Ontology-based metamodel knowledge representation method, device and equipment and storage medium

Abstract

The application belongs to the technical field of industrial intelligent manufacturing, and discloses an industrial meta-model knowledge representation method, device and equipment based on ontology and a storage medium. The method comprises the following steps: when an industrial meta-model construction instruction is received, an industrial meta-model knowledge ontology is constructed from top to bottom according to a preset knowledge ontology; each industrial meta-model knowledge ontology is perfected according to industrial model information, and a plurality of model ontology files are generated; an industrial meta-model knowledge base is built according to the plurality of model ontology files; and an industrial demand task solving result is determined according to the industrial meta-model knowledge base, industrial demand coding and example class instance name. Through the above method, the problems of inconsistent description granularity and standard of the industrial model, non-uniform compilation environment, great difficulty in model management and retrieval, etc. are effectively solved, the reusability of fragmented industrial model knowledge is realized, distributed computing application of the industrial meta-model is realized, and the model solving power problem is solved by fully utilizing heterogeneous computing power.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial intelligent manufacturing, and in particular to an industrial meta-model knowledge representation method based on ontology, a device, equipment and a storage medium. BACKGROUND

[0002] Industrial manufacturing is an important foundation for the development of China's national economy, and is also an important guarantee for China to become an industrial power. With the rapid development of Internet technology, artificial intelligence technology and industrial manufacturing are deeply integrated, and intelligent manufacturing is the primary problem we need to break through at present. However, as one of the world's industrial powers, China's industrial intelligence level has not reached the world's leading level. In order to accelerate the construction of an industrial intelligent manufacturing power, we must take the industrial internet as the infrastructure and promote the deep integration of information technology, artificial intelligence and modern industrial manufacturing. Industrial model is the encapsulation of physical and chemical mechanisms and best practices in industrial manufacturing processes, and is the knowledge support for industrial intelligence, which can promote the transformation of industrial intelligence and lay a solid knowledge foundation for an intelligent manufacturing power.

[0003] At present, a variety of model construction researches have appeared for different industrial scenarios, forming a series of industrial knowledge model libraries. For the preparation process of polyvinyl chloride, Zhang Bin built a polyvinyl chloride stripping industrial model based on weighted least squares support vector machine, which effectively predicted the temperature change in the preparation process. Through the study of the mechanism of selective catalytic reduction technology, Dai Ningkai et al. established a mechanism model of the flue gas system of the catalytic cracking unit. However, these models still have many defects. First, the model integration is too high and the construction standards are different, and non-industrial manufacturing professionals cannot disassemble the model and understand the industrial knowledge encapsulated by the model. At the same time, the granularity of model unit division is not uniform, which leads to poor generality and low reusability of the model. Second, the development language environment of the model is inconsistent, and the compatibility between models is poor, which seriously hinders the development process of industrial intelligence. Third, there is a lack of a unified management model library, and the number of these models is huge and scattered, which causes great difficulty in model retrieval, that is, the industrial model has the characteristics of "scattered", "mixed" and "chaotic". Therefore, there is an urgent need for a model representation method that can realize the reusability and generality of the model. SUMMARY

[0004] The main purpose of the present application is to provide an industrial meta-model knowledge representation method based on ontology, device, equipment and storage medium, which aims to solve the technical problem of how to realize the reusability of the model in the model representation construction in the prior art.

[0005] To achieve the above-mentioned purpose, the present application provides an industrial meta-model knowledge representation method based on ontology, which comprises:

[0006] When the model construction instruction of the industrial meta-model is received, a plurality of industrial meta-model knowledge ontologies are constructed in a top-down manner according to a preset industrial meta-model knowledge ontology;

[0007] Data of the plurality of industrial meta-model knowledge ontologies is perfected according to the collected industrial model information, and a plurality of model ontology files are generated;

[0008] The industrial meta-model knowledge base is built according to the plurality of model ontology files;

[0009] An industrial demand task solving result is determined according to the industrial meta-model knowledge base, industrial demand coding and example class instance name.

[0010] Optionally, the industrial meta-model knowledge ontology is constructed in a top-down manner according to the preset industrial meta-model knowledge ontology, and the method comprises the following steps of:

[0011] A domain range, a reuse relationship and a hierarchical relationship of the ontology are determined;

[0012] Basic attributes of the ontology are defined;

[0013] The industrial meta-model knowledge ontology is constructed according to the domain range, the reuse relationship, the hierarchical relationship and the basic attributes.

[0014] Optionally, the data of the plurality of industrial meta-model knowledge ontologies is perfected according to the collected industrial model information, and the plurality of model ontology files are generated, and the method comprises the following steps of:

[0015] The industrial model information is processed to obtain integrated model information;

[0016] Ontology instances of the plurality of industrial meta-model knowledge ontologies are constructed according to the integrated model information, and the ontology instances of the plurality of industrial meta-model knowledge ontologies are generated;

[0017] The data of the plurality of industrial meta-model knowledge ontologies is perfected according to the ontology instances of the plurality of industrial meta-model knowledge ontologies, and the plurality of model ontology files are generated.

