Industrial production data processing method, device, computer equipment and storage medium

Abstract

The present application relates to an industrial production data processing method, device, computer equipment and storage medium, which obtains a data filtering threshold parameter obtained based on a preset data analysis model at the current time point, collects and filters industrial production data according to the data filtering threshold parameter, inputs the filtered industrial production data into the preset data analysis model, obtains an updated data filtering threshold parameter, and uses the updated data filtering threshold parameter as the data filtering threshold parameter at the next time point, and when the next time point is reached, returns to the step of collecting and filtering industrial production data according to the data filtering threshold parameter at the current time point. By changing the input of the model, the data filtering threshold parameter is optimized, and the optimized data filtering threshold parameter is used for the next data collection and data filtering, and the cycle is repeated in this way, the rationality and accuracy of the data filtering threshold parameter are continuously improved, the "junk" data filtering is optimized, and unnecessary resource loss is reduced.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an industrial production data processing method, device, computer equipment and storage medium. Background Art

[0002] Edge data collection, processing and transmission in the edge computing gateway at the industrial site is a key scenario for realizing the overall functions of the industrial Internet platform.

[0003] At present, with the vigorous development of industrial Internet and industrial IoT, the industrial production data generated by industrial equipment has shown a substantial growth trend, which has brought about a huge test on the performance of modules such as data collection, edge analysis and data transmission. Due to the existence of a large amount of "junk" data, a high proportion of data collection, data calculation and data transmission resources are occupied, resulting in unnecessary resource loss.

[0004] Therefore, it is necessary to provide an industrial production data processing solution that can reduce unnecessary resource loss. Summary of the invention

[0005] Based on this, it is necessary to provide an industrial production data processing method, device, computer equipment and storage medium that can reduce unnecessary resource loss due to the collection and transmission of a large amount of "junk" data, which causes unnecessary resource loss.

[0006] An industrial production data processing method, the method comprising:

[0007] Obtaining a data filtering threshold parameter at a current time point, where the data filtering threshold parameter at the current time point is obtained based on a preset data analysis model, where the preset data analysis model is used to obtain the data filtering threshold parameter based on a prediction of industrial production data according to preset business plan data;

[0008] Collect and filter industrial production data based on data filtering threshold parameters at the current time point;

[0009] Inputting the filtered industrial production data into a preset data analysis model to obtain updated data filtering threshold parameters, and using the updated data filtering threshold parameters as data filtering threshold parameters at the next time point;

[0010] When the next time point is reached, the process returns to the step of collecting and filtering industrial production data according to the data filtering threshold parameter at the current time point.

[0011] In one embodiment, collecting and filtering industrial production data according to a data filtering threshold parameter at a current time point includes:

[0012] Adjust the preset rule filtering engine according to the data filtering threshold parameters;

[0013] According to the adjusted filtering rule engine, industrial production data is collected, and duplicate data and unnecessary data are filtered out.

[0014] In one embodiment, inputting the filtered industrial production data into a preset data analysis model includes:

[0015] Selecting a preset data analysis model from a preset model set according to the equipment identifier and the project identifier in the industrial production data;

[0016] The filtered industrial production data is input into the selected preset data analysis model.

[0017] In one embodiment, the filtered industrial production data is input into a preset data analysis model to obtain updated data filtering threshold parameters including:

[0018] According to the filtered industrial production data, the probability density distribution curve is fitted;

[0019] According to the preset confidence, select the upper and lower quantiles of the probability density distribution curve;

[0020] Based on the selected upper and lower quantiles and the preset amplification factor, an updated data filtering threshold parameter is obtained.

[0021] In one embodiment, obtaining the data filtering threshold parameter at the current time point includes:

[0022] Extract historical industrial production data within a preset time period;

[0023] Preprocess historical industrial production data;

[0024] The historical industrial production data after data preprocessing is input into the preset data analysis model so that the preset data analysis model performs threshold learning to obtain the data filtering threshold parameters at the current time point.

