Vehicle false touch prevention unlocking method and device, processor, electronic equipment and vehicle

Abstract

The application discloses a vehicle anti-mis-touch unlocking method and device, a processor, an electronic device and a vehicle. The method is applied to a vehicle. The method comprises the following steps: acquiring Bluetooth communication data of the vehicle and a mobile terminal, touch data collected by a contact collection device of the vehicle, and vehicle environment data collected by a plurality of sensors; respectively preprocessing the Bluetooth communication data, the touch data and the vehicle environment data to obtain target Bluetooth communication data, target touch data and target vehicle environment data; inputting the target Bluetooth communication data, the target touch data and the target vehicle environment data into a preset prediction model to perform prediction, and obtaining a target control result; and controlling the vehicle to perform an operation indicated by the target control result. The application solves the technical problem of low unlocking safety of the vehicle.

Description

Technical Field

[0001] This application relates to the field of vehicles, and more specifically, to a method, apparatus, processor, electronic device, and vehicle for preventing accidental unlocking. Background Technology

[0002] Currently, Bluetooth key systems are widely used in vehicle unlocking methods. Traditional Bluetooth key systems mainly rely on signal parameters such as Received Signal Strength Indicator (RSSI). By comparing these signal parameters with preset thresholds, the vehicle can be unlocked or started.

[0003] However, when the vehicle is in a complex environment such as a parking lot, the traditional Bluetooth key system is prone to false triggering events. That is, without the user's actual intention, the vehicle may incorrectly respond to the unlock or start command and unlock or start itself, resulting in low vehicle unlocking security.

[0004] There is currently no effective solution to the aforementioned technical problems. Summary of the Invention

[0005] This application provides a method, apparatus, processor, electronic device, and vehicle for preventing accidental unlocking of a vehicle, in order to at least solve the technical problem of low unlocking security of vehicles.

[0006] According to one aspect of the embodiments of this application, a method for preventing accidental unlocking of a vehicle is provided, applied to a vehicle. The method includes: acquiring Bluetooth communication data between the vehicle and a mobile terminal, touch data collected by a contact acquisition device of the vehicle, and vehicle environmental data collected by multiple sensors. The Bluetooth communication data includes: Bluetooth signal strength data, Bluetooth signal arrival time data, Bluetooth signal frequency offset data, and Bluetooth signal jitter amplitude data of the mobile terminal. The touch data is used to represent the touch state between the vehicle door and the object to which the mobile terminal belongs. The vehicle environmental data includes at least two of the following: temperature data, humidity data, rainfall data, surrounding obstacle data, and user approach direction data of the vehicle's environment. The Bluetooth communication data, touch data, and vehicle environmental data are preprocessed to obtain target Bluetooth communication data, target touch data, and target vehicle environmental data. The target Bluetooth communication data, target touch data, and target vehicle environmental data are input into a preset prediction model for prediction to obtain a target control result. The prediction model is obtained by lightweight transformation of an initial prediction model (not for the vehicle). The target control result is used to instruct the vehicle to perform any of the following operations: unlocking, locking, or holding. The vehicle is then controlled to execute the operation indicated by the target control result.

[0007] This application, based on the acquisition of Bluetooth communication data, touch data, and vehicle environment data, preprocesses the aforementioned Bluetooth communication data, touch data, and vehicle environment data respectively to obtain target Bluetooth communication data, target touch data, and target vehicle environment data. These target Bluetooth communication data, target touch data, and target vehicle environment data are then input into a preset prediction model for prediction, resulting in a target control outcome. Finally, the vehicle is controlled to perform an unlocking operation, locking operation, or holding operation that satisfies the indication of the aforementioned target control outcome. This achieves the goal of reducing environmental interference with the target control outcome, thereby solving the technical problem of low vehicle unlocking security and ultimately improving the technical effect of vehicle unlocking security.

[0008] Optionally, controlling the vehicle to perform the operation indicated by the target control result includes: in response to the target control result being a first target control result, controlling the vehicle to perform an unlocking operation indicated by the first target control result, wherein the first target control result is used to instruct the vehicle to perform the unlocking operation; in response to the target control result being a second target control result, controlling the vehicle to perform a locking operation indicated by the second target control result, wherein the second target control result is used to instruct the vehicle to perform the locking operation; in response to the target control result being a third target control result, controlling the vehicle to perform a holding operation indicated by the third target control result, and returning to the step of inputting the target Bluetooth communication data, target touch data, and target vehicle environmental data into a prediction model for prediction to obtain the target control result, wherein the third target control result is used to instruct the vehicle to perform the holding operation.

[0009] Since the vehicle can be controlled to perform unlocking, locking, or holding operations based on different target control results, the interference of the environment on the target control results can be reduced, thereby solving the technical problem of low vehicle unlocking security and achieving the technical effect of improving vehicle unlocking security.

[0010] Optionally, the Bluetooth communication data, touch data, and vehicle environment data are preprocessed separately to obtain target Bluetooth communication data, target touch data, and target vehicle environment data, including: performing noise reduction processing on the Bluetooth communication data, touch data, and vehicle environment data respectively to obtain target Bluetooth communication data, noise-reduced touch data, and noise-reduced vehicle environment data; and performing normalization processing on the noise-reduced touch data and noise-reduced vehicle environment data respectively to obtain target touch data and target vehicle environment data.

[0011] By preprocessing the acquired Bluetooth communication data, touch data, and vehicle environment data separately, the goal of obtaining target Bluetooth communication data, target touch data, and target vehicle environment data that are easy for prediction models to process is achieved, thereby realizing the technical effect of improving the accuracy of target Bluetooth communication data, target touch data, and target vehicle environment data.

[0012] Optionally, the method further includes: acquiring Bluetooth communication data samples between the vehicle and the mobile terminal, touch data samples collected by the vehicle's contact acquisition device, and vehicle environment data samples collected by multiple sensors. The Bluetooth communication data samples include: strength data of the Bluetooth signal sample from the mobile terminal, arrival time data of the Bluetooth signal sample, frequency offset data of the Bluetooth signal sample, and jitter amplitude data of the Bluetooth signal sample. The touch data samples are used to represent the historical touch states between the vehicle door and its associated object. The vehicle environment data samples include at least two of the following: temperature data samples, humidity data samples, rainfall data samples, surrounding obstacle data samples, and user approach direction data samples of the vehicle's environment. The Bluetooth communication data samples, touch data samples, and vehicle environment data samples are cleaned and preprocessed to obtain target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples. An initial prediction model is trained using the target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples to obtain a first trained prediction model. The first trained prediction model is then lightweighted using the vehicle's performance parameters related to running different models to obtain a prediction model.

[0013] By utilizing the vehicle's performance parameters related to different models, the first trained prediction model can be lightweighted and transformed into a prediction model, thereby achieving the goal of obtaining a prediction model suitable for the vehicle and thus realizing the technical effect of improving the flexibility of the prediction model.

[0014] Optionally, the method further includes: optimizing the initial prediction model to obtain an optimized prediction model; training the optimized prediction model using target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples to obtain a second trained prediction model; performing a lightweight transformation on the second trained prediction model using performance parameters to obtain a lightweight prediction model; and upgrading the prediction model to a lightweight prediction model.

[0015] By performing a model upgrade operation on the above-mentioned prediction model, it can be upgraded to a lightweight prediction model, thereby achieving the goal of upgrading the prediction model and thus realizing the technical effect of improving the accuracy of the prediction model.

[0016] Optionally, the Bluetooth communication data samples, touch data samples, and vehicle environment data samples are cleaned and preprocessed to obtain target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples, including: performing missing data processing on the Bluetooth communication data samples, touch data samples, and vehicle environment data samples to obtain missing data processed Bluetooth communication data samples, missing data processed touch data samples, and missing data processed vehicle environment data samples; performing anomaly filtering on the missing data processed Bluetooth communication data samples, missing data processed touch data samples, and missing data processed vehicle environment data samples to obtain target Bluetooth communication data samples, filtered touch data samples, and filtered vehicle environment data samples; and performing normalization processing on the filtered touch data samples and filtered vehicle environment data samples to obtain target touch data samples and target vehicle environment data samples.

[0017] By cleaning and preprocessing the Bluetooth communication data samples, touch data samples, and vehicle environment data samples respectively, the goal of obtaining target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples that are easy to train the initial prediction model is achieved, thereby realizing the technical effect of improving the accuracy of target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples.

