A method, system and storage medium for environmental dust monitoring and early warning

Abstract

The present invention relates to an environmental dust monitoring and early warning method, system and storage medium, belonging to the technical field. The present invention constructs a protective cover permeability membership prediction model based on a historical permeability membership change characteristic matrix, and predicts the permeability membership information of the protective cover at the current timestamp through the protective cover permeability membership prediction model. Finally, an evaluation is performed based on the permeability membership information of the protective cover at the current timestamp and the dust information of each sub-area in the current environmental area, an evaluation result is obtained, and relevant early warning information is generated based on the evaluation result. The present invention monitors the dust information of each sub-area in the current environmental area, thereby integrating a deep neural network and a Markov chain to estimate the permeability of the protective cover, and thus can timely perceive the threat of dust conditions in the environment to the health of the user, so as to timely improve protective measures according to the situation and ensure the health of relevant professional workers.

Description

Technical Field

[0001] The present invention relates to the technical field of dust monitoring, and in particular to an environmental dust monitoring and early warning method, system and storage medium. Background Art

[0002] With the increasing intensity of industrial production, workers are facing increasingly serious dust hazards. Because dust is affected by its physical properties (such as particle size, mass, and shape) and environmental parameters like wind speed and humidity, some large dust particles settle freely on the work surface, while others remain suspended in the air. Dust with an aerodynamic diameter of ≤7.07μm and a collection efficiency of 50% at 5μm is respirable dust. Once inhaled by workers, respirable dust accumulates in their lungs, forming a cumulative exposure. Prolonged inhalation of excessive respirable dust, reaching a certain peak, can lead to pneumoconiosis. Effective preventive measures in this process include environmental regulation and timely replacement of protective masks. Existing technologies lack high accuracy in identifying dust hazards, failing to promptly alert workers to prevent them based on the dust levels in the environment, seriously endangering their health. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides an environmental dust monitoring and early warning method, system and storage medium.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is:

[0005] A first aspect of the present invention provides an environmental dust monitoring and early warning method, comprising the following steps:

[0006] By deploying dust information monitoring sensors in the environmental area to be monitored and building a dust information monitoring network, the dust information of each sub-area in the current environmental area can be obtained through the dust information monitoring network;

[0007] The historical permeability change characteristic information of the protective cover under different dust information is obtained through big data. The historical permeability change characteristic information of the protective cover under different dust information is evaluated to obtain the historical permeability membership change characteristic matrix;

[0008] A protective cover permeability membership prediction model is constructed based on the historical permeability membership change characteristic matrix, and the permeability membership information of the protective cover at the current time stamp is predicted by the protective cover permeability membership prediction model;

[0009] An evaluation is performed based on the permeability membership information of the protective cover at the current timestamp and the dust information of each sub-area in the current environmental area, an evaluation result is obtained, and relevant early warning information is generated based on the evaluation result.

[0010] Furthermore, in this method, dust information monitoring sensors are deployed in the environmental area to be monitored, and a dust information monitoring network is constructed. The dust information of each sub-area in the current environmental area is obtained through the dust information monitoring network, specifically including:

[0011] Obtaining the layout range information of the environmental area to be monitored, configuring the dust information monitoring sensor, obtaining the estimated working range information of the dust information monitoring sensor, introducing the genetic algorithm, and setting the genetic generation according to the genetic algorithm;

[0012] Initialize the placement positions and number of dust information monitoring sensors, and calculate the total estimated working range information of the dust information monitoring sensors based on the estimated working range information, placement positions, and number of dust information monitoring sensors;

[0013] When the total estimated working range information of the dust information monitoring sensor is smaller than the layout range information of the environmental area to be monitored, genetic iteration is performed according to genetic algebra to adjust the layout position and layout quantity of the dust information monitoring sensor;

[0014] When the total estimated working range information of the dust information monitoring sensor is not less than the layout range information of the environmental area to be monitored, the layout position and number of the dust information monitoring sensor are output, and a dust information monitoring network is constructed to obtain the dust information of each sub-area in the current environmental area through the dust information monitoring network.

[0015] Furthermore, in this method, historical permeability change characteristic information of the protective cover under different dust information is obtained through big data. By evaluating the historical permeability change characteristic information of the protective cover under different dust information, a historical permeability membership change characteristic matrix is ​​obtained, which specifically includes:

[0016] The historical permeability change characteristics of the protective cover under different dust information are obtained through big data. The decision tree model is introduced to construct sample data based on the historical permeability change characteristics of the protective cover under different dust information, and several historical permeability membership split evaluation indicators are preset.

