A data-driven method, device, and medium for creating industrial mechanism models.

Abstract

This application provides a data-driven method, equipment, and medium for creating industrial mechanism models. The method generates corresponding data models based on preset production management elements. The data models include model parameter identifiers, model parameter values, model parameter types, and model data formats. Based on process configuration information from a user terminal and the data model, custom model data combination information is determined. The process configuration information includes at least: intermediate process indicators, indicator formulas, and indicator formula calculation frequencies. Based on the mechanism model corresponding to the custom model data combination information, production forecast data corresponding to the industrial production data is determined, and the production forecast data is sent to the corresponding monitoring terminal. The mechanism model is updated based on the operation of the monitoring terminal and / or the actual production data corresponding to the production forecast data.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a data-driven method, apparatus and medium for creating industrial mechanism models. Background Technology

[0002] Mechanism models, also known as white-box models, are precise mathematical models established based on the internal mechanisms of an object, production process, or the transmission mechanisms of material flow. They are mathematical models of objects or processes derived from mass balance equations, energy balance equations, momentum balance equations, phase balance equations, as well as certain physical property equations, chemical reaction laws, and fundamental circuit laws. The advantage of mechanism models is that their parameters have very clear physical meanings.

[0003] However, current mechanistic models are implemented in various ways, and enterprises can only use certain prescribed standards for constraint when using them, resulting in a high degree of customization. This limits the richness of mechanistic models, making it difficult for different industries to implement and reuse them, and raising the barrier to entry for their use. Summary of the Invention

[0004] To address the aforementioned technical problems, embodiments of this application provide a data-driven method, apparatus, and medium for creating industrial mechanism models.

[0005] On the one hand, embodiments of this application provide a data-driven method for creating industrial mechanism models, the method comprising:

[0006] Based on preset production management elements, a corresponding data model is generated; wherein, the data model includes model parameter identifiers, model parameter values, model parameter types, and model data formats;

[0007] Based on the process configuration information from the user terminal and the data model, the custom model data combination information is determined; wherein, the process configuration information includes at least: intermediate process indicators, indicator formulas, and indicator formula calculation frequency;

[0008] Based on the mechanism model corresponding to the data combination information of the custom model, determine the production forecast data corresponding to the industrial production collection data, and send the production forecast data to the corresponding monitoring terminal;

[0009] The mechanism model is updated based on the operation of the monitoring terminal and / or the actual production data corresponding to the production forecast data.

[0010] In one implementation of this application, production forecast data corresponding to industrial production collection data is determined based on a mechanistic model corresponding to the custom model data combination information, specifically including:

[0011] Acquire industrial production data from industrial data acquisition equipment and input the industrial production data into the mechanism model;

[0012] The output of the mechanistic model is used as the production forecast data.

[0013] In one implementation of this application, the method further includes:

[0014] When the industrial production data collected by the industrial data acquisition device is updated, the production forecast data corresponding to the updated industrial production data is determined to be the production forecast data to be updated.

[0015] Compare the production forecast data to be updated with the production forecast data of the previous period;

[0016] If the comparison result between the production forecast data to be updated and the production forecast data of the previous period is inconsistent, the production forecast data to be updated is used as the production forecast data according to the time series, and the number of times the time series database is updated is accumulated.

[0017] If the cumulative number of records exceeds a preset threshold, a prompt message is generated and sent to the user terminal so that the user terminal can update the process configuration information based on the prompt message to update the mechanism model; wherein, the prompt message includes text and images.

[0018] In one implementation of this application, the mechanism model is updated based on the operation of the monitoring terminal and / or the corresponding actual production data of the production forecast data, specifically including:

[0019] According to the time series in the time series database, each of the production forecast data is matched with the corresponding actual production data;

[0020] The matching results of each of the production forecast data and the corresponding actual production data are sent to the monitoring terminal;

[0021] Based on the production evaluation operation of the monitoring terminal, a model optimization scheme from the preset model optimization scheme list is determined, and the model optimization scheme is sent to the user terminal to update the mechanism model based on the updated process configuration information of the user terminal.

[0022] In one implementation of this application, a corresponding data model is generated based on preset production management elements, specifically including:

[0023] Based on the types of production management elements corresponding to the national identifier resolution system, the model parameter identifiers, model parameter values, model parameter types, and model data formats of the data model are determined to generate the data model; the types of production management elements include: personnel, machines, materials, methods, and environment.

