Vehicle control method and system

Abstract

The invention provides a vehicle control method and system, and the method comprises the steps: enabling a terminal device to serve as a digital key of a vehicle through short-distance wireless communication connection between the vehicle and the terminal device; when the method is applied to a vehicle, the method comprises the steps that when a disconnection event of short-distance wireless communication connection with terminal equipment is detected, vehicle locking failure risk parameters in a current scene are predicted based on a vehicle locking failure risk prediction model; wherein the cloud platform summarizes and analyzes vehicle leaving scene data packets reported by each vehicle to obtain a vehicle locking failure risk prediction model, and issues the vehicle locking failure risk prediction model to each vehicle; executing a corresponding vehicle control strategy according to the vehicle locking failure risk parameter; wherein the vehicle control strategy comprises a prompting strategy and / or an automatic locking strategy. Therefore, the safety of the vehicle can be guaranteed, and the vehicle using safety and convenience of the user are improved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a vehicle control method and system. Background Technology

[0002] With the development of intelligent connected vehicle technology, digital keys based on near-field wireless communication are widely used due to their convenience. A digital key generally refers to a solution where a terminal device (such as a mobile phone, smartwatch, or smart bracelet) is transformed into a car key by installing a key application within it. With a digital key, the vehicle can automatically lock after the user leaves the vehicle, achieving the "automatic locking upon leaving the vehicle" function.

[0003] However, in practical applications, the wireless communication connection between the digital key and the vehicle may be unexpectedly interrupted due to reasons such as battery depletion or signal obstruction. In such cases, users often fail to notice the disconnection in time, leading them to mistakenly believe that the digital key is still within range and the vehicle will automatically lock. In reality, the premature disconnection of the digital key results in a failed locking process, increasing the risk of vehicle theft and compromising vehicle security. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a vehicle control method and system that can ensure vehicle safety and improve the safety and convenience of users using the vehicle.

[0005] This application provides a vehicle control method applied to a vehicle, wherein the vehicle uses a terminal device as a digital key via a short-range wireless communication connection with the terminal device; the method includes: When a short-range wireless communication connection disconnection event is detected with the terminal device, the vehicle locking failure risk parameters in the current scenario are predicted based on the vehicle locking failure risk prediction model; wherein, the vehicle locking failure risk prediction model is obtained by the cloud platform by summarizing and analyzing the data packets of the vehicle departure scenario reported by each vehicle, and the vehicle locking failure risk prediction model is distributed to each vehicle. The corresponding vehicle control strategy is executed based on the vehicle locking failure risk parameters; wherein, the vehicle control strategy includes a prompt strategy and / or an automatic locking strategy.

[0006] This application also provides a vehicle control method, which is applied to a cloud platform and includes: Receive data packets of vehicle departure scenarios reported by each vehicle; A vehicle locking failure risk prediction model was obtained by summarizing and analyzing the data packets from the vehicle departure scenario. The vehicle locking failure risk prediction model is distributed to each vehicle so that when each vehicle detects a disconnection event in the short-range wireless communication connection with the terminal device, it predicts the vehicle locking failure risk parameters in the current scenario based on the vehicle locking failure risk prediction model and executes the corresponding vehicle control strategy. The terminal device serves as the vehicle's digital key through the short-range wireless communication connection. The vehicle control strategy includes a prompt strategy and / or an automatic locking strategy.

[0007] This application embodiment also provides a vehicle control system, the system including a vehicle and a cloud platform; the vehicle uses a terminal device as a digital key for the vehicle via a short-range wireless communication connection; The vehicle is used to report off-vehicle scenario data packets to the cloud platform and receive a vehicle locking failure risk prediction model issued by the cloud platform; when a short-range wireless communication connection with the terminal device is detected to be disconnected, the vehicle locking failure risk parameters in the current scenario are predicted based on the vehicle locking failure risk prediction model; and the corresponding vehicle control strategy is executed according to the vehicle locking failure risk parameters; wherein, the vehicle control strategy includes a prompt strategy and / or an automatic locking strategy. The cloud platform is used to receive data packets of vehicle departure scenarios reported by each vehicle; summarize and analyze the data packets of vehicle departure scenarios reported by each vehicle to obtain a vehicle locking failure risk prediction model; and distribute the vehicle locking failure risk prediction model to each vehicle.

[0008] This application provides a vehicle control method and system. When the vehicle detects a disconnection event in the short-range wireless communication connection with the terminal device, it predicts the locking failure risk parameters in the current scenario based on a locking failure risk prediction model. Then, it executes corresponding prompting strategies and / or automatic locking strategies according to the locking failure risk parameters. In this way, when the wireless communication connection between the digital key and the vehicle is unexpectedly interrupted, resulting in a risk of locking failure, the vehicle can proactively prompt the user and / or automatically lock, thereby ensuring vehicle safety and improving the user's safety and convenience. Furthermore, the locking failure risk prediction model is obtained by aggregating massive amounts of data packets from off-vehicle scenarios reported by various vehicles through big data analysis on a cloud platform, resulting in high accuracy in predicting locking failure risks.

