A method, system, device and medium for recovering volatile organic compounds

Abstract

The present invention provides a method, system, equipment and medium for recovering volatile organic compounds, which relates to the technical field of volatile organic compound recovery. The method includes generating a concentration map of volatile organic compounds based on laser radar data of volatile organic compounds using a generative adversarial network; determining information of personnel around the equipment using a personnel information determination model based on a monitoring video of personnel around the equipment, wherein the information of personnel around the equipment includes location information and health status; constructing a graph structure; processing the graph structure based on a graph neural network model to determine the working time length and power information of a recovery time period of a volatile organic compound recovery device; and controlling the volatile organic compound recovery device based on the working time length and power information of the recovery time period of the volatile organic compound recovery device to recover the volatile organic compounds. The method can accurately control the recovery speed of the volatile organic compounds.

Description

Technical Field

[0001] The present invention relates to the technical field of volatile organic compounds, and in particular to a method, system, equipment and medium for recovering volatile organic compounds. Background Art

[0002] Volatile organic compounds are a class of organic compounds that easily evaporate into gases at room temperature. They are widely present in industrial production, transportation, interior decoration and other fields. Volatile organic compounds are not only harmful to human health, but also pollute the environment, such as causing photochemical smog and ozone layer depletion. Therefore, the effective recovery and treatment of volatile organic compounds is an important task for environmental protection and human health. Existing volatile organic compound recovery equipment usually adopts a fixed control strategy, lacks the ability to dynamically adjust, and cannot flexibly adjust the working parameters according to actual conditions. This single control method cannot flexibly adjust the working parameters according to actual conditions, and leads to energy waste and low processing efficiency. Excessive power will cause energy waste and increase operating costs. Long-term high-power operation will accelerate equipment wear and reduce equipment life. If the power is too low, the volatile organic compounds in the environment cannot be effectively recovered, resulting in unsatisfactory treatment effects. Environmental hazards.

[0003] How to reasonably control the power of volatile organic compound recovery equipment is a problem that needs to be solved urgently. Summary of the invention

[0004] The main technical problem solved by the present invention is how to reasonably control the power of volatile organic compound recovery equipment.

[0005] According to a first aspect, the present invention provides a method for recovering volatile organic compounds, comprising: obtaining laser radar data of volatile organic compounds; generating a concentration map of volatile organic compounds using a generative adversarial network based on the laser radar data of volatile organic compounds; obtaining location information of a volatile organic compound recovery device and a monitoring video of personnel around the device; determining information about personnel around the device using a personnel information determination model based on the monitoring video of personnel around the device, wherein the information about personnel around the device includes location information and a degree of health status; constructing a graph structure, wherein the graph structure includes multiple nodes and multiple edges between the multiple nodes, the multiple nodes include a device node and multiple personnel nodes, the device node is a central node, and each Each personnel node establishes an edge with the equipment node respectively, the node characteristics of the equipment node include a concentration map of volatile organic compounds and location information of volatile organic compound recovery equipment, the node characteristics of each personnel node include location information and health status, and the characteristics of the edge between the equipment node and each personnel node include the distance and direction between the equipment and each personnel; the graph structure is processed based on a graph neural network model to determine the working time length and power information of the recovery time period of the volatile organic compound recovery equipment; based on the working time length and power information of the recovery time period of the volatile organic compound recovery equipment, the volatile organic compound recovery equipment is controlled to recover volatile organic compounds.

[0006] In a possible implementation, the personnel information determination model is a long-term and short-term neural network model.

[0007] In a possible implementation, the generative adversarial network includes a generator and a discriminator, the generator is used to generate a concentration map of volatile organic compounds, and the discriminator is used to distinguish between the generated concentration map and the true concentration map.

[0008] In one possible implementation, the step of processing the graph structure based on the graph neural network model to determine the working time length and power information of the recycling time period of the volatile organic compound recovery equipment includes: inputting the graph structure into the graph neural network model; updating the node features and edge features through the graph convolution layer; and outputting the working time length and power information of the recycling time period of the volatile organic compound recovery equipment through the output layer.