[0024] In one implementation of this application, after generating a corresponding data model based on preset production management elements, the method further includes:

[0025] Retrieve a list of preset data sources;

[0026] Based on the data source specification operation of the user terminal, the data source parameter fields corresponding to the data model in the data source list are matched to select the corresponding data source as the specified data source of the data model.

[0027] Based on the specified data source, establish a corresponding data extraction task for the data model; wherein, the data extraction task includes: task execution interval time and task execution specified time.

[0028] In one implementation of this application, custom model data combination information is determined based on process configuration information from the user terminal and the data model, specifically including:

[0029] According to the process configuration information from the user terminal, the data in the data model are combined to obtain a customized production process;

[0030] Based on the process configuration information, determine the intermediate indicators of the custom production process and the corresponding indicator formulas and the calculation frequency of the indicator formulas.

[0031] Based on the custom generation process, the intermediate indicators of the process, the corresponding indicator formulas, and the frequency of indicator formula calculations, the custom model data combination information is generated.

[0032] In one implementation of this application, the operation of the index formula includes at least four arithmetic operations, modulo, logical operations, and comparison operations.

[0033] On the other hand, embodiments of this application also provide a data-driven industrial mechanism model creation device, the device comprising:

[0034] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0035] Based on preset production management elements, a corresponding data model is generated; wherein, the data model includes model parameter identifiers, model parameter values, model parameter types, and model data formats;

[0036] Based on the process configuration information from the user terminal and the data model, the custom model data combination information is determined; wherein, the process configuration information includes at least: intermediate process indicators, indicator formulas, and indicator formula calculation frequency;

[0037] Based on the mechanism model corresponding to the data combination information of the custom model, determine the production forecast data corresponding to the industrial production collection data, and send the production forecast data to the corresponding monitoring terminal;

[0038] The mechanism model is updated based on the operation of the monitoring terminal and / or the actual production data corresponding to the production forecast data.

[0039] Furthermore, embodiments of this application also provide a non-volatile computer storage medium created based on a data-driven industrial mechanism model, storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:

[0040] Based on preset production management elements, a corresponding data model is generated; wherein, the data model includes model parameter identifiers, model parameter values, model parameter types, and model data formats;

[0041] Based on the process configuration information from the user terminal and the data model, the custom model data combination information is determined; wherein, the process configuration information includes at least: intermediate process indicators, indicator formulas, and indicator formula calculation frequency;

[0042] Based on the mechanism model corresponding to the data combination information of the custom model, determine the production forecast data corresponding to the industrial production collection data, and send the production forecast data to the corresponding monitoring terminal;

[0043] The mechanism model is updated based on the operation of the monitoring terminal and / or the actual production data corresponding to the production forecast data.

[0044] This application, through the aforementioned technical solution, establishes a mechanistic model customized based on data combinations from a data model. It can continuously optimize the mechanistic model based on production forecast data and actual production data, resulting in higher accuracy. This allows the mechanistic model to be applied to various industries for customized use, lowering the barrier to entry and reducing the complexity of its implementation. Attached Figure Description

[0045] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0046] Figure 1 This is a schematic flowchart of a data-driven industrial mechanism model creation method according to an embodiment of this application;

[0047] Figure 2 This is a schematic diagram of the structure of a data-driven industrial mechanism model creation device according to an embodiment of this application. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0049] Mechanism models are precise models built upon the internal mechanisms of objects, production processes, or the transmission mechanisms of material flow. Their underlying logic comprises mass balance equations, energy balance equations, momentum balance equations, phase balance equations, as well as certain physical property equations, chemical reaction laws, and fundamental circuit laws. They can be written in various high-level programming languages ​​such as C++, JAVA, Python, and MATLAB. Since we cannot uniformly define standards for constructing mechanism models, enterprises can only use certain prescribed standards for constraint, thus limiting the richness of mechanism models. Currently, there is no unified standard for encapsulating and calling existing industrial mechanism models for model collection, integration, and unified invocation.

[0050] Therefore, current mechanistic models are highly customized and their richness is limited, making it difficult for different industries to implement and reuse them, and the threshold for using mechanistic models is high.

[0051] Based on this, embodiments of this application provide a data-driven method, device, and medium for creating industrial mechanism models, which addresses the technical problem that current mechanism models are highly customized, have high usage barriers, and are difficult to use conveniently.