[0017] The historical permeability membership split evaluation index is used as the splitting criterion, the sample data is input into the decision tree model, the sample data is split according to the splitting criterion, a number of leaf nodes are obtained, and it is determined whether there is only one sample data within the historical permeability membership split evaluation index in the leaf node;

[0018] If so, the leaf node is output; if not, the leaf node is continuously split until there is only one sample data within the historical permeability membership split evaluation index in the leaf node. The leaf node is output, the historical permeability membership information corresponding to each sample data is obtained, and the historical permeability membership change feature matrix is ​​constructed.

[0019] Furthermore, in this method, a protective cover permeability membership prediction model is constructed based on the historical permeability membership change characteristic matrix, specifically including:

[0020] The Markov model is introduced, and the historical permeability membership change characteristic matrix is ​​input into the Markov model to obtain the membership transfer probability value of each historical permeability membership in the historical permeability membership change characteristic matrix transferring to another level of historical permeability membership;

[0021] A membership transfer probability value matrix is ​​constructed according to the membership transfer probability values, and a shield permeability membership prediction model is constructed based on a deep neural network. The membership transfer probability value matrix is ​​input into the shield permeability membership prediction model for coding learning;

[0022] When the model parameters of the protective cover permeability membership prediction model meet the preset requirements, the model parameters of the protective cover permeability membership prediction model are saved, and the protective cover permeability membership prediction model is output.

[0023] Furthermore, in this method, the permeability membership information of the protective cover at the current timestamp is predicted by the protective cover permeability membership prediction model, specifically including:

[0024] Obtaining the permeability membership of the protective mask worn by the staff in each sub-area at the current time stamp, and inputting the permeability membership of the protective mask worn by the staff in each sub-area at the current time stamp into the protective mask permeability membership prediction model for prediction;

[0025] Obtain, by prediction, a predicted transfer probability value of the permeability membership of the protective cover at the current timestamp being transferred to another level of permeability membership, and determine whether the predicted transfer probability value is greater than a preset transfer probability threshold;

[0026] When the predicted transition probability value is greater than the preset transition probability value, the permeability membership of another level is used as the permeability membership information of the protective cover at the current time stamp, and the permeability membership information of the protective cover at the current time stamp is output;

[0027] When the predicted transition probability value is not greater than the preset transition probability value, the permeability membership information of the protective cover at the current timestamp is output.

[0028] Furthermore, in this method, an evaluation is performed based on the permeability membership information of the protective cover at the current timestamp and the dust information of each sub-area in the current environmental area to obtain an evaluation result, and relevant warning information is generated based on the evaluation result, specifically including:

[0029] Based on the permeability membership information of the protective cover at the current timestamp and the dust information of each sub-area in the current environmental area, the permeability membership information of the protective cover under the current dust information is generated, and a permeability membership evaluation index is set;

[0030] When the permeability membership information of the protective cover under the current dust information is greater than the permeability membership evaluation index, relevant warning information is generated;

[0031] At the same time, relevant warning information is sent to the smart terminal held by the corresponding staff, who receive relevant prompt information through the smart terminal and control the environmental control equipment to control the environment of the target sub-area;

[0032] When the permeability membership information of the protective cover is not greater than the permeability membership evaluation index under the current dust information, a relevant prompt message is sent to the smart terminal held by the corresponding staff.

[0033] A second aspect of the present invention provides an environmental dust monitoring and early warning system, the system including a memory and a processor, the memory including a method program, and when the method program is executed by the processor, the following steps are implemented:

[0034] By deploying dust information monitoring sensors in the environmental area to be monitored and building a dust information monitoring network, the dust information of each sub-area in the current environmental area can be obtained through the dust information monitoring network;

[0035] The historical permeability change characteristic information of the protective cover under different dust information is obtained through big data. The historical permeability change characteristic information of the protective cover under different dust information is evaluated to obtain the historical permeability membership change characteristic matrix;

[0036] A protective cover permeability membership prediction model is constructed based on the historical permeability membership change characteristic matrix, and the permeability membership information of the protective cover at the current time stamp is predicted by the protective cover permeability membership prediction model;

[0037] An evaluation is performed based on the permeability membership information of the protective cover at the current timestamp and the dust information of each sub-area in the current environmental area, an evaluation result is obtained, and relevant early warning information is generated based on the evaluation result.

[0038] A third aspect of the present invention provides a computer-readable storage medium, which includes a method program. When the method program is executed by a processor, it implements the steps of any one of the environmental dust monitoring and early warning methods.

