A control method and system for an electronic cigarette

Abstract

The application provides a control method and system of an electronic cigarette, the method comprises the following steps: generating the current environment volume size and the current environment electronic cigarette smoke concentration distribution map based on the camera monitoring video of the current environment using a generative adversarial network; determining the personal information of each non-smoking person, the smoke concentration bearing threshold of each non-smoking person, the position of each electronic cigarette, the direction and distance between each electronic cigarette and each non-smoking person based on the camera monitoring video of the current environment using a camera processing model; constructing a knowledge graph; determining the power of each electronic cigarette based on the processing of the knowledge graph by a graph neural network model; and sending the power of each electronic cigarette to the corresponding electronic cigarette and adjusting the power of each electronic cigarette based on the power of each electronic cigarette, so that the influence of electronic cigarette smoke on non-smoking people in public places can be reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electronic cigarettes, in particular to a control method and system of an electronic cigarette. BACKGROUND

[0002] With the continuous development of modern science and technology, electronic cigarettes, as a new type of tobacco substitute, have gradually entered people's lives. Electronic cigarettes are used in various environments, including homes, offices, and public places. However, in public places, when the number of electronic cigarettes is too large, the smoke concentration may exceed the environmental capacity, causing discomfort to non-smokers and even affecting their health.

[0003] Therefore, how to reduce the impact of electronic cigarette smoke on non-smokers in public places is a problem to be solved at present. SUMMARY

[0004] The technical problem solved by the present application is how to reduce the impact of electronic cigarette smoke on non-smokers in public places.

[0005] According to a first aspect, the present application provides a control method of an electronic cigarette, comprising: judging whether the number of electronic cigarettes accessing a current environment exceeds a set threshold; if the number of electronic cigarettes accessing the current environment exceeds the set threshold, obtaining a camera monitoring video of the current environment; generating a current environment volume size and a current environment electronic cigarette smoke concentration distribution map based on the camera monitoring video of the current environment using a generative adversarial network; determining the personal information of each non-smoker, the smoke concentration threshold of each non-smoker, the position of each electronic cigarette, the direction and distance between each electronic cigarette and each non-smoker based on the camera monitoring video of the current environment using a camera processing model; constructing a knowledge graph, the knowledge graph comprising a plurality of nodes and a plurality of edges between the nodes, the plurality of nodes comprising a plurality of electronic cigarette nodes and a plurality of non-smoker nodes, each electronic cigarette node establishing an edge with each non-smoker node, the node features of each electronic cigarette node comprising the position of each electronic cigarette, the node features of each non-smoker node comprising the current environment volume size, the current environment electronic cigarette smoke concentration distribution map, the personal information of each non-smoker, the smoke concentration threshold of each non-smoker, and the features of the edge between each electronic cigarette node and each non-smoker node comprising the direction and distance between each electronic cigarette and each non-smoker; determining the power of each electronic cigarette based on a graph neural network model processing the knowledge graph; and sending the power of each electronic cigarette to the corresponding electronic cigarette and adjusting the power of each electronic cigarette based on the power of each electronic cigarette.

[0006] Further, the camera processing model is a recurrent neural network model.

[0007] Further, the method further comprises: if the number of electronic cigarettes accessing the current environment does not exceed a set threshold, determining that the environment is normal, and sending information that the environment is normal to a control terminal.

[0008] Further, the generative adversarial network is trained by a gradient descent method.

[0009] Further, the input of the generative adversarial network is the camera monitoring video of the current environment, and the output of the generative adversarial network is the volume size of the current environment and the electronic cigarette smoke concentration distribution map of the current environment.