[0009] According to a second aspect, the present invention provides a volatile organic compound recovery system, comprising:

[0010] A first acquisition module is used to acquire laser radar data of volatile organic compounds;

[0011] A generation module, configured to generate a concentration map of volatile organic compounds using a generative adversarial network based on the laser radar data of the volatile organic compounds;

[0012] The second acquisition module is used to obtain the location information of the volatile organic compound recovery equipment and the monitoring video of personnel around the equipment;

[0013] A personnel information determination module, configured to determine the personnel information around the device using a personnel information determination model based on the personnel monitoring video around the device, wherein the personnel information around the device includes location information and health status;

[0014] A construction module, for constructing a graph structure, wherein the graph structure includes a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes including a device node and a plurality of personnel nodes, the device node being a central node, each personnel node establishing an edge with the device node, the node features of the device node including a concentration map of volatile organic compounds and location information of a volatile organic compound recovery device, the node features of each personnel node including location information and health status, and the features of the edge between the device node and each personnel node including a distance and direction between the device and each personnel;

[0015] A determination module, configured to process the graph structure based on a graph neural network model to determine the working time length and power information of the recovery time period of the volatile organic compound recovery equipment;

[0016] The control module is used to control the volatile organic compound recovery device based on the working time length and power information of the recovery time period of the volatile organic compound recovery device to recover the volatile organic compounds.

[0017] In a possible implementation, the personnel information determination model is a long-term and short-term neural network model.

[0018] In a possible implementation, the generative adversarial network includes a generator and a discriminator, the generator is used to generate a concentration map of volatile organic compounds, and the discriminator is used to distinguish between the generated concentration map and the true concentration map.

[0019] In a possible implementation manner, the determining module is further configured to:

[0020] Inputting the graph structure into a graph neural network model;

[0021] Update node features and edge features through graph convolutional layers;

[0022] The working time length and power information of the recovery time period of the volatile organic compound recovery equipment are outputted through the output layer.

[0023] According to a third aspect, an embodiment of the present invention provides an electronic device, comprising: a processor; a memory; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method as described above, the method comprising: obtaining laser radar data of volatile organic compounds; generating a concentration map of volatile organic compounds using a generative adversarial network based on the laser radar data of volatile organic compounds; obtaining location information of a volatile organic compound recovery device and a monitoring video of personnel around the device; determining information of personnel around the device using a personnel information determination model based on the monitoring video of personnel around the device, the information of personnel around the device including location information and health status; constructing a graph structure, the graph structure including multiple nodes and multiple edges between the multiple nodes, The multiple nodes include a device node and multiple personnel nodes, the device node is a central node, and each personnel node establishes an edge with the device node respectively, the node characteristics of the device node include a concentration map of volatile organic compounds and location information of a volatile organic compound recovery device, the node characteristics of each personnel node include location information and health status, and the characteristics of the edge between the device node and each personnel node include the distance and direction between the device and each personnel; the graph structure is processed based on a graph neural network model to determine the working time length and power information of a recovery time period of the volatile organic compound recovery device; based on the working time length and power information of the recovery time period of the volatile organic compound recovery device, the volatile organic compound recovery device is controlled to recover volatile organic compounds.

[0024] According to the fourth aspect, the present embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the volatile organic compound recovery method provided above, the method comprising: obtaining laser radar data of volatile organic compounds; generating a concentration map of volatile organic compounds using a generative adversarial network based on the laser radar data of volatile organic compounds; obtaining location information of a volatile organic compound recovery device and a monitoring video of personnel around the device; determining information of personnel around the device using a personnel information determination model based on the monitoring video of personnel around the device, the information of personnel around the device including location information and health status; constructing a graph structure, the graph structure including multiple nodes and multiple edges between the multiple nodes, the multiple nodes including device nodes and multiple personnel nodes, the device node is a central node, each personnel node establishes an edge with the device node, the node characteristics of the device node include a concentration map of volatile organic compounds and location information of volatile organic compound recovery equipment, the node characteristics of each personnel node include location information and health status, and the characteristics of the edge between the device node and each personnel node include the distance and direction between the equipment and each personnel; based on the graph neural network model, the graph structure is processed to determine the working time length and power information of the recovery time period of the volatile organic compound recovery equipment; based on the working time length and power information of the recovery time period of the volatile organic compound recovery equipment, the volatile organic compound recovery equipment is controlled to recover volatile organic compounds.