[0018] Optionally, the industrial meta-model knowledge base is built according to the plurality of model ontology files, and the method comprises the following steps of:

[0019] Identification codes of the plurality of industrial meta-model knowledge ontologies are obtained;

[0020] The plurality of model ontology files are named according to the identification codes of the plurality of industrial meta-model knowledge ontologies, and a plurality of named model ontology files are obtained;

[0021] The industrial meta-model knowledge base is built according to the plurality of named model ontology files.

[0022] Optionally, the determining the industrial demand task solving result according to the industrial meta-model knowledge base, the industrial demand code and the case class instance name comprises:

[0023] When the industrial demand code and the case class instance name sent by the industrial equipment are received, a target model ontology file is determined in the industrial meta-model knowledge base according to the industrial demand code;

[0024] The data attribute value of the case class instance name is determined according to the target model ontology file;

[0025] The industrial demand task solving result of the industrial equipment is determined according to the data attribute value, and the industrial demand task solving result is sent to the industrial equipment.

[0026] Optionally, before the determining the target model ontology file in the industrial meta-model knowledge base according to the industrial demand code when the industrial demand code and the case class instance name sent by the industrial equipment are received, the method further comprises:

[0027] The case class instance in the initial model ontology file is updated according to the updated computing power class instance sent by the computing power equipment, to generate a target model ontology file, wherein the updated computing power class instance is generated according to the instance output result and the computing power class instance name after the computing power equipment receives the industrial demand code, the model implementation class instance name and the model input information sent by the industrial equipment, requests the initial ontology file according to the industrial demand code, determines the model implementation class instance in the initial ontology file according to the model implementation class instance name, and determines the instance output result according to the model input information and the model implementation class instance.

[0028] Optionally, after the determining the industrial demand task solving result according to the industrial meta-model knowledge base, the industrial demand code and the case class instance name, the method further comprises:

[0029] The ontology instance in the industrial meta-model knowledge base is parsed to generate a graph database;

[0030] According to the model label information, a process ontology file of a process flow is determined in the graph database;

[0031] The process visualization of the process flow is realized according to the process ontology file.

[0032] In addition, in order to achieve the above-mentioned purpose, the application further provides an industrial meta-model knowledge representation device based on ontology, which comprises:

[0033] The construction module is configured to construct a plurality of industrial meta-model knowledge ontologies in a top-down manner according to a preset industrial meta-model knowledge ontology when a model construction instruction of the industrial meta-model is received.

[0034] The perfecting module is configured to perform data perfecting on the industrial meta-model knowledge ontologies according to the collected industrial model information, and generate a plurality of model ontology files.

[0035] The building module is configured to build an industrial meta-model knowledge base according to the plurality of model ontology files.

[0036] The determining module is configured to determine an industrial demand task solving result according to the industrial meta-model knowledge base, industrial demand encoding and an example class instance name.

[0037] In addition, to achieve the above object, the present application further provides an industrial meta-model knowledge representation device based on ontology, which comprises a memory, a processor and an industrial meta-model knowledge representation program based on ontology stored in the memory and executable on the processor, and the industrial meta-model knowledge representation program based on ontology is configured to implement the industrial meta-model knowledge representation method based on ontology as described above.

[0038] In addition, to achieve the above object, the present application further provides a storage medium, which stores an industrial meta-model knowledge representation program based on ontology, and the industrial meta-model knowledge representation program based on ontology implements the industrial meta-model knowledge representation method based on ontology as described above when executed by a processor.

[0039] The application constructs multiple industrial meta-model knowledge ontologies in a top-down manner according to a preset industrial meta-model knowledge ontology when model construction instructions of an industrial meta-model are received; data of each industrial meta-model knowledge ontology is perfected according to collected industrial model information, and multiple model ontology files are generated; an industrial meta-model knowledge base is built according to the multiple model ontology files; and an industrial demand task solving result is determined according to the industrial meta-model knowledge base, industrial demand coding and example class instance name. In the above manner, multiple industrial meta-model knowledge ontologies are constructed in a preset top-down manner, and then the multiple industrial meta-model knowledge ontologies are perfected in data, the industrial meta-model knowledge base is built based on the generated multiple model ontology files, and finally the industrial demand task solving result is determined by using the industrial meta-model knowledge base, industrial demand coding and example class instance name, effectively solving the problems of inconsistent description granularity and standards of industrial models, non-uniform compilation environment, great difficulty in model management and retrieval, and the like, realizing the reusability and universality of fragmented industrial model knowledge, and also realizing the application of distributed computing of the industrial meta-model based on this, fully utilizing heterogeneous computing power to solve the computing power problem of the model. The application has important significance for realizing the representation, sharing and reuse of industrial manufacturing knowledge, and conforms to the development trend of intelligent manufacturing and networked collaboration. BRIEF DESCRIPTION OF DRAWINGS DETAILED DESCRIPTION OF THE INVENTION BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 is a structural schematic diagram of an ontology-based industrial meta-model knowledge representation device of a hardware running environment related to an embodiment scheme of the application;

