Data model establishment method and device, and server
By using historical data to establish a data model and combining real-time data optimization, the problems of poor model migration and low real-time data correlation in the existing technology are solved, and the rapid deployment and efficient migration of data models are achieved, and the efficiency of engineering deployment is improved.
Patent Information
- Application Number
- CN202111087999.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-09-16
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2041-09-16
AI Technical Summary
In the prior art, offline modeling of historical data requires a lot of time and poor mobility and continuity. The correlation between real-time data and the model is low, resulting in low efficiency in system model deployment.
By selecting historical running data from the data model library, and using the real-time running data of the target device to adjust and optimize its variable parameters, a data model suitable for the target device is established to achieve rapid deployment and migration of the model .
It improves the model's migration and real-time data correlation, reduces the difficulty of using data models, and improves the efficiency of engineering deployment.
Smart Images

Figure CN113792435B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of big data processing technology, and in particular to a data model establishment method, device and server. Background Art
[0002] With the continuous development of smart building systems, more and more building equipment is connected to the centralized monitoring system, generating a large amount of historical operation data. However, most of the applications that use these historical data currently adopt offline modeling methods, and there are few applications that combine historical data with real-time data.
[0003] Furthermore, offline modeling of historical data often takes a lot of time, and the established model has poor portability and continuity, and there is a functional disconnect between the model and real-time data.
[0004] There is currently no effective solution on how to make full use of historical building data while enabling real-time data to directly participate in model calculation, control and engineering debugging in order to achieve rapid deployment of system models. Summary of the invention
[0005] The embodiments of the present invention provide a data model establishment method, device and server to solve the problems of poor migration of existing models and low correlation with real-time data.
[0006] In one aspect, a method for establishing a data model is provided, comprising:
[0007] Selecting a data model component from a data model library, wherein the data model component is established through historical operation data of a sample device;
[0008] Establishing a binding relationship between the data model component and the target device parameters to obtain the data model component bound to the device parameters;
[0009] The variable parameters of the data model component bound with the device parameters are adjusted according to the real-time operation data of the target device, and the data model component after the variable parameters are adjusted is used as the data model deployed for the target device.
[0010] In one embodiment, selecting a data model component from a data model library includes:
[0011] Receiving a user's selection operation on a data model component through a Web data model configuration interface;
[0012] The data model component selected by the selection operation is used as the data model component selected from the data model library.
[0013] In one embodiment, adjusting the variable parameters of the data model component bound to the device parameters by using the real-time operation data of the target device includes:
[0014] Acquire real-time operation data of the target device;
[0015] Use the data model component bound to device parameters as a sample model;
[0016] Inputting the real-time operation data into the sample model, and performing parameter solving and loop optimization processing on the sample model;
[0017] The parameter values obtained after the cyclic optimization are used as the variable parameters after the sample model is adjusted.
[0018] In one embodiment, after using the data model component after the variable parameter adjustment as the data model deployed for the target device, the method further includes:
[0019] Bind the adjusted variable parameters to the Web data output component;
[0020] Convert the Web data output component bound with the adjusted variable parameters into a Web script;
[0021] The web script is stored in a database.
[0022] In one embodiment, after converting the Web data output component bound with the adjusted variable parameters into a Web script, the method further includes:
[0023] Get the engineering properties of the target device;
[0024] Generate interface parameters according to the project attributes;
[0025] An association relationship between the interface parameters and the Web script is established.
[0026] In one embodiment, the data model library includes at least one of the following data model components: an air conditioning fault diagnosis data model, an air conditioning fault prediction data model, a light strip energy-saving control model, and an air conditioning compressor life prediction model.
[0027] In one embodiment, the variable parameters include at least one of the following: a weight matrix, a number of input units, and a number of output units.
[0028] In another aspect, a data model building device is provided, comprising:
[0029] A selection module is used to select a data model component from a data model library, wherein the data model component is established through historical operation data of a sample device;
[0030] An establishing module, used to establish a binding relationship between the data model component and the target device parameters, and obtain a data model component bound with the device parameters;
[0031] The adjustment module is used to adjust the variable parameters of the data model component bound to the device parameters through the real-time operation data of the target device, and use the data model component after the variable parameters are adjusted as the data model deployed for the target device.
[0032] On the other hand, a server is provided, comprising: the above-mentioned data model building device.
[0033] On the other hand, a network device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.
[0034] On the other hand, a non-volatile computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.
