An industrial equipment key parameter mining method, device and medium

Abstract

The application discloses an industrial equipment key parameter mining method, device and medium, and the method comprises the following steps: determining the reference times of each industrial model in an industrial model database within a preset period; searching for a reference frequency level corresponding to the reference times in a mapping relationship table; determining an industrial model with a reference frequency level exceeding a preset level threshold as a to-be-mined industrial model; searching for the to-be-mined industrial model with a parameter correlation relationship in an industrial model correlation graph, and determining the to-be-mined industrial model with the parameter correlation relationship as a key industrial model; taking an industrial equipment parameter with a correlation relationship in the key industrial model as an industrial equipment key parameter; and generating an attention level of the industrial equipment key parameter according to the reference frequency level of the key industrial model. The method can discover problems of the industrial equipment key parameter in a timely manner, and effectively monitor the industrial equipment with the least monitoring workload.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to an industrial equipment key parameter mining method, device and medium. BACKGROUND

[0002] An industrial model is an important component of an industrial internet platform. Through the design and development of professional data models and algorithm combinations, a specific industrial data input is calculated and processed to output industrial control related parameters. The industrial model collects professional knowledge such as principles, theorems and laws in the production process of the industrial field, and combines actual industrial production experience to form a mechanism and build an industrial model, which is embedded in the industrial internet platform. The industrial model refines and encapsulates industrial experience knowledge, is located in the industrial internet platform layer (industrial PaaS layer), and serves as the core competitive ability of the industrial internet platform.

[0003] Currently, in the process of monitoring the operation of industrial equipment, the collected equipment data is analyzed by an industrial model in an industrial model library to determine whether the operation of the industrial equipment is abnormal. Due to different business needs of the industrial equipment, different industrial models or combinations of industrial models are required, and the importance of the business needs is different, and the importance of each industrial model is also different. However, each industrial model works independently, and the islands are serious. The current does not mine the relationship between the industrial models, so that in the process of monitoring, the industrial models are not divided into different importance, and the characteristic parameters of the industrial equipment are not divided into different importance. For example, if a characteristic parameter combination A is an input parameter of multiple industrial models, it means that the characteristic parameter combination A affects multiple businesses of the industrial equipment, and if the parameter value of the characteristic parameter combination A is problematic, it will cause the industrial equipment to have a higher degree of problems, and the monitoring of the characteristic parameter combination A is relatively important and more critical.

[0004] Therefore, there is an urgent need for an industrial equipment key parameter mining method to efficiently monitor the industrial equipment. SUMMARY

[0005] The embodiments of the present application provide an industrial equipment key parameter mining method, device and medium, which are used to solve the problem of the urgent need for an industrial equipment key parameter mining method to efficiently monitor the industrial equipment.

[0006] The embodiments of the present application adopt the following technical solutions:

[0007] In one aspect, the embodiments of the present application provide an industrial equipment key parameter mining method, which comprises: determining the reference times of each industrial model in an industrial model database within a preset period; retrieving the reference frequency level corresponding to the reference times in a pre-constructed mapping relationship table; determining the industrial model with a reference frequency level exceeding a preset level threshold as a to-be-mined industrial model; finding the to-be-mined industrial model having a parameter correlation relationship in a pre-constructed industrial model correlation graph, and determining the to-be-mined industrial model having the parameter correlation relationship as a key industrial model; taking the industrial equipment parameter having a correlation relationship in the industrial equipment parameter of the key industrial model as an industrial equipment key parameter; and generating an attention level of the industrial equipment key parameter according to the reference frequency level of the key industrial model, wherein the higher the reference frequency level is, the higher the attention level is.

