Smoker smoking cessation intervention method and device, intelligent wearable equipment and storage medium

Abstract

The invention relates to the technical field of medical care, and provides a smoker smoking cessation intervention method and device, intelligent wearable equipment and a storage medium, and the method is applied to the intelligent wearable equipment, and comprises the steps: collecting physiological data, behavior data, environment data and other multi-modal data of a user, and inputting the data into an intelligent monitoring model, obtaining an intervention strategy output by the intelligent monitoring model; the intelligent monitoring model is constructed based on a neural network model and is obtained through sample data training, and the sample data is constructed by taking historical data of multi-modal data as a sample and taking an intervention strategy marked with an intervention level as a label; and performing smoking cessation intervention on the user based on the intervention strategy. The limitation of traditional smoking cessation intervention is broken through through the intelligent wearable device, full-link intellectualization from data acquisition, risk prediction to accurate intervention is achieved, a dynamic intervention mechanism integrating environment, physiology and behaviors is constructed, efficient, accurate and personalized smoking cessation support is provided for a user, and the smoking cessation intervention effect is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of medical care technology, and in particular to a method, device, smart wearable device and storage medium for intervening in smokers to quit smoking. Background Art

[0002] Smoking is a major health hazard. Smokers are dependent on nicotine, making quitting smoking a challenging process for smokers, requiring sustained motivation, effective supervision, and personalized guidance. Traditional smoking cessation methods, such as nicotine replacement therapy and behavioral interventions, rely on user initiative and lack real-time monitoring and dynamic intervention, resulting in extremely low success rates.

[0003] With the widespread adoption and development of smart devices, using them to assist with smoking cessation has become a new possibility. Existing intervention devices used to assist with smoking cessation have limited functionality, simply recording the number of times smoked. These devices rely on the user's active recording and are unable to accurately identify the user's tobacco cravings and relapse risk. Their intervention methods are overly mechanical (only vibrating reminders), making it difficult to provide accurate and effective smoking cessation support and intervention effectiveness. Summary of the Invention

[0004] The present invention provides a method, device, smart wearable device and storage medium for smokers to quit smoking, which are used to solve the shortcomings of the existing technology of smart devices for assisting smoking cessation, such as single functions, overly mechanical intervention methods, difficulty in providing accurate and effective smoking cessation support, and limited intervention effects.

[0005] The present invention provides a method for intervening in smoking cessation for smokers, which is applied to a smart wearable device and comprises the following steps: Collecting multimodal data of the user; the multimodal data includes physiological data, behavioral data and environmental data; Inputting the multimodal data into an intelligent monitoring model to obtain an intervention strategy output by the intelligent monitoring model; the intelligent monitoring model is constructed based on a neural network model and trained with sample data, the sample data being constructed using historical data of the multimodal data as samples and intervention strategies as sample labels, wherein the sample labels are marked with intervention levels; Performing smoking cessation intervention on the user based on the intervention strategy.

[0006] According to the smoking cessation intervention method provided by the present invention, the process of the intelligent monitoring model processing the multimodal data to obtain the intervention strategy includes: determining, based on the physiological data in the multimodal data, a change trend of a physiological characteristic of the user associated with smoking craving; Identifying a posture change of the user based on the behavioral data in the multimodal data; the posture change includes an arm movement trajectory and a hand-raising frequency of the user; Performing scene classification on the environmental data in the multimodal data to determine the scene category of the user's environment; the scene category is used to characterize the degree of influence of the environment on the user's desire to smoke; Performing a comprehensive analysis of the changing trend of the physiological characteristics, the changing status of the posture, and the scene category to determine the probability and degree of the user's urge to smoke within a future preset time period; An intervention level is determined according to the probability and the degree of smoking urge, and an intervention strategy is generated based on the intervention level; the intervention strategy includes intervention content under the intervention level.

[0007] The smoking cessation intervention method for smokers provided by the present invention further comprises, after collecting the multimodal data of the user: Sending the multimodal data to a terminal application, and the terminal application sending the multimodal data to a server; The server periodically iteratively trains the intelligent engine corresponding to the intelligent monitoring model based on the multimodal data to obtain updated model parameters; Receive the updated model parameters sent by the server, and optimize the intelligent monitoring model using the updated model parameters.

[0008] According to the smoking cessation intervention method for smokers provided by the present invention, the smart wearable device is provided with a multimodal sensor array, and the multimodal sensor array is used to collect the multimodal data; wherein: The multimodal sensor array includes at least one carbon monoxide sensor, at least one temperature sensor, at least one biosensor, and at least one motion sensor; The biosensor is used to collect the physiological data, wherein the physiological data includes at least one of heart rate, blood pressure, blood sugar, blood oxygen, psychological state data, sleep data and skin conductivity; The motion sensor is used to collect the behavior data, and the behavior data includes at least one of the user's motion data, hand movements, hand raising frequency, and arm movement trajectory; The carbon monoxide sensor and the temperature sensor are used to collect the environmental data, which at least includes the ambient temperature and the ambient carbon monoxide concentration; and the ambient nicotine concentration is calculated based on the ambient carbon monoxide concentration.

[0009] According to the smoking cessation intervention method provided by the present invention, the smart wearable device is further provided with at least one environmental monitoring port for extracting air samples from the user's environment and collecting exhaled gas samples from the user; the physiological data also includes nicotine concentration in the body; and the multimodal data collected from the user includes: Based on a pre-generated timed sampling task, extract an air sample through the environmental monitoring hole, and detect a first concentration of carbon monoxide in the air sample; Output sampling prompt information; the sampling prompt information is used to prompt the user to blow air towards the environmental monitoring hole for a preset time; obtaining an exhaled gas sample of the user upon detecting that the user has completed blowing, and detecting a second concentration of carbon monoxide in the exhaled gas sample; estimating a nicotine concentration in the user's body based on a difference between the first concentration and the second concentration; The smart wearable device is also provided with a microphone hole, which is used to collect ambient sound for smoke detection; The smart wearable device is further provided with a display screen, which is used to display part or all of the multimodal data.

[0010] According to the smoking cessation intervention method provided by the present invention, after performing smoking cessation intervention on the user based on the intervention strategy, the method further includes: monitoring the intervention effect of the intervention strategy on the user; A smoking cessation report is generated based on the intervention effect and the record log, and the report is sent to a terminal application for the user to review. The record log is generated based on the timed reminder task and is based on the user's smoking record operation and / or the detected smoking behavior of the user. The timed reminder task is used to regularly remind the user to record smoking and learn smoking cessation techniques. The smoking cessation report includes smoking behavior statistics, physiological change trends, smoking addiction assessment results, nicotine concentration change curve in the body, and smoking cessation achievements. If it is determined that the user meets the reward conditions based on the smoking cessation achievement, a virtual object is issued to the user's account; the virtual object can be used to redeem products or services; The smoking cessation achievement is pushed to the terminal application of the user's interactive user; the interactive user is a user who has a social relationship with the user.

[0011] The present invention also provides a device for intervening in smoking cessation, which is applied to a smart wearable device. The device comprises the following modules: A data acquisition module, configured to collect multimodal data of the user, including physiological data, behavioral data, and environmental data; a smoking monitoring module configured to input the multimodal data into an intelligent monitoring model to obtain an intervention strategy output by the intelligent monitoring model; the intelligent monitoring model is constructed based on a neural network model and trained with sample data, the sample data being constructed using historical data of the multimodal data as samples and intervention strategies as sample labels, the sample labels being marked with intervention levels; A smoking cessation intervention module is used to perform smoking cessation intervention on the user based on the intervention strategy.