[0041] Figure 2 is a flowchart of a first embodiment of an ontology-based industrial meta-model knowledge representation method of the application;

[0042] Figure 3 is a model kernel schematic diagram of an embodiment of an ontology-based industrial meta-model knowledge representation method of the application;

[0043] Figure 4 is a hierarchical schematic diagram of an embodiment of an ontology-based industrial meta-model knowledge representation method of the application;

[0044] Figure 5 is a data attribute schematic diagram of an embodiment of an ontology-based industrial meta-model knowledge representation method of the application;

[0045] Figure 6 is an object attribute schematic diagram of an embodiment of an ontology-based industrial meta-model knowledge representation method of the application;

[0046] Figure 7 is an ontology instance schematic diagram of an embodiment of an ontology-based industrial meta-model knowledge representation method of the application;

[0047] Figure 8The flow chart for generating the ontology library of the embodiment of the ontology-based industrial meta-model knowledge representation method of the application;

[0048] Figure 9 The distributed computing schematic diagram of the embodiment of the ontology-based industrial meta-model knowledge representation method of the application;

[0049] Figure 10 The graph database schematic diagram of the first embodiment of the ontology-based industrial meta-model knowledge representation method of the application;

[0050] Figure 11 The flow schematic diagram of the second embodiment of the ontology-based industrial meta-model knowledge representation method of the application;

[0051] Figure 12 The structural block diagram of the first embodiment of the ontology-based industrial meta-model knowledge representation device of the application.

[0052] The implementation, functional features and advantages of the application will be further explained with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are intended to be illustrative only and not limiting of the application.

[0054] Reference Figure 1 , Figure 1 The ontology-based industrial meta-model knowledge representation device structure schematic diagram of the hardware running environment related to the embodiment of the application.

[0055] As Figure 1 shown, the ontology-based industrial meta-model knowledge representation device can include a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication among these components. The user interface 1003 can include a display, an input unit such as a keyboard, and can also include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a wireless fidelity (Wi-Fi) interface). The memory 1005 can be a high-speed random access memory (RAM) memory, or a stable non-volatile memory (NVM), such as a disk memory. The memory 1005 can also be a storage device independent of the aforementioned processor 1001.

[0056] Those skilled in the art can understand that Figure 1 The structure shown in the figure does not constitute a limitation on the ontology-based industrial meta-model knowledge representation device, and can include more or fewer components than the figure, or combine certain components, or different component arrangements.

[0057] As Figure 1 As shown, the memory 1005 as a storage medium can include an operating system, a network communication module, a user interface module, and an ontology-based industrial meta-model knowledge representation program.

[0058] In the ontology-based industrial meta-model knowledge representation device shown in Figure 1 In the ontology-based industrial meta-model knowledge representation device shown in the figure, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the ontology-based industrial meta-model knowledge representation device of the present application can be arranged in the ontology-based industrial meta-model knowledge representation device, and the ontology-based industrial meta-model knowledge representation device calls the ontology-based industrial meta-model knowledge representation program stored in the memory 1005 through the processor 1001, and executes the ontology-based industrial meta-model knowledge representation method provided by the embodiment of the present application.

[0059] The embodiment of the present application provides an ontology-based industrial meta-model knowledge representation method, which refers to Figure 2 , Figure 2 The flowchart of a first embodiment of an ontology-based industrial meta-model knowledge representation method of the present application.

[0060] The ontology-based industrial meta-model knowledge representation method comprises the following steps:

[0061] Step S10: When receiving the model construction instruction of the industrial meta-model, a plurality of industrial meta-model knowledge ontologies are constructed in a top-down manner according to a preset industrial meta-model knowledge ontology.

[0062] It should be noted that the execution subject of the present embodiment is a terminal device, and the terminal device is a computer, a tablet computer, a mobile phone and other intelligent terminals, which are not limited in the present embodiment. There is an ontology-based industrial meta-model knowledge representation system on the terminal device, which can be built by using but not limited to the Protégé ontology construction tool.

[0063] It can be understood that the ontology concept originates from philosophy, is used to describe the concepts in a field and the relationship between the concepts, and is helpful for knowledge representation and improving the machine readability of data. When receiving the model construction quality sent by the user's control cloud, a plurality of industrial meta-model knowledge ontologies are constructed in a preset top-down manner.

[0064] In a specific implementation, when a preset top-down industrial meta-model knowledge ontology is adopted, model generation needs to be performed according to the seven-step method of constructing the ontology, and further, the preset industrial meta-model knowledge ontology is constructed in a top-down manner, including: determining the domain range, reuse relationship and hierarchical relationship of the ontology; defining the basic attributes of the ontology; constructing the industrial meta-model knowledge ontology according to the domain range, reuse relationship, hierarchical relationship and basic attributes.

