Vehicle authentication method and device, intelligent vehicle, readable storage medium and program product

Abstract

The invention relates to a vehicle authentication method and device, an intelligent vehicle, a readable storage medium and a program product. The method comprises the following steps: receiving a shared key and a current timestamp sent by a user terminal, and generating a first token according to the shared key, vehicle identification information bound with a vehicle and the current timestamp; the shared key is a one-time password generated by the user terminal under the condition that the user passes face recognition of the user terminal; under the condition that the first token is matched with a second token sent by the user terminal, the vehicle is controlled to be in an unlocking state; the second token is generated by the user terminal according to the shared key, vehicle identification information pre-stored by the user terminal and a current timestamp; and under the condition that the user in the vehicle passes the living body detection of the living body detection component within the preset time and the distance between the user terminal and the vehicle meets the preset condition, determining that the authentication result of the vehicle to the user is that the authentication is passed. The method can improve the reliability of vehicle authentication.

Description

Vehicle authentication methods, devices, intelligent vehicles, readable storage media, and program products Technical Field

[0001] This application relates to the field of intelligent vehicle technology, and in particular to a vehicle authentication method, apparatus, intelligent vehicle, computer-readable storage medium, and computer program product. Background Technology

[0002] With the development of artificial intelligence technology, vehicles are becoming increasingly intelligent, and users are placing higher demands on vehicle safety, comfort, and convenience. In usage scenarios such as car sharing, smart rental vehicles, and high-security private vehicles, vehicle safety has become one of the most important factors in evaluating vehicle performance.

[0003] In traditional technologies, vehicles primarily authenticate user identities through physical keys, static passwords, or single biometric features (such as fingerprints) to unlock the vehicle. However, these methods are susceptible to risks such as lost or copied keys, password leaks, and forged biometric features. They cannot meet the requirements of high-security vehicle usage scenarios and suffer from low reliability in vehicle authentication. Summary of the Invention

[0004] Therefore, it is necessary to provide a vehicle authentication method, device, intelligent vehicle, computer-readable storage medium, and computer program product that can improve the reliability of vehicle authentication in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a vehicle authentication method, wherein the vehicle is equipped with a liveness detection component, including:

[0006] The system receives a shared key and a current timestamp sent by a user terminal, and generates a first token based on the shared key, the vehicle identification information bound to the vehicle, and the current timestamp; the shared key is a one-time password generated by the user terminal when the user performs facial recognition on the user terminal.

[0007] If the first token matches the second token sent by the user terminal, the vehicle is controlled to be in an unlocked state; the second token is generated by the user terminal based on the shared key, the vehicle identification information pre-stored by the user terminal, and the current timestamp.

[0008] If, within a preset time, a user inside the vehicle passes the liveness detection component and the distance between the user terminal and the vehicle meets a preset condition, the vehicle's authentication result for the user is determined to be successful.

[0009] In one embodiment, the liveness detection component includes an in-vehicle infrared camera, and the method further includes:

[0010] The infrared light signal reflected from the user's face is received by the vehicle-mounted infrared camera;

[0011] Extract the skin blood flow characteristics of the face from the infrared light signal;

[0012] If the skin blood flow characteristics conform to the pattern of living blood flow, it is determined that the user has passed the liveness detection of the liveness detection component.

[0013] In one embodiment, the method further includes:

[0014] The driving credit score of the vehicle is determined based on at least one of the vehicle's illegal parking records, speeding records, and abnormal unlocking records.

[0015] The vehicle's driving permissions are controlled based on the comparison result between the driving credit score and at least one preset score range.

[0016] In one embodiment, the illegal parking record includes the number of illegal parking incidents, the speeding record includes the duration of each speeding incident, and the abnormal unlocking record includes the number of abnormal unlocking events. Determining the vehicle's driving credit score based on at least one of the vehicle's illegal parking record, speeding record, and abnormal unlocking record includes:

[0017] Based on the number of illegal parking incidents, a severity score for the illegal parking of the vehicle is determined;

[0018] The speeding severity score of the vehicle is determined by weighted summation of the duration of each speeding violation; the weight of each speeding violation duration is determined based on the degree of speeding violation for each violation.

[0019] The number of occurrences of the abnormal unlocking events is weighted and summed to determine the degree of unlocking abnormality of the vehicle; the weight corresponding to the number of occurrences is determined according to the occurrence time of the abnormal unlocking event.

[0020] The driving credit score of the vehicle is determined based on the severity score of the illegal parking, the severity score of the speeding, and the score of the unlocking anomaly.

[0021] In one embodiment, the step of weighted summing of the number of occurrences of the abnormal unlocking events to determine the degree of unlocking abnormality of the vehicle includes:

[0022] The number of occurrences of the abnormal unlocking event is weighted and summed to determine the abnormal quantification value; the weight corresponding to the number of occurrences is determined according to the time interval between the occurrence time of the abnormal unlocking event and the current time.

[0023] The degree of unlocking anomaly of the vehicle is determined based on the anomaly quantification value and the penalty coefficient; the penalty coefficient is determined based on the number of consecutive days the abnormal unlocking event occurs.

[0024] In one embodiment, the at least one preset scoring interval includes a first scoring interval and a second scoring interval, wherein the second scoring interval is smaller than the first scoring interval; controlling the vehicle's driving permissions based on the comparison result between the driving credit score and the at least one preset scoring interval includes:

[0025] If the credit score meets the first score range, the maximum speed of the vehicle is limited to be less than a preset speed.

[0026] If the credit score falls within the second score range, the vehicle's activation is restricted.

[0027] Secondly, this application also provides a vehicle authentication device, wherein the vehicle is equipped with a liveness detection component, including:

[0028] The generation module is used to receive a shared key and a current timestamp sent by the user terminal, and generate a first token based on the shared key, the vehicle identification information bound to the vehicle, and the current timestamp; the shared key is a one-time password generated by the user terminal when the user performs facial recognition on the user terminal;

[0029] The control module is configured to control the vehicle to be in an unlocked state when the first token matches the second token sent by the user terminal; the second token is generated by the user terminal based on the shared key, the vehicle identification information pre-stored by the user terminal, and the current timestamp.