[0025] In one embodiment, the preset data analysis model performs threshold learning, and the generation of data filtering threshold parameters includes:

[0026] Fit the probability density distribution curve based on the historical industrial production data after data preprocessing;

[0027] Based on the probability density distribution curve and the preset confidence level, select upper and lower quantiles;

[0028] According to the selected upper and lower quantiles and the preset amplification factor, the data filtering threshold parameters are obtained.

[0029] In one embodiment, preprocessing the historical industrial production data includes:

[0030] Clear fault data, downtime data, and outliers from historical industrial production data.

[0031] An industrial production data processing device, comprising:

[0032] A parameter acquisition module is used to acquire a data filtering threshold parameter at a current time point, where the data filtering threshold parameter at the current time point is obtained based on a preset data analysis model, where the preset data analysis model is used to predict the data filtering threshold parameter for industrial production data based on preset business plan data;

[0033] A data processing module, used to collect and filter industrial production data according to the data filtering threshold parameters at the current time point;

[0034] A parameter updating module, used to input the filtered industrial production data into a preset data analysis model, obtain updated data filtering threshold parameters, and use the updated data filtering threshold parameters as data filtering threshold parameters at the next time point;

[0035] The loop processing module is used to control the data processing module to re-execute the operation of collecting and filtering industrial production data according to the data filtering threshold parameters at the current time point when the next time point is reached.

[0036] In one of the embodiments, the data processing module is also used to adjust the preset rule filtering engine according to the data filtering threshold parameters. The rule filtering engine is deployed in the edge side functional module. According to the adjusted filtering rule engine, industrial production data is collected, and duplicate data and unnecessary data are filtered out of the collected industrial production data.

[0037] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0038] Obtaining a data filtering threshold parameter at a current time point, where the data filtering threshold parameter at the current time point is obtained based on a preset data analysis model, where the preset data analysis model is used to obtain the data filtering threshold parameter based on a prediction of industrial production data according to preset business plan data;

[0039] Collect and filter industrial production data based on data filtering threshold parameters at the current time point;

[0040] Inputting the filtered industrial production data into a preset data analysis model to obtain updated data filtering threshold parameters, and using the updated data filtering threshold parameters as data filtering threshold parameters at the next time point;

[0041] When the next time point is reached, the process returns to the step of collecting and filtering industrial production data according to the data filtering threshold parameter at the current time point.

[0042] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0043] Obtaining a data filtering threshold parameter at a current time point, where the data filtering threshold parameter at the current time point is obtained based on a preset data analysis model, where the preset data analysis model is used to obtain the data filtering threshold parameter based on a prediction of industrial production data according to preset business plan data;

[0044] Collect and filter industrial production data based on data filtering threshold parameters at the current time point;

[0045] Inputting the filtered industrial production data into a preset data analysis model to obtain updated data filtering threshold parameters, and using the updated data filtering threshold parameters as data filtering threshold parameters at the next time point;

[0046] When the next time point is reached, the process returns to the step of collecting and filtering industrial production data according to the data filtering threshold parameter at the current time point.

[0047] The above industrial production data processing method, device, computer equipment and storage medium obtain the data filtering threshold parameters obtained based on the preset data analysis model at the current time point, the preset data analysis model is constructed based on business plan data and historical industrial production data training, and according to the data filtering threshold parameters at the current time point, the industrial production data is collected and filtered, and the filtered industrial production data is input into the preset data analysis model to obtain the updated data filtering threshold parameters, and the updated data filtering threshold parameters are used as the data filtering threshold parameters at the next time point. When the next time point is reached, the step of collecting and filtering the industrial production data according to the data filtering threshold parameters at the current time point is returned. In the above process, the filtered industrial production data is input into the data analysis model so that the model optimizes the data filtering threshold parameters according to the filtered data, obtains the updated data filtering threshold parameters, and then uses the optimized and updated data filtering threshold parameters to guide the next data collection and data filtering, and the cycle is repeated in this way to continuously improve the rationality and accuracy of the data filtering threshold parameters, thereby continuously optimizing the filtering of "junk" data and reducing unnecessary resource loss. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 An application environment diagram of an industrial production data processing method in one embodiment;

[0049] Figure 2A schematic diagram of a process flow of an industrial production data processing method in one embodiment;

