Remote vehicle control safety control method and system and readable storage medium

Through deep learning models, the user behavior patterns are analyzed and matched, combined with two-factor verification and biometric verification, the problem of remote vehicle control technology being easily attacked is solved, the security and recognition capabilities are improved, and the legality of remote vehicle control requests is ensured. accuracy.

CN119011561APending Publication Date: 2024-11-22ZHIJI AUTOMOTIVE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410964079.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The existing remote vehicle control technology is prone to malicious attacks and is difficult to adapt to network changes in real time. It lacks deep learning and analysis of user behavior, which leads to the inability to effectively distinguish between legitimate users and illegal attackers, increasing the risk of remote vehicle control.

Method used

The deep learning model is used to analyze the remote vehicle control request and vehicle control data, identify the user behavior pattern, and match it with the pre-stored behavior pattern to judge the legitimacy of the request, and combine two-factor verification and biometric verification to transmit information through the encrypted channel.

Benefits of technology

Effectively distinguishing between legal requests and malicious attacks, improving the ability to identify malicious attacks and vehicle security protection capabilities, ensuring the timeliness and accuracy of remote vehicle control requests, and enhancing security.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119011561A_ABST
    Figure CN119011561A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of automobile safety, and particularly relates to a remote automobile control safety control method and system and a readable storage medium, and the remote automobile control safety control method comprises the steps: obtaining a remote automobile control request and corresponding automobile control data; analyzing the remote vehicle control request and the vehicle control data through a deep learning model, and identifying a user behavior mode; and matching the user behavior mode with a pre-stored behavior mode, and judging the legality of the remote vehicle control request based on a matching result. According to the invention, the safety of remote vehicle control is improved, and the problem that the vehicle is easy to be maliciously attacked and illegally controlled in the remote vehicle control process is solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of automobile safety, and in particular relates to a remote vehicle safety control method, system and readable storage medium. Background Art

[0002] With the rapid development of science and technology, smart cars have gradually become an important part of modern transportation. Smart cars not only have traditional driving functions, but also integrate many advanced technologies such as automatic driving, remote control, OTA updates, etc.

[0003] Take remote car control technology as an example. Traditional remote car control technology is mainly based on wireless communication technology, such as RFID or Bluetooth technology to achieve remote control. Users can control certain functions of the car, such as unlocking, starting or shutting down the engine, through a dedicated remote control or smartphone application. However, these technologies mainly rely on traditional password authentication methods, which are easily cracked by malicious attackers and lack effective mechanisms to identify and block malicious remote car control requests. Moreover, in a complex network environment, these technologies are also difficult to adapt to network changes in real time, increasing the risk of being attacked. In addition, since different cars correspond to different users, different users have different behaviors, and the existing technology also lacks deep learning and analysis of user behavior, it is impossible to effectively distinguish between legitimate users and illegal attackers, increasing the risk of remote car control. Summary of the invention

[0004] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide a remote vehicle control safety control method, system and readable storage medium, which improve the safety of remote vehicle control and solve the problem that the vehicle is vulnerable to malicious attacks and illegal control during remote vehicle control.

[0005] To achieve the above purpose, the present invention adopts the following technical solution.

[0006] A first aspect of the present invention provides a remote vehicle control safety control method, comprising: Obtain remote vehicle control requests and corresponding vehicle control data; Analyzing the remote vehicle control request and the vehicle control data through a deep learning model to identify user behavior patterns; The user behavior pattern is matched with a pre-stored behavior pattern, and the legitimacy of the remote vehicle control request is determined based on the matching result.

[0007] As an implementation mode of the present invention, the deep learning model is a trained neural network, and the process of acquiring the pre-stored behavior pattern includes: Get the historical requests for remote vehicle control and the corresponding historical request data; Extracting preset features from the remote vehicle control history requests and the corresponding history request data, wherein the preset features at least include user behavior habit data, and the user behavior habit data includes normal behavior habit data and abnormal behavior habit data; The preset features are used as input independent variables of the neural network, and the neural network is trained to obtain pre-stored behavior patterns, which include pre-stored normal behavior patterns corresponding to the normal behavior habit data and pre-stored abnormal behavior patterns corresponding to the abnormal behavior data.