[0030] The authentication module is used to determine that the vehicle's authentication result for the user is successful if the user inside the vehicle passes the liveness detection component within a preset time and the distance between the user terminal and the vehicle meets preset conditions.

[0031] Thirdly, this application also provides an intelligent vehicle, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method.

[0032] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method.

[0033] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method.

[0034] The aforementioned vehicle authentication method, device, intelligent vehicle, computer-readable storage medium, and computer program product receive a shared key and a current timestamp sent by a user terminal. Based on the shared key, the vehicle's bound identification information, and the current timestamp, a first token is generated. The shared key is generated based on facial recognition on the user terminal and is a one-time password. This achieves initial identity verification through facial recognition while avoiding the risk of leakage associated with static passwords. Furthermore, it eliminates the need for a physical key, thus avoiding the risk of lost or copied keys. During the matching process between the first and second tokens, the vehicle and the user terminal independently generate tokens based on the shared key, their respective bound vehicle identification information, and the current timestamp, utilizing the time-sensitivity of the timestamp. The uniqueness of the vehicle identifier and the dynamic nature of the shared key enable real-time and accurate multi-verification. The vehicle unlocks when the first token matches the second token. Then, the liveness detection component configured in the vehicle performs a liveness check on the user inside the vehicle, which can effectively identify forged biometrics and avoid the risk of being easily forged when using a single biometric. Moreover, the vehicle is only confirmed to have passed the final authentication if the user completes the liveness detection within a preset time and the distance between the user terminal and the vehicle meets preset conditions. This binds the authentication process to the user's physical presence, avoiding the risk of unauthorized remote authentication. This significantly improves the authentication reliability of vehicles in scenarios such as sharing, leasing, and high-security use, thereby enhancing vehicle security. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 is an application environment diagram of a vehicle authentication method in one embodiment;

[0037] Figure 2 is a flowchart illustrating a vehicle authentication method in one embodiment;

[0038] Figure 3 is an example diagram of a vehicle authentication system in one embodiment;

[0039] Figure 4 is a flowchart of a vehicle authentication method in one embodiment;

[0040] Figure 5 is a flowchart illustrating a vehicle authentication method in another embodiment;

[0041] Figure 6 is a structural block diagram of a vehicle authentication device in one embodiment;

[0042] Figure 7 is an internal structure diagram of an intelligent vehicle in one embodiment. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0044] The vehicle authentication method provided in this application embodiment can be applied to the application environment shown in Figure 1. The intelligent vehicle 102 communicates with the server 104 via a network. A data storage system can store the data that the server 104 needs to process. The data storage system can be integrated onto the server 104, or it can be located in the cloud or on another network server.

[0045] The intelligent vehicle 102 receives a shared key and a current timestamp sent by the user terminal. Based on the shared key, the vehicle identification information bound to the vehicle, and the current timestamp, it generates a first token. The shared key is a one-time password generated by the user terminal when the user undergoes facial recognition. If the first token matches the second token sent by the user terminal, the intelligent vehicle 102 controls the vehicle to be in an unlocked state. The second token is generated by the user terminal based on the shared key, the vehicle identification information pre-stored by the user terminal, and the current timestamp. If the user inside the vehicle passes the liveness detection component within a preset time and the distance between the user terminal and the vehicle meets preset conditions, the intelligent vehicle 102 determines that the vehicle's authentication result for the user is successful.

[0046] Among them, server 104 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0047] In an exemplary embodiment, as shown in FIG2, a vehicle authentication method is provided. Taking the application of this method to the intelligent vehicle 102 in FIG1 as an example, the method includes:

[0048] Step S202: Receive the shared key and current timestamp sent by the user terminal, and generate the first token based on the shared key, the vehicle identification information bound to the vehicle, and the current timestamp.

[0049] The user terminal may include a smart device (such as a smartphone or smart bracelet) with communication and facial recognition capabilities. The user terminal may have a vehicle-specific application (APP) installed, allowing users to perform vehicle authentication, unlocking, and other vehicle control functions, as well as vehicle status monitoring. In practical applications, users can initiate a vehicle use request through the APP. The APP will respond to the request and prompt the user to complete facial recognition. Upon successful facial recognition, the user terminal can generate a one-time password, which serves as a shared key.

[0050] The shared key is a one-time password generated by the user terminal when the user undergoes facial recognition. This one-time password is only valid for the current authentication process and expires afterward, avoiding the risk of leakage associated with static passwords that remain valid for a long time. While time-synchronized one-time passwords improve password security, they cannot solve the problem of remote hijacking; therefore, a dynamic token needs to be generated together with the current timestamp and vehicle identification information.

[0051] The current timestamp can be a record of the time (in seconds or milliseconds) when the user initiates a ride request on the app. This time record can be a timestamp recorded on the user's terminal's operating system. The current timestamp is used to mark the timeliness of authentication information and prevent unauthorized users from reusing historical authentication information for forgery.

[0052] Among them, vehicle identification information is the unique identifier of a vehicle, such as the Vehicle Identification Number (VIN) and the dedicated device number. It is bound to the vehicle and cannot be tampered with, ensuring that the authentication process is only effective for a specific vehicle and avoiding illegal authentication across vehicles.

[0053] The first token is a verification credential generated by the vehicle using a preset algorithm based on the received shared key, its own bound vehicle identification information, and the current timestamp. This credential is used to match and verify the second token generated by the user terminal. Optionally, the preset algorithm may include a cryptographic hash algorithm, etc.