[0050] Figure 3 A schematic diagram of a flow chart of an industrial production data processing method in another embodiment;

[0051] Figure 4 A schematic diagram of a flow chart of a step of obtaining a data filtering threshold parameter at a current time point in an embodiment;

[0052] Figure 5 is a structural block diagram of an industrial production data processing device in one embodiment;

[0053] Figure 6 is a structural block diagram of an industrial production data processing device in another embodiment;

[0054] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] The industrial production data processing method provided in this application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network through the network. Specifically, the user can operate on the graphical interface of the terminal 102, send a data processing message to the server 102 through the terminal 102, and the server 102 receives the message to obtain the data filtering threshold parameter at the current time point. The data filtering threshold parameter at the current time point is obtained based on the preset data analysis model. The preset data analysis model is used to predict the data filtering threshold parameter for industrial production data according to the preset business plan data, and then, according to the data filtering threshold parameter at the current time point, collect and filter the industrial production data, and then input the filtered industrial production data into the preset data analysis model to train the model, obtain the updated data filtering threshold parameter, and use the updated data filtering threshold parameter as the data filtering threshold parameter at the next time point, wait for the arrival of the next time point, and when the next time point is reached, return to the step of collecting and filtering the industrial production data according to the data filtering threshold parameter at the current time point. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented with an independent server or a server cluster composed of multiple servers.

[0057] In one embodiment, if Figure 2 As shown, a method for processing industrial production data is provided, and the method is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0058] Step S200, obtaining data filtering threshold parameters at the current time point, the data filtering threshold parameters at the current time point are obtained based on a preset data analysis model, and the preset data analysis model is used to obtain data filtering threshold parameters for industrial production data prediction based on preset business plan data.

[0059] Data filtering threshold parameters are upper and lower limits used to guide data collection, data analysis, and filtering, which are more of a range value. Business plan data includes production plans and production content, where the production plan mainly includes the output and quality requirements, construction period requirements, production unit scope and task division, delivery requirements, etc. of industrial production. The production content mainly refers to the output of a specific production task, and the business plan data is obtained through the MES system at the beginning of building the data analysis model, and it is configured in the data analysis model to guide the generation process of the model's data filtering threshold parameters. Taking the data collection, analysis and transmission of industrial data based on the industrial Internet of Things platform as an example, the data analysis model can be an intelligent data analysis model deployed in the cloud, or it can be a model deployed in the data processing logic of the server. The model is built based on historical industrial production data and business plan data, and is used to generate data filtering threshold parameters for industrial production data according to preset business plan data. After obtaining the data filtering threshold parameters, the generated data filtering threshold parameters are sent to the edge side data collection module, data filtering module, data transmission module and other functional modules.

[0060] Step S400, collecting and filtering industrial production data according to the data filtering threshold parameter at the current time point.

[0061] Industrial production data refers to the production data provided by various industrial equipment at the industrial site. The industrial equipment will upload the industrial production data it generates to the edge side of the industrial Internet in real time. Since the edge side is close to the data source, the amount of data that needs to be collected, transmitted and processed is very large, including a large amount of "junk" data. Therefore, it is necessary to filter and process the data in a timely manner to ensure the quality of the data. In this embodiment, after the data filtering threshold parameters at the current time point are obtained, the industrial production data uploaded to the edge side by the industrial production equipment in real time is collected according to the data filtering threshold parameters at the current time point. At the same time, the collected industrial production data is filtered and processed in real time to clean up a large amount of "junk data" in time.

[0062] Step S600: input the filtered industrial production data into a preset data analysis model to obtain updated data filtering threshold parameters, and use the updated data filtering threshold parameters as data filtering threshold parameters at the next time point.

