A helmet-based emergency rescue implementation method and device

Abstract

This application provides a helmet-based emergency rescue method and apparatus, applied to a target helmet, which includes a driver state sensor and a processing unit. The method includes: using a state recognition model deployed on the processing unit to infer the real-time driver signals collected by the driver state sensor to determine the driver state category; determining the corresponding execution operation type based on the driver state category and generating a corresponding execution operation signal; and sending the execution operation signal to the vehicle's control unit via a communication module deployed on the target helmet, so that the vehicle's control unit can execute the corresponding operation. This application can accurately identify various driver states, improving the accuracy and reliability of driver state recognition.

Description

Technical Field

[0001] This application relates to the field of vehicle driving technology, and more specifically, to a helmet-based emergency rescue method and device. Background Technology

[0002] The emergency rescue function of smart helmets is a product of the integration of the Internet of Things, wearable devices, and traffic safety technologies. It aims to provide independent and automated collision detection and distress services for motorcyclists, cyclists, and special operations personnel (such as firefighters and construction workers), filling the safety gaps in "person-vehicle separation" scenarios that vehicle systems cannot cover.

[0003] Currently, the emergency rescue function of helmets mainly relies on the detection and identification of traditional sensors.

[0004] However, the current methods for implementing emergency rescue functions in helmets are limited by traditional sensors, allowing only simple functions and generally low accuracy and reliability in recognizing brainwave signals. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide a helmet-based emergency rescue method and device. By equipping the helmet with a driver state sensor and a processing unit, the processing unit uses a state recognition model to infer the driver state category from the real-time signals collected by the driver state sensor, and generates an execution operation signal corresponding to the driver state category, which is sent to the vehicle to trigger the corresponding operation. This can accurately identify various driver states and improve the accuracy and reliability of driver state recognition.

[0006] In a first aspect, embodiments of this application provide a helmet-based emergency rescue method, applied to a target helmet, the target helmet including a driver status sensor and a processing unit; the method includes: The driver's state category is determined by reasoning from the real-time signals collected by the driver's state sensor using the state recognition model deployed on the processing unit. The corresponding operation type is determined based on the driver's state category, and a corresponding operation signal is generated. The operation signal is sent to the vehicle's infotainment system via a communication module located on the target helmet, so that the corresponding operation can be performed by the vehicle's infotainment system.

[0007] In one possible implementation, the driver state sensor is a brainwave sensor, and the driver's real-time signal is a brainwave signal; the brainwave sensor is a non-contact electromagnetic field perturbation type brainwave sensing component; the internal structure of the target helmet is equipped with multiple signal generators and multiple signal receivers to construct an electromagnetic field environment covering the driver's head; the brainwave sensor collects the driver's brainwave signal through the following steps: The signal generator generates an electromagnetic field signal of a preset frequency, and the signal receiver receives the electromagnetic field signal after it passes through the driver's head area. The processing unit detects the changes in the electromagnetic field signal caused by the driver's brainwave activity, and indirectly obtains the driver's brainwave signal based on the changes.

[0008] In one possible implementation, the state recognition model is an edge-side inference model deployed on the processing unit after model distillation; the state recognition model is obtained through the following steps: The brainwave sensor collects brainwave signal samples of the driver in various riding scenarios, and establishes a brainwave signal database in the cloud based on the brainwave signal samples; wherein, the riding scenarios include at least normal riding, fatigued driving and accident collision scenarios; Based on the brainwave signal database, brainwave frequency domain features corresponding to different driver states are extracted, and a basic state recognition model is trained based on the brainwave frequency domain features; wherein, the brainwave frequency domain features include the differences in power spectral density distribution of alpha waves, beta waves and theta waves; The basic state recognition model is subjected to knowledge distillation, and the model is trimmed and compressed for the state classification function in the cycling scenario to obtain a state recognition model adapted to the computing power constraints of the processing unit; wherein, the state recognition model is an edge-side inference model.