[0039] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0040] The present invention deploys dust information monitoring sensors in the environmental area to be monitored and constructs a dust information monitoring network. The dust information of each sub-area in the current environmental area is obtained through the dust information monitoring network. Then, the historical permeability change characteristic information of the protective cover under different dust information is obtained through big data. The historical permeability change characteristic information of the protective cover under different dust information is evaluated to obtain a historical permeability membership change characteristic matrix. Then, a protective cover permeability membership prediction model is constructed based on the historical permeability membership change characteristic matrix. The protective cover permeability membership prediction model predicts the permeability membership information of the protective cover at the current timestamp using the protective cover permeability membership prediction model. Finally, an evaluation is performed based on the permeability membership information of the protective cover at the current timestamp and the dust information of each sub-area in the current environmental area to obtain an evaluation result, and relevant early warning information is generated based on the evaluation result. By monitoring the dust information of each sub-area in the current environmental area, the present invention integrates a deep neural network and a Markov chain to estimate the permeability of the protective cover, thereby being able to timely perceive the threat of dust conditions in the environment to the health of users, so as to timely improve protective measures according to the situation and protect the health of relevant occupational workers. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying any creative work, they can also obtain drawings of other embodiments based on these drawings.

[0042] Figure 1 The following is a flow chart showing an overall method of environmental dust monitoring and early warning method;

[0043] Figure 2 A first method flow chart of an environmental dust monitoring and early warning method is shown;

[0044] Figure 3 A second method flow chart of an environmental dust monitoring and early warning method is shown;

[0045] Figure 4 Shown is a system block diagram of an environmental dust monitoring and early warning system. DETAILED DESCRIPTION

[0046] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0048] like Figure 1 As shown, the first aspect of the present invention provides an environmental dust monitoring and early warning method, comprising the following steps:

[0049] S102: Deploy dust information monitoring sensors in the environmental area to be monitored and build a dust information monitoring network to obtain dust information of each sub-area in the current environmental area through the dust information monitoring network;

[0050] S104: Obtain historical permeability change characteristic information of the protective cover under different dust information through big data, and obtain a historical permeability membership change characteristic matrix by evaluating the historical permeability change characteristic information of the protective cover under different dust information;

[0051] S106: constructing a protective cover permeability membership prediction model based on the historical permeability membership change characteristic matrix, and predicting the permeability membership information of the protective cover at the current timestamp using the protective cover permeability membership prediction model;

[0052] S108: Evaluate the permeability membership information of the protective cover in the current timestamp and the dust information of each sub-area in the current environmental area, obtain the evaluation results, and generate relevant warning information based on the evaluation results.

[0053] It should be noted that this invention monitors dust information in each sub-area of ​​the current environmental area, integrating deep neural networks and Markov chains to estimate the permeability of protective covers. This allows for timely detection of environmental dust threats to user health, enabling timely improvement of protective measures based on these conditions and safeguarding the health of relevant workers. Dust information includes data such as dust type and concentration.

[0054] like Figure 2 As shown, further, in this method, in step S102, specifically including:

[0055] S202: Obtaining layout range information of the environmental area to be monitored, configuring a dust information monitoring sensor, obtaining estimated working range information of the dust information monitoring sensor, introducing a genetic algorithm, and setting a genetic generation according to the genetic algorithm;

[0056] S204: Initializing the placement positions and number of dust information monitoring sensors, and calculating the total estimated working range information of the dust information monitoring sensors based on the estimated working range information, the placement positions, and the number of dust information monitoring sensors;

[0057] S206: When the total estimated working range information of the dust information monitoring sensor is smaller than the layout range information of the environmental area to be monitored, genetic iteration is performed according to genetic algebra to adjust the layout position and layout quantity of the dust information monitoring sensor;

[0058] S208: When the total estimated working range information of the dust information monitoring sensor is not less than the layout range information of the environmental area to be monitored, the layout position and layout quantity of the dust information monitoring sensor are output, and a dust information monitoring network is constructed to obtain the dust information of each sub-area in the current environmental area through the dust information monitoring network.

[0059] It should be noted that this method can improve the rationality of the layout of the dust information monitoring network.

[0060] Furthermore, in this method, in step S104, it specifically includes:

[0061] The historical permeability change characteristics of the protective cover under different dust information are obtained through big data. The decision tree model is introduced to construct sample data based on the historical permeability change characteristics of the protective cover under different dust information, and several historical permeability membership split evaluation indicators are preset.

[0062] The historical permeability membership split evaluation index is used as the splitting criterion, the sample data is input into the decision tree model, the sample data is split according to the splitting criterion, a number of leaf nodes are obtained, and it is determined whether there is only one sample data within the historical permeability membership split evaluation index in the leaf node;

[0063] If so, the leaf node is output; if not, the leaf node is continuously split until there is only one sample data within the historical permeability membership split evaluation index in the leaf node. The leaf node is output, the historical permeability membership information corresponding to each sample data is obtained, and the historical permeability membership change feature matrix is ​​constructed.

[0064] It should be noted that the permeability of a protective cover indicates the amount of dust that can pass through the cover per unit time. Because the permeability varies depending on the dust type and concentration, a decision tree model can quickly classify sample data. Permeability membership includes low permeability membership, medium permeability membership, and high permeability membership.

