Urban hazardous waste output prediction method and device based on deep learning
Through a deep learning-based method, the prediction model is corrected by using the timing generation quantity and the generation quantity increase, and the problem that the existing technology cannot predict the fluctuations in solid waste production volume are solved, and the prediction accuracy and resource utilization efficiency are improved.
Patent Information
- Application Number
- CN202411157132.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing solid waste production forecasting method cannot effectively predict fluctuations in solid waste production in cases such as sudden events, resulting in low prediction accuracy.
The urban hazardous waste generation forecast method is adopted based on deep learning. By obtaining the timing generation amount and timing generation increase of each hazardous solid waste generation unit, the target timing generation amount is determined using the timing prediction model and the correction model, and the corrected generation amount is determined. As a prediction result, the accuracy of the prediction is improved.
A reasonable prediction of the fluctuations in the amount of hazardous solid waste is achieved, the accuracy of prediction is improved, and the production is accurately predicted in emergencies and other situations is possible, which improves the efficiency of solid waste resource utilization.
Smart Images

Figure CN119067306A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of solid waste utilization planning, and more specifically, to a method and device for predicting the amount of urban hazardous waste generated based on deep learning. Background Art
[0002] The efficient resource utilization of urban solid waste is an important issue in urban development. Among them, hazardous solid waste includes chemicals and chemical products (such as batteries, medicines, paints, pesticides and other solid wastes), industrial waste (such as mineral oil, solvents, metal processing waste, electroplating waste and other solid wastes), electronic waste (such as computers, mobile phones, televisions and other electronic product solid wastes) and medical waste (such as infectious waste, pathological waste, chemical waste and other solid wastes). How to recycle hazardous solid waste is a key issue in the resource utilization of solid waste. Therefore, predicting the generation of hazardous solid waste is a key link in the efficient recycling and utilization of subsequent hazardous solid waste.
[0003] Patent application CN113761801A (application number: CN202111051983.8) provides an intelligent prediction method for electronic solid waste generation, including obtaining historical data related to the electronic solid waste generation in the area to be predicted, and randomly dividing the historical data into a training set and a test set; using the training set to establish a mechanism model of electronic solid waste generation, solving the mechanism model, and obtaining an output prediction sequence of the mechanism model; intelligently compensating for the error between the output prediction sequence of the mechanism model and the actual electronic solid waste generation, and obtaining an intelligent prediction result of electronic solid waste generation. The intelligent prediction method for electronic solid waste generation in patent application CN113761801A can intelligently compensate for the modeling error of the mechanism model, but the intelligent prediction method for solid waste generation cannot reasonably predict the fluctuation of solid waste generation in situations such as sudden events. Summary of the invention
[0004] The purpose of this application is to provide a method and device for predicting the amount of urban hazardous waste generated based on deep learning, which solves the technical problem that it is impossible to reasonably predict the fluctuations in the amount of solid waste generated in situations such as sudden events, and achieves the technical effect of reasonably predicting the fluctuations in the amount of hazardous solid waste generated.
[0005] An embodiment of the present application provides a method for predicting the amount of urban hazardous waste generated based on deep learning, the method comprising: obtaining the time series generation amount of hazardous solid waste and the time series generation amount increase of each hazardous solid waste generating unit in the target area; wherein the time interval for obtaining the time series generation amount increase in each time period is smaller than the time interval for obtaining the time series generation amount; determining the predicted time series generation amount of each hazardous solid waste generating unit according to the time series generation amount of hazardous solid waste of each hazardous solid waste generating unit through a hazardous solid waste time series generation prediction model; determining the target time series generation amount of each hazardous solid waste generating unit according to the time series generation amount and the time series generation amount increase of each hazardous solid waste generating unit through a hazardous solid waste time series generation correction model, and taking the sum of the target time series generation amounts of all hazardous solid waste generating units in the target area as the prediction result of the hazardous solid waste generation amount in the target area.
[0006] In a possible implementation, the method also includes: obtaining the first mutation time point at which the time series generation increase of the target hazardous solid waste generating unit is greater than a preset time series generation increase, and obtaining the time series generation increase of the target hazardous solid waste generating unit after the first mutation time point; when the time series generation increase of the target hazardous solid waste generating unit after the first mutation time point meets the preset increase condition, retaining the time series generation increase at the first mutation time point in the time series generation increase; when the time series generation increase of the target hazardous solid waste generating unit after the first mutation time point does not meet the preset increase condition, replacing the time series generation increase at the first mutation time point with the historical time series generation increase.
[0007] In another possible implementation, the preset increase condition includes: the difference between the average value of the time series production increase of the target hazardous solid waste producing unit at the first mutation time point and after the first mutation time point and the preset time series production increase is less than the preset increase difference.
[0008] In another possible implementation, the method also includes: obtaining a second mutation time point at which the increase in the time series generation amount of the target hazardous solid waste generating unit is greater than a preset multiple of the preset time series generation amount increase; when the difference between the mean of the time series generation amount increase of the target hazardous solid waste generating unit after the second mutation time point and the preset time series generation amount increase is greater than or equal to the preset increase difference of the preset multiple, taking the time series generation amount of the target hazardous solid waste generating unit after the second mutation time point as the corrected time series generation amount, and taking the time series generation amount increase of the target hazardous solid waste generating unit after the second mutation time point as the corrected time series generation amount increase; determining the corrected predicted time series generation amount of the target hazardous solid waste generating unit according to the corrected time series generation amount through a hazardous solid waste time series generation amount prediction model; determining the corrected target time series generation amount of the target hazardous solid waste generating unit according to the corrected predicted time series generation amount and the corrected time series generation amount increase through a hazardous solid waste time series generation amount correction model.