[0054] For example, the vehicle's in-vehicle system and the user terminal's APP can each generate corresponding dynamic tokens based on a collaborative encryption algorithm, and the tokens can be valid for 60 seconds. Assuming the one-time password generated by the user terminal APP is 314592, the shared key can be 314592; assuming the last 6 digits of the Vehicle Identification Number (VIN) are 186109, the vehicle identification information bound to the vehicle can be 186109; assuming the timestamp recorded on the user terminal's operating system when the user initiates a vehicle use request on the APP is 15:28:37, the current timestamp can be the last 4 digits of that timestamp, 2837. Then, based on the shared key, the vehicle identification information bound to the vehicle, and the current timestamp, a dynamic token is generated. Specifically, the vehicle identification information (the last 6 bits of the VIN) is converted to ASCII 0X31 0X38 0X36 0X31 0X30 0X39; the current timestamp (the last 4 bits of the timestamp recorded by the operating system) is converted to hexadecimal 0xE90; the shared key (the one-time password generated by the APP) is converted to hexadecimal 0X04 0XCC 0XE0; concatenating the above data results in 0X31 0X38 0X36 0X31 0X30 0X39 0x0E 0X90 0X04 0XCC 0XE0; scrambling the above data results in 0X04 0XCC 0X31 0X38 0XE0 0x0E 0X30 0X39 0X36 0X90. 0X31, take the first 6 bytes and convert them into a decimal dynamic token: 5275045650446. This dynamic token can be the first token generated by the vehicle's onboard system. Similarly, the user terminal can also generate a second token in the same way based on the shared key, the vehicle identification information pre-stored by the user terminal, and the current timestamp, and return the second token to the vehicle's onboard system.

[0055] In step S204, if the first token matches the second token sent by the user terminal, the vehicle is controlled to be in an unlocked state.

[0056] The second token is generated by the user terminal based on the shared key, the vehicle identification information pre-stored on the user terminal, and the current timestamp. In practical applications, when a user binds a vehicle for the first time through the user terminal's APP, they can manually enter the complete vehicle VIN code in the APP. The APP automatically retrieves the last 6 digits of the VIN code and stores it in the APP as the vehicle identification information pre-stored on the user terminal.

[0057] In practice, a preset rule can be used to determine whether the first token matches the second token sent by the user terminal. For example, the values ​​of the first and second tokens can be directly compared; if they match, the first and second tokens are considered to match. Alternatively, the encryption signatures of the first and second tokens can be verified; if they match, the first and second tokens are considered to match. If the first and second tokens match, it indicates that the vehicle and the user terminal generate dynamic tokens based on the same authentication information (one-time shared key, vehicle identification information, and current timestamp), and this authentication information has not been illegally tampered with during transmission. The one-time shared key and current timestamp used by the vehicle and the user terminal to generate the tokens are the same, and the vehicle identification pre-stored by the user terminal is also the same as the actual vehicle identification. The vehicle can initially determine that the user's identity verification is successful and control the vehicle's doors and other components to switch to the unlocked state, allowing the user to enter the vehicle. At this time, the unlocked state of the vehicle is an intermediate state for the vehicle to complete the initial identity verification of the user, rather than the final authentication.

[0058] By generating and comparing tokens independently between the user terminal and the vehicle, it is possible to effectively prevent unauthorized users from initiating authentication by forging shared keys, tampering with vehicle identification, or reusing historical information. This provides a preliminary authentication basis for subsequent liveness detection and distance verification, ensuring the comprehensiveness and accuracy of the overall vehicle authentication.

[0059] Step S206: If the user inside the vehicle passes the liveness detection component within a preset time and the distance between the user terminal and the vehicle meets the preset conditions, the vehicle's authentication result for the user is determined to be successful.

[0060] The preset time may include a time limit from vehicle unlocking to the completion of final authentication, such as 5 minutes or 10 minutes.

[0061] The liveness detection component may include hardware devices for verifying whether a user is a real, living person. This component allows for dynamic biometric verification of in-vehicle users, identifying them as genuine living individuals rather than fake biometric carriers. For example, the liveness detection component may include an in-vehicle camera, heart rate sensor, pulse sensor, etc. The in-vehicle camera may include a 2D camera and an infrared camera, and may be installed directly in front of the driver's seat or near the center console. The infrared camera may be a near-infrared camera, operating in the near-infrared (NIR) band with a wavelength range of 780 nanometers to 2500 nanometers.

[0062] In the specific implementation, in the first stage, a 2D camera can be used to capture dynamic images of the user's face and identify key facial regions (such as eyelids and eyeballs) in the dynamic facial images. Then, the blinking action features in the micro-expressions of the face are analyzed from the key facial regions. If the blinking action features indicate that the blinking frequency exceeds the frequency threshold, such as 0.2 Hz, it can be determined that the user has passed the first stage of liveness detection by the liveness detection component and enters the second stage of liveness detection. If the blinking action features indicate that the blinking frequency is less than or equal to the frequency threshold, it can be determined that a static photo attack has been launched, and authentication, alarm, and vehicle locking can be terminated.

[0063] In the specific implementation, in the second stage, a near-infrared camera emits near-infrared light with a wavelength of 850 nanometers to illuminate the user's face. The reflected near-infrared light signal is then subjected to spectral analysis to obtain skin blood flow characteristics. Based on these characteristics, the authenticity of the user is determined, thus countering attacks from high-precision 3D masks. Near-infrared light with a wavelength of 850 nanometers has strong skin penetration, reaching deep into the capillary layer beneath the epidermis to capture the dynamic absorption characteristics of hemoglobin in the blood. The blood flow under real human skin undergoes periodic changes with the heartbeat, causing corresponding periodic fluctuations in the intensity of the near-infrared light reflected from the user's face. While high-precision 3D masks, silicone replicas, and other forgeries can simulate facial features, they lack a real blood circulatory system, and the intensity of their reflected near-infrared light does not exhibit periodic blood flow fluctuations, showing a significant difference from the real human body. Therefore, near-infrared spectroscopy analysis can be used to detect skin blood flow characteristics by analyzing the near-infrared light signals reflected from the user's face. If the skin blood flow characteristics match the periodic characteristics of real skin blood flow, it can be confirmed that the user has passed the second stage of liveness detection by the liveness detection component. If the skin blood flow characteristics do not match the periodic characteristics of real skin blood flow, it can be determined that the user has been attacked by a high-precision 3D mask or other imitation, which can trigger an alarm and lock the vehicle.