[0065] It should be noted that the reuse relationship of the ontology refers to whether there is a reusable industrial meta-model knowledge ontology, and the hierarchical relationship of the ontology refers to the hierarchical relationship between the classes of the industrial meta-model knowledge ontology. The basic attributes refer to the classes, attributes and axioms of the industrial meta-model knowledge ontology.

[0066] It can be understood that when constructing the industrial meta-model knowledge ontology, first, the domain range of the industrial meta-model knowledge ontology, whether there is a reusable industrial meta-model knowledge ontology, and the hierarchical relationship between the classes of the industrial meta-model knowledge ontology are determined, then the classes, attributes, axioms, etc. of the ontology are defined, and finally the industrial meta-model knowledge ontology is built based on, but not limited to, the Protégé ontology construction tool, and multiple industrial meta-ontology models are saved as, but not limited to, RDF / XML format owl ontology files. The industrial meta-model knowledge ontology includes a model kernel class, and the kernel class includes six subclasses: a model input class, a model output class, a model parameter class, a model implementation class, a model computing power class and a model attribute class. As shown in Figure 3 , the model implementation class includes the specific code implementation of the model and the programming language of the implementation, which can effectively support multiple compilation environments, the model computing power class effectively implements distributed computing, and the attribute class of the model includes the hierarchical dimension and category of the model. The model attribute class can be divided into eleven subclasses: a near-function model class, a model demo class, a model category class, a pre-order model class, a post-order model class, a model function class, a model hierarchical dimension class, a model keyword class, a model maturity class, a model unit class and a model name class, which is conducive to the management of the model library for massive industrial meta-model knowledge ontologies. As shown in Figure 4 , Figure 4 The hierarchical relationship between the classes of the industrial meta-model knowledge ontology is built based on the Protégé ontology construction tool, as shown in Figure 5 , Figure 5 The data attributes of the industrial meta-model knowledge ontology are defined, as shown in Figure 6 , Figure 6 The object attributes of the industrial meta-model knowledge ontology are defined, and the classes of the industrial meta-model knowledge ontology include data attributes and object attributes.

[0067] Step S20: data perfecting is performed on each industrial meta-model knowledge ontology according to the collected industrial model information, and a plurality of model ontology files are generated.

[0068] It should be noted that the industrial model information is all the industrial model information that can be obtained at present. According to the model data layer, the industrial model information is collected, including but not limited to the python third-party extension package owlready2 based on the Protégé ontology construction tool, and a plurality of meta-model ontologies are generated in batches. The files corresponding to the plurality of meta-model ontologies are model ontology files.

[0069] It can be understood that the knowledge graph is usually divided into two layers: a schema layer and a data layer. The schema layer is in the form of an ontology above the data layer. Therefore, after the industrial intelligent meta-model knowledge ontology is constructed, according to the related information of the model, including but not limited to the protégé-based batch generation of the meta-model ontology.

[0070] In a specific implementation, in order to reasonably utilize the collected industrial model information, further, the data perfecting is performed on each industrial meta-model knowledge ontology according to the collected industrial model information, and a plurality of model ontology files are generated, including: information processing is performed on the industrial model information to obtain integrated model information; according to the integrated model information, an instance of each industrial meta-model knowledge ontology is constructed to generate an ontology instance of each industrial meta-model knowledge ontology; and according to the ontology instance of each industrial meta-model knowledge ontology, data perfecting is performed on each industrial meta-model knowledge ontology to generate a plurality of model ontology files.

[0071] It should be noted that the information processing is performed on the industrial model information, specifically including extraction, completion and integration of the industrial model information. The processed industrial model information is the integrated model information. According to the integrated model information, an instance of each industrial meta-model knowledge is constructed, and according to the instance of each industrial meta-model knowledge, each industrial meta-model knowledge ontology is perfected to generate a plurality of model ontology files. For example, taking a model for calculating leaching rate in a zinc hydrometallurgy process as an example, an industrial meta-model knowledge ontology instance is shown in the accompanying drawings. Figure 7 The model for calculating leaching rate in the zinc hydrometallurgy process mainly completes the calculation of zinc oxide leaching rate. Alpha, mu, m, M_H, M_ZnO and Ch are model input class instances, respectively representing total zinc oxide, acid ion concentration, total powder, sulfuric acid molar mass, zinc oxide molar mass and PH value. Beta is a model output class instance, representing zinc oxide leaching rate. The model implementation class instance includes model implementation code, programming language, contributing author, version and other information, and is compatible with multiple programming languages.

[0072] Step S30: An industrial meta-model knowledge base is built according to the plurality of model ontology files.

[0073] It should be noted that after determining the plurality of model ontology files, the plurality of model ontology files can be summarized to build the industrial meta-model knowledge base.