[0052] The various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0053] This application provides a data-driven method for creating industrial mechanism models, such as... Figure 1As shown, the method may include steps S101-S104:

[0054] S101, the server generates the corresponding data model based on the preset production management elements.

[0055] The data model includes model parameter identifiers, model parameter values, model parameter types, and model data formats.

[0056] It should be noted that the server, as the execution subject of the data-driven industrial mechanism model creation method, exists only as an example, and the execution subject is not limited to the server. This application does not make any specific limitation in this regard.

[0057] In this embodiment, the server can determine the model parameter identifier, model parameter value, model parameter type, and model data format of the data model based on the type of production management element corresponding to the national identifier resolution system, in order to generate a data model. The types of production management elements include: personnel, machines, materials, methods, and environment.

[0058] In other words, the server can create data models suitable for industrial use according to different types of people, machines, materials, methods, and environments, and specify model parameter identifiers, model parameter values, model parameter types, and model data formats.

[0059] In addition, after generating the corresponding data model based on the preset production management elements, the method also includes:

[0060] The server retrieves a pre-defined list of data sources and, based on the user's specified data source operation, matches the data source parameter fields in the list that correspond to the data model, thus designating the corresponding data source as the specified data source for the data model. Based on the specified data source, the server establishes a corresponding data extraction task for the data model. This data extraction task includes: a task execution interval and a specified task execution time.

[0061] In other words, the server can obtain the parameters required by the data model through the aforementioned data sources, thereby ensuring the accuracy and completeness of the data source for the data model.

[0062] The specified data sources support relational databases, files, real-time data, and other data types. The data source is specified down to specific parameter fields to ensure the accuracy of the data source. After configuring the data source, a data extraction task is also specified to ensure the data model's data remains accurate for a certain period.

[0063] The above technical solution includes data model construction, data source configuration, and data extraction task execution, thereby providing a data background for custom data combinations for the mechanism model and ensuring the accuracy of the mechanism model calculation.

[0064] S102, the server determines the custom model data combination information based on the process configuration information and data model from the user terminal.

[0065] The process configuration information includes at least: intermediate process indicators, indicator formulas, and indicator formula calculation frequency.

[0066] In other words, the user terminal can customize the process configuration information according to the normal industrial production process, extract data from the data model based on the process configuration information, and combine the data to obtain the customized model data combination information. The user terminal can be a user's mobile phone, computer, or other device; this application does not specifically limit it.

[0067] In one embodiment of this application, the application can be applied to a rose drying scenario. A user terminal configures the rose drying process. Within this process, several data models exist, such as a temperature model and a humidity model, each containing a set of data. This application can combine these data to obtain customized model data combination information, such as temperature and humidity at the same time, thereby allowing the viewing of all real-time production data.

[0068] In this embodiment of the application, based on the process configuration information and data model from the user terminal, the custom model data combination information is determined, specifically including:

[0069] The server can combine data from the data model according to the process configuration information from the user terminal to obtain a custom production process. Next, based on the process configuration information, it determines the intermediate indicators of the custom production process, their corresponding formulas, and the frequency of formula calculations. Then, based on the custom production process, its intermediate indicators, their corresponding formulas, and the frequency of formula calculations, it generates custom model data combination information.

[0070] The calculation of the index formula includes at least four arithmetic operations, modulo, logical operations, and comparison operations.

[0071] In other words, after the data model is created, the server can define the production process by combining data according to the requirements of the industrial mechanism model and production technology. This allows viewing all real-time production data within the combined data. Intermediate indicators for the production process can be specified, and indicator formulas can be defined. These formulas support operations such as addition, subtraction, multiplication, division, modulo, logical operations, and comparison operations. Through free combination, they can support the formula requirements of most commonly used industrial mechanism models. After obtaining the data model and indicator formulas, the custom data combination can be further refined, specifying the relationship between indicator data and collected data, and setting the calculation frequency of the indicator formulas. This application can also specify the content and calculation method of the final indicator data to obtain custom model data combination information, thereby predicting the final data.

[0072] S103, the server determines the production forecast data corresponding to the industrial production data collection data based on the mechanism model corresponding to the data combination information of the custom model, and sends the production forecast data to the corresponding monitoring terminal.

