Vehicle function triggering method, electronic equipment and vehicle

Abstract

The invention relates to the technical field of vehicle control, and provides a vehicle function triggering method, electronic equipment and a vehicle. The method comprises the following steps: acquiring feature information of a driver and passengers; and determining that an emergency occurs in the vehicle according to the feature information, and transmitting help-seeking information to people outside the vehicle according to a preset emergency response mode by triggering an emergency response function. In this way, the situation that people in the vehicle cannot ask for help to the outside in emergency is avoided, and meanwhile people outside the vehicle can conveniently know the emergency in the vehicle in time.

Description

Technical Field

[0001] The present disclosure relates to the field of vehicle control technology, and in particular to a vehicle function triggering method, electronic equipment and a vehicle. Background Art

[0002] With the development of the vehicle industry, more and more attention is paid to the protection of privacy inside the car. However, in some scenarios, when an emergency occurs to the occupants of the car, there is a risk that the people outside the car cannot know the situation inside the car, and the people inside the car cannot ask for help from the outside world.

[0003] In view of this, how to prevent people in the car from being unable to seek help from the outside world in an emergency has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In view of this, the purpose of the present disclosure is to provide a vehicle function triggering method, an electronic device and a vehicle to solve the problem in the prior art that people in the vehicle cannot seek help from the outside in an emergency.

[0005] Based on the above purpose, the first aspect of the present disclosure proposes a method for triggering a vehicle function, the method comprising:

[0006] Obtaining characteristic information of drivers and passengers;

[0007] An emergency event is determined to have occurred in the vehicle based on the characteristic information, and an emergency response function is triggered to transmit a distress message to people outside the vehicle in a preset emergency response manner.

[0008] Based on the same inventive concept, the second aspect of the present disclosure proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method as described above when executing the computer program.

[0009] Based on the same inventive concept, a third aspect of the present disclosure provides a vehicle, which includes the electronic device described in the second aspect.

[0010] As can be seen from the above, the vehicle function triggering method, electronic device and vehicle provided by the present disclosure obtain characteristic information of the driver and passengers. According to the characteristic information of the driver and passengers, it is possible to accurately determine that an emergency event has occurred in the vehicle, and by triggering the emergency response function, it is possible to transmit a distress message to people outside the vehicle in accordance with a preset emergency response method, thereby avoiding the situation where people inside the vehicle are unable to seek help from the outside world in an emergency, and at the same time facilitating people outside the vehicle to be informed of the emergency situation in the vehicle in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present disclosure or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A flowchart of a method for triggering a vehicle function according to an embodiment of the present disclosure;

[0013] Figure 2 A flowchart of a method for triggering a vehicle emergency response according to an embodiment of the present disclosure;

[0014] Figure 3 A schematic diagram of the structure of a triggering device for a vehicle function according to an embodiment of the present disclosure;

[0015] Figure 4 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0016] In order to make the objectives, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0017] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the embodiments of the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0018] Based on the description of the background technology, the window glass commonly used in current vehicles is usually designed to protect the privacy of passengers in the car, so that the inside of the car can clearly see outside the car, but it is difficult for the outside to see the situation inside the car. Although this design provides necessary privacy protection under normal circumstances, in certain emergency situations, such as car accidents or violent incidents in the car, the people in the car cannot ask for help from the outside through the car window, resulting in the people outside the car being unable to understand the situation in the car in time, thereby delaying the rescue time, increasing the risk of life and health and the possibility of property loss. At present, there is still a lack of an effective technical means to promptly transmit the distress information to the people outside the car when an emergency occurs in the car.

[0019] As mentioned above, how to prevent people in a car from being unable to seek help from the outside world in an emergency has become an important research issue.

[0020] Based on the above description, if Figure 1 As shown, the method for triggering a vehicle function proposed in this embodiment includes:

[0021] Step 101, obtaining characteristic information of the driver and passengers.

[0022] In specific implementation, the feature information includes: image features and biometric features. The image features and biometric features of the driver and passengers are obtained by using sensors. Among them, the sensors include: cameras and biometric sensors.

[0023] The high-definition, wide-angle camera with infrared night vision function ensures that the situation inside the car can be clearly captured under various lighting conditions. The camera is installed near the central rearview mirror at the front of the car and in the center of the rear seat, covering the entire area of ​​the car to ensure no blind spot monitoring. The camera is connected to the central control system of the car, continuously recording in real time, and transmitting the video stream to the computer vision processing unit.

[0024] Biosensors include heart rate sensors and breathing sensors. High-precision heart rate sensors and breathing sensors can accurately capture biological data and have anti-interference capabilities. The heart rate sensor is embedded in the seat back and steering wheel, and the breathing sensor is installed in the seat back or under the seat to ensure close proximity to the passenger's body. The biosensor is connected to the vehicle's central control system wirelessly or wired, and transmits biological data to the data processing unit in real time.

[0025] The camera is used to obtain image data, and the image data is subjected to feature extraction processing to obtain image features. The biometric sensor is used to obtain biological data, and the biological data is subjected to feature extraction processing to obtain biological features.

[0026] Step 102, determining that an emergency event has occurred in the vehicle based on the characteristic information, triggering an emergency response function, and transmitting a distress message to people outside the vehicle in a preset emergency response manner.

[0027] In a specific implementation, when the characteristic information meets the preset emergency event characteristics, it can be accurately determined that an emergency event has occurred in the vehicle.

[0028] A plurality of emergency response methods are pre-stored. Specifically, the emergency response function is triggered, and a distress message is transmitted to a person outside the vehicle based on the plurality of pre-stored emergency response methods. Alternatively, the emergency response function is triggered, and at least one emergency response method is determined from the plurality of pre-stored emergency response methods according to the comprehensive score, and a distress message is transmitted to a person outside the vehicle based on the at least one emergency response method.

[0029] Through the above embodiments, the characteristic information of the driver and passengers is obtained. According to the characteristic information of the driver and passengers, it is possible to accurately determine that an emergency event has occurred in the car, and by triggering the emergency response function, it is possible to transmit a distress message to people outside the car in a preset emergency response manner, thereby avoiding the situation where people inside the car are unable to seek help from the outside world in an emergency, and at the same time, it is convenient for people outside the car to be informed of the emergency situation in the car in a timely manner.