[0018] According to one aspect of the embodiments of this application, a vehicle anti-accidental touch unlocking device is provided. The device may include: an acquisition unit, configured to acquire Bluetooth communication data between the vehicle and a mobile terminal, touch data collected by a contact acquisition device of the vehicle, and vehicle environmental data collected by multiple sensors. The Bluetooth communication data includes: Bluetooth signal strength data of the mobile terminal, Bluetooth signal arrival time data, Bluetooth signal frequency offset data, and Bluetooth signal jitter amplitude data. The touch data is used to indicate the touch state between the vehicle door and the object to which the mobile terminal belongs. The vehicle environmental data includes at least two of the following: temperature data, humidity data, and rainfall data of the vehicle's environment. The system includes: a target Bluetooth communication data unit, a target touch data unit, and a target vehicle environment data unit; a target Bluetooth communication data unit, a target touch data unit, and a target vehicle environment data unit; a prediction unit, a target prediction model, and a target control result unit; and an execution unit, a control unit that controls the vehicle to perform the operation indicated by the target control result. The prediction model is a lightweight transformation of the initial prediction model for non-vehicle components.

[0019] According to another aspect of the embodiments of this application, a processor is also provided. The processor is used to run a program, wherein the program is executed by the processor to perform the methods described in the embodiments of this application.

[0020] According to another aspect of the embodiments of this application, an electronic device is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of this application when it runs.

[0021] According to another aspect of the embodiments of this application, a vehicle is also provided, including the electronic device described in this application.

[0022] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided. This computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the methods of the embodiments of this application.

[0023] According to another aspect of the embodiments of this application, a computer program product is also provided, the computer program product including a computer program, wherein the computer program implements the method in the embodiments of this application when executed by a processor.

[0024] According to another aspect of the embodiments of this application, a computer program product is also provided, including a non-volatile computer-readable storage medium for storing a computer program, which, when executed by a processor, implements the method in the embodiments of this application.

[0025] According to another aspect of the embodiments of this application, the embodiments of this application also provide a computer program that, when executed by a processor, implements the methods described in the embodiments of this application.

[0026] In this embodiment, during the vehicle unlocking process, Bluetooth communication data between the vehicle and the mobile terminal, touch data collected by the vehicle's contact acquisition device, and vehicle environmental data collected by various sensors are acquired. The Bluetooth communication data, touch data, and vehicle environmental data are preprocessed to obtain target Bluetooth communication data, target touch data, and target vehicle environmental data. These data are then input into a preset prediction model for prediction to obtain a target control result. The vehicle is then controlled to execute the operation indicated by the target control result. Because this application preprocesses the Bluetooth communication data, touch data, and vehicle environmental data based on the acquired data, and inputs them into a preset prediction model for prediction to obtain a target control result, the vehicle is finally controlled to perform an unlocking, locking, or holding operation that satisfies the target control result indication. This reduces environmental interference with the target control result, thus solving the technical problem of low vehicle unlocking security and improving vehicle unlocking security. Attached Figure Description

[0027] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0028] Figure 1 This is a flowchart of a method for preventing accidental unlocking of a vehicle according to an embodiment of this application;

[0029] Figure 2 This is a flowchart of a method for generating a lightweight vehicle-side model according to an embodiment of this application;

[0030] Figure 3 This is a flowchart of a method for generating a preliminary model according to an embodiment of this application;

[0031] Figure 4 This is a flowchart of a method for preventing accidental triggering of a vehicle Bluetooth key based on a lightweight large model of the vehicle end, according to an embodiment of this application;

[0032] Figure 5 This is a schematic diagram of a vehicle anti-accidental unlocking device according to an embodiment of this application;

[0033] Figure 6 This is a schematic diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0034] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present application.

[0035] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0036] According to an embodiment of this application, a method for preventing accidental unlocking of a vehicle is provided. This method is applied to a vehicle. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0037] Figure 1 This is a flowchart of a method for preventing accidental unlocking of a vehicle according to an embodiment of this application, such as... Figure 1 As shown, the method may include the following steps:

[0038] Step S101: Acquire Bluetooth communication data between the vehicle and the mobile terminal, touch data collected by the vehicle's contact acquisition device, and vehicle environmental data collected by various sensors.

[0039] In the technical solution provided in step S101 of this application, the Bluetooth communication data may include: Bluetooth signal strength data of the mobile terminal, Bluetooth signal arrival time data, Bluetooth signal frequency offset data, and Bluetooth signal jitter amplitude data. Specifically, the Bluetooth signal strength data can be used to represent the strength of the Bluetooth signal, the Bluetooth signal arrival time data can be used to represent the Bluetooth signal arrival time difference, the Bluetooth signal frequency offset data can be used to represent the degree of frequency offset of the Bluetooth signal, and the Bluetooth signal jitter amplitude data can be used to represent the jitter amplitude of the Bluetooth signal.

[0040] In this embodiment, the mobile terminal can be used as a carrier representing the vehicle's digital key. For example, the carrier can be an electronic device that communicates with the vehicle via Bluetooth and initiates unlocking / locking operations on the vehicle.

[0041] In this embodiment, the Bluetooth signal can be a Bluetooth unlock signal, a Bluetooth lock signal, or a Bluetooth hold signal. This is only an example and is not a specific limitation.

[0042] In this embodiment, the touch data can be used to represent the touch state between the vehicle door and the mobile terminal's owner. For example, the touch state can be that the door has been touched by the owner (referred to as the door touch state), or the touch state can be that the door has not been touched by the owner (referred to as the door not touch state). The owner can be the vehicle owner or another person authorized by the vehicle owner.

[0043] In this embodiment, the contact acquisition device for the vehicle may include a door handle capacitive sensor.

[0044] In this embodiment, the vehicle environment data may include at least two of the following: temperature data, humidity data, rainfall data, surrounding obstacle data, and user approach direction data. Specifically, the temperature data represents the temperature of the vehicle's environment, the humidity data represents the humidity of the vehicle's environment, the rainfall data represents the rainfall in the vehicle's environment, the surrounding obstacle data represents the location and state of obstacles in the vehicle's environment, and the user approach direction data represents the direction of the vehicle owner relative to the vehicle, or the direction of another person with the owner's permission relative to the vehicle.

[0045] In this embodiment, the aforementioned multiple sensors may include: temperature sensors, humidity sensors, rain sensors, ultrasonic sensors, vehicle-mounted cameras, and GPS-based locators, etc.

[0046] In this embodiment, Bluetooth communication data between the vehicle and the mobile terminal, touch data collected by the vehicle's contact acquisition device, and vehicle environmental data collected by various sensors are acquired. Optionally, after the vehicle and the mobile terminal establish a Bluetooth connection, this embodiment can acquire Bluetooth communication data between the vehicle and the mobile terminal through Bluetooth sensors, touch data through the contact acquisition device, and vehicle environmental data through various sensors. Subsequently, by accessing the Bluetooth sensors, Bluetooth communication data can be obtained; by accessing the contact acquisition device, touch data can be obtained; and by accessing the various sensors, vehicle environmental data can be obtained, thereby achieving the purpose of acquiring Bluetooth communication data, touch data, and vehicle environmental data.

[0047] Step S102: Preprocess the Bluetooth communication data, touch data, and vehicle environment data respectively to obtain target Bluetooth communication data, target touch data, and target vehicle environment data.

[0048] In the technical solution provided by step S102 of this application, the preprocessing may include noise reduction processing and normalization processing.

[0049] In this embodiment, the target Bluetooth communication data, target touch data, and target vehicle environment data can be data suitable for processing by the prediction model. Specifically, the target Bluetooth communication data is preprocessed Bluetooth communication data, the target touch data is preprocessed touch data, and the target vehicle environment data is preprocessed vehicle environment data.

[0050] In this embodiment, after acquiring Bluetooth communication data between the vehicle and the mobile terminal, touch data collected by the vehicle's contact acquisition device, and vehicle environmental data collected by various sensors, the Bluetooth communication data, touch data, and vehicle environmental data are preprocessed to obtain target Bluetooth communication data, target touch data, and target vehicle environmental data, respectively. Optionally, based on the acquired Bluetooth communication data, touch data, and vehicle environmental data, this embodiment preprocesses the Bluetooth communication data to obtain target Bluetooth communication data, preprocesses the touch data to obtain target touch data, and preprocesses the vehicle environmental data to obtain target vehicle environmental data. This achieves the goal of converting Bluetooth communication data into target Bluetooth communication data, touch data into target touch data, and vehicle environmental data into target vehicle environmental data.