[0009] In one possible implementation, the driver status category includes normal status, awaiting rescue status, and executing command status; the step of determining the corresponding execution operation type based on the driver status category and generating the corresponding execution operation signal includes: When the driver's state category is normal, the vehicle's current operating mode is maintained and no additional operations are performed; When the driver's status category is "awaiting rescue", an emergency rescue signal is generated; When the driver's state category is executing a command, an action execution signal is generated.

[0010] In one possible implementation, the execution command state includes a steering intention command issued by the driver via brainwave signals; the generation of the action execution signal includes: The driver's steering intention command is identified by the state recognition model to obtain the driver's steering intention brainwave pattern; wherein, the steering intention brainwave pattern is a left turn intention brainwave pattern or a right turn intention brainwave pattern. The corresponding turn signal is generated based on the brainwave pattern of the identified turning intention.

[0011] In one possible implementation, the target helmet and the vehicle-mounted system transmit data bidirectionally via a Bluetooth communication link; the method further includes: When the vehicle's infotainment system receives an emergency rescue signal, it sends the signal to the cloud-based rescue platform via the vehicle's mobile communication module. When the target helmet detects an interruption in its Bluetooth communication link with the vehicle's infotainment system, it sends an emergency rescue signal directly to the cloud-based rescue platform via its own mobile communication module.

[0012] In one possible implementation, when the driver's status category is "awaiting rescue," the corresponding operation includes: The driver's status is reconfirmed. If no cancellation command is received from the driver within a preset time window, the real-time positioning information and collision detection data of the target helmet are obtained. The communication module sends a rescue notification containing the location information to a preset emergency contact. The location information and collision detection data are simultaneously uploaded to the cloud-based rescue platform to initiate a corresponding emergency rescue service request.

[0013] Secondly, embodiments of this application also provide a helmet-based emergency rescue device, applied to a target helmet, the target helmet including a driver status sensor and a processing unit; the device includes: The identification module is used to infer the driver's real-time signals collected by the driver's state sensor through the state identification model deployed on the processing unit, and determine the driver's state category. The decision module is used to determine the corresponding operation type based on the driver's state category and generate the corresponding operation signal; The execution module is used to send the execution operation signal to the vehicle's control unit through the communication module arranged on the target helmet, so that the vehicle's control unit can perform the corresponding operation.

[0014] In one possible implementation, the driver state sensor is a brainwave sensor, and the driver's real-time signal is a brainwave signal; the brainwave sensor is a non-contact electromagnetic field perturbation type brainwave sensing component; the internal structure of the target helmet is equipped with multiple signal generators and multiple signal receivers to construct an electromagnetic field environment covering the driver's head; the brainwave sensor collects the driver's brainwave signal through the following steps: The receiving module is used to generate an electromagnetic field signal of a preset frequency through the signal generator and to receive the electromagnetic field signal after it passes through the driver's head area through the signal receiver. The acquisition module is used to detect the changes in the electromagnetic field signal after it is disturbed by the driver's brainwave activity through the processing unit, and to indirectly acquire the driver's brainwave signal based on the changes in the electromagnetic field signal.

[0015] In one possible implementation, the state recognition model is an edge-side inference model deployed on the processing unit after model distillation; the state recognition model is obtained through the following steps: The module is used to collect brainwave signal samples of the driver in various cycling scenarios through the brainwave sensor, and to build a brainwave signal database in the cloud based on the brainwave signal samples; wherein, the cycling scenarios include at least normal cycling, fatigued driving and accident collision scenarios. The training module is used to extract brainwave frequency domain features corresponding to different driver states based on the brainwave signal database, and to train a basic state recognition model based on the brainwave frequency domain features; wherein, the brainwave frequency domain features include the differences in power spectral density distribution of alpha waves, beta waves and theta waves; The distillation module is used to perform knowledge distillation on the basic state recognition model and to trim and compress the model for the state classification function in the cycling scenario, so as to obtain a state recognition model adapted to the computing power constraints of the processing unit; wherein, the state recognition model is an edge-side inference model.

[0016] In one possible implementation, the driver status categories include normal status, awaiting rescue status, and executing command status; the decision module is specifically used for: When the driver's state category is normal, the vehicle's current operating mode is maintained and no additional operations are performed; When the driver's status category is "awaiting rescue", an emergency rescue signal is generated; When the driver's state category is executing a command, an action execution signal is generated.

