protocols increases

Engineering Contradiction:

Improvecompleteness of collected attributesVSAvoidcomplexity of managing multiple protocols

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The system automatically selects and coordinates collection protocols based on device type, alert severity, and historical data without requiring manual intervention. The machine learning model self-adjusts protocol selection to maximize attribute collection completeness while minimizing management complexity.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system dynamically changes protocol selection parameters based on real-time conditions such as alert severity levels, device types, and historical collection success rates. This allows the system to adapt protocol combinations to maximize information completeness while managing complexity through automated parameter adjustment.

Inventive Principle:

Principle #35Parameter changes

2Loss of information

If collection protocols continue executing after one protocol succeeds, then the completeness of collected attributes is improved, but the time required for data collection increases

Engineering Contradiction:

Improvecompleteness of collected attributesVSAvoidtime required for data collection

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of device types, alert severities, and historical collection data to predict which protocols are most likely to succeed and provide the most valuable attributes. This preliminary action allows the system to execute protocols in an optimized sequence, stopping early when sufficient attributes are collected while avoiding time-consuming protocols that are unlikely to provide additional value.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The collection process is dynamic rather than static - the system continuously monitors collection progress and adjusts protocol execution in real-time based on success rates and attribute completeness. This dynamic approach allows the system to extend collection time only when necessary to gather additional critical attributes while avoiding unnecessary delays when protocols are unlikely to provide additional value.

Inventive Principle:

Principle #15Dynamics

3Ease of operation

If manual selection of collection protocols is used, then the ease of operation is improved, but the productivity of system management decreases

Engineering Contradiction:

Improveease of protocol selectionVSAvoidproductivity of system management

Core Design Contradiction:

Ease of operationVSProductivity

Solution Approach 1:

The machine learning model automatically performs protocol selection based on device type, alert severity, and historical data, eliminating the need for manual intervention. This self-service approach maintains ease of operation for users while significantly improving system management productivity through automated, data-driven protocol selection.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system continuously learns from historical collection results, success rates, and attribute completeness feedback to improve its automated protocol selection over time. This feedback mechanism allows the system to become increasingly efficient at protocol selection, maintaining ease of operation while improving productivity through adaptive automation.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11687793B2Using machine learning to dynamically determine a protocol for collecting system state information from enterprise devices

Publication Date: 2023.06.27 EMC IP HLDG CO LLC

AI summary

A method includes receiving data collected from a plurality of managed devices in a plurality of data collections. The data collections are performed using a plurality of collection protocols. A trigger that generated each of given ones of the data collections is determined. The method further includes identifying a collection protocol of the plurality of collection protocols used for each of the given ones of the data collections, and determining one or more attributes of a plurality of attributes of the plurality of managed devices that have been collected using given ones of the collection protocols. A mapping is generated between the triggers, the collection protocols and the attributes using one or more machine learning algorithms. The generated mapping is used to predict one or more collection protocols of the plurality of collection protocols to use to collect data from one or more of the managed devices.