Business Device Selection Using NLP Requirement Graphs

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional device selection methods in business environments are manual, labor-intensive, prone to human error, and lack the ability to consistently align nuanced business needs with the most suitable devices, leading to suboptimal selection and increased costs.

Innovation Solution

A method and system utilizing advanced natural language processing and decision-making algorithms to automate device selection, incorporating semantic analysis, node correlation, and decision trees to match business requirements with historical device data, ensuring accurate and contextually relevant recommendations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If manual device selection methods are used, then device selection can be performed with simple processes, but the process becomes labor-intensive and time-consuming

Engineering Contradiction:

Improvesimplicity of selection processVSAvoidtime required for device selection

Core Design Contradiction:

Ease of manufactureVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical analysis with an automated computational system that uses natural language processing to extract requirements from stakeholder inputs and machine learning algorithms to match devices with requirements. This substitution eliminates manual labor while maintaining the selection process's accessibility.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service device selection by automatically processing stakeholder inputs and generating device recommendations without requiring manual intervention. The automated pipeline handles requirement extraction, matching, and recommendation generation, allowing users to obtain device selections through simple input provision.

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If manual device selection is performed, then flexibility in handling diverse needs is maintained, but human error increases and consistency decreases

Engineering Contradiction:

Improveflexibility in handling diverse needsVSAvoidconsistency of device selection

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system incorporates feedback mechanisms where stakeholder inputs are processed through NLP to extract requirements, which are then matched against device capabilities using trained models. The system learns from interactions and refines its matching accuracy, providing consistent results while adapting to diverse business needs through iterative improvement.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent transforms unstructured stakeholder inputs into structured requirement parameters through natural language processing. This parameter transformation enables consistent computational processing of diverse needs while maintaining the flexibility to handle various input formats and business requirements through standardized parameter mappings.

Inventive Principle:

Principle #35Parameter changes

3Productivity

If conventional automated solutions are used, then manual effort is reduced, but the system lacks intelligence in handling evolving business needs

Engineering Contradiction:

Improveefficiency of device selectionVSAvoidintelligence in handling diverse needs

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent replaces conventional rule-based automation with intelligent machine learning systems that can interpret nuanced business requirements. The NLP component understands natural language inputs, and the matching algorithms learn from historical data to provide intelligent recommendations that adapt to evolving business needs while maintaining high efficiency.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system implements dynamic adaptation through machine learning models that continuously learn from new data and evolving business requirements. The matching algorithms adjust their parameters and decision boundaries based on accumulated experience, enabling the system to handle diverse and changing needs while maintaining consistent performance.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentEP4617962A1Method and system for managing device selection within business environment

Publication Date: 2025.09.17 SIEMENS AG

Figure 1~2
Figure 3~4
Figure 5A~5B

AI summary

Disclosed is a method for managing device selection within a business environment. The method comprises acquiring business data for device-related requirements from one or more stakeholders. The method further comprises conducting a semantic analysis of the business data utilizing a natural language processing (NLP) technique, to generate a first graph representing the device-related requirements in terms of one or more of technical specifications, performance criteria, and device utilization. The method further comprises accessing a second graph based on historical data for multiple devices. The method further comprises executing a node correlation process for matching nodes of the first graph with nodes of the second graph. The method further comprises implementing a decision-making algorithm to select one or more devices based on the matched nodes. The method further comprises generating an output providing the selected one or more devices.