Vehicle relay scene detection method, device and system

Abstract

The present disclosure proposes a vehicle relay scene detection method, device and system. The method is applied to the relay detection system. In response to the Bluetooth main anchor point establishing a connection with the Bluetooth key, the first Bluetooth signal information set sent by at least one Bluetooth slave anchor point and the second Bluetooth signal information of the Bluetooth key are obtained; the relative position between each Bluetooth slave anchor point and the Bluetooth main anchor point remains unchanged, and the difference between the Bluetooth signal information obtained by each Bluetooth slave anchor point is relatively stable. Therefore, the first feature set of the first Bluetooth signal information set is extracted, and the second feature of the second Bluetooth signal is extracted; the preset classification model is called to determine whether the Bluetooth signal corresponding to the Bluetooth key is a relay forwarding signal based on the first feature set and the second feature. According to the characteristics of the Bluetooth signal information obtained by each anchor point, it can be classified to determine whether it is a relay forwarding signal, which improves the accuracy of recognition and ensures vehicle safety to a certain extent.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a vehicle relay scene detection method, device and system. Background Art

[0002] The digital car key system based on Bluetooth signal strength positioning technology is a technology that uses Bluetooth signal strength for location positioning and vehicle control. The vehicle determines the relative position of the Bluetooth key by the signal strength received from the Bluetooth key to determine whether to unlock the vehicle. Relay attacks use relay devices to monitor, forward or tamper with communication data, thereby extending the communication distance or bypassing security restrictions to achieve illegal access or steal information.

[0003] The means of detecting relay attacks in the prior art usually adopts controlling the transmission power of the Bluetooth key to identify whether it is a relay scenario. The Bluetooth key transmits the corresponding power according to the rules agreed upon with the vehicle, and the vehicle determines whether it is a relay scenario based on the change pattern of the detected Bluetooth key power.

[0004] However, the above-mentioned method for detecting relay attacks cannot be used in complex environments and is greatly affected by the environment, which leads to inaccurate results of detecting relay attacks and cannot ensure vehicle safety. Summary of the invention

[0005] The present disclosure provides a vehicle relay scene detection method, device and system.

[0006] In a first aspect of the present disclosure, an embodiment provides a vehicle relay scene detection method, the method is applied to a relay detection system, the relay detection system includes a Bluetooth key and a Bluetooth anchor point, the Bluetooth anchor point includes a Bluetooth master anchor point and at least one Bluetooth slave anchor point, the Bluetooth master anchor point is arranged inside the vehicle, the at least one Bluetooth slave anchor point is arranged outside the vehicle, the position between the Bluetooth master anchor point and the at least one Bluetooth slave anchor point is fixed, the method includes:

[0007] In response to the Bluetooth master anchor point establishing a connection with the Bluetooth key, obtaining a first Bluetooth signal information set sent by the at least one Bluetooth slave anchor point and second Bluetooth signal information of the Bluetooth key, wherein the first Bluetooth signal information set is information about the signal strength of the Bluetooth key detected by the at least one Bluetooth slave anchor point and information about the signal strength of the Bluetooth master anchor point, and the second Bluetooth signal information is information about the signal strength of the Bluetooth key detected by the Bluetooth master anchor point;

[0008] Extracting a first feature set of the first Bluetooth signal information set, and extracting a second feature of the second Bluetooth signal;

[0009] A preset classification model is called to determine whether the Bluetooth signal corresponding to the Bluetooth key is a relay forwarding signal according to the first feature set and the second feature.

[0010] In an embodiment of the present disclosure, the acquiring of the first Bluetooth signal information set sent by the at least one Bluetooth slave anchor point and the second Bluetooth signal information of the Bluetooth key includes:

[0011] Acquire, through the bus, first Bluetooth signal information sent by any Bluetooth slave anchor point within a preset time period, wherein the first Bluetooth signal information is any one in the first Bluetooth signal information set;

[0012] The second Bluetooth signal information of the Bluetooth key is detected within the preset time period.

[0013] In the embodiment of the present disclosure, there are four Bluetooth slave anchor points.

[0014] In the embodiment of the present disclosure, extracting the first feature set of the first Bluetooth signal information set and extracting the second feature of the second Bluetooth signal include:

[0015] For any first Bluetooth signal information, calculate a signal change feature corresponding to the first Bluetooth signal information to obtain the first feature, where the first feature is any one of the first feature set;

[0016] Calculate the signal change characteristic of the second Bluetooth signal information to obtain the second characteristic.

[0017] In the embodiment of the present disclosure, the signal change characteristics include the change amount, change rate, transmission delay, delay fluctuation and stability within the preset time period.

[0018] In the embodiment of the present disclosure, calling a preset classification model to determine whether the Bluetooth signal corresponding to the Bluetooth key is a relay forwarding signal according to the first feature set and the second feature includes:

[0019] Calling a preset classification model multiple times, and determining a classification result corresponding to each call of the preset classification model according to the first feature set and the second feature;

[0020] Determine the target classification result according to the relationship between the number of classification results and the number of times the preset classification model is called;

[0021] If the target classification result is an unstable signal, the Bluetooth signal corresponding to the Bluetooth key is a relay scenario;

[0022] If the target classification result is a stable signal, the Bluetooth signal corresponding to the Bluetooth key is a non-relay scenario.