[0009] 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

[0010] 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.

[0011] Figure 1 One of the flowcharts of a vehicle control method provided in an embodiment of this application is shown; Figure 2 A second flowchart of a vehicle control method provided in an embodiment of this application is shown; Figure 3 This paper shows a schematic diagram of the structure of a vehicle control system provided in an embodiment of this application; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0012] 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. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally 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 represents selected embodiments of this application. Based on the embodiments of this application, every other embodiment obtained by those skilled in the art without inventive effort falls within the scope of protection of this application.

[0013] Research has shown that with the development of intelligent connected vehicle technology, digital keys based on near-field communication are widely used due to their convenience. A digital key generally refers to a solution where a terminal device (such as a mobile phone, smartwatch, or smart bracelet) is transformed into a car key by installing a key application within it. With a digital key, the vehicle can automatically lock after the user leaves, achieving the "automatic locking upon leaving the vehicle" function.

[0014] However, in practical applications, the wireless communication connection between the digital key and the vehicle may be unexpectedly interrupted due to reasons such as battery depletion or signal obstruction. In such cases, users often fail to notice the disconnection in time, leading them to mistakenly believe that the digital key is still within range and the vehicle will automatically lock. In reality, the premature disconnection of the digital key results in a failed locking process, increasing the risk of vehicle theft and compromising vehicle security.

[0015] Based on this, embodiments of this application provide a vehicle control method and system to ensure vehicle safety and improve the safety and convenience of users using vehicles.

[0016] The vehicle control system in this embodiment includes a vehicle and a cloud platform; each vehicle is communicatively connected to the cloud platform, and data can be transmitted between each vehicle and the cloud platform.

[0017] In this embodiment, the vehicle uses a short-range wireless communication connection with a terminal device, which then functions as the vehicle's digital key. This allows vehicle users to use only the terminal device, eliminating the need for a traditional car key, and enabling functions such as active unlocking, locking, and keyless entry. The terminal device can be a mobile phone, a smartwatch, or a wearable device such as a smart bracelet. Therefore, the vehicle control system in this embodiment may also include terminal devices connected to each vehicle.

[0018] As a user carrying a terminal device approaches the vehicle, the terminal device establishes a short-range wireless communication connection with the in-vehicle equipment. It is understood that short-range wireless communication may include one or more of Bluetooth communication, infrared communication, WiFi communication, and Ultra Wide Band (UWB) communication; this application embodiment does not limit this. In the following specific embodiments of this application, Bluetooth communication will be used as an example for detailed description.

[0019] As an example, if a vehicle user carries a terminal device, such as a smartphone, and approaches the vehicle, the smartphone establishes a Bluetooth connection with the vehicle's onboard equipment, then the smartphone can be used as a digital key for the vehicle.

[0020] Please see Figure 1 , Figure 1 This is one of the flowcharts for a vehicle control method provided in an embodiment of this application. The method provided in this embodiment is applied to a vehicle, specifically a vehicle-side device. Figure 1 As shown in the embodiments of this application, the method includes: S101. When a short-range wireless communication connection disconnection event is detected with the terminal device, the vehicle locking failure risk parameters in the current scenario are predicted based on the vehicle locking failure risk prediction model.

[0021] Specifically, the cloud platform collects and analyzes the data packets of vehicle departure scenarios reported by each vehicle to obtain the vehicle locking failure risk prediction model, and then distributes the vehicle locking failure risk prediction model to each vehicle.

[0022] Therefore, in this step, the vehicle in this embodiment of the application has the ability to predict the risk of locking failure. When a disconnection event is detected, the scene parameters of the current scene in which the vehicle is located at the time of the disconnection event can be captured. Based on the locking failure risk prediction model and the scene parameters, the locking failure risk parameters in the current scene are predicted. Here, the locking failure risk parameters can be expressed as the probability of locking failure, the risk level of locking failure, the location of high-risk locking failure, the time period of locking failure, etc.

[0023] S102. Execute the corresponding vehicle control strategy according to the vehicle locking failure risk parameters; wherein, the vehicle control strategy includes a prompt strategy and / or an automatic locking strategy.

[0024] It should be noted that in this step, the vehicle may only execute the prompting strategy, only the automatic locking strategy, or both the prompting strategy and the automatic locking strategy, and the execution order can be sequential or simultaneous. The locking failure risk parameter is related to the vehicle control strategy. For example, when the locking failure risk parameter indicates a low risk, only the prompting strategy is executed; when the indicated risk is high, the automatic locking strategy is executed. Alternatively, the locking failure risk parameter may be related to the aggressiveness of the executed vehicle control strategy; when the indicated risk is high, the executed vehicle control strategy is more aggressive.