[0012] The present invention also provides a smart wearable device for smoking cessation intervention, wherein the main body of the smart wearable device includes a back shell and a display screen, the back shell includes a concave surface and a convex surface, and the display screen is embedded in the concave surface of the back shell; the convex surface of the back shell is provided with a multimodal sensor array; The smart wearable device also includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, any one of the above-described intervention methods for smokers to quit smoking is implemented.

[0013] According to the smart wearable device for smoking cessation intervention provided by the present invention, the multimodal sensor array includes at least one carbon monoxide sensor, at least one temperature sensor, at least one biosensor, and at least one motion sensor; The back shell also includes a first side surface and a second side surface that are opposite to each other, and a third side surface and a fourth side surface that are opposite to each other; the first side surface and the second side surface are provided with environmental monitoring holes for extracting gas samples required for detection; a microphone hole is provided on the first side surface or the second side surface, a magnetic charging contact is provided on the first side surface or the second side surface, and fixing parts for wearing are provided on the third side surface and the fourth side surface.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program implements any of the above-mentioned intervention methods for smokers to quit smoking.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned intervention methods for smokers to quit smoking.

[0016] The present invention provides a smoking cessation intervention method, device, smart wearable device, and storage medium for smokers. Through the collection of multimodal data by the smart wearable device and the recognition of multimodal data by the intelligent monitoring model, it can achieve real-time and comprehensive monitoring of the user's physiological state, behavioral changes, and environment. Based on the intervention strategy, dynamic and personalized intervention is carried out for the user to quit smoking. By using smart wearable devices, the limitations of traditional smoking cessation intervention are broken through, and the full chain from data collection and risk prediction to precise intervention is realized. A dynamic intervention mechanism integrating environment, physiology, and behavior is constructed to provide users with efficient, accurate, and personalized smoking cessation support in real time, thereby enhancing the effectiveness of smoking cessation intervention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 It is a flow chart of the smoking cessation intervention method for smokers provided by the present invention.

[0019] Figure 2 This is a data flow diagram provided by the present invention.

[0020] Figure 3 It is a structural schematic diagram of the smoking cessation intervention device provided by the present invention.

[0021] Figure 4 This is a front view of the smart wearable device provided by the present invention.

[0022] Figure 5 This is a rear view of the smart wearable device provided by the present invention.

[0023] Figure 6 This is another structural diagram of the smart wearable device provided by the present invention. DETAILED DESCRIPTION

[0024] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0025] Embodiments of the present invention provide a smoking cessation intervention method for smokers, which is applied to smart wearable devices, particularly smart wearable devices in a smoking cessation assistance system. The smart wearable devices are smart terminals such as smart watches, smart bracelets, or smart glasses. The smoking cessation assistance system also includes terminal applications and servers. Through the smart wearable devices, the user's physiological and psychological state can be monitored in real time and comprehensively, determining the user's degree of smoking dependence. Dynamic personalized intervention can then be implemented, providing users with precise and effective smoking cessation support, thereby enhancing the effectiveness of the intervention.

[0026] Specifically, Figure 1 Schematic diagram of the process of the smoking cessation intervention method provided by the present invention, such as Figure 1 As shown, the method includes the following steps: Step 100: Collect multimodal data of the user; the multimodal data includes physiological data, behavioral data, and environmental data; Step 200: Input the multimodal data into an intelligent monitoring model to obtain an intervention strategy output by the intelligent monitoring model; the intelligent monitoring model is constructed based on a neural network model and trained with sample data, wherein the sample data is constructed using historical data of the multimodal data as samples and intervention strategies as sample labels, wherein the sample labels are marked with intervention levels; Step 300: Perform smoking cessation intervention on the user based on the intervention strategy.

[0027] First, the user's multimodal data is collected, and the multimodal data includes at least the user's physiological data, behavioral data and environmental data, among which the physiological data includes blood pressure, blood sugar, blood oxygen, heart rate, body temperature, psychological state data and sleep data, etc. The sleep data can further include sleep depth and sleep duration, and the psychological state data includes stress index; the behavioral data characterizes the user's movement status, especially the movement status of the part where the user wears the smart wearable device; the environmental data includes ambient temperature, ambient humidity and air quality, etc. The air quality can further include the composition and concentration of gaseous compounds, including but not limited to carbon monoxide, which characterizes the external environment in which the user is located.

[0028] Optionally, the physiological data in the multimodal data reflects the user's internal physiological state and emotions, the user's behavioral data reflects the changes in the user's external body behavior, and the environmental data reflects the external environment of the space in which the user is located. Physiological data can reflect the user's physiological state before and after smoking and in daily life, analyze the correlation between the emergence of the user's smoking urge, that is, the onset of smoking addiction, and specific biological characteristics, and provide a basis for predicting the occurrence of smoking urges; the user's behavioral data can capture the user's hand movements, changes in the user's body posture, etc., and by matching them with specific smoking action patterns, such as the frequency of hand raising, arm movement trajectory, etc., it can monitor and identify the user's upcoming or ongoing smoking behavior in real time; environmental data can be used to monitor the carbon monoxide concentration in the user's environment, etc., which helps to understand the impact of the user's environment on the occurrence of smoking urges. For example, in an environment with a high carbon monoxide concentration, users are more likely to have a smoking urge, and it can also remind users to avoid environments with serious secondhand smoke pollution.

[0029] In one embodiment, a smart wearable device is equipped with multimodal sensors for collecting multimodal data from a user. The multimodal sensors include at least biosensors, motion sensors, and environmental sensors. The biosensors are used to collect physiological data from the user. The biosensors include a blood pressure sensor for collecting the user's blood pressure. The biosensors further include a heart rate sensor and a galvanic skin response sensor for collecting physiological data such as the user's heart rate and skin conductivity. The biosensors also include other sensors for collecting blood glucose, blood oxygen, sleep data, and psychological state data, which are not listed here. The environmental sensors include a carbon monoxide sensor and a temperature sensor. The temperature sensor is used to collect the air temperature of the user's environment. The carbon monoxide sensor is used to detect the carbon monoxide concentration in the air of the user's environment. Based on the carbon monoxide concentration detected by the carbon monoxide sensor, the nicotine concentration in the air can be inferred to obtain the ambient nicotine concentration. Optionally, the environmental data in the multimodal data also includes ambient audio data. The environmental sensors also include an audio sensor for collecting ambient audio data. By matching the audio features of the collected ambient audio data with the ambient audio features of the user when smoking, the device can detect in real time whether the user is smoking.

[0030] Smart wearable devices are equipped with an intelligent monitoring model. This model is built based on an artificial intelligence (AI) model, such as a deep neural network or machine learning model, and is trained using sample data. The sample data is constructed using historical multimodal data as samples and the user's intervention strategy as sample labels. The intervention strategy, as a sample label, is labeled with an intervention level. The intelligent monitoring model can monitor the user's smoking probability in real time. Specifically, the collected multimodal data of the user is input into the intelligent monitoring model, and the intelligent monitoring model outputs the user's intervention strategy.

[0031] In one embodiment, the intelligent monitoring model is constructed based on a neural network model, which includes an input layer, a first hidden layer, a second hidden layer, and an output layer. The input layer includes a plurality of neurons (D, where D is a positive integer greater than 1); the first hidden layer includes H1 neurons and a first activation function; the second hidden layer includes H2 neurons and a second activation function; and the output layer includes one neuron and a third activation function. Exemplarily, H1 is 128, H2 is 64, the first activation function is the same as the second activation function, both being ReLU functions; and the third activation function is a sigmoid function. When multimodal data is input into the intelligent monitoring model, it is specifically converted into feature vectors, which serve as input to the input layer of the intelligent monitoring model. The feature vectors corresponding to the multimodal data may include one or more, which may be determined based on the dimensionality of each data item in the multimodal data, and are not specifically limited to this.