[0051] Step S103: Input the target Bluetooth communication data, target touch data and target vehicle environment data into the preset prediction model for prediction to obtain the target control result.

[0052] In the technical solution provided in step S103 of this application, the preset prediction model is obtained by transforming the initial prediction model for non-vehicle applications. The preset prediction model can be deployed in the vehicle-side lightweight large model module, and the initial prediction model for non-vehicle applications can also be referred to as the initial version model.

[0053] In this embodiment, the target control result described above can be used to instruct the vehicle to perform any of the following operations: unlocking, locking, or holding.

[0054] In this embodiment, after preprocessing the Bluetooth communication data, touch data, and vehicle environment data to obtain target Bluetooth communication data, target touch data, and target vehicle environment data, these data are input into a preset prediction model for prediction to obtain the target control result. Optionally, this embodiment, based on obtaining the target Bluetooth communication data, target touch data, and target vehicle environment data, inputs these data into a preset prediction model and uses the prediction model to predict the target Bluetooth communication data, target touch data, and target vehicle environment data to obtain the target control result. This achieves the purpose of determining the desired control method of the vehicle door by the mobile terminal.

[0055] Step S104: Control the vehicle to perform the operation indicated by the target control result.

[0056] In the technical solution provided by step S104 of this application, after the target Bluetooth communication data, target touch data and target vehicle environment data are input into a preset prediction model for prediction and the target control result is obtained, the vehicle is controlled to perform the operation indicated by the target control result.

[0057] Optionally, this embodiment performs content analysis on the obtained target control result. If the analysis indicates that the target control result instructs the vehicle to perform an unlocking operation, the vehicle is controlled to perform the unlocking operation indicated by the target control result. If the analysis indicates that the target control result instructs the vehicle to perform a locking operation, the vehicle is controlled to perform the locking operation indicated by the target control result. If the analysis indicates that the target control result instructs the vehicle to perform a holding operation, the vehicle is controlled to perform the holding operation indicated by the target control result. This achieves the purpose of controlling the vehicle to perform the operations indicated by the target control result.

[0058] In steps S101 to S104 of this application, during the process of unlocking the vehicle, Bluetooth communication data between the vehicle and the mobile terminal, touch data collected by the vehicle's contact acquisition device, and vehicle environmental data collected by various sensors are acquired; the Bluetooth communication data, touch data, and vehicle environmental data are preprocessed respectively to obtain target Bluetooth communication data, target touch data, and target vehicle environmental data; the target Bluetooth communication data, target touch data, and target vehicle environmental data are input into a preset prediction model for prediction to obtain a target control result; and the vehicle is controlled to execute the operation indicated by the target control result. This application, based on the acquisition of Bluetooth communication data, touch data, and vehicle environment data, preprocesses the aforementioned Bluetooth communication data, touch data, and vehicle environment data respectively to obtain target Bluetooth communication data, target touch data, and target vehicle environment data. These target Bluetooth communication data, target touch data, and target vehicle environment data are then input into a preset prediction model for prediction, resulting in a target control outcome. Finally, the vehicle is controlled to perform an unlocking operation, locking operation, or holding operation that satisfies the indication of the aforementioned target control outcome. This achieves the goal of reducing environmental interference with the target control outcome, thereby solving the technical problem of low vehicle unlocking security and ultimately improving the technical effect of vehicle unlocking security.

[0059] The steps of the operation of the controlled vehicle executing the target control result instruction in this embodiment will be further described below.

[0060] As an optional embodiment, step S104, controlling the vehicle to perform the operation indicated by the target control result, includes: in response to the target control result being a first target control result, controlling the vehicle to perform an unlocking operation indicated by the first target control result, wherein the first target control result is used to instruct the vehicle to perform the unlocking operation; in response to the target control result being a second target control result, controlling the vehicle to perform a locking operation indicated by the second target control result, wherein the second target control result is used to instruct the vehicle to perform the locking operation; in response to the target control result being a third target control result, controlling the vehicle to perform a holding operation indicated by the third target control result, and returning to the step of inputting the target Bluetooth communication data, target touch data, and target vehicle environmental data into the prediction model for prediction to obtain the target control result, wherein the third target control result is used to instruct the vehicle to perform the holding operation.

[0061] In this embodiment, the aforementioned first target control result can be used to instruct the vehicle to perform an unlocking operation, that is, the current intention of the object to the vehicle is the unlocking intention.

[0062] In this embodiment, the aforementioned second target control result can be used to instruct the vehicle to perform a locking operation, that is, the current intention of the object to the vehicle is a locking intention.

[0063] In this embodiment, the aforementioned third target control result can be used to instruct the vehicle to perform a holding operation, that is, the object has no clear intention regarding the vehicle's current intent.

[0064] In this embodiment, after inputting target Bluetooth communication data, target touch data, and target vehicle environment data into a preset prediction model for prediction to obtain a target control result, in response to the target control result being a first target control result, the vehicle is controlled to execute the unlocking operation indicated by the first target control result. Optionally, this embodiment compares the obtained target control result with the first target control result, the second target control result, and the third target control result to obtain a comparison result. If the comparison result indicates that the target control result is the first target control result, the vehicle is controlled to execute the unlocking operation indicated by the first target control result.

[0065] In this embodiment, after inputting target Bluetooth communication data, target touch data, and target vehicle environment data into a preset prediction model for prediction to obtain a target control result, in response to the target control result being a second target control result, the vehicle is controlled to execute the locking operation indicated by the second target control result. Optionally, this embodiment compares the obtained target control result with a first target control result, a second target control result, and a third target control result to obtain a comparison result. If the comparison result indicates that the target control result is the second target control result, the vehicle is controlled to execute the locking operation indicated by the second target control result.

[0066] In this embodiment, after inputting target Bluetooth communication data, target touch data, and target vehicle environment data into a preset prediction model to obtain a target control result, in response to the target control result being a third target control result, the vehicle is controlled to perform a hold operation indicated by the third target control result, and the process returns to the step of inputting target Bluetooth communication data, target touch data, and target vehicle environment data into the prediction model to obtain the target control result. Optionally, this embodiment compares the obtained target control result with the first target control result, the second target control result, and the third target control result to obtain a comparison result. If the comparison result indicates that the target control result is the third target control result, the vehicle is controlled to perform a hold operation indicated by the third target control result, and the process returns to the step of inputting target Bluetooth communication data, target touch data, and target vehicle environment data into the prediction model to obtain the target control result.

[0067] Since the vehicle can be controlled to perform unlocking, locking, or holding operations based on different target control results, the interference of the environment on the target control results can be reduced, thereby solving the technical problem of low vehicle unlocking security and achieving the technical effect of improving vehicle unlocking security.

[0068] The following section further describes the steps of preprocessing Bluetooth communication data, touch data, and vehicle environment data to obtain target Bluetooth communication data, target touch data, and target vehicle environment data in this embodiment.

[0069] As an optional embodiment, step S102 involves preprocessing the Bluetooth communication data, touch data, and vehicle environment data to obtain target Bluetooth communication data, target touch data, and target vehicle environment data. This includes: performing noise reduction processing on the Bluetooth communication data, touch data, and vehicle environment data to obtain target Bluetooth communication data, noise-reduced touch data, and noise-reduced vehicle environment data; and performing normalization processing on the noise-reduced touch data and noise-reduced vehicle environment data to obtain target touch data and target vehicle environment data.

[0070] In this embodiment, after acquiring Bluetooth communication data between the vehicle and the mobile terminal, touch data collected by the vehicle's contact acquisition device, and vehicle environmental data collected by various sensors, the Bluetooth communication data, touch data, and vehicle environmental data are respectively denoised to obtain target Bluetooth communication data, denoised touch data, and denoised vehicle environmental data. Optionally, based on the acquired Bluetooth communication data, touch data, and vehicle environmental data, this embodiment can obtain target Bluetooth communication data by denoising the Bluetooth communication data, denoised touch data by denoising the touch data, and denoised vehicle environmental data by denoising the vehicle environmental data.