[0008] In one example, before the determination of the reference times of each industrial model in the industrial model database, the method further comprises: creating an industrial model database of an industrial equipment, and obtaining the industrial model of the industrial equipment from the industrial model database; calling a general industrial model identification registration template of the industrial equipment, filling the general industrial model identification registration template according to attribute information of the industrial model, and generating an identification registration template of the industrial model; the attribute information of the industrial model comprises a model name, a model characteristic parameter, a model use description, and a model classification; registering the identification registration template to an identification analysis node to generate a unique identification of the industrial model; associating the unique identification with the industrial model in the industrial model database; and generating an external reference API interface of the industrial model, and referencing the industrial model according to the unique identification and the external reference API interface.

[0009] In one example, after the association of the unique identification with the industrial model in the industrial model database, the method further comprises: taking a unique identification field as a primary key in the industrial model database, generating an industrial model data table according to attribute information of each industrial model, and displaying the industrial model data table to a reference party with authority.

[0010] In one example, the referencing of the industrial model according to the unique identification and the external reference API interface specifically comprises: receiving a reference request for the industrial model through the external reference API interface; the reference request comprises the unique identification; performing an identification analysis request to the identification analysis node according to the reference request to analyze the unique identification; and referencing the industrial model after successful analysis.

[0011] In one example, after the unique identification field is taken as the primary key and the industrial model data table is generated according to the attribute information of each industrial model, the method further comprises: creating an industrial model statistical analysis table template of the industrial model database; the fields of the industrial model statistical analysis table template include reference times, reference enterprises, and reference industries; in a preset period, statistical analysis data of each industrial model is counted, the statistical analysis data including reference times, reference enterprises, and reference industries; the industrial model statistical analysis table template is filled according to the statistical analysis data, and an industrial model statistical analysis table of the industrial model database is generated.

[0012] In one example, before the industrial model to be mined having a correlation relationship is found in the pre-constructed industrial model correlation graph, the method further comprises: determining industrial equipment parameters required to be input for each industrial model in the industrial model database; determining industrial models having coinciding industrial equipment parameters as industrial models having a correlation relationship; the higher the degree of coincidence of industrial equipment parameters between industrial models, the higher the correlation degree between the industrial models; and constructing a relationship graph composed of multiple industrial model nodes and multiple correlation edges between the industrial model nodes.

[0013] In one example, the generating of the attention level of the industrial equipment key parameter according to the reference frequency level of the key industrial model specifically comprises: determining a first reference frequency level of a first key industrial model and a second reference frequency level of a second key industrial model; matching the first reference frequency level and the second reference frequency level in a pre-constructed level mapping relationship table to generate the attention level of the industrial equipment key parameter.

[0014] In one example, after the attention level of the industrial equipment key parameter is generated according to the reference frequency level of the key industrial model, the method further comprises: collecting industrial equipment key parameters of each key industrial model to obtain a collection set; counting the number of occurrences of each industrial equipment key parameter in the collection set; and compensating the attention level of the industrial equipment key parameter according to the number; the higher the number, the higher the degree of compensation, and the compensation value is greater than 0.

[0015] In another aspect, an embodiment of the present application provides an industrial equipment key parameter mining device, comprising: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: determine a reference frequency level corresponding to the reference times in a pre-constructed mapping relationship table; determine a to-be-mined industrial model as an industrial model whose reference frequency level exceeds a preset level threshold; find, in a pre-constructed industrial model association graph, the to-be-mined industrial model having a parameter association relationship, and determine the to-be-mined industrial model having the parameter association relationship as a key industrial model; determine, in industrial equipment parameters of the key industrial model, an industrial equipment parameter having an association relationship as an industrial equipment key parameter; and generate a focus level of the industrial equipment key parameter according to the reference frequency level of the key industrial model, and the higher the reference frequency level, the higher the focus level.