[0010] According to a second aspect, the present application provides a control system of an electronic cigarette, comprising:

[0011] A judgment module is configured to judge whether the number of electronic cigarettes accessing the current environment exceeds a set threshold;

[0012] An acquisition module is configured to acquire a camera monitoring video of the current environment if the number of electronic cigarettes accessing the current environment exceeds the set threshold;

[0013] A generation module is configured to generate, based on the camera monitoring video of the current environment, a volume size of the current environment and an electronic cigarette smoke concentration distribution map of the current environment by using a generative adversarial network;

[0014] A camera processing module is configured to determine, based on the camera monitoring video of the current environment, personal information of each non-smoker, a smoke concentration bearing threshold of each non-smoker, a position of each electronic cigarette, a direction and distance between each electronic cigarette and each non-smoker by using a camera processing model;

[0015] A construction module is configured to construct a knowledge graph, the knowledge graph comprising a plurality of nodes and a plurality of edges between the nodes, the plurality of nodes comprising a plurality of electronic cigarette nodes and a plurality of non-smoker nodes, each electronic cigarette node establishing an edge with each non-smoker node, the node features of each electronic cigarette node comprising the position of each electronic cigarette, the node features of each non-smoker node comprising the volume size of the current environment, the electronic cigarette smoke concentration distribution map of the current environment, the personal information of each non-smoker, and the smoke concentration bearing threshold of each non-smoker, and the features of the edge established between each electronic cigarette node and each non-smoker node comprising the direction and distance between each electronic cigarette and each non-smoker;

[0016] A graph neural network module is configured to determine the power of each electronic cigarette by processing the knowledge graph based on a graph neural network model.

[0017] The power adjustment module is configured to send the power of each electronic cigarette to the corresponding electronic cigarette and adjust the power of each electronic cigarette based on the power of each electronic cigarette.

[0018] Further, the camera processing model is a recurrent neural network model.

[0019] Further, the system is further configured to determine that the environment is normal if the number of electronic cigarettes accessing the current environment does not exceed a set threshold, and send information about the normal environment to a control terminal.

[0020] Further, the generative adversarial network is trained by a gradient descent method.

[0021] Further, the input of the generative adversarial network is the camera monitoring video of the current environment, and the output of the generative adversarial network is the volume size of the current environment and the electronic cigarette smoke concentration distribution map of the current environment.

[0022] The present application provides a control method and system for electronic cigarettes, which comprises determining whether the number of electronic cigarettes accessing a current environment exceeds a set threshold, obtaining a camera monitoring video of the current environment if the number of electronic cigarettes accessing the current environment exceeds the set threshold, generating a volume size of the current environment and an electronic cigarette smoke concentration distribution map of the current environment using a generative adversarial network based on the camera monitoring video of the current environment, determining personal information of each non-smoker, a smoke concentration threshold of each non-smoker, a position of each electronic cigarette, a direction and distance between each electronic cigarette and each non-smoker using a camera processing model based on the camera monitoring video of the current environment, constructing a knowledge graph comprising a plurality of nodes and a plurality of edges between the nodes, the plurality of nodes comprising a plurality of electronic cigarette nodes and a plurality of non-smoker nodes, each electronic cigarette node establishing an edge with each non-smoker node, the node features of each electronic cigarette node comprising the position of each electronic cigarette, the node features of each non-smoker node comprising the volume size of the current environment, the electronic cigarette smoke concentration distribution map of the current environment, the personal information of each non-smoker, and the smoke concentration threshold of each non-smoker, and the features of the edge established between each electronic cigarette node and each non-smoker node comprising the direction and distance between each electronic cigarette and each non-smoker, processing the knowledge graph based on a graph neural network model to determine the power of each electronic cigarette, and sending the power of each electronic cigarette to the corresponding electronic cigarette and adjusting the power of each electronic cigarette based on the power of each electronic cigarette, which can reduce the influence of electronic cigarette smoke on non-smokers in public places. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1A flowchart of a control method of an electronic cigarette provided in an embodiment of the present application is shown in the figure.

[0024] Figure 2 A schematic diagram of a control system of an electronic cigarette provided in an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0025] In an embodiment of the present application, a control method of an electronic cigarette is provided, as shown in the figure. Figure 1 The control method of the electronic cigarette includes steps S1-S7.

[0026] Step S1: Determine whether the number of electronic cigarettes connected to the current environment exceeds a set threshold.