[0073] In this embodiment of the application, production forecast data corresponding to industrial production collection data is determined based on the mechanistic model corresponding to the custom model data combination information, specifically including:

[0074] The server acquires industrial production data from industrial data acquisition devices and inputs this data into a mechanistic model. The output of the mechanistic model is then used as production forecast data.

[0075] In other words, this application can establish a mechanistic model based on a combination of custom model data information, and then use the mechanistic model, combined with data collected during the actual production process, to make production predictions. For example, in the aforementioned mechanistic model for rose drying, the server can obtain drying data from the data model during the rose drying process, and predict the quality of dried roses based on the drying data and the mechanistic model.

[0076] For example, in the steelmaking industry, this application can establish a steelmaking mechanism model based on data from a steelmaking data model and predict steel production output based on the collected data. The custom steelmaking mechanism model consists of data configuration and indicator formulas, and intermediate indicator data is also calculated using these formulas. The collected data and indicator data together present the production process data.

[0077] In this application embodiment, since there are numerous and complex data models in industry, recording them one by one would affect the data acquisition and calculation efficiency of the mechanistic model and consume excessive storage resources. Therefore, this application provides the following technical solution, specifically including:

[0078] First, when the industrial production data collected by the industrial data acquisition equipment is updated, the server determines the corresponding production forecast data to be updated as the production forecast data to be updated.

[0079] Next, the server compares the production forecast data to be updated with the production forecast data from the previous period.

[0080] Subsequently, if the comparison between the production forecast data to be updated and the production forecast data of the previous period is inconsistent, the server updates the production forecast data to be updated into the preset time series database according to the time series, and accumulates the number of times the time series database is updated.

[0081] Finally, if the cumulative number of records exceeds a preset threshold, the server generates a prompt message and sends it to the user terminal. The user terminal then updates its process configuration information based on the prompt message to update the mechanism model. The prompt message includes text and images.

[0082] In other words, this application can collect industrial production data in real time and use a mechanistic model to obtain production forecast data based on this real-time data. The production forecast data at a given moment is compared with the production forecast data at the previous moment. This comparison can also be performed by calculating variance. If they match, the production forecast data for that moment will no longer be recorded; if they do not match, the server will store the production forecast data that differs from the previous moment's data in a time-series database, accumulating the number of times it is stored in the time-series database. When the accumulated number of records exceeds a preset threshold, a prompt message will be generated indicating that the process configuration information needs to be updated to update the mechanistic model. The preset threshold can be set according to actual use; this application does not specifically limit it. The time-series database is connected to the server and is used to store the production forecast data.

[0083] This application can determine whether the process configuration information used to generate the mechanistic model needs to be updated based on the frequency of production forecast data recorded during actual use of the mechanistic model. Generally, a mechanistic model that provides fewer production forecast data during actual use is considered superior, and vice versa. This application can update the mechanistic model based on the frequency of different production forecast data provided by the mechanistic model.

[0084] S104, the server updates the mechanism model based on the actual production data corresponding to the operation and / or production forecast data of the monitoring terminal.

[0085] In this embodiment of the application, the mechanism model is updated based on the actual production data corresponding to the operation and / or production forecast data of the monitoring terminal, specifically including:

[0086] The server matches each production forecast with the corresponding actual production data according to the time series in the time series database. Then, it sends the matching results to the monitoring terminal. Based on the production evaluation operations of the monitoring terminal, it determines the model optimization scheme from the preset model optimization scheme list and sends the model optimization scheme to the user terminal to update the mechanism model based on the updated process configuration information on the user terminal.

[0087] In other words, this application can proactively update the mechanism model based on the operation of the monitoring terminal. The monitoring terminal can be a mobile phone, computer, or other device belonging to the industrial production manager corresponding to the mechanism model; this application does not specify a particular device. For example, the monitoring terminal can proactively issue a command to update the mechanism model, thereby updating the mechanism model.

[0088] The mechanism model can also be updated based on the actual production data corresponding to the operation of the monitoring terminal and the production forecast data.

[0089] This application can also match production forecast data and actual production data sorted by time sequence one by one. For example, if the task execution interval is t, then the production forecast data for t1-t1+2t is x1, and the actual production data is x1, while the production forecast data for t1+3t is x2, and the actual production data is x2. The server then sends the matching results to the monitoring terminal. Users of the monitoring terminal can obtain the model optimization scheme from the model optimization scheme list through the Internet or by querying preset record information, and update the process configuration information by the user terminal, thereby updating the mechanism model.