[0071] For example, median filtering is used to remove burst noise from the Bluetooth communication data to obtain the target Bluetooth communication data. Median filtering is used to remove burst noise from the touch data to obtain denoised touch data. Median filtering is used to remove burst noise from the vehicle environment data to obtain denoised vehicle environment data.

[0072] In this embodiment, after denoising the Bluetooth communication data, touch data, and vehicle environment data respectively to obtain target Bluetooth communication data, denoised touch data, and denoised vehicle environment data, normalization processing is performed on the denoised touch data and denoised vehicle environment data respectively to obtain target touch data and target vehicle environment data. Optionally, based on obtaining the denoised touch data and denoised vehicle environment data, this embodiment can obtain target touch data by normalizing the denoised touch data, and obtain target vehicle environment data by normalizing the denoised vehicle environment data. For example, signals collected by different sensors can be unified to the same numerical range.

[0073] By preprocessing the acquired Bluetooth communication data, touch data, and vehicle environment data separately, the goal of obtaining target Bluetooth communication data, target touch data, and target vehicle environment data that are easy for prediction models to process is achieved, thereby realizing the technical effect of improving the accuracy of target Bluetooth communication data, target touch data, and target vehicle environment data.

[0074] The method for preventing accidental unlocking of the vehicle described in this embodiment will be further described below.

[0075] As an optional embodiment, the method further includes: acquiring Bluetooth communication data samples between the vehicle and the mobile terminal, touch data samples collected by the vehicle's contact acquisition device, and vehicle environment data samples collected by multiple sensors. The Bluetooth communication data samples include: strength data of the Bluetooth signal sample from the mobile terminal, arrival time data of the Bluetooth signal sample, frequency offset data of the Bluetooth signal sample, and jitter amplitude data of the Bluetooth signal sample. The touch data samples are used to represent the historical touch states between the vehicle door and its associated object. The vehicle environment data samples include at least two of the following: temperature data samples, humidity data samples, rainfall data samples, surrounding obstacle data samples, and user approach direction data samples of the vehicle's environment. The Bluetooth communication data samples, touch data samples, and vehicle environment data samples are cleaned and preprocessed to obtain target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples. An initial prediction model is trained using the target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples to obtain a first trained prediction model. The first trained prediction model is then lightweighted using the vehicle's performance parameters related to running different models to obtain a prediction model.

[0076] In this embodiment, the aforementioned Bluetooth communication data sample may include: Bluetooth signal strength data of the mobile terminal, Bluetooth signal time of arrival data, Bluetooth signal frequency offset data, and Bluetooth signal jitter amplitude data. Specifically, the Bluetooth signal strength data represents the strength of the Bluetooth signal sample, the Bluetooth signal frequency offset data represents the degree of frequency offset, and the Bluetooth signal jitter amplitude data represents the jitter amplitude of the Bluetooth signal sample.

[0077] In this embodiment, the aforementioned touch data samples can be used to represent the historical touch states between the car door and its associated object. For example, the historical touch states can be either a car door touch state or a car door not touched state.

[0078] In this embodiment, the vehicle environment data sample may include at least two of the following: temperature data sample, humidity data sample, rainfall data sample, surrounding obstacle data sample, and user approach direction data sample. Specifically, the temperature data sample may represent the historical temperature of the vehicle's environment, the humidity data sample may represent the historical humidity of the vehicle's environment, the rainfall data sample may represent the historical rainfall of the vehicle's environment, the surrounding obstacle data sample may represent the historical location and state of obstacles in the vehicle's environment, and the user approach direction data sample may represent the historical direction of the vehicle owner relative to the vehicle, or the historical direction of another person with the vehicle owner's permission relative to the vehicle.

[0079] In this embodiment, after acquiring Bluetooth communication data samples between the vehicle and the mobile terminal, touch data samples collected by the vehicle's contact acquisition device, and vehicle environment data samples collected by multiple sensors, the Bluetooth communication data samples, touch data samples, and vehicle environment data samples are cleaned and preprocessed respectively to obtain target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples.

[0080] Optionally, based on the Bluetooth communication data sample, touch data sample, and vehicle environment data sample obtained, this embodiment cleans and preprocesses the Bluetooth communication data sample to obtain a target Bluetooth communication data sample, cleans and preprocesses the touch data sample to obtain a target touch data sample, and cleans and preprocesses the vehicle environment data to obtain a target vehicle environment data sample.

[0081] In this embodiment, the first training prediction model can be an initial version of the model that has completed training.

[0082] In this embodiment, the performance parameters may include: model size, time taken per inference, and memory usage.

[0083] In this embodiment, the size parameters of the above model need to be adapted to the vehicle-side flash memory storage. For example, the size parameters of the above model are ≤10MB.

[0084] In this embodiment, the time consumed in a single inference operation must meet real-time requirements; for example, the time consumed in a single inference operation must be ≤50ms.

[0085] In this embodiment, the memory usage needs to be adapted to the vehicle's random access memory (RAM). For example, the memory usage is ≤50MB.

[0086] In this embodiment, after training an initial prediction model using target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples to obtain a first trained prediction model, the first trained prediction model is then transformed into a lightweight model using the vehicle's performance parameters related to running different models, thus obtaining a prediction model.

[0087] Optionally, based on the target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples obtained in this embodiment, a suspension process is performed on the initial model using these samples to obtain a trained initial model. By combining the model's size parameters, single inference time, and memory usage, a lightweight transformation is performed on the trained initial model to obtain a transformed initial model.

[0088] By utilizing the vehicle's performance parameters related to different models, the first trained prediction model can be lightweighted and transformed into a prediction model, thereby achieving the goal of obtaining a prediction model suitable for the vehicle and thus realizing the technical effect of improving the flexibility of the prediction model.

[0089] The method for preventing accidental unlocking of the vehicle described in this embodiment will be further described below.

[0090] As an optional embodiment, the method further includes: optimizing the initial prediction model to obtain an optimized prediction model; training the optimized prediction model using target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples to obtain a second trained prediction model; performing a lightweight transformation on the second trained prediction model using performance parameters to obtain a lightweight prediction model; and upgrading the prediction model to a lightweight prediction model.

[0091] In this embodiment, the second training prediction model can be an initial version of the model trained in the cloud or on a device with strong computing power.

[0092] In this embodiment, after optimizing the initial prediction model to obtain an optimized prediction model, the optimized prediction model is trained using target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples.

[0093] Optionally, this embodiment optimizes the initial model to obtain an optimized initial model. The optimized initial model is then trained using target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples to obtain a trained and optimized initial model.

[0094] In this embodiment, after the second training prediction model is transformed into a lightweight prediction model using performance parameters, the prediction model is upgraded to a lightweight prediction model.

[0095] Optionally, this embodiment combines the model's size parameters, single inference time, and memory usage to perform a lightweight transformation on the trained and optimized initial model, resulting in a lightweight prediction model. Subsequently, the prediction model can be upgraded to a lightweight prediction model via over-the-air (OTA) download technology.

[0096] By performing a model upgrade operation on the above-mentioned prediction model, it can be upgraded to a lightweight prediction model, thereby achieving the goal of upgrading the prediction model and thus realizing the technical effect of improving the accuracy of the prediction model.

[0097] The following section further describes the steps of cleaning and preprocessing the Bluetooth communication data sample, touch data sample, and vehicle environment data sample to obtain the target Bluetooth communication data sample, target touch data sample, and target vehicle environment data sample, respectively, in this embodiment.

[0098] As an optional embodiment, the Bluetooth communication data sample, touch data sample, and vehicle environment data sample are cleaned and preprocessed to obtain the target Bluetooth communication data sample, target touch data sample, and target vehicle environment data sample, respectively. This includes: performing missing data processing on the Bluetooth communication data sample, touch data sample, and vehicle environment data sample to obtain missing data processed Bluetooth communication data sample, missing data processed touch data sample, and missing data processed vehicle environment data sample; performing anomaly filtering on the missing data processed Bluetooth communication data sample, missing touch data sample, and missing vehicle environment data sample to obtain the target Bluetooth communication data sample, filtered touch data sample, and filtered vehicle environment data sample; and performing normalization processing on the filtered touch data sample and filtered vehicle environment data sample to obtain the target touch data sample and target vehicle environment data sample.