[0017] In one possible implementation, the execution command state includes a steering intention command issued by the driver via brainwave signals; the decision module is specifically used for: The driver's steering intention command is identified by the state recognition model to obtain the driver's steering intention brainwave pattern; wherein, the steering intention brainwave pattern is a left turn intention brainwave pattern or a right turn intention brainwave pattern. The corresponding turn signal is generated based on the brainwave pattern of the identified turning intention.

[0018] In one possible implementation, the target helmet and the vehicle-mounted system transmit data bidirectionally via a Bluetooth communication link; the device further includes: The first sending module is used to send an emergency rescue signal to the cloud rescue platform through the vehicle's mobile communication module after the vehicle receives the emergency rescue signal. The second sending module is used to send an emergency rescue signal directly to the cloud rescue platform through the mobile communication module configured on the target helmet itself when the target helmet detects that the Bluetooth communication link with the vehicle is interrupted.

[0019] In one possible implementation, the execution module is specifically used for: When the driver's status category is "awaiting rescue", the driver's status is reconfirmed. If no cancellation instruction is received from the driver within a preset time window, the real-time positioning information and collision detection data of the target helmet are obtained. The communication module sends a rescue notification containing the location information to a preset emergency contact. The location information and collision detection data are simultaneously uploaded to the cloud-based rescue platform to initiate a corresponding emergency rescue service request.

[0020] Thirdly, embodiments of this application provide an electronic device, including: a processor, a storage medium, and a bus. The storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the helmet-based emergency rescue implementation method as described in any of the first aspects.

[0021] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the helmet-based emergency rescue implementation method described in any one of the first aspects.

[0022] This application provides a helmet-based emergency rescue method and device. By using a state recognition model deployed on a processing unit to infer the real-time signals of the driver collected by the driver's state sensor, the method determines the driver's state category. Based on the driver's state category, it determines the corresponding execution operation type and generates a corresponding execution operation signal. This execution operation signal is then sent to the vehicle's control unit via a communication module deployed on the target helmet, allowing the vehicle to execute the corresponding operation. This application, by configuring a driver state sensor and processing unit on the helmet, and using the state recognition model deployed on the processing unit to infer the driver's state category from the real-time signals collected by the driver's state sensor, generates an execution operation signal corresponding to the driver's state category and sends it to the vehicle's control unit to trigger the corresponding operation, can accurately identify various driver states, improving the accuracy and reliability of driver state recognition.

[0023] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a helmet-based emergency rescue implementation method provided in the embodiments of this application; Figure 2 This is a structural diagram of the target helmet; Figure 3 This is a schematic diagram of the emergency rescue process based on a helmet; Figure 4 This is a schematic diagram of the structure of a helmet-based emergency rescue device provided according to an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0027] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0028] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0029] Considering the emergency rescue function of smart helmets, they are a product of the integration of the Internet of Things, wearable devices, and traffic safety technologies. They aim to provide independent and automated collision detection and distress services for motorcyclists, cyclists, and special operations personnel (such as firefighters and construction workers), filling the safety gaps in "person-vehicle separation" scenarios that vehicle systems cannot cover.

[0030] Currently, the emergency rescue function of helmets mainly relies on the detection and identification of traditional sensors. However, the current methods for implementing emergency rescue functions in helmets are limited by traditional sensors, enabling only simple functions, and the accuracy and reliability of identifying brainwave signals are generally poor.

[0031] To address this issue, this application provides a helmet-based emergency rescue method and device. By equipping the helmet with a driver state sensor and a processing unit, the processing unit uses a state recognition model to infer the driver's real-time signals collected by the driver state sensor to determine the driver's state category, and generates an execution operation signal corresponding to the driver's state category, which is sent to the vehicle's infotainment system to trigger the corresponding operation. This method can accurately identify various driver states, improving the accuracy and reliability of driver state recognition.

[0032] Figure 1 This is a flowchart of a helmet-based emergency rescue implementation method provided according to an embodiment of this application.