[0030] After the emergency response function is triggered, a variety of emergency response methods can be used to transmit a distress message to people outside the vehicle. The various emergency response methods are as follows:

[0031] In some embodiments, step 102 includes:

[0032] Step 1021, by triggering the emergency response function, the liquid crystal dimming glass is controlled to switch from an opaque state to a transparent state, so as to transmit a distress message to people outside the vehicle.

[0033] In specific implementation, the emergency response methods include: liquid crystal dimming glass transparency. Liquid crystal dimming glass is a technology that changes the transparency of glass under the action of an electric field by embedding liquid crystal materials in the glass. When the electric field acts, the liquid crystal molecules are arranged neatly and the glass is transparent; when the electric field is turned off, the liquid crystal molecules are arranged disorderly and the glass becomes opaque.

[0034] Liquid crystal dimming glass is usually composed of a multi-layer structure, including two glass layers and a liquid crystal layer sandwiched in the middle. The liquid crystal layer is usually composed of polymer dispersed liquid crystal (PDLC). Liquid crystal dimming glass adjusts its transparency through electrical control. The control system applies voltage to the liquid crystal layer, causing the liquid crystal dimming glass to respond quickly and switch between transparent and opaque states.

[0035] The camera and the liquid crystal dimming glass are connected through the vehicle central control system, and the transparency of the liquid crystal dimming glass is intelligently adjusted according to the detection results of the camera. After the emergency response function is triggered, the liquid crystal dimming glass is controlled to switch from an opaque state to a transparent state by turning off the electric field of the liquid crystal dimming glass, thus transmitting a distress message to people outside the vehicle.

[0036] In addition, the car windows can also be controlled to switch from a closed state to an open state. By opening the windows, it is convenient for people inside the car to call for help from outside, and it is also convenient for people outside the car to understand the emergency situation inside the car and provide rescue.

[0037] And / or, step 1022, by triggering the emergency response function, obtaining the sound inside the car and playing the sound inside the car through a speaker, so as to transmit a distress message to people outside the car.

[0038] In specific implementation, the emergency response methods include: external speakers playing sound. Waterproof and dustproof high-volume speakers can ensure effective operation in various environments. The speakers are installed at the front and rear of the vehicle, and the speakers are connected to the central control system of the vehicle.

[0039] After the emergency response function is triggered, the speaker is automatically activated to play the sound inside the car through the speaker to convey a distress message to people outside the car.

[0040] And / or, step 1023, by triggering the emergency response function, controlling the warning lights outside the vehicle to flash, and transmitting a distress message to people outside the vehicle.

[0041] In specific implementation, the emergency response methods include: flashing warning lights. High-brightness external warning lights can ensure effective operation in various environments. Warning lights are installed on the roof and four corners of the vehicle body to ensure that the warning signal can be transmitted in all directions, and the warning lights are connected to the central control system of the vehicle.

[0042] After the emergency response function is triggered, the warning light is automatically activated, and the warning light outside the vehicle is controlled to flash, thereby sending a distress message to people outside the vehicle.

[0043] After the emergency response function is triggered, the above three emergency response methods can be used to simultaneously transmit a distress message to people outside the vehicle. For example, after the emergency response function is triggered, the liquid crystal dimming glass is controlled to switch from an opaque state to a transparent state, the sound inside the vehicle is played through the speaker, and the warning light outside the vehicle is controlled to flash, so as to transmit a distress message to people outside the vehicle.

[0044] After the emergency response function is triggered, at least one emergency response method can be determined from the above three emergency response methods according to the urgency of the emergency event, and a distress message can be transmitted to people outside the vehicle based on the at least one emergency response method. For example, after the emergency response function is triggered, at least one emergency response method is determined from the above three emergency response methods according to the urgency of the emergency event, which is to make the dimming glass transparent and to play sound from the speaker. Then, the liquid crystal dimming glass is controlled to switch from an opaque state to a transparent state, and the sound inside the car is played through the speaker to transmit a distress message to people outside the vehicle.

[0045] Through the above scheme, when an emergency occurs in the car, a distress message can be transmitted to people outside the car through a variety of emergency response methods, which is convenient for people outside the car to find and provide help to people inside the car in time. In addition, at least one emergency response method is determined from a variety of emergency response methods according to the urgency of the emergency, and a distress message is transmitted to people outside the car based on at least one emergency response method, which can facilitate people outside the car to find and provide help to people inside the car in time, while minimizing the disturbance to the environment outside the car.

[0046] In order to avoid wasting resources, only the liquid crystal dimming glass at the position where the dangerous person is located in the car is controlled to switch from an opaque state to a transparent state. The specific process is as follows:

[0047] In some embodiments, step 1021 includes:

[0048] Step 10211, determine the position of the driver and passengers who are in an emergency state when an emergency occurs in the vehicle.

[0049] Step 10212, controlling the liquid crystal dimming glass of the window corresponding to the position of the driver and passenger in the emergency state to switch from an opaque state to a transparent state.

[0050] In specific implementation, when an emergency occurs in the car, in order to facilitate people outside the car to accurately understand the location of the emergency and the situation of people in the emergency state in the car, the position of the driver and passengers in the emergency state when the emergency occurs is determined, and the liquid crystal dimming glass of the window corresponding to the position of the driver and passengers in the emergency state is controlled to switch from an opaque state to a transparent state.

[0051] For example, when an emergency occurs in the car and the passenger in the front passenger seat is in an emergency state (in danger), the liquid crystal dimming glass of the front passenger seat window is controlled to switch from an opaque state to a transparent state.

[0052] In addition, when an emergency occurs in the car, in order to facilitate people outside the car in different positions to quickly understand the emergency, the liquid crystal dimming glass of all windows can also be controlled to switch from an opaque state to a transparent state.

[0053] Through the above scheme, by controlling the liquid crystal dimming glass of the window corresponding to the position of the driver and passenger in an emergency state to switch from an opaque state to a transparent state, it is convenient for people outside the car to accurately understand the location of the emergency event in the car and the situation of the people in the emergency state in the car, while avoiding the waste of resources caused by switching the liquid crystal dimming glass of all windows to a transparent state.

[0054] In order to accurately control the liquid crystal dimming glass to switch from an opaque state to a transparent state, the transparency of the liquid crystal dimming glass is determined according to the in-vehicle environment. The specific process is as follows:

[0055] In some embodiments, step 1021 includes:

[0056] Step 1021A, obtaining the light intensity inside the vehicle.

[0057] Step 1021B: determining the transparency of the liquid crystal dimming glass based on the light intensity inside the vehicle.

