Pollution discharge data early warning method, device, equipment, medium and program product

Abstract

The invention relates to the technical field of data processing, in particular to a pollution discharge data early warning method, device and equipment, a medium and a program product, and the method comprises the steps: carrying out the processing of enterprise historical emission data and a production schedule of a target enterprise based on a trained target prediction model, and obtaining the emission prediction data of various pollutants; processing the various pollutant emission prediction data based on preset early warning threshold information to obtain safety risk early warning information; wherein the training step of the target prediction model comprises the following steps: acquiring industry historical emission data based on the industry category of a target enterprise; obtaining emission mark data based on a production schedule of the target enterprise and the industry historical emission data; and training a preset primary prediction model based on the emission mark data to obtain the target prediction model. The device is convenient for preventing pollution discharge of pollution discharge enterprises from exceeding the standard.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a pollution discharge data early warning method, device, equipment, medium and program product. Background Art

[0002] Polluting enterprises will generate a large amount of pollutants during their operation. In order to prevent pollutant emissions from exceeding the standard, it is necessary to continuously monitor the pollutant emission data and then realize early warning of the pollutant emission data.

[0003] At present, the method to achieve pollution data early warning is: continuously monitor the pollution data of pollution-discharging enterprises to obtain monitoring data, conduct simple statistics on the monitoring data to obtain statistical data, judge whether the statistical data exceeds the standard based on the preset emission threshold, and issue early warning information to the pollution-discharging enterprises when it exceeds the standard.

[0004] However, the current method of early warning of pollution data is to achieve early warning of pollution data based on real-time monitoring data. When the early warning information is issued, the enterprise is still discharging pollutants and cannot shut down the pollution in time, which may easily lead to excessive pollutant emissions. It can be seen that the current method of early warning of pollution data may still cause polluting enterprises to discharge pollutants in excess of standards. Summary of the invention

[0005] In order to prevent polluting enterprises from exceeding the pollution standards, the present application provides a pollution data early warning method, device, equipment, medium and program product.

[0006] In a first aspect, the present application provides a pollution data early warning method, comprising:

[0007] Based on the trained target prediction model, the historical emission data and production schedule of the target enterprise are processed to obtain the emission prediction data of various pollutants;

[0008] Processing the predicted data of various pollutant emissions based on preset warning threshold information to obtain safety risk warning information;

[0009] The training step of the target prediction model includes:

[0010] Obtain historical industry emission data based on the industry category of the target enterprise;

[0011] Obtaining emission labeling data based on the production schedule of the target enterprise and the historical emission data of the industry;

[0012] The target prediction model is obtained by training a preset primary prediction model based on the emission labeling data.

[0013] In a second aspect, the present application provides a pollution data early warning device, comprising:

[0014] A prediction module is used to process the historical emission data and production schedule of the target enterprise based on the trained target prediction model to obtain emission prediction data of various pollutants;

[0015] An early warning module, used to process the predicted data of various pollutant emissions based on preset early warning threshold information to obtain safety risk early warning information;

[0016] The training step of the target prediction model includes:

[0017] Obtain historical industry emission data based on the industry category of the target enterprise;

[0018] Obtaining emission labeling data based on the production schedule of the target enterprise and the historical emission data of the industry;

[0019] The target prediction model is obtained by training a preset primary prediction model based on the emission labeling data.

[0020] In a third aspect, the present application provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method when executing the computer program.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps in the above method when executed by a processor.

[0022] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0023] The above-mentioned pollution data early warning method, device, equipment, medium and program product obtain various pollutant emission prediction data by processing the target enterprise's historical emission data and production schedule based on the trained target prediction model; and obtain safety risk warning information by processing the various pollutant emission prediction data based on the preset warning threshold information; wherein, the training step of the target prediction model includes: obtaining the industry's historical emission data based on the industry category of the target enterprise; obtaining emission label data based on the production schedule of the target enterprise and the industry's historical emission data; and training the preset primary prediction model based on the emission label data to obtain the target prediction model. Through the above implementation, the pollution data of the target enterprise in the future can be predicted, thereby obtaining various pollutant emission prediction data, and the target enterprise can be warned in advance based on the various pollutant emission prediction data, so that the safety risk warning information can be received before the target enterprise's pollutant emission exceeds the standard, so that the pollution discharge can be shut down in time, which is convenient for preventing the pollution discharge enterprises from exceeding the standard.