[0025] The present invention provides a method and system for recovering volatile organic compounds, the method comprising obtaining laser radar data of volatile organic compounds; generating a concentration map of volatile organic compounds using a generative adversarial network based on the laser radar data of volatile organic compounds; obtaining location information of volatile organic compound recovery equipment and a monitoring video of personnel around the equipment; determining personnel information around the equipment using a personnel information determination model based on the monitoring video of personnel around the equipment, the personnel information around the equipment including location information and health status; constructing a graph structure, the graph structure including multiple nodes and multiple edges between the multiple nodes, the multiple nodes including device nodes and multiple personnel nodes, the device nodes being central nodes, and each personnel node being respectively connected to the device nodes; The node establishes an edge, the node characteristics of the device node include a concentration map of volatile organic compounds and location information of volatile organic compound recovery equipment, the node characteristics of each personnel node include location information and health status, and the characteristics of the edge between the device node and each personnel node include the distance and direction between the device and each personnel; the graph structure is processed based on a graph neural network model to determine the working time length and power information of the recovery time period of the volatile organic compound recovery equipment; based on the working time length and power information of the recovery time period of the volatile organic compound recovery equipment, the volatile organic compound recovery equipment is controlled to recover volatile organic compounds. The method can reasonably control the power of the volatile organic compound recovery equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A schematic diagram of an application scenario of a method for recovering volatile organic compounds provided by an embodiment of the present invention;

[0027] Figure 2 A schematic flow chart of a method for recovering volatile organic compounds provided by an embodiment of the present invention;

[0028] Figure 3 A schematic diagram of a volatile organic compound recovery system provided by an embodiment of the present invention;

[0029] Figure 4 A schematic diagram of an electronic device provided by an embodiment of the present invention;

[0030] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present invention better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present invention are not shown or described in the specification, this is to avoid the core part of the present invention being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0032] Figure 1 A schematic diagram of an application scenario of a method for recovering volatile organic compounds provided in an embodiment of the present invention. Figure 1 The application scenario of the method for recovering volatile organic compounds may include a server 11 , a network 12 , a terminal 13 and a storage device 14 .

[0033] In some embodiments, the server 11 may be a single server or a server group. The server 11 may access information and / or data stored in the terminal 13 or the storage device 14 through the network 12. In some embodiments, the server 11 may be used to execute Figure 2 The method for recovering volatile organic compounds shown in .

[0034] The network 12 may facilitate the exchange of information and / or data. In some embodiments, the network 12 may be any form of wired or wireless network, or any combination thereof.

[0035] Terminal 13 may refer to one or more terminal devices used by a user. In some embodiments, terminal 13 may include one or more combinations of a mobile device, a tablet computer, a laptop computer, etc. For example, the terminal may store a screen recording video obtained after the screen recording function is turned on.

[0036] The storage device 14 may store data and / or instructions. For example, the storage device 14 may store data instructions of a method for recovering volatile organic compounds.

[0037] In an embodiment of the present invention, there is provided Figure 2 A method for recovering volatile organic compounds is shown, and the method for recovering volatile organic compounds comprises steps S1 to S7:

[0038] Step S1, obtaining laser radar data of volatile organic compounds.

[0039] LiDAR is a long-range sensing technology that can determine the distance of a target by emitting laser pulses and measuring the time it takes for those pulses to return to the sensor. LiDAR can be used to detect volatile organic compounds in the air and generate data on their spatial distribution.