[0008] As an implementation manner of the present invention, the vehicle control data at least includes user location data, user request time data and user device information when the remote vehicle control request occurs.

[0009] As an implementation mode of the present invention, the behavior habit data at least includes user request content, user operation frequency, user operation time and user operation sequence.

[0010] As an implementation mode of the present invention, the user behavior pattern at least includes a normal behavior pattern and an abnormal behavior pattern; The matching of the user behavior pattern with the pre-stored behavior pattern includes: If the user behavior pattern is a normal behavior pattern, the user behavior pattern successfully matches the pre-stored normal behavior pattern; if the user behavior pattern is an abnormal behavior pattern, the user behavior pattern successfully matches the pre-stored abnormal behavior pattern.

[0011] As an implementation mode of the present invention, after successfully matching with a pre-stored normal behavior pattern and obtaining the remote vehicle control request as a legitimate request, it also includes security verification of the remote vehicle control request and the vehicle control data by using two-factor verification and / or biometric verification.

[0012] A second aspect of the present invention provides a remote vehicle control safety control method, the remote vehicle control safety control method is implemented using a user device, a server and a vehicle-side device as carriers, and an application and / or a mini-program for remote vehicle control is installed on the user device; The application program and / or applet obtains a remote vehicle control request, and obtains corresponding vehicle control data based on the remote vehicle control request; The application program and / or applet sends the remote vehicle control request and corresponding vehicle control data to a server; The server analyzes the remote vehicle control request and the vehicle control data through a deep learning model to identify user behavior patterns; The server matches the user behavior pattern with a pre-stored behavior pattern, and determines the legitimacy of the remote vehicle control request based on the matching result; When the remote vehicle control request is a legitimate request, the server performs security verification on the remote vehicle control request and the vehicle control data through two-factor verification and / or biometrics, and if the verification is successful, the server sends the remote vehicle control request to the vehicle-end device; The vehicle-end device performs corresponding remote vehicle control operations based on the remote vehicle control request.

[0013] As an implementation manner of the present invention, information is transmitted between the user device and the server, and between the server and the vehicle-end device via an encrypted channel.

[0014] A third aspect of the present invention provides a remote vehicle control safety control system, comprising: An acquisition module, at least used to acquire a remote vehicle control request and corresponding vehicle control data; an identification module, at least used to analyze the remote vehicle control request and the vehicle control data through a deep learning model to identify a user behavior pattern; A matching module, at least used to match the user behavior pattern with a pre-stored behavior pattern; The judgment module is at least used to judge the legitimacy of the remote vehicle control request based on the matching result.

[0015] As an embodiment of the present invention, the remote vehicle control safety control system further includes a secondary verification module, an encryption module, an alarm module and / or a recording module; The secondary verification module is at least used to perform security verification on the remote vehicle control request and the vehicle control data by using two-factor verification and / or biometric verification; The encryption module is at least used to provide an encryption channel for information transmission between modules; The warning module is at least used to immediately notify the user when the remote vehicle control request is an illegal request; The recording module is at least used to record the generation information of the remote vehicle control request, and the generation information at least includes the request time, the request location and the operation type.

[0016] A fourth aspect of the present invention provides an electronic device, comprising: At least one processor; and at least one memory in communication with the processor, wherein: the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the steps of the method described in the first aspect or the second aspect of the present invention.

[0017] A fifth aspect of the present invention provides a readable storage medium storing a computer program, wherein the computer program is executed by a processor to perform the steps of the method described in the first aspect or the second aspect of the present invention.