[0035] In the above embodiment, data model components are established through the historical operation data of the sample device. When establishing a data model for the target device, it is only necessary to select these data model components, then perform parameter binding, and then optimize the model parameters based on the real-time operation data of the target data to obtain a data model suitable for the target device. The above solution solves the problems of poor model mobility and low correlation with real-time data, achieves the technical effect of improving model mobility and associating model establishment with real-time operation data, reduces the difficulty of using the data model, and improves the efficiency of engineering deployment. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] The drawings constituting a part of this application are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:
[0037] Figure 1 is a method flow chart of a method for establishing a data model according to an embodiment of the present invention;
[0038] Figure 2 is a schematic diagram of a configuration data model system according to an embodiment of the present invention;
[0039] Figure 3 is a logical schematic diagram of establishing a data model in a data model library according to an embodiment of the present invention;
[0040] Figure 4It is a logical schematic diagram of model migration, online solving and tuning to obtain a usable model according to an embodiment of the present invention;
[0041] Figure 5 is a schematic diagram of establishing a model based on Web components according to an embodiment of the present invention;
[0042] Figure 6 It is a structural block diagram of a data model building device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0043] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments and the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.
[0044] Offline modeling of existing historical data often takes a lot of time, and the established model has poor portability and continuity. There is a problem of functional disconnection between the model and real-time data. In this example, a data model establishment method is provided to realize the configuration processing and model migration of the data model. Specifically, Figure 1 As shown, the following steps are included:
[0045] Step 101: selecting a data model component from a data model library, wherein the data model component is established based on historical operation data of a sample device;
[0046] The data model library may include but is not limited to at least one of the following data model components: air conditioner fault diagnosis data model, air conditioner fault prediction data model, light strip energy-saving control model, and air conditioner compressor life prediction model. Based on the models in the data model library, users can select according to their needs. For example, if they intend to diagnose the fault of the air conditioner, they can select the air conditioner fault diagnosis data model. If they intend to predict the life of the compressor, they can select the air conditioner compressor life prediction model.
[0047] These models can be established based on the historical operation data of sample equipment (such as air conditioners and compressors in sample building equipment). These models can be used as basic models and as the basis for the establishment of subsequent models of similar equipment based on the migration method, so that data models for target equipment can be quickly established.
[0048] Step 102: Establishing a binding relationship between the data model component and the target device parameters, and obtaining the data model component bound with the device parameters;
[0049] For example, after selecting a specific data model, the model may have fixed hyperparameters, such as the number of model layers, the activation function used, etc. The user may bind the devices and parameters participating in the model through a Web data input component (the Web data input component may be a Web data input component based on topo.js). That is, for the server side, a binding relationship between the selected data model component and the target device parameters may be established.
[0050] For example, if the target device is an air conditioner, the target device parameters may include: temperature, humidity, mode, wind speed, ambient temperature, etc.; if the target device is a light strip, the target device parameters may include: number of lights, illumination, ambient brightness, etc.; if the target device is a compressor, the target device parameters may include: rated power, input current, input voltage, etc. That is, these target device parameters are bound to the selected data model components.
[0051] Step 103: adjusting the variable parameters of the data model component bound to the device parameters according to the real-time operation data of the target device, and using the data model component after the variable parameters are adjusted as the data model deployed for the target device.
[0052] For the target device, its real-time operation data can be obtained, and then the variable parameters of the data model components that have been bound to the device parameters can be adjusted through the real-time operation data, that is, the new parameters of the data model are solved and tuned online so that the real-time data model components can be applicable to new scenarios and target devices.
[0053] The variable parameters mentioned above may include but are not limited to at least one of the following: a weight matrix, a number of input units, and a number of output units.
[0054] Specifically, the data model component selected from the data model library may be selected by the user, that is, the server may receive a selection operation of the data model component by the user through the Web data model configuration interface; and use the data model component selected by the selection operation as the data model component selected from the data model library. For example, multiple data model components may be set on the Web interface, and the user may select one of the multiple data model components as the selected data model component by clicking or the like.
[0055] In one embodiment, the variable parameters of the data model component bound to the device parameters are adjusted by the real-time operation data of the target device, which can be obtained by obtaining the real-time operation data of the target device; using the data model component bound to the device parameters as a sample model; inputting the real-time operation data into the sample model, performing parameter solving and loop optimization processing on the sample model; and using the parameter values obtained after the loop optimization as the variable parameters after the sample model is adjusted. That is, the model is optimized by performing online parameter optimization on the model through the real-time operation data of the target device, thereby achieving parameter optimization of the model.