[0025] The vehicle control method provided in this application embodiment ensures vehicle safety and improves user security and convenience when the wireless communication connection between the digital key and the vehicle is unexpectedly interrupted, posing a risk of locking failure. Furthermore, the locking failure risk prediction model is obtained through big data analysis of massive amounts of data packets from various vehicles reported by the cloud platform, demonstrating high accuracy in predicting locking failure risks.

[0026] In an optional embodiment, regarding step S101, the method of detecting the disconnection event of the short-range wireless communication connection with the terminal device may include: Step a1: Detect the connection signal of the short-range wireless communication connection with the terminal device, the locking signal of the driver's seat belt, and / or the opening and closing signal of the vehicle door.

[0027] In practice, the Bluetooth communication module (BTM) in the vehicle is used to detect the connection signal with the Bluetooth key; the airbag control module (ACU) is used to detect the locking signal of the driver's seat belt; and the body control module (IBCM) is used to detect the opening and closing signals of the doors.

[0028] Step a2: If the connection signal changes from connected to disconnected, and the lock signal changes from locked to unlocked; and / or, the connection signal changes from connected to disconnected, and the opening / closing signal of at least one door changes from closed to open, then it is determined that the disconnection event has been detected.

[0029] Here, for the connection signal: BTM detects that the Bluetooth key has been disconnected from the connection and feeds back the connection signal to the central control unit (CCU). The CCU routes the Bluetooth key status, that is, CCU_RPAIntrpt_BLELost=0x1:Connected switches to 0x0:Lost.

[0030] For the locking signal, the ACU detects the driver's seatbelt unlocking action and feeds it back to the CCU. The CCU transmits the seatbelt unlocking signal to the click control unit (MCU) on the main controller (IDCU) side. The MCU reports to the instrument panel. The instrument panel receives the signal and the driver's seatbelt is unlocked. The driver's seatbelt status changes from locked to unlocked: that is: ACU_DrvrSeatBltSts = 0x0: Buckle Lock switches to 0x1: Buckle Unlock.

[0031] For opening / closing signals, the IBCM detects changes in the opening / closing state of the doors (including side doors and / or tailgate) and feeds this information back to the CCU. The CCU then transmits the door status to the MCU on the IDCU side. The MCU reports this to the instrument cluster. Upon receiving this information, the door changes from fully closed to open. Taking the four side doors and tailgate as an example: When the four side doors and the tailgate are closed: IBCM_DoorDrveClsSt = 0x0:Close and IBCM_DoorPassClsSt = 0x0:Close and IBCM_DoorReLeClsSt =0x0:Close and IBCM_DoorReRiClsSt = 0x0:Close and TLCM_L_TrunkOpenCloseSts = 0x0: fully locked.

[0032] When any one of the four side doors and the tailgate is open: IBCM_DoorDrveClsSt = 0x1:open or IBCM_DoorPassClsSt = 0x1:open or IBCM_DoorReLeClsSt =0x1:open or IBCM_DoorReRiClsSt = 0x1:open or TLCM_L_TrunkOpenCloseSts! = 0x0: fully locked.

[0033] In this step, if the instrument panel detects that the connection signal changes from connected to disconnected and the lock signal changes from locked to unlocked; and / or, the connection signal changes from connected to disconnected and the open / close signal of at least one door changes from closed to open, then a disconnection event is determined to have been detected. Furthermore, the instrument panel can also prompt the user via a pop-up window on the vehicle's central control screen: "Bluetooth key has been disconnected; please reconnect to avoid locking failure."

[0034] It should be noted that during one ignition cycle of the vehicle, the above-mentioned trigger conditions for the connection signal and lock signal are displayed only once when they are met, and the above-mentioned trigger conditions for the connection signal and open / close signal are also displayed only once when they are met. When the two trigger conditions are met sequentially, if the time interval is less than a predetermined interval (e.g., 10 seconds), the display will not be repeated when the later trigger condition is met; if the time interval is greater than or equal to the predetermined interval, the display will be executed when the later trigger condition is met. This ensures the simplicity of the display, improves the interactive effect, and avoids repeatedly disturbing the user.

[0035] In another optional embodiment, regarding step S101, when the vehicle locking failure risk prediction model is a machine learning model, predicting the vehicle locking failure risk parameters in the current scenario based on the vehicle locking failure risk prediction model may include: A scene feature representation is constructed based on the scene parameters of the current scene. The scene feature representation is then input into the vehicle locking failure risk prediction model to obtain the vehicle locking failure risk parameters output by the vehicle locking failure risk prediction model.