[0099] In this embodiment, after performing missing data processing on the Bluetooth communication data sample, touch data sample, and vehicle environment data sample respectively to obtain the missing data processed Bluetooth communication data sample, the missing data processed touch data sample, and the missing data processed vehicle environment data sample, anomaly filtering is performed on the missing data processed Bluetooth communication data sample, the missing data processed touch data sample, and the missing data processed vehicle environment data sample respectively to obtain the target Bluetooth communication data sample, the filtered touch data sample, and the filtered vehicle environment data sample.

[0100] Optionally, this embodiment performs missing data processing on the aforementioned Bluetooth communication data samples to obtain missing data samples, performs missing data processing on the aforementioned touch data samples to obtain missing data samples, and performs missing data processing on the vehicle environment data samples to obtain missing environment data samples. Then, anomaly filtering is performed on the missing Bluetooth communication data samples to obtain target Bluetooth communication data samples, anomaly filtering is performed on the missing touch data samples to obtain filtered touch data samples, and anomaly filtering is performed on the missing vehicle environment data samples to obtain filtered vehicle environment data samples.

[0101] For example, cleaning and standardizing Bluetooth communication data samples, touch data samples, and vehicle environment data samples can eliminate noise in these data samples and unify their format.

[0102] Optionally, missing value processing is performed on the Bluetooth communication data samples, touch data samples, and vehicle environment data samples, respectively. That is, data samples with more than 10% missing key features are removed from the above data samples. Outlier filtering is then performed on the missing value processing Bluetooth communication data samples, missing value processing touch data samples, and missing value processing vehicle environment data samples, respectively. That is, outliers exceeding the mean ± 3 times the standard deviation are removed from the above missing value processing data samples.

[0103] In this embodiment, after performing anomaly filtering on the missing Bluetooth communication data sample, the missing touch data sample, and the missing vehicle environment data sample to obtain the target Bluetooth communication data sample, the filtered touch data sample, and the filtered vehicle environment data sample, the filtered touch data sample and the filtered vehicle environment data sample are normalized to obtain the target touch data sample and the target vehicle environment data sample.

[0104] Optionally, this embodiment performs normalization processing on the Bluetooth communication data samples after missing data processing to obtain target touch data samples, and performs normalization processing on the filtered vehicle environment data samples to obtain target vehicle environment data samples. For example, Z-score normalization processing is performed on the filtered touch data samples and the filtered vehicle environment data samples respectively to obtain target touch data samples and target vehicle environment data samples.

[0105] By cleaning and preprocessing the Bluetooth communication data samples, touch data samples, and vehicle environment data samples respectively, the goal of obtaining target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples that are easy to train the initial prediction model is achieved, thereby realizing the technical effect of improving the accuracy of target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples.

[0106] In this embodiment, during the vehicle unlocking process, Bluetooth communication data between the vehicle and the mobile terminal, touch data collected by the vehicle's contact acquisition device, and vehicle environmental data collected by various sensors are acquired. The Bluetooth communication data, touch data, and vehicle environmental data are preprocessed to obtain target Bluetooth communication data, target touch data, and target vehicle environmental data. These data are then input into a preset prediction model for prediction to obtain a target control result. The vehicle is then controlled to execute the operation indicated by the target control result. Because this application preprocesses the Bluetooth communication data, touch data, and vehicle environmental data based on the acquired data, and inputs them into a preset prediction model for prediction to obtain a target control result, the vehicle is finally controlled to perform an unlocking, locking, or holding operation that satisfies the target control result indication. This reduces environmental interference with the target control result, thus solving the technical problem of low vehicle unlocking security and improving vehicle unlocking security.

[0107] The technical solutions of the embodiments of this application will be illustrated below with reference to preferred embodiments.

[0108] Currently, Bluetooth key systems are widely used in vehicle unlocking methods. Traditional Bluetooth key systems mainly rely on signal parameters such as RSSI, comparing these parameters with preset thresholds to unlock or start the vehicle.

[0109] However, when the vehicle is in a complex environment such as a parking lot, the traditional Bluetooth key system is prone to false triggering events. That is, without the user's actual intention, the vehicle may incorrectly respond to the unlock or start command and unlock or start itself, resulting in low vehicle unlocking security.

[0110] To address the aforementioned technical problems, this application proposes a method for preventing accidental unlocking of vehicles. Based on acquired Bluetooth communication data, touch data, and vehicle environment data, these data are preprocessed to obtain target Bluetooth communication data, target touch data, and target vehicle environment data. These data are then input into a preset prediction model for prediction, yielding a target control result. Finally, the vehicle is controlled to perform an unlocking, locking, or holding operation that satisfies the target control result. This reduces environmental interference with the target control result, thus solving the technical problem of low vehicle unlocking security and improving vehicle unlocking security.

[0111] In this embodiment, a lightweight vehicle model can be generated by executing the method for generating a lightweight vehicle model. For example, Figure 2 This is a flowchart of a method for generating a lightweight vehicle-side model according to an embodiment of this application, such as... Figure 2 As shown, the method may include the following steps:

[0112] Step S201: Obtain the initial model for non-vehicle components.

[0113] In the technical solution provided by step S201 of this application, the initial model can be trained in the cloud or on a device with stronger computing power.

[0114] After obtaining the initial model for the non-vehicle side, step S202 is executed to optimize and iterate the initial model, resulting in an optimized model.

[0115] In the technical solution provided in step S202 of this application, the initial model is continuously learned and optimized to form an optimized model, which is also trained in the cloud or on a device with stronger computing power.

[0116] After optimizing and iterating the initial model to obtain the optimized model, step S203 is executed to perform a lightweight transformation on the optimized model, resulting in a lightweight vehicle-side model.

[0117] In the technical solution provided in step S203 of this application, after the initial model is completed, pruning, quantization, knowledge distillation, and other methods are used to lightweight the model into a vehicle-side lightweight model that can run on the vehicle module. For example, based on the following parameters: model size ≤ 10MB (adapting to vehicle-side flash storage), single inference time ≤ 50ms (meeting real-time requirements), memory usage ≤ 50MB (adapting to vehicle-side random access memory), etc., the model is compressed into a vehicle-side lightweight model. The specific degree of model compression depends on the performance settings of the vehicle-side module.

[0118] In this embodiment, a preliminary model can be generated by executing the method for generating a preliminary model. For example, Figure 3 This is a flowchart of a method for generating a preliminary model according to an embodiment of this application, such as... Figure 3 As shown, the method may include the following steps:

[0119] Step S301, Data preparation.

[0120] In the technical solution provided by step S301 of this application, the data preparation may include: data acquisition, data cleaning and data preprocessing.

[0121] In this embodiment, data collection can include vehicle-side data collection and non-vehicle-side data collection.

[0122] In this embodiment, the collected vehicle-side data covers different vehicle usage scenarios, and the number of collected data sets is no less than 50,000. This vehicle-side data can include Bluetooth signal data and environmental data. Specifically, the Bluetooth signal data can be collected through the vehicle's Bluetooth module and can include signal strength data, Time Difference of Arrival (TDOA) data, Frequency Offset (FOF) data, and jitter amplitude data. The environmental data can include temperature data, humidity data, rainfall data, electromagnetic interference intensity data, multipath effect index data, tag data, valid trigger data, and false trigger data.

[0123] In this embodiment, the aforementioned non-vehicle data may include: parking lot location information, interference source location information, Bluetooth strength information of other vehicles, etc., and the non-vehicle data can be directly obtained from an existing database.

[0124] In this embodiment, data cleaning and preprocessing refer to cleaning and standardizing the raw data to eliminate noise and unify the data format. Optionally, missing value processing, outlier filtering, and normalization are performed on the raw data. For example, data with a missing rate of more than 10% for key features are removed from the raw data. Then, outliers exceeding the mean ± 3 standard deviations are removed from the raw data, such as invalid data where the RSSI suddenly drops to -120dBm. Numerical features are also standardized using Z-scores.

[0125] After data preparation, proceed to step S302 to perform feature engineering.

[0126] In the technical solution provided by step S302 of this application, key features are extracted, such as "humidity-signal attenuation correlation value", "electromagnetic interference-signal jitter amplitude", "obstacle material-signal attenuation correlation value", and "obstacle distance-signal attenuation correlation value".

[0127] After performing feature engineering, step S303 is executed to design and train the model.

[0128] In the technical solution provided in step S303 of this application, a suitable model architecture and hardware are selected, and the model is trained. For example, a deep neural network (DNN) or a graph neural network (GNN) is used, with the input being Bluetooth signal + environmental features, and the output being the probability of false triggering.