[0063] As in the above embodiment, after filtering the industrial production data according to the data filtering threshold parameter, the filtered industrial production data is obtained. Since the initial value of the data filtering threshold parameter is a rough value, in the actual data collection and data filtering process, each data filtering may only filter out a small part of duplicate data or unnecessary data. In order to effectively clear the redundant data, the data filtering threshold parameter needs to be continuously optimized. It can be that the filtered industrial production data is input into the data analysis model again, so that the data analysis model performs corresponding processing according to the filtered industrial production data again, regenerates the data filtering threshold parameter, obtains the updated data filtering threshold parameter, and at the same time, uses the updated data filtering threshold parameter as the data filtering threshold parameter at the next time point, waiting for the arrival of the next time point. Specifically, the data analysis model performs corresponding processing according to the filtered industrial production data, and regenerating the data filtering threshold parameter can be based on the filtered industrial production data, fitting the probability density distribution curve, selecting the upper and lower quantiles of the probability density distribution curve according to the preset confidence, and obtaining the updated data filtering threshold parameter based on the selected upper and lower quantiles and the preset magnification factor.

[0064] Step S800, when the next time point is reached, return to the step of collecting and filtering industrial production data according to the data filtering threshold parameter at the current time point.

[0065] In practical applications, the update of data filtering threshold parameters is a process of continuous cycle optimization. When the previous round of data filtering threshold parameter update is completed, when the next time point arrives, the industrial production data will continue to be collected and filtered according to the updated data filtering threshold parameters. In this way, recursion is performed to continuously optimize the data filtering threshold parameters.

[0066] In the above industrial production data processing method, the data filtering threshold parameters obtained based on the preset data analysis model at the current time point are obtained. The preset data analysis model is constructed based on the business plan data and the historical industrial production data training. According to the data filtering threshold parameters at the current time point, the industrial production data is collected and filtered, and the filtered industrial production data is input into the preset data analysis model to obtain the updated data filtering threshold parameters, and the updated data filtering threshold parameters are used as the data filtering threshold parameters at the next time point. When the next time point is reached, the step of collecting and filtering the industrial production data according to the data filtering threshold parameters at the current time point is returned. In the above process, the filtered industrial production data is input into the data analysis model so that the model optimizes the data filtering threshold parameters according to the filtered data, obtains the updated data filtering threshold parameters, and then guides the next data collection and data filtering with the optimized and updated data filtering threshold parameters. In this way, the rationality and accuracy of the data filtering threshold parameters are continuously improved, so that the filtering of "junk" data can be continuously optimized to reduce unnecessary resource loss. Further, the data analysis model can accurately estimate the quantity and quality trend of production data according to input information such as business plans.

[0067] In one embodiment, if Figure 3 As shown, according to the data filtering threshold parameters at the current time point, collecting and filtering industrial production data includes: step S420, adjusting the preset rule filtering engine according to the data filtering threshold parameters, collecting industrial production data according to the adjusted filtering rule engine, and filtering duplicate data and unnecessary data for the collected industrial production data.

[0068] A rule filtering engine refers to a rule engine used for data filtering, which is a type of rule engine. The rule engine is developed from an inference engine and is a component embedded in an application. It realizes the separation of business decisions from application code and uses predefined semantic modules to write business decisions. The specific execution of the rule engine can be divided into several processes: accepting data input, interpreting business rules, and making business decisions based on business rules. The use of a rule engine can separate complex and redundant business rules from the entire support system, so that the architecture can be reusable and transplanted. In actual applications, since the collected data will include a large amount of duplicate data and unnecessary data that does not conform to the production plan and production content, a rule filtering engine is deployed in front of the functional modules such as data collection, data analysis, and data transmission on the edge side to filter duplicate data and unnecessary data. In specific implementation, the data collection and data filtering process can be to adjust the deployed rule filtering engine according to the data filtering threshold parameters, that is, according to the data filtering threshold parameters, set the corresponding filtering parameters in the rule filtering engine, and then, according to the adjusted rule filtering engine, collect industrial production data at each stage, and at the same time, according to the adjusted rule filtering engine, filter the duplicate data and unnecessary data in the collected industrial production data. In this embodiment, by filtering data through a rule filtering engine, data filtering can be separated from the entire business system, reducing the complexity of implementing data filtering business logic and improving scalability.