[0032] Furthermore, based on the intervention strategy output by the intelligent monitoring model, smoking cessation intervention is carried out on the user. Optionally, the intervention strategy is generated based on the probability of the user's smoking craving occurring within a preset time period in the future. The intervention strategy includes intervention methods and intervention levels. The intervention methods include pushing smoking cessation reminder content, reminding the user of the current smoking cessation effect and progress, pushing alternative activities for attention diversion, etc. The intervention level is the intervention level. The intervention level can be determined according to the predicted probability of the user's smoking craving occurring. Based on the intervention level in the intervention strategy, graded intervention in the user's smoking cessation can be achieved according to the different levels of the user's smoking craving.

[0033] Optionally, the intelligent monitoring model detects the user's smoking intention or the probability of smoking behavior based on multimodal data and generates an intervention strategy based on the user's smoking intention or the probability of smoking behavior. This intervention strategy includes the intervention method and intervention level. Intervention methods include sending reminders to users through vibration, sound, flashing lights, etc. The reminders include smoking cessation goals, warnings about the health risks of current smoking behavior, and recommended coping strategies, helping users to promptly recognize smoking cravings and take appropriate quitting measures. Considering the important role of psychological factors in the smoking cessation process, the reminders may also include stress management methods such as exercise, entertainment and relaxation (music, movies), deep breathing training, meditation guidance, and drinking ice water to help users relieve the negative emotions and stress caused by withdrawal.

[0034] For example, if the probability of a user smoking within a preset time period is less than a preset low-risk threshold, content of interest can be pushed to the user, or a push instruction can be sent to the application to instruct the application to push content of interest to the user, thereby attracting the user's attention through the content of interest, allowing the user to maintain the current low-probability smoking state. If the probability of a user smoking within a preset time period is greater than or equal to a preset high-risk threshold, a smoking alternative activity can be pushed to the user, or a push instruction can be sent to the application to instruct the application to push a smoking alternative activity to the user, thereby diverting the user's attention through the smoking alternative activity, or reminding the user to perform attention diversion activities instead of smoking behavior when the urge to smoke arises. When the user is detected in an environment containing nicotine, the user is reminded to leave the current area in a timely manner.

[0035] In one embodiment, the intelligent monitoring model can be deployed in a smart wearable device using edge computing. The smart wearable device inputs the collected multimodal data into the intelligent monitoring model to obtain the intervention strategy output by the intelligent monitoring model.

[0036] In another embodiment, the intelligent monitoring model can also be deployed on the application side of the mobile terminal. The smart wearable device sends the collected multimodal data to the application side, and the application side inputs the received multimodal data into the intelligent monitoring model to obtain the intervention strategy output by the intelligent monitoring model. Alternatively, the smart wearable device extracts features from the collected multimodal data to obtain multimodal features, and sends the multimodal features to the application side. The application side inputs the received multimodal features into the intelligent monitoring model to obtain the intervention strategy output by the intelligent monitoring model. The application side sends the intervention strategy to the smart wearable device, and the smart wearable device receives the intervention strategy sent by the application side to perform smoking cessation intervention on the user.

[0037] In some embodiments, the intelligent monitoring model can also be deployed on the server side. The intelligent wearable device sends the collected multimodal data to the application side. The application side sends the received multimodal data to the server. The server inputs the received multimodal data into the intelligent monitoring model to obtain the intervention strategy output by the intelligent monitoring model. Alternatively, the intelligent wearable device extracts features from the collected multimodal data to obtain multimodal features, sends the multimodal features to the application side, and the application side sends the received multimodal features to the server. The server inputs the received multimodal features into the intelligent monitoring model to obtain the intervention strategy output by the intelligent monitoring model. The server side sends the intervention strategy output by the intelligent monitoring model to the intelligent wearable device, or sends it to the intelligent wearable device through the application side. The intelligent wearable device performs smoking cessation intervention on the user based on the received intervention strategy.

[0038] The intelligent monitoring model comprehensively analyzes the user's multimodal data. Based on the user's internal physiological state and external behavioral changes, combined with the user's environment, it predicts the probability of the user experiencing smoking cravings within a preset time period in the future. It then generates intervention strategies based on the user's current smoking cessation stage. The smoking cessation stages primarily include the pre-quit phase (preparation before quitting), the action phase (implementation of smoking cessation behaviors), and the maintenance phase (preventing relapse after successful quitting).

[0039] In this embodiment, through the collection of multimodal data by smart wearable devices and the recognition of multimodal data by intelligent monitoring models, real-time monitoring of the user's physiological state, behavioral changes, and environment is achieved. Based on the intervention strategy generated by real-time monitoring, dynamic personalized intervention is carried out for the user to quit smoking. By breaking through the limitations of traditional smoking cessation interventions through smart wearable devices, the full chain from data collection and risk prediction to precise intervention is realized, and a dynamic intervention mechanism integrating environment, physiology, and behavior is constructed to provide users with efficient, accurate, and personalized smoking cessation support in real time, thereby enhancing the effectiveness of smoking cessation interventions.

[0040] The intelligent monitoring model comprehensively analyzes multimodal data to predict the probability of a user experiencing a smoking craving in the future. Based on the user's current smoking cessation stage, it generates an intervention strategy based on the probability of the user experiencing a smoking craving. Specifically, the intelligent monitoring model processes multimodal data to derive an intervention strategy, including: determining, based on the physiological data in the multimodal data, a change trend of a physiological characteristic of the user associated with smoking craving; Identifying a posture change of the user based on the behavioral data in the multimodal data; the posture change includes an arm movement trajectory and a hand-raising frequency of the user; Performing scene classification on the environmental data in the multimodal data to determine the scene category of the user's environment; the scene category is used to characterize the degree of influence of the environment on the user's urge to smoke; Performing a comprehensive analysis of the changing trend of the physiological characteristics, the changing status of the posture, and the scene category to determine the probability and degree of the user's urge to smoke within a future preset time period; An intervention level is determined according to the probability and the degree of smoking urge, and an intervention strategy is generated based on the intervention level; the intervention strategy includes intervention content under the intervention level.

[0041] The intelligent monitoring model processes multimodal data, including multimodal feature extraction of multimodal data, comprehensive analysis based on the extracted multimodal features, determining the probability and degree of smoking urge in users within a preset time period in the future, and then generating intervention strategies.

[0042] Specifically, for the physiological data in the multimodal data, the changing trend of the user's physiological characteristics related to the urge to smoke is determined based on the physiological data. The changing trend of the physiological characteristics represents the changes in the user's physiological state related to the urge to smoke within a preset time period in the future. The probability of the user's urge to smoke is predicted based on the changing trend of the physiological characteristics.

[0043] For the behavioral data in the multimodal data, the user's posture changes are analyzed by analyzing the user's behavioral data. The posture changes include the user's arm movement trajectory and hand-raising frequency. By matching them with the user's specific smoking action pattern, it is determined whether the user is about to or is currently smoking.

[0044] For the environmental data in the multimodal data, the environmental data is classified into scenes, and the scene category of the user's environment is determined based on the ambient nicotine concentration in the environment, etc. The scene category is used to characterize the degree of influence of the user's environment on the user's urge to smoke.