[0074] It can be understood that, in order to facilitate the management of the industrial meta-model knowledge base, further, the industrial meta-model knowledge base built according to the plurality of model ontology files comprises: obtaining the identification code of each industrial meta-model knowledge ontology; naming the plurality of model ontology files according to the identification code of each industrial meta-model knowledge ontology to obtain a plurality of named model ontology files; and building the industrial meta-model knowledge base according to the plurality of named model ontology files.

[0075] In a specific implementation, the model ontology files are named by the identification code of each industrial meta-model knowledge ontology, the named model ontology files are saved, and the industrial meta-model knowledge base is constructed based on the plurality of named model ontology files. As shown in Figure 8 After constructing the plurality of industrial meta-model knowledge ontologies, the industrial model information is obtained, the model ontology script is written based on the third-party library owlready2 of Python, and finally the industrial meta-model knowledge base is generated by using the named model ontology files.

[0076] It should be noted that, as shown in Figure 9 According to the formalized representation of the ontology for the industrial intelligent meta-model, the current model can obtain the identification code of the previous model of the current model according to the data attribute information of the previous model class instance, so as to build a connection relationship between the current model and the previous model. The current model can obtain the data of the input variables and parameters of the previous model and the calculation result of the output as the input of the current model according to the identification code of the previous model. The calculation result is saved to the computing power class instance for reading by other models. In order to adapt to a multi-language environment, the code of the model implementation class supports multiple programming languages. Based on the docker container technology, the multi-language code can be executed. In addition, in order to fully utilize the computing power, the industrial meta-model knowledge base supports distributed computing. Any computer with heterogeneous computing power meeting the requirements of the meta-model can access the industrial meta-model knowledge base, read the code of the ontology model implementation class, execute the code based on docker locally to obtain the calculation result, and save it to the ontology. Other ontologies can access the ontology and read the calculation result through the identification code of the model, so as to realize the interaction and distributed computing between models.

[0077] Step S40: determining the industrial demand task solving result according to the industrial meta-model knowledge base, the industrial demand code and the example class instance name.

[0078] It should be noted that the example class instance name is the industrial demand code and the example class instance name sent by the industrial equipment to the terminal device when the industrial calculation is needed. The industrial demand code is the identification code of the model ontology file. The industrial demand task solving result refers to the model calculation result output by the terminal device after receiving the industrial demand code and the example class instance name.

[0079] It can be understood that in order to intuitively query and detect the parameter value of the process flow in subsequent actual application, the data flow between the graph database visual ontology is based on. Further, after determining the industrial demand task solving result according to the industrial meta-model knowledge base, the industrial demand code and the example class instance name, the method further comprises: parsing the ontology instance in the industrial meta-model knowledge base to generate a graph database; determining the process ontology file of the process flow in the graph database according to the model label information; and realizing process visualization of the process flow according to the process ontology file.

[0080] In a specific implementation, the industrial meta-model knowledge ontology is to unitize the process flow mechanism, maintain appropriate granularity, and the splicing between the industrial meta-model knowledge ontology represents the mechanism calculation process of the entire process flow. For the ontology instance corresponding to the constructed industrial meta-model knowledge ontology, the ontology instance is stored as an OWL document. The API provided by the third-party library owlready2 of python is used to read and parse the ontology instance and store it to the graph database. The hierarchical relationship, instance attribute and other information of the visual model ontology in the graph database are visualized, as shown in the graph database. Figure 10

[0081] It should be noted that when the process flow needs to be tracked, the model label information is obtained, and the model label information includes but is not limited to the keyword of the model, the model hierarchical dimension and the model category and other label information. According to the model label information and the graph data query language, a plurality of model ontology files related to the process flow are determined. The plurality of model ontology files related to the process flow are process ontology files. The data flow and control flow of the industrial meta-model knowledge ontology calculation are visualized according to the process ontology file, process visualization of the process flow is realized, so that the industrial manufacturing knowledge can be intuitively identified, and the data of the industrial process can also be monitored in real time, abnormal data can be quickly located, and the safety factor of the process flow and the product precision play an important role in improving.

[0082] ​The embodiment constructs multiple industrial meta-model knowledge ontologies in a top-down manner according to a preset industrial meta-model knowledge ontology when model construction instructions of the industrial meta-model are received; data of each industrial meta-model knowledge ontology is perfected according to collected industrial model information, and multiple model ontology files are generated; an industrial meta-model knowledge base is built according to the multiple model ontology files; and an industrial demand task solving result is determined according to the industrial meta-model knowledge base, industrial demand coding and example class instance name. In the above manner, multiple industrial meta-model knowledge ontologies are constructed in a preset top-down manner, and then data of the multiple industrial meta-model knowledge ontologies is perfected, an industrial meta-model knowledge base is built based on the generated multiple model ontology files, and finally an industrial demand task solving result is determined by using the industrial meta-model knowledge base, industrial demand coding and example class instance name, effectively solving the problems of inconsistent model granularity and standards, non-uniform compilation environment, difficult model management and retrieval, realizing the reusability and universality of the model, and also realizing distributed computing of the meta-model, fully utilizing computing power to solve the computing problem of the model, and having important significance for realizing representation, sharing and reuse of industrial manufacturing knowledge, conforming to the development trend of industrial intelligent manufacturing and networked collaboration.

