Linking Textual Concepts to Physical Components via Visual Interface

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Users of complex devices like printers face difficulties in navigating searchable knowledge bases (SKBs) without expert knowledge, as they need to identify technical component names through text-based navigation, which is labor-intensive and prone to errors due to the complexity of devices and variability in terminology.

Innovation Solution

A system and method that links textual and physical concepts by extracting candidate phrases from the SKB, generating mapped concepts through a graphical user interface, and indexing the knowledge base to connect textual expressions with physical components, utilizing natural language processing for semi-automatic component and action mapping.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If text-based navigation of searchable knowledge base is used, then users can access troubleshooting information, but users need expert knowledge to identify technical component names, making the process labor-intensive and error-prone

Engineering Contradiction:

Improveease of navigationVSAvoidcomplexity of device terminology

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The patent introduces an image-based interface as an intermediary between the user and the textual knowledge base. Users point a camera at the physical device component, and the system automatically identifies and links it to the corresponding technical terminology and troubleshooting information, eliminating the need for users to manually navigate complex technical catalogs

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces manual text-based navigation with automated optical recognition and image processing. The camera captures an image of the physical component, and computer vision algorithms automatically identify the component and retrieve relevant information, substituting the mechanical process of manual searching with automated digital processing

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If manual mapping of graphical views to knowledge base terms is implemented, then links between visual and textual information are created, but the process is labor-intensive and prone to errors due to device complexity and terminology variability

Engineering Contradiction:

Improveaccuracy of concept linkingVSAvoidtime for mapping and maintenance

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs self-service by automatically extracting component information from images and autonomously creating and updating the mappings between visual components and knowledge base terms. The patent employs automated image processing and natural language generation to populate the knowledge base structure without requiring manual intervention for each component mapping

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent performs preliminary actions by pre-processing and structuring the knowledge base content in advance, organizing terminology and component relationships before they are needed. This preliminary organization enables faster and more accurate automatic matching when images are processed, reducing the time required for real-time lookups

Inventive Principle:

Principle #10Preliminary action

3Loss of information

If comprehensive searchable knowledge base is provided, then all device information is available, but the large size and variability of terminology make navigation difficult without expert knowledge

Engineering Contradiction:

Improvecompleteness of knowledge baseVSAvoidease of access to information

Core Design Contradiction:

Loss of informationVSEase of operation

Solution Approach 1:

The patent extracts only the specific component information relevant to the user's current need by using image recognition to identify the particular device component being viewed. Instead of requiring users to search through the entire comprehensive knowledge base, the system extracts and presents only the troubleshooting information related to the identified component

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS8935199B2Method and system for linking textual concepts and physical concepts

Publication Date: 2015.01.13 XEROX CORP

AI summary

A system and a method for linking textual and physical concepts are disclosed. The method includes extracting candidate phrases from a knowledge base for a device, the candidate phrases including noun phrases. A set of candidate concepts is generated, based on the extracted noun phrases. Provision is made, e.g., on a graphical user interface, for a user to generate mapped concepts for physical components of the device by selecting, for each concept to be mapped, a physical component shown in a graphical representation of the device and at least one of the candidate concepts which is to be linked to that physical component. The knowledge base is indexed, based on the mapped concepts. In this way, textual expressions in the knowledge base are linked to a respective physical component through one of the mapped concepts.