[0064] In practice, if a user passes both the first and second stages of liveness detection by the liveness detection component, it can be confirmed that the user inside the vehicle has passed the final liveness detection. By combining liveness detection with facial recognition, multimodal biometric authentication is achieved, improving the accuracy of vehicle authentication.

[0065] The distance between the user terminal and the vehicle can be detected using communication technologies such as Bluetooth, Near Field Communication (NFC), or Ultra Wide Band (UWB). Alternatively, the distance can be determined based on the user terminal's Global Positioning System (GPS) data and the vehicle's onboard BeiDou positioning data. The distance between the user terminal and the vehicle must meet preset conditions, which may include the distance being less than a distance threshold, such as 30 meters or 40 meters.

[0066] In practice, if a user inside the vehicle passes the liveness detection component within a preset time and the distance between the user terminal and the vehicle meets the preset conditions, the vehicle's authentication result for the user is determined to be successful, and the user can then start the vehicle.

[0067] Since single biometric features are vulnerable to forgery attacks (such as 3D-printed face masks and fingerprint films), and static passwords are easily intercepted, dual authentication based on environment binding verification logic with spatiotemporal thresholds (distance less than the threshold and time to pass liveness detection less than the threshold) reduces the risk of biometric forgery. Furthermore, binding dynamic tokens to the vehicle environment can prevent remote hijacking, reduce the risk of unauthorized remote authorization, and improve vehicle security. Moreover, the spatiotemporal dual constraints ensure a strong correlation between real people, real vehicles, and real locations, realizing dynamic environment verification.

[0068] In the aforementioned vehicle authentication method, a shared key and a current timestamp are received from the user terminal. Based on the shared key, the vehicle's bound identification information, and the current timestamp, a first token is generated. The shared key is generated based on the user terminal's facial recognition and is a one-time password. This achieves initial identity verification through facial recognition while avoiding the risk of leakage associated with static passwords. Furthermore, it eliminates the need for a physical key, thus avoiding the risk of lost or copied keys. During the matching process between the first and second tokens, the vehicle and the user terminal independently generate tokens based on the shared key, their respective bound vehicle identification information, and the current timestamp. This leverages the timeliness of the timestamp, the uniqueness of the vehicle identification, and the shared key's validity. The dynamic nature of the key enables real-time and accurate multi-verification. Vehicle unlocking is controlled only when the first and second tokens match. A liveness detection component in the vehicle then performs a liveness check on the user inside, effectively identifying forged biometrics and avoiding the vulnerability of relying on a single biometric feature. Furthermore, vehicle authentication is only confirmed when the user completes the liveness detection within a preset time and the distance between the user's terminal and the vehicle meets preset conditions. This binds the authentication process to the user's physical presence, preventing the risk of unauthorized remote authentication and significantly improving the reliability of vehicle authentication in scenarios such as sharing, leasing, and high-security usage, thereby enhancing vehicle security.

[0069] In another embodiment, the liveness detection component includes an in-vehicle infrared camera, and further includes: receiving infrared light signals reflected from a user's face via the in-vehicle infrared camera; extracting skin blood flow features of the face from the infrared light signals; and determining that the user has passed the liveness detection component if the skin blood flow features conform to the liveness pattern.

[0070] The vehicle-mounted infrared camera may include an infrared camera integrated inside the vehicle (such as in front of the driver's seat or on the center console), used to emit infrared light of a specific wavelength and receive the infrared light signal reflected from the user's face. For example, the vehicle-mounted infrared camera may be a near-infrared camera that emits infrared light with a wavelength of 850 nanometers.

[0071] The infrared light signal is the light signal emitted by the vehicle-mounted infrared camera, which shines near-infrared light onto the user's face and is reflected back to the camera through the skin and subcutaneous tissue. The intensity and spectral characteristics of the infrared light signal can change due to the absorption and scattering characteristics of facial tissues (such as blood in the capillaries under the skin).

[0072] In practice, the infrared light signal reflected from the user's face can be filtered (to remove interference from ambient light, camera noise, etc.), amplified, and analyzed by algorithms to extract core features related to blood flow. For example, the periodic fluctuations of the signal can be identified through time-domain analysis, the characteristic frequency peaks that match the heart rate can be detected through frequency-domain analysis, and the intensity range of the signal fluctuations can be calculated through amplitude analysis, thereby obtaining the skin blood flow characteristics.

[0073] Among them, the living blood flow pattern is the physiological pattern of blood flow under the skin of a real human body, which can be characterized by stable periodicity, fluctuation amplitude within a specific range, and characteristic peaks in the spectrum that match the heart rate.

[0074] In practice, skin blood flow characteristics can be compared with preset live blood flow patterns. If the characteristic parameters (such as periodicity, frequency range, amplitude, etc.) contained in the skin blood flow characteristics all fall within the threshold range of the live blood flow pattern, the user is determined to be a real living person and passes the liveness detection. If there is a significant deviation between the characteristic parameters and the threshold range of the live blood flow pattern, the user is determined to be a non-living person (such as a 3D mask, photo, or other forgery). Since non-living people do not have real blood flow, they cannot generate signals that conform to the pattern, and therefore do not pass the liveness detection.

[0075] The technical solution of this embodiment analyzes the skin blood flow characteristics of the user's face to determine whether the user has passed the liveness detection. This can effectively combat attacks by forgeries such as high-precision 3D masks, make up for the authentication defects that rely solely on static facial features, and improve the reliability of vehicle authentication.