[0045] A comprehensive analysis is conducted on the changing trends of biological characteristics related to smoking cravings, changes in the user's posture, and the scene categories of the user's environment to determine the probability and degree of smoking cravings that the user will experience within a preset time period in the future, and an intervention strategy is generated based on the probability and degree of smoking cravings.

[0046] Furthermore, for intervention strategies, an intervention level is first determined based on the probability of smoking craving and the degree of smoking craving. Based on this intervention level, an intervention strategy is generated. The intervention strategy includes an intervention method and an intervention level (also referred to as an intervention degree). The intervention strategy further includes intervention content at that intervention level. Specifically, an intervention strategy represents a specific intervention method and outputs intervention content at the corresponding intervention level. Different intervention strategies are generated based on different probabilities of smoking craving and / or degrees of smoking craving. Different intervention strategies correspond to different intervention methods, intervention levels, and intervention content.

[0047] Optionally, intervention content includes diversified intervention content such as positive guidance, exercise reminders, and hazard warnings.

[0048] In one embodiment, the intelligent monitoring model processes data from different modalities in multimodal data in parallel, or processes data from different modalities in multimodal data in serial. When the intelligent monitoring model processes data from different modalities in multimodal data in parallel, the intelligent monitoring model includes multiple network branches, each of which is obtained by dividing the input layer, first hidden layer, and second hidden layer of the neural network model. Each network branch corresponds to data from one modality. That is, the intelligent monitoring model includes at least a first network branch corresponding to physiological data, a second network branch corresponding to behavioral data, and a third network branch corresponding to environmental data. Partitioning processing of data from different modalities is achieved through multiple independent network branches. The intelligent monitoring model may also include a feature fusion layer that fuses the multimodal features output by different network branches and, based on the fused multimodal features, predicts the probability of a user experiencing a smoking urge and the degree of smoking urge within a preset future time period.

[0049] Furthermore, the first network branch outputs changes in the user's biological characteristics related to smoking cravings; the second network branch outputs changes in the user's target body position related to smoking behavior, including arm movement trajectory and hand-raising frequency; and the third network branch outputs the scene category of the user's environment to identify the extent to which the environment affects the user's smoking cravings. Optionally, a prediction is performed based on the output features of the first, second, and third network branches to obtain the probability and degree of smoking cravings of the user corresponding to each network branch within a preset future time period, including a first probability and first degree of smoking craving corresponding to the first network branch, a second probability and second degree of smoking craving corresponding to the second network branch, and a third probability and third degree of smoking craving corresponding to the third network branch. Finally, a weighted sum or weighted average of the first, second, and third probabilities is performed to obtain the final probability of the user experiencing smoking cravings within the preset future time period. The first, second, and third degrees of smoking cravings are then weighted summed or weighted averaged to obtain the user's degree of smoking cravings within the preset future time period. Alternatively, the output features of each network branch are fused to obtain fused multimodal features, and predictions are made based on the fused multimodal features to obtain the probability and degree of the user's desire to smoke within a preset time period in the future.

[0050] The intelligent monitoring model uses the nicotine concentration in the user's environment and the nicotine concentration in the user's body, combined with the user's physiological data such as heart rate, blood pressure and stress index, and multi-scenario classification of the user's environment to predict the probability of the user's desire to smoke and the degree of the desire to smoke, generate intervention strategies in real time, and provide dynamic and graded personalized intervention for users to quit smoking.

[0051] Furthermore, smart wearable devices have broken through the limitations of traditional smoking cessation interventions, realizing full-link intelligence from data collection, risk prediction and precise intervention, and building a dynamic intervention mechanism of "environment-physiology-behavior" to provide smokers with efficient, precise and personalized smoking cessation support.

[0052] In one embodiment, the intelligent monitoring model is deployed in the smart wearable device, and the model parameters are optimized in the cloud through the server. While ensuring the model performance of the intelligent monitoring model, real-time intervention and support for users to quit smoking are achieved. The use of distributed edge computing can, on the one hand, ensure the security of user privacy data, and on the other hand, reduce the intervention delay compared to deploying the intelligent monitoring model on the server side, which is conducive to improving the real-time nature of smoking cessation intervention. Based on this, after step 100, it can also include: Step 110: Send the multimodal data to a terminal application. The terminal application iteratively optimizes the intelligent monitoring model based on the multimodal data to obtain first model parameters, and sends the first model parameters to a server. The server periodically iteratively optimizes the intelligent engine corresponding to the intelligent monitoring model based on the first model parameters sent by terminal applications of different users to obtain second model parameters. Step 120: Receive the second model parameters sent by the server, and optimize and update the intelligent monitoring model using the second model parameters.

[0053] The collected multimodal data is sent to the terminal application, which stores the multimodal data and iteratively optimizes the intelligent monitoring model based on the multimodal data to obtain first model parameters. The first model parameters are then sent to the server. The server periodically iteratively optimizes the intelligent engine corresponding to the intelligent monitoring model based on the first model parameters received from different users' terminal applications to obtain second model parameters. The second model parameters are then sent to the smart wearable device.

[0054] The smart wearable device receives the second model parameters sent by the server and optimizes and updates the model parameters of the local smart monitoring model using the second model parameters. Optionally, the server sends the second model parameters directly to the smart wearable device, or the server sends the second model parameters to the smart wearable device through a terminal application.

[0055] In one embodiment, referring to Figure 2 The data flow diagram during the optimization and update of the intelligent monitoring model shown in the figure shows that the intelligent wearable device sends the collected multimodal data to the terminal application. The terminal application iteratively optimizes the local model based on the multimodal data, obtains the first model parameters and sends them to the server. The cloud-based intelligent engine of the server contains global model parameters, which are obtained by federal training of the local intelligent monitoring model of the intelligent wearable device with the terminal applications of different users as participants. Based on the first model parameters received from the terminal applications of different users, the server periodically iteratively trains the global model parameters of the intelligent engine to obtain the second model parameters, and sends the second model parameters to the intelligent wearable device, or sends the second model parameters to the intelligent wearable device through the terminal application, thereby optimizing and updating the model parameters of the local intelligent monitoring model of each intelligent wearable device, and realizing the privacy protection of the user's multimodal data while optimizing the intelligent monitoring model.

[0056] A multimodal sensor array is deployed on the smart wearable device, which is used to collect multimodal data. The multimodal sensor array includes at least one carbon monoxide sensor, at least one temperature sensor, at least one biosensor, and at least one motion sensor. The temperature sensor is used to collect at least one of the user's body temperature and the ambient temperature.

[0057] Furthermore, the carbon monoxide sensor and the temperature sensor are used to collect environmental data. The collected environmental data includes at least the ambient carbon monoxide concentration and the ambient temperature collected by the temperature sensor, and is used to monitor the air quality, such as the nicotine concentration and ambient temperature, in the user's surrounding environment in real time. The ambient nicotine concentration is calculated based on the carbon monoxide concentration in the air detected by the carbon monoxide sensor. Optionally, the multimodal sensor array may also include a humidity sensor for collecting ambient humidity, or a temperature and humidity sensor may be used instead of the temperature sensor to simultaneously collect ambient temperature and ambient humidity. Optionally, the multimodal sensor array may also include an air quality sensor, which may be a gas sensor or an electrochemical sensor, for collecting the type and content of gaseous compounds in the air. Based on this, the collected environmental data may also include the type and content of gaseous compounds, in particular the content of harmful gases. The gaseous compounds include but are not limited to carbon oxides and nitrogen oxides.