[0023] In the embodiment of the present disclosure, the multiple calls to the preset classification model, and determining the classification results corresponding to each call of the preset classification model according to the first feature set and the second feature, respectively, include:

[0024] Calling the preset classification model for the i-th time, and determining the i-th classification result according to the first feature set and the second feature set;

[0025] If i is equal to the preset number of calls, determine the classification results from the i-th to the i-th time;

[0026] If i is less than the preset number of calls, continue to call the preset classification model, and determine the i+1th classification result according to the first feature set and the second feature set, until i+1 is equal to the preset number of calls.

[0027] In the embodiment of the present disclosure, the classification result includes a stable signal and an unstable signal, and the target classification result is determined according to the relationship between the number of classification results and the number of times the preset classification model is called, including:

[0028] If the number of times the signal is determined to be the stable signal is greater than the number of times the signal is determined to be the unstable signal, the target classification result is a stable signal;

[0029] If the number of times the signal is determined to be the stable signal is less than or equal to the number of times the signal is determined to be the unstable signal, the target classification result is an unstable signal.

[0030] In a second aspect of the present disclosure, an embodiment provides a vehicle relay scene detection device, which is applied to a relay detection system. The relay detection system includes a Bluetooth key and a Bluetooth anchor point, wherein the Bluetooth anchor point includes a Bluetooth master anchor point and at least one Bluetooth slave anchor point, wherein the Bluetooth master anchor point is arranged inside the vehicle, and the at least one Bluetooth slave anchor point is arranged outside the vehicle, and the positions between the Bluetooth master anchor point and the at least one Bluetooth slave anchor point are fixed. The device includes:

[0031] an information acquisition module, configured to acquire, in response to the Bluetooth master anchor point establishing a connection with the Bluetooth key, a first Bluetooth signal information set sent by the at least one Bluetooth slave anchor point and second Bluetooth signal information of the Bluetooth key, wherein the first Bluetooth signal information set is information about the signal strength of the Bluetooth key detected by the at least one Bluetooth slave anchor point and information about the signal strength of the Bluetooth master anchor point, and the second Bluetooth signal information is information about the signal strength of the Bluetooth key detected by the Bluetooth master anchor point;

[0032] A feature extraction module, used to extract a first feature set of the first Bluetooth signal information set, and to extract a second feature of the second Bluetooth signal;

[0033] The determination module is used to call a preset classification model to determine whether the Bluetooth signal corresponding to the Bluetooth key is a relay forwarding signal according to the first feature set and the second feature.

[0034] The third aspect of the present disclosure provides a vehicle relay scene detection system, characterized in that the system includes a Bluetooth key and a Bluetooth anchor point, the Bluetooth anchor point includes a Bluetooth master anchor point and at least one Bluetooth slave anchor point, the Bluetooth master anchor point is arranged inside the vehicle, the at least one Bluetooth slave anchor point is arranged outside the vehicle, the Bluetooth master anchor point and the at least one Bluetooth slave anchor point are fixed in position, and the Bluetooth master anchor point and the at least one Bluetooth slave anchor point communicate via wired communication;

[0035] The Bluetooth master anchor point is used to send a detection instruction to the at least one Bluetooth slave anchor point and detect the second Bluetooth signal information of the Bluetooth key after establishing a connection with the Bluetooth key;

[0036] Any Bluetooth slave anchor point, configured to detect the first Bluetooth signal information of the Bluetooth key and the Bluetooth master anchor point within a preset time period after receiving the detection instruction, and send the first Bluetooth signal information to the Bluetooth master anchor point through a bus;

[0037] The Bluetooth main anchor point is also used to determine whether the Bluetooth signal corresponding to the Bluetooth key is a relay forwarding signal according to the method described in the first aspect or any optional implementation method of the first aspect based on the second Bluetooth signal information and the first Bluetooth signal information set sent by any Bluetooth slave anchor point.

[0038] The technical solution provided in the embodiments of the present disclosure has at least the following technical effects or advantages:

[0039] The vehicle relay scene detection method in the embodiment of the present disclosure is applied to the relay detection system, wherein the relay detection system includes a Bluetooth key and a Bluetooth anchor point, the Bluetooth anchor point includes a Bluetooth main anchor point and at least one Bluetooth slave anchor point, the Bluetooth main anchor point is set inside the vehicle, the at least one Bluetooth slave anchor point is set outside the vehicle, and the position between the Bluetooth main anchor point and the at least one Bluetooth slave anchor point is fixed. On this basis, in response to the Bluetooth main anchor point establishing a connection with the Bluetooth key, the first Bluetooth signal information set sent by the at least one Bluetooth slave anchor point and the second Bluetooth signal information of the Bluetooth key are obtained; since the positional relationship between each Bluetooth slave anchor point and the Bluetooth main anchor point is relatively unchanged, the difference between the Bluetooth signal information obtained by each slave anchor point and the Bluetooth signal information obtained by the Bluetooth main anchor point is relatively stable. Therefore, the first feature set of the first Bluetooth signal information set is extracted, and the second feature of the second Bluetooth signal is extracted; the preset classification model is called, and according to the first feature set and the second feature, it is determined whether the Bluetooth signal corresponding to the Bluetooth key is a relay forwarding signal. According to the characteristics of the Bluetooth signal information obtained by each anchor point, it can be classified to determine whether it is a relay forwarding signal, which improves the accuracy of recognition and ensures vehicle safety to a certain extent.

[0040] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] By reading the detailed description of the preferred embodiment below, various other advantages and benefits will become clear to those of ordinary skill in the art. The accompanying drawings are only used for the purpose of illustrating the preferred embodiment and are not considered to be limitations of the present disclosure. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings.

[0042] In the attached picture:

[0043] Figure 1 A schematic diagram of a vehicle relay scenario provided by an embodiment of the present disclosure is shown;

[0044] Figure 2 A schematic diagram of a relay detection system provided by an embodiment of the present disclosure is shown;

[0045] Figure 3 A flow chart of a vehicle relay scene detection method provided by an embodiment of the present disclosure is shown;

[0046] Figure 4 A schematic structural diagram of a vehicle relay scene detection device provided by another embodiment of the present disclosure is shown;

[0047] Figure 5A schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure is shown;

[0048] Figure 6 A schematic diagram of a storage medium provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0049] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0050] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in the present disclosure should have the common meanings understood by those skilled in the art to which the present disclosure belongs.

[0051] The vehicle's Passive Entry Passive Start (PEPS) system is a keyless entry and start system. The main function of the system can be keyless entry: when the driver enters the designated range of the vehicle with an authorized car key, the PEPS system can quickly identify and automatically unlock the door without the driver manually operating the key. Keyless start: Inside the vehicle, the driver only needs to press the start button to start the engine without inserting the key and turning it. When the driver leaves the vehicle, the PEPS system automatically locks the door and enters the anti-theft state, effectively preventing the vehicle from being stolen. The PEPS system can also be personalized, such as seat position, air conditioning temperature, entertainment system preferences, etc., and automatically restored the next time you drive.

[0052] The working principle of the PEPS system is based on the communication between the low-frequency antenna, the car key and the high-frequency receiver. The low-frequency antenna can be installed on the door handle or body of the car to receive the signal from the car key. The car key stores the ID information paired with the vehicle. When the driver approaches the vehicle with the car key, the low-frequency antenna detects the key's signal. The high-frequency receiver is installed inside the vehicle to receive the signal forwarded by the low-frequency antenna and interpret the ID information in it. If the ID information matches the information pre-stored in the vehicle, the system will unlock the door or start the engine.

[0053] Based on the PEPS system, the digital car key system based on Bluetooth received signal strength (RSSI) positioning technology is a technology that uses Bluetooth signal strength for location positioning and vehicle control. The system uses Bluetooth technology to achieve wireless communication between the car key and the vehicle, and uses the RSSI (received signal strength indicator) value as a positioning basis to determine the relative position between the car key (usually a smart device such as a smartphone or a bracelet) and the vehicle. When the car key is close to the vehicle, the system can automatically unlock the door and even start the vehicle, providing users with a convenient and intelligent car experience. The digital car key system based on Bluetooth RSSI positioning technology usually includes the following main components: Bluetooth key controller: As the core control unit of the system, it is responsible for receiving Bluetooth signals from the car key and processing these signals to determine the position and control the vehicle. The Bluetooth antenna can be installed in different locations of the vehicle (such as the door, trunk, etc.) to receive the Bluetooth signal emitted by the car key and transmit the signal strength information to the Bluetooth key controller. The main control module communicates with the Bluetooth key controller, determines the location of the car key based on the received RSSI value, and controls the opening and closing of functions such as vehicle door locks and engine start. The Bluetooth key can be a smartphone, bracelet, or other device with a built-in Bluetooth module, which can be used as a digital car key. Users can pair and communicate with the vehicle through mobile phone apps or other methods.

[0054] The user first needs to pair and connect the smart device to the vehicle via Bluetooth. After successful pairing, the smart device can be used as a digital car key. When the smart device is close to the vehicle, the Bluetooth antenna on the vehicle will receive the Bluetooth signal from the smart device and measure the signal strength (RSSI value). The Bluetooth key controller determines the relative position between the smart device (i.e., Bluetooth key) and the vehicle based on the received RSSI value. Generally, the larger the RSSI value, the closer the distance; conversely, the farther the distance. Based on the position judgment result, the main control module will control the opening and closing of vehicle door locks, engine start and other functions. For example, when the smart device is within the preset unlocking area, the system will automatically unlock the door; when the smart device leaves the preset area, the door will automatically lock.