[0076] In another embodiment, the method further includes: determining a vehicle's driving credit score based on at least one of the vehicle's illegal parking records, speeding records, and abnormal unlocking records; and controlling the vehicle's driving permissions based on a comparison of the driving credit score with at least one preset score range.

[0077] The illegal parking record may include historical data on violations such as parking in no-parking areas, exceeding the time limit, or parking in non-designated parking spaces, and may include information such as the number of illegal parking incidents and the duration of illegal parking.

[0078] The speeding record may include historical data of the vehicle speed exceeding the road speed limit, including the number of speeding incidents, the duration of speeding (such as the duration of each speeding incident), and the degree of speeding (such as exceeding the speed limit by 20% or 30%).

[0079] The abnormal unlocking record can include historical data on abnormal unlocking events that failed to unlock through the normal authentication process, including the number of abnormal unlocking events and the time of occurrence. In practical applications, abnormal unlocking events may include facial recognition failure, dynamic token verification failure, user failure to complete liveness detection within the scheduled time period, liveness detection failure, and the distance between the user terminal and the vehicle not meeting preset conditions.

[0080] For example, parking location information recorded by a vehicle positioning module (such as Beidou or GPS) can be combined with no-parking zone data (such as no-parking road sections) in electronic fences or map points of interest (POIs) to automatically identify recent illegal parking events by the vehicle system or cloud platform to generate illegal parking records.

[0081] For example, vehicle speed can be collected in real time by an onboard speed sensor and combined with the current road speed limit standard provided by a navigation system (such as an onboard map). When the vehicle speed exceeds the speed limit standard, an overspeed record can be automatically generated.

[0082] For example, abnormal unlocking events automatically recorded in the system logs of the vehicle system or cloud platform can be obtained to obtain abnormal unlocking records.

[0083] In practice, a vehicle's driving credit score is determined based on at least one of the vehicle's illegal parking records, speeding records, and abnormal unlocking records. This can be achieved by generating corresponding deduction values ​​based on the vehicle's illegal parking records, speeding records, and abnormal unlocking records, and then accumulating the initial base score (e.g., 100 points) according to the deduction values ​​to obtain the final driving credit score.

[0084] The preset scoring intervals are multiple consecutive score ranges set in advance, such as [80,100], [50,80), [20,50), and [0,20). Each interval corresponds to a different driving permission control strategy. The interval division can be determined according to the vehicle safety management needs. For example, stricter interval thresholds can be set for high-safety-level scenarios.

[0085] In practice, the driving credit score is compared with a preset score range to determine which preset score range the driving credit score falls into, and the corresponding driving permissions for the vehicle are determined accordingly. For example, the higher the preset score range, the more driving permissions the vehicle has; the lower the preset score range, the fewer driving permissions the vehicle has.

[0086] Existing vehicle systems have fixed permissions that cannot be dynamically adjusted based on user behavior, resulting in high-risk users continuously enjoying full privileges. The technical solution in this embodiment integrates driving behavior data to generate credit scores and perform hierarchical mapping of driving permissions. This allows for a more accurate assessment of a user's credit risk level. By comparing the driving credit score with a preset score range, the real-time performance of vehicle driving permission management is improved, enabling risk-adaptive functional control and enhancing vehicle safety.

[0087] In another embodiment, the illegal parking record includes the number of illegal parking incidents, the speeding record includes the duration of each speeding incident, and the abnormal unlocking record includes the number of abnormal unlocking events. Based on at least one of the vehicle's illegal parking record, speeding record, and abnormal unlocking record, a driving credit score for the vehicle is determined, including: determining a illegal parking severity score based on the number of illegal parking incidents; determining a speeding severity score by weighted summation of the duration of each speeding incident; determining an unlocking anomaly score by weighted summation of the number of abnormal unlocking events; and determining a driving credit score for the vehicle based on the illegal parking severity score, speeding severity score, and unlocking anomaly score.

[0088] The number of illegal parking incidents can be the total number of times a vehicle commits illegal parking offenses within the statistical period, such as the past three months.

[0089] In practice, the severity score of a vehicle's illegal parking can be determined by the ratio of the number of illegal parking incidents to the number of days the vehicle was used effectively within the statistical period. This severity score reflects the historical frequency of illegal parking incidents. The number of days the vehicle was used effectively can be the number of days the user actually used the vehicle within the statistical period.

[0090] The duration of each speeding violation can be the total time from start to finish of each speeding behavior within the statistical period. The severity of each speeding violation includes the proportion or absolute value of the vehicle's actual speed exceeding the road speed limit (e.g., exceeding the speed limit by 10%, 20 km / h, etc.), used to distinguish the severity of the speeding behavior. The higher the severity of the speeding violation, the greater the weight of each speeding duration.

[0091] The weight corresponding to each speeding duration is determined based on the degree of speeding in each instance.

[0092] In practice, the weight of each speeding duration can be determined based on the degree of speeding during the statistical period. Then, the weighted sum of the single speeding durations corresponding to each speeding can be obtained to get the speeding quantification value. Then, the speeding severity score of the vehicle can be determined based on the ratio of the speeding quantification value to the total driving time of the vehicle during the statistical period.

[0093] The occurrence count of abnormal unlocking events can include the number of abnormal unlocking events that occur within each time unit. For example, the occurrence count of abnormal unlocking events can include the number of abnormal unlocking events per day. The occurrence time of abnormal unlocking events can be used to calculate the interval between the abnormal unlocking event and the current time, distinguishing between recent and distant abnormalities. The smaller the time interval between the occurrence time of the abnormal unlocking event and the current time, the greater the weight of the occurrence count of abnormal unlocking events within that time unit.

[0094] The weight corresponding to the number of occurrences is determined based on the occurrence time of the abnormal unlocking event.