[0083] Reference Figure 11 , Figure 11 FIG. 1 is a flowchart of an embodiment of an industrial meta-model knowledge representation method based on ontology.

[0084] Based on the above first embodiment, in the industrial meta-model knowledge representation method based on ontology, the step S40 comprises the following steps.

[0085] Step S41: When the industrial demand coding and example class instance name sent by the industrial equipment are received, the target model ontology file is determined in the industrial meta-model knowledge base according to the industrial demand coding.

[0086] It should be noted that when the industrial demand coding and example class instance name sent by the industrial equipment are received, the target model ontology file is determined in the industrial meta-model knowledge base according to the industrial demand coding, and the target model ontology file is the updated model ontology file.

[0087] It can be understood that, in order to obtain the corresponding target model ontology file corresponding to the accurate industrial demand code, further, when receiving the industrial demand code and the example class instance name sent by the industrial equipment, before determining the target model ontology file in the industrial meta-model knowledge base according to the industrial demand code, it further comprises: updating the example class instance in the initial model ontology file according to the updated computing power class instance sent by the computing power equipment, generating the target model ontology file, the updated computing power class instance is that the computing power equipment requests the initial ontology file according to the industrial demand code, determines the model implementation class instance in the initial ontology file according to the model implementation class instance name, determines the instance output result according to the model input information and the model implementation class instance, and generates according to the instance output result and the computing power class instance name.

[0088] In a specific implementation, when the industrial equipment needs to perform industrial calculation, it sends the industrial demand code, the model implementation class instance name and the model input information to the computing power equipment in the cloud or the edge, and the model input information includes the model output name and the input value. The computing power equipment pulls the corresponding model ontology file from the industrial meta-model knowledge base of the terminal device according to the industrial demand code, that is, the initial ontology file, obtains the model implementation class instance in the initial ontology file according to the model implementation class instance name, inputs the model input information into the specific code of the model implementation class instance, realizes the model calculation based on the Dockers container technology compatible with multiple programming languages, obtains the model output value and the corresponding computing power class instance name, and the model output value is the instance output result.

[0089] It should be noted that the computing power equipment writes the instance output result and the computing power class instance name into the computing power class instance of the initial ontology file to obtain the updated computing power class instance (i.e. the updated computing power class instance), and the computing power equipment returns the updated computing power class instance to the terminal device, and the terminal device updates the initial ontology file according to the updated computing power class instance to generate the target model ontology file. At the same time, the computing power equipment sends the computing power class instance name to the industrial equipment.

[0090] Step S42: determining the data attribute value of the example class instance name according to the target model ontology file.

[0091] It should be noted that the terminal device queries the hashrate_result data attribute value of the computing power class instance in the target model ontology file according to the example class instance name.

[0092] Step S43: determining the industrial demand task solving result of the industrial equipment according to the data attribute value, and sending the industrial demand task solving result to the industrial equipment.

[0093] It should be noted that the data attribute value determined by the terminal device is the solution result of the industrial demand task corresponding to the industrial calculation of the industrial equipment, and the solution result of the industrial demand task is sent to the industrial equipment.

[0094] In the embodiment, when the industrial demand code and the example class instance name sent by the industrial equipment are received, the target model ontology file is determined in the industrial meta-model knowledge base according to the industrial demand code; the data attribute value of the example class instance name is determined according to the target model ontology file; the solution result of the industrial demand task of the industrial equipment is determined according to the data attribute value, and the solution result of the industrial demand task is sent to the industrial equipment. Through the above-mentioned manner, by using distributed computing, the computing power can be fully utilized, and the calculation speed of the model can be accelerated.

[0095] In addition, with reference to Figure 12 , the embodiment of the present application also provides an ontology-based industrial meta-model knowledge representation device, which comprises:

[0096] The construction module 10 is configured to, when receiving a model construction instruction of an industrial meta-model, construct a plurality of industrial meta-model knowledge ontologies in a top-down manner according to a preset industrial meta-model knowledge ontology.

[0097] The perfecting module 20 is configured to perform data perfecting on each industrial meta-model knowledge ontology according to the collected industrial model information, and generate a plurality of model ontology files.

[0098] The building module 30 is configured to build an industrial meta-model knowledge base according to the plurality of model ontology files.

[0099] The determining module 40 is configured to determine a solution result of an industrial demand task according to the industrial meta-model knowledge base, an industrial demand code and an example class instance name.