[0055] In the above Bluetooth digital key system, if the Bluetooth key is far away from the vehicle and is not at a distance that can unlock the vehicle. Figure 1 As shown, in this case, if there is a relay device (such as a repeater, router, etc.) to monitor, forward or tamper with the Bluetooth signal, the communication distance between the Bluetooth key and the vehicle can be extended to achieve the purpose of unlocking and controlling the vehicle. In this case, the safety of the vehicle cannot be ensured.

[0056] When the environment between the vehicle and the Bluetooth key remains unchanged, the greater the signal transmission power of the Bluetooth key, the greater the signal strength received by the vehicle. Based on this feature, in the related technology, after the Bluetooth key approaches the vehicle and establishes a Bluetooth connection with the vehicle, the vehicle side will actively negotiate with the Bluetooth key to change the transmission power of the Bluetooth key according to certain rules; if it is a non-relay scenario, the vehicle side can detect the change in the signal strength emitted by the Bluetooth key; if it is a relay scenario, because the vehicle side detects the signal strength after the repeater amplification, and the signal strength of the repeater at this time will not change according to the agreed rules, it can be identified as a relay scenario, and then the signal can be identified as an illegal signal.

[0057] However, in the above implementation, the Bluetooth signal strength is more easily affected by the surrounding environment, and when there is only one Bluetooth signal, the judgment of the relay scene is inaccurate. Secondly, in a complex environment, changes in the transmission power of the Bluetooth key may cause the Bluetooth connection to be disconnected, affecting the user experience. On the basis of the original Bluetooth key, it is necessary to add additional power control and signal strength detection processes, which affects the original efficiency of vehicle unlocking and control. Furthermore, the direction, speed, and position of the user approaching the vehicle may be different each time, so the signal strength itself will change, which may lead to inaccurate judgment of the relay scene; the vehicle and the Bluetooth key need to cooperate with each other, which is more complicated.

[0058] In view of this, the present disclosure proposes a vehicle relay scene detection method. Figure 2 As shown, the method is applied to a relay detection system, wherein the relay detection system includes a Bluetooth key and a Bluetooth anchor point, the Bluetooth anchor point includes a Bluetooth master anchor point and at least one Bluetooth slave anchor point, the Bluetooth master anchor point is arranged inside a vehicle, and the at least one Bluetooth slave anchor point is arranged outside the vehicle, and the position between the Bluetooth master anchor point and the at least one Bluetooth slave anchor point is fixed.

[0059] The Bluetooth main anchor point is located inside the vehicle, and the Bluetooth main anchor point can be connected to the Bluetooth key by Bluetooth, and connected to the CAN bus of the Bluetooth slave anchor point set outside the vehicle for communication. A processor or a connection processor can also be set in the Bluetooth main anchor point, and the processor is used to identify and determine whether it is a relay scenario based on the signal strength of the Bluetooth key.

[0060] The Bluetooth master anchor point is used to send a detection instruction to at least one Bluetooth slave anchor point and detect the second Bluetooth signal information of the Bluetooth key after establishing a connection with the Bluetooth key; any Bluetooth slave anchor point is used to detect the first Bluetooth signal information of the Bluetooth key and the Bluetooth master anchor point within a preset time period after receiving the detection instruction, and send the first Bluetooth signal information to the Bluetooth master anchor point through a bus; the Bluetooth master anchor point is also used to determine whether the Bluetooth signal corresponding to the Bluetooth key is a relay forwarding signal according to the method of the present invention based on the second Bluetooth signal information and the first Bluetooth signal information set sent by any Bluetooth slave anchor point.

[0061] like Figure 3 As shown, the vehicle relay scene detection method of the embodiment of the present disclosure is applied to Figure 1 The relay detection system shown, specifically, the method may include the following steps:

[0062] In step S31, in response to the Bluetooth master anchor point establishing a connection with the Bluetooth key, a first Bluetooth signal information set sent by at least one Bluetooth slave anchor point and second Bluetooth signal information of the Bluetooth key are obtained.

[0063] The first Bluetooth signal information set includes information about the signal strength of a Bluetooth key detected by at least one Bluetooth slave anchor point and information about the signal strength of a Bluetooth master anchor point, and the second Bluetooth signal information includes information about the signal strength of a Bluetooth key detected by the Bluetooth master anchor point.

[0064] For example, when a user needs to unlock a vehicle, he usually needs to press the unlock button of the Bluetooth key, and the Bluetooth key transmits a Bluetooth signal. After the Bluetooth main anchor point located inside the vehicle detects the Bluetooth signal of the Bluetooth key, it establishes a connection with the Bluetooth key.

