An intelligent mosquito-repelling method in a vehicle

Abstract

The application discloses an intelligent mosquito repelling method in a vehicle, and relates to the technical field of intelligent vehicle environment control, which comprises the following steps: synchronously collecting multi-modal data in the vehicle through a sensor, and pre-processing the multi-modal data in the vehicle to obtain pre-processed multi-modal data in the vehicle; selecting a chemical mosquito repelling mode or a physical mosquito repelling mode based on the pre-processed multi-modal data, and performing mosquito repelling control in the vehicle; calculating the mosquito density at an air outlet of an air conditioner, and starting a UV LED lamp to catalytically decompose mosquito repellent ester residues in the air when the mosquito density in a unit volume exceeds a predetermined density; obtaining historical driving data of a user through a vehicle-mounted T-BOX, and predicting the mosquito occurrence probability by using an LSTM neural network; and pushing a pre-mosquito repelling request to a user mobile terminal according to the prediction result, so as to complete the intelligent mosquito repelling in the vehicle based on multi-modal sensing. The application realizes efficient, safe and low-pollution mosquito repelling measures, and can quickly respond to ensure the health and comfort of passengers.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent vehicle environment control, and in particular to an intelligent mosquito-repelling method in a vehicle. BACKGROUND

[0002] In recent years, the trend of integration of intelligent vehicle environment technology and mosquito-repelling technology has become increasingly prominent. Traditional mosquito-repelling in a vehicle relies on single chemical spraying or physical electric mesh isolation, which is difficult to balance safety and comfort. With the rapid development of microelectronic sensing, vehicle communication and artificial intelligence algorithms, multi-modal sensors have continuously improved their performance in millimeter wave radar, gas sensing and physiological signal acquisition, providing reliable support for real-time sensing of the vehicle environment. At the same time, breakthroughs in deep learning and time series prediction models in the field of environment and behavior analysis have led to an increase in research on the close relationship between mosquito activity patterns and passenger physiological states, providing a new technical path for precise and dynamic mosquito-repelling control. Based on this, many scholars have proposed using neural networks to predict mosquito density and feeding behavior to guide the intelligent switching of mosquito-repelling strategies and explore the feasibility of remote monitoring and active intervention in the context of vehicle-to-everything (V2X).

[0003] However, the existing technology still has many shortcomings: first, most vehicle mosquito-repelling solutions only activate chemical or physical intervention when mosquito infestation is obvious, lacking comprehensive assessment of the environment and passenger physiological state, and unable to achieve precise intervention at the optimal time; second, single chemical spraying can quickly repel mosquitoes, but may leave residues in the vehicle cabin, affecting air quality and passenger health; and pure physical electric mesh or wind-driven ventilation mode is often restricted by static settings and cannot adapt to mosquito populations of different densities and motion states. Third, existing prediction systems are mostly based on simple statistics or single-mode data, which are difficult to consider spatial, temporal and physiological three-dimensional features, and lack of prediction accuracy and stability. SUMMARY

[0004] In view of the problems of the existing vehicle intelligent mosquito-repelling method, the present application is proposed. Therefore, the problem to be solved by the present application is how to provide a vehicle intelligent mosquito-repelling method.

[0005] To solve the above technical problems, the present application provides the following technical solutions:

[0006] In a first aspect, the present application provides a vehicle intelligent mosquito-repelling method, which comprises synchronously collecting multi-modal data in a vehicle by a sensor and pre-processing the multi-modal data in the vehicle to obtain pre-processed multi-modal data in the vehicle;

[0007] Based on the pre-processed multi-modal data, a chemical mosquito-repelling mode or a physical mosquito-repelling mode is selected for vehicle mosquito-repelling control;

[0008] The mosquito density at the air outlet of the air conditioner is calculated, and if the mosquito density in unit volume exceeds the predetermined density, the ultraviolet LED lamp is turned on to catalytically decompose the mosquito repellent ester residues in the air.

[0009] The user historical driving data is acquired through the vehicle-mounted T-BOX, the LSTM neural network is used for mosquito appearance probability prediction, the pre-mosquito driving request is pushed to the user mobile terminal according to the prediction result, and the intelligent mosquito driving in the vehicle based on multi-modal perception is completed.