[0033] It should be noted that the helmet-based emergency rescue implementation method of this application is applied to the target helmet, which includes a driver status sensor and a processing unit; for example, such as Figure 2 As shown, the helmet-side control unit represents the processing unit, and the brainwave sensor represents the driver's status sensor.

[0034] like Figure 1 As shown, the helmet-based emergency rescue implementation method of this application embodiment may specifically include: S101. By using the state recognition model deployed on the processing unit, the driver's real-time signals collected by the driver's state sensor are inferred to determine the driver's state category.

[0035] S102. Determine the corresponding execution operation type based on the driver's status category, and generate the corresponding execution operation signal.

[0036] S103. Send an operation signal to the vehicle's control unit via the communication module mounted on the target helmet, so that the corresponding operation can be performed by the vehicle's control unit.

[0037] In the above-mentioned helmet-based emergency rescue implementation method, by configuring a driver status sensor and a processing unit on the helmet, the driver status category is determined by reasoning the real-time signals of the driver collected by the driver status sensor through the status recognition model deployed on the processing unit, and the corresponding execution operation signal is generated and sent to the vehicle to trigger the corresponding operation. This can accurately identify various driver states and improve the accuracy and reliability of driver status recognition.

[0038] The exemplary steps described above in the embodiments of this application are illustrated below with specific examples: S101 uses the state recognition model deployed on the processing unit to infer the driver's real-time signals collected by the driver's state sensor and determine the driver's state category.

[0039] It should be noted that the state recognition model is an edge-side inference model deployed on the processing unit after model distillation. The state recognition model is obtained through the following steps: collecting brainwave signal samples of the driver in various cycling scenarios using a brainwave sensor, and establishing a brainwave signal database in the cloud based on these samples; extracting brainwave frequency domain features corresponding to different driver states based on the brainwave signal database, and training a basic state recognition model based on these features; performing knowledge distillation on the basic state recognition model, and tailoring and compressing the model for state classification in cycling scenarios to obtain a state recognition model adapted to the computing power constraints of the processing unit. For example, as... Figure 3 As shown, the cloud-based large model represents the state recognition model.

[0040] Among them, the cycling scenarios include at least normal cycling, fatigued driving, and accident collision scenarios; the brainwave frequency domain features include the differences in the power spectral density distribution of alpha waves, beta waves, and theta waves; and the state recognition model is an end-side inference model.

[0041] Specifically, a large database of brainwave signals is established based on brainwave signals. The brainwave signal data in the database is used to train the model running in the processing unit and perform targeted functional dehydration and pruning to improve the recognition of the driver's real-time number under normal conditions.

[0042] Among them, the driver status sensor is a brainwave sensor, and the driver's real-time signal is a brainwave signal; the brainwave sensor is a non-contact electromagnetic field disturbance type brainwave sensing component; multiple signal generators and multiple signal receivers are arranged in the internal structure of the target helmet to construct an electromagnetic field environment covering the driver's head.

[0043] In addition, the brainwave sensor collects the driver's brainwave signals through the following steps: generating an electromagnetic field signal of a preset frequency through a signal generator, receiving the electromagnetic field signal after it passes through the driver's head area through a signal receiver; detecting the changes in the electromagnetic field signal caused by the driver's brainwave activity through a processing unit, and indirectly obtaining the driver's brainwave signals based on the changes in the electromagnetic field signal.

[0044] Clearly, the brainwave sensor is a non-contact sensor, which does not need to be in direct contact with the driver's scalp. It indirectly collects brainwave signals through feedback from field disturbances in the electromagnetic field environment.

[0045] In this embodiment, the driver's state includes a normal state, a state awaiting rescue, and a state executing commands. The driver's state category is obtained by reasoning from the real-time signals collected by the driver's state sensors through the state recognition model deployed on the processing unit, and then processed accordingly.

[0046] Optionally, the state recognition model is deployed on the vehicle's infotainment system; the driver's real-time signals are identified through the state recognition model deployed on the vehicle's infotainment system to determine the driver's state category.