[0069] In one embodiment, if Figure 4 As shown, the data filtering threshold parameters for obtaining the current time point include:

[0070] Step S100, extracting historical industrial production data within a preset time period;

[0071] Step S120, performing data preprocessing on historical industrial production data;

[0072] Step S140, inputting the historical industrial production data after data preprocessing into a preset data analysis model, so that the preset data analysis model performs threshold learning to obtain data filtering threshold parameters at the current time point.

[0073] In the specific implementation, the updating process of the data filtering threshold parameter is that the data analysis model generates the initial value of the data filtering threshold parameter, and then the industrial production data filtered according to the initial value of the data filtering threshold parameter is input into the data analysis model, and the model is trained to update the data filtering threshold parameter, and the optimization is continuously cycled in this way. Therefore, in this embodiment, the method of obtaining the data filtering threshold parameter can be to first extract the historical industrial production data within the Th time period according to the configured time parameter. Since the extracted historical data also contains a large amount of redundant data and non-essential data, and the data analysis model has certain requirements for the input data, it is necessary to perform data preprocessing on the extracted historical industrial production data. After the data preprocessing is completed, the industrial production data after data preprocessing is input into the above-mentioned preset data analysis model, so that the preset data analysis model performs threshold learning according to the production content data and the production plan data, and generates the data filtering threshold parameter at the current time point. When the data filtering threshold parameter at the current time point is generated, the data filtering threshold parameter is sent down to each functional module on the edge side. In this embodiment, through the data analysis model, the data filtering threshold parameter can be automatically and intelligently generated, reducing human intervention and improving efficiency.

[0074] In one embodiment, preprocessing the historical industrial production data includes: removing fault data, downtime data, and outliers in the historical industrial production data.

[0075] In specific implementation, data preprocessing includes clearing fault data in historical industrial production data according to fault record data, clearing shutdown data according to start-stop frequency or operation frequency, and using the Raida method to clear outliers in historical industrial production data. It is understandable that in other embodiments, clearing outliers can also be done by using a box plot method, a 4D test method, or other methods, which are not limited here. In this embodiment, the quality of industrial production data can be improved through data preprocessing.

[0076] In one of the embodiments, a data analysis model is preset to perform threshold learning, and generating data filtering threshold parameters includes: fitting a probability density distribution curve based on historical industrial production data after data preprocessing, selecting upper and lower quantiles based on the probability density distribution curve and preset confidence, and obtaining data filtering threshold parameters based on the selected upper and lower quantiles and preset amplification factors.

[0077] Probability refers to the chance of an event occurring randomly. For a uniform distribution function, the probability density is equal to the probability of a section (the range of values ​​of the event) divided by the length of the section. Its value is non-negative and can be large or small. The probability density distribution curve is a curve graph with variable values ​​as the horizontal axis and cumulative frequency (probability) as the vertical axis, that is, a graph of a probability distribution function, such as a normal curve. In this embodiment, industrial production data takes temperature values ​​as an example, and the temperature values ​​are filtered. That is, after a batch of temperature values ​​are collected, each temperature value in the batch of data may become a threshold value. It can also be considered that the upper and lower limits of the threshold parameters of the filtered temperature values ​​must be two of the collected temperature values. Therefore, all the collected temperature values ​​can be visualized by fitting the probability density distribution, and all discrete temperature values ​​are fitted into a probability density distribution curve. Then, based on the preset confidence level, the upper and lower quantiles are selected, and then the selected upper and lower quantiles are multiplied by the preset magnification factor to obtain the data filtering threshold parameter. Further, the calculated data filtering threshold parameter is saved and issued. Specifically, the quantiles include binary quantiles and quartile quantiles. In this embodiment, the data filtering threshold parameters can be obtained more accurately through the probability density distribution curve and the confidence level.

[0078] In one embodiment, if Figure 3 As shown, inputting the filtered industrial production data into the preset data analysis model includes: step S620, selecting the corresponding preset data analysis model from the preset model set according to the equipment identifier and the project identifier in the industrial production data, inputting the filtered industrial production data into the selected preset data analysis model, obtaining updated data filtering threshold parameters, and using the updated data filtering threshold parameters as the data filtering threshold parameters at the next time point.