[0056] In order to realize the storage of the finally generated data model, after the data model component after the variable parameters are adjusted is used as the data model deployed for the target device, the adjusted variable parameters can be bound to the Web data output component; the Web data output component bound with the adjusted variable parameters can be converted into a Web script; and the Web script can be stored in the database. Furthermore, after the Web data output component bound with the adjusted variable parameters is converted into a Web script, the engineering properties of the target device can be obtained; interface parameters are generated according to the engineering properties; and an association relationship between the interface parameters and the Web script is established. Among them, the engineering properties can include but are not limited to at least one of the following: engineering address, subsystem, device type, etc. That is, these engineering properties are used as interface parameters, and can be associated with the Web script through foreign keys in the database, thereby realizing flexible calling of the interface.
[0057] In actual implementation, before building a model through historical operation data and optimizing model parameters through real-time operation data, the acquired data can be preprocessed, where the preprocessing operations may include but are not limited to: removing the mean, normalization, and feature dimensionality reduction.
[0058] The above method is described below in conjunction with a specific embodiment. However, it should be noted that this specific embodiment is only for better illustrating the present application and does not constitute an improper limitation on the present application.
[0059] In this example, a configurable data model establishment method is provided to effectively solve the disconnection problem between the functional combination of historical data and real-time data, thereby speeding up the construction and deployment of the project, reducing manpower consumption, and lowering the learning cost and difficulty of model users.
[0060] Specifically, a configuration data model system is provided, which can be used as follows Figure 2As shown, the building equipment is connected to the server through the communication module. For the server, historical data can be obtained, pre-processed to form a historical database, and then model training is performed to obtain a data model library, in which model hyper-variable parameters and model variable parameters are stored.
[0061] The data models in the data model library can be Figure 3 The method shown can be established by obtaining historical data, performing data preprocessing on the obtained historical data, and then training the model to obtain the model's hyperparameters. The hyperparameters may include: model type, number of model layers, number of model units, discriminant function, etc., and a hyperparameter model library is established based on the obtained model hyperparameters.
[0062] After obtaining the model database, model migration can be performed. Model migration refers to the use of the idea of transfer learning to quickly use existing models in new systems for similar problems, building equipment, or usage scenarios. In order to achieve model migration, data preprocessing components, model configuration components, and model evaluation components can be established to obtain a usable model.
[0063] Specifically, model migration, online solving and tuning to obtain a usable model can be done as follows: Figure 4 As shown in the figure, real-time data is obtained, and variable parameters are solved by migrating the model. The variable parameters of the model include: weight matrix, number of input units and number of output units, so as to obtain model components. That is, after migrating the existing model, new parameters are solved and tuned online for the model to make it suitable for new scenarios.
[0064] The device and method provided in this example realizes the configuration creation of complex data models. In the actual implementation process, it mainly depends on the data acquisition server and the data model storage server, which can specifically include the following steps:
[0065] S1: The user enters the Web data model configuration interface and can select the following data model components from the data model library:
[0066] 1) Air conditioning fault diagnosis data model;
[0067] 2) Air conditioning failure prediction data model;
[0068] 3) Light strip energy-saving control model;
[0069] 4) Air conditioning compressor life prediction model.
[0070] S2: After the user selects a specific data model, the model has fixed hyperparameters, such as the number of model layers, the activation function used, etc. Figure 5As shown, the user can bind the devices and parameters participating in the model through the Web data input component (the Web data input component can be a Web data input component based on topo.js), for example:
[0071] 1) Air conditioning unit 1: temperature, humidity, mode, wind speed, ambient temperature, etc.;
[0072] 2) Light strip: number of lights, illumination, ambient brightness, etc.;
[0073] 3) Compressor: rated power, input current, input voltage, etc.
[0074] S3: After the user binds the selected data model with specific equipment and points, the entire system can be started during the engineering commissioning process to adjust the variable parameters of the data model online until the desired effect is achieved.
[0075] S4: After determining the variable parameters of the data model, such as Figure 5 As shown, these parameters are bound to a Web data output component (the Web data output component may be a Web data output component based on topo.js), and are converted into a Web script and stored in a database.
[0076] S5: After completing the above configured binding, the debugging data can be cleared, the configured script can be retained, and provided for interface display and use in the form of a Web interface.
[0077] S6: In the process of converting the above configuration components into Web interfaces, the project attributes in the actual project, such as project address, subsystem, equipment type, etc., can be combined as interface parameters and associated with the Web script through foreign keys in the database, thereby realizing flexible calling of the interface.
