Project Information Access Using NLP for Accurate Expert Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing information retrieval systems in large organizations face challenges such as time-consuming content maintenance, insufficient granularity in employee profiles, inconsistency across departments, and reliance on manual skill descriptors, leading to inefficient communication and information retrieval.

Innovation Solution

A project information access system using an electronic computing device that automatically matches various formulations of information requests to relevant resources by employing natural language processing and machine learning algorithms, providing two-way communication and matching project information data with worker contact details.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If wikis and departmental websites are used for information retrieval, then information accessibility is improved, but time expense for content maintenance increases

Engineering Contradiction:
Improveinformation accessibilityVSAvoidcontent maintenance time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system automatically crawls and extracts information from multiple sources including wikis, departmental websites, and employee profiles without requiring manual content maintenance. The automated information aggregation and matching system serves itself by continuously updating the knowledge base without human intervention, thus improving information accessibility while eliminating maintenance time expense

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system pre-processes and structures information from various organizational sources in advance, creating a ready-to-query knowledge base. By performing information extraction, normalization, and indexing beforehand, the system eliminates the need for reactive content maintenance while ensuring information is immediately accessible when queries are submitted

Inventive Principle:
Principle #10Preliminary action

2Ease of manufacture

If employee profiles use general skill descriptors, then profile creation is simplified, but profile distinguishability decreases

Engineering Contradiction:
Improveprofile creation easeVSAvoidprofile distinguishability
Core Design Contradiction:
Ease of manufactureVSMeasurement precision

Solution Approach 1:

The system segments employee expertise into hierarchical categories: broad skill areas, specific technologies, and detailed project experiences. This segmentation allows profiles to be created with simple descriptors while the system automatically breaks down general skills into granular components for precise matching, thereby maintaining ease of profile creation while achieving high distinguishability

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system adds temporal and contextual dimensions to skill descriptors by tracking when employees applied specific skills and in what project contexts. This transforms static, one-dimensional skill tags into multi-dimensional expertise profiles that are both easy to create and highly distinguishable for matching purposes

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Adaptability or versatility

If departments maintain separate websites with different layouts and jargon, then departmental autonomy is preserved, but inter-departmental communication becomes inconsistent

Engineering Contradiction:
Improvedepartmental autonomyVSAvoidcommunication consistency
Core Design Contradiction:
Adaptability or versatilityVSStability of the object's composition

Solution Approach 1:

The system creates a universal communication layer that operates across all departmental websites simultaneously. The standardized query interface and unified matching algorithm work consistently across diverse departmental structures, preserving each department's autonomy while ensuring consistent information retrieval experiences throughout the organization

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system acts as an intermediary layer between users and diverse departmental websites. It translates various departmental jargons and layouts into a unified understanding through automated information extraction and normalization, thereby maintaining departmental independence while ensuring communication consistency across the entire organization

Inventive Principle:
Principle #24Intermediary (Mediator)

4Ease of operation

If search bars are used for information retrieval, then keyword-based searching is enabled, but retrieval accuracy decreases due to wording sensitivity

Engineering Contradiction:
Improvesearch operation simplicityVSAvoidretrieval accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system replaces the mechanical keyword-matching mechanism of traditional search bars with semantic understanding based on natural language processing and machine learning. This substitution maintains the simplicity of user input while dramatically improving retrieval accuracy by understanding the intent and context behind queries rather than merely matching keywords

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes the matching parameters from exact keyword correspondence to semantic similarity and contextual relevance. By transforming the matching criteria from rigid textual equality to flexible semantic equivalence, the system preserves ease of operation while achieving high retrieval accuracy even when query wording varies

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4703966A1A method for providing a project information access system by an electronic computing device, a computer program product, a non-transitory computer-readable storage medium, as well as an electronic computing device
Publication Date: 2026.03.04 SIEMENS AG
  • EP4703966A1 patent drawingFigure 1
  • EP4703966A1 patent drawingFigure 2
  • EP4703966A1 patent drawing

AI summary

The invention relates to a method for providing a project information access system (14) by an electronic computing device (10). The method comprises the steps of: providing at least one project information datum (18) by the electronic computing device (10), where each of the at least one project information datum (18) is associated with at least one worker contact detail (20); providing a communication platform (26) by the electronic computing device (10) for two-way communication with a user (28) of the project information access system (14); receiving a project information request (34) from the user (28) by the electronic computing device (10) via the communication platform (26); matching the project information request (34) by the electronic computing device (10) to at least one matching datum (38) of the at least one project information datum (18); and providing the at least one matching datum (38) and/or at least one matching worker contact detail (40) corresponding to the at least one matching datum (38) to the user (28) via the communication platform (26) by the electronic computing device (10), depending on the project information request (34).