[0079] In practical applications, the collection of industrial production data can be based on industrial equipment, that is, each time the industrial production data provided by a specific industrial equipment is collected. Since the production plan data and production content of each type of industrial production data are different, each type of industrial production data needs to be processed with a specific data analysis model. The R&D personnel have built a corresponding data analysis model for each type of industrial production data in advance, and built and preset a model set. After the industrial production data is filtered, the corresponding data analysis model can be selected from the preset model set according to the equipment identification and project identification carried in the industrial production data, and then the filtered industrial production data is input into the selected preset data analysis model for processing, and the updated data filtering threshold parameters are obtained, and the updated data filtering threshold parameters are used as the data filtering threshold parameters at the next time point. In this embodiment, according to the equipment identification and project identification of the industrial production data, the corresponding preset data analysis model is identified for processing, which can analyze the data in a targeted manner and improve the accuracy of data processing and prediction.

[0080] It should be understood that although Figure 2-4 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-4 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0081] In one embodiment, if Figure 5 As shown, an industrial production data processing device is provided, including: a parameter acquisition module 510, a data processing module 520, a parameter update module 530 and a loop processing module 540, wherein:

[0082] The parameter acquisition module 510 is used to obtain the data filtering threshold parameters at the current time point. The data filtering threshold parameters at the current time point are obtained based on a preset data analysis model. The preset data analysis model is used to obtain the data filtering threshold parameters for industrial production data prediction based on preset business plan data.

[0083] The data processing module 520 is used to collect and filter industrial production data according to the data filtering threshold parameters at the current time point.

[0084] The parameter updating module 530 is used to input the filtered industrial production data into a preset data analysis model, obtain updated data filtering threshold parameters, and use the updated data filtering threshold parameters as the data filtering threshold parameters at the next time point.

[0085] The loop processing module 540 is used to control the data processing module to re-execute the operation of collecting and filtering the industrial production data according to the data filtering threshold parameters at the current time point when the next time point is reached.

[0086] In one embodiment, the data processing module 520 is also used to adjust the preset rule filtering engine according to the data filtering threshold parameters, collect industrial production data according to the adjusted filtering rule engine, and filter duplicate data and unnecessary data on the collected industrial production data.

[0087] In one embodiment, the parameter update module 530 is also used to select a corresponding preset data analysis model from a preset model set based on the equipment identifier and the project identifier in the industrial production data, and input the filtered industrial production data into the selected preset data analysis model.

[0088] In one embodiment, if Figure 6 As shown, the device also includes a parameter generation module 550, which is used to extract historical industrial production data within a preset time period, perform data preprocessing on the historical industrial production data, and input the preprocessed historical industrial production data into a preset data analysis model so that the preset data analysis model performs threshold learning to obtain data filtering threshold parameters at the current time point.

[0089] In one embodiment, the parameter generation module 550 is also used to fit a probability density distribution curve based on the historical industrial production data after data preprocessing, select upper and lower quantiles based on the probability density distribution curve and preset confidence, and obtain data filtering threshold parameters based on the selected upper and lower quantiles and preset amplification factor.

[0090] In one embodiment, the parameter generation module 550 is further used to remove fault data, shutdown data and outliers in the historical industrial production data.

[0091] For the specific definition of the industrial production data processing device, please refer to the definition of the industrial production data processing method above, which will not be repeated here. Each module in the above industrial production data processing device can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0092] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as data filtering threshold parameters, confidence and amplification factor. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an industrial production data processing method is implemented.

[0093] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0094] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: obtaining data filtering threshold parameters at a current time point, wherein the data filtering threshold parameters at the current time point are obtained based on a preset data analysis model, wherein the preset data analysis model is used to obtain data filtering threshold parameters for industrial production data prediction based on preset business plan data, and according to the data filtering threshold parameters at the current time point, collecting and filtering industrial production data, inputting the filtered industrial production data into the preset data analysis model, obtaining updated data filtering threshold parameters, and using the updated data filtering threshold parameters as the data filtering threshold parameters at the next time point, and when the next time point is reached, returning to the step of collecting and filtering industrial production data according to the data filtering threshold parameters at the current time point.