[0009] In another possible implementation, the method also includes: when the time series generation increase of the target hazardous solid waste producing unit is greater than a preset multiple of the preset time series generation increase, obtaining the target type of hazardous solid waste corresponding to the hazardous solid waste produced by the target hazardous solid waste producing unit, obtaining a set of hazardous solid waste producing units that produce the target type of hazardous solid waste in the target area, and obtaining the first time series total generation of hazardous solid waste of the target type of all hazardous solid waste producing units in the set of hazardous solid waste producing units; determining the first predicted time series generation of hazardous solid waste of the target type of the set of hazardous solid waste producing units according to the first time series total generation through a hazardous solid waste time series total generation prediction model; and predicting the hazardous solid waste generation of hazardous solid waste types other than the target type in the target area to obtain a second predicted time series generation of hazardous solid waste types other than the target type; and taking the sum of the first predicted time series generation amount and the second predicted time series generation amount as the target time series total generation amount of the target area.
[0010] In another possible implementation, the first time series total generation of hazardous solid waste of the target type of all hazardous solid waste generating units in the set of hazardous solid waste generating units is obtained, including: obtaining a second mutation time point at which the time series generation increase of hazardous solid waste of the target type of the target hazardous solid waste generating unit is greater than a preset multiple of the preset time series generation increase, and obtaining the first time series total generation of hazardous solid waste of the target type of all hazardous solid waste generating units in the set of hazardous solid waste generating units starting from the second mutation time point; determining the first predicted time series generation of hazardous solid waste of the target type of the set of hazardous solid waste generating units according to the first time series total generation through a hazardous solid waste time series total generation prediction model, including: starting from the second mutation time point, determining the first predicted time series generation of hazardous solid waste of the target type of the set of hazardous solid waste generating units according to the first time series total generation through a hazardous solid waste time series total generation prediction model.
[0011] In another possible implementation, the method also includes: when the time series generation increase of the target hazardous solid waste producing unit is greater than a preset multiple of the preset time series generation increase, obtaining the relevant hazardous solid waste corresponding to the target type of hazardous solid waste produced by the target hazardous solid waste producing unit, and obtaining the set of relevant hazardous solid waste producing units that produce the relevant hazardous solid waste, and determining the correlation factors of the target type of hazardous solid waste and the relevant hazardous solid waste; wherein the relevant hazardous solid waste includes the upstream hazardous solid waste and downstream hazardous solid waste of the target type of hazardous solid waste; through the hazardous solid waste time series total generation prediction model, the predicted time series generation of the relevant hazardous solid waste producing unit set is determined according to the time series total generation of the relevant hazardous solid waste of the relevant hazardous solid waste producing unit set in time series.
[0012] In another possible implementation, the correlation factors of the target type of hazardous solid waste and the related hazardous solid waste are determined, including: obtaining the related production amount of the related hazardous solid waste corresponding to the target production amount of the target type of hazardous solid waste, and taking the ratio of the related production amount to the target production amount as the correlation factor.
[0013] An embodiment of the present application also provides a device for predicting the amount of urban hazardous waste generated based on deep learning, comprising a unit for executing any of the above methods.
[0014] An embodiment of the present application also provides a device for predicting the amount of urban hazardous waste generated based on deep learning, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the methods described above when executing the computer program.
[0015] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the above items is implemented.
[0016] An embodiment of the present application also provides a computer program product, including a computer program, which implements the steps of any of the methods described above when executed by a processor.
[0017] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:
[0018] The embodiment of the present application provides a method for predicting the generation of urban hazardous waste based on deep learning, and the method includes: obtaining the time series generation of hazardous solid waste and the time series generation increase of each hazardous solid waste generating unit in the target area; determining the predicted time series generation of each hazardous solid waste generating unit according to the time series generation of hazardous solid waste of each hazardous solid waste generating unit through the prediction model of the time series generation of hazardous solid waste; determining the target time series generation of each hazardous solid waste generating unit according to the time series generation and the time series generation increase of each hazardous solid waste generating unit through the correction model of the time series generation of hazardous solid waste, and taking the sum of the target time series generation of all hazardous solid waste generating units in the target area as the prediction result of the generation of hazardous solid waste in the target area. The method in the embodiment of the present application can determine the predicted time series generation of each hazardous solid waste generating unit, and can determine the target time series generation of each hazardous solid waste generating unit according to the time series generation and the time series generation increase of each hazardous solid waste generating unit, and the target time series generation is the hazardous solid waste generation corrected according to the time series generation increase, thereby improving the accuracy of the prediction of the generation of hazardous solid waste. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0020] Figure 1 A flowchart of a method for predicting the amount of urban hazardous waste generated based on deep learning provided in an embodiment of the present application;
[0021] Figure 2 A schematic diagram of the workflow of a method for predicting the amount of urban hazardous waste generated based on deep learning provided in an embodiment of the present application;
[0022] Figure 3 A schematic diagram of a timing generation quantity increase provided in an embodiment of the present application;
[0023] Figure 4 A schematic diagram of another timing generation quantity increase provided in an embodiment of the present application;
[0024] Figure 5 A schematic diagram of the logical structure of a device for predicting the amount of urban hazardous waste generated based on deep learning provided in an embodiment of the present application;
[0025] Figure 6 A schematic diagram of the physical structure of a device for predicting the amount of urban hazardous waste generated based on deep learning provided in an embodiment of the present application. DETAILED DESCRIPTION
[0026] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.