[0095] In practice, the weight of the number of times an abnormal unlocking event occurs within each time unit can be determined based on the occurrence time of the abnormal unlocking event. The number of times an abnormal unlocking event occurs within each time unit is then weighted and summed to determine the score of the degree of vehicle unlocking abnormality.

[0096] In practice, the severity scores for illegal parking, speeding, and unlocking anomalies are weighted and summed to obtain a total deduction value. This total deduction value is then subtracted from the initial baseline score to arrive at the vehicle's driving credit score. The weights of each of these scores can be determined based on actual vehicle safety management needs. For example, the weight of the illegal parking severity score could be 0.4, the speeding severity score 0.35, and the unlocking anomaly score 0.25.

[0097] The technical solution of this embodiment achieves accurate quantification of driving credit score through scoring the severity of illegal parking, speeding, and unlocking anomaly, which can improve the accuracy of vehicle driving authority control and enhance vehicle safety.

[0098] In another embodiment, the vehicle's unlocking anomaly score is determined by weighted summation of the number of abnormal unlocking events, including: weighted summation of the number of abnormal unlocking events to determine an anomaly quantification value; and determining the vehicle's unlocking anomaly score based on the anomaly quantification value and a penalty coefficient.

[0099] The weight corresponding to the number of occurrences is determined based on the time interval between the occurrence time of the abnormal unlocking event and the current time.

[0100] For example, the number of abnormal unlocking events may include the number of abnormal unlocking events occurring daily for the vehicle. The time interval between the occurrence time of the abnormal unlocking event and the current time may be determined by the number of days between the date of the abnormal unlocking event and the current date. Since recent abnormalities have a more significant impact on credit scores, the smaller the time interval between the occurrence time of the abnormal unlocking event and the current time, the greater the weight corresponding to the number of occurrences.

[0101] In a specific implementation, the number of times an abnormal unlocking event occurs can be determined based on the time interval between the occurrence time of the abnormal unlocking event and the current time. The number of occurrences of abnormal unlocking events is then weighted and summed to determine the abnormal quantification value, where the abnormal quantification value is the weighted sum of the number of occurrences of abnormal unlocking events.

[0102] The penalty coefficient is determined based on the number of consecutive days that the abnormal unlocking event occurs. The penalty coefficient amplifies the impact of consecutive abnormal unlocking actions, and its value is determined by the number of consecutive days the abnormal unlocking event occurs. Since consecutive occurrences usually imply higher risks, such as the vehicle potentially being maliciously unlocked multiple times, the more consecutive days the event occurs, the greater the penalty coefficient.

[0103] In practice, the degree of vehicle unlocking abnormality can be determined by multiplying the abnormality quantification value and the penalty coefficient, thereby comprehensively reflecting the frequency, timeliness, and persistence risk of abnormal unlocking events.

[0104] The technical solution of this embodiment can determine the weighting coefficient by the time interval between the occurrence time of the abnormal unlocking event and the current time, highlighting the impact of recent abnormalities on the driving credit score. Furthermore, it can more accurately assess persistent abnormal behavior by using a penalty coefficient determined by the number of consecutive abnormal days, thereby improving the accuracy of the unlocking abnormality score and thus improving the accuracy of the driving credit score.

[0105] In one embodiment, a credit assessment model can be constructed, with inputs including illegal parking records, speeding records, and abnormal unlocking records, and outputs including a driving credit score of 0 to 100.

[0106] Credit assessment models may include:

[0107] ;

[0108] in, Score the severity of illegal parking.

[0109] ;

[0110] in, The severity of speeding is scored. The speeding weighting coefficient can be 0.25 (speeding less than 10%), 0.75 (speeding 10% to 40%), or 1 (speeding more than 40%).

[0111] ;

[0112] in, An abnormal unlocking event is scored. Here, 'd' represents the number of days since the current time. For example, an abnormal unlocking event occurring today has 'd' = 1; an abnormal unlocking event occurring yesterday has 'd' = 2, resulting in an exponential decay rate of 15% for the daily occurrence of abnormal unlocking events. The penalty coefficient is determined by the number of consecutive days the abnormal unlocking event occurs. For instance, a penalty coefficient of 3 is applied for 4 consecutive days; 5 for more than 5 days; 7 for more than 6 days; and 9 for more than 7 days.

[0113] The driving credit score S can be represented as:

[0114] ;

[0115] in, , and These are their respective weights, for example, It is 0.4. It is 0.35. It is 0.25.

[0116] Therefore, credit scoring models and permission-based mapping rules that integrate driving behavior data can more accurately assess a user's credit risk level. Based on different risk levels, the system can implement risk-adaptive function control and dynamically reduce privileges or restrict functions based on user behavior.

[0117] In another embodiment, at least one preset scoring interval includes a first scoring interval and a second scoring interval, wherein the second scoring interval is smaller than the first scoring interval; based on the comparison result between the driving credit score and at least one preset scoring interval, the vehicle's driving authority is controlled, including: if the credit score meets the first scoring interval, limiting the vehicle's maximum speed to less than a preset speed; if the credit score meets the second scoring interval, restricting the vehicle's starting.

[0118] The first scoring interval is used to represent a preset higher risk scoring range, for example, [20, 80); the second scoring interval is used to represent a preset lower risk scoring range, for example, [0, 20).

[0119] In practice, if the credit score falls into the first scoring range, the vehicle's maximum speed can be limited to below a preset speed, such as 80 km / h. If the credit score falls into the second scoring range, the vehicle's starting can be restricted, causing the vehicle to lock and become unstartable.