[0047] Specifically, the state recognition model can be deployed not only on the processing unit of the target helmet, but also on the vehicle's infotainment system. The state recognition model deployed on the vehicle's infotainment system can infer the driver's real-time signals collected by the driver's state sensors to determine the driver's state category.

[0048] S102, determine the corresponding operation type based on the driver's status category, and generate the corresponding operation signal.

[0049] In this embodiment, the execution operation signal includes emergency rescue signal and action execution signal. The corresponding execution operation type is determined by the driver status category in step S1O1, and the corresponding execution operation signal is generated for subsequent processing. For example, as Figure 3 As shown. In some implementations, when the driver's state category is normal, the vehicle's current operating mode is maintained and no additional operations are performed; when the driver's state category is awaiting rescue, an emergency rescue signal is generated; when the driver's state category is executing a command, an action execution signal is generated. The executing command state includes steering intention commands issued by the driver via brainwave signals.

[0050] Optionally, when generating the action execution signal, the driver's steering intention command is identified through the state recognition model to obtain the driver's steering intention brainwave pattern; and the corresponding turn signal control signal is generated based on the identified steering intention brainwave pattern.

[0051] The brainwave pattern for turning intention is either a left turn intention brainwave pattern or a right turn intention brainwave pattern. The left turn intention brainwave pattern controls the left turn signal to process the turning signal, while the right turn intention brainwave pattern controls the right turn signal to process the turning signal.

[0052] S103 sends an operation signal to the vehicle's infotainment system via a communication module mounted on the target helmet, so that the vehicle's infotainment system can perform the corresponding operation.

[0053] In this embodiment, the operations performed include at least emergency rescue and action execution; the communication module mounted on the target helmet sends an operation signal to the vehicle's infotainment system, which then executes the corresponding operation. For example, Figure 3 As shown.

[0054] In some implementations, the turn signal control signal is sent to the vehicle's infotainment system via a communication module located on the target helmet, so that the vehicle's infotainment system can control the turn signal in the corresponding direction to perform the corresponding operation.

[0055] It should be noted that communication modules, such as 4G / 5G modules, can be installed inside the target helmet, allowing the helmet to initiate a rescue call directly when faced with an emergency rescue signal. Alternatively, they can be installed inside the vehicle's infotainment system, allowing the helmet to send signals to the system to enable and command it to initiate emergency rescue operations.

[0056] The helmet-based emergency rescue method provided in this application uses a state recognition model deployed on a processing unit to infer the real-time signals of the driver collected by the driver's state sensor, determine the driver's state category, determine the corresponding execution operation type based on the driver's state category, generate a corresponding execution operation signal, and send the execution operation signal to the vehicle's control unit through a communication module deployed on the target helmet, so that the vehicle's control unit can execute the corresponding operation. This helmet-based emergency rescue method, by configuring a driver state sensor and a processing unit on the helmet, and using the state recognition model deployed on the processing unit to infer the driver's state category from the real-time signals collected by the driver's state sensor, generates an execution operation signal corresponding to the driver's state category and sends it to the vehicle's control unit to trigger the corresponding operation, can accurately identify various driver states, improving the accuracy and reliability of driver state recognition.

[0057] Furthermore, the target helmet and the vehicle's infotainment system transmit data bidirectionally via a Bluetooth communication link. When the vehicle's infotainment system receives an emergency rescue signal, it sends the emergency rescue signal to the cloud rescue platform through the vehicle's mobile communication module. When the target helmet detects that the Bluetooth communication link with the vehicle's infotainment system is interrupted, it sends the emergency rescue signal directly to the cloud rescue platform through the mobile communication module configured on the target helmet itself.

[0058] In some implementations, when the driver's status is classified as pending rescue, the corresponding operations include: performing a secondary confirmation of the driver's status; if no cancellation instruction is received from the driver within a preset time window, obtaining the real-time location information and collision detection data of the target helmet; sending a rescue notification containing location information to a preset emergency contact via the communication module; and simultaneously uploading the location information and collision detection data to the cloud rescue platform to initiate a corresponding emergency rescue service request.