[0016] In another aspect, an embodiment of the present application provides an industrial equipment key parameter mining nonvolatile computer storage medium, which stores computer executable instructions, and the computer executable instructions are configured to: determine a reference frequency level corresponding to the reference times in a pre-constructed mapping relationship table; determine a to-be-mined industrial model as an industrial model whose reference frequency level exceeds a preset level threshold; find, in a pre-constructed industrial model association graph, the to-be-mined industrial model having a parameter association relationship, and determine the to-be-mined industrial model having the parameter association relationship as a key industrial model; determine, in industrial equipment parameters of the key industrial model, an industrial equipment parameter having an association relationship as an industrial equipment key parameter; and generate a focus level of the industrial equipment key parameter according to the reference frequency level of the key industrial model, and the higher the reference frequency level, the higher the focus level.

[0017] The above at least one technical solution adopted by the embodiments of the present application can achieve the following beneficial effects:

[0018] By creating an industrial model association graph based on parameter association relationships, the industrial models that meet the user's business requirements and are relatively important to the user, i.e., key industrial models, are mined in combination with the reference times of each industrial model, and the key parameters that simultaneously affect multiple key industrial models are further mined, and it is simultaneously indicated that the key parameters are relatively important to the industrial equipment, so that the key parameters are given a higher degree of attention, and problems of key parameters of the industrial equipment can be found in time, and the industrial equipment can be more effectively monitored with minimal monitoring workload. That is, abnormal conditions of the industrial equipment can be efficiently and timely found and an alarm can be issued, and the problems of monitoring, unattended operation and data collection of the industrial equipment are solved, and the severity of problems of the industrial equipment is reduced as much as possible. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the present application, some embodiments of the present application will be described in detail below with reference to the accompanying drawings, in which:

[0020] Figure 1 A flowchart of an industrial equipment key parameter mining method provided by an embodiment of the present application is shown.

[0021] Figure 2 A framework diagram of an industrial equipment key parameter mining system provided by an embodiment of the present application is shown.

[0022] Figure 3 A capability description diagram of an industrial model provided by an embodiment of the present application is shown.

[0023] Figure 4 A structural diagram of an industrial equipment key parameter mining device provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0024] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described in detail below with reference to specific embodiments and corresponding drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0025] Some embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0026] Figure 1 A flowchart of an industrial equipment key parameter mining method provided by an embodiment of the present application is shown. Some input parameters or intermediate results in the flow allow manual intervention to adjust to help improve accuracy.

[0027] The implementation of the analysis method related to the embodiments of the present application can be a terminal device or a server, and the present application does not make special limitations thereon. For the convenience of understanding and description, the following embodiments are described in detail taking the server as an example.

[0028] It should be noted that the server can be a single device, or a system composed of multiple devices, i.e., a distributed server, and the present application does not make specific limitations thereon.

[0029] Figure 1 The flow in the above embodiment can include the following steps:

[0030] S101: In a preset period, determine the reference times of each industrial model in the industrial model database.

[0031] In some embodiments of the present application, a unique identification is given to each industrial model through identification analysis system, so that the industrial model can be statistically analyzed based on the unique identification. For example, an enterprise A creates an industrial model library so that multiple other enterprises can reference the industrial model. In order to more efficiently and accurately distinguish the industrial model, it is necessary to give the industrial model a customized identity through unique identification.

[0032] The identification analysis system is the nerve center supporting the interconnection of the industrial internet, and is also the key core facility driving the innovation and development of the industrial internet. Its role is similar to that of the domain name resolution system (DNS) in the Internet field. The identification is a string composed of numbers, letters, symbols, etc. in a certain rule, which is used to identify the name mark of different goods, entities, and Internet of Things objects. The identification analysis technology refers to the process of mapping the object identification to the information required by the actual information service, such as address, goods, spatial location, etc. For example, by analyzing the identification of a certain object, the server address storing its associated information can be obtained.

[0033] Based on this, first, an industrial model database of industrial equipment is created, and the industrial model of the industrial equipment is obtained from the industrial model database.

[0034] Then, the general industrial model identification registration template of the industrial equipment is called, and the general industrial model identification registration template is filled according to the attribute information of the industrial model to generate the identification registration template of the industrial model.