[0036] The scenario parameters for the current scenario may include at least one of the following: vehicle parameters at the time of the disconnection event, environmental parameters, and user driving habit parameters obtained with prior user authorization.

[0037] Here, scene feature representations that characterize the current scene are extracted from the scene parameters of the current scene. The scene feature representations are then input into the vehicle locking failure risk prediction model. Based on the knowledge learned during the training process, the vehicle locking failure risk prediction model can predict the vehicle locking failure risk parameters in the current scene.

[0038] or, When the vehicle locking failure risk prediction model is a vehicle locking failure risk probability table, the vehicle locking failure risk parameters predicted based on the vehicle locking failure risk prediction model in the current scenario may include: Based on the scenario parameters of the current scenario, the vehicle locking failure risk probability table is consulted to determine the vehicle locking failure risk parameters for the current scenario.

[0039] The vehicle locking failure risk probability table includes the vehicle locking failure probability under different scenario parameter dimensions. Thus, by looking up the corresponding dimension in the vehicle locking failure risk probability table according to the scenario parameters, the vehicle locking failure risk parameter corresponding to the scenario parameters of the current scenario can be determined.

[0040] Alternatively, when the vehicle locking failure risk prediction model is a machine learning model and a vehicle locking failure risk probability table, the prediction results of the two models can be combined using methods such as weighted summation to determine the vehicle locking failure risk parameters corresponding to the current scenario. The specific method for obtaining the vehicle locking failure risk prediction model will be described in the subsequent implementation details of the cloud platform.

[0041] In one optional embodiment, the vehicle locking failure risk parameter indicates the vehicle locking failure risk level of the current scenario. For example, the vehicle locking failure risk level can be divided into high risk, medium risk, and low risk.

[0042] In a first possible implementation, step S102 may include: prompting the user through at least one interactive method under the risk level of the car locking failure.

[0043] The intensity of the prompts varies depending on the risk level of the vehicle locking failure. The interaction methods include: controlling the vehicle's sound system to emit a sound, controlling the vehicle's display system to show the prompt information, controlling the vehicle's lights to illuminate, and pushing messages to the terminal device. In one example, low risk (<2%): basic prompts are given; medium risk (2%-10%): enhanced prompts are given (rapid beeping + APP notification); high risk (>10%): strong prompts are given (horn + final warning), and the automatic locking recovery mechanism is prepared to be triggered more aggressively.

[0044] In another example, when a Bluetooth disconnection event occurs, if there are no lock failure risk parameters or the lock failure risk level is low, a basic first-level prompt can be executed, such as: a traditional beep + hazard lights + instrument panel pop-up; if the lock failure risk level is medium or high, a second-level enhanced prompt can be executed, such as: a continuous, rapid beep + horn blast (which can be set to a short single sound) + sending a push message to the terminal device (such as the user's mobile APP) via the cloud platform, with the message content: "Your vehicle is still unlocked!".

[0045] In this way, different levels of alerts for different lock failure risk levels have different alert strengths, allowing users to intuitively and conveniently perceive the risk of lock failure when Bluetooth is disconnected. Indirectly, this helps users to proactively lock their vehicles to ensure vehicle security.

[0046] In a second possible implementation, when the vehicle locking failure risk parameter indicates that the vehicle locking failure risk in the current scenario is high, step S102 may further include: If the vehicle remains unlocked within a preset time period after prompting the user through at least one interaction method under the aforementioned vehicle lock failure risk level, then, if the vehicle meets the safety conditions, the vehicle will be automatically locked, and a vehicle lock notification will be pushed to the terminal device.

[0047] Here, after a period of time following the enhanced prompt (e.g., 2 minutes), if the vehicle is still unlocked and meets safety requirements, the vehicle will push a locking notification to the terminal device (such as the user's mobile app) via the cloud platform. The message will read: "The vehicle will automatically lock in 30 seconds!" or "Risk detected, your vehicle has automatically locked at [location xx], please be aware!" Simultaneously, the automatic locking mechanism will be controlled, including controlling the door locks to perform the locking action and simultaneously closing all open windows and sunroof.

[0048] Safety conditions include: in-vehicle status sensors confirming the absence of living beings inside the vehicle (to prevent children / pets from being locked inside); and the vehicle being in the off-road or parked position.

[0049] It should be noted that the prerequisite for the vehicle to execute the method in this embodiment is that the automatic door locking function needs to be activated in advance. Specifically, the user can set the automatic door locking function to the enabled state on the IDCU central control screen. The IDCU setting application responds to the user setting and sends IDCU_DepartAutoLockSet = 0x1, Disable (disable) through the MCU. The IBCM responds to the user setting and feeds back the automatic door locking function as enabled: IBCM_DepartAutoLockRes = 0x1, Enable (enabled).