[0129] After designing and training the model, step S304 is executed to evaluate and optimize the model.

[0130] In the technical solution provided in step S304 of this application, the accuracy, precision, recall, etc. of the model are verified. For example, the model is trained using labeled data and the hyperparameters (e.g., learning rate, number of network layers) are optimized through cross-validation to ensure high accuracy, that is, to ensure that the accuracy of false trigger recognition is ≥95%.

[0131] After evaluating and optimizing the model, step S305 is executed to compress and transform the model.

[0132] In the technical solution provided in step S305 of this application, model compression technology is used to simplify the initial large model into a lightweight model. Common simplification methods may include pruning, quantization, knowledge distillation, etc.

[0133] In this embodiment, when the model is compressed, the performance parameters of the module when it runs on the vehicle should be considered: model size ≤ 10MB (adapting to vehicle Flash storage), single inference time ≤ 50ms (meeting real-time requirements), and memory usage ≤ 50MB (adapting to vehicle RAM).

[0134] In this embodiment, by implementing a vehicle Bluetooth key anti-mistriggering method based on a lightweight large-scale vehicle model, the vehicle can be controlled to perform an unlocking operation, a locking operation, or a holding operation that satisfies the aforementioned desired control result. For example, Figure 4 This is a flowchart of a method for preventing accidental triggering of a vehicle Bluetooth key based on a lightweight large-scale vehicle model according to an embodiment of this application, such as... Figure 4 As shown, the method may include the following steps:

[0135] Step S401: Collect data.

[0136] In the technical solution provided in step S401 of this application, after the Bluetooth connection is established, the Bluetooth sensor in the data acquisition module continuously collects the Bluetooth signal of the mobile terminal. The door handle capacitive sensor monitors the touch status of the car door in real time. Temperature sensors, humidity sensors, rain sensors, etc., continuously detect information such as temperature, humidity, and rainfall. At the same time, ultrasonic sensors, vehicle cameras, etc., continuously detect the distance to surrounding obstacles and the direction in which the user approaches. A GPS-based locator provides vehicle location information, etc., where the location information is not essential data.

[0137] After data collection, step S402 is executed to preprocess the data.

[0138] In the technical solution provided in step S402 of this application, the data preprocessing module is used to denoise the acquired Bluetooth signal data. For example, median filtering is used to remove burst noise from the Bluetooth signal data. The Bluetooth signal data is then normalized to unify the signals acquired by different sensors to the same numerical range, thereby facilitating subsequent model processing.

[0139] After the data is preprocessed, step S403 is executed to input the preprocessed data into the vehicle-side lightweight large model for prediction.

[0140] In the technical solution provided by step S403 of this application, the preprocessed data is input into the vehicle-side lightweight large model module. The model predicts the user's intention based on the learned patterns and rules, and can output the prediction result, such as "unlock intention", "lock intention" or "no clear intention".

[0141] In this embodiment, the lightweight vehicle-side large model can deduce user intent by analyzing multi-dimensional data such as the changing trend of the current Bluetooth signal strength, signal frequency characteristics, whether the car door is touched, whether someone is approaching the vehicle, temperature and humidity information, and interference information.

[0142] After the preprocessed data is input into the vehicle-side lightweight large model for prediction, step S404 is executed to make control decisions for the vehicle based on the model prediction results.

[0143] In the technical solution provided in step S404 of this application, the control decision module performs different operations on the vehicle based on the prediction results output by the model. If the output prediction result is "unlocking intention", the control decision module sends an unlocking command to the vehicle unlocking execution mechanism to perform the vehicle unlocking operation; if the output prediction result is "locking intention", the control decision module sends a locking command to the vehicle locking execution mechanism to perform the vehicle locking operation; if the output prediction result is "no clear intention", no unlocking or locking operation is performed, and the intention judgment continues.

[0144] In this embodiment, based on the acquired Bluetooth communication data, touch data, and vehicle environment data, the Bluetooth communication data, touch data, and vehicle environment data are preprocessed to obtain target Bluetooth communication data, target touch data, and target vehicle environment data. These target Bluetooth communication data, target touch data, and target vehicle environment data are then input into a preset prediction model for prediction to obtain the target control result. Finally, the vehicle is controlled to perform an unlocking operation, a locking operation, or a holding operation that satisfies the target control result. This achieves the goal of reducing environmental interference with the target control result, thereby solving the technical problem of low vehicle unlocking security and ultimately improving the technical effect of vehicle unlocking security.

[0145] According to an embodiment of this application, a vehicle anti-accidental unlocking device is also provided. It should be noted that this vehicle anti-accidental unlocking device can be used to execute one of the vehicle anti-accidental unlocking methods described in the embodiments.

[0146] Figure 5 This is a schematic diagram of a vehicle anti-accidental unlocking device according to an embodiment of this application. Figure 5 As shown, the vehicle's anti-accidental unlocking device 500 may include: a first acquisition unit 501, a preprocessing unit 502, a prediction unit 503, and an execution unit 504.

[0147] The first acquisition unit 501 is used to acquire Bluetooth communication data between the vehicle and the mobile terminal, touch data collected by the vehicle's contact acquisition device, and vehicle environment data collected by various sensors. The Bluetooth communication data includes: Bluetooth signal strength data of the mobile terminal, Bluetooth signal arrival time data, Bluetooth signal frequency offset data, and Bluetooth signal jitter amplitude data. The touch data is used to represent the touch state between the vehicle door and the object to which the mobile terminal belongs. The vehicle environment data includes at least two of the following: temperature data, humidity data, rainfall data, surrounding obstacle data, and user approach direction data of the vehicle's environment.

[0148] The preprocessing unit 502 is used to preprocess the Bluetooth communication data, touch data and vehicle environment data respectively to obtain target Bluetooth communication data, target touch data and target vehicle environment data.

[0149] The prediction unit 503 is used to input the target Bluetooth communication data, target touch data and target vehicle environment data into a preset prediction model for prediction to obtain the target control result. The prediction model is obtained by lightweight transformation of the initial prediction model for non-vehicles. The target control result is used to instruct the vehicle to perform any of the following operations: unlocking operation, locking operation or holding operation.

[0150] The execution unit 504 is used to control the vehicle to perform the operation of the target control result indication.

[0151] Optionally, the execution unit 504 may include: a first execution module, configured to control the vehicle and execute an unlocking operation indicated by the first target control result in response to the target control result being a first target control result, wherein the first target control result is used to instruct the vehicle to perform the unlocking operation; a second execution module, configured to control the vehicle and execute a locking operation indicated by the second target control result in response to the target control result being a second target control result, wherein the second target control result is used to instruct the vehicle to perform the locking operation; and a third execution module, configured to control the vehicle and execute a holding operation indicated by the third target control result in response to the target control result being a third target control result, and return to the step of inputting the target Bluetooth communication data, target touch data, and target vehicle environmental data into a prediction model for prediction to obtain the target control result, wherein the third target control result is used to instruct the vehicle to perform the holding operation.

[0152] Optionally, the preprocessing unit 502 may include: a noise reduction module, used to perform noise reduction processing on the Bluetooth communication data, touch data and vehicle environment data respectively, to obtain target Bluetooth communication data, noise-reduced touch data and noise-reduced vehicle environment data; and a first normalization processing module, used to perform normalization processing on the noise-reduced touch data and noise-reduced vehicle environment data respectively, to obtain target touch data and target vehicle environment data.

[0153] Optionally, the vehicle's anti-accidental touch unlocking device 500 may further include: a second acquisition unit, used to acquire Bluetooth communication data samples between the vehicle and the mobile terminal, touch data samples acquired by the vehicle's contact acquisition device, and vehicle environment data samples acquired by multiple sensors. The Bluetooth communication data samples include: Bluetooth signal strength data, Bluetooth signal arrival time data, Bluetooth signal frequency offset data, and Bluetooth signal jitter amplitude data. The touch data samples are used to represent the historical touch states between the door and the associated object. The vehicle environment data samples include at least two of the following: temperature data samples of the vehicle's environment. The system includes: a humidity data sample, a rainfall data sample, a surrounding obstacle data sample, and a user approach direction data sample; a cleaning and processing unit, used to clean and preprocess the Bluetooth communication data sample, touch data sample, and vehicle environment data sample respectively to obtain target Bluetooth communication data sample, target touch data sample, and target vehicle environment data sample; a first training unit, used to train an initial prediction model using the target Bluetooth communication data sample, target touch data sample, and target vehicle environment data sample to obtain a first training prediction model; and a first transformation unit, used to perform a lightweight transformation of the first training prediction model using the vehicle's performance parameters related to running different models to obtain a prediction model.

