# US 2018/0024511 A1 · Model generating method and apparatus

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2018/0024511 A1
- Document ID: US20180024511A1
- Status: Published application
- Kind: A1
- Application number: 15/648,569
- Filed: 2017-07-13
- Published: 2018-01-25
- Earliest claimed: 2016-07-21
- Assignees: Siemens Aktiengesellschaft
- Applicants: Siemens Aktiengesellschaft
- Inventors: Qi WANG; Yong YUAN; Ming YU
- Web page: https://patentgrep.com/patent/US20180024511A1

## CPC

- G05B 13/04: involving the use of models or simulators
- G05B 13/0265: {the criterion being a learning criterion}
- G06F 30/00: Computer-aided design [CAD]
- G06F 2111/20: Configuration CAD, e.g. designing by assembling or positioning modules selected from libraries of predesigned modules
- Y02P 90/02: Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS

## Abstract

An embodiment of the present invention relates to a model generating method and apparatus, for realizing automatic creation of a system model. A model generating method of an embodiment includes: collecting configuration information of a system; extracting semantic description information from the configuration information; generating a model of the system according to the semantic description information, the model of the system including a relationship between model nodes and the model nodes corresponding to a device in the system or data produced by a device in the system. By extracting semantic description information from configuration information to generate a system model, a method for realizing automatic creation of a system model is provided, giving higher precision than manual creation of a system model.

## Claims

### Claim 1

A model generating method to generate a model of a system, comprising:
collecting configuration information of the system;
extracting semantic description information from the configuration information;
generating a model of the system according to the semantic description information, wherein
the model of the system includes at least two model nodes and a relationship between the at least two model nodes, and wherein each of the at least two model nodes corresponds to a device in the system or data produced by a device in the system.

### Claim 2 (depends on 1)

The method as claimed in claim 1, wherein the collecting of the configuration information of the system comprises collecting configuration information of the system in at least one of the following ways:
collecting configuration information of the system from at least two devices in the system, respectively;
collecting configuration information of the system from at least one controller which controls an operating process of at least one device in the system;
collecting configuration information of the system from at least one control platform which controls an operating process of at least one device in the system;
receiving manually inputted configuration information of the system; and
collecting configuration information of the system from at least one auxiliary device, the auxiliary device being usable for at least one of monitoring an operating state of at least one device in the system and collecting information of at least one device in the system.

### Claim 3 (depends on 1)

The method of claim 1, wherein the configuration information comprises at least one of the following:
description information of data produced during operation of at least one device in the system;
description information of at least one device in the system;
process control information for controlling an operating process of at least one device in the system; and
information for describing logic for realizing a function of the system.

### Claim 4 (depends on 1)

The method of claim 1, wherein the extracting of the semantic description information from the configuration information comprises:
extracting the semantic description information from the configuration information according to a keyword in the configuration information, wherein the keyword is used to indicate at least one of the following relationships:
a portion of description in the configuration information being an attribute of a device in the system;
a portion of description in the configuration information being an attribute of data produced by a device in the system;
a relationship between a device corresponding to a portion of description in the configuration information and another device corresponding to another portion of description;
a relationship between data produced by a device corresponding to a portion of description in the configuration information and other data produced by said device corresponding to another portion of description or data produced by another device; and
a relationship between data produced by a device corresponding to a portion of description in the configuration information and said device corresponding to another portion of description or another device.

### Claim 5 (depends on 1)

The method of claim 1, wherein semantic description information of the system comprises at least two items of information, and the generating of the model of the system according to the semantic description information comprises:
identifying, for each item of a portion of or all information of the semantic description information, at least two model nodes associated with said item of information;
generating a sub-model for each item of the portion of or all information, the sub-model comprising at least two model nodes associated with at least one of said item of information and a relationship between at least two model nodes associated with said item of information; and
integrating the sub-models generated to form a model of the system, according to the model nodes associated with a portion of or all of the information.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
obtaining, after generating a model of the system according to the semantic description information, an adjusted model of the system on the basis of the generated model of the system; wherein the generating of the model of the system according to the semantic description information comprises:
generating at least two models of the system according to the semantic description information, and
wherein either
the obtaining of the adjusted model of the system on the basis of the generated model of the system comprises:
selecting one of the at least two generated models of the system to serve as an adjusted model of the system; or
the generating of the model of the system according to the semantic description information comprises:
generating one model of the system according to the semantic description information, and
the obtaining of the adjusted model of the system on the basis of the generated model of the system comprises:
adjusting the generated model of the system, to obtain an adjusted model of the system.