[0050] Furthermore, the method in this application embodiment also includes: When the vehicle is determined to enter a high-risk scenario for locking failure based on the vehicle locking failure risk prediction model, the user is given a pre-warning of the risk of locking failure.

[0051] At this time, when the vehicle determines through the positioning module that it has entered a high-risk scenario for locking failure set in the vehicle locking failure risk prediction model (such as being turned off in a high-risk area and / or during a high-risk period), the user can be reminded in advance through interactive methods such as the central control screen or voice. The prompt can be: "You have entered a high-frequency area where you forget to lock your car. Please pay attention to the locking prompt after leaving the car."

[0052] In this way, even if the Bluetooth connection is not lost, the system can proactively alert the user to the risk of locking failure identified through big data analysis, thereby further ensuring vehicle security.

[0053] Furthermore, in this embodiment of the application, the step of determining the off-vehicle scenario data packet by the vehicle includes: Step b1: When a short-range wireless communication connection disconnection event is detected with the terminal device, determine the identification data of the disconnection event, the scene parameters at the moment of disconnection, and the vehicle locking result data within a predetermined time period after the disconnection event occurs.

[0054] Step b2: Anonymize and encapsulate the identification data of the disconnection event, the scene parameters at the moment of disconnection, and the vehicle locking result data into the vehicle departure scene data packet.

[0055] Each vehicle departure scenario data packet in this application embodiment is a structured data object, representing a complete Bluetooth key disconnection event. It should be noted that the vehicle departure scenario data packet in this application embodiment is obtained based on prior user authorization, and it includes the following parts: The identification data for disconnection events may include: (1) event_id: a unique event identifier (GUID) used for deduplication and tracking. (2) vin_hash: vehicle identification number (VIN); preferably, the vehicle identification number can be anonymously hashed to obtain a hash value instead of the original VIN, which is used to anonymize the tracking of continuous behavior of the same vehicle while protecting user privacy. (3) timestamp: the timestamp of the event (ISO 8601 format, accurate to milliseconds), for example, 2023-08-15T21:30:45.123Z. (4) data_version: the data packet version number, used for compatibility with subsequent format upgrades.

[0056] Scene parameters at the moment of disconnection can include: vehicle location (e.g., coordinates or point of interest), disconnection time (e.g., date, day of the week, and time of day), vehicle status data (ignition status, gear position), and ambient environment (e.g., noise, visibility). In one example, scene parameters are represented as: bluetooth_event: "disconnected" (Event type, fixed as disconnected). gnss_data: { latitude: 39.9042 longitude: 116.4074 accuracy: 15, / / Positioning accuracy (meters) geofence_id: "home_parking_lot_A" / / Identifier of POI (Point of Interest) matched by geofencing } vehicle_status: { ignition_status: "off", gear_position: "P", door_status: {driver_door: "open", other_doors: "closed"}, window_status: "all_closed", trunk_status: "closed" } environment_estimate: { ambient_noise_level: "high", / / Ambient noise level (low / medium / high) estimated using in-vehicle microphones. time_of_day: "night", / / A rough determination based on location and time (dawn / morning / afternoon / evening / night) day_of_week: 1 / / Day of the week, 0 for Sunday, 1 for Monday, and so on. }

[0057] For vehicle locking result data, it can include `lockoutcome` (locking result) and `outcome_timestamp` (timestamp confirming the locking result). The locking result includes successful locking and failed locking. For failed locking, if the vehicle does not detect a valid locking signal (including Bluetooth key reconnection and locking, locking via mobile app, physical key, etc.) within a time window T1 (e.g., 10 minutes) after Bluetooth disconnection, it is marked as "failed". For successful locking, if the vehicle detects any locking signal within the time window T1, it is marked as "success".

[0058] Furthermore, the locking result also includes special cases reported by the user. Specifically, if the Bluetooth key re-enters the range and reconnects within time T1, but the car is not locked, this may mean the user only temporarily left. In this case, the T1 timer can be reset to await the final result; alternatively, this can be treated as an independent "temporary interruption" event, discarding the data and not reporting it as a locking failure case to avoid noisy data.

[0059] In implementation, firstly, when the vehicle's Bluetooth module detects a disconnection from the authenticated Bluetooth key, it immediately sends an event signal to the main controller, triggering the collection of the vehicle departure scenario data packet. Next, the main controller freezes the current vehicle status, location, time, and other information to form an initial departure scenario data packet; at this point, `lockoutcome` is still empty. Then, the main controller starts a timer for a period of T1 (e.g., 10 minutes) and listens for all possible locking signals; the main controller determines the locking result according to the aforementioned method, forming a complete departure scenario data packet. Finally, the departure scenario data packet is encrypted and temporarily stored in the vehicle's local storage. When the vehicle detects an available, low-cost wireless network, it uploads multiple cached data packets in batches to the cloud platform. Furthermore, to prevent storage overflow, a storage limit and a maximum cache time can be set.