[0035] The attribute information of the industrial model includes model name, model characteristic parameter, model purpose description, model classification, model formula, model fitting degree, etc.

[0036] It should be noted that the general industrial model identification registration template is in the form of a library table, and the table fields of the general industrial model identification registration template are attribute information, such as fields including model name, model characteristic parameter, model use description, model classification, model formula, model fitting degree, etc.

[0037] Then, the identification registration template is registered to the identification analysis node to generate a unique identification of the industrial model.

[0038] Then, in the industrial model database, the unique identification is associated with the industrial model.

[0039] Finally, an external reference API interface of the industrial model is generated, and the industrial model is referenced according to the unique identification and the external reference API interface.

[0040] In some embodiments of the present application, for the unique identification of each industrial model, an industrial model data table of the industrial model is generated, so that it is more convenient for users to view the related information of the industrial model.

[0041] Based on this, in the industrial model database, the unique identification field is used as the primary key, and an industrial model data table is generated according to the attribute information of each industrial model, so as to display the industrial model data table to the reference party with authority.

[0042] Therefore, the reference party can obtain the unique identification of the industrial model by accessing the industrial model data table.

[0043] Based on this, when the industrial model is referenced, the reference request for the industrial model is received through the external reference API interface. The reference request includes the unique identification.

[0044] Then, according to the reference request, an identification analysis request is sent to the identification analysis node to analyze the unique identification. Finally, after successful analysis, the industrial model is referenced.

[0045] In some embodiments of the present application, based on the identification analysis system, the use of the industrial model can be statistically analyzed.

[0046] Specifically, first, an industrial model statistical analysis table template of the industrial model database is created. The fields of the industrial model statistical analysis table template include reference times, reference enterprises, and reference industries.

[0047] Then, within a preset period, statistical analysis data of each industrial model is counted, including reference times, reference enterprises, and reference industries.

[0048] Finally, the industrial model statistical analysis table template is filled according to the statistical analysis data to generate an industrial model statistical analysis table of the industrial model database.

[0049] It can be understood that the application implements an identification registration template creation function supporting industrial models, and supports registration of attribute information of the industrial models to an identification resolution node, thereby realizing a synchronous identification registration function of various industrial models, including but not limited to an external API model, a custom mathematical model, a machine learning algorithm model, and the like. The application also supports generation of an external reference API interface, realizes identification resolution of an industrial model application scenario, and when the external reference API interface is called and parameters are passed, synchronously calls an identification resolution interface to perform identification resolution of the industrial model. The application realizes an industrial model identification registration and resolution data statistical summary function according to an industry, a type, an enterprise, a reference frequency, and the like, and realizes real-time statistical analysis of an industrial model application frequency and model effectiveness.

[0050] The parameter attribute of the industrial model is registered to the identification resolution node, and main information includes but is not limited to a model name, a model classification (industry classification, field classification, business use range and product life cycle classification, application scenario classification, and the like), a model use description (function), a model principle, a model attribution, a model input parameter, a model formula, a model output parameter (meaning, example), a model version, a running environment, and a model application effect.

[0051] The industrial model is connected to the external reference API interface, and record interface addresses, calling manners, and output types are set, and parameter name, parameter type, parameter meaning, and parameter default value are configured as input parameter information. Through automatic execution of running tests, it is verified whether the industrial model is normally running. The custom mathematical model has built-in mathematical functions, including commonly used shortcut calculations such as summation, average value, maximum value, minimum value, variance, and the like, built-in trigonometric functions such as COS(X), SIN(X), TAN(X), and the like, built-in basic mathematical operators and other commonly used mathematical formulas, and provides mathematical operation formulas created by the user according to industrial production. The machine learning can automatically fit functions according to provided basic data and selected algorithm types, and supports fitting degree evaluation indexes such as mean squared error (MSE), decision coefficient regression score function (R2 Score), mean absolute percentage error (MAE), and explainable variance (EV), and can judge fitting effects according to the indexes.