[0065] After the Bluetooth master anchor point establishes a connection with the Bluetooth key, a first Bluetooth signal information set for detecting the Bluetooth signal sent by each Bluetooth slave anchor point is obtained, wherein each Bluetooth slave anchor point will send corresponding first Bluetooth signal information. The first Bluetooth signal information may include the identifier of the Bluetooth slave anchor point and the signal strength of the first Bluetooth signal. After detecting the Bluetooth signal of the Bluetooth key, the Bluetooth slave anchor point sends the first Bluetooth signal information to the Bluetooth master anchor point, which may be sent through the vehicle's local area network or other methods. In the actual implementation process, the Bluetooth slave anchor point may send the detected signal to the Bluetooth master anchor point after detecting the Bluetooth signal corresponding to the pre-stored Bluetooth signal identifier. Alternatively, after the Bluetooth master anchor point establishes a connection with the Bluetooth key, the Bluetooth master anchor point sends a detection instruction to the Bluetooth slave anchor point, and the Bluetooth slave anchor point detects the Bluetooth signal with the corresponding Bluetooth identifier in the detection instruction, and sends the detected Bluetooth signal information to the Bluetooth slave anchor point.

[0066] In an optional embodiment, the above step S31 can also be implemented in the following manner: obtaining the first Bluetooth signal information sent by any Bluetooth from the anchor point within a preset time period through the bus, the first Bluetooth signal information being any one in the first Bluetooth signal information set; detecting the second Bluetooth signal information of the Bluetooth key within the preset time period

[0067] For example, the first Bluetooth signal information sent by each Bluetooth slave anchor point can be obtained through the CAN bus. Compared with obtaining through wireless means, the information obtained through the CAN bus reduces the delay to a certain extent and reduces the loss of information.

[0068] To determine whether it is a relay scenario based on the detected Bluetooth signal information, it is necessary to continuously monitor the changes in the Bluetooth signal over a period of time, and determine whether it is a relay forwarding signal based on its changes, thereby improving the accuracy of recognition.

[0069] In step S32, a first feature set of the first Bluetooth signal information set is extracted, and a second feature set of the second Bluetooth signal information is extracted.

[0070] Exemplarily, after receiving the first Bluetooth signal information set and the second Bluetooth signal information set, the received Bluetooth signal may be filtered and denoised to improve the signal quality.

[0071] After preprocessing, the strength, frequency characteristics, arrival time difference and content of the Bluetooth signal in the first Bluetooth signal information sent by each Bluetooth slave anchor point can be extracted. The strength of the Bluetooth signal can reflect the attenuation of signal propagation. The frequency characteristics can obtain the spectrum characteristics of the signal, which is helpful to identify the type and source of the signal. The arrival time difference can determine the time difference between the Bluetooth signal arriving at each Bluetooth slave anchor point based on the positional relationship between each Bluetooth slave anchor point, which is used to locate and analyze the Bluetooth key corresponding to the Bluetooth signal. Parse the content of the Bluetooth signal packet to extract information such as device address and data type.

[0072] The above features can also be extracted from the second Bluetooth signal information, and the extracted features can be compared with the features of each Bluetooth slave anchor point to determine the differences between Bluetooth signals at different detection points.

[0073] Furthermore, after extracting the features in the Bluetooth signal information corresponding to each Bluetooth slave anchor point and the main anchor point, analysis can be performed based on each feature to obtain more important features for identifying relay scenarios. Specifically, principal component analysis (PCA), linear discriminant analysis (LDA), etc. can be used to reduce feature dimensions and improve classification performance.

[0074] In an optional embodiment, for any first Bluetooth signal information, a signal change feature corresponding to the first Bluetooth signal information is calculated to obtain a first feature, where the first feature is any one of the first feature set; and a signal change feature of the second Bluetooth signal information is calculated to obtain a second feature. Specifically, the signal change feature includes a change amount, a change rate, a transmission delay, a delay fluctuation, and stability within a preset time period.

[0075] Exemplarily, the signal change feature can represent the change of the Bluetooth signal during the detection process, where in the non-relay scenario, there will also be changes in signal strength, but the average change is relatively stable; in the relay scenario, the signal strength will be enhanced for a long time, so the average change in signal strength will be large. The signal strength may suddenly increase in the relay scenario, that is, the signal strength change rate is large. In the non-relay scenario, the transmission of the Bluetooth signal will have a relatively stable average delay; however, in the relay scenario, its average delay may increase significantly. In the relay scenario, due to the long signal transmission distance, the delay fluctuation will also increase relatively. In the relay scenario, due to the long signal transmission distance and the presence of factors such as occlusion, the stability of the signal will be significantly reduced.

[0076] The change can be calculated by subtracting the Bluetooth signal strength at the end time from the Bluetooth signal strength at the start time of the preset time period; the change can be calculated by dividing the change by the preset time period; the transmission delay can be calculated based on the average value of the delays of multiple signals sent by each Bluetooth within the preset time period; the delay fluctuation can calculate the standard deviation or variance of the delay of each signal; the stability can calculate the packet loss rate / disconnection and reconnection frequency of each signal within the preset time period.

[0077] In step S33, a preset classification model is called to determine whether the Bluetooth signal corresponding to the Bluetooth key is a relay forwarding signal according to the first feature set and the second feature.