[0065] Furthermore, in this method, in step S206, a protection cover permeability membership prediction model is constructed based on the historical permeability membership change characteristic matrix, specifically including:

[0066] The Markov model is introduced, and the historical permeability membership change characteristic matrix is ​​input into the Markov model to obtain the membership transfer probability value of each historical permeability membership in the historical permeability membership change characteristic matrix transferring to another level of historical permeability membership;

[0067] A membership transfer probability value matrix is ​​constructed according to the membership transfer probability values, and a shield permeability membership prediction model is constructed based on a deep neural network. The membership transfer probability value matrix is ​​input into the shield permeability membership prediction model for coding learning;

[0068] When the model parameters of the protective cover permeability membership prediction model meet the preset requirements, the model parameters of the protective cover permeability membership prediction model are saved, and the protective cover permeability membership prediction model is output.

[0069] It should be noted that, as the performance of the protective cover gradually degrades during use, the permeability continues to increase, that is, it transfers from one level of permeability membership to another. This method can further improve the prediction accuracy of the permeability of the protective cover.

[0070] Furthermore, in this method, the permeability membership information of the protective cover at the current timestamp is predicted by the protective cover permeability membership prediction model, specifically including:

[0071] Obtaining the permeability membership of the protective mask worn by the staff in each sub-area at the current time stamp, and inputting the permeability membership of the protective mask worn by the staff in each sub-area at the current time stamp into the protective mask permeability membership prediction model for prediction;

[0072] Obtain, by prediction, a predicted transfer probability value of the permeability membership of the protective cover at the current timestamp being transferred to another level of permeability membership, and determine whether the predicted transfer probability value is greater than a preset transfer probability threshold;

[0073] When the predicted transition probability value is greater than the preset transition probability value, the permeability membership of another level is used as the permeability membership information of the protective cover at the current time stamp, and the permeability membership information of the protective cover at the current time stamp is output;

[0074] When the predicted transition probability value is not greater than the preset transition probability value, the permeability membership information of the protective cover at the current timestamp is output.

[0075] It should be noted that when the predicted transfer probability value is greater than the preset transfer probability value, it means that the permeability membership has been transferred from one to another. The permeability membership information of the protective cover in the current timestamp means the permeability membership information of the protective cover under different dust types and dust concentration information, which is a collection of multiple permeability membership parameters.

[0076] like Figure 3 As shown, further, in this method, an evaluation is performed based on the permeability membership information of the protective cover at the current timestamp and the dust information of each sub-area in the current environmental area to obtain an evaluation result, and relevant warning information is generated based on the evaluation result, specifically including:

[0077] S302: generating permeability membership information of the protective cover under the current dust information based on the permeability membership information of the protective cover at the current timestamp and the dust information of each sub-area in the current environmental area, and setting a permeability membership evaluation index;

[0078] S304: When the permeability membership information of the protective cover under the current dust information is greater than the permeability membership evaluation index, relevant warning information is generated;

[0079] S306: At the same time, relevant warning information is sent to the smart terminal held by the corresponding staff member, who receives the relevant prompt information through the smart terminal and controls the environmental control equipment to perform environmental control on the target sub-area;

[0080] S308: When the permeability membership information of the protective cover is not greater than the permeability membership evaluation index under the current dust information, a relevant prompt message is sent to the smart terminal held by the corresponding staff.

[0081] It should be noted that the smart terminal can be a mobile phone, smartwatch, or similar device. When the permeability membership information of the protective cover under the current dust information is greater than the permeability membership evaluation index, it indicates that the amount of dust passing through the protective cover per unit time exceeds a predetermined threshold. The environmental control equipment can be an air conditioner, fan, or other device. Related prompts may include thickening the protective cover or replacing the protective cover.

[0082] In addition, the method may further comprise the following steps:

[0083] Obtain basic data information of workers in the current environmental area and the type of dust in the current environmental area, construct a search tag based on the dust type in the current environmental area, and search through big data based on the search tag to obtain the disease type associated with the dust type;

[0084] Retrieving basic data information of workers in the current environment area according to the disease type associated with the dust type, and obtaining workers corresponding to the disease type associated with the dust type;

[0085] Obtaining work distribution layout information in the current environmental area, introducing a particle swarm algorithm, setting an iterative algebra according to the particle swarm algorithm, and determining whether there is a worker corresponding to a disease type associated with the dust type in the work distribution layout information in the current environmental area;

[0086] When there are workers corresponding to the disease types associated with the dust types in the work assignment layout information in the current environment area, iteration is performed according to the iterative algebra to readjust the work assignment layout information in the current environment area until there are no workers corresponding to the disease types associated with the dust types in the work assignment layout information in the current environment area.