[0010] As a preferred scheme of the intelligent mosquito driving method in the vehicle, the sensor includes a millimeter wave radar, a steering wheel capacitive electrode and an air conditioner inlet gas sensor; the multi-modal data in the vehicle includes millimeter wave radar data, a passenger electrocardiogram waveform and a histamine concentration in the air.

[0011] As a preferred scheme of the intelligent mosquito driving method in the vehicle, the preprocessing of the multi-modal data in the vehicle includes:

[0012] The target micro-Doppler frequency is calculated through the millimeter wave radar data, when the target micro-Doppler frequency is in a predetermined range and the target radial velocity exceeds a predetermined speed, the target is determined as a mosquito, and the three-dimensional coordinates and the speed vector of the mosquito are extracted;

[0013] The HRV standard deviation is calculated according to the passenger electrocardiogram waveform, and when the mosquito is detected, the current histamine concentration and the HRV standard deviation are recorded.

[0014] As a preferred scheme of the intelligent mosquito driving method in the vehicle, the expression of the target micro-Doppler frequency is:

[0015]

[0016] In the formula, f m is the target micro-Doppler frequency, s(t) is the radar echo signal received at time t, w(t) is the window function at time t, F[·] is the Fourier transform operator, and T is the signal time window length;

[0017] The expression of the HRV standard deviation is:

[0018]

[0019] In the formula, SDNN is the HRV standard deviation, RR i is the R-R interval of the i-th heartbeat, is the average value of all R-R intervals, and N is the number of sampled heartbeats.

[0020] As a preferred scheme of the intelligent mosquito repellent method in the car, the method comprises the following steps:

[0021] The histamine concentration and the HRV standard deviation are read, and if the histamine concentration is less than the predetermined histamine concentration and the HRV standard deviation exceeds the predetermined HRV standard deviation, the chemical mosquito repellent mode is executed; otherwise, the physical mosquito repellent mode is executed.

[0022] The chemical mosquito repellent mode controls mosquitoes by releasing chemicals, and the release amount is calculated as follows:

[0023]

[0024] In the formula, m is the release amount, V is the volume of the car, n is the number of mosquitoes, v is the average movement speed, and t is the time. m

[0025] The atomization pump speed is controlled to maintain the spray concentration of the picaridin solution at ≤0.5%, and the spray duration is self-adaptive according to the initial concentration and the size of the car space.

[0026] The physical mosquito repellent mode adjusts the output DC voltage of the static grid when the millimeter wave radar predicts the minimum distance change of the mosquitoes, and is expressed as:

[0027]

[0028] In the formula, U is the DC voltage intensity, and d is the minimum distance of the mosquitoes. g

[0029] The air conditioning air flow control is performed, the air direction is switched to the foot air outlet, and the upward air supply mixing mode is turned on for a predetermined time; the current mosquito repellent mode and the expected remaining time are fed back through the central control screen or the mobile phone App pop-up window.

[0030] As a preferred scheme of the intelligent mosquito repellent method in the car, the method comprises the following steps:

[0031] The detection area is positioned as the photocatalyst coating area of the air conditioning air outlet, and the mosquito density in a unit volume is calculated, which is expressed as:

[0032]

[0033] In the formula, ρ is the mosquito density in a unit volume, n is the target number of mosquitoes falling into the catalytic area detection volume, V is the catalytic area detection volume, and t is the time. c d

[0034] ​​​​If the mosquito density in a unit volume exceeds the predetermined density, it is determined that mosquitoes are gathered and the ultraviolet LED light is started, the power of the ultraviolet LED light is adjusted through a preset power gear, and the mosquito repellent ester residues in the air are catalytically decomposed.