[0040] For example, one or more LiDAR devices are installed in a chemical plant, which are set to scan the plant area periodically. When the laser beam hits particles containing volatile organic compounds in the air, scattering occurs. By analyzing the intensity and time delay of the reflected laser signal, the location and concentration of the volatile organic compounds can be inferred.

[0041] Step S2: generating a concentration map of volatile organic compounds using a generative adversarial network based on the laser radar data of the volatile organic compounds.

[0042] The generative adversarial network includes a generator and a discriminator, wherein the generator is used to generate a concentration map of volatile organic compounds, and the discriminator is used to distinguish the generated concentration map from the true concentration map. The input of the generative adversarial network is the laser radar data of the volatile organic compounds, and the output of the generative adversarial network is the concentration map of the volatile organic compounds.

[0043] LiDAR data includes spatial position information, reflected signal intensity information, and spectral information. LiDAR can accurately determine the location of VOCs in the air by emitting laser pulses and measuring their return time. This provides the distribution of VOCs in three-dimensional space. Different types of VOCs have different absorption and scattering characteristics of lasers, so the intensity of the reflected signal can reflect different types and concentrations of VOCs. Lasers of different wavelengths have different responses to different types of VOCs. Through multi-wavelength scanning, richer VOC information can be obtained.

[0044] The concentration map of volatile organic compounds is a concentration distribution map of volatile organic compounds generated by the generative adversarial network.

[0045] The generator in the generative adversarial network learns to extract features from the input data distribution through training and synthesize new samples based on these features. The generator can learn how to extract the spatial distribution pattern of volatile organic compounds from low-resolution or sparse lidar data and convert it into a higher-resolution and more detailed concentration map.

[0046] Step S3, obtaining the location information of the volatile organic compound recovery equipment and the monitoring video of personnel around the equipment.

[0047] The position information of the volatile organic compound recovery device refers to the position information of the volatile organic compound recovery device when processing volatile organic compounds.

[0048] The equipment surrounding personnel monitoring video is the monitoring video obtained by monitoring the surrounding personnel with the cameras installed around the equipment.

[0049] Step S4, determining the information of people around the device using a personnel information determination model based on the monitoring video of people around the device, wherein the information of people around the device includes location information and health status.

[0050] The personnel information determination model is a long-term and short-term neural network model. The input of the personnel information determination model is the monitoring video of personnel around the device, and the output of the personnel information determination model is the personnel information around the device, and the personnel information around the device includes location information and health status.

[0051] The long-term and short-term neural network model includes a long-term and short-term neural network (LSTM, Long Short-Term Memory). The long-term and short-term neural network model can process the monitoring videos of people around the device in continuous time periods, can better capture the relationship in the time series of the monitoring videos of people around the device, and can output the features that comprehensively consider the correlation between the monitoring videos of people around the device at each time point, so that the output features are more accurate and comprehensive.

[0052] In some embodiments, the personnel information determination model includes a personnel segmentation layer, a personnel information determination layer, a single health data layer, a single health determination layer, and a health status degree determination layer. The personnel segmentation layer, the personnel information determination layer, the single health data layer, the single health determination layer, and the health status degree determination layer all include long-term and short-term neural network structures. The input of the personnel segmentation layer is the monitoring video of personnel around the device, and the output of the personnel segmentation layer is the segmented video and location information of each person. The input of the personnel information determination layer is the segmented video of each person, and the output of the personnel information determination layer is the facial expression sequence data of each person, the body posture sequence data of each person, the breathing behavior sequence data of each person, and the skin color sequence data of each person. The input of the single health data layer is the health degree of each person's facial expression, the body posture sequence data of each person, the breathing behavior sequence data of each person, and the skin color sequence data of each person. The output of the single health data layer is the emotional state data of each person, the physical activity level data of each person, The breathing quality data of each person and the skin condition data of each person. The input of the single health determination layer is the emotional state data of each person, the physical activity level data of each person, the breathing quality data of each person, the physical activity level data of each person, the breathing quality data of each person, and the skin condition data of each person. The output of the single health determination layer is the psychological condition data of each person, the bone condition data of each person, the lung data of each person, and the aging data of each person. The input of the health status degree determination layer is the psychological condition data of each person, the bone condition data of each person, the lung data of each person, and the aging data of each person. The output of the health status degree determination layer is the health status degree of each person.