[0058] Step 1021C: according to the transparency, control the liquid crystal dimming glass to switch from an opaque state to a transparent state.

[0059] In specific implementation, when controlling the liquid crystal dimming glass to switch from an opaque state to a transparent state, in order to ensure that people outside the vehicle can clearly understand the emergency situation inside the vehicle, the transparency of the liquid crystal dimming glass is determined according to the light intensity inside the vehicle, and the liquid crystal dimming glass is controlled to switch from an opaque state to a transparent state according to the determined transparency, so that people outside the vehicle can clearly see the situation inside the vehicle.

[0060] Specifically, a correspondence between the light intensity and the transparency in the vehicle is pre-stored. Based on the pre-stored correspondence between the light intensity and the transparency in the vehicle, the transparency of the liquid crystal dimming glass corresponding to the light intensity in the vehicle is determined. According to the determined transparency, the liquid crystal dimming glass is controlled to switch from an opaque state to a transparent state.

[0061] Through the above scheme, the transparency of the liquid crystal dimming glass is determined according to the light intensity inside the car, and the liquid crystal dimming glass is controlled to switch from an opaque state to a transparent state according to the determined transparency, so that people outside the car can see the situation inside the car clearly, making it convenient for people outside the car to clearly understand the emergency situation inside the car.

[0062] When the vehicle is in a dark environment, in order to facilitate people outside the vehicle to see the situation inside the vehicle clearly, while controlling the liquid crystal dimming glass to switch from an opaque state to a transparent state, the interior lighting is controlled to turn on. The specific process is as follows:

[0063] In some embodiments, step 1021 includes:

[0064] Step 1021a, obtaining the brightness outside the vehicle.

[0065] Step 1021b, in response to determining that the brightness outside the vehicle is less than a preset brightness threshold, while controlling the liquid crystal dimming glass to switch from an opaque state to a transparent state, the interior lighting is controlled to turn on.

[0066] In specific implementation, when the brightness outside the vehicle is less than a preset brightness threshold, it indicates that the external environment of the vehicle is a dark environment (for example, a night environment, a cloudy environment, and a basement environment). In order to facilitate people outside the vehicle to clearly understand the emergency situation inside the vehicle, while controlling the liquid crystal dimming glass to switch from an opaque state to a transparent state, the interior lights are controlled to turn on.

[0067] Through the above scheme, when the brightness outside the vehicle is less than the preset brightness threshold, the liquid crystal dimming glass is controlled to switch from an opaque state to a transparent state, and the interior lighting is controlled to turn on. In this way, when the vehicle is in a dark environment, people outside the vehicle can also see the situation inside the vehicle clearly, which is convenient for people outside the vehicle to clearly understand the emergency situation inside the vehicle.

[0068] Judging whether an emergency has occurred in the car based on the characteristic information of the driver and passengers, the specific process is as follows:

[0069] In some embodiments, the feature information includes: image features and biometric features; step 102 includes:

[0070] Step 1021: Score the image feature to obtain an image feature score, and score the biometric feature to obtain a biometric feature score.

[0071] In a specific implementation, an image scoring rule is pre-stored, and the pre-stored image scoring rule can determine the probability of an emergency occurring to a person in the vehicle based on the image features. According to the pre-stored image scoring rule, the image features are scored to obtain an image feature score. The image feature score is used to determine the probability of an emergency occurring to a person in the vehicle based on the image features.

[0072] A biometric scoring rule is pre-stored, and the pre-stored biometric scoring rule can determine the probability of an emergency occurring to a person in the vehicle based on the biometric feature. According to the pre-stored biometric scoring rule, the biometric feature is scored to obtain a biometric feature score. The biometric feature score is used to determine the probability of an emergency occurring to a person in the vehicle based on the biometric feature.

[0073] Step 1022, determining a comprehensive score based on the image feature score and the biometric score.

[0074] In specific implementation, the comprehensive score can determine the probability of an emergency occurring to the occupants of the vehicle based on image features and biometric features.

[0075] The image feature score and the biometric score are summed to obtain a comprehensive score. Alternatively, the image feature score and the biometric score are averaged to obtain a comprehensive score.

[0076] In addition, the image feature weights and biometric weights are determined; the image feature score and the image feature weight are multiplied to obtain the image feature comprehensive score; the biometric score and the biometric weight are multiplied to obtain the biometric comprehensive score; the image feature comprehensive score and the biometric comprehensive score are summed to obtain the comprehensive score.

[0077] Step 1023: In response to the comprehensive score being greater than a preset score threshold, determining that an emergency occurs in the vehicle.

[0078] In specific implementation, the preset scoring threshold is a pre-set scoring standard indicating that an emergency event has occurred in the vehicle. When the comprehensive score is greater than the preset scoring threshold, it can be accurately determined that an emergency event has occurred in the vehicle.

[0079] Through the above scheme, the image features are scored to obtain the image feature score, and the biometric features are scored to obtain the biometric feature score. A comprehensive score is determined based on the image feature score and the biometric feature score. In this way, the determined comprehensive score can reflect both the image features of the driver and the passenger and the biometric features of the driver and the passenger, thereby comprehensively, accurately and intuitively reflecting the status of the driver and the passenger based on the comprehensive score. When the comprehensive score is greater than the preset score threshold, it can be accurately determined that an emergency has occurred in the car.

[0080] The image features are scored to obtain the image feature scores. The specific process is as follows:

[0081] In some embodiments, the image features include: behavioral features and expression features; step 1021 includes:

[0082] Step 1021A: classify the behavior features based on the pre-trained behavior detection model to obtain a behavior classification result.

[0083] Step 1021B: Based on the behavior classification result, score the behavior feature to obtain a behavior feature score.

[0084] In specific implementation, the pre-trained behavior detection model is used to classify the behavior characteristics of the driver and passengers. The behavior detection model is trained using a large amount of sample behavior data.

[0085] The image data is acquired by using a camera, and the image data is pre-processed to remove noise to obtain denoised image data, and the denoised image data is subjected to behavioural feature extraction to obtain behavioural features. The behavioural features are input into a pre-trained behaviour detection model, and the behavioural features are classified using the input pre-trained behaviour detection model, and behavioural classification results are output. Different behavioural classification results correspond to different behavioural feature scores. A correspondence between the classification results and the scores is pre-stored. Based on the correspondence between the pre-stored classification results and the scores, the behavioural feature scores corresponding to the behavioural classification results are determined.

