ML-Based Software License Allocation Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Organizations face challenges in determining the appropriate number of standalone and floating software licenses to maximize productivity while minimizing costs, due to difficulties in accurately assessing license usage, especially when users remain logged in without actively using the software.
Innovation Solution
A method using machine learning to cluster users based on their software usage patterns, generating persona clusters, and determining the optimal number of each license type, which involves processing key performance indicators and applying machine learning models to manage license allocation effectively.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If users remain logged in without active usage monitoring, then system simplicity is maintained, but license usage measurement precision deteriorates
Solution Approach 1:
The patent replaces manual login/logout tracking (mechanical system) with automated machine learning-based usage detection that analyzes actual software interaction patterns. This substitution enables precise measurement of genuine usage without requiring complex manual monitoring systems, as the ML model automatically distinguishes between logged-in but inactive users and actively using users through behavioral analysis.
2Ease of manufacture
If traditional usage-based license allocation is used, then implementation ease is maintained, but productivity optimization deteriorates
Solution Approach 1:
The patent transitions from static, rule-based license allocation (easy to implement but rigid) to dynamic, ML-driven allocation that continuously adapts to actual usage patterns. The system dynamically adjusts license recommendations based on real-time behavioral analysis, enabling optimal productivity outcomes while maintaining ease of implementation through automated decision-making algorithms.
Solution Approach 2:
The patent changes the fundamental parameters of license allocation from fixed time-based thresholds to multi-dimensional behavioral parameters analyzed by machine learning models. This includes analyzing usage intensity, task completion patterns, and collaboration behaviors, transforming license management from a simple time-tracking system to an intelligent optimization system.
3Device complexity
If standalone licenses are allocated based on login time alone, then measurement simplicity is maintained, but cost optimization deteriorates
Solution Approach 1:
The patent replaces simple login-time measurement (simple but inaccurate) with machine learning-based behavioral analysis that detects genuine usage patterns. This substitution identifies users who are logged in but not actively using the software, preventing unnecessary standalone license allocations and reducing overall licensing costs while maintaining measurement simplicity through automated analysis.
Data Source
AI summary
Techniques are provided for software license optimization using machine learning-based user clustering. One method comprises obtaining key performance indicators indicating individual usage by a plurality of users of a software product; applying at least one function to the key performance indicators to obtain a plurality of time dependent features; processing the time dependent features using a machine learning model to cluster the users into a plurality of persona clusters; and determining a number of each available license type for the software product for the plurality of users based on the persona clusters. The key performance indicators comprise, for example, user behavioral data with respect to usage of the software product and/or performance data with respect to usage of the software product. One or more policies can be determined for managing an allocation of the available license types for the software product to the plurality of users.