[0100] The embodiment constructs multiple industrial meta-model knowledge ontologies in a top-down manner according to a preset industrial meta-model knowledge ontology by adopting a top-down manner when a model construction instruction of an industrial meta-model is received; data of the multiple industrial meta-model knowledge ontologies is perfected according to collected industrial model information, multiple model ontology files are generated; an industrial meta-model knowledge base is built according to the multiple model ontology files; and an industrial demand task solving result is determined according to the industrial meta-model knowledge base, industrial demand coding and example class instance name. In the above manner, multiple industrial meta-model knowledge ontologies are constructed in a preset top-down manner, data of the multiple industrial meta-model knowledge ontologies is perfected, an industrial meta-model knowledge base is built based on the generated multiple model ontology files, and finally the industrial meta-model knowledge base, industrial demand coding and example class instance name are used to determine an industrial demand task solving result, effectively solving problems such as inconsistent description granularity and standards of industrial models, non-uniform compilation environment, great difficulty in model management and retrieval, and realizing reusability and universality of fragmented industrial model knowledge. At the same time, distributed computing application of the industrial meta-model is realized based on this, and heterogeneous computing power is fully utilized to solve the computing power problem of the model. And it has important significance for realizing representation, sharing and reuse of industrial manufacturing knowledge, and conforms to the development trend of industrial intelligent manufacturing and networked collaboration.

[0101] In an embodiment, the construction module 10 is further configured to determine a domain range, a reuse relationship and a hierarchical relationship of the ontology;

[0102] define basic attributes of the ontology;

[0103] construct an industrial meta-model knowledge ontology according to the domain range, the reuse relationship, the hierarchical relationship and the basic attributes.

[0104] In an embodiment, the perfection module 20 is further configured to perform information processing on the industrial model information to obtain integrated model information;

[0105] construct an instance of each industrial meta-model knowledge ontology according to the integrated model information to generate an ontology instance of each industrial meta-model knowledge ontology;

[0106] perfect data of each industrial meta-model knowledge ontology according to the ontology instance of each industrial meta-model knowledge ontology to generate multiple model ontology files.

[0107] In an embodiment, the construction module 30 is further configured to obtain an identification code of each industrial meta-model knowledge ontology;

[0108] name the multiple model ontology files according to the identification code of each industrial meta-model knowledge ontology to obtain multiple named model ontology files;

[0109] According to the plurality of named model ontology files, an industrial meta-model knowledge base is built.

[0110] In an embodiment, the determining module 40 is further configured to, when receiving the industrial demand code and the case class instance name sent by the industrial equipment, determine a target model ontology file in the industrial meta-model knowledge base according to the industrial demand code;

[0111] According to the target model ontology file, determine the data attribute value of the case class instance name;

[0112] According to the data attribute value, determine the industrial demand task solving result of the industrial equipment, and send the industrial demand task solving result to the industrial equipment.

[0113] In an embodiment, the determining module 40 is further configured to update the case class instance in the initial model ontology file according to the update computing power class instance sent by the computing power equipment, to generate a target model ontology file, wherein the update computing power class instance is generated according to the instance output result and the computing power class instance name after the computing power equipment receives the industrial demand code, the model implementation class instance name and the model input information sent by the industrial equipment, requests the initial ontology file according to the industrial demand code, determines the model implementation class instance in the initial ontology file according to the model implementation class instance name, and determines the instance output result according to the model input information and the model implementation class instance.

[0114] In an embodiment, the determining module 40 is further configured to parse the ontology instance in the industrial meta-model knowledge base, to generate a graph database;

[0115] According to the model label information, determine a process ontology file of the process flow in the graph database;

[0116] According to the process ontology file, realize process visualization of the process flow.

[0117] Since the device adopts all the technical solutions of the above-mentioned embodiments, it at least has all the beneficial effects brought by the technical solutions of the above-mentioned embodiments, which will not be repeated here.

[0118] In addition, the embodiment of the present application further proposes a storage medium, which stores an ontology-based industrial meta-model knowledge representation program, and the ontology-based industrial meta-model knowledge representation program is executed by a processor to realize the steps of the ontology-based industrial meta-model knowledge representation method as described above.

[0119] Since the storage medium adopts all the technical solutions of the above-mentioned embodiments, it at least has all the beneficial effects brought by the technical solutions of the above-mentioned embodiments, which will not be repeated here.

[0120] It should be noted that the above-described workflow is merely illustrative and does not limit the scope of protection of the present application. In actual applications, a person skilled in the art can select part or all of the above-described workflow to achieve the purpose of the embodiment according to actual needs, which is not limited herein.

[0121] In addition, technical details not described in detail in the embodiment can be found in the ontology-based industrial meta-model knowledge representation method provided by any embodiment of the present application, which will not be described here.

[0122] In addition, it should be noted that in this document, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system that includes a list of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent in such a process, method, article or system. Without more limitations, the element defined by the statement "comprises a" does not exclude the presence of additional identical elements in the process, method, article or system that includes the element.

[0123] The above-mentioned embodiment numbers of the present application are only for description, not representing the advantages and disadvantages of the embodiments.

[0124] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and the necessary general hardware platform, of course, it can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, an optical disk) and includes a plurality of instructions for making a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) execute the method described in each embodiment of the present application.