[0052] S102: In the pre-constructed mapping relationship table, the reference frequency level corresponding to the reference frequency is searched.

[0053] It should be noted that the mapping relationship table includes a corresponding relationship between the reference frequency and the reference frequency level.

[0054] S103: The industrial model with a reference frequency level exceeding a preset level threshold is determined as a to-be-mined industrial model.

[0055] The higher the reference frequency level is, the more important the industrial model is to the enterprise and the more in line with the business needs.

[0056] S104: In the pre-constructed industrial model association graph, find the to-be-mined industrial model having a parameter association relationship, and determine the to-be-mined industrial model having the parameter association relationship as a key industrial model.

[0057] In some embodiments of the present application, an industrial model association graph needs to be pre-constructed.

[0058] Specifically, first, determine the industrial equipment parameters required to be input by each industrial model in the industrial model database.

[0059] Then, determine the industrial models having coinciding industrial equipment parameters as industrial models having an association relationship.

[0060] The higher the coincidence degree of the industrial equipment parameters between the industrial models is, the higher the association degree between the industrial models is.

[0061] Then, construct a relationship graph composed of a plurality of industrial model nodes and a plurality of association edges between the industrial model nodes.

[0062] S105: In the industrial equipment parameters of the key industrial model, determine the industrial equipment parameters having an association relationship as industrial equipment key parameters.

[0063] S106: According to the reference frequency level of the key industrial model, generate an attention level of the industrial equipment key parameters, and the higher the reference frequency level is, the higher the attention level is.

[0064] In some embodiments of the present application, for different reference frequency levels, different colors are set in the industrial model association graph, and the deeper the color is, the higher the reference frequency level is, so that the reference party can intuitively find the key industrial model having a higher reference frequency, and the attention level of the industrial equipment key parameters is notified to the reference party, so that the reference party can timely pay attention to the key parameters of the monitored industrial equipment.

[0065] In some embodiments of the present application, first, determine a first reference frequency level of a first key industrial model and a second reference frequency level of a second key industrial model.

[0066] Then, in the pre-constructed level mapping relationship table, match the first reference frequency level and the second reference frequency level to generate an attention level of the industrial equipment key parameters.

[0067] It should be noted that the level mapping relationship table includes a corresponding relationship between different reference frequency level combinations and attention levels.

[0068] In some embodiments of the present application, since each two key industrial models in the industrial model association graph have corresponding industrial equipment key parameters, that is, the A industrial equipment key parameter is an input parameter of the A key industrial model and an input parameter of the B key industrial model.

[0069] Further, different key industrial model combinations can have overlapping industrial equipment key parameters, for example, the A and B industrial equipment key parameters are input parameters of the C key industrial model and input parameters of the D key industrial model.

[0070] At this time, the A industrial equipment key parameter is not only related to the A and B key industrial models, but also related to the C and D key industrial models. Therefore, the A industrial equipment key parameter is more important than the B industrial equipment key parameter.

[0071] It should be noted that at this time, the a reference party may monitor all industrial equipment of the b factory, and the A key industrial model and the B key industrial model need to be used.

[0072] It can also be that the a reference party monitors all industrial equipment of the b factory through the A key industrial model, and the c reference party monitors all industrial equipment of the d factory through the B key industrial model.

[0073] However, since it is monitoring of industrial equipment, even if the a reference party does not use the B key industrial model at this time, it is still more likely to use the B key industrial model, and therefore, the B key industrial model can become important to the a reference party in the future. Similarly, even if the c reference party does not use the A key industrial model at this time, it is still more likely to use the A key industrial model, and therefore, the A key industrial model can become important to the c reference party in the future. Therefore, for the a and c reference parties to monitor industrial equipment, the industrial equipment key parameters are relatively important.