### Claim 7 (depends on 6)

The method of claim 6, wherein the obtaining of the adjusted model of the system on the basis of the generated model of the system comprises at least one of:
obtaining an adjusted model of the system according to real-time data; wherein the real-time data is data produced by at least one device in the system during operation of the system; and
obtaining an adjusted model of the system according to a training rule; wherein the training rule comprises a rule to which a relationship between different types of at least two model nodes of the model conforms.

### Claim 8 (depends on 7)

The method of claim 7, wherein the adjusting of the model of the system according to real-time data comprises:
performing, for each of at least two model nodes in the model of the system, the following operations:
acquiring data produced at at least two times respectively during operation of the system by a device in the system corresponding to the model node;
forming the data produced at the at least two times respectively into a time series according to chronological order;
determining a time variation trend of variation with time of the time series; and
obtaining an adjusted model of the system according to a relationship between the time variation trends corresponding to the at least two model nodes respectively.

### Claim 9 (depends on 7)

The method of claim 7, further comprising:
updating, after obtaining an adjusted model of the system on the basis of the generated model of the system, the training rule according to the adjusted model of the system.

### Claim 10

A model generating apparatus to generate a model of a system, comprising:
a configuration information collecting module, to collect configuration information of the system;
a semantic description information extracting module, to extract semantic description information from the configuration information;
a model generating module, to generate a model of the system according to the semantic description information, wherein the model of the system includes at least two model nodes and a relationship between the at least two model nodes, and wherein each of the at least two model nodes corresponds to a device in the system or data produced by a device in the system.

### Claim 11 (depends on 10)

The apparatus of claim 10, wherein the configuration information collecting module is configured to collect the configuration information of the system in at least one of the following ways:
collecting configuration information of the system from at least two devices in the system respectively;
collecting configuration information of the system from at least one controller which controls an operating process of at least one device in the system;
collecting configuration information of the system from at least one control platform which controls an operating process of at least one device in the system;
receiving manually inputted configuration information of the system; and
collecting configuration information of the system from at least one auxiliary device, the auxiliary device being configured to at least one of monitor an operating state of at least one device in the system and collect information of at least one device in the system.

### Claim 12 (depends on 10)

The apparatus of claim 10, wherein the configuration information comprises at least one of the following information:
description information of data produced during operation of at least one device in the system;
description information of at least one device in the system; process control information for controlling an operating process of at least one device in the system; and
information for describing logic for realizing a function of the system.

### Claim 13 (depends on 10)

The apparatus of claim 10, wherein the semantic description information extracting module is configured to extract the semantic description information from the configuration information according to a keyword in the configuration information, wherein the keyword is used to indicate at least one of the following relationships:
a portion of description in the configuration information being an attribute of a device in the system;
a portion of description in the configuration information being an attribute of data produced by a device in the system;
a relationship between a device corresponding to a portion of description in the configuration information and another device corresponding to another portion of description;
a relationship between data produced by a device corresponding to a portion of description in the configuration information and other data produced by said device corresponding to another portion of description or data produced by another device; and
a relationship between data produced by a device corresponding to a portion of description in the configuration information and said device corresponding to another portion of description or another device.

### Claim 14 (depends on 10)

The apparatus of claim 10, wherein the semantic description information extracted by the semantic description information extracting module includes at least two items of information, and the model generating module is configured to:
for each item of a portion of or all information of the semantic description information,
identifying at least two model nodes associated with said item of information;
generating a sub-model for each item of the portion of or all information, the sub-model comprising at least two model nodes associated with said item of information and/or a relationship between at least two model nodes associated with said item of information; and
integrating all the sub-models generated to form a model of the system, according to all model nodes associated with the portion of or all information.