[0053] Through multi-layer processing, data from multiple modalities (such as facial expressions, body posture, breathing behavior, skin color) can be integrated to generate a more comprehensive health assessment. Through hierarchical design, the personnel information determination model can gradually extract and process information at different levels, and finally generate a comprehensive personnel health status assessment. This design not only improves the robustness and accuracy of the model, but also enhances the modularity and interpretability of the model.

[0054] Step S5, constructing a graph structure, wherein the graph structure includes multiple nodes and multiple edges between the multiple nodes, the multiple nodes include a device node and multiple personnel nodes, the device node is a central node, and each personnel node establishes an edge with the device node respectively, the node characteristics of the device node include a concentration map of volatile organic compounds and location information of volatile organic compound recovery equipment, the node characteristics of each personnel node include location information and health status, and the characteristics of the edge between the device node and each personnel node include the distance and direction between the device and each personnel.

[0055] The graph structure includes multiple nodes and multiple edges. The multiple nodes include device nodes and multiple personnel nodes, the device node is the central node, and each personnel node establishes an edge with the device node. Each node and edge has specific characteristics.

[0056] The device node represents the VOC recovery device, and its characteristics include the VOC concentration map and the location information of the device.

[0057] The personnel node represents the personnel around the equipment, and its characteristics include location information and health status.

[0058] Edges represent the relationship between device nodes and personnel nodes, and the characteristics of the edges include the distance and direction between the device and each person.

[0059] The operation of volatile organic compound recovery equipment will directly affect the health of surrounding workers. By building a graph structure, the relationship between the equipment and each person can be clearly represented, including distance and direction.

[0060] Step S6: Process the graph structure based on the graph neural network model to determine the working time length and power information of the recovery time period of the volatile organic compound recovery equipment.

[0061] Graph neural network is a deep learning model specially designed for processing graph structured data. Graph neural network transfers information between nodes in the graph through message passing mechanism, thereby learning the representation of nodes in the graph.

[0062] The graph structure naturally represents the connections between equipment nodes and personnel nodes, which helps capture the impact of equipment operations on surrounding workers, such as the interaction between VOC concentrations and equipment locations and employee locations and health status.

[0063] Both device nodes and person nodes contain multiple features that can provide rich contextual information to the model. The location and VOC concentration of the device can help understand the environmental conditions, while the location and health status of the person provide information about potential risks.

[0064] The graph structure can comprehensively consider multiple factors such as the operating status of the equipment, the concentration distribution of volatile organic compounds, the location and health status of personnel, etc., to achieve global optimization. For example, by analyzing the information in the graph structure, it is possible to determine under which time periods and power settings the equipment has the best recycling effect while having the least impact on personnel health.

[0065] The graph structure helps to assess the potential risks of equipment operation to personnel health. For example, by analyzing the distance and direction between the equipment and personnel, the impact of the equipment under different time periods and power settings can be predicted, so as to select the best operation plan to ensure personnel health.

[0066] The VOC concentration map can be used in the graph neural network model to accurately understand the distribution of VOCs in the environment, which is the basis for deciding when and where the equipment works.

[0067] The location information and health status of personnel obtained through monitoring video analysis can ensure that the equipment operates without affecting the health of personnel.