[0078] Exemplarily, the preset classification model can be SVM, neural network, KNN, decision tree, random forest classifier, etc. The embodiment of the present disclosure does not limit the type of classification model, and those skilled in the art can determine it according to actual conditions. The first feature set and the second feature are combined into a complete feature vector (or feature matrix), and then input into the classification model. Use the classification model to predict the input feature vector. This may involve passing the feature vector to the prediction function of the model and receiving an output (such as a category label or probability distribution). According to the output of the model, determine whether the Bluetooth signal corresponding to the Bluetooth key is a relay forwarding signal. If the model outputs a category label (such as "real signal" or "relay signal"), the judgment is made directly based on the label. If the model outputs a probability distribution, you can set a threshold to decide whether to classify the signal as a relay forwarding signal.

[0079] Of course, in some optional embodiments, the preset classification model may be one or more. If the preset classification model is one, the classification model may be called multiple times for classification prediction, and whether it is a relay forwarding signal is determined based on the classification results of multiple predictions. If there are multiple preset classification models, multiple measurements or one measurement may be performed for each classification model, and whether it is a relay forwarding signal is determined based on the prediction results of multiple types of classification models.

[0080] It should be noted that the weight of the corresponding classification model may also be determined according to the prediction accuracy of multiple types of classification models, and after the classification result is weighted according to the weight, it is finally determined whether it is a relay forwarding signal.

[0081] Specifically, in an optional embodiment, the preset classification model is called multiple times, and the classification results corresponding to each call of the preset classification model are determined according to the first feature set and the second feature; the target classification result is determined according to the relationship between the number of each classification result and the number of times the preset classification model is called; if the target classification result is an unstable signal, the Bluetooth signal corresponding to the Bluetooth key is a relay scenario; if the target classification result is a stable signal, the Bluetooth signal corresponding to the Bluetooth key is a non-relay scenario.

[0082] Among them, calling the preset classification model multiple times to determine the corresponding classification results can be the i-th calling of the preset classification model, and determining the i-th classification result according to the first feature set and the second feature set; if i is equal to the preset number of calls, determining the classification results from the 1st to the i-th time; if i is less than the preset number of calls, continuing to call the preset classification model, and determining the i+1-th classification result according to the first feature set and the second feature set, until i+1 is equal to the preset number of calls.

[0083] The preset classification model can also be pre-trained in the following way to ensure the accuracy of identifying Bluetooth signals.

[0084] 1. Collect data in different scenarios (various indoor and outdoor parking lots, open areas, crowded areas, etc., covering all common car use scenarios); in each scenario, collect data in relay (multiple relay modes are possible) and non-relay modes;

[0085] 2. Data preprocessing: extract the above features from the collected data as a data element of the data set. All data elements will form a data set, of which 20% of the data is used as a test set and 80% as a training set.

[0086] 3. Use the prepared data set to train the machine learning classifier. After training, the trained classifier can be integrated into the Bluetooth main anchor point so that it can run on the Bluetooth main anchor point.

[0087] The vehicle relay scene detection method provided by the embodiment of the present disclosure is applied to the relay detection system, wherein the relay detection system includes a Bluetooth key and a Bluetooth anchor point, the Bluetooth anchor point includes a Bluetooth main anchor point and at least one Bluetooth slave anchor point, the Bluetooth main anchor point is set inside the vehicle, and the at least one Bluetooth slave anchor point is set outside the vehicle, and the position between the Bluetooth main anchor point and the at least one Bluetooth slave anchor point is fixed. On the basis of the original Bluetooth digital key system, there is no need to add / modify hardware, and the anti-relay function can be realized by modifying the software strategy. On this basis, in response to the Bluetooth main anchor point and the Bluetooth key establishing a connection, the first Bluetooth signal information set sent by at least one Bluetooth slave anchor point and the second Bluetooth signal information of the Bluetooth key are obtained; since the positional relationship between each Bluetooth slave anchor point and the Bluetooth main anchor point is relatively unchanged, the difference between the Bluetooth signal information obtained by each slave anchor point and the Bluetooth signal information obtained by the Bluetooth main anchor point is relatively stable. Therefore, the first feature set of the first Bluetooth signal information set is extracted, and the second feature of the second Bluetooth signal is extracted; the preset classification model is called, and according to the first feature set and the second feature, it is determined whether the Bluetooth signal corresponding to the Bluetooth key is a relay forwarding signal. According to the characteristics of the Bluetooth signal information obtained by each anchor point, it can be classified to determine whether it is a relay forwarding signal, which improves the accuracy of recognition and ensures vehicle safety to a certain extent.