[0027] The set threshold refers to the upper limit or threshold of the number of electronic cigarettes set in advance. The system can determine whether the number of electronic cigarettes in the current environment exceeds the set threshold by monitoring the connection of the electronic cigarette device. As an example, the system monitors the Bluetooth connection of the electronic cigarettes in the current environment and identifies the number of connected electronic cigarette devices.

[0028] Step S2: If the number of electronic cigarettes connected to the current environment exceeds the set threshold, obtain the camera monitoring video of the current environment.

[0029] The camera monitoring video is a video signal captured by a camera device and can be used to monitor and record activities and situations in the current environment.

[0030] In some embodiments, if the number of electronic cigarettes connected to the current environment does not exceed the set threshold, it is determined that the environment is normal, and information that the environment is normal is sent to the control terminal.

[0031] Step S3: Based on the camera monitoring video of the current environment, use a generative adversarial network to generate a current environment volume size and a current environment electronic cigarette smoke concentration distribution map.

[0032] The generative adversarial network is trained by gradient descent method.

[0033] The input of the generative adversarial network is the camera monitoring video of the current environment, and the output of the generative adversarial network is the current environment volume size and the current environment electronic cigarette smoke concentration distribution map.

[0034] A generative adversarial network (GAN) is composed of a generator and a discriminator, which is used to generate realistic data samples. The generator tries to generate samples that look similar to real data, while the discriminator tries to distinguish between generated samples and real samples.

[0035] The generator part of the generative adversarial network can learn the environmental features in the camera monitoring video, including the visual features of the smoke. Through the learned environmental features, the generator can attempt to generate data samples similar to the real environment, which also includes the distribution of the smoke. The camera monitoring video can capture visual information in the current environment, including the color, density, and diffusion degree of the smoke. The generative adversarial network learns the visual features of the smoke in the environment and models the concentration distribution of the smoke through these features. The generator generates a smoke concentration distribution map that matches the actual smoke distribution in the current environment based on the input camera monitoring video.

[0036] In step S4, the camera processing model is used to determine the personal information of each non-smoker, the smoke concentration tolerance threshold of each non-smoker, the location of each electronic cigarette, and the direction and distance between each electronic cigarette and each non-smoker based on the camera monitoring video of the current environment.

[0037] The camera processing model is a recurrent neural network model. The input of the camera processing model is the camera monitoring video of the current environment, and the output of the camera processing model is the personal information of each non-smoker, the smoke concentration tolerance threshold of each non-smoker, the location of each electronic cigarette, and the direction and distance between each electronic cigarette and each non-smoker.

[0038] The recurrent neural network model includes a recurrent neural network (RNN). The recurrent neural network model can process sequence data, capture sequence information, and output results based on the correlation between data in the sequence. By processing the camera monitoring video of the current environment in a continuous time period through the recurrent neural network model, the output features can be obtained by comprehensively considering the correlation between sequences at each time point, making the output features more accurate and comprehensive.

[0039] The camera processing model can extract personal information of personnel by analyzing the camera monitoring video, such as facial recognition technology that can identify the identity features of each person. At the same time, target detection technology can be used to detect the location of electronic cigarettes.

[0040] The personal information of each non-smoker includes age, gender, height, weight, activity level, location, etc. As an example, people of different ages may have different tolerance to smoke, and the younger or older the person is, the lower the tolerance may be. Body factors such as weight and height can affect a person's physical function and tolerance to electronic cigarette smoke. The more active a person is, the stronger the tolerance to electronic cigarettes, and the higher the smoke concentration tolerance threshold.

[0041] The smoke concentration tolerance threshold of each non-smoker refers to the upper limit or maximum allowable value of the smoke concentration in the environment that the non-smoker can tolerate or bear. When the smoke concentration exceeds this threshold, it may have a negative impact on the health of the non-smoker.

