Cognitive IT Change Request Evaluator Using ML
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional IT change approval processes are inefficient and time-consuming due to the extensive coordination required among multiple stakeholders, leading to significant delays and reduced productivity, ultimately resulting in low customer satisfaction.
Innovation Solution
A cognitive system utilizing machine learning and natural language processing to evaluate IT change requests, which includes a change request evaluator, a historical database, and a definitions database, to automate the approval process by identifying dependencies, business impacts, and contractual criteria, thereby reducing the need for extensive stakeholder involvement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple stakeholders manually review and approve change requests, then the approval process ensures thorough evaluation of change impact and compliance, but the process becomes time-consuming and inefficient
Solution Approach 1:
The patent introduces an automated change evaluation system that acts as an intermediary between change requesters and human approvers. This system uses machine learning models and natural language processing to pre-evaluate change requests, assess their impact, and identify required approvals, thereby filtering and preparing information before it reaches human stakeholders and reducing their manual evaluation time
Solution Approach 2:
The system performs preliminary evaluation of change requests automatically before they reach human approvers. It pre-identifies dependencies, assesses business impact, determines compliance requirements, and prepares approval recommendations in advance, so that human stakeholders only need to review pre-processed information rather than conducting full evaluations from scratch
2Reliability
If extensive coordination among multiple approvers is required, then comprehensive stakeholder input is obtained, but the coordination complexity and effort increase significantly
Solution Approach 1:
The automated evaluation system serves multiple functions simultaneously: it identifies all required approvers based on change type and impact, assesses business impact across different departments, checks compliance with multiple policies, and generates coordination schedules. This multi-functional approach consolidates what would otherwise require multiple separate manual processes into a single automated system
Solution Approach 2:
The system implements feedback loops where evaluation results from previous change requests are used to improve future evaluations. It learns from historical approval patterns, successively refines its impact assessment algorithms, and continuously improves its ability to identify required stakeholders, thereby reducing coordination complexity over time while maintaining comprehensive stakeholder coverage
3Reliability
If the change owner manually oversees the approval process including generating approver lists and evaluating change parameters, then comprehensive control is maintained, but the time and effort expenditure increases
Solution Approach 1:
The system enables self-service for change owners by automatically generating complete approver lists based on change characteristics, pre-evaluating business impact and compliance requirements, and providing recommended approval paths. Change owners can review and approve changes with minimal manual effort, as the system handles the administratively intensive tasks of identifying stakeholders and assessing change parameters
Data Source
AI summary
The present invention is a system and method for evaluating an IT change request system based on cognitive and machine learning technologies. The system includes a computing device having a change request evaluator based on a machine learning trained model and in digital communication with a server. A historical database stores change records and a definitions database stores a definition for words appearing in the change records. A change request is received at the change request evaluator, which finds a model change record by comparing the change request to the change records in the historical database and identifying definitions common to both the change request and the change record. A business mapping tool interfaces with the change request evaluator and determines a business impact of the model change record and associates the business impact with the change request. The change request evaluator approves or rejects the change request.