[0024] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 A flow chart of a pollution discharge data early warning method provided in an embodiment of the present application;

[0027] Figure 2 A flow chart of another pollution discharge data early warning method provided in an embodiment of the present application;

[0028] Figure 3 A schematic diagram of the structure of a pollution discharge data early warning device provided in an embodiment of the present application;

[0029] Figure 4 This is a structural schematic diagram of another pollution discharge data early warning device provided in an embodiment of the present application;

[0030] Figure 5 A schematic diagram of the structure of a computer device provided in an embodiment of the present application;

[0031] Figure 6 This is a diagram of the internal structure of a computer-readable storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present disclosure more clear, the present disclosure 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 disclosure and are not used to limit the present disclosure.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of this article and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of this article described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0034] In this article, the term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the related objects before and after are in an "or" relationship.

[0035] Embodiment 1

[0036] Figure 1 A flow chart of a pollution data early warning method provided in Example 1 of this application, refer to Figure 1 The method may be performed by a device for performing the method, and the device may be implemented by software and / or hardware. The method includes:

[0037] S110. Based on the trained target prediction model, the historical emission data and production schedule of the target enterprise are processed to obtain emission prediction data of various pollutants.

[0038] Among them, the target enterprise is the polluting enterprise that needs to conduct pollution data warning; the historical emission data of the enterprise is the pollutant emission data of the target enterprise in a period of history, and the historical emission data of the enterprise at least includes historical emission data of gaseous pollutants and historical emission data of liquid pollutants. In this embodiment, the historical emission data of the enterprise is preferably the pollutant emission data of the target enterprise in the past year; the production schedule is the time scheduling information of the production activities of the target enterprise; the target prediction model is used to process the historical emission data and production schedule of the target enterprise input therein, and output various types of pollutant emission prediction data, including but not limited to gaseous sulfur oxides, gaseous nitrogen oxides, gaseous particulate matter, wastewater COD, wastewater ammonia nitrogen, acidic wastewater and alkaline wastewater, etc. The emission prediction data is the expected emission data of the corresponding type of pollutants in the future.

[0039] Specifically, the historical emission data and production schedule of the target enterprise are obtained, and the historical emission data and production schedule of the enterprise are input into the trained target prediction model for processing, and the target prediction model outputs the emission prediction data of various pollutants.

[0040] S120, processing the various pollutant emission prediction data based on preset warning threshold information to obtain safety risk warning information.

[0041] Among them, the warning threshold information includes warning thresholds that correspond one-to-one to various types of pollutant emission forecast data. The warning threshold information is established based on the annual total amount of various pollutants that can be emitted by the enterprise and the emission limit standards of various pollutants in the industry. The warning threshold is used to determine whether the corresponding type of pollutant emission forecast data exceeds the standard; if it exceeds the standard, safety risk warning information is sent to the target enterprise. The forms of sending safety risk warning information to the target enterprise include but are not limited to APP notifications, SMS notifications, email notifications, and website notifications. The safety risk warning information is used to remind the target enterprise that at least one pollutant emission forecast data exceeds the standard.

[0042] Specifically, taking one type of pollutant emission prediction data as an example, determine whether the pollutant emission prediction data of this type exceeds the corresponding warning threshold in the warning threshold information. If so, send safety risk warning information to the target enterprise.

[0043] The training step of the target prediction model includes:

[0044] A110. Obtain historical industry emission data based on the industry category of the target enterprise.

[0045] Among them, industry categories include but are not limited to chemical industry, steel industry, thermal power industry, pharmaceutical industry, textile printing and dyeing industry, papermaking industry and food processing industry, etc. The historical emission data of the industry include the types of pollutants, pollutant emissions, pollutant emission time, average emissions, maximum emissions, minimum emissions and emission flow of each pollutant-discharging enterprise in the corresponding industry over a period of time in history. For example, the historical emission data of the industry include the types of pollutants, pollutant emissions, pollutant emission time, etc. of each pollutant-discharging enterprise in the corresponding industry over at least three years in history.

[0046] Specifically, the historical emission data of the industry corresponding to the industry category is obtained according to the industry category of the target enterprise.