[0087] It should be noted that since workers may have related diseases, and since the type of dust may aggravate the type of disease associated with the dust type, this method can further obtain work distribution layout information in the current environmental area and improve the rationality of work task allocation for workers.

[0088] In addition, controlling the environment control device to control the environment of the target sub-area includes the following steps:

[0089] Obtaining control parameter information of the optimal environmental control equipment for each dust type through big data, and introducing a graph neural network to input the control parameter information of the optimal environmental control equipment for each dust type into the graph neural network;

[0090] Using the dust type and the control parameter information of the optimal environmental control equipment as graph nodes of the graph neural network, constructing an undirected heterogeneous graph based on the graph nodes, constructing a knowledge graph, and inputting the undirected heterogeneous graph into the knowledge graph for storage;

[0091] Obtaining the dust type in the current environmental area, inputting the dust type in the current environmental area into the knowledge graph for data matching, and obtaining control parameter information of the optimal environmental control equipment for the dust type in the current environmental area;

[0092] The environment of the target sub-area is controlled according to the control parameter information of the optimal environment control device in the dust type in the current environment area.

[0093] It should be noted that, in fact, dust has its own unique physical and chemical characteristics. The degree of wettability of dust particles by liquid is called dust wettability.

[0094] Dusts like graphite are difficult to wet with water and are therefore considered hydrophobic. For hydrophilic dust, increasing humidity can reduce dust generation, and appropriate dust removal equipment can be used to prevent secondary dust generation. Intelligently controlling dust removal based on whether it is hydrophobic or hygroscopic improves the effectiveness of dust removal and parameter control of environmental equipment.

[0095] like Figure 4 As shown, the second aspect of the present invention provides an environmental dust monitoring and early warning system 4, which includes a memory 41 and a processor 42. The memory 41 includes a method program. When the method program is executed by the processor 42, the following steps are implemented:

[0096] By deploying dust information monitoring sensors in the environmental area to be monitored and building a dust information monitoring network, the dust information of each sub-area in the current environmental area can be obtained through the dust information monitoring network;

[0097] The historical permeability change characteristic information of the protective cover under different dust information is obtained through big data. The historical permeability change characteristic information of the protective cover under different dust information is evaluated to obtain the historical permeability membership change characteristic matrix;

[0098] A protective cover permeability membership prediction model is constructed based on the historical permeability membership change characteristic matrix, and the permeability membership information of the protective cover at the current time stamp is predicted by the protective cover permeability membership prediction model;

[0099] An evaluation is performed based on the permeability membership information of the protective cover at the current timestamp and the dust information of each sub-area in the current environmental area, an evaluation result is obtained, and relevant early warning information is generated based on the evaluation result.

[0100] Furthermore, in this system, dust information monitoring sensors are deployed in the environmental area to be monitored, and a dust information monitoring network is constructed. The dust information of each sub-area in the current environmental area is obtained through the dust information monitoring network, specifically including:

[0101] Obtaining the layout range information of the environmental area to be monitored, configuring the dust information monitoring sensor, obtaining the estimated working range information of the dust information monitoring sensor, introducing the genetic algorithm, and setting the genetic generation according to the genetic algorithm;

[0102] Initialize the placement positions and number of dust information monitoring sensors, and calculate the total estimated working range information of the dust information monitoring sensors based on the estimated working range information, placement positions, and number of dust information monitoring sensors;

[0103] When the total estimated working range information of the dust information monitoring sensor is smaller than the layout range information of the environmental area to be monitored, genetic iteration is performed according to genetic algebra to adjust the layout position and layout quantity of the dust information monitoring sensor;

[0104] When the total estimated working range information of the dust information monitoring sensor is not less than the layout range information of the environmental area to be monitored, the layout position and number of the dust information monitoring sensor are output, and a dust information monitoring network is constructed to obtain the dust information of each sub-area in the current environmental area through the dust information monitoring network.

[0105] Furthermore, in this system, the historical permeability change characteristic information of the protective cover under different dust information is obtained through big data. By evaluating the historical permeability change characteristic information of the protective cover under different dust information, the historical permeability membership change characteristic matrix is ​​obtained, which specifically includes:

[0106] The historical permeability change characteristics of the protective cover under different dust information are obtained through big data. The decision tree model is introduced to construct sample data based on the historical permeability change characteristics of the protective cover under different dust information, and several historical permeability membership split evaluation indicators are preset.

[0107] The historical permeability membership split evaluation index is used as the splitting criterion, the sample data is input into the decision tree model, the sample data is split according to the splitting criterion, a number of leaf nodes are obtained, and it is determined whether there is only one sample data within the historical permeability membership split evaluation index in the leaf node;

[0108] If so, the leaf node is output; if not, the leaf node is continuously split until there is only one sample data within the historical permeability membership split evaluation index in the leaf node. The leaf node is output, the historical permeability membership information corresponding to each sample data is obtained, and the historical permeability membership change feature matrix is ​​constructed.