[0120] For example, the first scoring interval may further include a first sub-interval and a second sub-interval, where the second sub-interval is smaller than the first sub-interval. If the credit score meets the third scoring interval (the third scoring interval is higher than the first scoring interval, such as [80, 100]), all driving functions of the vehicle can be enabled without any restrictions; if the credit score meets the first sub-interval (such as [50, 80)), the maximum speed of the vehicle is limited to less than a first preset speed (such as 90 km / h), thus restricting high-speed driving; if the credit score meets the second sub-interval (such as [20, 50)), the maximum speed of the vehicle is limited to less than a second preset speed (the second preset speed is less than the first preset speed, such as 20 km / h), allowing the vehicle only to enter the basic parking mode; if the credit score meets the second scoring interval (such as [0, 20)), the vehicle can be locked directly, preventing it from starting.

[0121] To facilitate understanding by those skilled in the art, Figure 3 provides an exemplary diagram of a vehicle authentication system. This vehicle authentication system integrates biometric recognition, dynamic environment verification, and behavioral credit assessment, and is suitable for use scenarios such as car sharing, smart rental vehicles, and high-security vehicles.

[0122] The mobile app serves as the central hub for interaction among various modules in the vehicle access control system, connecting in-vehicle hardware, cloud services, and the backend engine, and is responsible for command forwarding, data integration, and result presentation.

[0123] In practical applications, biometric authentication terminals can be deployed inside vehicles to collect user biometrics (such as facial features and fingerprints), perform liveness detection (such as infrared blood flow analysis), and verify the legitimacy of the user's identity. Environmental verification modules can be deployed on cloud servers to verify the security of the vehicle's environment (such as whether the geographical location is compliant, whether there are network attack risks, and whether abnormal activity of surrounding devices is detected). Behavioral analysis engines can be deployed on backend servers to analyze vehicle / user behavior data (such as illegal parking, speeding, and abnormal unlocking), calculate driving credit scores, and assess risk levels.

[0124] To facilitate understanding by those skilled in the art, Figure 4 provides an exemplary flowchart of a vehicle authentication method. In its implementation, the user initiates a vehicle use request via a mobile app; the user's biometric features are determined through facial recognition on the phone to assess authentication success; the dynamic tokens generated by the phone and vehicle are compared to determine if authentication is successful; environmental parameters such as whether the user completes liveness detection within a preset time and whether the user's location is close to the vehicle are also considered to assess authentication success; then, based on the credit score range, corresponding permission commands are generated and sent to the vehicle's electronic control unit (ECU), causing the vehicle's powertrain system to enter the corresponding operating mode. If any of the above authentication steps fail, an onboard alarm can be triggered.

[0125] In another embodiment, as shown in FIG5, a vehicle authentication method is provided. Taking the application of this method to the intelligent vehicle 102 in FIG1 as an example, the method includes the following steps:

[0126] Step S502: Receive the shared key and current timestamp sent by the user terminal, and generate the first token based on the shared key, the vehicle identification information bound to the vehicle, and the current timestamp.

[0127] In step S504, if the first token matches the second token sent by the user terminal, the vehicle is controlled to be in an unlocked state.

[0128] Step S506: If the user inside the vehicle passes the liveness detection component within a preset time and the distance between the user terminal and the vehicle meets the preset conditions, the vehicle's authentication result for the user is determined to be successful.

[0129] Step S508: Determine the vehicle's driving credit score based on at least one of the vehicle's illegal parking records, speeding records, and abnormal unlocking records.

[0130] Step S510: Control the vehicle's driving permissions based on the comparison result between the driving credit score and at least one preset score range.

[0131] It should be noted that the specific limitations of the above steps can be found in the specific limitations of a vehicle authentication method described above.

[0132] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0133] Based on the same inventive concept, this application also provides a vehicle authentication device for implementing the vehicle authentication method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more vehicle authentication device embodiments provided below can be found in the limitations of the vehicle authentication method described above, and will not be repeated here.

[0134] In one exemplary embodiment, as shown in FIG6, a vehicle authentication device is provided, comprising:

[0135] The generation module 610 is used to receive a shared key and a current timestamp sent by the user terminal, and generate a first token based on the shared key, the vehicle identification information bound to the vehicle, and the current timestamp; the shared key is a one-time password generated by the user terminal when the user performs facial recognition.

[0136] The control module 620 is used to control the vehicle to be in an unlocked state when the first token matches the second token sent by the user terminal; the second token is generated by the user terminal based on the shared key, the vehicle identification information pre-stored by the user terminal, and the current timestamp.

[0137] The authentication module 630 is used to determine that the authentication result of the vehicle for the user is successful if the user inside the vehicle passes the liveness detection component within a preset time and the distance between the user terminal and the vehicle meets a preset condition.

[0138] In one embodiment, the authentication module 630 is specifically used to receive infrared light signals reflected from the user's face via the vehicle-mounted infrared camera; extract skin blood flow features of the face from the infrared light signals; and determine that the user has passed the liveness detection of the liveness detection component if the skin blood flow features conform to the living blood flow pattern.

[0139] In one embodiment, the vehicle authentication device further includes an authorization module, which is specifically used to determine the vehicle's driving credit score based on at least one of the vehicle's illegal parking records, speeding records, and abnormal unlocking records; and to control the vehicle's driving permissions based on a comparison of the driving credit score with at least one preset score range.

[0140] In one embodiment, the illegal parking record includes the number of illegal parking incidents, the speeding record includes the duration of each speeding incident, and the abnormal unlocking record includes the number of abnormal unlocking events.

[0141] In one embodiment, the permission module is specifically used to determine the severity score of the vehicle's illegal parking based on the number of illegal parking incidents; to determine the speeding severity score by weighted summation of the duration of each speeding incident, where the weight of the duration of each speeding incident is determined based on the degree of each speeding incident; to determine the unlocking anomaly score of the vehicle by weighted summation of the number of abnormal unlocking events, where the weight of the number of events is determined based on the time of occurrence of the abnormal unlocking event; and to determine the vehicle's driving credit score based on the illegal parking severity score, the speeding severity score, and the unlocking anomaly score.