[0086] For example, the behavior feature is input into a pre-trained behavior detection model, and the output behavior classification result is normal behavior; based on the correspondence between the pre-stored classification result and the score, it is determined that the behavior feature score corresponding to the normal behavior is 0 points.

[0087] For another example, the behavioral features are input into a pre-trained behavior detection model, and the output behavior classification result is abnormal behavior (for example, fainting behavior, quarreling behavior); based on the correspondence between the pre-stored classification results and the scores, the behavioral feature score corresponding to the fainting behavior is determined to be 70 points, and the behavioral feature score corresponding to the quarreling behavior is determined to be 90 points.

[0088] Step 1021C, classifying the expression features based on the pre-trained expression detection model to obtain an expression classification result.

[0089] Step 1021D: Based on the expression classification result, the expression feature is scored to obtain an expression feature score.

[0090] In specific implementation, the pre-trained expression detection model is used to classify the expression features of the driver and passengers. The expression detection model is trained using a large amount of sample expression data.

[0091] The image data is acquired by using a camera, and the image data is pre-processed to remove noise to obtain denoised image data, and the denoised image data is subjected to expression feature extraction processing to obtain expression features. The expression features are input into a pre-trained expression detection model, and the expression features are classified using the input pre-trained expression detection model, and expression classification results are output. Different expression classification results correspond to different expression feature scores. The corresponding relationship between the classification results and the scores is pre-stored. Based on the corresponding relationship between the classification results and the scores stored in advance, the expression feature score corresponding to the expression classification result is determined.

[0092] For example, the expression features are input into a pre-trained expression detection model, and the output expression classification result is a normal expression; based on the correspondence between the pre-stored classification results and the scores, it is determined that the expression feature score corresponding to the normal expression is 0 points.

[0093] For example, the facial expression features are input into a pre-trained facial expression detection model, and the output facial expression classification result is an abnormal expression (for example, a fearful expression, a painful expression); based on the correspondence between the pre-stored classification results and the scores, the facial expression feature score corresponding to the fearful expression is determined to be 50 points, and the facial expression feature score corresponding to the painful expression is determined to be 80 points.

[0094] Through the above scheme, the behavior features can be accurately classified based on the pre-trained behavior detection model, so that the obtained behavior classification results are more accurate. Different behavior classification results correspond to different behavior feature scores, and the behavior feature scores can be accurately determined based on the behavior classification results. Similarly, the expression features can be accurately classified based on the pre-trained expression detection model, so that the obtained expression classification results are more accurate. Different expression classification results correspond to different expression feature scores, and the expression feature scores can be accurately determined based on the expression classification results.

[0095] In some embodiments, the behavior detection model and the expression detection model are used as target detection models; the training process of the target detection model includes:

[0096] Step 10211, obtaining initial sample image data of the driver and passengers.

[0097] In specific implementation, a large amount of video data of the vehicle's passengers in various scenarios is collected while protecting the privacy of the users, and used as the initial sample image data of the passengers. The initial sample image data includes data of normal scenes and emergency events (such as car accidents, violent incidents, etc.). The data sources include at least one of the following: simulation experiments, real accident videos, and public data sets.

[0098] Step 10212: pre-process the initial sample image data to obtain target sample image data.

[0099] In the specific implementation, the collected initial sample image data is preprocessed to obtain the target sample image data. The preprocessing includes at least one of the following: denoising, cropping and enhancement. The denoising can be performed using a convolutional neural network (CNN) for image noise reduction, and the cropping and enhancement can be performed using an image processing library (such as OpenCV).

[0100] Step 10213, obtaining labeled sample image data by labeling the target sample image data.

[0101] In the specific implementation, the pre-processed target sample image data is annotated to obtain annotated sample image data. The annotation content includes normal status and various emergency events to ensure that the target detection model can accurately identify different scenes. The semi-automatic annotation tool is used in combination with expert manual proofreading to improve the annotation efficiency and accuracy.

[0102] Step 10214, using the labeled sample image data, adopting the target detection algorithm to train the original detection model to obtain a trained target detection model.

[0103] In the specific implementation, the YOLO V4 target detection algorithm is used to train the original detection model to obtain the trained target detection model. During the model training process, a large amount of labeled sample image data is used to perform multiple rounds of iterative training and verification to optimize the detection accuracy and speed of the model.

[0104] Deploy the trained object detection model in the control system inside the car. Use embedded hardware (such as NVIDIA Jetson Nano or Raspberry Pi) to perform real-time inference of the model, ensuring that the system runs with low latency and high accuracy.

[0105] Through the above scheme, the initial sample image data is pre-processed by denoising, cropping and enhancing, so that the obtained target sample image data is more accurate. By annotating the target sample image data, the trained target detection model can recognize different scenes. Using the annotated sample image data, the original detection model is trained using the target detection algorithm, so that the trained target detection model can accurately classify image features.

[0106] The biometrics are scored to obtain a biometric score, and the specific process is as follows:

[0107] In some embodiments, the biometric features include: heart rate features and breathing features; step 1021 includes:

[0108] Step 1021a, determining the target heart rate range to which the heart rate characteristic belongs.

[0109] Step 1021b: Determine the heart rate characteristic score corresponding to the target heart rate range based on a pre-stored first correspondence between the heart rate range and the characteristic score.

[0110] In a specific implementation, different target heart rate ranges to which different heart rate characteristics belong correspond to different heart rate characteristic scores. A first correspondence between the heart rate range and the characteristic score is pre-stored. Based on the pre-stored first correspondence between the heart rate range and the characteristic score, the heart rate characteristic score corresponding to the target heart rate range to which the heart rate characteristic belongs is determined.

[0111] For example, it is determined that the target heart rate range to which the heart rate feature belongs is a normal heart rate range, and based on a pre-stored first correspondence between the heart rate range and the feature score, the heart rate feature score is determined to be 0.

[0112] For another example, it is determined that the target heart rate range to which the heart rate feature belongs is 10% beyond the normal heart rate range, and based on the first correspondence between the pre-stored heart rate range and the feature score, the heart rate feature score is determined to be 50 points. It is determined that the target heart rate range to which the heart rate feature belongs is 20% beyond the normal heart rate range, and based on the first correspondence between the pre-stored heart rate range and the feature score, the heart rate feature score is determined to be 80 points.

[0113] Step 1021c, determining the target breathing range to which the breathing feature belongs.