[0035] As a preferred solution of the intelligent mosquito repellent method in the vehicle, the mosquito occurrence probability prediction using the LSTM neural network comprises:

[0036] The LSTM model is composed of two layers of stacked long short-term memory units, each layer has a hidden state dimension of 64, in the model training stage, historical data samples are used and binary cross entropy is used as the loss function, combined with the Adam optimizer, the learning rate is 0.001, the batch size is 32 and the iteration is 50 rounds for optimization, the data set is divided into training set and validation set according to 8:2;

[0037] The probability value output by the model is greater than the predetermined probability, which is regarded as a pre-mosquito repellent trigger signal, after three consecutive prediction results meet the condition of being greater than the predetermined probability, the user confirmation link is entered, the cloud sends a pre-mosquito repellent reminder to the user's mobile phone App or the vehicle-mounted central control, and notifies the user of the mosquito occurrence probability in the next hour, and suggests starting the pre-mosquito repellent mode;

[0038] After the user confirms, a control instruction is generated and issued to the vehicle-mounted T-BOX, the millimeter wave radar is switched to the scanning mode first, then the ultraviolet LED light source is started according to the predetermined power and time length, and the photocatalyst area is activated, and finally the vehicle window is lowered to a predetermined height.

[0039] In a second aspect, the present application provides a computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the intelligent mosquito repellent method in the vehicle when executing the computer program.

[0040] In a third aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of the intelligent mosquito repellent method in the vehicle.

[0041] The present application has the following advantages: through multi-modal synchronous acquisition and preprocessing, the present application realizes the spatio-temporal fusion and quality guarantee of data; through dynamic mode switching and hierarchical catalytic purification, the present application realizes the efficiency, safety and low pollution of mosquito repellent measures; through spatio-temporal prediction based on LSTM and user interaction, the present application realizes the initiative and intelligence of pre-mosquito repellent, so that the whole intelligent mosquito repellent system in the vehicle achieves remarkable effects in ensuring rapid response, passenger health and comfort and energy utilization. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and all other drawings obtained by those skilled in the art without creative effort based on these drawings should also fall within the protection scope of the present application.

[0043] Figure 1 A flowchart of an intelligent mosquito-repelling method in a vehicle. DETAILED DESCRIPTION

[0044] In order to make the above-mentioned objects, features and advantages of the present application more apparent, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort should also fall within the protection scope of the present application.

[0045] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application. However, the present application can be practiced in other manners different from those described herein, and those skilled in the art can make similar generalizations without departing from the scope of the present application. Therefore, the present application is not limited to the specific embodiments disclosed below.

[0046] Secondly, the term "one embodiment" or "embodiments" as used herein means that a specific feature, structure or characteristic described can be included in at least one implementation of the present application. The term "one embodiment" appearing in different places in the specification does not mean the same embodiment, nor does it mean an embodiment that is separate from or mutually exclusive with other embodiments.

[0047] Reference Figure 1 For the first embodiment of the present application, the embodiment provides an intelligent mosquito-repelling method in a vehicle, comprising:

[0048] S1: synchronously collecting multi-modal data in the vehicle through a sensor, and pre-processing the multi-modal data in the vehicle to obtain pre-processed multi-modal data in the vehicle;

[0049] Specifically, S1.1: multi-modal data collection, collecting millimeter wave radar data, passenger electrocardiogram waveform and histamine concentration in the air; millimeter wave radar installation position: central roof, left and right A-pillar inner side. Steering wheel capacitive electrode installation position: both sides of the steering wheel. Air conditioner air inlet gas sensor position: air conditioner air inlet.

[0050] S1.2: millimeter wave radar data preprocessing, in the radar return signal, the target wing frequency, speed and spatial position are extracted by using micro-Doppler effect. The target micro-Doppler frequency is expressed as:

[0051]

[0052] In the formula: f m Let be the target micro-Doppler frequency, s(t) be the radar echo signal received at time t, w(t) be the window function at time t, F[·] be the Fourier transform operator, and T be the signal time window length;

[0053] When the target's micro-Doppler frequency is within a predetermined range and the target's radial velocity exceeds a predetermined velocity, the target is identified as a mosquito, and the mosquito's three-dimensional coordinates and velocity vector are extracted.

[0054] S1.3: Calculate the HRV standard deviation. Extract the heart rate interval (RR interval) from the ECG waveform acquired by the electrodes, and calculate the HRV standard deviation, expressed as:

[0055]

[0056] Where: SDNN is the standard deviation of HRV, RR i Let be the RR interval of the i-th heartbeat. is the average of all RR intervals, and N is the number of sampled heartbeats.

[0057] S1.4: Histamine concentration analysis. When mosquitoes are detected, the system will record the current histamine concentration and the standard deviation of HRV.