[0047] A120. Obtain emission labeling data based on the target enterprise's production schedule and the industry's historical emission data.

[0048] Among them, the data corresponding to the production schedule in the industry's historical emission data can be marked through the production schedule of the target enterprise, and the marked industry's historical emission data is also the emission marking data.

[0049] Specifically, according to the production schedule of the target enterprise, the data corresponding to the production schedule in the industry's historical emission data is marked to obtain emission marking data.

[0050] A130. Train a preset primary prediction model based on the emission labeling data to obtain the target prediction model.

[0051] Among them, the emission label data can be decomposed into a training set and a test set. The preset primary prediction model can be trained through the training set and the test set. The primary prediction model is also an untrained prediction model. In this embodiment, the primary prediction model is constructed based on a multivariate linear regression algorithm. In other embodiments, there is no specific limitation; the target prediction model is a prediction model that has completed training; when training the preset primary prediction model, it is necessary to iteratively train the primary prediction model. Taking one generation of training as an example, the primary prediction model is first trained with the training set to obtain a prediction model to be tested, and then the performance of the prediction model to be tested is evaluated through the test set, and the model parameters of the prediction model to be tested are optimized according to the evaluation results, thereby obtaining the next generation of primary prediction model; and so on, the primary prediction model is trained for multiple generations through emission label data to obtain the target prediction model.

[0052] Specifically, the emission label data is decomposed into a training set and a test set, and the preset primary prediction model is iteratively trained with the training set and the test set to obtain the target prediction model.

[0053] It should be noted that, in this embodiment, the target enterprise's historical emission data and production schedule are processed based on the trained target prediction model to obtain various pollutant emission prediction data; the various pollutant emission prediction data are processed based on the preset warning threshold information to obtain safety risk warning information; wherein, the training step of the target prediction model includes: obtaining the industry's historical emission data based on the industry category of the target enterprise; obtaining emission label data based on the production schedule of the target enterprise and the industry's historical emission data; and training the preset primary prediction model based on the emission label data to obtain the target prediction model. Through the above implementation, the pollution emission data of the target enterprise in the future can be predicted, thereby obtaining various pollutant emission prediction data, and the target enterprise can be warned in advance based on the various pollutant emission prediction data, so that the safety risk warning information can be received before the target enterprise's pollutant emission exceeds the standard, so that the pollution discharge can be shut down in time, which is convenient for preventing the pollution discharge enterprises from exceeding the standard.

[0054] It should also be noted that the core of this application is to use the target prediction model to conduct in-depth analysis and mining of the target enterprise's historical emission data and production schedule, accurately predict future emission trends, and provide timely and accurate data support to enterprises through real-time early warning mechanisms and data calculations to help enterprises formulate response measures. This application has the ability to comprehensively and accurately monitor and warn of data risks, and can provide reference for enterprises to formulate response measures, which has important practical value and social benefits.

[0055] In addition, the pollution data early warning method provided by this application can reduce monitoring costs while ensuring the early warning effect, saving manpower and material resources for enterprises.

[0056] Embodiment 2

[0057] A pollution data early warning method provided in Example 2 of the present application optimizes the "obtaining historical industry emission data based on the industry category of the target enterprise" in Example 1; it should be noted that for the parts not described in detail in this embodiment, reference can be made to the descriptions of other embodiments, and the method includes:

[0058] S210. Based on the trained target prediction model, the historical emission data and production schedule of the target enterprise are processed to obtain emission prediction data of various pollutants.

[0059] S220: Processing the predicted data of various pollutant emissions based on preset warning threshold information to obtain safety risk warning information.

[0060] The training step of the target prediction model includes:

[0061] A211. Determine the industry category of the target enterprise.

[0062] Among them, the industry categories of the target enterprises include but are not limited to the chemical industry, steel industry, thermal power industry, pharmaceutical industry, textile printing and dyeing industry, papermaking industry and food processing industry, etc.; in order to subsequently generate a target prediction model corresponding to the target enterprise, it is necessary to first determine the industry historical emission data corresponding to the industry category of the target enterprise. For this purpose, it is necessary to first determine the industry category corresponding to the target enterprise.

[0063] Specifically, determine the industry category corresponding to the target enterprise.

[0064] A212. Based on the industry category, historical emission data corresponding to the industry category is obtained from a preset pollution emission monitoring platform historical database to obtain industry historical emission data.