[0018] In summary, compared with the prior art, the present invention includes at least one of the following beneficial technical effects: 1. The present invention uses a deep learning model to compare user behavior patterns with pre-stored behavior patterns, which can effectively distinguish between legitimate requests and malicious attacks, thereby improving the ability to identify malicious attacks and protect vehicle safety; 2. The present invention can self-learn and adjust according to the ever-changing network environment and attack strategies, and can also analyze and process the information from the remote vehicle control instructions and the corresponding vehicle control data in real time, so as to ensure the timeliness and accuracy of the remote vehicle control request in real time, and ensure the convenience of vehicle control and vehicle safety for users; 3. After making a legality judgment, the present invention also adds a two-factor verification and / or a biometric feature link, further improving the security of remote vehicle control. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 It is a flowchart of a remote vehicle safety control method according to a specific embodiment of the present invention.

[0021] Figure 2 It is a flowchart of another remote vehicle safety control method according to a specific embodiment of the present invention.

[0022] Figure 3 The present invention is a block diagram of a remote vehicle control safety control system according to a specific embodiment of the present invention. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application. In addition, it should be understood that the specific implementation methods described herein are only used to illustrate and explain the present application, and are not used to limit the present application.

[0024] It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments of the present application. In addition, in the following embodiments, the description of each embodiment has its own emphasis, and for parts not described in detail in one embodiment, reference can be made to the relevant description of other embodiments.

[0025] With the rapid development of science and technology, smart driving cars have gradually become an important part of modern transportation. Smart driving cars not only have traditional driving functions, but also integrate many advanced technologies such as automatic driving, remote control, OTA updates, etc. However, the introduction of these technologies also brings a series of safety challenges.

[0026] As cars are connected to the Internet, they have indirectly become targets of cyber attacks. Malicious attackers can invade the car's control system through the network, tamper with its behavior or steal user data.

[0027] Self-driving cars rely on a range of sensors and algorithms to perceive their environment and make decisions, but they can also be vulnerable to attacks, such as sensor data being tampered with or algorithms being deceived.

[0028] Over-the-air technology allows automakers to remotely update a car's software, but if the update process is not adequately protected, attackers could insert malicious code or tamper with the updates.

[0029] Early remote car control technologies were mainly based on wireless communication technologies, such as RFID or Bluetooth. Users could control certain functions of the car, such as unlocking, starting or shutting down the engine, through dedicated remote controls or smartphone applications. However, these technologies are vulnerable to man-in-the-middle attacks or replay attacks.

[0030] To enhance security, some automakers have introduced two-factor authentication or biometric authentication, but these authentication methods still have vulnerabilities, such as SMS verification codes being intercepted or biometrics being copied.

[0031] In view of this, if Figure 1 As shown, the first aspect of the present invention provides a remote vehicle safety control method, comprising the following steps.

[0032] Step S11: Obtain a remote vehicle control request and corresponding vehicle control data; specifically, there are many types of remote vehicle control requests, such as a request to unlock a door, a request to start an engine, a request to lock a door, etc. The remote vehicle control request can be obtained by a user inputting a corresponding instruction in a designated area of ​​an application or applet on a user device such as a tablet computer, a smart phone, or other mobile terminal; different remote vehicle control requests have corresponding vehicle control data, and the vehicle control data at least includes user location data when the remote vehicle control request occurs, user request time data, and user device information, for example, the vehicle control data corresponding to a request to unlock a door or a request to lock a door includes user identity information, instruction type, timestamp, geographic location, device information, network information, and a security token.

[0033] Step S12: Analyze the remote vehicle control request and the vehicle control data through a deep learning model to identify user behavior patterns; specifically, by using a deep learning model to conduct an in-depth analysis of the user's remote vehicle control request and identify the user behavior pattern represented by the remote vehicle control request, it is possible to effectively distinguish between legitimate requests and malicious attacks.