[0027] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0028] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.
[0029] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.
[0030] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.
[0031] The existing prediction method for solid waste generation can compensate for the modeling error of the mechanism model, but the intelligent prediction method for solid waste generation cannot reasonably predict the fluctuation of solid waste generation in situations such as sudden events.
[0032] Based on the above reasons, an embodiment of the present application provides a method for predicting the generation of urban hazardous waste based on deep learning, and the method includes: obtaining the time series generation of hazardous solid waste and the time series generation increase rate of each hazardous solid waste generating unit in the target area; determining the predicted time series generation of each hazardous solid waste generating unit according to the time series generation of hazardous solid waste of each hazardous solid waste generating unit through a hazardous solid waste time series generation prediction model; determining the target time series generation of each hazardous solid waste generating unit according to the time series generation and the time series generation increase rate of each hazardous solid waste generating unit through a hazardous solid waste time series generation correction model, and taking the sum of the target time series generation of all hazardous solid waste generating units in the target area as the prediction result of the hazardous solid waste generation in the target area. The method in the embodiment of the present application can determine the predicted time series generation amount of each hazardous solid waste producing unit, and can determine the target time series generation amount of each hazardous solid waste producing unit based on the time series generation amount and the time series generation amount increase of each hazardous solid waste producing unit. The target time series generation amount is the hazardous solid waste generation amount corrected according to the time series generation amount increase, which improves the accuracy of the hazardous solid waste generation prediction.
[0033] In some scenarios, a method for predicting urban hazardous waste generation based on deep learning in an embodiment of the present application can be applied to the resource utilization planning of urban hazardous solid waste. It can plan the resource utilization of hazardous solid waste according to the predicted hazardous solid waste generation, and can improve the efficiency of solid waste resource utilization.
[0034] The following is a detailed description of a method for predicting the amount of urban hazardous waste generated based on deep learning provided in an embodiment of the present application with reference to specific examples.
[0035] Figure 1 A flowchart of a method for predicting the amount of urban hazardous waste generated based on deep learning is provided in an embodiment of the present application, such as Figure 1 As shown, the method includes S110 to S120, and S110 to S120 are described in detail below.
[0036] S110. Obtain the time series generation amount and time series generation amount increase of hazardous solid waste for each hazardous solid waste generating unit in the target area; wherein the time interval for obtaining the time series generation amount increase in each time period is shorter than the time interval for obtaining the time series generation amount.
[0037] In order to predict the time series generation of hazardous solid waste, the time series generation of hazardous solid waste of each hazardous solid waste generating unit in the target area can be obtained, and then the time series generation of hazardous solid waste can be predicted through the time series prediction model.
[0038] Exemplarily, the time series generation amount of hazardous solid waste by each hazardous solid waste generating unit includes the moment information at the end of each preset time period and the generation amount information of hazardous solid waste.
[0039] In order to further improve the prediction accuracy of the time series generation amount, the time series generation amount may be corrected by the time series generation amount increase, and the time series generation amount increase represents the variation characteristics of the time series generation amount in each time period.
[0040] Exemplarily, the time series generation amount increase of hazardous solid waste of each hazardous solid waste generating unit includes a plurality of moment information in each preset time period and the generation amount increase of hazardous solid waste in the time period corresponding to the plurality of moment information respectively.
[0041] Exemplarily, the length of the preset time period may be 12 hours to 24 hours.
[0042] When obtaining the increase in the timing generation amount, within each time period, the time interval of the obtained timing generation amount increase is smaller than the time interval of obtaining the timing generation amount, so that the timing generation amount increase can correct the timing generation amount at a finer time granularity, thereby improving the prediction accuracy of the timing generation amount.
[0043] Exemplarily, when the time interval for detecting the timing generation amount is 12 hours, the time interval for increasing the timing generation amount may be 3 hours to 4 hours.
[0044] Exemplarily, when obtaining the time-series generation amount and time-series generation amount of hazardous solid waste, the time-series generation amount and time-series generation amount of hazardous solid waste can be obtained through a networked device capable of automatic weighing.
[0045] S120. Determine the predicted time series generation of each hazardous solid waste generating unit according to the time series generation of hazardous solid waste of each hazardous solid waste generating unit through the prediction model of time series generation of hazardous solid waste. Determine the target time series generation of each hazardous solid waste generating unit according to the time series generation and time series generation increment of each hazardous solid waste generating unit through the correction model of time series generation of hazardous solid waste. The sum of the target time series generation of all hazardous solid waste generating units in the target area is taken as the prediction result of the hazardous solid waste generation in the target area.
[0046] Figure 2 A schematic diagram of the workflow of a method for predicting the amount of urban hazardous waste generated based on deep learning provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, firstly, the predicted time series generation amount of each hazardous solid waste producing unit can be determined according to the time series generation amount of hazardous solid waste of each hazardous solid waste producing unit through the hazardous solid waste time series generation amount prediction model, and then the time series generation amount of hazardous solid waste can be predicted according to the predicted time series generation amount.