[0065] Among them, the historical database of the pollution monitoring platform is used to store historical emission data of various industry categories related to pollution emissions. The historical emission data are the pollutant emission data of the corresponding industry categories in the historical database of the pollution monitoring platform within a period of historical time. In this embodiment, a period of historical time is at least three years; the industry historical emission data are the historical emission data corresponding to the industry categories in the historical database of the pollution monitoring platform.

[0066] Specifically, the historical emission data corresponding to the industry category is obtained from the historical database of the preset pollution monitoring platform, thereby obtaining the historical emission data of the industry.

[0067] A220. Obtain emission labeling data based on the production schedule of the target enterprise and the historical emission data of the industry.

[0068] A230. Train a preset primary prediction model based on the emission labeling data to obtain the target prediction model.

[0069] Embodiment 3

[0070] A pollution data early warning method provided in Example 3 of the present application optimizes the "obtaining emission label data based on the production schedule of the target enterprise and the historical emission data of the industry" in Example 1; it should be noted that for the parts not described in detail in this embodiment, reference can be made to the descriptions of other embodiments, and the method includes:

[0071] S310. Based on the trained target prediction model, the historical emission data and production schedule of the target enterprise are processed to obtain emission prediction data of various pollutants.

[0072] S320: Process the various pollutant emission prediction data based on preset warning threshold information to obtain safety risk warning information.

[0073] The training step of the target prediction model includes:

[0074] A310. Obtain historical industry emission data based on the industry category of the target enterprise.

[0075] A321. Pre-process the historical emission data of the industry to obtain processed data.

[0076] Among them, the industry's historical emission data may have problems such as data errors, data duplication, data missing, and data format errors. Therefore, the industry's historical emission data needs to be preprocessed; the processed data is the industry's historical emission data after preprocessing.

[0077] Specifically, the acquired historical emission data of the industry is preprocessed to obtain processed data.

[0078] A322. Label the processed data based on the production schedule of the target enterprise to obtain emission label data.

[0079] Among them, the production schedule includes the enterprise production time and the enterprise shutdown time. The enterprise production time and the enterprise shutdown time both have corresponding processed data in time. It should be noted that the processed data corresponding to the enterprise shutdown time is not suitable for subsequent training of the primary prediction model. The reason is that the processed data corresponding to the enterprise shutdown time is stable and abnormal. For example, stability and abnormality are reflected in the emission volume continuing to be 0 and the total emission volume continuing to remain unchanged. This type of processed data is not suitable for subsequent training of the primary prediction model. For this reason, it is necessary to mark the data corresponding to the enterprise shutdown time in the processed data; emission marking data is also processed data containing some marked data.

[0080] Specifically, the production stop time of the target enterprise in the production schedule is obtained, and the data corresponding to the production stop time in the processed data is marked, thereby obtaining emission marking data.

[0081] It should be noted that when the primary prediction model is subsequently trained using the emission labeling data, the labeled data needs to be excluded and the remaining data needs to be decomposed into a training set and a test set.

[0082] A330. Train a preset primary prediction model based on the emission labeling data to obtain the target prediction model.

[0083] Embodiment 4

[0084] A pollution data early warning method provided in Example 4 of the present application optimizes the "preprocessing the historical emission data of the industry to obtain processed data" in Example 3; it should be noted that for the parts not described in detail in this embodiment, reference can be made to the descriptions of other embodiments, and the method includes:

[0085] S410, based on the trained target prediction model, the historical emission data and production schedule of the target enterprise are processed to obtain emission prediction data of various pollutants.

[0086] S420: Process the various pollutant emission prediction data based on preset warning threshold information to obtain safety risk warning information.

[0087] The training step of the target prediction model includes:

[0088] A410. Obtain historical industry emission data based on the industry category of the target enterprise.

[0089] A421A. Correct the historical emission data of the industry to obtain corrected data.

[0090] Among them, there may be a certain amount of erroneous data in the industry's historical emission data, so it is necessary to correct the industry's historical emission data. In this embodiment, the least squares correction algorithm is specifically used to correct the data. In other embodiments, the hash error correction code algorithm can also be used to correct the industry's historical emission data, without specific limitation.

[0091] Specifically, the industry's historical emission data is corrected based on a preset correction algorithm to correct the data.