[0095] In one of the embodiments, when the processor executes the computer program, it also implements the following steps: according to the data filtering threshold parameters, adjusting the preset rule filtering engine, collecting industrial production data according to the adjusted filtering rule engine, and filtering the collected industrial production data for duplicate data and unnecessary data.

[0096] In one of the embodiments, when the processor executes the computer program, it also implements the following steps: based on the equipment identifier and the project identifier in the industrial production data, select the corresponding preset data analysis model from the preset model set, and input the filtered industrial production data into the selected preset data analysis model.

[0097] In one of the embodiments, when the processor executes the computer program, it also implements the following steps: extracting historical industrial production data within a preset time period, performing data preprocessing on the historical industrial production data, and inputting the preprocessed historical industrial production data into a preset data analysis model so that the preset data analysis model performs threshold learning to obtain data filtering threshold parameters at the current time point.

[0098] In one of the embodiments, when the processor executes the computer program, it also implements the following steps: fitting a probability density distribution curve based on the historical industrial production data after data preprocessing, selecting upper and lower quantiles based on the probability density distribution curve and preset confidence, and obtaining data filtering threshold parameters based on the selected upper and lower quantiles and preset amplification factor.

[0099] In one of the embodiments, when the processor executes the computer program, the processor further implements the following steps: clearing fault data, downtime data, and outliers in the historical industrial production data.

[0100] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: obtaining data filtering threshold parameters at a current time point, the data filtering threshold parameters at the current time point are obtained based on a preset data analysis model, the preset data analysis model is used to obtain data filtering threshold parameters for industrial production data prediction based on preset business plan data, collecting and filtering industrial production data based on the data filtering threshold parameters at the current time point, inputting the filtered industrial production data into the preset data analysis model, obtaining updated data filtering threshold parameters, and using the updated data filtering threshold parameters as the data filtering threshold parameters at the next time point, and when the next time point is reached, returning to the step of collecting and filtering industrial production data based on the data filtering threshold parameters at the current time point.

[0101] In one of the embodiments, when the computer program is executed by the processor, the following steps are also implemented: according to the data filtering threshold parameters, the preset rule filtering engine is adjusted, and according to the adjusted filtering rule engine, industrial production data is collected, and duplicate data and unnecessary data are filtered out of the collected industrial production data.

[0102] In one of the embodiments, when the computer program is executed by the processor, the following steps are also implemented: based on the equipment identification and project identification in the industrial production data, a corresponding preset data analysis model is selected from a preset model set, and the filtered industrial production data is input into the selected preset data analysis model.

[0103] In one of the embodiments, when the computer program is executed by the processor, the following steps are also implemented: extracting historical industrial production data within a preset time period, performing data preprocessing on the historical industrial production data, and inputting the preprocessed historical industrial production data into a preset data analysis model so that the preset data analysis model performs threshold learning to obtain data filtering threshold parameters at the current time point.

[0104] In one of the embodiments, when the computer program is executed by the processor, the following steps are also implemented: fitting a probability density distribution curve based on the historical industrial production data after data preprocessing, selecting upper and lower quantiles based on the probability density distribution curve and preset confidence, and obtaining data filtering threshold parameters based on the selected upper and lower quantiles and preset amplification factor.

[0105] In one of the embodiments, when the computer program is executed by the processor, the following steps are further implemented: clearing fault data, downtime data and outliers in the historical industrial production data.

[0106] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0107] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0108] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. An industrial production data processing method, applied to the edge side of an industrial site, the method comprising: Obtain the data filtering threshold parameters at the current time point. The preset data analysis model is built based on historical industrial production data and business plan data, and is used to predict the data filtering threshold parameters for industrial production data based on the preset business plan data; Collecting and filtering industrial production data according to the data filtering threshold parameter at the current time point; According to the equipment identifier and the project identifier in the industrial production data, a preset data analysis model is selected from a preset model set, the filtered industrial production data is input into the preset data analysis model, the updated data filtering threshold parameter is obtained, and the updated data filtering threshold parameter is used as the data filtering threshold parameter at the next time point; When the next time point is reached, returning to the step of collecting and filtering industrial production data according to the data filtering threshold parameter at the current time point; Among them, the data filtering threshold parameters at the current time point are obtained based on the following method: extracting historical industrial production data within a preset time period, performing data preprocessing on the historical industrial production data, and inputting the historical industrial production data after data preprocessing into a preset data analysis model, so that the preset data analysis model fits the probability density distribution curve according to the historical industrial production data after data preprocessing; according to the preset confidence, selecting the upper and lower quantiles of the probability density distribution curve, multiplying the selected upper and lower quantiles and the preset amplification factor to obtain the data filtering threshold parameters at the current time point.