[0047] Exemplarily, the hazardous solid waste time series generation prediction model can be a LSTM-based time series prediction model. When training the hazardous solid waste time series generation prediction model, it can be trained by actually detecting and collecting the historical time series generation and the historical actual time series generation of each hazardous solid waste generating unit.
[0048] like Figure 2 As shown, after obtaining the time series generation amount, the time series generation amount correction model of hazardous solid waste can be used to determine the target time series generation amount of each hazardous solid waste generating unit according to the time series generation amount and time series generation amount increase of each hazardous solid waste generating unit, so as to realize the correction of the time series generation amount.
[0049] After obtaining the target time series generation amount of each hazardous solid waste generating unit, the sum of the target time series generation amounts of all hazardous solid waste generating units in the target area can be used as the prediction result of the hazardous solid waste generation amount in the target area.
[0050] Exemplarily, when training a hazardous solid waste time series generation correction model, it can be trained through the predicted time series generation of each hazardous solid waste generating unit, the actual detected historical time series generation increase and the actual detected historical time series generation. The difference between the historical time series generation and the predicted time series generation can be corrected through the hazardous solid waste time series generation correction model.
[0051] The beneficial effect brought about by the above-mentioned implementation method is that the time-series generation amount can be corrected by the time-series generation amount increase of hazardous solid waste, and the accuracy of the prediction of the time-series generation amount can be improved according to the fluctuation of the hazardous solid waste generation amount.
[0052] The beneficial effect brought about by the above implementation method is that the time interval for obtaining the timing generation amount increase is smaller than the time interval for obtaining the timing generation amount, so that the timing generation amount increase can correct the timing generation amount at a finer time granularity, thereby ensuring the accuracy of the timing generation amount correction.
[0053] When the amount of solid waste generated fluctuates greatly, the situation with large fluctuations can be processed to improve the accuracy of the time series generation prediction.
[0054] In some implementations, the above method further includes S210 to S220, and S210 to S220 are described in detail below.
[0055] S210, obtaining the first mutation time point at which the increase in the time series production volume of the target hazardous solid waste producing unit is greater than a preset increase in the time series production volume, and obtaining the increase in the time series production volume of the target hazardous solid waste producing unit after the first mutation time point.
[0056] After obtaining the time series generation increase at all moments, the first mutation time point at which the time series generation increase of the target hazardous solid waste generating unit is greater than the preset time series generation increase can be obtained, and then the time series generation increase of the target hazardous solid waste generating unit after the first mutation time point can be obtained, so as to facilitate the processing of the time series generation increase at the first mutation time point and after the first mutation time point to improve the prediction accuracy of the time series generation.
[0057] Exemplarily, the preset timing generation amount increase may be 90% to 200%.
[0058] S220: When the increase in the time series production volume of the target hazardous solid waste generating unit after the first mutation time point meets the preset increase condition, the increase in the time series production volume at the first mutation time point is retained in the increase in the time series production volume. When the increase in the time series production volume of the target hazardous solid waste generating unit after the first mutation time point does not meet the preset increase condition, the increase in the time series production volume at the first mutation time point is replaced by the increase in the historical time series production volume.
[0059] After obtaining the time series generation volume increase data of the target hazardous solid waste producing unit after the first mutation time point, a preset increase condition can be set to determine whether the time series generation volume increase after the first mutation time point will affect the prediction accuracy of the time series generation volume. When the time series generation volume increase of the target hazardous solid waste producing unit after the first mutation time point meets the preset increase condition, it means that the time series generation volume increase after the first mutation time point does not affect the accuracy of the predicted time series generation volume, and then the time series generation volume increase at the first mutation time point can be retained in the time series generation volume increase to achieve the prediction of the time series generation volume.
[0060] After obtaining the time series generation volume increase data of the target hazardous solid waste producing unit after the first mutation time point, when the time series generation volume increase of the target hazardous solid waste producing unit after the first mutation time point does not meet the preset increase condition, it means that the time series generation volume increase after the first mutation time point may affect the accuracy of the predicted time series generation volume. The time series generation volume increase at the first mutation time point can be replaced by the historical time series generation volume increase to ensure the subsequent prediction accuracy of the time series generation volume.
[0061] Exemplarily, when replacing the time series generation amount increase at the first mutation time point with the historical time series generation amount increase, the time series generation amount increase at the first mutation time point can be replaced by the average of the historical time series generation amount increase, or the time series generation amount increase at the first mutation time point can be replaced by interpolating the historical time series generation amount increase.
[0062] The beneficial effect brought about by the above-mentioned implementation method is that a preset increase condition is set to determine whether the increase in the timing generation amount after the first mutation time point will affect the prediction accuracy of the timing generation amount, so as to ensure the accuracy of the prediction of the timing generation amount, so as to avoid excessive fluctuations in the timing generation amount, which will affect the prediction accuracy of the timing generation amount.
[0063] In some implementations, in order to ensure the accuracy of the time series production volume prediction, the preset increase conditions include: the difference between the average value of the time series production volume increase of the target hazardous solid waste producing unit at the first mutation time point and after the first mutation time point and the preset time series production volume increase is less than the preset increase difference.