[0114] Step 1021d: Determine the breathing characteristic score corresponding to the target breathing range based on a pre-stored second correspondence between the breathing range and the characteristic score.

[0115] In a specific implementation, different target breathing ranges to which different breathing features belong correspond to different breathing feature scores. A second corresponding relationship between the breathing range and the feature score is pre-stored. Based on the pre-stored second corresponding relationship between the breathing range and the feature score, the breathing feature score corresponding to the target breathing range to which the breathing feature belongs is determined.

[0116] For example, it is determined that the target breathing range to which the breathing feature belongs is the normal breathing range, and based on a pre-stored second corresponding relationship between the breathing range and the feature score, the breathing feature score is determined to be 0.

[0117] For another example, it is determined that the target breathing range to which the breathing feature belongs is 10% beyond the normal breathing range, and based on the second correspondence between the pre-stored breathing range and the feature score, the breathing feature score is determined to be 50 points. It is determined that the target breathing range to which the breathing feature belongs is 20% beyond the normal breathing range, and based on the second correspondence between the pre-stored breathing range and the feature score, the breathing feature score is determined to be 80 points.

[0118] Through the above scheme, the target heart rate ranges to which different heart rate characteristics belong correspond to different heart rate characteristic scores, and the heart rate characteristic scores can be accurately determined based on the first correspondence between the pre-stored heart rate ranges and the characteristic scores. Similarly, the target breathing ranges to which different breathing characteristics belong correspond to different breathing characteristic scores, and the breathing characteristic scores can be accurately determined based on the second correspondence between the pre-stored breathing ranges and the characteristic scores.

[0119] The comprehensive score is determined based on the image feature score and the biometric score. The specific process is as follows:

[0120] In some embodiments, step 1022 includes:

[0121] Step 10221, determine the image feature weights and biometric feature weights.

[0122] Step 10222: multiply the image feature score and the image feature weight to obtain a comprehensive image feature score.

[0123] Step 10223, multiplying the biometric score and the biometric weight to obtain a comprehensive biometric score.

[0124] Step 10224, summing the image feature comprehensive score and the biometric feature comprehensive score to obtain a comprehensive score.

[0125] In specific implementation, the image feature weights include behavior feature weights and expression feature weights, and the biometric feature weights include heart rate feature weights and breathing feature weights.

[0126] Determine the behavioral feature weight, facial expression feature weight, heart rate feature weight, and respiratory feature weight. Multiply the behavioral feature score and the behavioral feature weight to obtain a comprehensive behavioral feature score. Multiply the facial expression feature score and the facial expression feature weight to obtain a comprehensive facial expression feature score. Multiply the heart rate feature score and the heart rate feature weight to obtain a comprehensive heart rate feature score. Multiply the respiratory feature score and the respiratory feature weight to obtain a comprehensive respiratory feature score. Sum the behavioral feature comprehensive score, the facial expression comprehensive score, the heart rate comprehensive score, and the respiratory comprehensive score to obtain a comprehensive score.

[0127] For example, the weight of behavior feature is 0.5, the weight of expression feature is 0.3, the weight of heart rate feature is 0.4, and the weight of breathing feature is 0.3. Then the comprehensive score = 0.5 × behavior feature score + 0.3 × expression feature score + 0.4 × heart rate feature score + 0.3 × breathing feature score.

[0128] Through the above scheme, based on the behavioral feature weights, facial expression feature weights, heart rate feature weights and breathing feature weights, the weighted summed comprehensive score can be accurately obtained, making the obtained comprehensive score more accurate, so that it is possible to accurately judge whether an emergency has occurred in the car based on the comprehensive score, avoiding misjudgment of emergency events.

[0129] Through the above embodiments, the characteristic information of the driver and passengers is obtained. According to the characteristic information of the driver and passengers, it is possible to accurately determine that an emergency event has occurred in the car, and by triggering the emergency response function, it is possible to transmit a distress message to people outside the car in a preset emergency response manner, thereby avoiding the situation where people inside the car are unable to seek help from the outside world in an emergency, and at the same time, it is convenient for people outside the car to be informed of the emergency situation in the car in a timely manner.

[0130] It should be noted that the embodiments of the present disclosure may be further described in the following manner:

[0131] The embodiments of the present disclosure are intended to solve the problem that the current vehicle glass cannot transmit the distress information inside the vehicle to the outside of the vehicle in an emergency. By integrating computer vision technology, biometric sensors, liquid crystal dimming glass, and external speakers and alarm systems, real-time monitoring of the situation inside the vehicle is achieved. When an emergency is detected, the transparency of the glass is immediately adjusted, the distress information is played, the external lights of the vehicle are flashed, and an alarm sound is sounded, thereby improving the safety of passengers in the vehicle and the rescue efficiency in an emergency.

[0132] 1. Specific implementation steps

[0133] Figure 2 FIG. 1 is a flow chart of a method for triggering a vehicle emergency response according to an embodiment of the present disclosure. Figure 2 As shown, the system starts; the camera and biosensor collect real-time data; computer vision data processing includes: behavior feature extraction, scoring the behavior features to obtain a behavior feature score; expression feature extraction, scoring the expression features to obtain an expression feature score; biosensor data processing includes: heart rate feature extraction, scoring the heart rate feature to obtain a heart rate feature score; breathing feature extraction, scoring the breathing feature to obtain a breathing feature score; determining a comprehensive score based on the behavior feature score, the expression feature score, the heart rate feature score and the breathing feature score; performing a score threshold judgment, and when the comprehensive score does not exceed the preset score threshold, continuing monitoring; when the comprehensive score exceeds the preset score threshold, controlling the liquid crystal glass to become transparent, controlling the speaker to play the sound inside the car, controlling the warning light to flash, transmitting a distress message to the outside of the car, and the system recording data at the same time.

[0134] 2. Installation location

[0135] (1) Camera

[0136] Device selection: Use a high-definition, wide-angle camera with infrared night vision to ensure that the situation inside the car can be clearly captured in all light conditions.

[0137] Installation location: The camera is installed near the central rearview mirror at the front of the car and in the center of the rear seat, covering the entire area of ​​the car to ensure no blind spot monitoring.

[0138] Control logic: The camera is connected to the vehicle's central control system, continuously records real-time video, and transmits the video stream to the computer vision processing unit.