[0034] Step S13: Match the user behavior pattern with the pre-stored behavior pattern, and judge the legitimacy of the remote vehicle control request based on the matching result. The legitimacy specifically refers to whether the remote vehicle control is legal or illegal. The illegality of remote vehicle control indicates that a suspicious or malicious request may be detected.

[0035] Here, by comparing the user behavior pattern with the pre-stored behavior pattern, legitimate requests and malicious attacks can be effectively distinguished. The present invention analyzes the user's remote vehicle control request through a deep learning model, identifies the user's behavior pattern, and then judges the legitimacy of the request by matching it with the pre-stored behavior pattern to ensure the security of remote vehicle control. Compared with traditional token- or rule-based authentication methods, the deep learning-based security authentication method of the present invention has higher flexibility and can adapt to complex and personalized user behaviors. By integrating information from multiple dimensions such as user location data, request time data, and device information, more factors are considered when judging legitimacy, so that possible malicious attacks can be effectively dealt with and the security of remote vehicle control can be improved.

[0036] In one embodiment of the present invention, the deep learning model is a trained neural network. Specifically, obtaining the deep learning model includes the following contents.

[0037] Data collection: A large amount of historical remote vehicle control requests and corresponding vehicle control data need to be collected. These data include multi-dimensional information such as user operation behavior, user operation time, user operation location, and user operation frequency.

[0038] Data preprocessing: Clean and format the collected data to meet the input requirements of the deep learning model.

[0039] Feature engineering: Extract key features from preprocessed data that are helpful in predicting user behavior patterns. These key features can characterize the specific user behavior habits when the user makes a specific remote vehicle control request, also known as user behavior habit data, such as user operation frequency, user operation time, and user operation sequence.

[0040] Model selection: Select a suitable neural network according to the characteristics of different remote vehicle control requests, for example, select a convolutional neural network (CNN) for remote vehicle control requests related to image data, and a recurrent neural network (RNN) for remote vehicle control requests related to time series data, etc. In an application scenario of the present invention, the selected convolutional neural network (CNN) consists of an input layer, a convolutional layer, a pooling layer, a fully connected layer, an activation function layer, a batch normalization layer, and an output layer; the recurrent neural network (RNN) consists of an input layer, a recurrent layer, a hidden layer, an output layer, an activation function layer, and other layers such as a fully connected layer and a Dropout layer.

[0041] Model training: Use a large number of historical remote vehicle control requests and corresponding vehicle control data that have completed feature engineering to train the neural network, and continuously optimize the neural network parameters through the back propagation algorithm to minimize the prediction error. Among them, these data include the user's normal operation mode and known abnormal or malicious modes, so that the model training is more diverse. After training, the model can identify the behavior patterns in the new request data and compare them with the learned normal behavior patterns or abnormal behavior patterns, where abnormal behavior patterns include but are not limited to malicious attack behavior patterns and illegal behavior patterns. Select a training set and a validation set, where the training set is used to train the model data set, and the validation set is used to adjust the model hyperparameters and evaluate the model performance data set. Usually the data set accounts for about 80%, the validation set accounts for about 10%, and the remaining 10% is the test set. The data can be better utilized through techniques such as cross-validation. Implementation method of the back propagation algorithm for remote vehicle control: 1. Obtain a neural network model, such as CNN or RNN; 2. Collect data sets, including vehicle sensor data and control instructions under different environments; 3. Train the neural network model, use the collected data sets to train the neural network model, and use the back propagation algorithm to optimize the model parameters; 4. Control the vehicle in real time, deploy a control unit, control system or control module on the vehicle, receive the control instructions output by the model, and convert them into actual control actions, such as remote start.

[0042] Pattern recognition: After training, the model can recognize new remote vehicle control requests and corresponding user behavior patterns in the vehicle control data, and compare or match them with the learned user behavior patterns.

[0043] Model validation and testing: Evaluate the performance of the model on independent validation and test sets to ensure that the model has good generalization capabilities.

