ML-Based Storage Version Analysis for Service Request Grouping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional storage system management approaches are labor-intensive and often inaccurate in identifying and addressing software version-related data access issues and other version-related challenges.
Innovation Solution
The implementation of machine learning techniques for reactive and proactive storage system-based software version analysis, which involves obtaining user service requests, calculating similarity measures, grouping requests based on software versions, and generating outputs for necessary actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional storage system management approaches are used to identify software version-related data access issues, then the process is simple to implement, but it is labor-intensive and inaccurate
Solution Approach 1:
The patent introduces an intermediary classification system that acts as a mediator between raw service request data and problem identification. This classification system processes and categorizes service requests based on software versions, storage systems, and problem types, thereby improving accuracy without requiring direct complex analysis of all raw data. The intermediary layer filters and structures information to make it more manageable and accurate for identification purposes.
Solution Approach 2:
The patent replaces manual, labor-intensive mechanical analysis with an automated classification and identification system. Instead of human operators manually reviewing service requests to identify software version issues, the system uses automated algorithms and classification rules to perform this task, significantly improving accuracy while reducing labor intensity. This substitution transforms a manual mechanical process into an automated intelligent process.
2Productivity
If conventional storage system management approaches are used, then the system structure is simple, but the process is labor-intensive and inefficient
Solution Approach 1:
The patent implements preliminary classification of service requests into categories based on software versions, storage systems, and problem types before detailed analysis. This preliminary action organizes data in advance, creating structured groups that can be quickly processed. By pre-categorizing service requests, the system reduces the time needed for subsequent analysis and resolution, significantly improving productivity without sacrificing accuracy.
Solution Approach 2:
The system enables self-service by automatically classifying and identifying issues without requiring continuous manual intervention. Once the classification framework is established, the system autonomously processes new service requests, categorizes them appropriately, and identifies potential software version-related problems. This self-service capability dramatically reduces both labor intensity and processing time, thereby improving productivity.
3Reliability
If conventional approaches are used to detect version-related issues, then the implementation is straightforward, but the detection is inconsistent and inaccurate
Solution Approach 1:
The patent segments the detection process into distinct classification stages: first classifying by software version, then by storage system type, and finally by problem category. This segmentation breaks down the complex detection task into manageable, consistent segments. Each segment applies specific classification rules that ensure consistency within that category. The segmented approach maintains reliability by ensuring each aspect of the issue is systematically evaluated according to predefined criteria.
Solution Approach 2:
The patent changes the parameters used for detection from vague, subjective criteria to specific, measurable parameters such as software version numbers, storage system models, and standardized problem categories. By transforming the detection parameters into quantifiable and standardized metrics, the system achieves consistent and reliable detection results. This parameter transformation allows for objective comparison and classification across different service requests, eliminating inconsistency while maintaining system manageability.
Data Source
AI summary
Methods, apparatus, and processor-readable storage media for reactive storage system-based software version analysis using machine learning techniques are provided herein. An example computer-implemented method includes obtaining user service requests, each comprising a description of problems and data pertaining to storage systems associated with the requests; calculating similarity measures for the user service requests by applying a machine learning algorithm to the user service requests; automatically grouping the user service requests into a set based on the similarity measures; automatically grouping, within the set, two or more of the user service requests into subsets based on a software version attributed to the storage systems associated with the two or more user service requests; generating an output pertaining to actions related to a software version update; and transmitting the output to at least one of the users corresponding to the user service requests in at least one of the subsets.