Change Request Risk Prediction Using Generated Documentation Notes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional risk assessment of software and hardware changes is inefficient and resource-intensive due to the large volume of change requests and lack of sufficient training data for cognitive systems, making it difficult to automate the process effectively.
Innovation Solution
A computer-implemented method using neural networks to predict the outcome of change requests, incorporating a risk assessment machine learning model and a generative language model trained on historical change requests, to enhance risk assessment operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional risk assessment methods are used, then manual evaluation can be performed, but the process becomes inefficient and resource-intensive due to large volume of change requests
Solution Approach 1:
The patent replaces manual mechanical risk assessment processes with an automated neural network system. The neural network model processes change requests automatically, substituting human evaluators with an AI system that can handle large volumes of data efficiently, thereby resolving the contradiction between manual evaluation capability and the increasing volume of change requests
Solution Approach 2:
The system uses historical change request data to train the neural network, enabling it to autonomously perform risk assessments without continuous human intervention. The model learns from past patterns and independently evaluates new change requests, reducing dependency on manual resources while maintaining assessment quality
2Extent of automation
If cognitive systems are used for risk assessment, then automation can be achieved, but insufficient training data makes effective automation difficult
Solution Approach 1:
The patent performs preliminary action by collecting and storing historical change request data before the neural network is deployed. This historical data serves as the training foundation, enabling the system to learn from past patterns and make effective automated assessments. The preliminary data collection and model training occur before actual automated risk assessment begins
Solution Approach 2:
The system incorporates feedback loops where the neural network's risk assessments can be reviewed and validated against actual outcomes. This feedback mechanism allows the model to learn from real-world results and continuously improve its accuracy, effectively compensating for any initial limitations in training data quality or quantity
Data Source
AI summary
A computer-implemented method includes inputting a first input and a second input into a risk assessment machine learning model, such that, in response, the risk assessment machine learning model generates, as an output, a risk-based prediction associated with a change request (CR). The first input includes the CR, and the CR relates to a requested change for an information technology (IT) system. The second input includes a predicted set of documentation textual notes that would accompany implementation of the CR, the predicted set being generated as output from a generative language machine learning model in response to the CR being input into the generative language machine learning model.