[0125] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. An ontology-based industrial metamodel knowledge representation method, characterized in that, The ontology-based industrial meta-model knowledge representation method comprises: When a model construction instruction of an industrial meta-model is received, a plurality of industrial meta-model knowledge ontologies are constructed in a top-down manner according to a preset industrial meta-model knowledge ontology; Data of the industrial meta-model knowledge ontologies is perfected according to collected industrial model information, and a plurality of model ontology files are generated; An industrial meta-model knowledge base is built according to the plurality of model ontology files; An industrial demand task solving result is determined according to the industrial meta-model knowledge base, industrial demand coding and example class instance name; The industrial demand task solving result is determined according to the industrial meta-model knowledge base, industrial demand coding and example class instance name, which comprises: When industrial demand coding and example class instance name sent by an industrial equipment are received, a target model ontology file is determined in the industrial meta-model knowledge base according to the industrial demand coding; Data attribute values of the example class instance name are determined according to the target model ontology file; An industrial demand task solving result of the industrial equipment is determined according to the data attribute values, and the industrial demand task solving result is sent to the industrial equipment; Before the target model ontology file is determined in the industrial meta-model knowledge base according to the industrial demand coding when the industrial demand coding and example class instance name sent by the industrial equipment are received, the method further comprises: An example class instance in an initial model ontology file is updated according to an updated computing power class instance sent by a computing power equipment, and a target model ontology file is generated, wherein the updated computing power class instance is generated according to the industrial demand coding, the model implementation class instance name and the model input information sent by the industrial equipment, the model implementation class instance in the initial ontology file, the instance output result determined according to the model input information and the model implementation class instance, and the computing power class instance name.

2. The ontology-based industrial metamodel knowledge representation method of claim 1, wherein, The industrial meta-model knowledge ontology is constructed in a top-down manner according to the preset industrial meta-model knowledge ontology, which comprises: The domain range, reuse relationship and hierarchical relationship of the ontology are determined; The basic attributes of the ontology are defined; The industrial meta-model knowledge ontology is constructed according to the domain range, reuse relationship, hierarchical relationship and basic attributes.

3. The ontology-based industrial metamodel knowledge representation method of claim 1, wherein, The data of the industrial meta-model knowledge ontologies is perfected according to the collected industrial model information, and the plurality of model ontology files are generated, which comprises: The industrial model information is processed to obtain integrated model information; The ontology instances of the industrial meta-model knowledge are constructed according to the integrated model information, and the model ontology files are generated; The data of the industrial meta-model knowledge ontologies is perfected according to the ontology instances of the industrial meta-model knowledge, and the plurality of model ontology files are generated.

4. The ontology-based industrial metamodel knowledge representation method of any one of claims 1 to 3, wherein, The industrial meta-model knowledge base is built according to the plurality of model ontology files, which comprises: The identification codes of the industrial meta-model knowledge are obtained; The plurality of model ontology files are named according to the identification codes of the industrial meta-model knowledge, and the plurality of named model ontology files are obtained; According to the plurality of named model ontology files, an industrial meta-model knowledge base is built.

5. The ontology-based industrial metamodel knowledge representation method of any one of claims 1 to 3, wherein, After the industrial demand task solving result is determined according to the industrial meta-model knowledge base, industrial demand coding and example class instance name, the method further includes: The ontology instances in the industrial meta-model knowledge base are parsed to generate a graph database; According to the model label information, a process ontology file of the process flow is determined in the graph database; Process visualization of the process flow is realized according to the process ontology file.

6. An ontology-based industrial metamodel knowledge representation apparatus for performing the ontology-based industrial metamodel knowledge representation method according to any one of claims 1 to 5, characterized in that, The ontology-based industrial meta-model knowledge representation device includes: A construction module is configured to, when a model construction instruction of an industrial meta-model is received, construct a plurality of industrial meta-model knowledge ontologies in a top-down manner according to a preset industrial meta-model knowledge ontology; A perfecting module is configured to perform data perfecting on each industrial meta-model knowledge ontology according to collected industrial model information to generate a plurality of model ontology files; A building module is configured to build an industrial meta-model knowledge base according to the plurality of model ontology files; A determining module is configured to determine an industrial demand task solving result according to the industrial meta-model knowledge base, industrial demand coding and example class instance name.

7. An ontology-based industrial metamodel knowledge representation device, characterized by, The device includes a memory, a processor and an ontology-based industrial meta-model knowledge representation program stored on the memory and executable on the processor, and the ontology-based industrial meta-model knowledge representation program is configured to implement the ontology-based industrial meta-model knowledge representation method in any one of claims 1 to 5.

8. A storage medium, characterized by The storage medium stores an ontology-based industrial meta-model knowledge representation program, and the ontology-based industrial meta-model knowledge representation program is executed by the processor to implement the ontology-based industrial meta-model knowledge representation method in any one of claims 1 to 5.

Images