[0060] This application provides a vehicle control method that predicts the risk of future vehicle locking failures based on a big data model. When the vehicle experiences Bluetooth disconnection in such scenarios, it triggers an enhanced prompt control strategy and an automatic locking control strategy to reduce the security risks of the vehicle not locking due to the user not noticing the disconnection, thereby improving vehicle anti-theft security.

[0061] The system employs a multi-level alert strategy, dynamically adjusting the alert intensity based on risk level. This ensures users receive a strong enough warning in high-risk situations while avoiding excessive disruption in low-risk scenarios, achieving a good balance between security and user experience. When the combined preconditions of a high-risk level, disconnection timeout, and vehicle safety confirmation are met, the vehicle can automatically lock and close windows, ensuring that even if the user does not respond to the alert, the vehicle will automatically lock and return to a safe state.

[0062] Please see Figure 2 , Figure 2 This is a second flowchart illustrating a vehicle control method according to another embodiment of this application. The method provided in this embodiment is applied to a cloud platform. Figure 2 As shown in the embodiments of this application, the method includes: S201, Receive data packets of vehicle departure scenarios reported by each vehicle.

[0063] S202. Summarize and analyze the data packets of the vehicle departure scenario to obtain the vehicle locking failure risk prediction model.

[0064] S203. The vehicle locking failure risk prediction model is distributed to each vehicle so that when each vehicle detects a disconnection event in the short-range wireless communication connection with the terminal device, it can predict the vehicle locking failure risk parameters in the current scenario based on the vehicle locking failure risk prediction model and execute the corresponding vehicle control strategy.

[0065] The cloud platform can distribute the vehicle locking failure risk prediction model to each vehicle via over-the-air (OTA) technology or conventional network communication; the terminal device serves as the vehicle's digital key through a short-range wireless communication connection; the vehicle control strategy includes a prompt strategy and / or an automatic locking strategy.

[0066] Furthermore, as mentioned above, the vehicle departure scenario data packet includes the identification data of the disconnection event, the scenario parameters at the moment of disconnection, and the vehicle locking result data within a predetermined time period after the disconnection event occurs.

[0067] In one possible implementation, regarding step S201, the cloud platform's data access service receives data packets from a massive number of vehicles. Then, the cloud platform preprocesses the data, including: (1) data cleaning; (2) format verification, checking whether the data packet format is compliant; (3) invalid data filtering, removing data with excessively low positioning accuracy (e.g., accuracy > 100 meters) or abnormal vehicle status (e.g., interrupted driving connection); and (4) deduplication: removing duplicate data packets based on event_id.

[0068] Furthermore, as mentioned above, the vehicle departure scenario data packet includes the identification data of the disconnection event, the scenario parameters at the moment of disconnection, and the vehicle locking result data within a predetermined time period after the disconnection event occurs.

[0069] In one possible implementation, step S202 may include: S2021. For each vehicle departure scenario data packet, convert the vehicle coordinates in the scenario parameters into location points of interest, and convert the timestamps in the scenario parameters into business time feature tags.

[0070] In this step, for coordinate location clustering: the original GPS coordinates are converted into meaningful location interest point labels through geocoding services, such as "Beijing XX District XX Shopping Mall B2 Parking Lot", and similar coordinate points are merged. For time feature labels, the time period is discretized, and the timestamp is mapped to business time feature labels with business significance, such as "Weekday commuting evening peak (18:00-19:30)", "Weekend afternoon (13:00-17:00)", "Late night (23:00-04:00)".

[0071] S2022. When the vehicle locking failure risk prediction model includes a machine learning model, a sample scenario feature representation set is constructed based on the identifier data of the disconnection event, the location point of interest, the business time feature label, and the vehicle locking result data in each vehicle departure scenario data packet; the machine learning model is trained based on the sample scenario feature representation set to obtain the vehicle locking failure risk prediction model.

[0072] In this step, each data packet representing a vehicle exit scene can be constructed into a sample scene feature representation by methods such as dimensional concatenation, forming a sample scene feature representation set. The method for training a machine learning model based on the sample scene feature representation set can refer to relevant implementations in existing technologies, and this application does not impose any limitations on this.

[0073] S2023. When the vehicle locking failure risk prediction model includes a vehicle locking failure risk probability table, group and aggregate according to the location points of interest and the business time feature labels to determine the total number of disconnection events in each group and the first number of disconnection events whose locking result data is a failure; determine the vehicle locking failure probability of the group based on the ratio between the first number and the total number; summarize the location points of interest, the business time feature labels and the vehicle locking failure probability of each group to form the vehicle locking failure risk probability table.