[0154] Optionally, the vehicle's anti-accidental touch unlocking device 500 may further include: an optimization unit for optimizing an initial prediction model to obtain an optimized prediction model; a second training unit for training the optimized prediction model using target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples to obtain a second training prediction model; a second conversion unit for performing a lightweight conversion on the second training prediction model using performance parameters to obtain a lightweight prediction model; and an upgrade unit for upgrading the prediction model to a lightweight prediction model.

[0155] Optionally, the cleaning processing unit may include: a missing data processing module, used to perform missing data processing on the Bluetooth communication data sample, touch data sample, and vehicle environment data sample respectively, to obtain missing data processed Bluetooth communication data sample, missing data processed touch data sample, and missing vehicle environment data sample; an anomaly filtering module, used to perform anomaly filtering on the missing data processed Bluetooth communication data sample, missing data sample, and missing vehicle environment data sample respectively, to obtain a target Bluetooth communication data sample, a filtered touch data sample, and a filtered vehicle environment data sample; and a second normalization processing module, used to normalize the filtered touch data sample and the filtered vehicle environment data sample respectively, to obtain a target touch data sample and a target vehicle environment data sample.

[0156] In this embodiment, a vehicle anti-accidental touch unlocking device is provided. The device may include: an acquisition unit for acquiring Bluetooth communication data between the vehicle and a mobile terminal, touch data collected by a vehicle contact acquisition device, and vehicle environmental data collected by multiple sensors. The Bluetooth communication data includes: Bluetooth signal strength data, Bluetooth signal arrival time data, Bluetooth signal frequency offset data, and Bluetooth signal jitter amplitude data. The touch data indicates the touch state between the vehicle door and the mobile terminal. The vehicle environmental data includes at least two of the following: temperature data, humidity data, rainfall data, and ambient temperature data of the vehicle's environment. The system includes: obstacle data and user approach direction data; a preprocessing unit for preprocessing Bluetooth communication data, touch data, and vehicle environment data to obtain target Bluetooth communication data, target touch data, and target vehicle environment data; a prediction unit for inputting the target Bluetooth communication data, target touch data, and target vehicle environment data into a preset prediction model for prediction to obtain the target control result, wherein the prediction model is obtained by lightweight transformation of the initial prediction model for non-vehicles, and the target control result is used to instruct the vehicle to perform any of the following operations: unlocking operation, locking operation, or holding operation; and an execution unit for controlling the vehicle to execute the operation indicated by the target control result. This application, based on the acquisition of Bluetooth communication data, touch data, and vehicle environment data, preprocesses the aforementioned Bluetooth communication data, touch data, and vehicle environment data respectively to obtain target Bluetooth communication data, target touch data, and target vehicle environment data. These target Bluetooth communication data, target touch data, and target vehicle environment data are then input into a preset prediction model for prediction, resulting in a target control outcome. Finally, the vehicle is controlled to perform an unlocking operation, locking operation, or holding operation that satisfies the indication of the aforementioned target control outcome. This achieves the goal of reducing environmental interference with the target control outcome, thereby solving the technical problem of low vehicle unlocking security and ultimately improving the technical effect of vehicle unlocking security.

[0157] According to an embodiment of this application, an electronic device is also provided. Figure 6 This is a schematic diagram of an electronic device according to an embodiment of this application, such as... Figure 6 As shown, the electronic device 600 may include a memory 610 and a processor 620, wherein the memory 610 is used to store an executable program; and the processor 620 is used to run the program stored in the memory 610, and the program executes the method of this application when it runs.

[0158] In this application, "multiple" refers to two or more.

[0159] In this application, unless otherwise expressly defined, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0160] The terms “first,” “second,” “third,” “fourth,” etc., in this application (if present) are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0161] In this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, in this application, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0162] According to another aspect of the embodiments of this application, a processor is also provided for running a program, wherein the program is executed by the processor to perform the methods in the embodiments.

[0163] According to another aspect of the embodiments of this application, a computer program product is also provided, the computer program product including a computer program, wherein the computer program, when executed by a processor, implements the methods in the embodiments.

[0164] According to another aspect of the embodiments of this application, a computer program product is also provided, including a non-volatile computer-readable storage medium for storing a computer program that, when executed by a processor, implements the methods in the embodiments.

[0165] According to another aspect of the embodiments of this application, a computer program is also provided, which, when executed by a processor, implements the methods in the embodiments.

[0166] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided. This computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method described in the embodiments.

[0167] According to another aspect of the embodiments of this application, a vehicle is also provided, including the electronic device described in this application.

[0168] Computer-readable storage media, also known as computer storage media, may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. These propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable storage media can transmit, propagate, or transfer programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0169] The program code contained in a computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, radio frequency, or any suitable combination thereof.

[0170] According to an embodiment of this application, a computer program product is also provided, which includes a computer program, wherein the computer program, when executed by a processor, implements the method in the embodiment.

[0171] According to an embodiment of this application, a computer program product is also provided, including a non-volatile computer-readable storage medium for storing a computer program, which, when executed by a processor, implements the method described in the embodiment.

[0172] According to an embodiment of this application, a computer program is also provided, which, when executed by a processor, implements the method described in the embodiment.

[0173] Optionally, when the above-mentioned computer program is executed by the processor, the program code implements the following steps: acquiring Bluetooth communication data between the vehicle and the mobile terminal, touch data collected by the vehicle's contact acquisition device, and vehicle environmental data collected by multiple sensors. The Bluetooth communication data includes: Bluetooth signal strength data, Bluetooth signal arrival time data, Bluetooth signal frequency offset data, and Bluetooth signal jitter amplitude data. The touch data represents the touch state between the vehicle door and the mobile terminal. The vehicle environmental data includes at least two of the following: temperature data, humidity data, rainfall data, surrounding obstacle data, and user approach direction data of the vehicle's environment. The Bluetooth communication data, touch data, and vehicle environmental data are preprocessed to obtain target Bluetooth communication data, target touch data, and target vehicle environmental data. The target Bluetooth communication data, target touch data, and target vehicle environmental data are input into a preset prediction model for prediction to obtain a target control result. The prediction model is obtained by lightweight transformation of the initial prediction model (not for the vehicle). The target control result is used to instruct the vehicle to perform any of the following operations: unlocking, locking, or holding. The vehicle is then controlled to execute the operation indicated by the target control result.

[0174] Optionally, when the above-mentioned computer program is executed by the processor, the program code implements the following steps: in response to the target control result being a first target control result, controlling the vehicle to perform an unlocking operation indicated by the first target control result, wherein the first target control result is used to instruct the vehicle to perform the unlocking operation; in response to the target control result being a second target control result, controlling the vehicle to perform a locking operation indicated by the second target control result, wherein the second target control result is used to instruct the vehicle to perform the locking operation; in response to the target control result being a third target control result, controlling the vehicle to perform a holding operation indicated by the third target control result, and returning to the step of inputting the target Bluetooth communication data, target touch data, and target vehicle environmental data into the prediction model for prediction to obtain the target control result, wherein the third target control result is used to instruct the vehicle to perform the holding operation.

[0175] Optionally, when the above computer program is executed by the processor, the program code performs the following steps: denoising the Bluetooth communication data, touch data, and vehicle environment data respectively to obtain the target Bluetooth communication data, the denoised touch data, and the denoised vehicle environment data; and normalizing the denoised touch data and the denoised vehicle environment data respectively to obtain the target touch data and the target vehicle environment data.

[0176] Optionally, when the above-mentioned computer program is executed by the processor, the program code implements the following steps: acquiring Bluetooth communication data samples between the vehicle and the mobile terminal, touch data samples collected by the vehicle's contact acquisition device, and vehicle environment data samples collected by multiple sensors. The Bluetooth communication data samples include: strength data of the Bluetooth signal sample from the mobile terminal, arrival time data of the Bluetooth signal sample, frequency offset data of the Bluetooth signal sample, and jitter amplitude data of the Bluetooth signal sample. The touch data samples are used to represent the historical touch states between the car door and the object. The vehicle environment data samples include at least two of the following: temperature data samples, humidity data samples, rainfall data samples, surrounding obstacle data samples, and user approach direction data samples of the vehicle's environment. The Bluetooth communication data samples, touch data samples, and vehicle environment data samples are cleaned and preprocessed to obtain target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples. An initial prediction model is trained using the target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples to obtain a first trained prediction model. The first trained prediction model is then lightweighted using the vehicle's performance parameters related to running different models to obtain a prediction model.