[0064] Figure 3 A schematic diagram of a timing generation amount increase provided in an embodiment of the present application, such as Figure 3 As shown by the solid line in the figure, the difference between the average value of the time series generation increase of the target hazardous solid waste generating unit at the first mutation time point and after the first mutation time point and the preset time series generation increase is less than the preset increase difference, indicating that there is no major mutation in the time series generation after the first mutation time point, and will not affect the prediction accuracy of the subsequent time series generation. At this time, the time series generation increase at the first mutation time point can be retained in the time series generation increase to achieve the prediction of the time series generation.
[0065] like Figure 3 As shown by the dotted line in the figure, the difference between the average value of the time series generation increase of the target hazardous solid waste generating unit at the first mutation time point and after the first mutation time point and the preset time series generation increase is greater than or equal to the preset increase difference, indicating that a large mutation has occurred in the time series generation after the first mutation time point, which may affect the prediction accuracy of the subsequent time series generation. At this time, the time series generation increase at the first mutation time point can be replaced by the historical time series generation increase to ensure the subsequent prediction accuracy of the time series generation.
[0066] Exemplarily, the preset increase difference may be 50% to 80%.
[0067] The beneficial effect brought by the above implementation method is that it is possible to judge whether to retain the increase in the timing generation amount at the first mutation time point by the average value of the increase in the timing generation amount at the first mutation time point and after the first mutation time point. The average value of the increase in the timing generation amount at the first mutation time point and after the first mutation time point represents the magnitude of the fluctuation amplitude of the timing generation amount at the first mutation time point, thereby ensuring the accuracy of the prediction of the timing generation amount.
[0068] In some implementations, the above method further includes S310 to S320, and S310 to S320 are described in detail below.
[0069] S310, obtaining a second mutation time point at which the increase in the time series production volume of the target hazardous solid waste generating unit is greater than a preset multiple of the preset time series production volume increase. When the difference between the mean of the time series production volume increase of the target hazardous solid waste generating unit after the second mutation time point and the preset time series production volume increase is greater than or equal to the preset increase difference of the preset multiple, the time series production volume of the target hazardous solid waste generating unit after the second mutation time point is taken as the corrected time series production volume, and the time series production volume increase of the target hazardous solid waste generating unit after the second mutation time point is taken as the corrected time series production volume increase.
[0070] Figure 4 Another schematic diagram of the timing generation amount increase provided by the embodiment of the present application is as follows: Figure 4 As shown, after obtaining the time series generation volume increase data of the target hazardous solid waste generating unit, a second mutation time point when the time series generation volume increase is greater than a preset multiple of the preset time series generation volume increase can be obtained.
[0071] Exemplarily, the preset multiple may be 3 times to 10 times.
[0072] Similarly, when the difference between the mean of the increase in the time series generation volume of the target hazardous solid waste producing unit after the second mutation time point and the preset time series generation volume increase is greater than or equal to the preset increase difference of the preset multiple, it means that the increase in the time series generation volume after the second mutation time point has synchronously increased by the preset multiple. At this time, the time series generation volume after the second mutation time point can be predicted separately to ensure the accuracy of the time series generation volume prediction when the time series generation volume fluctuates greatly.
[0073] When predicting the time series production quantity after the second mutation time point alone, the time series production quantity of the target hazardous solid waste producing unit after the second mutation time point can be used as the corrected time series production quantity, and the time series production quantity increase of the target hazardous solid waste producing unit after the second mutation time point can be used as the corrected time series production quantity increase.
[0074] S320: Determine the corrected predicted time series generation of the target hazardous solid waste generating unit according to the corrected time series generation through the prediction model of the time series generation of hazardous solid waste. Determine the corrected target time series generation of the target hazardous solid waste generating unit according to the corrected predicted time series generation and the corrected time series generation increment through the correction model of the time series generation of hazardous solid waste.
[0075] When predicting the time series generation after the second mutation time point alone, the time series generation prediction model for hazardous solid waste can be used to determine the corrected predicted time series generation of the target hazardous solid waste generating unit based on the corrected time series generation, and then obtain the corrected predicted time series generation after the second mutation time point.
[0076] After obtaining the corrected predicted time series production, the corrected target time series production of the target hazardous solid waste producing unit can be determined through the hazardous solid waste time series production correction model according to the corrected predicted time series production and the corrected time series production increase. The corrected target time series production corresponds to the predicted result of the time series production after the second mutation time point.
[0077] The beneficial effect brought about by the above implementation method is that it can separately predict the time series production volume after the time point with a large mutation amplitude of the production volume, and can improve the accuracy and comprehensiveness of the prediction when the mutation amplitude of the production volume is large.
[0078] In some cases, such as when an emergency occurs in the target area, the amount of hazardous solid waste generated by hazardous solid waste generating units in the target area may increase simultaneously. At this time, in order to improve the prediction accuracy, the amount of hazardous solid waste generated in the target area can be predicted according to the region.
[0079] In some implementations, the above method further includes S410 to S430, and S410 to S430 are described in detail below.
[0080] S410. When the time series generation increase of the target hazardous solid waste producing unit is greater than the preset multiple of the preset time series generation increase, obtain the target type of hazardous solid waste corresponding to the hazardous solid waste produced by the target hazardous solid waste producing unit, obtain the set of hazardous solid waste producing units that produce the target type of hazardous solid waste in the target area, and obtain the first time series total generation of hazardous solid waste of the target type of all hazardous solid waste producing units in the set of hazardous solid waste producing units.