[0074] In this step, the data can be grouped by geofence_id, time_slot (e.g., 2 hours per time slot), and day_type (weekday / weekend); for each group, the probability of locking failure is calculated: failure rate = (number of data packets with lockoutcome = 'failed' in this group) / (total number of data packets in this group); finally, a global probability table of locking failure risk is generated. For example, Table 1 below is a probability table of locking failure risk provided in an embodiment of this application.

[0075] Table 1. Probability of Car Locking Failure

[0076] As can be seen from Table 1, the probability of bike locking failure at XX Gym on weekday evenings is as high as 10%, so the risk level of bike locking failure is high.

[0077] This application provides a vehicle control method in which a cloud platform aggregates massive data packets of vehicle departure scenarios reported by each vehicle, and obtains a vehicle locking failure risk prediction model through big data analysis. By collecting massive amounts of actual vehicle operation data (including vehicle locking success / failure result labels) through anonymization, the cloud platform can continuously iterate and optimize the risk prediction model, making the model prediction more and more accurate, and the prediction accuracy of vehicle locking failure risk is higher.

[0078] Please see Figure 3 , Figure 3 This is a schematic diagram of a vehicle control system provided in an embodiment of this application. The system includes a vehicle and a cloud platform; the vehicle uses a terminal device as a digital key via short-range wireless communication. Figure 3As shown, the vehicle control system includes multiple vehicles A1...An, where n is a positive integer greater than 1.

[0079] The vehicle is used to report off-vehicle scenario data packets to the cloud platform and receive a vehicle locking failure risk prediction model issued by the cloud platform; when a short-range wireless communication connection with the terminal device is detected to be disconnected, the vehicle locking failure risk parameters in the current scenario are predicted based on the vehicle locking failure risk prediction model; and the corresponding vehicle control strategy is executed according to the vehicle locking failure risk parameters; wherein, the vehicle control strategy includes a prompt strategy and / or an automatic locking strategy. The cloud platform is used to receive data packets of vehicle departure scenarios reported by each vehicle; summarize and analyze the data packets of vehicle departure scenarios reported by each vehicle to obtain a vehicle locking failure risk prediction model; and distribute the vehicle locking failure risk prediction model to each vehicle.

[0080] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 400 includes a processor 410, a memory 420, and a bus 430.

[0081] The memory 420 stores machine-readable instructions that can be executed by the processor 410. When the electronic device 400 is running, the processor 410 and the memory 420 communicate via the bus 430. When the machine-readable instructions are executed by the processor 410, the steps of the vehicle control method as described in the above method embodiment can be executed. For specific implementation details, please refer to the method embodiment, which will not be repeated here.

[0082] This application also provides a computer-readable storage medium storing a computer program. When the computer program is run by a processor, it can execute the steps of the vehicle control method as described in the above method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0083] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0084] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0085] The units described as separate components may or may not be physically separate. The components shown as units 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.

[0086] 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.

[0087] 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 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, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0088] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered 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 vehicle control method, characterized in that, The method is applied to a vehicle, which uses the terminal device as a digital key for the vehicle via a short-range wireless communication connection; the method includes: When a short-range wireless communication connection disconnection event is detected with the terminal device, the vehicle locking failure risk parameters in the current scenario are predicted based on the vehicle locking failure risk prediction model; wherein, the vehicle locking failure risk prediction model is obtained by the cloud platform by summarizing and analyzing the data packets of the vehicle departure scenario reported by each vehicle, and the vehicle locking failure risk prediction model is distributed to each vehicle. The corresponding vehicle control strategy is executed based on the vehicle locking failure risk parameters; wherein, the vehicle control strategy includes a prompt strategy and / or an automatic locking strategy.

2. The method according to claim 1, characterized in that, The vehicle locking failure risk parameter indicates the risk level of vehicle locking failure in the current scenario. Therefore, a corresponding vehicle control strategy is executed based on the vehicle locking failure risk parameter, including: The user is prompted through at least one interactive method under the aforementioned risk level of vehicle locking failure; The intensity of the prompts varies depending on the risk level of the vehicle locking failure. The interaction methods include: controlling the vehicle's sound device to make a sound, controlling the vehicle's display device to display prompt information, controlling the vehicle's lights to illuminate, and pushing messages to the terminal device.

3. The method according to claim 2, characterized in that, When the vehicle locking failure risk parameter indicates that the vehicle locking failure risk in the current scenario is high, the corresponding vehicle control strategy is executed according to the vehicle locking failure risk parameter, further including: If the vehicle remains unlocked within a preset time period after prompting the user through at least one interaction method under the aforementioned vehicle lock failure risk level, then, if the vehicle meets the safety conditions, the vehicle will be automatically locked, and a vehicle lock notification will be pushed to the terminal device.