[0059] Furthermore, the target helmet includes an eye-tracking camera; it collects and identifies the driver's eye movement data to determine the driver's gaze direction; and sends the driver's gaze direction to the vehicle's infotainment system, enabling the system to perform corresponding operations based on the gaze direction. The gaze direction includes at least looking left and looking right.

[0060] Optionally, when performing corresponding operations based on the gaze direction, the gaze direction of the driver and the direction of the target device of the vehicle are kept consistent; through the vehicle-mounted computer, the target device is controlled based on the gaze direction to turn the target device towards the gaze direction of the driver. Among them, the target device at least includes headlights and a driving recorder, and the headlights and the driving recorder are configured with a follow-up system.

[0061] Specifically, through the vehicle-mounted computer, the target device is controlled based on the gaze direction to turn the target device towards the gaze direction of the driver. The camera follow-up mechanism of the driving recorder is controlled through the vehicle-mounted computer to move the camera of the driving recorder towards the gaze direction of the driver.

[0062] In summary, adding an eye recognition function to the helmet, as well as intelligent headlights with movable steering and a movable camera. Based on the camera inside the helmet, eye tracking and the recognition of the driver's gaze direction are completed, realizing the linkage between the direction of the driver's eyes inside the helmet and the recording directions of the intelligent headlights and the camera of the driving recorder in the whole vehicle, achieving the linkage between the intelligent helmet and the headlights and the driving recorder in the whole vehicle, solving the problems of functional isolation and non-linkage between the helmet and the in-vehicle functional components, and improving the user experience.

[0063] Further, a corresponding reminder signal is determined based on the user's gaze direction and sent to the vehicle-mounted computer; the reminder signal is executed through the vehicle-mounted computer.

[0064] Figure 4 It is a schematic structural diagram of an emergency rescue implementation device based on a helmet provided by an embodiment of the present application; as Figure 4 shown, the emergency rescue implementation device 400 based on a helmet in an embodiment of the present application is applied to a target helmet, and the target helmet includes a driver status sensor and a processing unit; specifically, it may include: An identification module 401, configured to infer the real-time signal of the driver collected by the driver status sensor through a status identification model deployed on the processing unit to determine the driver status category; A decision module 402, configured to determine the corresponding execution operation type according to the driver status category and generate a corresponding execution operation signal; An execution module 403, configured to send the execution operation signal to the vehicle-mounted computer through a communication module arranged on the target helmet, so as to execute the corresponding operation through the vehicle-mounted computer.

[0065] In a possible implementation manner, the driver status sensor is an electroencephalogram sensor, and the real-time signal of the driver is an electroencephalogram signal; the electroencephalogram sensor is a non-contact electromagnetic field perturbation type electroencephalogram sensing component; multiple groups of signal generators and multiple groups of signal receivers are arranged in the internal structure of the target helmet to construct an electromagnetic field environment covering the driver's head; the electroencephalogram sensor collects the electroencephalogram signal of the driver through the following steps: The receiving module is used to generate an electromagnetic field signal of a preset frequency through a signal generator, and to receive the electromagnetic field signal after it passes through the driver's head area through a signal receiver. The acquisition module is used to detect the changes in electromagnetic field signals caused by disturbances in the driver's brainwave activity through the processing unit, and to indirectly acquire the driver's brainwave signals based on the changes in these characteristics.

[0066] In one possible implementation, the state recognition model is an edge-side inference model deployed on the processing unit after model distillation; the state recognition model is obtained through the following steps: The module is used to collect brainwave signal samples of drivers in various cycling scenarios through brainwave sensors, and to build a brainwave signal database in the cloud based on the brainwave signal samples; the cycling scenarios include at least normal cycling, fatigued driving and accident collision scenarios. The training module is used to extract brainwave frequency domain features corresponding to different driver states based on the brainwave signal database, and to train a basic state recognition model based on the brainwave frequency domain features; wherein, the brainwave frequency domain features include the differences in the power spectral density distribution of alpha waves, beta waves and theta waves; The distillation module is used to perform knowledge distillation on the basic state recognition model and to trim and compress the model for the state classification function in the cycling scenario, so as to obtain a state recognition model adapted to the computing power constraints of the processing unit; wherein, the state recognition model is an edge-side inference model.