[0068] Graph structures and graph neural network models can help determine the optimal length of working time, avoid working time that is too long or too short, and ensure that the equipment operates in the most appropriate time period to achieve the best recovery effect. Through graph structure analysis, the power of the equipment can be reasonably set to avoid energy waste, equipment wear and increased operating costs caused by excessive power, and also avoid poor recovery effects caused by too low power. Graph structures can be used to evaluate the potential risks of equipment operation to personnel health. For example, if the concentration of volatile organic compounds in a certain area is high and there are people nearby, the impact on personnel can be reduced by increasing the operating power of the equipment. The personnel nodes in the graph structure contain location information and health status, which helps to monitor the health status of personnel in real time and ensure that the operation of the equipment will not have adverse effects on personnel. Both graph structures and graph neural network models are trained based on a large amount of historical data, and can learn the optimal operation strategy from the data to improve the scientificity and accuracy of decision-making.

[0069] The working time length of the recovery time period indicates how long the volatile organic compound recovery device works when recovering organic compounds. The power information indicates the power size of the volatile organic compound recovery device in the recovery time period.

[0070] In some embodiments, the step of processing the graph structure based on the graph neural network model to determine the working time length and power information of the recovery time period of the volatile organic compound recovery equipment includes:

[0071] Inputting the graph structure into a graph neural network model;

[0072] Update node features and edge features through graph convolutional layers;

[0073] The working time length and power information of the recovery time period of the volatile organic compound recovery equipment are outputted through the output layer.

[0074] Step S7: controlling the volatile organic compound recovery device based on the working time length of the recovery time period of the volatile organic compound recovery device and the power information to recover the volatile organic compounds.

[0075] When the working time length and power information of the recovery time period of the volatile organic compound recovery device are determined, the volatile organic compound recovery device is controlled to recover the volatile organic compounds. For example, if the working time length of the recovery time period of the volatile organic compound recovery device is one hour and the power is one kilowatt, the volatile organic compound recovery device is controlled to work for one hour, and the working power of this one hour is one kilowatt.

[0076] Based on the same inventive concept, Figure 3 A schematic diagram of a volatile organic compound recovery system provided in an embodiment of the present invention, the volatile organic compound recovery system comprising:

[0077] A first acquisition module 31 is used to acquire laser radar data of volatile organic compounds;

[0078] A generating module 32, configured to generate a concentration map of volatile organic compounds using a generative adversarial network based on the laser radar data of the volatile organic compounds;

[0079] The second acquisition module 33 is used to obtain the location information of the volatile organic compound recovery equipment and the monitoring video of personnel around the equipment;

[0080] A personnel information determination module 34, configured to determine the personnel information around the device using a personnel information determination model based on the personnel monitoring video around the device, wherein the personnel information around the device includes location information and health status;

[0081] A construction module 35 is used to construct a graph structure, wherein the graph structure includes a plurality of nodes and a plurality of edges between the plurality of nodes, wherein the plurality of nodes include a device node and a plurality of personnel nodes, wherein the device node is a central node, and each personnel node establishes an edge with the device node, wherein the node characteristics of the device node include a concentration diagram of volatile organic compounds and location information of a volatile organic compound recovery device, the node characteristics of each personnel node include location information and health status, and the characteristics of the edge between the device node and each personnel node include a distance and direction between the device and each personnel;

[0082] A determination module 36, configured to process the graph structure based on a graph neural network model to determine the working time length and power information of the recovery time period of the volatile organic compound recovery equipment;

[0083] The control module 37 is used to control the volatile organic compound recovery device to recover the volatile organic compounds based on the working time length and power information of the recovery time period of the volatile organic compound recovery device.

[0084] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, such as Figure 4 As shown, including:

