Cognitive Software Component Distribution via Deep Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Organizations face challenges in selecting and distributing software components that maximize productivity for all end users, as existing methods often result in software choices that are feasible for only a few users, leading to inefficiencies and unoptimized license usage.

Innovation Solution

A cognitive and deep learning-based method that generates cognitive usage keys from user interaction data, analyzing behavioral and sentiment metrics to determine which software components increase productivity and redistribute them accordingly, ensuring optimal software and license distribution across the enterprise.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If software components are distributed based on requests, registrations, and license availability, then license management is simplified, but productivity optimization for all end users is compromised

Engineering Contradiction:

Improvelicense management simplicityVSAvoidend user productivity

Core Design Contradiction:

Ease of manufactureVSProductivity

Solution Approach 1:

The system implements feedback loops by continuously collecting cognitive data from workstations, analyzing usage patterns, and redistributing software components based on measured productivity impact. This closed-loop approach allows the system to adapt to actual user needs while maintaining automated license management.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system changes the distribution parameters from static license availability to dynamic cognitive metrics including usage patterns, productivity impact, and user behavior analysis. This enables optimized software allocation that responds to actual organizational needs rather than following fixed licensing rules.

Inventive Principle:

Principle #35Parameter changes

2Adaptability or versatility

If multiple competitive software components are distributed to different users, then individual user needs are met, but overall license utilization efficiency decreases

Engineering Contradiction:

Improveuser-specific software matchingVSAvoidlicense utilization efficiency

Core Design Contradiction:

Adaptability or versatilityVSLoss of energy

Solution Approach 1:

The system makes licenses universal by allowing dynamic reallocation across different users and software components based on organizational productivity needs. Instead of binding licenses to specific users or applications, the system optimizes assignment to maximize overall utility while maintaining individual user effectiveness.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The software distribution system transitions from static license assignment to dynamic allocation based on real-time cognitive data analysis. The system continuously adapts software component distribution to changing user needs and productivity requirements, optimizing license utilization throughout the organization.

Inventive Principle:

Principle #15Dynamics

3Ease of operation

If software component distribution is based on cumulative understanding among groups, then social acceptance is improved, but objective productivity measurement is lost

Engineering Contradiction:

Improvesocial acceptanceVSAvoidproductivity measurement

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system replaces subjective social consensus mechanisms with objective cognitive data collection and analysis. Instead of relying on group discussions and cumulative understanding, the system uses automated workstation data capture, behavioral analysis, and productivity metric measurement to determine optimal software distribution.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11281558B2Cognitive and deep learning-based software component distribution

Publication Date: 2022.03.22 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Provided are techniques for cognitive and deep learning-based component distribution. In response to receiving cognitive data from a plurality of workstations, the cognitive data is stored as global cognitive data. A plurality of cognitive usage keys are generated using the global cognitive data, where each cognitive usage key of the plurality of cognitive usage keys is generated for each end user and each software component. Usage insights are generated using the plurality of cognitive usage keys, where each of the usage insights describes a software component and indicates whether the software component increases productivity of one or more end users. Licenses available for each software component described in the usage insights are determined. Based on the usage insights and the licenses available for the software components, the software components and the licenses for the software components are redistributed.