[0090] This application enables the use of mechanistic models to perform calculations, predictions, and storage on collected data. The ultimate goal of the mechanistic model is to obtain production forecast data, thereby guiding the production process and comparing it with real data to further optimize the mechanistic model. Specifically, this application performs calculations based on the frequency of the aforementioned indicator formulas and real-time data to obtain the calculation results, i.e., production forecast data. The calculated results are ultimately stored in a time-series database, recording the production forecast data along the time dimension. By comparing the production forecast data with the collected real data, the data can be compared and displayed in a data twin manner, thereby assisting customers in production decisions. Based on the comparison results, the mechanistic model can be optimized in reverse, further ensuring the accuracy of the forecast data.

[0091] This application, through the above technical solution, can integrate mechanistic models from different professional fields, making them part of the integrated mechanistic model in the form of custom components. This allows non-professionals to call multiple models to work collaboratively according to their own business processes, solving the problem that mechanistic model designers do not understand programmers, and programmers do not understand the complex professional knowledge inside the mechanistic model. On the other hand, the system based on the custom mechanistic model does not expose the internal principles of the mechanistic model, thus protecting intellectual property rights while allowing knowledge and experience to be shared and monetized.

[0092] Based on existing mechanistic models and collected real-time data, we can freely combine and define them to construct a reasonable data model framework. We can then use the mechanistic model to predict the indicator data and continuously optimize it based on the comparison between the predicted data and the actual data. This solves the problems of high customization and difficulty in implementation when applying mechanistic models in different industries, thereby lowering the threshold for using mechanistic models.

[0093] This application also provides a system based on data-driven custom use of mechanistic models, which consists of three modules: a heterogeneous data acquisition module, a custom mechanistic model construction module, and a mechanistic model operation and execution module.

[0094] The heterogeneous data acquisition module is used to collect data for the system, which supports the application of the data in the mechanistic model.

[0095] The custom mechanism model module is the core module of the system. It is used to define the data model collected and to build the custom mechanism model by dragging and dropping based on the data model.

[0096] The mechanism model operation and execution module is used to perform data operations and storage based on the constructed mechanism model and the collected data.

[0097] This application employs data acquisition methods to obtain key parameters of industrial production and combines data based on these parameters to enable the application of mechanistic models. Customized mechanistic models can be developed for various industries, effectively reducing the complexity of implementing these models. The variance between the calculated and actual values ​​is used as a reference parameter for the quality of the mechanistic model. The model is continuously optimized based on the fluctuation range of this parameter, further refining the mechanistic model, narrowing the prediction error range, and bringing it closer to actual values. This results in higher model accuracy and a more convincing and interpretable model library.

[0098] By leveraging big data and employing mechanistic models and digital twins, the physical world and virtual space are mapped and interact collaboratively, thereby constructing a system digital twin based on data-driven, software-defined, platform-supported, and virtual-physical interaction. Ultimately, this achieves full-process, full-element digitization and virtualization, real-time and visualization of all states, and collaborative and intelligent operation and maintenance of the system, from design and construction to management.

[0099] Figure 2 A schematic diagram of a data-driven industrial mechanism model creation device provided in this application embodiment, the device comprising:

[0100] At least one processor; and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to:

[0101] Based on the preset production management elements, a corresponding data model is generated. The data model includes model parameter identifiers, model parameter values, model parameter types, and model data formats.

[0102] Based on the process configuration information and data model from the user terminal, the custom model data combination information is determined. The process configuration information includes at least: intermediate process indicators, indicator formulas, and the frequency of indicator formula calculations.

[0103] Based on the mechanistic model corresponding to the data combination information of the custom model, the corresponding production forecast data of the industrial production collection data is determined, and the production forecast data is sent to the corresponding monitoring terminal.

[0104] The mechanism model is updated based on the actual production data corresponding to the operation and / or production forecast data from the monitoring terminal.

[0105] This application also provides a data-driven industrial mechanism model-based creation of a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:

[0106] Based on the preset production management elements, a corresponding data model is generated. The data model includes model parameter identifiers, model parameter values, model parameter types, and model data formats.

[0107] Based on the process configuration information and data model from the user terminal, the custom model data combination information is determined. The process configuration information includes at least: intermediate process indicators, indicator formulas, and the frequency of indicator formula calculations.