[0092] A421B, deduplicate the correction data to obtain deduplicated data.

[0093] Among them, there may be a certain amount of duplicate data in the correction data, so the correction data needs to be deduplicated. In this embodiment, a hash algorithm is specifically used to deduplicate the correction data. In other embodiments, a distributed deduplication algorithm can also be used to deduplicate the correction data, which is not specifically limited.

[0094] Specifically, the correction data is deduplicated based on a preset deduplication algorithm to obtain deduplicated data.

[0095] A421C. Perform format conversion on the deduplicated data to obtain converted data.

[0096] Among them, there may be a certain amount of data with inconsistent data formats in the deduplicated data, that is, there is a small amount of data in the deduplicated data, and the data format of this small amount of data is inconsistent with the mainstream data format of the deduplicated data. Therefore, the deduplicated data needs to be format converted.

[0097] Specifically, it is determined that data in the deduplicated data whose data format is inconsistent with the mainstream data format is obtained to obtain non-mainstream format data, and the data format of the non-data stream format data is converted into the mainstream data format, thereby obtaining converted data.

[0098] A421D. Fill missing values ​​in the converted data to obtain the processed data.

[0099] Among them, there may be a certain number of missing values ​​in the converted data. Therefore, it is necessary to fill the missing values ​​in the converted data. In this embodiment, a missing value filling algorithm selected from the mean filling algorithm, the median filling algorithm, the mode filling algorithm, the difference filling algorithm and the K nearest neighbor filling algorithm can be used to fill the missing values ​​in the converted data. There is no specific limitation in other embodiments.

[0100] Specifically, missing values ​​are filled in the converted data based on a preset missing value filling algorithm to obtain processed data.

[0101] It should be noted that the correction, deduplication, format conversion and missing value filling of the correction data in sequence conforms to the sequential processing logic of preprocessing the correction data. In addition, the accuracy of the correction data can be improved by correcting, deduplication, format conversion and missing value filling of the correction data in sequence, so that the processed data with higher accuracy can be applied to the subsequent primary prediction model, thereby improving the training effect of the primary prediction model.

[0102] A422. Label the processed data based on the production schedule of the target enterprise to obtain emission label data.

[0103] A430. Train a preset primary prediction model based on the emission labeling data to obtain the target prediction model.

[0104] Embodiment 5

[0105] A pollution data early warning method provided in Example 5 of the present application optimizes the "processing the various types of pollutant emission prediction data based on preset early warning threshold information to obtain safety risk early warning information" in Example 1; it should be noted that the early warning threshold information includes a single type of early warning threshold corresponding to the various types of pollutant emission prediction data; for the parts not described in detail in this embodiment, please refer to the description of other embodiments, the method includes:

[0106] S510. Based on the trained target prediction model, the historical emission data and production schedule of the target enterprise are processed to obtain emission prediction data of various pollutants.

[0107] S520: In response to at least one type of pollutant emission prediction data among the various types of pollutant emission prediction data exceeding the corresponding single-type warning threshold, issuing safety risk warning information to the target enterprise.

[0108] Among them, the warning threshold information includes single-type warning thresholds corresponding to various types of pollutant emission prediction data; illustratively, one type of pollutant emission prediction data among the various types of pollutant emission prediction data is the total amount of gaseous pollutant emissions, and the warning threshold information presets a single-type warning threshold of the total amount of gaseous pollutant emissions threshold for the total amount of gaseous pollutant emissions; if a type of pollutant emission prediction data exceeds the corresponding single-type warning threshold, it is necessary to send the target enterprise the safety risk warning information corresponding to the type of pollutant emission prediction data, such as sending "The total amount of gaseous pollutant emissions is about to exceed the standard, please pay attention in time."

[0109] Specifically, if it is determined that at least one type of pollutant emission prediction data among various types of pollutant emission prediction data exceeds the corresponding single-type warning threshold, safety risk warning information is immediately sent to the target enterprise.

[0110] It should be noted that sending safety risk warning information to target enterprises will help prevent the risk of enterprises exceeding pollution discharge standards.

[0111] The training step of the target prediction model includes:

[0112] A510. Obtain historical industry emission data based on the industry category of the target enterprise.

[0113] A520. Obtain emission labeling data based on the production schedule of the target enterprise and the historical emission data of the industry.

