Fuzzy Expert System for IT Problem Prioritization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current problem management systems in IT infrastructures require expert knowledge to analyze and prioritize issues, which is not always available, leading to inadequate prioritization and increased costs due to dependency on skilled personnel and limitations in handling ambiguous or incomplete data.

Innovation Solution

A method utilizing a fuzzy expert system to analyze input parameters, generating a fuzzy result with a linguistic and crisp value to determine problem priority, allowing for objective and realistic quantification of issues without needing an expert operator, thereby reducing incorrect prioritizations and dependency on experts.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If expert knowledge is used to analyze and prioritize problems, then prioritization accuracy is improved, but dependency on skilled personnel increases and costs increase

Engineering Contradiction:

Improveprioritization accuracyVSAvoiddependency on expert personnel

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent creates a virtual expert system that copies and encodes expert knowledge into a computational model. The system uses historical problem data and expert judgments to train a machine learning algorithm, creating a digital replica of expert reasoning capabilities that can automatically prioritize problems without requiring actual experts to be present.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system enables self-service problem prioritization by automatically analyzing problem descriptions, extracting relevant features, and generating priority assignments without human intervention. The machine learning model independently processes incoming problems and assigns priorities based on learned patterns from historical data.

Inventive Principle:

Principle #25Self-service

2Ease of operation

If static matrices are used for problem analysis, then ease of operation is improved, but adaptability to new conditions deteriorates

Engineering Contradiction:

Improvesimplicity of analysis processVSAvoidadaptability to new problem conditions

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent transitions from static prioritization matrices to dynamic machine learning models that continuously adapt to new problem conditions. The system retrain s on new data, updates its internal representations, and adjusts its prioritization logic based on emerging patterns, enabling it to handle novel problem types and changing organizational priorities.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the parameters of the analysis process by moving from fixed categorical ratings to continuous feature vectors extracted by natural language processing. This allows for more nuanced differentiation between problems and enables the model to capture subtle variations in problem characteristics that static matrices cannot represent.

Inventive Principle:

Principle #35Parameter changes

3Ease of operation

If limited input variables are used, then ease of operation is improved, but measurement precision of problem definition deteriorates

Engineering Contradiction:

Improvesimplicity of data collectionVSAvoidproblem definition accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent segments the problem analysis into multiple independent feature extraction components. The natural language processing system identifies and extracts various features from problem descriptions including technical severity, business impact, affected systems, and temporal patterns. Each feature is processed independently and then combined to form a comprehensive priority assessment.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system employs a universal natural language processing pipeline that can extract multiple types of features from diverse problem descriptions using the same underlying technology. This multi-functional approach allows the system to handle different problem types, formats, and languages while maintaining consistent analysis quality.

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Ease of operation

If fixed selected values are used for input variables, then ease of operation is improved, but reliability of prioritization results deteriorates

Engineering Contradiction:

Improvesimplicity of data entryVSAvoidprioritization result accuracy

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The patent replaces the mechanical process of manual value selection with automated natural language processing and machine learning inference. Instead of requiring operators to manually select values from predefined options, the system automatically analyzes problem text, extracts relevant information, and determines priority based on learned patterns, eliminating the need for fixed value selection while improving reliability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10878324B2Problem analysis and priority determination based on fuzzy expert systems

Publication Date: 2020.12.29 ENT SERVICES DEV CORP LP

AI summary

A method for analysis of problems is described, comprising receiving values for a plurality of input parameters specifying a problem, analyzing the values of the plurality of input parameters with a fuzzy expert system thereby calculating a fuzzy result, including a value of a linguistic variable and a crisp value, and determining a priority of the problem, wherein the priority is determined based on the value of the linguistic variable and the crisp value of the fuzzy result. Furthermore, a corresponding problem analysis system is provided.