[0088] Corresponding to the implementation of the above vehicle relay scene detection method, the embodiment of the present disclosure also provides a vehicle relay scene detection device, which is used to perform the above Figure 3 The vehicle relay scene detection method of any embodiment shown in the figure. The device is applied to a relay detection system, the relay detection system includes a Bluetooth key and a Bluetooth anchor point, the Bluetooth anchor point includes a Bluetooth master anchor point and at least one Bluetooth slave anchor point, the Bluetooth master anchor point is set inside the vehicle, the at least one Bluetooth slave anchor point is set outside the vehicle, and the position between the Bluetooth master anchor point and the at least one Bluetooth slave anchor point is fixed, such as Figure 4 As shown, the vehicle relay scene detection device includes:

[0089] an information acquisition module 401, configured to acquire, in response to the Bluetooth master anchor point establishing a connection with the Bluetooth key, a first Bluetooth signal information set sent by the at least one Bluetooth slave anchor point and second Bluetooth signal information of the Bluetooth key, wherein the first Bluetooth signal information set is information about the signal strength of the Bluetooth key detected by the at least one Bluetooth slave anchor point and information about the signal strength of the Bluetooth master anchor point, and the second Bluetooth signal information is information about the signal strength of the Bluetooth key detected by the Bluetooth master anchor point;

[0090] A feature extraction module 402, configured to extract a first feature set of the first Bluetooth signal information set, and extract a second feature of the second Bluetooth signal information;

[0091] The determination module 403 is used to call a preset classification model and determine whether the Bluetooth signal corresponding to the Bluetooth key is a relay forwarding signal according to the first feature set and the second feature.

[0092] The vehicle relay scene detection device provided in the above-mentioned embodiment of the present disclosure and the vehicle relay scene detection method provided in the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0093] The present disclosure also provides an electronic device for executing the above data transmission method. Figure 5 , which shows a schematic diagram of an electronic device provided by some embodiments of the present disclosure. Figure 5 As shown, the electronic device includes: a processor 500, a memory 501, a bus 502 and a communication interface 503, the processor 500, the communication interface 503 and the memory 501 are connected through the bus 502; the memory 501 stores a computer program that can be run on the processor 500, and the processor 500 executes the aforementioned Figure 3 The method provided.

[0094] The memory 501 may include a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 503 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0095] The bus 502 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 501 is used to store programs. After receiving the execution instruction, the processor 500 executes the program. Figure 3 The disclosed method may be applied in the processor 500 or implemented by the processor 500 .

[0096] The processor 500 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 500 or the instruction in the form of software. The above processor 500 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 501, and the processor 500 reads the information in the memory 501 and completes the steps of the above method in combination with its hardware.

[0097] The electronic device provided by the embodiment of the present disclosure and the data transmission method provided by the embodiment of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented by them.

[0098] The present disclosure also provides a computer-readable storage medium corresponding to the data transmission method provided in the above embodiment. Figure 6 The computer-readable storage medium shown is a CD 30 on which a computer program (ie, a program product) is stored. When the computer program is run by a microprocessor, it will execute the data transmission method provided by any of the aforementioned embodiments.

[0099] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0100] The computer-readable storage medium provided by the above-mentioned embodiments of the present disclosure and the data transmission method provided by the embodiments of the present disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0101] It should be noted that:

[0102] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present disclosure can be practiced without these specific details. In some instances, well-known structures and technologies are not shown in detail so as not to obscure the understanding of this description.

[0103] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present disclosure, the various features of the present disclosure are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following schematic diagram: the claimed disclosure requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, the inventive aspects lie in less than all the features of the single embodiment disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present disclosure.

[0104] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present disclosure and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0105] The above are only preferred specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present disclosure should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A vehicle relay scene detection method, characterized in that: The method is applied to a relay detection system, the relay detection system includes a Bluetooth key and a Bluetooth anchor point, the Bluetooth anchor point includes a Bluetooth master anchor point and at least one Bluetooth slave anchor point, the Bluetooth master anchor point is arranged inside a vehicle, the at least one Bluetooth slave anchor point is arranged outside the vehicle, and the positions between the Bluetooth master anchor point and the at least one Bluetooth slave anchor point are fixed, the method includes: In response to the Bluetooth master anchor point establishing a connection with the Bluetooth key, obtaining a first Bluetooth signal information set sent by the at least one Bluetooth slave anchor point and second Bluetooth signal information of the Bluetooth key, wherein the first Bluetooth signal information set is information about the signal strength of the Bluetooth key detected by the at least one Bluetooth slave anchor point and information about the signal strength of the Bluetooth master anchor point, and the second Bluetooth signal information is information about the signal strength of the Bluetooth key detected by the Bluetooth master anchor point; Extracting a first feature set of the first Bluetooth signal information set, and extracting a second feature of the second Bluetooth signal information; A preset classification model is called to determine whether the Bluetooth signal corresponding to the Bluetooth key is a relay forwarding signal according to the first feature set and the second feature.

2. The method according to claim 1, characterized in that The acquiring of the first Bluetooth signal information set sent by the at least one Bluetooth slave anchor point and the second Bluetooth signal information of the Bluetooth key includes: Acquire, through the bus, first Bluetooth signal information sent by any Bluetooth slave anchor point within a preset time period, wherein the first Bluetooth signal information is any one in the first Bluetooth signal information set; The second Bluetooth signal information of the Bluetooth key is detected within the preset time period.