[0081] After obtaining the time series generation increase of the target hazardous solid waste producing unit, when the time series generation increase of the target hazardous solid waste producing unit is greater than the preset multiple of the preset time series generation increase, it means that the time series generation increase of the target hazardous solid waste producing unit is too large, indicating that an emergency may have occurred in the area where the target hazardous solid waste producing unit is located.
[0082] When an emergency may occur in the area where the target hazardous solid waste producing unit is located, the set of hazardous solid waste producing units in the target area that produce the same type of hazardous solid waste as the target hazardous solid waste producing unit can be obtained. Since the collection and treatment procedures of hazardous solid waste are relatively strict, the total solid waste generated by the hazardous solid waste producing units in the set of hazardous solid waste producing units represents the amount of solid waste generated caused by the emergency in the target area.
[0083] Exemplarily, the target type of hazardous solid waste corresponding to the target hazardous solid waste produced by the target hazardous solid waste producing unit can be obtained, and the set of hazardous solid waste producing units that produce the target type of hazardous solid waste in the target area can be obtained. The target type of hazardous solid waste produced by the set of hazardous solid waste producing units is the target type of hazardous solid waste caused by the emergency.
[0084] For example, when dividing the target area, it can be divided according to the distribution characteristics of the solid waste treatment sites.
[0085] Exemplarily, emergencies that produce target types of hazardous solid waste may be emergencies such as disease infection, chemical leakage, or natural disasters.
[0086] S420: Determine the first predicted time series generation amount of the target type of hazardous solid waste of the hazardous solid waste generating unit set according to the first time series total generation amount through the prediction model of the total generation amount of hazardous solid waste. And predict the generation amount of hazardous solid waste of types other than the target type in the target area to obtain the second predicted time series generation amount of hazardous solid waste of types other than the target type.
[0087] After obtaining the first time series total generation of hazardous solid waste of the target type of hazardous solid waste of all hazardous solid waste producing units in the hazardous solid waste producing unit set, the first predicted time series generation of hazardous solid waste of the target type of the set of hazardous solid waste producing units can be determined based on the first time series total generation through a hazardous solid waste time series total generation prediction model. The first predicted time series generation characterizes the generation of the target type of hazardous solid waste caused by the emergency in the target area.
[0088] In order to obtain the generation amount of hazardous solid waste of types other than the target type, the generation amount of hazardous solid waste of types other than the target type in the target area can be predicted according to the above method to obtain the second predicted time series generation amount of hazardous solid waste of types other than the target type.
[0089] Exemplarily, the time-series total hazardous solid waste generation prediction model can be trained based on the generation data of a specific type of hazardous solid waste in the target area.
[0090] Exemplarily, the time-series total hazardous solid waste generation prediction model can also be trained based on the generation data of a specific type of hazardous solid waste caused by the emergency in the target area when an emergency occurs.
[0091] S430: Taking the sum of the first predicted time series generation amount and the second predicted time series generation amount as the total target time series generation amount of the target area.
[0092] In order to obtain the total generation of hazardous solid waste in the target area, the sum of the first predicted time series generation and the second predicted time series generation can be used as the target time series total generation of the target area. The target time series total generation is the total generation of all types of hazardous solid waste in the target area.
[0093] The beneficial effect brought about by the above-mentioned implementation method is that when an emergency occurs, the amount of hazardous solid waste generated by the emergency shows a stronger variation pattern within the region. By accurately predicting the amount of specific types of hazardous solid waste generated in the target area, the amount of specific types of hazardous solid waste generated by emergencies in the target area can be accurately predicted.
[0094] In some implementations, in the above-mentioned S410, the first time series total generation of hazardous solid waste of the target type of all hazardous solid waste generating units in the set of hazardous solid waste generating units is obtained, including: obtaining a second mutation time point at which the time series generation increase of hazardous solid waste of the target type of the target hazardous solid waste generating unit is greater than a preset multiple of the preset time series generation increase; and obtaining the first time series total generation of hazardous solid waste of the target type of all hazardous solid waste generating units in the set of hazardous solid waste generating units starting from the second mutation time point.
[0095] When in use, a second mutation time point can be obtained at which the time series generation increase of the target type of hazardous solid waste of the target hazardous solid waste producing unit is greater than a preset multiple of the preset time series generation increase. An emergency may have occurred from the second mutation time point, and then the first time series total generation of the target type of hazardous solid waste of all hazardous solid waste producing units in the set of hazardous solid waste producing units starting from the second mutation time point can be obtained, and then the target type of hazardous solid waste can be accurately predicted starting from the second mutation time point.
[0096] In some implementations, in the above-mentioned S420, the first predicted time series generation amount of hazardous solid waste of the target type of the set of hazardous solid waste producing units is determined based on the first time series total generation amount through the hazardous solid waste time series total generation amount prediction model, including: starting from the second mutation time point, the first predicted time series generation amount of hazardous solid waste of the target type of the set of hazardous solid waste producing units is determined based on the first time series total generation amount through the hazardous solid waste time series total generation amount prediction model.
[0097] When in use, starting from the second mutation time point, the total time series generation of hazardous solid waste can be predicted through the hazardous solid waste generation prediction model, and the first predicted time series generation of hazardous solid waste of the target type of hazardous solid waste generating unit set can be determined according to the first time series total generation, so that the generation of the target type of hazardous solid waste can be accurately predicted starting from the second mutation time point.
[0098] The beneficial effect brought about by the above-mentioned implementation method is that when the generation amount of hazardous solid waste of the target type increases from the second mutation time point, the generation amount of hazardous solid waste of the target type can be accurately predicted from the second mutation time point.