[0109] Furthermore, in this system, a protective cover permeability membership prediction model is constructed based on the historical permeability membership change characteristic matrix, specifically including:

[0110] The Markov model is introduced, and the historical permeability membership change characteristic matrix is ​​input into the Markov model to obtain the membership transfer probability value of each historical permeability membership in the historical permeability membership change characteristic matrix transferring to another level of historical permeability membership;

[0111] A membership transfer probability value matrix is ​​constructed according to the membership transfer probability values, and a shield permeability membership prediction model is constructed based on a deep neural network. The membership transfer probability value matrix is ​​input into the shield permeability membership prediction model for coding learning;

[0112] When the model parameters of the protective cover permeability membership prediction model meet the preset requirements, the model parameters of the protective cover permeability membership prediction model are saved, and the protective cover permeability membership prediction model is output.

[0113] Furthermore, in this system, the permeability membership information of the protective cover at the current timestamp is predicted by the protective cover permeability membership prediction model, specifically including:

[0114] Obtaining the permeability membership of the protective mask worn by the staff in each sub-area at the current time stamp, and inputting the permeability membership of the protective mask worn by the staff in each sub-area at the current time stamp into the protective mask permeability membership prediction model for prediction;

[0115] Obtain, by prediction, a predicted transfer probability value of the permeability membership of the protective cover at the current timestamp being transferred to another level of permeability membership, and determine whether the predicted transfer probability value is greater than a preset transfer probability threshold;

[0116] When the predicted transition probability value is greater than the preset transition probability value, the permeability membership of another level is used as the permeability membership information of the protective cover at the current time stamp, and the permeability membership information of the protective cover at the current time stamp is output;

[0117] When the predicted transition probability value is not greater than the preset transition probability value, the permeability membership information of the protective cover at the current timestamp is output.

[0118] Furthermore, in this system, an evaluation is performed based on the permeability membership information of the protective cover at the current timestamp and the dust information of each sub-area in the current environmental area to obtain an evaluation result, and relevant warning information is generated based on the evaluation result, specifically including:

[0119] Based on the permeability membership information of the protective cover at the current timestamp and the dust information of each sub-area in the current environmental area, the permeability membership information of the protective cover under the current dust information is generated, and a permeability membership evaluation index is set;

[0120] When the permeability membership information of the protective cover under the current dust information is greater than the permeability membership evaluation index, relevant warning information is generated;

[0121] At the same time, relevant warning information is sent to the smart terminal held by the corresponding staff, who receive relevant prompt information through the smart terminal and control the environmental control equipment to control the environment of the target sub-area;

[0122] When the permeability membership information of the protective cover is not greater than the permeability membership evaluation index under the current dust information, a relevant prompt message is sent to the smart terminal held by the corresponding staff.

[0123] A third aspect of the present invention provides a computer-readable storage medium, which includes a method program. When the method program is executed by a processor, it implements the steps of any one of the environmental dust monitoring and early warning methods.

[0124] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0125] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0126] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0127] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0128] Alternatively, if the integrated units described above are implemented as software modules and sold or used as standalone products, they can also be stored on a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product, stored on a storage medium, includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute all or part of the methods of the various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as removable storage devices, ROM, RAM, magnetic disks, or optical disks.