[0078] Among them, topo.js refers to a visual Web human-computer interaction plug-in that provides a card-style module interaction method. Web scripts can include script texts such as html, js, and css after the Web component and the data model component are combined.
[0079] The above-mentioned data model configuration refers to combining the general data model with the idea of configured human-computer interaction to provide a configured model building system. Model migration refers to using the idea of transfer learning to quickly use existing models in new systems for similar problems, building equipment, or usage scenarios. Model online solving and tuning refers to migrating existing models to new usage scenarios, and then solving and tuning new parameters for the model online to make it suitable for new scenarios.
[0080] A communication module can be established between building equipment and servers. For example, it can support wired or wireless communication methods such as Ethernet, WiFi, NB-IOT, and 5G.
[0081] In this example, a data preprocessing component may also be set to preprocess the collected data through the data preprocessing component. The main preprocessing may include: removing the mean, normalization, and feature dimensionality reduction.
[0082] In the above example, the data model is configured so that the model can be built once and used for the purpose of migration, and the model can be solved and tuned online. By engineering migration of data models with hyperparameters in different usage scenarios, the difficulty of using data models is reduced and engineering deployment is accelerated.
[0083] Based on the same inventive concept, a data model building device is also provided in the embodiments of the present invention, as described in the following embodiments. Since the principle of solving the problem by the data model building device is similar to that of the data model building method, the implementation of the data model building device can refer to the implementation of the data model building method, and the repeated parts will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived. Figure 6 is a structural block diagram of a data model building device according to an embodiment of the present invention. Figure 6 As shown, it may include: a selection module 601, an establishment module 602 and an adjustment module 603, and the structure is described below.
[0084] A selection module 601 is used to select a data model component from a data model library, wherein the data model component is established through historical operation data of a sample device;
[0085] Establishing module 602, used to establish a binding relationship between the data model component and the target device parameter, and obtain the data model component bound with the device parameter;
[0086] The adjustment module 603 is used to adjust the variable parameters of the data model component bound to the device parameters according to the real-time operation data of the target device, and use the data model component after the variable parameters are adjusted as the data model deployed for the target device.
[0087] In one embodiment, the selection module 601 may specifically receive a selection operation of a data model component by a user through a Web data model configuration interface; and use the data model component selected by the selection operation as a data model component selected from a data model library.
[0088] In one embodiment, the above-mentioned adjustment module 603 can specifically obtain the real-time operation data of the target device; use the data model component bound to the device parameters as a sample model; input the real-time operation data into the sample model, and perform parameter solution and loop optimization processing on the sample model; and use the parameter value obtained after the loop optimization as the variable parameter after the sample model is adjusted.
[0089] In one embodiment, the data model building device can also bind the adjusted variable parameters to the Web data output component after using the data model component after the variable parameters are adjusted as the data model deployed for the target device; convert the Web data output component bound with the adjusted variable parameters into a Web script; and store the Web script in a database.
[0090] In one embodiment, after converting the Web data output component bound to the adjusted variable parameters into a Web script, the data model building device can also obtain the engineering properties of the target device; generate interface parameters based on the engineering properties; and establish an association relationship between the interface parameters and the Web script.
[0091] In one embodiment, the data model library includes at least one of the following data model components: an air conditioning fault diagnosis data model, an air conditioning fault prediction data model, a light strip energy-saving control model, and an air conditioning compressor life prediction model.
[0092] In one embodiment, the variable parameters may include but are not limited to at least one of the following: a weight matrix, a number of input units, and a number of output units.
[0093] In another embodiment, a software is provided, which is used to execute the technical solutions described in the above embodiments and preferred implementation modes.
[0094] In another embodiment, a storage medium is provided, in which the above software is stored. The storage medium includes but is not limited to: a CD, a floppy disk, a hard disk, an erasable memory, etc.
[0095] From the above description, it can be seen that the embodiments of the present invention achieve the following technical effects: by establishing data model components through the historical operation data of the sample device, when establishing a data model for the target device, it is only necessary to select these data model components, then perform parameter binding, and then optimize the model parameters based on the real-time operation data of the target data, and a data model suitable for the target device can be obtained. The above scheme solves the problems of poor model mobility and low correlation with real-time data, and achieves the technical effect of improving model mobility and associating model establishment with real-time operation data, which reduces the difficulty of using the data model and improves the efficiency of engineering deployment.