[0058] The biosensor is used to collect the user's physiological data, which includes at least one of heart rate, blood pressure, blood sugar, blood oxygen, psychological state data, sleep data and skin conductivity. The psychological state data includes a stress index to represent the user's emotions, and the sleep data includes sleep depth and sleep duration, etc.

[0059] Motion sensors are used to collect user behavior data. Motion sensors include accelerometers and gyroscopes, etc., which are used to capture behavioral data such as changes in the user's body posture, especially changes in the posture of the target parts of the smart wearable device, including but not limited to the user's motion data, hand movements, hand raising frequency and arm movement trajectory.

[0060] In one embodiment, the smart wearable device is further provided with at least one environmental monitoring port for extracting air samples from the user's environment and collecting exhaled gas samples from the user. The user's physiological data also includes nicotine concentration in the body. Based on this, step 100 includes: Step 101: based on a pre-generated timed sampling task, extract an air sample through the environmental monitoring hole and detect a first concentration of carbon monoxide in the air sample; Step 102: Output sampling prompt information; the sampling prompt information is used to prompt the user to blow air towards the environmental monitoring hole for a preset time; Step 103: obtaining an exhaled gas sample of the user upon detecting that the user has completed blowing, and detecting a second concentration of carbon monoxide in the exhaled gas sample; Step 104: Calculate the nicotine concentration in the user's body based on the difference between the first concentration and the second concentration.

[0061] Based on pre-produced scheduled sampling tasks, the smart wearable device periodically outputs a sampling prompt. This prompt prompts the user to blow into the environmental monitoring hole for a preset duration. This prompt may include, but is not limited to, vibration and text prompts, such as "Please blow into the monitoring hole." Before outputting the sampling prompt, an air sample is drawn through the environmental monitoring hole, and a carbon monoxide sensor detects a first concentration of carbon monoxide in the air. Upon detecting that the user has completed blowing, a sample of the user's exhaled air is obtained, and a second concentration of carbon monoxide in the exhaled air sample is detected.

[0062] Furthermore, the nicotine concentration in the user's body is determined based on the difference between the first and second carbon monoxide concentrations detected by the carbon monoxide sensor, thereby obtaining the user's body nicotine concentration. Optionally, at least two environmental monitoring holes are provided, each corresponding to a corresponding carbon monoxide sensor. The environmental monitoring holes simultaneously sample the air and the user's exhaled gas and detect the carbon monoxide concentration, thereby achieving simultaneous detection of the carbon monoxide concentrations in the exhaled gas and air, thereby ensuring the accuracy of the detection results.

[0063] In one embodiment, based on a pre-generated scheduled sampling task, the user is reminded to measure the nicotine concentration in the body at a fixed time point every day to maintain data stability. For example, a sampling reminder message is output one hour after waking up every morning to avoid the morning CO peak.

[0064] Based on the carbon monoxide concentration in the air sample detected by the carbon monoxide sensor, the nicotine concentration in the air, that is, the ambient nicotine concentration, can be calculated; based on the carbon monoxide concentration in the exhaled gas sample detected by the carbon monoxide sensor, the nicotine concentration in the exhaled gas can be calculated, but the exhaled gas sample contains air. Therefore, the nicotine concentration in the user's body is calculated based on the difference in carbon monoxide concentration between the exhaled gas and the air to ensure data accuracy.

[0065] Alternatively, the ambient nicotine concentration can be estimated as follows: Ambient nicotine concentration (ppm) = [CO]_{ppm} × K × MW_{nicotine} / MW_{CO} × CF; Where [CO]_{ppm} represents the carbon monoxide (CO) concentration in the air detected by the carbon monoxide sensor (ppm represents concentration), K represents the tobacco release coefficient (default 0.08, range 0.06-0.12), MW_{nicotine} represents the molecular weight of nicotine (generally 162.23 g / mol), MW_{CO} represents the molecular weight of CO (generally 28 g / mol), and CF is the environmental calibration factor. For example, CF for ventilated space is 0.3, and CF for confined space is 1.2.

[0066] The nicotine concentration in the user's body can be calculated by combining the body's metabolism of nicotine with the concentration relationship between carbon monoxide and nicotine. Specifically, when the body metabolizes nicotine, the proportion of CO bound to hemoglobin is strongly correlated with the nicotine intake, which can be expressed as: {Exhaled CO (ppm)}≈0.92×{Blood carboxyhemoglobin (COHb\%)}; The relationship between COHb\% and nicotine dose can be expressed as: COHb\%=0.16×nicotine intake (mg); Therefore, the nicotine concentration in the user's body can be calculated as follows: Nicotine concentration in the body (ppm) = (exhaled CO2 - ambient CO2) ÷ (0.92 × 0.16) × α; Exhaled CO represents the average CO concentration at the end of a user's breath, ambient CO represents the simultaneously measured CO concentration in the air, and α represents the individual metabolic factor, with a default value of 1.0 and a range of 1.2 to 1.5 for smokers. The ambient CO concentration is dynamically deducted from the exhaled CO concentration to ensure accurate detection of the user's CO concentration.

[0067] In one embodiment, during the user's breath sampling process for a preset time, the smart wearable device performs a sampling countdown and real-time airflow intensity feedback, the preset time being, for example, 5 seconds or 10 seconds. After the user completes the breath-blowing, the sampling result is fed back to the user through a sampling completion prompt, which indicates that the sampling is successful or unsuccessful. For example, if the sampling is successful, the sampling completion prompt can remind the user of the successful sampling by flashing a green light + a short vibration, and can also output and display the detected nicotine concentration in the user's body; if the sampling is unsuccessful, the user can be prompted to blow again by flashing a red light + outputting a re-sampling prompt message, and the output re-sampling prompt message can be, for example, "Insufficient airflow, please blow again".

[0068] The extracted air sample is also used as a detection sample for the temperature sensor in the multimodal sensor array, for the temperature sensor to detect the ambient temperature. Optionally, the temperature sensor can also be exposed to the air for real-time detection of the ambient temperature, which is not specifically limited.

[0069] Furthermore, the smart wearable device is equipped with a microphone hole and a display screen. The microphone hole is used to collect ambient sounds for smoke detection (such as the sound of a lighter or coughing), thereby determining whether the user is smoking or whether there are smokers around the user. The display screen is used to display some or all of the collected multimodal data.

[0070] Optionally, the multimodal sensor array may also include an image sensor, which may be a camera. The collected multimodal data may also include an environmental image, which may be collected with the user's authorization and can be used to further assist in determining the scene category of the user's environment. For example, the ambient sound collected through the microphone hole can detect the sound of a lighter igniting, and the image features of a burning cigarette can be identified from the ambient image, thereby determining that the user is smoking and improving the accuracy of smoking behavior recognition. Optionally, the image sensor is set at a target position on the smart wearable device. The target position ensures that the user's hand movements can be captured when the user is smoking when the smart wearable device is worn normally.

[0071] For intervention strategies generated by the intelligent monitoring model, it is necessary to monitor their effectiveness on users. This effectiveness is determined by monitoring whether users subsequently smoke or whether they stop smoking in a timely manner. Furthermore, to increase users' motivation to quit smoking, social interaction features and smoking history logging are provided.