[0044] Model deployment: Deploy the trained model to the server for real-time processing of remote vehicle control requests. In addition, the model has self-learning capabilities. As time goes by, the model can continue to learn new data, thereby gaining a deeper understanding and recognition of user behavior patterns.

[0045] The learned behavior pattern is also called a pre-stored behavior pattern, and the pre-stored behavior pattern includes a pre-stored normal behavior pattern and a pre-stored abnormal behavior pattern.

[0046] Furthermore, the process of obtaining the pre-stored behavior pattern includes: Get the historical requests for remote vehicle control and the corresponding historical request data; Extracting preset features from the historical requests for remote vehicle control and historical request data thereof, wherein the preset features at least include user behavior habit data, and the user behavior habit data includes normal behavior habit data and abnormal behavior habit data; The preset features are used as input independent variables of the neural network, and the neural network is trained to obtain pre-stored behavior patterns, which include pre-stored normal behavior patterns corresponding to the normal behavior habit data and pre-stored abnormal behavior patterns corresponding to the abnormal behavior data.

[0047] In one embodiment of the present invention, the user behavior pattern includes at least a normal behavior pattern and an abnormal behavior pattern; wherein the normal behavior pattern can be understood as for a legitimate user, its operating behavior will form a certain pattern, such as starting the vehicle every morning, or locking the vehicle at a specific location; the abnormal behavior pattern can be understood as for illegal operations or malicious attackers, the behavior pattern is usually significantly different from the normal pattern, such as requests initiated at abnormal times or locations, or frequent and irregular operations, etc.

[0048] Furthermore, matching the user behavior pattern with a pre-stored behavior pattern includes: If the user behavior pattern is a normal behavior pattern, the user behavior pattern successfully matches the pre-stored normal behavior pattern, which means that the remote vehicle control request is legal; If the user behavior pattern is an abnormal behavior pattern, and the user behavior pattern successfully matches the pre-stored abnormal behavior pattern, it means that the remote vehicle control request is illegal, and the remote vehicle control request will be rejected or further verified.

[0049] In one embodiment of the present invention, after successfully matching with the pre-stored normal behavior pattern and obtaining that the remote vehicle control request is a legitimate request, please continue to refer to Figure 1 The remote vehicle control safety control method further includes step S14: performing safety verification on the remote vehicle control request and the vehicle control data by using two-factor verification and / or biometric verification.

[0050] Here, dual authentication can be achieved in this way to improve the security of remote vehicle control.

[0051] like Figure 2 As shown, the second aspect of the present invention provides a remote vehicle control safety control method, wherein the remote vehicle control safety control method is implemented with a user device, a server and a vehicle-side device as carriers, and an application and / or a small program for remote vehicle control is installed on the user device, and the method mainly includes: Step S21: the application and / or applet obtains a remote vehicle control request, and obtains corresponding vehicle control data based on the remote vehicle control request, wherein the remote vehicle control request corresponds to at least a door opening and closing request or an engine starting request; Step S22: the application and / or applet sends the remote vehicle control request and the corresponding vehicle control data to the server; Step S23: the server analyzes the remote vehicle control request and the vehicle control data through a deep learning model to identify user behavior patterns; Step S24: the server matches the user behavior pattern with a pre-stored behavior pattern, and determines the legitimacy of the remote vehicle control request based on the matching result; Step S25: When the remote vehicle control request is a legitimate request, the server performs security verification on the remote vehicle control request and the vehicle control data through two-factor verification and / or biometrics. If the verification is successful, the server sends the remote vehicle control request to the vehicle-end device; Step S26: The vehicle-side device performs corresponding remote vehicle control operations based on the remote vehicle control request. The remote vehicle control operations at least include opening and closing vehicle doors or starting the engine. Specifically, the opening and closing vehicle doors operations include unlocking vehicle doors or locking vehicle doors. The starting engine operation can also be understood as starting the vehicle.