[0096] Although different specific embodiments are mentioned in the content of this application, this application is not limited to the situations described in the industry standards or embodiments, etc. Some industry standards or slightly modified implementation plans based on the implementation of the custom methods or embodiments can also achieve the same, equivalent or similar, or predictable implementation effects after deformation of the above embodiments. The embodiments of data acquisition, processing, output, judgment methods, etc. after these modifications or deformations can still fall within the scope of the optional implementation plans of this application.
[0097] Although the present application provides method operation steps as described in the embodiments or flow charts, more or less operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiments is only one way of executing the order of many steps and does not represent a unique execution order. When the device or client product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The term "includes", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or equipment including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, product or equipment. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or equipment including the elements.
[0098] The devices or modules described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. For the convenience of description, the above devices are described separately by dividing them into various modules according to their functions. Of course, when implementing this application, the functions of each module can be implemented in the same or more software and / or hardware, or the modules that implement the same function can be implemented by a combination of multiple sub-modules. The device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed.
[0099] Those skilled in the art also know that, in addition to implementing the controller in a purely computer-readable program code, the controller can be made to implement the same function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered as a hardware component, and the devices for implementing various functions included therein can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules for implementing the method and structures within the hardware component.
[0100] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0101] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a mobile terminal, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present application or certain parts of the embodiments.
[0102] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.
[0103] Although the present application has been described through embodiments, those skilled in the art will appreciate that there are many modifications and changes to the present application without departing from the spirit of the present application. It is intended that the attached embodiments include these modifications and changes without departing from the present application.
Claims
1. A method for establishing a data model, characterized in that: include: Selecting a data model component from a data model library, wherein the data model component is established through historical operation data of a sample device; Establishing a binding relationship between the data model component and the target device parameters to obtain the data model component bound to the device parameters; Adjusting the variable parameters of the data model component bound to the device parameters according to the real-time operation data of the target device, and using the data model component after the variable parameters are adjusted as the data model deployed by the target device; After the data model component after the variable parameter adjustment is used as the data model deployed on the target device, the following further includes: Bind the adjusted variable parameters to the Web data output component; Convert the Web data output component bound with the adjusted variable parameters into a Web script; Storing the web script in a database; After converting the Web data output component bound with the adjusted variable parameters into a Web script, it also includes: Get the engineering properties of the target device; Generate interface parameters according to the project attributes; An association relationship between the interface parameters and the Web script is established.
2. The method according to claim 1, characterized in that Select data model components from the data model library, including: Receiving a user's selection operation on a data model component through a Web data model configuration interface; The data model component selected by the selection operation is used as the data model component selected from the data model library.
3. The method according to claim 1, characterized in that Adjusting the variable parameters of the data model component bound to the device parameters according to the real-time operation data of the target device includes: Acquire real-time operation data of the target device; Use the data model component bound to device parameters as a sample model; Inputting the real-time operation data into the sample model, and performing parameter solving and loop optimization processing on the sample model; The parameter values obtained after the cyclic optimization are used as the variable parameters after the sample model is adjusted.
4. The method according to claim 1, characterized in that: The data model library includes at least one of the following data model components: an air conditioning fault diagnosis data model, an air conditioning fault prediction data model, a light strip energy-saving control model, and an air conditioning compressor life prediction model.
5. The method according to claim 1, characterized in that The variable parameters include at least one of the following: a weight matrix, a number of input units, and a number of output units.
6. A data model building device, characterized in that: include: A selection module is used to select a data model component from a data model library, wherein the data model component is established through historical operation data of a sample device; An establishing module, used to establish a binding relationship between the data model component and the target device parameters, and obtain a data model component bound with the device parameters; An adjustment module is used to adjust the variable parameters of the data model component bound to the device parameters through the real-time operation data of the target device, and use the data model component after the variable parameters are adjusted as the data model deployed by the target device; after using the data model component after the variable parameters are adjusted as the data model deployed by the target device, it also includes: binding the adjusted variable parameters to the Web data output component; converting the Web data output component bound to the adjusted variable parameters into a Web script; storing the Web script in a database; after converting the Web data output component bound to the adjusted variable parameters into a Web script, it also includes: acquiring the engineering properties of the target device; generating interface parameters according to the engineering properties; and establishing an association relationship between the interface parameters and the Web script.
7. A server, comprising: The data model building device as described in claim 6.
8. A network device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 5 when executing the computer program.
9. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.
Citation Information
Patent Citations
Algorithm middle station construction method and system
CN112507623A
Online fault diagnosis method for rolling bearing under variable load based on transfer learning
CN112964469A