[0129] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for monitoring and early warning of environmental dust, characterized in that: The following steps are involved: By deploying dust information monitoring sensors in the environmental area to be monitored and building a dust information monitoring network, the dust information of each sub-area in the current environmental area is obtained through the dust information monitoring network; Obtain historical permeability change characteristic information of the protective cover under different dust information through big data, and obtain a historical permeability membership change characteristic matrix by evaluating the historical permeability change characteristic information of the protective cover under different dust information; Constructing a protective cover permeability membership prediction model based on the historical permeability membership change characteristic matrix, and predicting the permeability membership information of the protective cover at the current timestamp using the protective cover permeability membership prediction model; Evaluate the dust in each sub-area in the current environment area according to the permeability membership information of the protective cover at the current timestamp, obtain an evaluation result, and generate relevant warning information based on the evaluation result; Evaluate the dust in each sub-area in the current environment area according to the permeability membership information of the protective cover at the current timestamp and obtain an evaluation result, and generate relevant warning information based on the evaluation result, specifically including: generating permeability membership information of the protective cover under the current dust information based on the permeability membership information of the protective cover at the current timestamp and the dust information of each sub-area in the current environmental area, and setting a permeability membership evaluation index; When the permeability membership information of the protective cover under the current dust information is greater than the permeability membership evaluation index, relevant warning information is generated; At the same time, relevant warning information is sent to the smart terminal held by the corresponding staff, who receive relevant prompt information through the smart terminal and control the environmental control equipment to control the environment of the target sub-area; When the permeability membership information of the protective cover under the current dust information is not greater than the permeability membership evaluation index, a relevant prompt message is sent to the smart terminal held by the corresponding staff member; The method further comprises the following steps: Obtain basic data information of workers in the current environmental area and the type of dust in the current environmental area, construct a search tag based on the dust type in the current environmental area, and search through big data based on the search tag to obtain the disease type associated with the dust type; Retrieving basic data information of workers in the current environment area according to the disease type associated with the dust type, and obtaining workers corresponding to the disease type associated with the dust type; Obtaining work distribution layout information in the current environmental area, introducing a particle swarm algorithm, setting an iterative algebra according to the particle swarm algorithm, and determining whether there is a worker corresponding to a disease type associated with the dust type in the work distribution layout information in the current environmental area; When a worker corresponding to a disease type associated with the dust type exists in the work assignment layout information in the current environment area, iterating according to the iterative algebra, and readjusting the work assignment layout information in the current environment area until no worker corresponding to the disease type associated with the dust type exists in the work assignment layout information in the current environment area; Controlling the environmental control device to control the environment of the target sub-area includes the following steps: Obtaining control parameter information of the optimal environmental control equipment for each dust type through big data, and introducing a graph neural network to input the control parameter information of the optimal environmental control equipment for each dust type into the graph neural network; Using the dust type and the control parameter information of the optimal environmental control equipment as graph nodes of the graph neural network, constructing an undirected heterogeneous graph based on the graph nodes, constructing a knowledge graph, and inputting the undirected heterogeneous graph into the knowledge graph for storage; Obtaining the dust type in the current environmental area, inputting the dust type in the current environmental area into the knowledge graph for data matching, and obtaining control parameter information of the optimal environmental control equipment for the dust type in the current environmental area; The environment of the target sub-area is controlled according to the control parameter information of the optimal environment control device in the dust type in the current environment area.

2. The environmental dust monitoring and early warning method according to claim 1, characterized in that: By deploying dust information monitoring sensors in the environmental area to be monitored and building a dust information monitoring network, the dust information of each sub-area in the current environmental area is obtained through the dust information monitoring network, specifically including: Obtaining layout range information of the environmental area to be monitored, configuring a dust information monitoring sensor, obtaining estimated working range information of the dust information monitoring sensor, introducing a genetic algorithm, and setting a genetic generation according to the genetic algorithm; Initializing the placement positions and the number of the dust information monitoring sensors, and calculating the total estimated working range information of the dust information monitoring sensors based on the estimated working range information, the placement positions, and the number of the dust information monitoring sensors; When the total estimated working range information of the dust information monitoring sensor is smaller than the layout range information of the environmental area to be monitored, genetic iteration is performed according to the genetic generation to adjust the layout position and layout quantity of the dust information monitoring sensor; When the total estimated working range information of the dust information monitoring sensor is not less than the layout range information of the environmental area to be monitored, the layout position and layout quantity of the dust information monitoring sensor are output, and a dust information monitoring network is constructed to obtain the dust information of each sub-area in the current environmental area through the dust information monitoring network.

3. The environmental dust monitoring and early warning method according to claim 1, characterized in that: The historical permeability change characteristic information of the protective cover under different dust information is obtained through big data, and the historical permeability change characteristic information of the protective cover under different dust information is evaluated to obtain the historical permeability membership change characteristic matrix, which specifically includes: The historical permeability change characteristic information of the protective cover under different dust information is obtained through big data, and a decision tree model is introduced to construct sample data based on the historical permeability change characteristic information of the protective cover under different dust information, and a number of historical permeability membership split evaluation indicators are preset; Using the historical permeability membership split evaluation index as a splitting criterion, inputting the sample data into the decision tree model, splitting the sample data according to the splitting criterion, obtaining a plurality of leaf nodes, and determining whether there is only one sample data within the historical permeability membership split evaluation index in the leaf node; If so, the leaf node is output; if not, the leaf node is continuously split until there is only one sample data within the historical permeability membership split evaluation index in the leaf node, the leaf node is output, the historical permeability membership information corresponding to each sample data is obtained, and a historical permeability membership change feature matrix is ​​constructed.

4. The environmental dust monitoring and early warning method according to claim 1, characterized in that: A protective cover permeability membership prediction model is constructed based on the historical permeability membership change characteristic matrix, specifically including: Introducing a Markov model, inputting the historical permeability membership change characteristic matrix into the Markov model, and obtaining a membership transition probability value of each historical permeability membership in the historical permeability membership change characteristic matrix transferring to another level of historical permeability membership; Constructing a membership transfer probability value matrix according to the membership transfer probability values, and constructing a protective cover permeability membership prediction model based on a deep neural network, and inputting the membership transfer probability value matrix into the protective cover permeability membership prediction model for coding learning; When the model parameters of the protection cover permeability membership prediction model meet the preset requirements, the model parameters of the protection cover permeability membership prediction model are saved, and the protection cover permeability membership prediction model is output.