[0042] In some embodiments, the camera processing model includes an information determination layer, a smoke concentration tolerance threshold layer, and a position determination layer. The information determination layer, the smoke concentration tolerance threshold layer, and the position determination layer all include a recurrent neural network structure. The input of the information determination layer is the camera monitoring video of the current environment, and the output of the information determination layer is the personal information of each non-smoker and the position of each electronic cigarette. The input of the smoke concentration tolerance threshold layer is the personal information of each non-smoker, and the output of the smoke concentration tolerance threshold layer is the smoke concentration tolerance threshold of each non-smoker. The input of the position determination layer is the position of each electronic cigarette and the personal information of each non-smoker, and the output of the position determination layer is the direction and distance between each electronic cigarette and each non-smoker.

[0043] Different layers are responsible for different levels of information abstraction and processing. For example, the information determination layer is responsible for extracting the position information of personnel and electronic cigarettes from the monitoring video, the smoke concentration tolerance threshold layer is responsible for determining the smoke concentration tolerance threshold according to the personal information, and the position determination layer is responsible for determining the relative position relationship between personnel and electronic cigarettes. Through such hierarchical processing, complex information can be processed more effectively. Building multiple layers can improve the modularity of the system, more effectively process information, and improve the accuracy and efficiency of the system.

[0044] Step S5, constructing a knowledge graph, the knowledge graph includes a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes includes a plurality of electronic cigarette nodes and a plurality of non-smoker nodes, each electronic cigarette node and each non-smoker node establish an edge, the node features of each electronic cigarette node includes the position of each electronic cigarette, the node features of each non-smoker node includes the volume size of the current environment, the electronic cigarette smoke concentration distribution map of the current environment, the personal information of each non-smoker, the smoke concentration tolerance threshold of each non-smoker, and the features of the edge between each electronic cigarette node and each non-smoker node includes the direction and distance between each electronic cigarette and each non-smoker.

[0045] The electronic cigarette node is a node representing each electronic cigarette, and the node features include the position of each electronic cigarette.

[0046] The non-smoker node is a node representing each non-smoker, and the node features include the volume size of the current environment, the electronic cigarette smoke concentration distribution map of the current environment, the personal information of each non-smoker, and the smoke concentration tolerance threshold of each non-smoker.

[0047] An edge represents the association between nodes, and each e-cigarette node establishes an edge with each non-smoker node. The characteristics of the edge include the direction and distance of each e-cigarette from each non-smoker.

[0048] In step S6, the power of each e-cigarette is determined based on the processing of the knowledge graph by the graph neural network model.

[0049] The graph neural network model includes a graph neural network (GNN) and a fully connected layer. The graph neural network is a neural network that directly acts on the knowledge graph, which is a data structure composed of nodes and edges. The input of the graph neural network model is the knowledge graph, and the output of the graph neural network model is the power of each e-cigarette.

[0050] If the power of the e-cigarette is too large, it may cause the concentration of e-cigarette smoke in the environment to be too high, and if the power of the e-cigarette is too small, it may cause the smoker to not have the pleasure of smoking, affecting the experience of the smoker. Therefore, by constructing a knowledge graph and using a graph neural network model to comprehensively consider the output of the appropriate power of each e-cigarette.

[0051] The knowledge graph represents the e-cigarette nodes and non-smoker nodes and their relationships as a graph structure. The knowledge graph integrates various information (such as the location of the e-cigarette, the size of the environment, the smoke concentration distribution map, personal information, etc.) in a structure. The characteristics of the edge include distance and direction, and the spatial position relationship between the e-cigarette and the non-smoker can be considered. These information can help the model better understand the propagation path and influence range of the e-cigarette. The knowledge graph can integrate the feature information of multiple nodes, including the location of the e-cigarette, the size of the environment, the smoke concentration distribution map, personal information, etc. Integrating these multi-source information into the knowledge graph can provide more comprehensive input data, which can help the graph neural network model to learn and predict the power of the e-cigarette more accurately.

[0052] In step S7, the power of each e-cigarette is sent to the corresponding e-cigarette, and the power of each e-cigarette is adjusted based on the power of each e-cigarette.