4. The method according to claim 1, characterized in that, Detecting a disconnection event of the short-range wireless communication connection with the terminal device includes: The system detects the connection signal of the short-range wireless communication connection with the terminal device, as well as the locking signal of the driver's seat belt and / or the opening and closing signal of the vehicle door. If the connection signal changes from connected to disconnected, and the lock signal changes from locked to unlocked; and / or, the connection signal changes from connected to disconnected, and the open / close signal of at least one door changes from closed to open, then the disconnection event is determined to have been detected.

5. The method according to claim 1, characterized in that, When the vehicle locking failure risk prediction model includes a machine learning model, the prediction of vehicle locking failure risk parameters in the current scenario based on the vehicle locking failure risk prediction model includes: A scene feature representation is constructed based on the scene parameters of the current scene, and the scene feature representation is input into the vehicle locking failure risk prediction model to obtain the vehicle locking failure risk parameters output by the vehicle locking failure risk prediction model. or, When the vehicle locking failure risk prediction model includes a vehicle locking failure risk probability table, the vehicle locking failure risk probability table is searched according to the scenario parameters of the current scenario to determine the vehicle locking failure risk parameters under the current scenario; wherein, the vehicle locking failure risk probability table includes the vehicle locking failure probability corresponding to different scenario parameter dimensions.

6. The method according to claim 1, characterized in that, The method further includes: When the vehicle is determined to enter a high-risk scenario for locking failure based on the vehicle locking failure risk prediction model, the user is given a pre-warning of the risk of locking failure.

7. The method according to claim 1, characterized in that, The step of determining the vehicle exit scenario data packet includes: When a short-range wireless communication connection disconnection event is detected with the terminal device, the identification data of the disconnection event, the scene parameters at the moment of disconnection, and the vehicle locking result data within a predetermined time period after the disconnection event are determined. The identification data of the disconnection event, the scene parameters at the moment of disconnection, and the vehicle locking result data are anonymized and encapsulated into the vehicle departure scene data packet.

8. A vehicle control method, characterized in that, The method is applied to a cloud platform, and the method includes: Receive data packets of vehicle departure scenarios reported by each vehicle; A vehicle locking failure risk prediction model was obtained by summarizing and analyzing the data packets from the vehicle departure scenario. The vehicle locking failure risk prediction model is distributed to each vehicle so that when each vehicle detects a disconnection event in the short-range wireless communication connection with the terminal device, it predicts the vehicle locking failure risk parameters in the current scenario based on the vehicle locking failure risk prediction model and executes the corresponding vehicle control strategy. The terminal device serves as the vehicle's digital key through the short-range wireless communication connection. The vehicle control strategy includes a prompt strategy and / or an automatic locking strategy.

9. The method according to claim 8, characterized in that, The vehicle departure scenario data packet includes the identification data of the disconnection event, the scenario parameters at the moment of disconnection, and the vehicle locking result data within a predetermined time period after the disconnection event occurs. The data packets from the vehicle departure scenario are then analyzed to obtain a vehicle locking failure risk prediction model, including: For each vehicle exit scenario data packet, the vehicle coordinates in the scenario parameters are converted into location points of interest, and the timestamps in the scenario parameters are converted into business time feature tags. When the vehicle locking failure risk prediction model includes a machine learning model, a sample scenario feature representation set is constructed based on the identifier data of the disconnection event, the location point of interest, the business time feature label, and the vehicle locking result data in each vehicle departure scenario data packet; the machine learning model is trained based on the sample scenario feature representation set to obtain the vehicle locking failure risk prediction model; and / or, When the vehicle locking failure risk prediction model includes a vehicle locking failure risk probability table, it is grouped and aggregated according to the location points of interest and the business time feature labels to determine the total number of disconnection events in each group and the first number of disconnection events whose locking result data is a failure; the vehicle locking failure probability of the group is determined according to the ratio between the first number and the total number; the location points of interest, the business time feature labels and the vehicle locking failure probability of each group are summarized to form the vehicle locking failure risk probability table.

10. A vehicle control system, characterized in that, The system includes a vehicle and a cloud platform; the vehicle uses a terminal device as a digital key for the vehicle via a short-range wireless communication connection. The vehicle is used to report off-vehicle scenario data packets to the cloud platform and receive a vehicle locking failure risk prediction model issued by the cloud platform; when a short-range wireless communication connection with the terminal device is detected to be disconnected, the vehicle locking failure risk parameters in the current scenario are predicted based on the vehicle locking failure risk prediction model; and the corresponding vehicle control strategy is executed according to the vehicle locking failure risk parameters; wherein, the vehicle control strategy includes a prompt strategy and / or an automatic locking strategy. The cloud platform is used to receive data packets of vehicle departure scenarios reported by each vehicle; summarize and analyze the data packets of vehicle departure scenarios reported by each vehicle to obtain a vehicle locking failure risk prediction model; and distribute the vehicle locking failure risk prediction model to each vehicle.

Images