[0067] In one possible implementation, the driver status categories include normal status, awaiting rescue status, and executing command status; the decision module is specifically used for: When the driver's status category is normal, maintain the vehicle's current operating mode and do not perform any additional operations; An emergency rescue signal is generated when the driver's status category is "awaiting rescue". When the driver's status category is "execute command", an action execution signal is generated.

[0068] In one possible implementation, the command execution state includes a steering intention command issued by the driver via brainwave signals; the decision module is specifically used for: The driver's steering intention command is identified by the state recognition model, and the driver's steering intention brainwave pattern is obtained; the steering intention brainwave pattern is either the left turn intention brainwave pattern or the right turn intention brainwave pattern. The corresponding turn signal is generated based on the brainwave pattern of the identified turning intention.

[0069] In one possible implementation, the target helmet and the vehicle's infotainment system transmit data bidirectionally via a Bluetooth communication link; the device further includes: The first sending module is used to send an emergency rescue signal to the cloud rescue platform through the vehicle's mobile communication module after the vehicle receives the emergency rescue signal. The second sending module is used to send an emergency rescue signal directly to the cloud rescue platform through the mobile communication module configured on the target helmet when the target helmet detects that the Bluetooth communication link with the vehicle is interrupted.

[0070] In one possible implementation, the execution module is specifically used for: When the driver's status is in the state of waiting for rescue, the driver's status is confirmed a second time. If no cancellation instruction is received from the driver within the preset time window, the real-time positioning information and collision detection data of the target helmet are obtained. Send a rescue notification containing location information to a pre-set emergency contact via the communication module; Simultaneously upload location information and collision detection data to the cloud-based rescue platform to initiate corresponding emergency rescue service requests.

[0071] The helmet-based emergency rescue device provided in this application uses a state recognition model deployed on a processing unit to infer the real-time signals of the driver collected by the driver's state sensor, determine the driver's state category, determine the corresponding execution operation type based on the driver's state category, generate a corresponding execution operation signal, and send the execution operation signal to the vehicle's control unit via a communication module deployed on the target helmet, so that the vehicle's control unit can execute the corresponding operation. This helmet-based emergency rescue device, by configuring a driver's state sensor and a processing unit on the helmet, and using the state recognition model deployed on the processing unit to infer the driver's state category from the real-time signals collected by the driver's state sensor, generates an execution operation signal corresponding to the driver's state category and sends it to the vehicle's control unit to trigger the corresponding operation, can accurately identify various driver states, improving the accuracy and reliability of driver state recognition.

[0072] like Figure 5 As shown in the embodiment of this application, an electronic device 500 includes a processor 501, a memory 502, and a bus. The memory 502 stores machine-readable instructions executable by the processor 501. When the electronic device is running, the processor 501 communicates with the memory 502 via the bus, and the processor 501 executes the machine-readable instructions to perform the steps of the helmet-based emergency rescue implementation method described above.

[0073] Specifically, the memory 502 and processor 501 mentioned above can be general-purpose memory and processor, without any specific limitations. When the processor 501 runs the computer program stored in the memory 502, it can execute the above-mentioned helmet-based emergency rescue implementation method.

[0074] Corresponding to the above-described helmet-based emergency rescue implementation method, this application embodiment also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the above-described helmet-based emergency rescue implementation method.

[0075] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0076] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0077] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0078] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the deployment methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, external hard drives, ROM, RAM, magnetic disks, or optical disks.

[0079] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A helmet-based emergency rescue method, characterized in that, Applied to a target helmet, the target helmet including a driver status sensor and a processing unit; the method includes: The driver's state category is determined by reasoning from the real-time signals collected by the driver's state sensor using the state recognition model deployed on the processing unit. The corresponding operation type is determined based on the driver's state category, and a corresponding operation signal is generated. The operation signal is sent to the vehicle's infotainment system via a communication module located on the target helmet, so that the corresponding operation can be performed by the vehicle's infotainment system.