[0099] When some emergencies occur, there may also be an increase in the generation of hazardous solid wastes of types related to the emergencies.
[0100] In some implementations, the above method further includes S510 to S520, and S510 to S520 are described in detail below.
[0101] S510: When the time series generation amount increase of the target hazardous solid waste generating unit is greater than the preset multiple of the preset time series generation amount increase, obtain the relevant hazardous solid waste corresponding to the target type of hazardous solid waste generated by the target hazardous solid waste generating unit, obtain the set of relevant hazardous solid waste generating units that generate the relevant hazardous solid waste, and determine the relevant factors of the target type of hazardous solid waste and the relevant hazardous solid waste. The relevant hazardous solid waste includes the upstream hazardous solid waste and the downstream hazardous solid waste of the target type of hazardous solid waste.
[0102] During use, when the time series production increase of the target hazardous solid waste producing unit is greater than a preset multiple of the preset time series production increase, the related hazardous solid waste corresponding to the target type of hazardous solid waste produced by the target hazardous solid waste producing unit can be obtained. The related hazardous solid waste is hazardous solid waste related to the target type of hazardous solid waste. The related hazardous solid waste is hazardous solid waste related to the target type of hazardous solid waste caused by an emergency.
[0103] Exemplarily, the relevant hazardous solid wastes include upstream hazardous solid wastes and downstream hazardous solid wastes of the target type of hazardous solid wastes.
[0104] After obtaining the category information of the relevant hazardous solid waste, the relevant hazardous solid waste producing units that produce the relevant hazardous solid waste can be obtained, and then the generation amount of the relevant hazardous solid waste can be predicted based on the relevant hazardous solid waste generation amount of the relevant hazardous solid waste producing units.
[0105] When predicting the generation of relevant hazardous solid waste, the correlation factors between the target type of hazardous solid waste and the relevant hazardous solid waste can be obtained, and the correlation factors characterize the relationship between the generation of the target type of hazardous solid waste and the generation of relevant hazardous solid waste.
[0106] S520. Determine the predicted total time series generation of the relevant hazardous solid waste generating unit set according to the total time series generation of the relevant hazardous solid waste generating unit set in time series through a hazardous solid waste generating total time series prediction model.
[0107] When in use, the total time series generation prediction model for hazardous solid waste can be used to determine the predicted total time series generation of relevant hazardous solid waste producing units based on the total time series generation of relevant hazardous solid wastes of the relevant hazardous solid waste producing units. The predicted time series generation of relevant hazardous solid waste producing units represents the generation of relevant hazardous solid waste caused by the emergency.
[0108] Exemplarily, when determining the predicted total time series generation of relevant hazardous solid waste generating units, the prediction can be performed using the same prediction method as the generation of hazardous solid waste of the above-mentioned target type.
[0109] The beneficial effect brought about by the above-mentioned implementation method is that when an emergency occurs, the amount of hazardous solid waste generated by the emergency will show a stronger variation pattern in the region. By predicting the total amount of related hazardous solid waste caused by the emergency in the target area, the prediction accuracy of the amount of hazardous solid waste generated in emergency situations can be improved.
[0110] In some implementations, in the above S510, determining the correlation factors of the target type of hazardous solid waste and the related hazardous solid wastes includes: obtaining the related production volume of the related hazardous solid waste corresponding to the target type of hazardous solid waste with the target production volume, and taking the ratio of the related production volume to the target production volume as the correlation factor.
[0111] When in use, the relevant production volume of relevant hazardous solid waste corresponding to the target type of hazardous solid waste with the target production volume can be actually obtained, and the ratio of the relevant production volume to the target production volume can be used as a correlation factor, so as to accurately measure the production volume of hazardous solid waste in practice.
[0112] Exemplarily, the relevant generation amount (weight / kg) of relevant hazardous solid waste corresponding to 1kg of the target type of hazardous solid waste can be actually obtained, and the ratio of the relevant generation amount to 1kg is used as the correlation factor.
[0113] An embodiment of the present application also provides a device for predicting the amount of urban hazardous waste generated based on deep learning, comprising a unit for executing any of the above methods.
[0114] Figure 5 A schematic diagram of the logical structure of a device for predicting the amount of urban hazardous waste generated based on deep learning is provided in one embodiment of the present application, such as Figure 5 As shown, the device 1 of this embodiment includes a processing unit 11, a storage unit 12 and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to send and receive data. The processing unit 11, the storage unit 12 and the transceiver unit 13 cooperate with each other to implement the above method. The beneficial effects brought about by the embodiment of the present application have been described in the above method and will not be repeated here.
[0115] An embodiment of the present application also provides a device for predicting the amount of urban hazardous waste generated based on deep learning, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the methods described above when executing the computer program.
[0116] Figure 6 A schematic diagram of the physical structure of a device for predicting the amount of urban hazardous waste generated based on deep learning provided in one embodiment of the present application is shown in FIG. Figure 6 As shown, the device 2 of this embodiment includes: at least one processor 20 ( Figure 6 Only one processor 20 is shown in the figure), a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20. When the processor 20 executes the computer program 22, the steps in any of the above-mentioned method embodiments are implemented. The beneficial effects brought about by the embodiments of the present application have been described in the above-mentioned methods and will not be repeated here.
[0117] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.
[0118] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0119] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.