[0072] After step 300, the following steps may also be included: Step 401: monitoring the intervention effect of the intervention strategy on the user; Step 402: Generate a smoking cessation report based on the intervention effect and the record log, and send the smoking cessation report to the terminal application for the user to review. The record log is generated based on the timed reminder task and is based on the user's smoking record operation and / or the detected smoking behavior of the user. The timed reminder task is used to regularly remind the user to record smoking and learn smoking cessation techniques. The smoking cessation report includes smoking behavior statistics, physiological change trends, smoking addiction assessment results, nicotine concentration change curve in the body, and smoking cessation achievements. Step 403: If it is determined that the user meets the reward conditions based on the smoking cessation achievement, a virtual object is issued to the user's account; the virtual object can be used to redeem products or services; Step 404: Push the smoking cessation achievement to the terminal application of the user's interactive user; the interactive user is a user who has a social relationship with the user.

[0073] Monitor the effectiveness of intervention strategies on users, generate a smoking cessation report based on the intervention results and the recorded log, and send the report to the terminal application for the user to review. The recorded log is generated based on the user's smoking record operation and / or detected smoking behavior based on the scheduled reminder task. The scheduled reminder task is used to regularly remind users to record their smoking and learn smoking cessation techniques. The generated smoking cessation report includes smoking behavior statistics, physiological change trends, smoking addiction assessment results, nicotine concentration change curve in the body, and smoking cessation results.

[0074] In the terminal application, user information management can be achieved, including the display of smoking cessation results, the setting of personalized smoking cessation plans, and social interaction. On the one hand, the smart wearable device provides the user with a log recording interface for operation based on the scheduled reminder task. The user can also actively trigger the log recording by pressing buttons, etc., and manually record the number of cigarettes smoked, the feedback on the smoking cessation intervention strategy, and the feedback on the intervention effect in the log recording interface provided by the smart wearable device. On the other hand, the smart wearable device monitors the user's smoking intention or smoking behavior in real time through the collected multimodal data, generates intervention strategies for reminders, and ensures that the user can receive smoking cessation intervention and care information in a timely manner.

[0075] Specifically, based on a user's smoking cessation achievements, if the user is determined to meet the reward issuance conditions, a virtual object is sent to the user's account. This virtual object can be redeemed for products or services. The smoking cessation achievements are pushed to the user's interactive users' terminal applications, where interactive users are users with whom the user has a social relationship. The reward issuance condition is that the user's smoking cessation achievements are positive, for example, during the implementation phase of smoking cessation, the user's smoking frequency decreases significantly, or the number of times they experience smoking cravings decreases within a monitoring period. By establishing a social interaction mechanism, users can invite other users to create a smoking cessation group. Group members can view the user's smoking cessation progress and achievements, and provide encouragement and support. Alternatively, group members can view each other's smoking cessation achievements to encourage each other. Furthermore, by setting up an incentive mechanism, users are rewarded with corresponding virtual objects based on their smoking cessation achievements, such as completed smoking cessation tasks and reduced smoking consumption. These virtual objects can be points, medals, or coupons, which can be redeemed for smoking cessation or health-related products or services, motivating users to persist in quitting smoking.

[0076] In some embodiments, smoking cessation reports can also be uploaded to the server through the terminal application for secure storage and in-depth analysis. The server summarizes and analyzes the smoking cessation data of different users, and explores common problems and patterns in the smoking cessation process, thereby further optimizing the intelligent engine and improving the generation of smoking cessation intervention strategies. At the same time, cloud storage can ensure the security and traceability of user data. Users can obtain complete smoking cessation data at any time when changing devices or need to review their smoking cessation process.

[0077] It should be noted that during the communication and data transmission process, smart wearable devices, terminal applications and servers encrypt and control the transmitted data, and desensitize the user's sensitive information. Users have full control over their own data and can choose to delete or modify any data, thereby ensuring the privacy and security of user data.

[0078] In this embodiment, a smart wearable device is used, allowing users to wear it anytime, anywhere, enabling real-time monitoring of smoking behavior and physiological status and intervention for smoking cessation. Its portability and real-time nature reduce the need for manual recording by users, reducing costs and burdens, and improving the timeliness and accuracy of data. Furthermore, through real-time reminders, emotional regulation, social support, and incentive mechanisms, the functionality of the smart wearable device is enriched. Flexible and diverse intervention methods provide users with comprehensive care and support, making the smoking cessation process easier and more manageable, enhancing user compliance and persistence with the cessation plan, and enhancing the user experience.

[0079] Furthermore, multimodal data fusion reduces the misjudgment rate of smoking intentions or behaviors. Through more accurate and comprehensive smoking behavior monitoring and personalized smoking cessation plans, customized intervention measures are provided for each user's tobacco dependence characteristics and personal circumstances, effectively helping users overcome physical and psychological dependence and improving the success rate of smoking cessation. Combined with the continuous optimization of intelligent monitoring algorithms based on data-driven, real-time monitoring can be continuously optimized and improved based on the collected and analyzed user smoking cessation data, thereby providing more accurate and effective smoking cessation intervention services to meet the diverse needs of different users.

[0080] Smart wearable devices have broken through the limitations of traditional smoking cessation interventions, achieving full-chain intelligence from data collection and risk prediction to precise intervention. They have built a three-in-one intervention mechanism: environmental, physiological, and behavioral. Based on the predicted probability and degree of a user's craving for smoking, intervention strategies are generated in real time, providing dynamic, graded, and personalized intervention for users to quit smoking. Furthermore, through diverse intervention content such as positive guidance, exercise reminders, and hazard warnings, they provide smokers with efficient, precise, and personalized smoking cessation support, possessing significant application value in the field of intelligent healthcare.

[0081] The smoker cessation intervention device provided by the present invention is described below. The smoker cessation intervention device described below and the smoker cessation intervention method described above can be referenced to each other.

[0082] Reference Figure 3 The smoker cessation intervention device provided by the embodiment of the present invention is applied to a smart wearable device, and the smoker cessation intervention device includes: The data acquisition module 10 is used to collect multimodal data of the user; the multimodal data includes physiological data, behavioral data and environmental data; The smoking monitoring module 20 is configured to input the multimodal data into an intelligent monitoring model to obtain an intervention strategy output by the intelligent monitoring model; the intelligent monitoring model is constructed based on a neural network model and trained with sample data, wherein the sample data is constructed using historical data of the multimodal data as samples and intervention strategies as sample labels, wherein the sample labels are marked with intervention levels; The smoking cessation intervention module 30 is configured to perform smoking cessation intervention on the user based on the intervention strategy.

[0083] In one embodiment, the intelligent monitoring model includes a multimodal recognition module for: determining, based on the physiological data in the multimodal data, a change trend of a physiological characteristic of the user associated with smoking craving; Identifying a posture change of the user based on the behavioral data in the multimodal data; the posture change includes an arm movement trajectory and a hand-raising frequency of the user; Performing scene classification on the environmental data in the multimodal data to determine the scene category of the user's environment; the scene category is used to characterize the degree of influence of the environment on the user's urge to smoke; Performing a comprehensive analysis of the changing trend of the physiological characteristics, the changing status of the posture, and the scene category to determine the probability and degree of the user's urge to smoke within a future preset time period; An intervention level is determined according to the probability and the degree of smoking urge, and an intervention strategy is generated based on the intervention level; the intervention strategy includes intervention content under the intervention level.

[0084] In one embodiment, the smoker cessation intervention device further includes a model optimization module for: Sending the multimodal data to a terminal application, the terminal application iteratively optimizing the intelligent monitoring model based on the multimodal data to obtain first model parameters, and sending the first model parameters to a server; The server periodically iteratively optimizes the intelligent engine corresponding to the intelligent monitoring model based on the first model parameters sent by terminal applications of different users to obtain second model parameters; Receive the second model parameters sent by the server, and optimize and update the intelligent monitoring model using the second model parameters.