[0139] (2) Intelligent LCD dimming glass

[0140] 1) Liquid crystal dimming glass principle: Liquid crystal dimming glass is a technology that changes the transparency of glass under the action of an electric field by embedding liquid crystal materials in the glass. When the electric field is applied, the liquid crystal molecules are arranged neatly and the glass is transparent; when the electric field is turned off, the liquid crystal molecules are arranged disorderly and the glass becomes opaque.

[0141] 2) Glass structure: Liquid crystal dimming glass usually consists of a multi-layer structure, including two glass layers and a liquid crystal layer sandwiched in between. The liquid crystal layer is usually composed of polymer dispersed liquid crystal (PDLC).

[0142] 3) Control mechanism: Liquid crystal dimming glass adjusts transparency through electrical control. The control system applies voltage to the liquid crystal layer, making the liquid crystal dimming glass respond quickly and switch between transparent and opaque states.

[0143] 4) In-vehicle control logic: The camera and liquid crystal dimming glass are connected through the vehicle central control system, and the transparency of the liquid crystal dimming glass is intelligently adjusted according to the camera's detection results.

[0144] (3) Biosensors

[0145] Device selection: Choose high-precision heart rate sensors and breathing sensors that can accurately capture physiological data and have anti-interference capabilities.

[0146] Installation location: The heart rate sensor is embedded in the seat back and steering wheel, and the breathing sensor is installed on the seat back or under the seat to ensure closeness to the passenger's body.

[0147] Control logic: The sensor is connected to the vehicle central control system wirelessly or wired, and transmits physiological data to the data processing unit in real time.

[0148] (4) External speakers and alarm system

[0149] Device selection: Waterproof and dustproof high-volume speakers and high-brightness exterior warning lights ensure effective operation in all environments.

[0150] Installation location: The speakers are installed at the front and rear of the vehicle, and the warning lights are installed on the roof and the four corners of the vehicle body to ensure that the warning signal can be transmitted in all directions.

[0151] Control logic: The speakers and warning lights are connected to the vehicle's central control system, and automatically start after an emergency event is detected, playing sounds inside the vehicle and flashing warning lights.

[0152] 3. Object detection model development

[0153] (1) Data preparation: A large amount of video data of vehicle occupants in various scenarios is collected while protecting user privacy, and used as the initial sample image data of the occupants. The initial sample image data includes data of normal scenes and emergency events (such as car accidents, violent incidents, etc.). The data sources include at least one of the following: simulation experiments, real accident videos, and public data sets.

[0154] (2) Data processing: Preprocess the collected initial sample image data to obtain target sample image data. The preprocessing includes at least one of the following: denoising, cropping and enhancement. Denoising can be performed using a convolutional neural network (CNN) for image noise reduction, and cropping and enhancement can be performed using an image processing library (such as OpenCV).

[0155] (3) Data labeling: Label the preprocessed target sample image data to obtain labeled sample image data. The labeling content includes normal status and various emergency events to ensure that the target detection model can accurately identify different scenarios. Use semi-automatic labeling tools combined with expert manual proofreading to improve labeling efficiency and accuracy.

[0156] (4) Model training: The YOLO V4 target detection algorithm is used to train the original detection model to obtain a trained target detection model. During the model training process, a large amount of labeled sample image data is used to perform multiple rounds of iterative training and verification to optimize the detection accuracy and speed of the model.

[0157] (5) Model deployment: Deploy the trained object detection model in the control system inside the vehicle. Use embedded hardware (such as NVIDIA Jetson Nano or Raspberry Pi) to perform real-time inference of the model to ensure that the system runs with low latency and high accuracy.

[0158] 4. Comprehensively judge emergency events in the car

[0159] (1) Data Collection

[0160] 1) Computer Vision Data

[0161] Camera: Capture the in-car video stream in real time, remove noise through preprocessing and then input it into the target detection model.

[0162] Target detection model: Use the trained target detection model to analyze the video stream and extract behavioral features, such as passengers’ sitting posture, movements, and facial expressions.

[0163] Behavior classification: The target detection model outputs behavior classification results, including normal behavior and abnormal behavior (such as sudden fainting, quarreling, struggling, etc.).

[0164] 2) Biosensor data

[0165] Heart rate sensor: monitors passengers’ heart rate in real time and collects heart rate data.

[0166] Respiratory sensor: monitors passengers' breathing rate in real time and collects respiratory data.

[0167] Physiological data analysis: Set the normal physiological parameter range, and mark it as abnormal when the heart rate or breathing rate exceeds the range.

[0168] (2) Data processing and feature extraction

[0169] 1) Computer Vision Features

[0170] Behavioral features: Extract behavioral features, such as passengers’ movement trajectories, posture changes, etc.

[0171] Expression features: Extract passengers’ facial expression features and analyze their emotional states.

[0172] 2) Biosensor characteristics

[0173] Heart rate characteristics: calculate the average, maximum, minimum, fluctuation, etc. of the heart rate.

[0174] Respiratory characteristics: Calculate the average value and fluctuation of respiratory frequency, etc.

[0175] (3) Anomaly detection and scoring mechanism

[0176] 1) Computer Vision Anomaly Detection

[0177] Behavior scoring: According to the classification results of behavioral characteristics, risk scores for different behaviors are set. For example, normal behavior is scored as 0 points, and abnormal behaviors such as fainting and quarreling are set with higher risk scores (such as 70 points, 90 points).

[0178] Expression score: According to the analysis results of expression characteristics, risk scores for different emotional states are set. For example, a normal expression score is 0 points, and expressions such as fear and pain are set with higher risk scores (such as 50 points, 80 points).

[0179] 2) Biosensor anomaly detection

[0180] Heart rate score: Set the heart rate abnormality threshold. When the heart rate exceeds the normal heart rate range, set the risk score according to the degree of the excess. For example, if the heart rate exceeds the normal heart rate range by 10%, it is set to 50 points, and if it exceeds the normal heart rate range by 20%, it is set to 80 points.

[0181] Respiratory score: Set the abnormal respiratory rate threshold. When the respiratory rate exceeds the normal respiratory range, set the risk score according to the degree of exceeding the normal respiratory range. For example, if the respiratory rate exceeds the normal respiratory range by 10%, it is set to 50 points, and if it exceeds the normal respiratory range by 20%, it is set to 80 points.

[0182] (4) Data fusion and weighted judgment

[0183] 1) Weight setting

[0184] Computer vision weight: According to experimental data and actual application scenarios, the weight of computer vision is set (for example, the weight of behavioral features is 0.5, and the weight of expression features is 0.3).