### Claim 15 (depends on 10)

The apparatus of claim 10, further comprising:
a model adjusting module, to obtain an adjusted model of the system on the basis of a model of the system generated by the model generating module wherein
the model generating module is configured to generate at least two models of the system, and the model adjusting module is configured to select one of the at least two models generated by the model generating module to serve as an adjusted model of the system;
or
the model generating module is configured to generate one model of the system, and the model adjusting module is configured to adjust the one model generated by the model generating module, to obtain an adjusted model of the system.

### Claim 16 (depends on 15)

The apparatus of claim 15, wherein the model adjusting module is configured to at least one of:
obtain an adjusted model of the system according to real-time data, wherein the real-time data is data produced by at least one device in the system during operation of the system;
and
obtain an adjusted model of the system according to a training rule, the training rule including a rule to which a relationship between different types of at least two model nodes of the model conforms.

### Claim 17 (depends on 16)

The apparatus of claim 16, wherein the model adjusting module, when adjusting a model of the system according to real-time data, is configured to, for each of at least two model nodes in the model of the system, perform the following operations:
acquiring data produced at at least two times respectively during operation of the system by a device in the system corresponding to the model node;
forming the data produced at the at least two times respectively into a time series according to chronological order;
determining a time variation trend of variation with time of the time series; and
obtaining an adjusted model of the system according to a relationship between the time variation trends corresponding to the at least two model nodes respectively.

### Claim 18 (depends on 16)

The apparatus of claim 16, wherein the model adjusting module is further configured to:
update, after obtaining an adjusted model of the system, the training rule according to the adjusted model of the system.

### Claim 19

A model generating apparatus, configured to generate a model of a system, comprising:
a memory to store at least one computer instruction; and
at least one processor, to call the at least one computer instruction to:
collect configuration information of the system;
extract semantic description information from the configuration information;
generate a model of the system according to the semantic description information, wherein the model of the system includes at least two model nodes and a relationship between the at least two model nodes, and wherein each of the at least two model nodes corresponds to a device in the system or data produced by a device in the system.

### Claim 20 (depends on 1)

A non-transitory computer readable medium, on which is stored at least one computer instruction which, when executed by a processor, causes the processor to execute the method of claim 1.

### Claim 21 (depends on 2)

The method of claim 2, wherein the configuration information comprises at least one of the following:
description information of data produced during operation of at least one device in the system;
description information of at least one device in the system;
process control information for controlling an operating process of at least one device in the system; and
information for describing logic for realizing a function of the system.

### Claim 22 (depends on 8)

The method of claim 8, further comprising:
updating, after obtaining an adjusted model of the system on the basis of the generated model of the system, the training rule according to the adjusted model of the system.

### Claim 23 (depends on 19)

The apparatus of claim 19, wherein the at least one processor is configured to call the at least one computer instruction to collect the configuration information of the system in at least one of the following ways:
collecting configuration information of the system from at least two devices in the system respectively;
collecting configuration information of the system from at least one controller which controls an operating process of at least one device in the system;
collecting configuration information of the system from at least one control platform which controls an operating process of at least one device in the system;
receiving manually inputted configuration information of the system; and
collecting configuration information of the system from at least one auxiliary device, the auxiliary device being configured to at least one of monitor an operating state of at least one device in the system and collect information of at least one device in the system.

### Claim 24 (depends on 23)

The apparatus of claim 23, wherein the configuration information comprises at least one of the following information:
description information of data produced during operation of at least one device in the system;
description information of at least one device in the system; process control information for controlling an operating process of at least one device in the system; and
information for describing logic for realizing a function of the system.

### Claim 25 (depends on 11)

The apparatus of claim 11, wherein the configuration information comprises at least one of the following information:
description information of data produced during operation of at least one device in the system;
description information of at least one device in the system; process control information for controlling an operating process of at least one device in the system; and
information for describing logic for realizing a function of the system.

### Claim 26 (depends on 17)

The apparatus of claim 17, wherein the model adjusting module is further configured to:
update, after obtaining an adjusted model of the system, the training rule according to the adjusted model of the system.

### Claim 27 (depends on 2)

A non-transitory computer readable medium, on which is stored at least one computer instruction which, when executed by a processor, causes the processor to execute the method of claim 2.