[0052] Specifically, the server can be a central server, which is used to process and verify remote vehicle control requests, wherein the deep learning model and the database can be built into the central server; the vehicle-side device can be installed inside the car and communicate with the central server to receive and execute the remote vehicle control instructions of the central server.

[0053] Specifically, the database establishment process includes the following information: Database design: Design the database architecture based on the requirements of remote vehicle control and determine the data table structure, fields, and relationships. Data storage: The collected remote vehicle control requests and corresponding vehicle control data are stored in the database, including the original data of the remote vehicle control requests and the corresponding vehicle control data and the processed key feature data. Data maintenance: Regularly maintain the database, including data backup, index optimization, data cleanup and other operations.

[0054] Specifically, the database content includes the following information: User information: including user’s basic information, registration information, login records, operating habits, etc. Request log: records detailed information of each remote vehicle control request, including request time, request location, operation type, etc. Behavior patterns: store identified user behavior patterns, commonly used remote vehicle control operations, and time periods of frequent operations, etc. Security events: record all suspicious or malicious requests detected by the system and the corresponding processing results. System feedback: includes user feedback on remote vehicle control operations and automatic feedback information from the system.

[0055] Here, through the above process and content design, the central server can effectively process and verify remote vehicle control requests, while using deep learning models to improve the accuracy of identifying illegal operations and ensure vehicle safety.

[0056] Furthermore, in order to ensure data security, information is transmitted between the user device and the server, and between the server and the vehicle-end device through an encrypted channel.

[0057] Further, in step S22, the application and / or applet sends the user's remote vehicle control request and corresponding vehicle control data to the central server. The vehicle control data described generally includes but is not limited to the user's identity information, request type, timestamp, geographic location, device information, etc.

[0058] In order to better describe the vehicle control data, the relevant data required for a specific remote vehicle control request or instruction is exemplified below.

[0059] Remote control command 1: open and close the door User identity information: used to verify whether the operator has the authority to perform the operation; Command type: Specify whether to lock or unlock the door; Timestamp: prevent replay attacks and ensure the timeliness of requests; Geographic location: used to verify whether the user is near the vehicle. This data is not required and can be selected according to the actual situation, because it is normal for the vehicle to be away during remote control. Device information: including device model, operating system version, etc., used to verify the source of the request; Network information: IP address, used to analyze the requested network environment; Security token: used to verify the legitimacy of the request;

[0060] Remote control vehicle command 2: Start the vehicle: User identity information: same as above; Command type: It is clear that the command is to start the vehicle; Timestamp: Same as above; Geographic location: To start the vehicle, the user is usually required to be within a certain distance from the vehicle to ensure safety; Equipment information: Same as above; Network information: Same as above; Security token: Same as above; Battery status: The battery level and health of the electric vehicle to ensure that the vehicle has enough power to start; Charging status: whether the vehicle is being charged, as electric vehicles cannot be started while charging; Temperature Information: Battery performance may be affected by temperature, especially under extreme weather conditions.

[0061] It should be noted that most of the data requirements for opening and closing doors and starting the vehicle are consistent, as these basic data are the basic elements for safety verification and operation authorization. However, starting the vehicle is a more complex operation than opening and closing doors, involving the vehicle's power system.

[0062] Therefore, additional data is needed to ensure operational safety and vehicle availability. For example: Battery status: Before starting the vehicle, you need to make sure the battery has sufficient power. Charging Status: Requires confirmation that the vehicle is not in a charging state to allow starting. Temperature information: The battery performance of electric vehicles is greatly affected by temperature, so it is necessary to check before starting to ensure that the battery is working in the best condition.

[0063] These differences are mainly due to the fact that starting a vehicle is a higher safety risk operation than opening and closing a door, which may have a more direct impact on the vehicle and the surrounding environment. Therefore, the system needs more data to ensure the legality and safety of the operation.

[0064] Although the vehicle control data corresponding to different remote vehicle control commands may be different, the acquisition logic itself is consistent, that is, to ensure the legality of the execution of remote vehicle control and the safety of the controlled vehicle.