[0185] Biosensor weights: Set the weights of biosensors based on experimental data and actual application scenarios (for example, heart rate feature weight 0.4, breathing feature weight 0.3).

[0186] 2) Comprehensive score calculation

[0187] Comprehensive score of behavioral characteristics: behavioral characteristics score * behavioral characteristics weight.

[0188] Comprehensive score of expression features: expression feature score * expression feature weight.

[0189] Comprehensive score of heart rate characteristics: heart rate characteristic score*heart rate characteristic weight.

[0190] Comprehensive score of respiratory characteristics: respiratory characteristic score*respiratory characteristic weight.

[0191] 3) Comprehensive score calculation

[0192] Comprehensive score = comprehensive score of behavioral characteristics + comprehensive score of expression characteristics + comprehensive score of heart rate characteristics + comprehensive score of breathing characteristics.

[0193] (5) Decision logic

[0194] 1) Threshold setting

[0195] The emergency event threshold of the comprehensive score is set based on experiments and actual applications (for example, a comprehensive score exceeding 70 points is considered an emergency event).

[0196] 2) Emergency judgment

[0197] When the comprehensive score exceeds the set emergency event threshold, the system determines that an emergency is occurring in the car and triggers emergency response measures (such as dimming glass becoming transparent, speakers playing sound, warning lights flashing, etc.); if the comprehensive score does not exceed the emergency event threshold, the system considers the situation in the car to be normal and maintains the current status.

[0198] 5. Overall control logic

[0199] (1) Initialization: After the system is started, the camera, biometric sensor, LCD dimming glass, speaker and warning light enter the standby state.

[0200] (2) Real-time monitoring: Cameras and biosensors monitor the situation inside the vehicle in real time and transmit the data to the central control system of the vehicle.

[0201] (3) Emergency event detection: The vehicle central control system analyzes the video stream and physiological data to determine whether an emergency event has occurred.

[0202] (4) Emergency response: If an emergency is detected, the vehicle's central control system immediately triggers the liquid crystal dimming glass to become transparent, starts the external speakers to play the sounds inside the vehicle, and flashes the warning lights.

[0203] (5) Transmission of distress information: Transmit distress information to people outside the vehicle through transparent glass, external sound and warning lights to attract attention.

[0204] (6) Status recovery: When the emergency is resolved, the system returns to normal, the LCD dimming glass returns to opacity, and the speaker and warning light stop working.

[0205] Beneficial effects of the embodiments of the present disclosure:

[0206] (1) Balancing privacy protection and emergency rescue: Under normal circumstances, the liquid crystal dimming glass remains opaque to protect the privacy of passengers in the car; in an emergency, the glass automatically adjusts to a transparent state to ensure that the rescue information is transmitted in a timely manner.

[0207] (2) Automated detection and response: Through biometric sensors and computer vision technology, in-vehicle emergency events can be automatically detected without human intervention, greatly improving the efficiency and accuracy of the transmission of distress information.

[0208] (3) Multi-directional distress information transmission: In addition to visual signals, distress information is also transmitted through sound and light signals, ensuring that people outside the vehicle can promptly detect emergency situations inside the vehicle.

[0209] (4) Improving passenger safety: It effectively solves the problem of passengers in the car asking for help in emergency situations, significantly improves passenger safety and rescue efficiency, and reduces life and health threats and property losses caused by untimely information transmission.

[0210] It should be noted that the method of the embodiment of the present disclosure can be performed by a single device, such as a computer or a server. The method of the present embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present disclosure, and the multiple devices will interact with each other to complete the described method.

[0211] It should be noted that the above describes some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0212] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present disclosure also provides a triggering device for a vehicle function.

[0213] refer to Figure 3 , the triggering device of the vehicle function comprises:

[0214] An acquisition module 301 is configured to acquire characteristic information of a driver or passenger;

[0215] The control module 302 is configured to determine that an emergency event has occurred in the vehicle based on the characteristic information, and transmit a distress message to people outside the vehicle in a preset emergency response manner by triggering an emergency response function.

[0216] In some embodiments, the control module 302 includes:

[0217] The first control unit is configured to control the liquid crystal dimming glass to switch from an opaque state to a transparent state by triggering an emergency response function, so as to transmit a distress message to people outside the vehicle;

[0218] and / or,

[0219] The second control unit is configured to trigger an emergency response function, obtain the sound inside the vehicle, and play the sound inside the vehicle through a speaker to transmit a distress message to people outside the vehicle;

[0220] and / or,

[0221] The third control unit is configured to trigger the emergency response function to control the flashing of the warning lights outside the vehicle to transmit a distress message to people outside the vehicle.

[0222] In some embodiments, the first control unit includes:

[0223] A position determination subunit configured to determine the position of a driver or passenger in an emergency state when an emergency occurs in the vehicle;

[0224] The first control subunit is configured to control the liquid crystal dimming glass of the vehicle window corresponding to the position of the driver and passenger in the emergency state to switch from an opaque state to a transparent state.

[0225] In some embodiments, the first control unit includes:

[0226] The vehicle interior light intensity acquisition subunit is configured to acquire the vehicle interior light intensity;

[0227] A transparency determination subunit, configured to determine the transparency of the liquid crystal dimming glass based on the light intensity inside the vehicle;

[0228] The first control subunit is configured to control the liquid crystal dimming glass to switch from an opaque state to a transparent state according to the transparency.

[0229] In some embodiments, the first control unit includes:

[0230] The vehicle exterior brightness acquisition subunit is configured to acquire the vehicle exterior brightness;

[0231] The first control subunit is configured to control the interior lighting to turn on while controlling the liquid crystal dimming glass to switch from an opaque state to a transparent state in response to determining that the exterior brightness of the vehicle is less than a preset brightness threshold.

[0232] In some embodiments, the feature information includes: image features and biometric features;

[0233] The control module 302 includes:

[0234] a scoring unit configured to score the image feature to obtain an image feature score, and score the biometric feature to obtain a biometric feature score;

[0235] a comprehensive score determination unit configured to determine a comprehensive score based on the image feature score and the biometric feature score;

[0236] The emergency event determination unit is configured to determine that an emergency event occurs in the vehicle in response to the comprehensive score being greater than a preset score threshold.

