Unlock instant, AI-driven research and patent intelligence for your innovation.

Industrial plant and method for constructing and/or processing knowledge graphs

A technology of industrial equipment and knowledge graph, applied in reasoning methods, knowledge representation, neural learning methods, etc.

Pending Publication Date: 2022-07-29
SIEMENS AG
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Such input data is inherently well-structured, e.g., pixels in an image have fixed positioning, and applicability is often limited to a narrow set of tasks that exploit this structure and do not extend beyond the domain of the initial data.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Industrial plant and method for constructing and/or processing knowledge graphs
  • Industrial plant and method for constructing and/or processing knowledge graphs
  • Industrial plant and method for constructing and/or processing knowledge graphs

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0088] In the following description, various aspects of the present invention and embodiments thereof will be described. However, one skilled in the art will appreciate that the embodiments may be practiced with only some or all aspects thereof. For purposes of explanation, specific numbers and configurations are set forth in order to provide a thorough understanding. However, it should be apparent to those skilled in the art that embodiments may be practiced without these specific details.

[0089] In the following description, the terms "mode" and "stage" are used interchangeably. If the learning component runs in the first mode, it also runs for the duration of the first phase, and vice versa. Also, the terms "triple" and "triple statement" will be used interchangeably.

[0090] Nickel, M., Tresp, V., and Kriegel, H.-P., "A three-way model for collective learning on multi-relational data" (in Icml 11 (2011), pp. 809–816), published in A widely used graph embedding algor...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

An industrial device (ED) for constructing and / or processing a knowledge graph (KG), having at least one sensor (S) and / or at least one data source (DS), configured to provide raw data (RD); a processor having an ETL component (ETLC) configured to convert the raw data (RD) into a triple statement (T) using a mapping rule (MR); a triple storage (ETS), which stores a triple statement (T) as a dynamically changing knowledge graph (KG); a learning component (LC) configured to process the triad statement (T) in a learning mode and to perform reasoning (IF) in a reasoning mode; and a control component (CC) configured to switch between different operating modes of the learning component (LC).

Description

technical field [0001] Graph-based data analysis is playing an increasingly important role in industrial applications. A prominent example is the knowledge graph, which is based on a graph-structured database capable of ingesting and (with semantic information) representing knowledge from potentially multiple sources and domains. Knowledge graphs are rich data structures that enable symbolic descriptions of abstract concepts and their interrelationships. The use of knowledge graphs enables the integration of previously isolated data sources in a way that enables AI and data analysis applications to work on a unified, contextualized, semantically rich knowledge base, enabling the use of data from (one or more) ) well-defined entities and relationships in a domain of interest (e.g., industrial automation or building systems) to perform its tasks (e.g., inference or reasoning) more general, interpretable, interoperable, and accurate AI algorithms. Background technique [0002...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/04G06N3/08G06N5/04G05B13/02
CPCG06N3/049G06N3/08G06N5/04G05B13/0265G06N3/084G06N3/088G06N5/022G05B2219/25428G06N3/042G06N3/065G06N5/01G06N3/047G06N7/01G06N3/048G06N3/045G06F16/254G05B13/029
Inventor J·索勒加里多D·多尔德
Owner SIEMENS AG