[0065] Furthermore, after the remote vehicle control is completed, the vehicle-side device can feed back the final result of the remote vehicle control to the central server, and the central server can send the operation result to the user device, and the user can see the result of the remote vehicle control on the application or mini program.

[0066] Here, the present invention can self-learn and adjust according to the ever-changing network environment and attack strategies, and can also ensure the timeliness and accuracy of remote vehicle control requests in real time by real-time analysis and processing of information from remote vehicle control instructions and corresponding vehicle control data, thereby ensuring user convenience in vehicle control and safety in vehicle use.

[0067] like Figure 3 As shown, the third aspect of the present invention provides a remote vehicle control safety control system, comprising: An acquisition module 31 is at least used to acquire a remote vehicle control request and corresponding vehicle control data; The identification module 32 is at least used to analyze the remote vehicle control request and the vehicle control data through a deep learning model to identify a user behavior pattern; A matching module 33, at least used to match the user behavior pattern with a pre-stored behavior pattern; The judgment module 34 is at least used to judge the legitimacy of the remote vehicle control request based on the matching result.

[0068] In one embodiment of the present invention, the remote vehicle control safety control system further includes a secondary verification module 35, an encryption module 36, an alarm module 37 and / or a recording module 38; The secondary verification module 35 is at least used to perform security verification on the remote vehicle control request and the vehicle control data by using two-factor verification and / or biometric verification; The encryption module 36 is at least used to provide an encryption channel for information transmission between modules, which can reflect that the system has the function of protecting data security; The alarm module 37 is at least used to immediately notify the user when the remote vehicle control request is an illegal request. Here, it can be reflected that the system has the function of real-time feedback and alarm, and when a suspicious or malicious request is detected, the user can be notified immediately. The recording module 38 is at least used to record the generation information of the remote vehicle control request, and the generation information at least includes the request time, request location and operation type. Here, it can be reflected that the system has a detailed logging function, which can record all the system's requirements and responses to facilitate subsequent auditing and analysis.

[0069] Here, this system uses modular design and division of labor to make module responsibilities clear and easy to maintain and upgrade. The system can self-learn and adjust according to the ever-changing network environment and attack strategies, and can also analyze and process information from remote vehicle control commands and corresponding vehicle control data in real time, thereby ensuring the timeliness and accuracy of remote vehicle control requests in real time, and ensuring user convenience in vehicle control and safety.

[0070] A fourth aspect of the present invention provides an electronic device, comprising: At least one processor; and at least one memory in communication with the processor, wherein: the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the steps of the remote vehicle safety control method as described in any one of the above embodiments.

[0071] A fifth aspect of the present invention discloses a readable storage medium storing a computer program, wherein the computer program is executed by a processor to perform the steps of the remote vehicle safety control method as described in any one of the above embodiments.

[0072] Computer-readable storage media may include: any entity or device capable of carrying a computer program, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), and a software distribution medium, etc. A computer program includes a computer program code. The computer program code may be in source code form, object code form, an executable file, or some intermediate form, etc. A computer-readable storage medium may include: any entity or device capable of carrying a computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), and a software distribution medium, etc.

[0073] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0074] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processing module, or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0075] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A remote vehicle control safety control method, characterized in that: include: Obtain remote vehicle control requests and corresponding vehicle control data; Analyzing the remote vehicle control request and the vehicle control data through a deep learning model to identify user behavior patterns; The user behavior pattern is matched with a pre-stored behavior pattern, and the legitimacy of the remote vehicle control request is determined based on the matching result.

2. The remote vehicle control safety control method according to claim 1, characterized in that: The deep learning model is a trained neural network, and the process of acquiring the pre-stored behavior pattern includes: Get the historical requests for remote vehicle control and the corresponding historical request data; Extracting preset features from the remote vehicle control history requests and the corresponding history request data, wherein the preset features at least include user behavior habit data, and the user behavior habit data includes normal behavior habit data and abnormal behavior habit data; The preset features are used as input independent variables of the neural network, and the neural network is trained to obtain pre-stored behavior patterns, which include pre-stored normal behavior patterns corresponding to the normal behavior habit data and pre-stored abnormal behavior patterns corresponding to the abnormal behavior data.