[0058] S2: Select either chemical or physical mosquito repellent mode based on the preprocessed multimodal data to control mosquito repellency inside the vehicle.

[0059] Specifically, S2.1: Read the histamine concentration and HRV standard deviation. If the histamine concentration is less than the predetermined histamine concentration and the HRV standard deviation exceeds the predetermined HRV standard deviation, execute the chemical mosquito repellent mode; otherwise, execute the physical mosquito repellent mode.

[0060] S2.2: Chemical mosquito repellent mode. The number of mosquitoes is detected and statistically analyzed using millimeter-wave radar. The average speed of the mosquitoes is obtained by averaging the velocity vectors of all detected mosquitoes, and the vehicle's interior volume is acquired to calculate the release amount, expressed as:

[0061]

[0062] In the formula: m is the release amount, V is the vehicle interior volume, determined based on the vehicle model and cabin volume; n is the number of mosquitoes, v m The average speed of motion;

[0063] Control the atomizing pump speed to maintain the spray concentration at ≤0.5% picaridin solution. The spray duration is adaptive based on the initial concentration and the size of the vehicle interior. Generally, spray continuously for 60 seconds after startup, and then spray again for 10 seconds every 5 minutes.

[0064] S2.3: Physical mosquito repellent mode, activates the electrostatic grid to output DC voltage, and dynamically adjusts the voltage when the millimeter-wave radar predicts changes in the minimum distance to mosquitoes.

[0065]

[0066] In the formula: U g d represents the DC voltage intensity, and d represents the minimum distance between the mosquitoes.

[0067] Control the airflow of the air conditioner, switch the airflow direction to the foot vents, and turn on the upward airflow mixing mode to continuously supply air for a predetermined time.

[0068] The current mode and estimated remaining time will be displayed via a pop-up window on the central control screen or mobile app.

[0069] S3: Calculate the mosquito density at the air conditioner vent. If the mosquito density per unit volume exceeds the predetermined density, turn on the ultraviolet LED lamp to catalyze the decomposition of mosquito repellent residues in the air.

[0070] Specifically, mosquito aggregation detection is performed, with the detection area located at the air conditioner vent, covering the area of ​​the photocatalytic coating. Millimeter-wave radar is used to continuously scan the area, and the mosquito density per unit volume is calculated, expressed as:

[0071]

[0072] In the formula: ρ is the mosquito density per unit volume, n c V represents the number of mosquitoes that fall into the detection volume of the catalytic region. d For the detection volume of the catalytic region;

[0073] If the mosquito density per unit volume exceeds the predetermined density, it is determined that mosquitoes have gathered and the ultraviolet LED light is activated. The power of the ultraviolet LED light is adjusted through the preset power level to catalyze the decomposition of mosquito repellent residues in the air.

[0074] S4: Acquire users' historical driving data through the vehicle-mounted T-BOX, and use LSTM neural network to predict the probability of mosquito appearance. Based on the prediction results, push pre-mosquito repellent requests to users' mobile terminals to complete in-vehicle intelligent mosquito repellent based on multimodal perception.

[0075] Specifically, S4.1: The in-vehicle T-BOX reads the user's historical driving data from various sensor systems in the vehicle according to a pre-set sampling period. This includes timestamps, current GPS latitude and longitude coordinates, the mosquito density value detected by the last millimeter-wave radar, in-vehicle temperature, humidity, vehicle speed, and air conditioning status. The data is then uploaded to the cloud server via 4G / 5G or in-vehicle Wi-Fi link for subsequent model training and online prediction.

[0076] S4.2: After the cloud receives the raw data, it first encodes the time information, converting the hour and the day of the week into corresponding vectors, respectively; and maps the latitude and longitude to a fixed-size grid index. Numerical features such as historical mosquito density, temperature, humidity, and vehicle speed are normalized by the minimum-maximum method to scale them to the range [0, 1]. Finally, the continuous data is spliced into a multi-dimensional time series sample according to the set sequence length, which is used as the input of the LSTM model.