[0114] A530. Train a preset primary prediction model based on the emission labeling data to obtain the target prediction model.

[0115] Embodiment 6

[0116] Figure 2 A flow chart of a pollution data early warning method provided in Example 1 of this application, refer to Figure 2 The method may be performed by a device for performing the method, and the device may be implemented by software and / or hardware. The method includes:

[0117] S610. Based on the trained target prediction model, the historical emission data and production schedule of the target enterprise are processed to obtain emission prediction data of various pollutants.

[0118] S620: Process the predicted data of various pollutant emissions based on preset warning threshold information to obtain safety risk warning information.

[0119] The training step of the target prediction model includes:

[0120] A610. Obtain historical industry emission data based on the industry category of the target enterprise.

[0121] A620. Obtain emission labeling data based on the production schedule of the target enterprise and the historical emission data of the industry.

[0122] A630. Train a preset primary prediction model based on the emission labeling data to obtain the target prediction model.

[0123] S630, managing the enterprise's historical emission data, the forecast data for various types of pollutant emissions, the safety risk warning information, the industry's historical emission data, the production schedule, and the emission labeling data to obtain management data.

[0124] Among them, management means storing, backing up, restoring and sharing data, and management data means the data obtained after managing the company's historical emission data, various pollutant emission forecast data, safety risk warning information, industry historical emission data, production schedules and emission labeling data.

[0125] Specifically, the company's historical emission data, various pollutant emission forecast data, safety risk warning information, industry historical emission data, production schedules and emission labeling data are managed to obtain management data.

[0126] It should be noted that by managing the company's historical emission data, various pollutant emission forecast data, safety risk warning information, industry historical emission data, production schedules and emission labeling data, the efficiency and accuracy of subsequent data processing can be improved, and the unified management and application of various data can be facilitated.

[0127] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0128] Embodiment 7

[0129] Based on the same inventive concept, this embodiment also provides a pollution data early warning device for implementing the pollution data early warning method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more pollution data early warning device embodiments provided below can refer to the limitations of the pollution data early warning method above, and will not be repeated here.

[0130] In this embodiment, Figure 3 As shown, a pollution discharge data early warning device is provided, comprising:

[0131] The prediction module is used to process the historical emission data and production schedule of the target enterprise based on the trained target prediction model to obtain the emission prediction data of various pollutants.

[0132] The early warning module is used to process the predicted data of various pollutant emissions based on preset early warning threshold information to obtain safety risk early warning information.

[0133] The training step of the target prediction model includes:

[0134] Obtain historical industry emissions data based on the industry category of the target enterprise.

[0135] Emission labeling data is obtained based on the production schedule of the target enterprise and the historical emission data of the industry.

[0136] The target prediction model is obtained by training a preset primary prediction model based on the emission labeling data.

[0137] Embodiment 8

[0138] Based on the same inventive concept, this embodiment further provides a pollution data early warning device for implementing the pollution data early warning method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more pollution data early warning device embodiments provided below can refer to the limitations of the pollution data early warning method above, and will not be repeated here.

[0139] In this embodiment, Figure 4 As shown, a pollution discharge data early warning device is provided, comprising:

[0140] The prediction module is used to process the historical emission data and production schedule of the target enterprise based on the trained target prediction model to obtain the emission prediction data of various pollutants.

[0141] The early warning module is used to process the predicted data of various pollutant emissions based on preset early warning threshold information to obtain safety risk early warning information.

[0142] The training step of the target prediction model includes:

[0143] Obtain historical industry emissions data based on the industry category of the target enterprise.

[0144] Emission labeling data is obtained based on the production schedule of the target enterprise and the historical emission data of the industry.

[0145] The target prediction model is obtained by training a preset primary prediction model based on the emission labeling data.

[0146] A management module is used to manage the enterprise's historical emission data, the forecast data of various pollutant emissions, the safety risk warning information, the industry's historical emission data, the production schedule and the emission labeling data to obtain management data.