[0108] Based on the mechanistic model corresponding to the data combination information of the custom model, the corresponding production forecast data of the industrial production collection data is determined, and the production forecast data is sent to the corresponding monitoring terminal.

[0109] The mechanism model is updated based on the actual production data corresponding to the operation and / or production forecast data from the monitoring terminal.

[0110] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0111] The devices, media, and methods provided in this application are one-to-one correspondences. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0112] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0113] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A data-driven method for creating industrial mechanism models, characterized in that, The method includes: Based on preset production management elements, a corresponding data model is generated; wherein, the data model includes model parameter identifiers, model parameter values, model parameter types, and model data formats; Based on the process configuration information from the user terminal and the data model, the custom model data combination information is determined; wherein, the process configuration information includes at least: intermediate process indicators, indicator formulas, and indicator formula calculation frequency; Based on the mechanism model corresponding to the data combination information of the custom model, determine the production forecast data corresponding to the industrial production collection data, and send the production forecast data to the corresponding monitoring terminal; The mechanism model is updated based on the operation of the monitoring terminal and / or the actual production data corresponding to the production forecast data. The method further includes: When the industrial production data collected by the industrial data acquisition equipment is updated, the production forecast data corresponding to the updated industrial production data is determined to be the production forecast data to be updated. Compare the production forecast data to be updated with the production forecast data of the previous period; If the comparison result between the production forecast data to be updated and the production forecast data of the previous period is inconsistent, the production forecast data to be updated is used as the production forecast data according to the time series, and the number of times the time series database is updated is accumulated. If the cumulative number of updates exceeds a preset threshold, a prompt message is generated and sent to the user terminal so that the user terminal can update the process configuration information according to the prompt message to update the mechanism model; wherein, the prompt message includes text and images; Specifically, updating the mechanism model based on the operation of the monitoring terminal and / or the corresponding actual production data of the production forecast data includes: According to the time series in the time series database, each of the production forecast data is matched with the corresponding actual production data; The matching results of each of the production forecast data and the corresponding actual production data are sent to the monitoring terminal; Based on the production evaluation operation of the monitoring terminal, a model optimization scheme from the preset model optimization scheme list is determined, and the model optimization scheme is sent to the user terminal to update the mechanism model based on the updated process configuration information of the user terminal.

2. The method according to claim 1, characterized in that, Based on the mechanistic model corresponding to the data combination information of the custom model, determine the production forecast data corresponding to the industrial production collection data, specifically including: Acquire industrial production data from industrial data acquisition equipment and input the industrial production data into the mechanism model; The output of the mechanistic model is used as the production forecast data.

3. The method according to claim 1, characterized in that, Based on the preset production management elements, a corresponding data model is generated, specifically including: Based on the types of production management elements corresponding to the national identifier resolution system, the model parameter identifiers, model parameter values, model parameter types, and model data formats of the data model are determined to generate the data model; the types of production management elements include: personnel, machines, materials, methods, and environment.

4. The method according to claim 3, characterized in that, After generating the corresponding data model based on the preset production management elements, the method further includes: Retrieve a list of preset data sources; Based on the data source specification operation of the user terminal, the data source parameter fields corresponding to the data model in the data source list are matched to select the corresponding data source as the specified data source of the data model. Based on the specified data source, establish a corresponding data extraction task for the data model; wherein, the data extraction task includes: task execution interval time and task execution specified time.

5. The method according to claim 1, characterized in that, Based on the process configuration information from the user terminal and the data model, the custom model data combination information is determined, specifically including: According to the process configuration information from the user terminal, the data in the data model are combined to obtain a customized production process; Based on the process configuration information, determine the intermediate indicators of the custom production process and the corresponding indicator formulas and the calculation frequency of the indicator formulas. Based on the custom generation process, the intermediate indicators of the process, the corresponding indicator formulas, and the calculation frequency of the indicator formulas, the custom model data combination information is generated.

6. The method according to claim 5, characterized in that, The calculation of the index formula includes at least four arithmetic operations, modulo, logical operations, and comparison operations.

7. A data-driven industrial mechanism model creation device, characterized in that, The device includes: At least one processor; and, 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 data-driven industrial mechanism model creation method according to any one of claims 1-6.

8. A non-volatile computer storage medium based on a data-driven industrial mechanism model, storing computer-executable instructions, characterized in that, The computer-executable instructions are configured to execute the data-driven industrial mechanism model creation method according to any one of claims 1-6.

Images