[0077] S4.3: The LSTM model consists of two layers of stacked long short-term memory units, with a hidden state dimension of 64 in each layer. The model receives the preprocessed time series input and automatically captures the temporal and spatial features through the gating mechanism; the hidden state of the last LSTM layer is mapped through a fully connected layer and activated by Sigmoid, outputting a real number between 0 and 1, representing the probability of mosquito density exceeding the threshold in the next hour.

[0078] S4.4: During the model training phase, the cloud uses historical data samples and uses binary cross-entropy as the loss function, with an Adam optimizer (learning rate 0.001), a batch size of 32, and 50 iterations for optimization. The dataset is divided into training and validation sets in the ratio of 8:2.

[0079] S4.5: When the user's vehicle is driving again, the T-BOX collects the latest sequence data of a specified length in real time and sends it to the LSTM model deployed in the cloud or on the vehicle for inference.

[0080] S4.6: If the probability output by the model is greater than the predetermined probability, it is considered as a pre-mosquito driving trigger signal. After three consecutive prediction results meet the condition of being greater than the predetermined probability, the user enters the confirmation link, the cloud sends a pre-mosquito driving reminder to the user's mobile phone App or vehicle-mounted central control, notifies the probability of mosquito occurrence in the next hour, and suggests starting the pre-mosquito driving mode. The user can choose to confirm the start or say later.

[0081] S4.7: After the user clicks to confirm, the cloud generates and issues control instructions to the vehicle-mounted T-BOX, which receives the instructions and drives the corresponding subsystems in turn: first, switch the millimeter wave radar to scanning mode; then start the ultraviolet LED light source according to the predetermined power and duration and activate the photocatalyst area; finally, control the vehicle window to lower to a predetermined height to achieve air convection.

[0082] The embodiment also provides a computer device suitable for the case of the intelligent mosquito driving method in the vehicle, which includes a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to implement all or part of the steps of the method described in the embodiments of the application.

[0083] The embodiment further provides a storage medium on which a computer program is stored, and the computer program is executed by a processor to perform the method in any optional implementation manner of the above-mentioned embodiment. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage, a flash memory, a magnetic disk, or an optical disk.

[0084] The storage medium proposed in the embodiment belongs to the same inventive concept as the data storage method proposed in the above-mentioned embodiment, and the technical details not described in the embodiment can be referred to the above-mentioned embodiment, and the embodiment has the same beneficial effects as the above-mentioned embodiment.

[0085] To sum up, the application realizes the spatio-temporal fusion and quality guarantee of data through multi-modal synchronous acquisition and preprocessing, realizes the efficiency, safety and low pollution of the mosquito repellent measures through dynamic mode switching and hierarchical catalytic purification, realizes the initiative and intelligence of the pre-mosquito repellent through the spatio-temporal prediction based on LSTM and user interaction, and makes the whole in-vehicle intelligent mosquito repellent system achieve remarkable effects in ensuring rapid response, passenger health and comfort, and energy utilization.

[0086] It should be noted that the above embodiments are only used to illustrate the technical solutions of the application rather than limit the application. Although the application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the application can be modified or replaced equivalently without departing from the spirit and scope of the application, and all of them should be covered in the scope of the claims of the application.

Claims

1. A smart mosquito repellent method for vehicles, characterized in that: include, Multimodal data inside the vehicle is collected synchronously by sensors, and the multimodal data inside the vehicle is preprocessed to obtain preprocessed multimodal data inside the vehicle. The sensors include millimeter-wave radar, a steering wheel capacitive electrode, and an air conditioning inlet gas sensor. The in-vehicle multimodal data includes millimeter-wave radar data, occupant electrocardiogram waveforms, and histamine concentration in the air; Based on the preprocessed multimodal data, a chemical or physical mosquito repellent mode is selected for in-vehicle mosquito control. The selection of chemical or physical mosquito repellent modes based on preprocessed multimodal data includes: Read the histamine concentration and HRV standard deviation. If the histamine concentration is less than the predetermined histamine concentration and the HRV standard deviation exceeds the predetermined HRV standard deviation, execute the chemical mosquito repellent mode; otherwise, execute the physical mosquito repellent mode. Chemical mosquito repellent methods control mosquitoes by releasing chemical substances. The release amount is calculated and expressed as follows: In the formula: For release amount, This refers to the interior volume of the vehicle. For the number of mosquitoes, The average speed of motion; Control the atomizing pump speed to maintain the spray concentration at ≤0.5% picaridin solution, and the spray duration adapts to the initial concentration and the size of the vehicle interior space; The physical mosquito repellent mode activates an electrostatic grid to output a DC voltage, which is dynamically adjusted when the millimeter-wave radar predicts changes in the minimum distance to mosquitoes. This is represented as follows: In the formula: DC voltage intensity This is the minimum distance for mosquitoes; Control the airflow of the air conditioner, switch the airflow direction to the foot vents, and turn on the upward airflow mixing mode to continuously supply air for the preset time; the current mosquito repellent mode and the estimated remaining time will be displayed on the central control screen or mobile app. Calculate the mosquito density at the air conditioner vent. If the mosquito density per unit volume exceeds the predetermined density, turn on the ultraviolet LED lamp to catalyze the decomposition of mosquito repellent residues in the air. By acquiring users' historical driving data through the in-vehicle T-BOX and using an LSTM neural network to predict the probability of mosquito appearance, a pre-mosquito repellent request is pushed to the user's mobile terminal based on the prediction results, thus completing in-vehicle intelligent mosquito repellent based on multimodal perception.