[0085] In one embodiment, the data acquisition module 10 includes a multimodal sensor array, and the multimodal sensor array is used to acquire the multimodal data; wherein: The multimodal sensor array includes at least one carbon monoxide sensor, at least one temperature sensor, at least one biosensor, and at least one motion sensor; The biosensor is used to collect the physiological data, wherein the physiological data includes at least one of heart rate, blood pressure, blood sugar, blood oxygen, psychological state data, sleep data and skin conductivity; The motion sensor is used to collect the behavior data, and the behavior data includes at least one of the user's motion data, hand movements, hand raising frequency, and arm movement trajectory; The carbon monoxide sensor and the temperature sensor are used to collect the environmental data, which at least includes the ambient temperature and the ambient carbon monoxide concentration; and the ambient nicotine concentration is calculated based on the ambient carbon monoxide concentration.

[0086] In one embodiment, the data acquisition module 10 further includes at least one environmental monitoring port for extracting air samples from the user's environment and collecting exhaled gas samples from the user; the physiological data also includes nicotine concentration in the body; the data acquisition module 10 is further used to; Based on a pre-generated timed sampling task, extract an air sample through the environmental monitoring hole, and detect a first concentration of carbon monoxide in the air sample; Output sampling prompt information; the sampling prompt information is used to prompt the user to blow air towards the environmental monitoring hole for a preset time; obtaining an exhaled gas sample of the user upon detecting that the user has completed blowing, and detecting a second concentration of carbon monoxide in the exhaled gas sample; estimating a nicotine concentration in the user's body based on a difference between the first concentration and the second concentration; The data acquisition module 10 also includes a microphone hole, which is used to collect environmental sounds for smoke detection; The smoker cessation intervention device further includes a display module, which includes a display screen, and the display screen is used to display part or all of the multimodal data.

[0087] In one embodiment, the smoker cessation intervention device further includes an interaction and management module for: monitoring the intervention effect of the intervention strategy on the user; A smoking cessation report is generated based on the intervention effect and the record log, and the report is sent to a terminal application for the user to review. The record log is generated based on the timed reminder task and is based on the user's smoking record operation and / or the detected smoking behavior of the user. The timed reminder task is used to regularly remind the user to record smoking and learn smoking cessation techniques. The smoking cessation report includes smoking behavior statistics, physiological change trends, smoking addiction assessment results, nicotine concentration change curve in the body, and smoking cessation achievements. If it is determined that the user meets the reward conditions based on the smoking cessation achievement, a virtual object is issued to the user's account; the virtual object is used to redeem products or services; The smoking cessation achievement is pushed to the terminal application of the user's interactive user; the interactive user is a user who has a social relationship with the user.

[0088] In this embodiment, the data acquisition module collects multimodal data through a multimodal sensor array, and the smoking monitoring module identifies and analyzes the multimodal data collected by the data acquisition module based on an intelligent monitoring model, determines the probability and degree of the user's urge to smoke, and generates an intervention strategy based on the probability and degree of the user's urge to smoke, thereby achieving real-time and comprehensive monitoring of the user's physiological state, behavior, and environment, as well as dynamic personalized intervention based on the intervention strategy, realizing full-link intelligence from data acquisition, risk prediction to precise intervention, and constructing a dynamic intervention mechanism integrating environment, physiology, and behavior, providing users with efficient, accurate, and personalized smoking cessation support, and enhancing the intervention effect.

[0089] An embodiment of the present invention also provides a smart wearable device for smoking cessation intervention. The main body of the smart wearable device includes a back shell and a display screen. The back shell includes a concave surface and a convex surface. The display screen is embedded in the concave surface of the back shell. The convex surface of the back shell is provided with a multimodal sensor array. The multimodal sensor array is used to collect multimodal data.

[0090] The smart wearable device also includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the smoker cessation intervention method described in the above embodiments is implemented, which will not be described in detail here.

[0091] In one embodiment, the multimodal sensor array includes at least one carbon monoxide sensor, at least one temperature sensor, at least one biosensor, and at least one motion sensor. Optionally, the multimodal sensor array may also include an air quality sensor and an image sensor.

[0092] The back shell includes first and second opposing sides, as well as third and fourth opposing sides. The first and second sides are provided with environmental monitoring holes for extracting gas samples required for testing, and the environmental monitoring holes are covered with a hydrophobic film. A microphone hole and magnetic charging contacts are provided on the first or second side. The third and fourth sides are provided with wearable fixing components. Optionally, if the smart wearable device is a smartwatch, the fixing components are watch straps provided on the third and fourth sides.

[0093] The convex surface of the back shell is the side that is in close contact with the skin of the wearing part, and the first side surface, the second side surface, the third side surface and the fourth side surface are the sides between the convex surface and the concave surface of the back shell. Figure 4 The front view of the smart wearable device shown in the figure shows that the display screen is embedded in the concave surface of the back shell, and the power button and the emergency button are also provided on the fourth side surface of the back shell.

[0094] Further references Figure 5 The rear view of the smart wearable device shown in the figure shows a multimodal sensor array arranged on the convex surface of the back shell of the smart wearable device. Figure 5 The blood pressure sensor, carbon monoxide sensor and temperature sensor in the multimodal sensor array are given as examples. Figure 5 As shown, environmental monitoring holes for sampling are provided on both the first and second sides of the back shell. These holes are covered with a hydrophobic membrane to protect against saliva and water vapor during gas sampling. The hydrophobic membrane can be made of polytetrafluoroethylene (PTFE) (also known as perfluoroethylene). The hydrophobic membrane can cover the environmental monitoring holes, shielding them, or be positioned on the inner surface of the holes, without specific limitation. Optionally, the back shell of the smart wearable device is made of ceramic and also includes a metal frame.

[0095] Figure 6 Another physical structure diagram of a smart wearable device is shown as follows: Figure 6 As shown, the smart wearable device may include: a processor 610, a communications interface 620, a memory 630, and a communication bus 640, wherein the processor 610, the communications interface 620, and the memory 630 communicate with each other via the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the steps of the smoking cessation intervention method for smokers, for example, including: Collecting multimodal data of the user; the multimodal data includes physiological data, behavioral data and environmental data; Inputting the multimodal data into an intelligent monitoring model to obtain an intervention strategy output by the intelligent monitoring model; the intelligent monitoring model is constructed based on a neural network model and trained with sample data, the sample data being constructed using historical data of the multimodal data as samples and intervention strategies as sample labels, wherein the sample labels are marked with intervention levels; Performing smoking cessation intervention on the user based on the intervention strategy.

[0096] Furthermore, the logic instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0097] In another aspect, the present invention further provides a computer program product, comprising a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the steps of the above-mentioned intervention methods for smokers to quit smoking, for example, including: Collecting multimodal data of the user; the multimodal data includes physiological data, behavioral data and environmental data; Inputting the multimodal data into an intelligent monitoring model to obtain an intervention strategy output by the intelligent monitoring model; the intelligent monitoring model is constructed based on a neural network model and trained with sample data, the sample data being constructed using historical data of the multimodal data as samples and intervention strategies as sample labels, wherein the sample labels are marked with intervention levels; Performing smoking cessation intervention on the user based on the intervention strategy.

[0098] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program is implemented to perform the steps of the above-mentioned methods for intervening in smoking cessation, for example, including: Collecting multimodal data of the user; the multimodal data includes physiological data, behavioral data and environmental data; Inputting the multimodal data into an intelligent monitoring model to obtain an intervention strategy output by the intelligent monitoring model; the intelligent monitoring model is constructed based on a neural network model and trained with sample data, the sample data being constructed using historical data of the multimodal data as samples and intervention strategies as sample labels, wherein the sample labels are marked with intervention levels; Performing smoking cessation intervention on the user based on the intervention strategy.