3. The remote vehicle control safety control method according to claim 1 or 2, characterized in that: The vehicle control data at least includes user location data, user request time data and user device information when the remote vehicle control request occurs.

4. The remote vehicle control safety control method according to claim 2, characterized in that: The behavior habit data at least includes user request content, user operation frequency, user operation time and user operation sequence.

5. The remote vehicle control safety control method according to claim 2, characterized in that: The user behavior pattern includes at least a normal behavior pattern and an abnormal behavior pattern; The matching of the user behavior pattern with the pre-stored behavior pattern includes: If the user behavior pattern is a normal behavior pattern, the user behavior pattern successfully matches the pre-stored normal behavior pattern; If the user behavior pattern is an abnormal behavior pattern, the user behavior pattern successfully matches the pre-stored abnormal behavior pattern.

6. The remote vehicle control safety control method according to claim 1 or 2, characterized in that: After successfully matching with the pre-stored normal behavior pattern and obtaining the remote vehicle control request as a legitimate request, it also includes performing security verification on the remote vehicle control request and the vehicle control data by using two-factor verification and / or biometric verification.

7. A remote vehicle control safety control method, characterized in that: The remote vehicle control safety control method is implemented using a user device, a server and a vehicle-side device as carriers, and an application and / or a mini-program for remote vehicle control is installed on the user device; The application program and / or applet obtains a remote vehicle control request, and obtains corresponding vehicle control data based on the remote vehicle control request; The application program and / or applet sends the remote vehicle control request and corresponding vehicle control data to a server; The server analyzes the remote vehicle control request and the vehicle control data through a deep learning model to identify user behavior patterns; The server matches the user behavior pattern with a pre-stored behavior pattern, and determines the legitimacy of the remote vehicle control request based on the matching result; When the remote vehicle control request is a legitimate request, the server performs security verification on the remote vehicle control request and the vehicle control data through two-factor verification and / or biometrics, and if the verification is successful, the server sends the remote vehicle control request to the vehicle-end device; The vehicle-end device performs corresponding remote vehicle control operations based on the remote vehicle control request.

8. The remote vehicle control safety control method according to claim 7, characterized in that: Information is transmitted between the user device and the server, and between the server and the vehicle-end device through an encrypted channel.

9. A remote control vehicle safety control system, characterized in that: include: An acquisition module, at least used to acquire a remote vehicle control request and corresponding vehicle control data; an identification module, at least used to analyze the remote vehicle control request and the vehicle control data through a deep learning model to identify a user behavior pattern; A matching module, at least used to match the user behavior pattern with a pre-stored behavior pattern; The judgment module is at least used to judge the legitimacy of the remote vehicle control request based on the matching result.

10. The remote vehicle control safety control system according to claim 9, characterized in that: It also includes a secondary verification module, an encryption module, an alarm module and / or a recording module; The secondary verification module is at least used to perform security verification on the remote vehicle control request and the vehicle control data by using two-factor verification and / or biometric verification; The encryption module is at least used to provide an encryption channel for information transmission between modules; The warning module is at least used to immediately notify the user when the remote vehicle control request is an illegal request; The recording module is at least used to record the generation information of the remote vehicle control request, and the generation information at least includes the request time, the request location and the operation type.

11. An electronic device, characterized in that: include: at least one processor; And at least one memory communicatively connected to the processor, wherein: the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the steps of the remote vehicle safety control method as described in any one of claims 1-8.

12. A readable storage medium storing a computer program, characterized in that: The computer program is executed by a processor to perform the steps of the remote vehicle safety control method as described in any one of claims 1-8.