2. The intelligent mosquito repellent method for vehicles as described in claim 1, characterized in that: The preprocessing of in-vehicle multimodal data includes: The target's micro-Doppler frequency is calculated using millimeter-wave radar data. When the target's micro-Doppler frequency is within a predetermined range and the target's radial velocity exceeds a predetermined velocity, the target is identified as a mosquito, and the mosquito's three-dimensional coordinates and velocity vector are extracted. The HRV standard deviation is calculated based on the passenger's electrocardiogram waveform. When mosquitoes are detected, the current histamine concentration and HRV standard deviation are recorded.

3. The intelligent mosquito repellent method for vehicles as described in claim 2, characterized in that: The expression for the target micro-Doppler frequency is: In the formula: For the target micro-Doppler frequency, For a moment Received radar echo signal, For a moment Window functions, For Fourier transform operators, The length of the signal time window; The expression for the HRV standard deviation is: In the formula: The standard deviation of HRV For the first The RR interval of one heartbeat, The average value for all RR intervals. This is for sampling heart rate.

4. The intelligent mosquito repellent method for vehicles as described in claim 3, characterized in that: The calculation of mosquito density at the air conditioner vent includes: The detection area is the area covered by the photocatalytic coating at the air conditioner vent. The mosquito density per unit volume is calculated and expressed as: In the formula: Mosquito density per unit volume To determine the number of mosquitoes that fall into the detection zone within the target volume. For the detection volume of the catalytic region; If the mosquito density per unit volume exceeds the predetermined density, it is determined that mosquitoes have gathered and the ultraviolet LED light is activated. The power of the ultraviolet LED light is adjusted through the preset power level to catalyze the decomposition of mosquito repellent residues in the air.

5. The intelligent mosquito repellent method for vehicles as described in claim 4, characterized in that: The method of using an LSTM neural network to predict the probability of mosquito occurrence includes: The LSTM model consists of two stacked layers of long short-term memory units, with each layer having a hidden state dimension of 64. During the model training phase, historical data samples are used with binary cross-entropy as the loss function, along with the Adam optimizer, a learning rate of 0.001, a batch size of 32, and 50 iterations for optimization. The dataset is divided into training and validation sets in an 8:2 ratio. If the probability value output by the model is greater than the predetermined probability, it is considered a pre-mosquito repellent trigger signal. After three consecutive prediction results are greater than the predetermined probability, the user confirmation process begins. The cloud sends a pre-mosquito repellent reminder to the user's mobile app or vehicle central control, notifying them of the predicted probability of mosquito appearance in the next hour and suggesting that the pre-mosquito repellent mode be activated. After user confirmation, control commands are generated and sent to the vehicle-mounted T-BOX. First, the millimeter-wave radar is switched to scanning mode; then, the ultraviolet LED light source is activated and the photocatalytic area is activated according to the predetermined power and duration; finally, the window is lowered to the predetermined height.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the intelligent mosquito repellent method for vehicles as described in any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the intelligent mosquito repellent method for vehicles as described in any one of claims 1 to 5.

Images