3. The method according to claim 2, characterized in that The number of the Bluetooth slave anchor points is four.

4. The method according to claim 2 or 3, characterized in that: The extracting the first feature set of the first Bluetooth signal information set and the extracting the second feature of the second Bluetooth signal information include: For any first Bluetooth signal information, calculate a signal change feature corresponding to the first Bluetooth signal information to obtain the first feature, where the first feature is any one of the first feature set; Calculate the signal change characteristic of the second Bluetooth signal information to obtain the second characteristic.

5. The method according to claim 4, characterized in that The signal change characteristics include the change amount, change rate, transmission delay, delay fluctuation and stability within the preset time period.

6. The method according to claim 1, characterized in that The calling of the preset classification model to determine whether the Bluetooth signal corresponding to the Bluetooth key is a relay forwarding signal according to the first feature set and the second feature includes: Calling a preset classification model multiple times, and determining a classification result corresponding to each call of the preset classification model according to the first feature set and the second feature; Determine the target classification result according to the relationship between the number of classification results and the number of times the preset classification model is called; If the target classification result is an unstable signal, the Bluetooth signal corresponding to the Bluetooth key is a relay scenario; If the target classification result is a stable signal, the Bluetooth signal corresponding to the Bluetooth key is a non-relay scenario.

7. The method according to claim 6, characterized in that The multiple calls to the preset classification model, and determining the classification results corresponding to each call of the preset classification model according to the first feature set and the second feature, respectively, include: Calling the preset classification model for the i-th time, and determining the i-th classification result according to the first feature set and the second feature set; If i is equal to the preset number of calls, determine the classification results from the 1st to the i-th time; If i is less than the preset number of calls, continue to call the preset classification model, and determine the i+1th classification result according to the first feature set and the second feature set, until i+1 is equal to the preset number of calls.

8. The method according to claim 6 or 7, characterized in that: The classification results include stable signals and unstable signals, and determining the target classification results according to the relationship between the number of classification results and the number of times the preset classification model is called includes: If the number of times the signal is determined to be the stable signal is greater than the number of times the signal is determined to be the unstable signal, the target classification result is a stable signal; If the number of times the signal is determined to be the stable signal is less than or equal to the number of times the signal is determined to be the unstable signal, the target classification result is an unstable signal.

9. A vehicle relay scene detection device, characterized in that: The device is applied to a relay detection system, the relay detection system includes a Bluetooth key and a Bluetooth anchor point, the Bluetooth anchor point includes a Bluetooth master anchor point and at least one Bluetooth slave anchor point, the Bluetooth master anchor point is arranged inside the vehicle, the at least one Bluetooth slave anchor point is arranged outside the vehicle, the position between the Bluetooth master anchor point and the at least one Bluetooth slave anchor point is fixed, and the device includes: an information acquisition module, configured to acquire, in response to the Bluetooth master anchor point establishing a connection with the Bluetooth key, a first Bluetooth signal information set sent by the at least one Bluetooth slave anchor point and second Bluetooth signal information of the Bluetooth key, wherein the first Bluetooth signal information set is information about the signal strength of the Bluetooth key detected by the at least one Bluetooth slave anchor point and information about the signal strength of the Bluetooth master anchor point, and the second Bluetooth signal information is information about the signal strength of the Bluetooth key detected by the Bluetooth master anchor point; A feature extraction module, used to extract a first feature set of the first Bluetooth signal information set, and to extract a second feature of the second Bluetooth signal information; The determination module is used to call a preset classification model to determine whether the Bluetooth signal corresponding to the Bluetooth key is a relay forwarding signal according to the first feature set and the second feature.

10. A vehicle relay scene detection system, characterized in that: The system comprises a Bluetooth key and a Bluetooth anchor point, wherein the Bluetooth anchor point comprises a Bluetooth master anchor point and at least one Bluetooth slave anchor point, wherein the Bluetooth master anchor point is arranged inside the vehicle, and the at least one Bluetooth slave anchor point is arranged outside the vehicle, wherein the positions of the Bluetooth master anchor point and the at least one Bluetooth slave anchor point are fixed, and the Bluetooth master anchor point and the at least one Bluetooth slave anchor point communicate via wires; The Bluetooth master anchor point is used to send a detection instruction to the at least one Bluetooth slave anchor point and detect the second Bluetooth signal information of the Bluetooth key after establishing a connection with the Bluetooth key; Any Bluetooth slave anchor point, configured to detect the first Bluetooth signal information of the Bluetooth key and the Bluetooth master anchor point within a preset time period after receiving the detection instruction, and send the first Bluetooth signal information to the Bluetooth master anchor point through a bus; The Bluetooth main anchor point is also used to determine whether the Bluetooth signal corresponding to the Bluetooth key is a relay forwarding signal according to the method described in any one of claims 1 to 8 above based on the second Bluetooth signal information and the first Bluetooth signal information set sent by any Bluetooth slave anchor point.

Images