[0074] Based on this, the industrial equipment key parameters of each key industrial model are summarized to obtain a summary set. In the summary set, the number of occurrences of each industrial equipment key parameter is counted. According to the number, the attention level of the industrial equipment key parameter is compensated. The higher the number, the higher the compensation, and the compensation value is greater than 0.

[0075] In some embodiments of the present application, after the industrial equipment key parameters are screened out, the device parameter values of the industrial equipment key parameters can be obtained from the reference party, so as to analyze the device parameter values according to a preset rule to determine whether an abnormality occurs.

[0076] By identifying the attribute characteristics of the industrial model associated with the system, the industrial model associated graph is formed, for example, an industrial model corresponds to n characteristic parameters, n docking applications, n enterprises, and each characteristic parameter is applied to n models, n applications, n enterprises, each application, and each enterprise is analogous. Thus, by mining and analyzing various relationships of the industrial model, the value chain hidden in the application degree behavior of the industrial model is found, and intuitive legend display is performed.

[0077] Industrial model characteristic parameters are mostly complex nonlinear relationships. By analyzing key industrial models and key characteristic parameters through industrial model association graph, integrating enterprise multi-source heterogeneous data, forming statistical analysis data table view, and comprehensively mining data value.

[0078] In addition, combined with the attribute information of the industrial model, the industrial model is uniquely identified using identification analysis technology. When the citing party cites the unique industrial model, the model characteristic parameters (industrial equipment parameters) input for the industrial model can be accurately obtained, the operation of the industrial equipment can be summarized, and data summary and analysis based on big data can be performed based on the collected data.

[0079] It should be noted that although the embodiments of the present application are introduced and described in sequence with reference to Figure 1 steps S101 to S106, this does not mean that steps S101 to S106 must be executed in strict sequence. The embodiments of the present application introduce and describe steps S101 to S106 in sequence as shown in Figure 1 in order to facilitate understanding of the technical solutions of the embodiments of the present application by those skilled in the art. In other words, in the embodiments of the present application, the sequence between steps S101 to S106 can be adjusted as needed.

[0080] By Figure 1 the method, by creating an industrial model association graph based on parameter association relationships, the key industrial models that meet the user's business needs and are relatively important to the user are mined by combining the number of citations of each industrial model, that is, key industrial models, and the key parameters that simultaneously affect multiple key industrial models are further mined, and it is simultaneously indicated that the key parameters are also relatively important to the industrial equipment, thereby giving the key parameters a higher degree of attention, so that problems of key parameters of industrial equipment can be found in time, and the industrial equipment can be more effectively monitored with minimal monitoring effort. That is, it can timely discover abnormal conditions of industrial equipment operation and issue an alarm, solve the problems of monitoring, unattended operation and data collection of industrial equipment, minimize the severity of problems of industrial equipment, and effectively reduce personnel expenses, avoiding waste of manpower and material resources.

[0081] Figure 2 A framework schematic diagram of an industrial equipment key parameter mining system provided by an embodiment of the present application.

[0082] In Figure 2 , the functions of the data template module include template type, template creation, template query, and template deletion.

[0083] The functions of the model management module include API model, mathematical model, machine learning, execution test, generation of interfacing API, and identification registration. Industrial model creation and identification analysis registration are performed through the model management function.

[0084] The functions of the model application module include model application and identification analysis. Identification analysis is performed through the model application function.

[0085] The functions of the identification data statistics module include identification registration quantity, identification analysis quantity, industry dimension, enterprise dimension, model type, and model application times (reference times). Analysis of model reference times, reference frequency, and model effectiveness of industrial models according to industry, enterprise, and other dimensions is performed through the identification data statistics function.

[0086] The functions of the correlation graph module include data integration, entity extraction, relationship extraction, attribute extraction, event extraction, entity alignment, data processing, and visual display. Industrial model attribute correlation is formed into a data graph and relationship mining analysis is performed through the correlation graph function.

[0087] Based on Figure 2 the system, Figure 3 a capability description schematic diagram of an industrial model provided by an embodiment of the present application.