2. The industrial production data processing method according to claim 1, characterized in that: The collecting and filtering of industrial production data according to the data filtering threshold parameter at the current time point includes: Adjusting a preset rule filtering engine according to the data filtering threshold parameter; According to the adjusted filtering rule engine, industrial production data is collected, and duplicate data and unnecessary data are filtered out.

3. The industrial production data processing method according to claim 1, characterized in that: Inputting the filtered industrial production data into the preset data analysis model to obtain the updated data filtering threshold parameters includes: fitting a probability density distribution curve according to the filtered industrial production data; According to the preset confidence, select the upper and lower quantiles of the probability density distribution curve; Based on the selected upper and lower quantiles and the preset amplification factor, the updated data filtering threshold parameter is obtained.

4. The industrial production data processing method according to any one of claims 1 to 3, characterized in that: The data preprocessing of the historical industrial production data comprises: Fault data, downtime data and outliers in the historical industrial production data are cleared.

5. An industrial production data processing device, characterized in that: Applied to the edge side of an industrial site, the device comprises: A parameter acquisition module, used to acquire a data filtering threshold parameter at a current time point, wherein the data filtering threshold parameter at the current time point is obtained based on a preset data analysis model, wherein the preset data analysis model is constructed based on historical industrial production data and business plan data, and is used to predict the data filtering threshold parameter for historical industrial production data according to preset business plan data; A data processing module, used to collect and filter industrial production data according to the data filtering threshold parameter at the current time point; A parameter updating module, used to select a preset data analysis model from a preset model set according to the equipment identifier and the project identifier in the industrial production data, input the filtered industrial production data into the preset data analysis model, obtain the updated data filtering threshold parameter, and use the updated data filtering threshold parameter as the data filtering threshold parameter at the next time point; A loop processing module, used for controlling the data processing module to re-execute the operation of collecting and filtering industrial production data according to the data filtering threshold parameter at the current time point when the next time point is reached; A parameter generation module is used to extract historical industrial production data within a preset time period, perform data preprocessing on the historical industrial production data, input the historical industrial production data after data preprocessing into a preset data analysis model so that the preset data analysis model performs threshold learning to obtain data filtering threshold parameters at the current time point; and, based on the historical industrial production data after data preprocessing, fit a probability density distribution curve, select the upper and lower quantiles of the probability density distribution curve according to a preset confidence level; and multiply the selected upper and lower quantiles by a preset amplification factor to obtain a data filtering threshold parameter.

6. The device according to claim 5, characterized in that The data processing module is also used to adjust the preset rule filtering engine according to the data filtering threshold parameters, collect industrial production data according to the adjusted filtering rule engine, and filter duplicate data and unnecessary data on the collected industrial production data.

7. The device according to claim 5, characterized in that The parameter updating module is also used to fit a probability density distribution curve according to the filtered industrial production data, select the upper and lower quantiles of the probability density distribution curve according to a preset confidence level, and obtain the updated data filtering threshold parameters based on the selected upper and lower quantiles and a preset amplification factor.

8. The device according to claim 5, characterized in that The parameter generation module is also used to clear fault data, shutdown data and outliers in the historical industrial production data.

9. A computer device, characterized in that: It comprises at least one processor, at least one memory, and a bus; wherein the processor and the memory communicate with each other through the bus; the processor is used to call the program instructions in the memory to execute the method as described in any one of claims 1 to 4.

10. A 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 4 are implemented.

Images