[0085] The invention comprises: a processor 41; a memory 42; and a computer program; wherein the computer program is stored in the memory 42 and is configured to be executed by the processor 41 to implement the volatile organic compound recovery method as provided above, the method comprising: obtaining laser radar data of volatile organic compounds; generating a concentration map of volatile organic compounds using a generative adversarial network based on the laser radar data of volatile organic compounds; obtaining location information of a volatile organic compound recovery device and a monitoring video of personnel around the device; determining information of personnel around the device using a personnel information determination model based on the monitoring video of personnel around the device, the information of personnel around the device including location information and health status; constructing a graph structure, the graph structure including multiple nodes and multiple edges between the multiple nodes, multiple nodes The points include a device node and multiple personnel nodes, the device node is a central node, and each personnel node establishes an edge with the device node respectively, the node characteristics of the device node include a concentration map of volatile organic compounds and location information of volatile organic compound recovery equipment, the node characteristics of each personnel node include location information and health status, and the characteristics of the edge between the device node and each personnel node include the distance and direction between the device and each personnel; the graph structure is processed based on a graph neural network model to determine the working time length and power information of the recovery time period of the volatile organic compound recovery equipment; based on the working time length and power information of the recovery time period of the volatile organic compound recovery equipment, the volatile organic compound recovery equipment is controlled to recover volatile organic compounds.

[0086] Based on the same inventive concept, this embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor 41, implements the aforementioned method for recovering volatile organic compounds, the method comprising: obtaining laser radar data of volatile organic compounds; generating a concentration map of volatile organic compounds using a generative adversarial network based on the laser radar data of volatile organic compounds; obtaining location information of a volatile organic compound recovery device and a monitoring video of personnel around the device; determining information of personnel around the device using a personnel information determination model based on the monitoring video of personnel around the device, the information of personnel around the device including location information and health status; constructing a graph structure, the graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes comprising a device node and a plurality of personnel nodes, the device node being a central node, and each personnel node being respectively connected to the device node. Establish edges, the node characteristics of the device node include a concentration map of volatile organic compounds and location information of volatile organic compound recovery equipment, the node characteristics of each personnel node include location information and health status, and the characteristics of the edge between the device node and each personnel node include the distance and direction between the device and each personnel; based on the graph neural network model, the graph structure is processed to determine the working time length and power information of the recovery time period of the volatile organic compound recovery equipment; based on the working time length and power information of the recovery time period of the volatile organic compound recovery equipment, the volatile organic compound recovery equipment is controlled to recover volatile organic compounds.

[0087] The method for recovering volatile organic compounds provided in the embodiments of the present application can be applied to terminal devices (such as mobile phones), tablet computers, laptop computers, ultra-mobile personal computers (UMPCs), handheld computers, netbooks, personal digital assistants (PDAs), wearable devices (such as smart watches, smart glasses or smart helmets, etc.), augmented reality (AR) and virtual reality (VR) devices, smart home devices, car computers and other electronic devices, and the embodiments of the present application do not impose any restrictions on this.

[0088] Taking the mobile phone 100 as an example of the electronic device, Figure 5 A schematic structural diagram of the mobile phone 100 is shown.

[0089] like Figure 5As shown, the mobile phone 100 may include a processing module 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0090] The mobile phone 100 can be used to control a volatile organic compound recovery device.

[0091] The processing module 110 may include one or more processing units, for example, the processing module 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0092] The processing module 110 can be used to obtain laser radar data of volatile organic compounds; generate a concentration map of volatile organic compounds based on the laser radar data of the volatile organic compounds using a generative adversarial network; obtain the location information of the volatile organic compound recovery equipment and the monitoring video of personnel around the equipment; determine the personnel information around the equipment using a personnel information determination model based on the monitoring video of personnel around the equipment, the personnel information around the equipment includes location information and health status; construct a graph structure, the graph structure includes multiple nodes and multiple edges between the multiple nodes, the multiple nodes include a device node and multiple personnel nodes, the device node is a central node, and each personnel node is respectively connected to the The device node establishes an edge, the node characteristics of the device node include a concentration map of volatile organic compounds and location information of volatile organic compound recovery equipment, the node characteristics of each personnel node include location information and health status, and the characteristics of the edge between the device node and each personnel node include the distance and direction between the device and each personnel; the graph structure is processed based on a graph neural network model to determine the working time length and power information of the recovery time period of the volatile organic compound recovery equipment; based on the working time length and power information of the recovery time period of the volatile organic compound recovery equipment, the volatile organic compound recovery equipment is controlled to recover volatile organic compounds.