[0053] The control system can refer to sending instructions to control the power of the e-cigarette to the e-cigarette device to adjust the working strength of the heater and the amount of smoke generated. As an example, the power adjustment instructions can be sent from the control system to the e-cigarette device through Bluetooth or Wi-Fi connection.

[0054] Based on the same inventive concept, Figure 2 A control system for an e-cigarette is provided, which includes:

[0055] A judgment module 21 is configured to judge whether the number of electronic cigarettes accessing the current environment exceeds a set threshold value;

[0056] An acquisition module 22 is configured to acquire camera monitoring video of the current environment if the number of electronic cigarettes accessing the current environment exceeds the set threshold value.

[0057] A generation module 23 is configured to generate a current environment volume size and a current environment electronic cigarette smoke concentration distribution map based on the camera monitoring video of the current environment using a generative adversarial network.

[0058] A camera processing module 24 is configured to determine personal information of each non-smoker, a smoke concentration bearing threshold of each non-smoker, a position of each electronic cigarette, a direction and distance between each electronic cigarette and each non-smoker based on the camera monitoring video of the current environment using a camera processing model.

[0059] A construction module 25 is configured to construct a knowledge graph, the knowledge graph comprising a plurality of nodes and a plurality of edges between the nodes, the plurality of nodes comprising a plurality of electronic cigarette nodes and a plurality of non-smoker nodes, each electronic cigarette node establishing an edge with each non-smoker node, node features of each electronic cigarette node comprising a position of each electronic cigarette, node features of each non-smoker node comprising a current environment volume size, a current environment electronic cigarette smoke concentration distribution map, personal information of each non-smoker, a smoke concentration bearing threshold of each non-smoker, and features of an edge established by each electronic cigarette node with each non-smoker node comprising a direction and distance between each electronic cigarette and each non-smoker.

[0060] A graph neural network module 26 is configured to determine a power of each electronic cigarette based on processing of the knowledge graph using a graph neural network model.

[0061] A power adjustment module 27 is configured to send the power of each electronic cigarette to the corresponding electronic cigarette and adjust the power of each electronic cigarette based on the power of each electronic cigarette.

Claims

1. A control method of an electronic cigarette, characterized by, The method comprises the following steps: determining whether the number of electronic cigarettes accessing the current environment exceeds a set threshold, wherein the set threshold refers to a pre-set upper limit of the number of electronic cigarettes; if the number of electronic cigarettes accessing the current environment exceeds the set threshold, obtaining a camera monitoring video of the current environment, and if the number of electronic cigarettes accessing the current environment does not exceed the set threshold, determining that the environment is normal and sending information about the normal environment to a control terminal; generating the volume size of the current environment and the electronic cigarette smoke concentration distribution map of the current environment based on the camera monitoring video of the current environment using a generative adversarial network, wherein the generative adversarial network is trained by a gradient descent method; determining the personal information of each non-smoker, the smoke concentration bearing threshold of each non-smoker, the position of each electronic cigarette, the direction and distance between each electronic cigarette and each non-smoker based on the camera monitoring video of the current environment using a camera processing model, wherein the personal information of each non-smoker includes age, gender, height, weight, activity level and position, the camera processing model is a recurrent neural network model, and the camera processing model comprises an information determination layer, a smoke concentration bearing threshold layer and a position determination layer, wherein the information determination layer, the smoke concentration bearing threshold layer and the position determination layer all comprise a recurrent neural network structure, the input of the information determination layer is the camera monitoring video of the current environment, the output of the information determination layer is the personal information of each non-smoker and the position of each electronic cigarette, the input of the smoke concentration bearing threshold layer is the personal information of each non-smoker, the output of the smoke concentration bearing threshold layer is the smoke concentration bearing threshold of each non-smoker, the input of the position determination layer is the position of each electronic cigarette and the personal information of each non-smoker, and the output of the position determination layer is the direction and distance between each electronic cigarette and each non-smoker; constructing a knowledge graph, wherein the knowledge graph comprises a plurality of nodes and a plurality of edges between the nodes, the plurality of nodes comprise a plurality of electronic cigarette nodes and a plurality of non-smoker nodes, each electronic cigarette node is connected to each non-smoker node to form an edge, the node features of each electronic cigarette node comprise the position of each electronic cigarette, the node features of each non-smoker node comprise the volume size of the current environment, the electronic cigarette smoke concentration distribution map of the current environment, the personal information of each non-smoker and the smoke concentration bearing threshold of each non-smoker, and the features of the edge between each electronic cigarette node and each non-smoker node comprise the direction and distance between each electronic cigarette and each non-smoker; determining the power of each electronic cigarette based on a graph neural network model processing the knowledge graph; sending the power of each electronic cigarette to the corresponding electronic cigarette and adjusting the power of each electronic cigarette based on the power of each electronic cigarette.