[0142] In one embodiment, the permission module is specifically used to perform a weighted summation of the number of occurrences of the abnormal unlocking event to determine an abnormality quantification value; the weight corresponding to the number of occurrences is determined according to the time interval between the occurrence time of the abnormal unlocking event and the current time; the abnormality quantification value and the penalty coefficient are used to determine the unlocking abnormality score of the vehicle; the penalty coefficient is determined according to the number of consecutive days the abnormal unlocking event occurs.

[0143] In one embodiment, the at least one preset scoring range includes a first scoring range and a second scoring range, wherein the second scoring range is smaller than the first scoring range; the permission module is specifically used to restrict the maximum speed of the vehicle to be less than a preset speed when the credit score meets the first scoring range; and to restrict the starting of the vehicle when the credit score meets the second scoring range.

[0144] Each module in the aforementioned vehicle authentication device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the intelligent vehicle in hardware form or independent of it, or stored in the memory of the intelligent vehicle in software form, so that the processor can call and execute the corresponding operations of each module.

[0145] In an exemplary embodiment, an intelligent vehicle is provided, comprising an on-board processing unit, the internal structure of which is shown in Figure 7. The on-board processing unit includes a processor, a memory, an input / output interface, and a communication interface. The processor, memory, and input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the on-board processing unit provides computing and control capabilities. The memory of the on-board processing unit includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the on-board processing unit stores data for implementing the aforementioned in-vehicle environment control method. The input / output interface of the on-board processing unit is used for exchanging information between the processor and external devices. The communication interface of the on-board processing unit is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a vehicle authentication method.

[0146] Those skilled in the art will understand that the structure shown in Figure 7 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the intelligent vehicle to which the present application is applied. A specific intelligent vehicle may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0147] In one exemplary embodiment, an intelligent vehicle is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0148] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0149] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0150] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0151] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0152] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0153] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A vehicle authentication method, characterized in that, The vehicle is equipped with a liveness detection component. The method includes: receiving a shared key and a current timestamp sent by a user terminal; generating a first token based on the shared key, vehicle identification information bound to the vehicle, and the current timestamp; the shared key is a one-time password generated by the user terminal when the user performs facial recognition; controlling the vehicle to be in an unlocked state when the first token matches a second token sent by the user terminal; the second token is generated by the user terminal based on the shared key, vehicle identification information pre-stored by the user terminal, and the current timestamp; and determining that the vehicle's authentication result for the user is successful when the user inside the vehicle passes the liveness detection component within a preset time and the distance between the user terminal and the vehicle meets a preset condition.

2. The method according to claim 1, characterized in that, The liveness detection component includes an in-vehicle infrared camera, and the method further includes: receiving infrared light signals reflected from the user's face through the in-vehicle infrared camera; extracting skin blood flow features of the face from the infrared light signals; and determining that the user has passed the liveness detection of the liveness detection component if the skin blood flow features conform to the liveness pattern.

3. The method according to claim 1, characterized in that, The method further includes: determining the vehicle's driving credit score based on at least one of the vehicle's illegal parking records, speeding records, and abnormal unlocking records; and controlling the vehicle's driving permissions based on a comparison of the driving credit score with at least one preset score range.

4. The method according to claim 3, characterized in that, The illegal parking record includes the number of illegal parking incidents; the speeding record includes the duration of each speeding incident; and the abnormal unlocking record includes the number of abnormal unlocking events. The step of determining the driving credit score of the vehicle based on at least one of the vehicle's illegal parking records, speeding records, and abnormal unlocking records includes: determining the severity score of the vehicle's illegal parking based on the number of illegal parking incidents; The speeding severity score of the vehicle is determined by weighted summation of the duration of each speeding violation; the weight corresponding to the duration of each speeding violation is determined based on the severity of each speeding violation. The unlocking anomaly score of the vehicle is determined by weighted summation of the number of occurrences of abnormal unlocking events; the weight corresponding to the number of occurrences is determined based on the occurrence time of the abnormal unlocking event. The driving credit score of the vehicle is determined based on the illegal parking severity score, the speeding severity score, and the unlocking anomaly score.

5. The method according to claim 4, characterized in that, The step of weighted summing of the number of occurrences of the abnormal unlocking events to determine the unlocking abnormality score of the vehicle includes: weighted summing of the number of occurrences of the abnormal unlocking events to determine an abnormality quantification value; the weight corresponding to the number of occurrences is determined based on the time interval between the occurrence time of the abnormal unlocking event and the current time; the unlocking abnormality score of the vehicle is determined based on the abnormality quantification value and the penalty coefficient; the penalty coefficient is determined based on the number of consecutive days the abnormal unlocking events occur.

6. The method according to claim 3, characterized in that, The at least one preset scoring interval includes a first scoring interval and a second scoring interval, wherein the second scoring interval is smaller than the first scoring interval; controlling the vehicle's driving permissions based on the comparison result between the driving credit score and at least one preset scoring interval includes: limiting the vehicle's maximum speed to less than a preset speed when the credit score meets the first scoring interval; and restricting the vehicle's starting when the credit score meets the second scoring interval.

7. A vehicle authentication device, characterized in that, The vehicle is equipped with a liveness detection component. The device includes: a generation module, used to receive a shared key and a current timestamp sent by a user terminal, and generate a first token based on the shared key, vehicle identification information bound to the vehicle, and the current timestamp; the shared key is a one-time password generated by the user terminal when the user performs facial recognition; a control module, used to control the vehicle to be in an unlocked state when the first token matches a second token sent by the user terminal; the second token is generated by the user terminal based on the shared key, vehicle identification information pre-stored by the user terminal, and the current timestamp; and an authentication module, used to determine that the vehicle's authentication result for the user is successful when the user inside the vehicle passes the liveness detection of the liveness detection component within a preset time and the distance between the user terminal and the vehicle meets a preset condition.

8. An intelligent vehicle, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images