[0177] Optionally, when the above computer program is executed by the processor, the program code implements the following steps: optimizing the initial prediction model to obtain an optimized prediction model; training the optimized prediction model using target Bluetooth communication data samples, target touch data samples, and target vehicle environment data samples to obtain a second trained prediction model; using performance parameters to perform a lightweight transformation on the second trained prediction model to obtain a lightweight prediction model; and upgrading the prediction model to a lightweight prediction model.

[0178] Optionally, when the above-mentioned computer program is executed by the processor, the program code implements the following steps: performing missing data processing on the Bluetooth communication data sample, touch data sample, and vehicle environment data sample respectively to obtain missing data processed Bluetooth communication data sample, missing data sample, and missing vehicle environment data sample; performing anomaly filtering on the missing data processed Bluetooth communication data sample, missing data sample, and missing vehicle environment data sample respectively to obtain target Bluetooth communication data sample, filtered touch data sample, and filtered vehicle environment data sample; and performing normalization processing on the filtered touch data sample and filtered vehicle environment data sample respectively to obtain target touch data sample and target vehicle environment data sample.

[0179] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0180] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0181] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0182] 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 units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0183] Furthermore, 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. The integrated unit can be implemented in hardware or as a software functional unit.

[0184] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to related technologies, or all or part 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 of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0185] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for preventing accidental unlocking of a vehicle, characterized in that, Applied to the vehicle, the method includes: The system acquires Bluetooth communication data between the vehicle and the mobile terminal, touch data collected by the vehicle's contact acquisition device, and vehicle environmental data collected by multiple sensors. The Bluetooth communication data includes: Bluetooth signal strength data of the mobile terminal, Bluetooth signal arrival time data, Bluetooth signal frequency offset data, and Bluetooth signal jitter amplitude data. The touch data indicates the touch state between the vehicle door and the mobile terminal. The vehicle environmental data includes at least two of the following: temperature data, humidity data, rainfall data, surrounding obstacle data, and user approach direction data of the vehicle's environment. The Bluetooth communication data, the touch data, and the vehicle environment data are preprocessed respectively to obtain target Bluetooth communication data, target touch data, and target vehicle environment data. The target Bluetooth communication data, the target touch data, and the target vehicle environment data are input into a preset prediction model for prediction to obtain the target control result. The prediction model is obtained by lightweight transformation of the initial prediction model for non-vehicles. The target control result is used to instruct the vehicle to perform any of the following operations: unlocking operation, locking operation, or holding operation. Control the vehicle to perform the operation indicated by the target control result.

2. The method according to claim 1, characterized in that, Controlling the vehicle to perform the operation indicated by the target control result includes: In response to the target control result being a first target control result, the vehicle is controlled to perform the unlocking operation indicated by the first target control result, wherein the first target control result is used to instruct the vehicle to perform the unlocking operation; In response to the target control result being a second target control result, the vehicle is controlled to perform the locking operation indicated by the second target control result, wherein the second target control result is used to instruct the vehicle to perform the locking operation; In response to the target control result being a third target control result, the vehicle is controlled to perform the hold operation indicated by the third target control result, and the process returns to the step of inputting the target Bluetooth communication data, the target touch data, and the target vehicle environment data into the prediction model for prediction to obtain the target control result, wherein the third target control result is used to instruct the vehicle to perform the hold operation.

3. The method according to claim 1, characterized in that, The Bluetooth communication data, the touch data, and the vehicle environment data are preprocessed respectively to obtain target Bluetooth communication data, target touch data, and target vehicle environment data, including: The Bluetooth communication data, the touch data, and the vehicle environment data are denoised respectively to obtain the target Bluetooth communication data, the denoised touch data, and the denoised vehicle environment data; The noise-processed touch data and the noise-reduced vehicle environment data are normalized to obtain the target touch data and the target vehicle environment data.

4. The method according to any one of claims 1 to 3, characterized in that, The method further includes: The system acquires Bluetooth communication data samples between the vehicle and the mobile terminal, touch data samples collected by the vehicle's contact acquisition device, and vehicle environment data samples collected by various sensors. The Bluetooth communication data samples include: Bluetooth signal strength data, Bluetooth signal arrival time data, Bluetooth signal frequency offset data, and Bluetooth signal jitter amplitude data. The touch data samples represent the historical touch states between the vehicle door and the associated object. The vehicle environment data samples include at least two of the following: temperature data samples, humidity data samples, rainfall data samples, surrounding obstacle data samples, and user approach direction data samples of the vehicle's environment. The Bluetooth communication data sample, the touch data sample, and the vehicle environment data sample are cleaned and preprocessed respectively to obtain the target Bluetooth communication data sample, the target touch data sample, and the target vehicle environment data sample. Using the target Bluetooth communication data sample, the target touch data sample, and the target vehicle environment data sample, the initial prediction model is trained to obtain the first trained prediction model; By utilizing the vehicle's performance parameters related to different operating models, the first trained prediction model is transformed into a lightweight model to obtain the prediction model.

5. The method according to claim 4, characterized in that, The method further includes: The initial prediction model is optimized to obtain an optimized prediction model; Using the target Bluetooth communication data sample, the target touch data sample, and the target vehicle environment data sample, the optimized prediction model is trained to obtain the second trained prediction model; Using the aforementioned performance parameters, the second training prediction model is subjected to a lightweight transformation to obtain a lightweight prediction model; The prediction model is upgraded to the lightweight prediction model.

6. The method according to claim 4, characterized in that, The Bluetooth communication data sample, the touch data sample, and the vehicle environment data sample are cleaned and preprocessed respectively to obtain the target Bluetooth communication data sample, the target touch data sample, and the target vehicle environment data sample, including: The Bluetooth communication data sample, the touch data sample, and the vehicle environment data sample are respectively processed to obtain the Bluetooth communication data sample, the touch data sample, and the vehicle environment data sample after the missing data processing. Anomaly filtering is performed on the missing Bluetooth communication data sample, the missing touch data sample, and the missing vehicle environment data sample respectively to obtain the target Bluetooth communication data sample, the filtered touch data sample, and the filtered vehicle environment data sample. The filtered touch data samples and the filtered vehicle environment data samples are normalized respectively to obtain the target touch data samples and the target vehicle environment data samples.

7. A vehicle anti-accidental unlocking device, characterized in that, include: The first acquisition unit is used to acquire Bluetooth communication data between the vehicle and the mobile terminal, touch data collected by the vehicle's contact acquisition device, and vehicle environment data collected by multiple sensors. The Bluetooth communication data includes: Bluetooth signal strength data of the mobile terminal, Bluetooth signal arrival time data, Bluetooth signal frequency offset data, and Bluetooth signal jitter amplitude data. The touch data is used to indicate the touch state between the vehicle door and the object to which the mobile terminal belongs. The vehicle environment data includes at least two of the following: temperature data, humidity data, rainfall data, surrounding obstacle data, and user approach direction data of the vehicle's environment. The preprocessing unit is used to preprocess the Bluetooth communication data, the touch data, and the vehicle environment data respectively to obtain target Bluetooth communication data, target touch data, and target vehicle environment data. The prediction unit is used to input the target Bluetooth communication data, the target touch data and the target vehicle environment data into a preset prediction model for prediction to obtain the target control result. The prediction model is obtained by lightweight transformation of the initial prediction model for non-vehicles. The target control result is used to instruct the vehicle to perform any of the following operations: unlocking operation, locking operation or holding operation. An execution unit is used to control the vehicle to perform the operation indicated by the target control result.

8. A processor, characterized in that, The processor is used to run a program, wherein the program is executed by the processor to perform the anti-accidental touch unlocking method for the vehicle according to any one of claims 1 to 6.

9. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, executes the method for preventing accidental unlocking of the vehicle according to any one of claims 1 to 6.

10. A vehicle, characterized in that, It includes the electronic device as described in claim 9.

Images