[0099] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0100] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for smokers to quit smoking, characterized in that: Applied to smart wearable devices, the smoking cessation intervention method for smokers includes: Collecting multimodal data of the user; the multimodal data includes physiological data, behavioral data and environmental data; Inputting the multimodal data into an intelligent monitoring model to obtain an intervention strategy output by the intelligent monitoring model; the intelligent monitoring model is constructed based on a neural network model and trained with sample data, the sample data being constructed using historical data of the multimodal data as samples and intervention strategies as sample labels, wherein the sample labels are marked with intervention levels; performing smoking cessation intervention on the user based on the intervention strategy; The process of the intelligent monitoring model processing the multimodal data to obtain an intervention strategy includes: determining, based on the physiological data in the multimodal data, a change trend of a physiological characteristic of the user associated with smoking craving; Identifying a posture change of the user based on the behavioral data in the multimodal data; the posture change includes an arm movement trajectory and a hand-raising frequency of the user; Performing scene classification on the environmental data in the multimodal data to determine the scene category of the user's environment; the scene category is used to characterize the degree of influence of the environment on the user's urge to smoke; Performing a comprehensive analysis of the changing trend of the physiological characteristics, the changing status of the posture, and the scene category to determine the probability and degree of the user's urge to smoke within a future preset time period; An intervention level is determined according to the probability and the degree of smoking urge, and an intervention strategy is generated based on the intervention level; the intervention strategy includes intervention content under the intervention level.

2. The smoking cessation intervention method according to claim 1, characterized in that: After collecting the multimodal data of the user, the method further includes: Sending the multimodal data to a terminal application, the terminal application iteratively optimizing the intelligent monitoring model based on the multimodal data to obtain first model parameters, and sending the first model parameters to a server; The server periodically iteratively optimizes the intelligent engine corresponding to the intelligent monitoring model based on the first model parameters sent by terminal applications of different users to obtain second model parameters; Receive the second model parameters sent by the server, and optimize and update the intelligent monitoring model using the second model parameters.

3. The smoking cessation intervention method according to claim 1, characterized in that: The smart wearable device is provided with a multimodal sensor array, and the multimodal sensor array is used to collect the multimodal data; wherein: The multimodal sensor array includes at least one carbon monoxide sensor, at least one temperature sensor, at least one biosensor, and at least one motion sensor; The biosensor is used to collect the physiological data, wherein the physiological data includes at least one of heart rate, blood pressure, blood sugar, blood oxygen, psychological state data, sleep data and skin conductivity; The motion sensor is used to collect the behavior data, and the behavior data includes at least one of the user's motion data, hand movements, hand raising frequency, and arm movement trajectory; The carbon monoxide sensor and the temperature sensor are used to collect the environmental data, which at least includes the ambient temperature and the ambient carbon monoxide concentration; and the ambient nicotine concentration is calculated based on the ambient carbon monoxide concentration.

4. The smoking cessation intervention method according to claim 3, characterized in that: The smart wearable device is further provided with at least one environmental monitoring port for extracting air samples from the user's environment and collecting exhaled gas samples from the user; the physiological data also includes nicotine concentration in the body; and the multimodal data collected from the user includes: Based on a pre-generated timed sampling task, extract an air sample through the environmental monitoring hole, and detect a first concentration of carbon monoxide in the air sample; Output sampling prompt information; the sampling prompt information is used to prompt the user to blow air towards the environmental monitoring hole for a preset time; obtaining an exhaled gas sample of the user upon detecting that the user has completed blowing, and detecting a second concentration of carbon monoxide in the exhaled gas sample; estimating a nicotine concentration in the user's body based on a difference between the first concentration and the second concentration; The smart wearable device is also provided with a microphone hole, which is used to collect ambient sound for smoke detection; The smart wearable device is further provided with a display screen, which is used to display part or all of the multimodal data.

5. The smoking cessation intervention method according to claim 1, characterized in that: After performing the smoking cessation intervention on the user based on the intervention strategy, the method further includes: monitoring the intervention effect of the intervention strategy on the user; A smoking cessation report is generated based on the intervention effect and the record log, and the report is sent to a terminal application for the user to review. The record log is generated based on the timed reminder task and is based on the user's smoking record operation and / or the detected smoking behavior of the user. The timed reminder task is used to regularly remind the user to record smoking and learn smoking cessation techniques. The smoking cessation report includes smoking behavior statistics, physiological change trends, smoking addiction assessment results, nicotine concentration change curve in the body, and smoking cessation achievements. If it is determined that the user meets the reward conditions based on the smoking cessation achievement, a virtual object is issued to the user's account; the virtual object can be used to redeem products or services; The smoking cessation achievement is pushed to the terminal application of the user's interactive user; the interactive user is a user who has a social relationship with the user.

6. A smoking cessation intervention device for smokers, characterized in that: Applied to smart wearable devices, the smoker cessation intervention device includes: A data acquisition module, configured to collect multimodal data of the user, including physiological data, behavioral data, and environmental data; a smoking monitoring module configured to input the multimodal data into an intelligent monitoring model to obtain an intervention strategy output by the intelligent monitoring model; the intelligent monitoring model is constructed based on a neural network model and trained with sample data, the sample data being constructed using historical data of the multimodal data as samples and intervention strategies as sample labels, the sample labels being marked with intervention levels; a smoking cessation intervention module, configured to perform smoking cessation intervention on the user based on the intervention strategy; The intelligent monitoring model includes a multimodal recognition module for: determining, based on the physiological data in the multimodal data, a change trend of a physiological characteristic of the user associated with smoking craving; Identifying a posture change of the user based on the behavioral data in the multimodal data; the posture change includes an arm movement trajectory and a hand-raising frequency of the user; Performing scene classification on the environmental data in the multimodal data to determine the scene category of the user's environment; the scene category is used to characterize the degree of influence of the environment on the user's urge to smoke; Performing a comprehensive analysis of the changing trend of the physiological characteristics, the changing status of the posture, and the scene category to determine the probability and degree of the user's urge to smoke within a future preset time period; An intervention level is determined according to the probability and the degree of smoking urge, and an intervention strategy is generated based on the intervention level; the intervention strategy includes intervention content under the intervention level.

7. A smart wearable device for smoking cessation intervention, characterized in that: The main body of the smart wearable device includes a back shell and a display screen, the back shell includes a concave surface and a convex surface, and the display screen is embedded in the concave surface of the back shell; the convex surface of the back shell is provided with a multimodal sensor array; The smart wearable device also includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for smoker cessation intervention according to any one of claims 1 to 5 is implemented.

8. The smart wearable device for smoking cessation intervention according to claim 7, characterized in that: The multimodal sensor array includes at least one carbon monoxide sensor, at least one temperature sensor, at least one biosensor, and at least one motion sensor; The back shell also includes a first side surface and a second side surface arranged opposite to each other, and a third side surface and a fourth side surface arranged opposite to each other; the first side surface and the second side surface are provided with environmental monitoring holes for extracting gas samples required for detection, and the environmental monitoring holes are covered with a hydrophobic film; a microphone hole is provided on the first side surface or the second side surface, a magnetic charging contact is provided on the first side surface or the second side surface, and fixing parts for wearing are provided on the third side surface and the fourth side surface.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the smoking cessation intervention method for smokers according to any one of claims 1 to 5 is implemented.

Images