[0088] In Figure 3 , the information of the industrial model includes model name, model classification, model function, model principle, model ownership, model version, running environment, and model application effect.

[0089] The working principle is as follows: the industrial model obtains model input parameters (independent variable 1, independent variable 2, independent variable 3, and independent variable 4), and then obtains model output parameters (dependent variable 1, dependent variable 2, dependent variable 3, and dependent variable 4) through theorems, laws, algorithms, data models, principles, and other capabilities of the industrial model.

[0090] Based on the same idea, some embodiments of the present application also provide a device and a non-volatile computer storage medium corresponding to the above method.

[0091] Figure 4 A structural schematic diagram of an industrial equipment key parameter mining device provided by an embodiment of the present application, comprising:

[0092] at least one processor; and

[0093] a memory in communication connection with the at least one processor; wherein

[0094] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0095] determine the number of references of each industrial model in the industrial model database within a preset period;

[0096] retrieve the reference frequency level corresponding to the number of references in the pre-constructed mapping relationship table;

[0097] determine the industrial model whose reference frequency level exceeds a preset level threshold as a to-be-mined industrial model;

[0098] find the to-be-mined industrial model having a parameter correlation relationship in the pre-constructed industrial model correlation graph, and determine the to-be-mined industrial model having the parameter correlation relationship as a key industrial model;

[0099] industrial equipment key parameters having a correlation relationship in the industrial equipment parameters of the key industrial model;

[0100] generate an attention level of the industrial equipment key parameters according to the reference frequency level of the key industrial model, and the higher the reference frequency level, the higher the attention level.

[0101] Some embodiments of the present application provide a non-volatile computer storage medium for mining industrial equipment key parameters, which stores computer executable instructions, and the computer executable instructions are configured to:

[0102] determine the number of references of each industrial model in the industrial model database within a preset period;

[0103] retrieve the reference frequency level corresponding to the number of references in the pre-constructed mapping relationship table;

[0104] determine the industrial model whose reference frequency level exceeds a preset level threshold as a to-be-mined industrial model;

[0105] find the to-be-mined industrial model having a parameter correlation relationship in the pre-constructed industrial model correlation graph, and determine the to-be-mined industrial model having the parameter correlation relationship as a key industrial model;

[0106] industrial equipment key parameters having a correlation relationship in the industrial equipment parameters of the key industrial model;

[0107] According to a reference frequency level of the key industrial model, a concern level of the key parameter of the industrial equipment is generated, and the higher the reference frequency level is, the higher the concern level is.

[0108] The embodiments in the present application are described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment mainly describes the difference from other embodiments. Especially, the device and medium embodiments are described simply because they are basically similar to the method embodiments, and the related parts can be referred to the description of the method embodiments.

[0109] The device and medium provided by the embodiments in the present application are one-to-one corresponding to the method, and therefore, the device and medium also have the similar beneficial technical effects as the method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the device and medium will not be described here.

[0110] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0111] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device implemented in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the function specified by the one or more blocks.

[0112] These computer program instructions can also be stored in a computer-readable memory capable of causing the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction means, which implements the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0113] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 Figure 1

[0114] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0115] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the processor can execute instructions. The memory can also include non-volatile memory, such as read only memory (ROM), electrically programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), erasable programmable read only memory (EPROM), flash memory, or a combination of non-volatile memories in different types. The memory is an example of computer readable storage media.

[0116] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to computing devices. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0117] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to encompass a non-exclusive inclusion, such that a process, method, article or apparatus that comprises a list of elements does not include only those elements recited, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without further limitation, an element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0118] ​​The above merely provides an example of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. within the technical principles of the present application should fall into the protection scope of the present application.