5. The environmental dust monitoring and early warning method according to claim 1, characterized in that: Predicting the permeability membership information of the protective cover at the current timestamp by using the protective cover permeability membership prediction model specifically includes: Obtaining the permeability membership of the protective shield worn by the worker in each sub-region at the current time stamp, and inputting the permeability membership of the protective shield worn by the worker in each sub-region at the current time stamp into the protective shield permeability membership prediction model for prediction; Obtaining, by prediction, a predicted transfer probability value of the permeability membership of the protective cover at the current timestamp transferring to another level of permeability membership, and determining whether the predicted transfer probability value is greater than a preset transfer probability threshold; When the predicted transition probability value is greater than the preset transition probability value, the permeability membership of another level is used as the permeability membership information of the protective cover at the current time stamp, and the permeability membership information of the protective cover at the current time stamp is output; When the predicted transition probability value is not greater than the preset transition probability value, the permeability membership information of the protective cover in the current timestamp is output.

6. An environmental dust monitoring and early warning system, characterized in that: The system includes a memory and a processor. The memory includes a method program. When the method program is executed by the processor, the following steps are implemented: By deploying dust information monitoring sensors in the environmental area to be monitored and building a dust information monitoring network, the dust information of each sub-area in the current environmental area is obtained through the dust information monitoring network; Obtain historical permeability change characteristic information of the protective cover under different dust information through big data, and obtain a historical permeability membership change characteristic matrix by evaluating the historical permeability change characteristic information of the protective cover under different dust information; Constructing a protective cover permeability membership prediction model based on the historical permeability membership change characteristic matrix, and predicting the permeability membership information of the protective cover at the current timestamp using the protective cover permeability membership prediction model; Evaluate the dust in each sub-area in the current environment area according to the permeability membership information of the protective cover at the current timestamp, obtain an evaluation result, and generate relevant warning information based on the evaluation result; Evaluate the dust in each sub-area in the current environment area according to the permeability membership information of the protective cover at the current timestamp and obtain an evaluation result, and generate relevant warning information based on the evaluation result, specifically including: generating permeability membership information of the protective cover under the current dust information based on the permeability membership information of the protective cover at the current timestamp and the dust information of each sub-area in the current environmental area, and setting a permeability membership evaluation index; When the permeability membership information of the protective cover under the current dust information is greater than the permeability membership evaluation index, relevant warning information is generated; At the same time, relevant warning information is sent to the smart terminal held by the corresponding staff, who receive relevant prompt information through the smart terminal and control the environmental control equipment to control the environment of the target sub-area; When the permeability membership information of the protective cover under the current dust information is not greater than the permeability membership evaluation index, a relevant prompt message is sent to the smart terminal held by the corresponding staff member; The method further comprises the following steps: Obtain basic data information of workers in the current environmental area and the type of dust in the current environmental area, construct a search tag based on the dust type in the current environmental area, and search through big data based on the search tag to obtain the disease type associated with the dust type; Retrieving basic data information of workers in the current environment area according to the disease type associated with the dust type, and obtaining workers corresponding to the disease type associated with the dust type; Obtaining work distribution layout information in the current environmental area, introducing a particle swarm algorithm, setting an iterative algebra according to the particle swarm algorithm, and determining whether there is a worker corresponding to a disease type associated with the dust type in the work distribution layout information in the current environmental area; When a worker corresponding to a disease type associated with the dust type exists in the work assignment layout information in the current environment area, iterating according to the iterative algebra, and readjusting the work assignment layout information in the current environment area until no worker corresponding to the disease type associated with the dust type exists in the work assignment layout information in the current environment area; Controlling the environmental control device to control the environment of the target sub-area includes the following steps: Obtaining control parameter information of the optimal environmental control equipment for each dust type through big data, and introducing a graph neural network to input the control parameter information of the optimal environmental control equipment for each dust type into the graph neural network; Using the dust type and the control parameter information of the optimal environmental control equipment as graph nodes of the graph neural network, constructing an undirected heterogeneous graph based on the graph nodes, constructing a knowledge graph, and inputting the undirected heterogeneous graph into the knowledge graph for storage; Obtaining the dust type in the current environmental area, inputting the dust type in the current environmental area into the knowledge graph for data matching, and obtaining control parameter information of the optimal environmental control equipment for the dust type in the current environmental area; The environment of the target sub-area is controlled according to the control parameter information of the optimal environment control device in the dust type in the current environment area.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a method program, and when the method program is executed by a processor, the steps of the environmental dust monitoring and early warning method according to any one of claims 1 to 5 are implemented.

Images