2. The method according to claim 1, characterized in that, The driver's state sensor is a brainwave sensor, and the driver's real-time signal is a brainwave signal; the brainwave sensor is a non-contact electromagnetic field perturbation type brainwave sensing component; the internal structure of the target helmet is equipped with multiple signal generators and multiple signal receivers to construct an electromagnetic field environment covering the driver's head; the brainwave sensor collects the driver's brainwave signal through the following steps: The signal generator generates an electromagnetic field signal of a preset frequency, and the signal receiver receives the electromagnetic field signal after it passes through the driver's head area. The processing unit detects the changes in the electromagnetic field signal caused by the driver's brainwave activity, and indirectly obtains the driver's brainwave signal based on the changes.

3. The method according to claim 2, characterized in that, The state recognition model is an edge-side inference model deployed on the processing unit after model distillation; the state recognition model is obtained through the following steps: The brainwave sensor collects brainwave signal samples of the driver in various riding scenarios, and establishes a brainwave signal database in the cloud based on the brainwave signal samples; wherein, the riding scenarios include at least normal riding, fatigued driving and accident collision scenarios; Based on the brainwave signal database, brainwave frequency domain features corresponding to different driver states are extracted, and a basic state recognition model is trained based on the brainwave frequency domain features; wherein, the brainwave frequency domain features include the differences in power spectral density distribution of alpha waves, beta waves and theta waves; The basic state recognition model is subjected to knowledge distillation, and the model is trimmed and compressed for the state classification function in the cycling scenario to obtain a state recognition model adapted to the computing power constraints of the processing unit; wherein, the state recognition model is an edge-side inference model.

4. The method according to claim 1, characterized in that, The driver status categories include normal status, awaiting rescue status, and executing command status; the step of determining the corresponding execution operation type based on the driver status category and generating the corresponding execution operation signal includes: When the driver's state category is normal, the vehicle's current operating mode is maintained and no additional operations are performed; When the driver's status category is "awaiting rescue", an emergency rescue signal is generated; When the driver's state category is executing a command, an action execution signal is generated.

5. The method according to claim 4, characterized in that, The execution command status includes steering intention commands issued by the driver via brainwave signals; The generation of the action execution signal includes: The driver's steering intention command is identified by the state recognition model to obtain the driver's steering intention brainwave pattern; wherein, the steering intention brainwave pattern is a left turn intention brainwave pattern or a right turn intention brainwave pattern. The corresponding turn signal is generated based on the brainwave pattern of the identified turning intention.

6. The method according to claim 1, characterized in that, The target helmet and the vehicle-mounted system transmit data bidirectionally via a Bluetooth communication link; the method further includes: When the vehicle's infotainment system receives an emergency rescue signal, it sends the signal to the cloud-based rescue platform via the vehicle's mobile communication module. When the target helmet detects an interruption in its Bluetooth communication link with the vehicle's infotainment system, it sends an emergency rescue signal directly to the cloud-based rescue platform via its own mobile communication module.

7. The method according to claim 6, characterized in that, When the driver's status category is "awaiting rescue," the corresponding operation includes: The driver's status is reconfirmed. If no cancellation command is received from the driver within a preset time window, the real-time positioning information and collision detection data of the target helmet are obtained. A rescue notification containing the positioning information is sent to a preset emergency contact through the communication module. The location information and collision detection data are simultaneously uploaded to the cloud-based rescue platform to initiate a corresponding emergency rescue service request.

8. A helmet-based emergency rescue device, characterized in that, Applied to a target helmet, the target helmet including a driver status sensor and a processing unit; the device includes: The identification module is used to infer the driver's real-time signals collected by the driver's state sensor through the state identification model deployed on the processing unit, and determine the driver's state category. The decision module is used to determine the corresponding operation type based on the driver's state category and generate the corresponding operation signal; The execution module is used to send the execution operation signal to the vehicle's control unit through the communication module arranged on the target helmet, so that the vehicle's control unit can perform the corresponding operation.

9. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the steps of the helmet-based emergency rescue implementation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the helmet-based emergency rescue implementation method as described in any one of claims 1 to 7.

Images