Claims

1. A method for mining key parameters of industrial equipment, characterized in that, The method includes: Within a preset period, determine the number of references for each industrial model in the industrial model database; In a pre-built mapping table, retrieve the reference frequency level corresponding to the number of references; Industrial models whose citation frequency level exceeds the preset level threshold are identified as industrial models to be explored. In the pre-constructed industrial model association map, find the industrial models to be explored that have parameter association relationships, and identify the industrial models to be explored that have parameter association relationships as key industrial models; Among the industrial equipment parameters in the key industrial model, those with correlation are designated as key industrial equipment parameters. Based on the reference frequency level of the key industrial model, the attention level of the key parameters of the industrial equipment is generated; the higher the reference frequency level, the higher the attention level. Before searching for industrial models with related relationships in a pre-constructed industrial model association map, the method further includes: Determine the industrial equipment parameters that need to be input for each industrial model in the industrial model database; Industrial models with overlapping industrial equipment parameters are identified as having an association relationship; the higher the degree of overlap of industrial equipment parameters between industrial models, the higher the degree of association between the industrial models. Construct a relational graph consisting of multiple industrial model nodes and the associated edges between them; The step of generating the attention level of key parameters of the industrial equipment based on the citation frequency level of the key industrial model specifically includes: Determine the first reference frequency level of the first key industry model and the second reference frequency level of the second key industry model; In a pre-built hierarchy mapping table, the first reference frequency level and the second reference frequency level are matched to generate the attention level of the key parameters of the industrial equipment. After generating the attention level of the key parameters of the industrial equipment based on the citation frequency level of the key industrial model, the method further includes: The key parameters of industrial equipment in each key industrial model are summarized to obtain a summary set; In the aggregated set, the frequency of occurrence of key parameters for each industrial device is counted; The level of attention for the key parameters of the industrial equipment is compensated based on the number of times ...

2. The method according to claim 1, characterized in that, Before determining the number of references for each industrial model in the industrial model database, the method further includes: Create an industrial model database for industrial equipment, and retrieve the industrial models of the industrial equipment from the industrial model database; The general industrial model identifier registration template of the industrial equipment is invoked, and the general industrial model identifier registration template is filled in according to the attribute information of the industrial model to generate the identifier registration template of the industrial model; the attribute information of the industrial model includes model name, model feature parameters, model purpose description, and model classification; Register the identifier registration template to the identifier resolution node to generate a unique identifier for the industrial model; In the industrial model database, the unique identifier is associated with the industrial model; Generate an external reference API interface for the industrial model, and reference the industrial model based on the unique identifier and the external reference API interface.

3. The method according to claim 2, characterized in that, After associating the unique identifier with the industrial model in the industrial model database, the method further includes: In the industrial model database, a unique identifier field is used as the primary key. Based on the attribute information of each industrial model, an industrial model data table is generated to display the industrial model data table to authorized users.

4. The method according to claim 3, characterized in that, The step of referencing the industrial model based on the unique identifier and the external API interface specifically includes: The system receives a reference request for the industrial model through the external reference API interface; the reference request includes the unique identifier. Based on the reference request, an identifier resolution request is sent to the identifier resolution node to resolve the unique identifier; After successful parsing, the industrial model is referenced.

5. The method according to claim 3, characterized in that, After generating an industrial model data table based on the attribute information of each industrial model, using the unique identifier field as the primary key, the method further includes: Create an industrial model statistical analysis table template for the industrial model database; the fields of the industrial model statistical analysis table template include citation count, citing company, and citing industry; Within a preset period, statistical analysis data for each industrial model is collected, including the number of citations, citing companies, and citing industries. The industrial model statistical analysis table template is populated with the statistical analysis data to generate the industrial model statistical analysis table of the industrial model database.

6. A key parameter mining device for industrial equipment, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method for mining key parameters of industrial equipment as described in any one of claims 1-5.

7. A non-volatile computer storage medium for mining key parameters of industrial equipment, storing computer-executable instructions, characterized in that, The computer-executable instructions are configured to execute the method for mining key parameters of industrial equipment as described in any one of claims 1-5.

Images