[0120] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.
[0121] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.
[0122] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0123] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0124] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0125] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0126] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A method for predicting the amount of urban hazardous waste generation based on deep learning, It is characterized in that The method comprises: Obtain the time series generation amount and time series generation amount increase of hazardous solid wastes for each hazardous solid waste generating unit in the target area; wherein the time interval for obtaining the time series generation amount increase in each time period is less than the time interval for obtaining the time series generation amount; Through the hazardous solid waste time series generation prediction model, the predicted time series generation of each hazardous solid waste producing unit is determined according to the time series generation of hazardous solid waste of each hazardous solid waste producing unit in time series; through the hazardous solid waste time series generation correction model, the target time series generation of each hazardous solid waste producing unit is determined according to the time series generation and time series generation increase of each hazardous solid waste producing unit, and the sum of the target time series generation of all hazardous solid waste producing units in the target area is taken as the prediction result of hazardous solid waste generation in the target area.
2. The method according to claim 1, It is characterized in that The method further comprises: Obtain the first mutation time point at which the increase in the time series generation volume of the target hazardous solid waste generating unit is greater than the preset time series generation volume increase, and obtain the time series generation volume increase of the target hazardous solid waste generating unit after the first mutation time point; When the increase in the time series generation volume of the target hazardous solid waste producing unit after the first mutation time point meets the preset increase condition, the increase in the time series generation volume at the first mutation time point is retained in the increase in the time series generation volume; when the increase in the time series generation volume of the target hazardous solid waste producing unit after the first mutation time point does not meet the preset increase condition, the increase in the time series generation volume at the first mutation time point is replaced by the historical time series generation volume increase.
3. The method according to claim 2, It is characterized in that The preset increase condition includes: the difference between the average value of the time series production increase of the target hazardous solid waste producing unit at the first mutation time point and after the first mutation time point and the preset time series production increase is less than the preset increase difference.
4. The method according to claim 3, It is characterized in that The method further comprises: Obtain a second mutation time point at which the increase in the time series generation amount of the target hazardous solid waste generating unit is greater than a preset multiple of the preset time series generation amount increase; when the difference between the average of the time series generation amount increase of the target hazardous solid waste generating unit after the second mutation time point and the preset time series generation amount increase is greater than or equal to the preset increase difference of the preset multiple, take the time series generation amount of the target hazardous solid waste generating unit after the second mutation time point as the corrected time series generation amount, and take the time series generation amount increase of the target hazardous solid waste generating unit after the second mutation time point as the corrected time series generation amount increase; Through the hazardous solid waste time series generation prediction model, the revised predicted time series generation of the target hazardous solid waste generating unit is determined according to the revised time series generation; through the hazardous solid waste time series generation correction model, the revised target time series generation of the target hazardous solid waste generating unit is determined according to the revised predicted time series generation and the revised time series generation increase.
5. The method according to claim 4, It is characterized in that The method further comprises: When the time series generation amount increase of the target hazardous solid waste generating unit is greater than the preset time series generation amount increase of the preset multiple, the target type of hazardous solid waste corresponding to the hazardous solid waste generated by the target hazardous solid waste generating unit is obtained, the set of hazardous solid waste generating units generating the target type of hazardous solid waste in the target area is obtained, and the first time series total generation amount of hazardous solid waste of the target type of all hazardous solid waste generating units in the set of hazardous solid waste generating units is obtained; By using the hazardous solid waste total time series generation prediction model, the first predicted time series generation of hazardous solid waste of the target type of the hazardous solid waste generation unit set is determined according to the first time series total generation; and the hazardous solid waste generation of types other than the target type in the target area is predicted to obtain the second predicted time series generation of hazardous solid waste of types other than the target type; The sum of the first predicted time series generation amount and the second predicted time series generation amount is taken as the target time series total generation amount of the target area.
6. The method according to claim 5, It is characterized in that Get the first time series total generation of the target type of hazardous solid waste of all hazardous solid waste generating units in the hazardous solid waste generating unit set, including: Obtain a second mutation time point at which the increase in the time series generation amount of hazardous solid waste of the target type of the target hazardous solid waste generating unit is greater than a preset multiple of the preset time series generation amount increase, and obtain the first time series total generation amount of the target type of hazardous solid waste of all hazardous solid waste generating units in the hazardous solid waste generating unit set starting from the second mutation time point; By using the hazardous solid waste time series total generation prediction model, according to the first time series total generation, the first predicted time series generation of hazardous solid waste of the target type of the hazardous solid waste generation unit set is determined, including: Starting from the second mutation time point, the first predicted time series generation amount of hazardous solid waste of the target type of hazardous solid waste generating unit set is determined according to the first time series total generation amount through the hazardous solid waste time series total generation amount prediction model.
7. A device for predicting the amount of urban hazardous waste generated based on deep learning, It is characterized in that Comprising means for performing the method according to any one of claims 1 to 6.
8. A device for predicting the amount of urban hazardous waste generated based on deep learning, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.
9. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.
10. A computer program product comprising a computer program, It is 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.
Citation Information
Patent Citations
Electronic solid waste output intelligent prediction method and system
CN113761801A
Power station boiler ash generation amount online prediction method and system based on LSTM
CN116401948A
Wind power prediction method under abnormal weather based on LightGBM-Seq2Seq and storage medium
CN116979502A
Medical image processing apparatus and medical image processing method
US20170103526A1