[0237] In some embodiments, the image features include: behavioral features and expression features;

[0238] The scoring unit comprises:

[0239] A behavior classification subunit is configured to classify the behavior features based on a pre-trained behavior detection model to obtain a behavior classification result;

[0240] A behavior scoring subunit is configured to score the behavior feature based on the behavior classification result to obtain a behavior feature score;

[0241] The expression classification subunit is configured to classify the expression features based on a pre-trained expression detection model to obtain an expression classification result;

[0242] The expression scoring subunit is configured to score the expression feature based on the expression classification result to obtain an expression feature score.

[0243] In some embodiments, the biometric features include: heart rate features and breathing features;

[0244] The scoring unit comprises:

[0245] a target heart rate range determination subunit, configured to determine a target heart rate range to which the heart rate feature belongs;

[0246] a heart rate scoring subunit, configured to determine a heart rate characteristic score corresponding to the target heart rate range based on a pre-stored first correspondence between the heart rate range and the characteristic score;

[0247] a target breathing range determination subunit, configured to determine a target breathing range to which the breathing feature belongs;

[0248] The breathing scoring subunit is configured to determine the breathing feature score corresponding to the target breathing range based on a pre-stored second correspondence between the breathing range and the feature score.

[0249] For the convenience of description, the above device is described by dividing it into various modules according to its functions. Of course, when implementing the present disclosure, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0250] The device of the above embodiment is used to implement the triggering method of the corresponding vehicle function in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0251] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the triggering method of the vehicle function described in any of the above embodiments is implemented.

[0252] Figure 4 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0253] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0254] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0255] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0256] The communication interface 1040 is used to connect a communication module (not shown in the figure) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB (Universal Serial Bus), network cable, etc.), or through a wireless mode (such as mobile network, WIFI (Wireless Fidelity, wireless network communication technology), Bluetooth, etc.).

[0257] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0258] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0259] The electronic device of the above-mentioned embodiment is used to implement the triggering method of the corresponding vehicle function in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0260] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present disclosure also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the triggering method of the vehicle function as described in any of the above embodiments.

[0261] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0262] The computer instructions stored in the storage medium of the above embodiments are used to enable the computer to execute the vehicle function triggering method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0263] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides a vehicle, including a triggering device, or an electronic device, or a storage medium for the vehicle function in the above-mentioned embodiments, and the vehicle equipment implements the triggering method for the vehicle function described in any of the above embodiments.

[0264] The vehicle of the above-mentioned embodiment is used to implement the triggering method of the vehicle function described in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0265] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present disclosure is limited to these examples. Based on the concept of the present disclosure, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present disclosure as described above, which are not provided in detail for the sake of simplicity.

[0266] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present disclosure difficult to understand, the known power / ground connections to the integrated circuit (IC) chips and other components may or may not be shown in the provided figures. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present disclosure difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present disclosure will be implemented (that is, these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present disclosure, it is apparent to those skilled in the art that the embodiments of the present disclosure can be implemented without these specific details or with changes in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0267] Although the present disclosure has been described in conjunction with specific embodiments of the present disclosure, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0268] The embodiments of the present disclosure are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the present disclosure. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A method for triggering a vehicle function, characterized in that: The method comprises: Obtaining characteristic information of drivers and passengers; An emergency event is determined to have occurred in the vehicle based on the characteristic information, and an emergency response function is triggered to transmit a distress message to people outside the vehicle in a preset emergency response manner.

2. The method according to claim 1, characterized in that The triggering of the emergency response function to transmit the distress information to the personnel outside the vehicle in accordance with the preset emergency response method includes: By triggering the emergency response function, the liquid crystal dimming glass is controlled to switch from an opaque state to a transparent state, transmitting a distress message to people outside the vehicle; and / or, By triggering the emergency response function, the sound inside the car is acquired and played out through the speaker to transmit a distress message to people outside the car; and / or, By triggering the emergency response function, the warning lights outside the vehicle are controlled to flash, sending a distress message to people outside the vehicle.

3. The method according to claim 2, characterized in that The controlling the liquid crystal dimming glass to switch from an opaque state to a transparent state comprises: Determine the location of the driver and passengers in an emergency situation when an emergency occurs in the vehicle; The liquid crystal dimming glass of the vehicle window corresponding to the position of the driver and passenger in the emergency state is controlled to switch from an opaque state to a transparent state.

4. The method according to claim 2, characterized in that: The controlling the liquid crystal dimming glass to switch from an opaque state to a transparent state comprises: Get the light intensity inside the car; Determining the transparency of the liquid crystal dimming glass based on the light intensity inside the vehicle; According to the transparency, the liquid crystal dimming glass is controlled to switch from an opaque state to a transparent state.

5. The method according to claim 2, characterized in that: The controlling the liquid crystal dimming glass to switch from an opaque state to a transparent state comprises: Get the brightness outside the vehicle; In response to determining that the brightness outside the vehicle is less than a preset brightness threshold, the interior lighting is controlled to turn on while controlling the liquid crystal dimming glass to switch from an opaque state to a transparent state.

6. The method according to claim 1, characterized in that The feature information includes: image features and biometric features; The determining, based on the characteristic information, that an emergency event occurs in the vehicle includes: Scoring the image feature to obtain an image feature score, and scoring the biometric feature to obtain a biometric feature score; determining a combined score based on the image feature score and the biometric score; In response to the comprehensive score being greater than a preset score threshold, it is determined that an emergency occurs in the vehicle.

7. The method according to claim 6, characterized in that The image features include: behavioral features and expression features; Scoring the image feature to obtain an image feature score includes: Classify the behavior features based on a pre-trained behavior detection model to obtain a behavior classification result; Based on the behavior classification result, scoring the behavior characteristics to obtain a behavior characteristic score; Classify the expression features based on a pre-trained expression detection model to obtain an expression classification result; Based on the expression classification result, the expression feature is scored to obtain an expression feature score.

8. The method according to claim 6, characterized in that The biological characteristics include: heart rate characteristics and breathing characteristics; Scoring the biometric feature to obtain a biometric feature score includes: Determine a target heart rate range to which the heart rate characteristic belongs; Determining a heart rate characteristic score corresponding to the target heart rate range based on a pre-stored first correspondence between the heart rate range and the characteristic score; determining a target breathing range to which the breathing characteristic belongs; Based on a pre-stored second correspondence between the breathing range and the feature score, a breathing feature score corresponding to the target breathing range is determined.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 8 is implemented.

10. A vehicle, characterized in that: An electronic device comprising the electronic device described in claim 9.

Images