2. The control method of the electronic cigarette according to claim 1, wherein The input of the generative adversarial network is the camera monitoring video of the current environment, and the output of the generative adversarial network is the volume size of the current environment and the electronic cigarette smoke concentration distribution map of the current environment.

3. A control system for an electronic cigarette, characterized in that The method comprises the following steps: The judgment module is configured to judge whether the number of electronic cigarettes accessing the current environment exceeds a set threshold value, and the set threshold value refers to a pre-set upper limit of the number of electronic cigarettes. The acquisition module is configured to acquire camera monitoring video of the current environment if the number of electronic cigarettes accessing the current environment exceeds the set threshold value. The generation module is configured to generate a current environment volume size and a current environment electronic cigarette smoke concentration distribution map based on the camera monitoring video of the current environment using a generative adversarial network trained by a gradient descent method. The camera processing module is configured to determine personal information of each non-smoker, a smoke concentration bearing threshold value of each non-smoker, a position of each electronic cigarette, a direction and distance between each electronic cigarette and each non-smoker based on the camera monitoring video of the current environment using a camera processing model, and the personal information of each non-smoker includes age, gender, height, weight, activity level, and position. The camera processing model is a recurrent neural network model, and the camera processing model includes an information determination layer, a smoke concentration bearing threshold value layer, and a position determination layer. The information determination layer, the smoke concentration bearing threshold value layer, and the position determination layer all include a recurrent neural network structure. The input of the information determination layer is the camera monitoring video of the current environment, the output of the information determination layer is the personal information of each non-smoker and the position of each electronic cigarette, the input of the smoke concentration bearing threshold value layer is the personal information of each non-smoker, the output of the smoke concentration bearing threshold value layer is the smoke concentration bearing threshold value of each non-smoker, and the input of the position determination layer is the position of each electronic cigarette and the personal information of each non-smoker. The output of the position determination layer is the direction and distance between each electronic cigarette and each non-smoker. The construction module is configured to construct a knowledge graph, and the knowledge graph includes a plurality of nodes and a plurality of edges between the plurality of nodes. The plurality of nodes includes a plurality of electronic cigarette nodes and a plurality of non-smoker nodes. Each electronic cigarette node establishes an edge with each non-smoker node. The node features of each electronic cigarette node include the position of each electronic cigarette. The node features of each non-smoker node include the current environment volume size, the current environment electronic cigarette smoke concentration distribution map, the personal information of each non-smoker, and the smoke concentration bearing threshold value of each non-smoker. The features of the edge established between each electronic cigarette node and each non-smoker node include the direction and distance between each electronic cigarette and each non-smoker. The graph neural network module is configured to determine the power of each electronic cigarette based on a graph neural network model processing the knowledge graph. The power adjustment module is configured to send the power of each electronic cigarette to the corresponding electronic cigarette and adjust the power of each electronic cigarette based on the power of each electronic cigarette. The system is further configured to determine that the environment is normal if the number of electronic cigarettes accessing the current environment does not exceed the set threshold value, and send information about the normal environment to a control terminal.

4. A control system for an electronic cigarette according to claim 3, wherein, The input of the generative adversarial network is a camera monitoring video of the current environment, and the output of the generative adversarial network is a current environment volume size and a current environment electronic cigarette smoke concentration distribution map.

Images