[0093] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0094] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0095] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0096] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0097] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for recovering volatile organic compounds, characterized in that: The following steps are involved: Obtain lidar data for volatile organic compounds; Generate a concentration map of volatile organic compounds using a generative adversarial network based on the laser radar data of the volatile organic compounds, wherein the generative adversarial network includes a generator and a discriminator, wherein the generator is used to generate the concentration map of volatile organic compounds, and the discriminator is used to distinguish between the generated concentration map and the true concentration map; Obtain the location information of volatile organic compound recovery equipment and surveillance video of personnel around the equipment; Based on the monitoring video of personnel around the device, a personnel information determination model is used to determine the personnel information around the device, wherein the personnel information around the device includes location information and health status, and the personnel information determination model is a long-term and short-term neural network model; Constructing a graph structure, the graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes comprising a device node and a plurality of personnel nodes, the device node being a central node, each personnel node establishing an edge with the device node, the node features of the device node comprising a concentration map of volatile organic compounds and location information of a volatile organic compound recovery device, the node features of each personnel node comprising location information and health status, and the features of the edge between the device node and each personnel node comprising a distance and direction between the device and each personnel; Processing the graph structure based on a graph neural network model to determine the working time length and power information of the recovery time period of the volatile organic compound recovery equipment; The volatile organic compound recovery device is controlled based on the working time length of the recovery time period of the volatile organic compound recovery device and the power information to recover the volatile organic compounds.

2. The method according to claim 1, characterized in that The step of processing the graph structure based on the graph neural network model to determine the working time length and power information of the recovery time period of the volatile organic compound recovery equipment includes: Inputting the graph structure into a graph neural network model; Update node features and edge features through graph convolutional layers; The working time length and power information of the recovery time period of the volatile organic compound recovery equipment are outputted through the output layer.

3. A volatile organic compound recovery system, characterized in that: include: A first acquisition module is used to acquire laser radar data of volatile organic compounds; A generating module, configured to generate a concentration map of volatile organic compounds using a generative adversarial network based on the laser radar data of the volatile organic compounds, wherein the generative adversarial network includes a generator and a discriminator, wherein the generator is configured to generate the concentration map of the volatile organic compounds, and the discriminator is configured to distinguish between the generated concentration map and the true concentration map; The second acquisition module is used to obtain the location information of the volatile organic compound recovery equipment and the monitoring video of personnel around the equipment; A personnel information determination module, used to determine the personnel information around the device using a personnel information determination model based on the personnel monitoring video around the device, wherein the personnel information around the device includes location information and health status, and the personnel information determination model is a long-term and short-term neural network model; A construction module, for constructing a graph structure, wherein the graph structure includes a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes including a device node and a plurality of personnel nodes, the device node being a central node, each personnel node establishing an edge with the device node, the node features of the device node including a concentration map of volatile organic compounds and location information of a volatile organic compound recovery device, the node features of each personnel node including location information and health status, and the features of the edge between the device node and each personnel node including a distance and direction between the device and each personnel; A determination module, configured to process the graph structure based on a graph neural network model to determine the working time length and power information of the recovery time period of the volatile organic compound recovery equipment; The control module is used to control the volatile organic compound recovery device to recover the volatile organic compounds based on the working time length and power information of the recovery time period of the volatile organic compound recovery device.

4. The volatile organic compound recovery system according to claim 3, characterized in that: The determining module is also used for: Inputting the graph structure into a graph neural network model; Update node features and edge features through graph convolutional layers; The working time length and power information of the recovery time period of the volatile organic compound recovery equipment are outputted through the output layer.

5. An electronic device, characterized in that: include: processor; Memory; and a computer program; wherein the computer program is stored in the memory and is configured to be executed by the processor to implement the method for recovering volatile organic compounds as claimed in any one of claims 1 to 2.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for recovering volatile organic compounds as claimed in any one of claims 1 to 2 is implemented.

Images