[0147] Each module in the above-mentioned pollution data early warning device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned 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 in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0148] It should be noted that, in this embodiment, the target enterprise's historical emission data and production schedule are processed based on the trained target prediction model to obtain various pollutant emission prediction data; the various pollutant emission prediction data are processed based on the preset warning threshold information to obtain safety risk warning information; wherein, the training step of the target prediction model includes: obtaining the industry's historical emission data based on the industry category of the target enterprise; obtaining emission label data based on the production schedule of the target enterprise and the industry's historical emission data; and training the preset primary prediction model based on the emission label data to obtain the target prediction model. Through the above implementation, the pollution emission data of the target enterprise in the future can be predicted, thereby obtaining various pollutant emission prediction data, and the target enterprise can be warned in advance based on the various pollutant emission prediction data, so that the safety risk warning information can be received before the target enterprise's pollutant emission exceeds the standard, so that the pollution discharge can be shut down in time, which is convenient for preventing the pollution discharge enterprises from exceeding the standard.

[0149] Embodiment 9

[0150] In this embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory and a network interface 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. 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, a pollution data early warning method is implemented.

[0151] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present disclosure, and does not constitute a limitation on the computer device to which the scheme of the present disclosure 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.

[0152] Embodiment 10

[0153] In this embodiment, a computer readable storage medium is provided. Figure 6 As shown, a computer program is stored thereon, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0154] Embodiment 11

[0155] In this embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0156] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0157] 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 the memory, database or other medium used in the embodiments provided by the present disclosure can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided by the present disclosure may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto. The processor involved in each embodiment provided by the present disclosure may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited thereto.

[0158] 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.

[0159] The above-described embodiments only express several implementation methods of the present disclosure, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present disclosure, and these all belong to the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the attached claims.

Claims

1. A pollution discharge data early warning method, characterized in that: include: Based on the trained target prediction model, the historical emission data and production schedule of the target enterprise are processed to obtain the emission prediction data of various pollutants; Processing the predicted data of various pollutant emissions based on preset warning threshold information to obtain safety risk warning information; The training steps of the target prediction model include: Obtain historical industry emission data based on the industry category of the target enterprise; Obtaining emission labeling data based on the production schedule of the target enterprise and the historical emission data of the industry; The target prediction model is obtained by training a preset primary prediction model based on the emission label data.

2. The method according to claim 1, characterized in that The historical emission data of the industry is obtained based on the industry category of the target enterprise, including: Determine the industry category of the target enterprise; Based on the industry category, historical emission data corresponding to the industry category is obtained from a preset pollution emission monitoring platform historical database to obtain industry historical emission data.

3. The method according to claim 1, characterized in that The emission marking data is obtained based on the production schedule of the target enterprise and the historical emission data of the industry, including: Preprocessing the historical emission data of the industry to obtain processed data; The processed data is marked based on the production schedule of the target enterprise to obtain emission marking data.

4. The method according to claim 3, characterized in that The preprocessing of the industry historical emission data to obtain processed data includes: Correcting the historical emission data of the industry to obtain corrected data; Deduplication of the correction data to obtain deduplication data; Performing format conversion on the deduplicated data to obtain converted data; Missing values ​​are filled in the converted data to obtain the processed data.

5. The method according to claim 1, characterized in that The warning threshold information includes a single type of warning threshold corresponding to each type of pollutant emission prediction data; the safety risk warning information is obtained by processing the various types of pollutant emission prediction data based on the preset warning threshold information, including: In response to at least one type of pollutant emission prediction data among the various types of pollutant emission prediction data exceeding the corresponding single-type warning threshold, safety risk warning information is issued to the target enterprise.

6. The method according to claim 1, characterized in that Also includes: The historical emission data of the enterprise, the emission forecast data of various pollutants, the safety risk warning information, the historical emission data of the industry, the production schedule and the emission label data are managed to obtain management data.

7. A pollution data early warning device, characterized in that: The device comprises: A prediction module is used to process the historical emission data and production schedule of the target enterprise based on the trained target prediction model to obtain emission prediction data of various pollutants; An early warning module, used to process the predicted data of various pollutant emissions based on preset early warning threshold information to obtain safety risk early warning information; The training step of the target prediction model includes: Obtain historical industry emission data based on the industry category of the target enterprise; Obtaining emission labeling data based on the production schedule of the target enterprise and the historical emission data of the industry; The target prediction model is obtained by training a preset primary prediction model based on the emission label data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. 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 6 are implemented.

10. A computer program product, comprising a computer program, 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 6 are implemented.

Images