Method and device for controlling vehicle, vehicle and storage medium

By responding to remote start commands in the vehicle and disabling the voice recognition function, combining user identity and correlation judgment, the problem of the voice recognition system being attacked by criminals after the vehicle is remotely started is solved, and the safety of vehicle usage is improved.

CN119078728AActive Publication Date: 2024-12-06GREAT WALL MOTOR CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411360801.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-27
Publication Date
2024-12-06
Estimated Expiration
2044-09-27

AI Technical Summary

Technical Problem

In the prior art, the voice recognition system is automatically started after the vehicle is started remotely, resulting in criminals using the system to attack the vehicle, causing the safety risk of losing users' property, and it is urgent to improve the safety of vehicle use.

Method used

The vehicle controller in the vehicle responds to the remote start command, controls the target function matching the command to start, and puts the voice recognition function in a disabled state when starting, detects whether there is a user around the vehicle, and if there is, compares whether its behavior is For dangerous behavior, if so, the voice recognition function will be disabled; if the user's identity is a preset identity or correlation degree, the voice recognition function will be unlocked; otherwise, the face image will be collected through the on-board camera to determine the correlation degree and send it to the target terminal to determine the function status.

Benefits of technology

It effectively avoids criminals using voice recognition systems to attack vehicles, improves the safety of users using vehicles, ensures the safety of the property in the car, and meets the voice control needs of legal users.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119078728A_ABST
    Figure CN119078728A_ABST
Patent Text Reader

Abstract

The invention provides a vehicle control method and device, a vehicle and a storage medium, and relates to the field of vehicles. In the method, the vehicle responds to a remote starting instruction of the vehicle, and a target function of a target vehicle part matched with the remote starting instruction is controlled to be started. In this way, the requirement of a user for remotely starting the target function in the vehicle can be met. In a case where the target function is remotely activated, the speech recognition system may disable the speech recognition function. That is to say, the voice recognition system in the method can obtain the working state (forbidden state or available state) of the current voice recognition function in real time. And when the target function is remotely started, the voice recognition system controls the voice recognition function to be in a forbidden state, so that the problem that the vehicle is awakened by lawbreakers can be avoided, and the risk that the lawbreakers attack the vehicle by using the voice recognition system to cause loss of properties in the vehicle is further avoided. Therefore, the method can improve the safety of using the vehicle by the user.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of vehicles, and more specifically, to a method, a device, a vehicle and a storage medium for controlling a vehicle in the field of vehicles. Background Art

[0002] With the development of vehicle technology, vehicles provide users with a variety of convenient functions. The various convenient functions include the function of remotely starting the vehicle. For example, after the vehicle is remotely started, the positioning function in the vehicle is turned on to help locate the vehicle when the vehicle cannot be found in the parking lot.

[0003] In the related art, after the vehicle is remotely started, the voice recognition system in the vehicle will automatically start, which may cause criminals to use the voice recognition system to attack the vehicle, resulting in the security risk of the user losing property.

[0004] Therefore, there is an urgent need for a method for controlling a vehicle to improve the safety of users using the vehicle. Summary of the invention

[0005] The present application provides a method, device, vehicle and storage medium for controlling a vehicle, and the method can improve the safety of users using the vehicle.

[0006] In a first aspect, a method for controlling a vehicle is provided, the method comprising: in response to a remote start command to the vehicle, controlling the start of a target function of a target vehicle component that matches the remote start command; and when the target function is started, controlling a voice recognition function of the vehicle to be in a disabled state through a voice recognition system in the vehicle.

[0007] In the above technical solution, the vehicle responds to the remote start command of the vehicle and controls the start of the target function of the target vehicle component that matches the remote start command. In this way, the user's need to remotely start the target function in the vehicle can be met. In this way, when the target function is remotely started, the voice recognition system can disable the voice recognition function. In other words, in this method, the voice recognition system can know in real time the working state (disabled state or available state) that the current voice recognition function should be in. When the target function is remotely started, controlling the voice recognition function to be in a disabled state through the voice recognition system can avoid the problem of the vehicle being awakened by criminals, thereby avoiding the risk of criminals using the voice recognition system to attack the vehicle, resulting in the loss of property in the vehicle. Therefore, this method can improve the safety of users using the vehicle.

[0008] In combination with the first aspect, in some possible implementations, the voice recognition function of the vehicle is controlled to be in a disabled state through the voice recognition system in the vehicle, including: detecting whether there is a user around the vehicle; when there is a user around the vehicle, comparing the user's current behavior with multiple dangerous behaviors to determine whether the current behavior is a dangerous behavior; when the current behavior is a dangerous behavior, controlling the voice recognition function to be in a disabled state through the voice recognition system.

[0009] In the above technical solution, the vehicle controller also detects whether there are users around the vehicle. When there are users around the vehicle, the current behavior of the user is compared with multiple dangerous behaviors to determine whether the current behavior is a dangerous behavior. Furthermore, when the current behavior is a dangerous behavior, the voice recognition function is disabled through the voice recognition system. Among them, the dangerous behavior can be prying open the door or lock with professional tools, wandering around the vehicle, and marking the vehicle. This method can prevent unauthorized users (illegal elements) from controlling the vehicle through voice commands and protect the vehicle from potential theft or damage.

[0010] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the method also includes: when the current behavior is not a dangerous behavior, determining the identity of the user; when the identity is a preset identity, adjusting the working state of the voice recognition function from the disabled state to the available state through the voice recognition system, and the preset identity is used to provide maintenance services and / or maintenance services for the vehicle; when the identity is not the preset identity, collecting the user's facial image through the vehicle-mounted camera, and determining the association between the user and the vehicle based on the facial image, and the association is used to measure whether the user has ridden in the vehicle before; based on the association, determining the working state of the voice recognition function.

[0011] In the above technical solution, when the current behavior is not a dangerous behavior, the vehicle controller further determines the identity of the user. When it is clear that the identity is a preset identity, that is, when the user will not bring danger to the vehicle, the working state of the voice recognition function is adjusted from a disabled state to an available state through the voice recognition system. For example, in a scenario where a car washer is cleaning a vehicle, the car washer may need to control the wipers in the vehicle through voice commands to deeply remove dirt and impurities on the windshield and improve the car washing effect. Therefore, this method can meet the needs of users who really need to use the voice recognition function. When the identity is not a preset identity, the vehicle controller collects the user's facial image through the vehicle camera and determines whether the user has ridden in the vehicle before based on the facial image. In other words, it is indirectly inferred whether the user has an intersection with the owner or the owner's family, and then the working state of the voice recognition function is determined based on the inference result. The method can reasonably determine the working state of the voice recognition function by logically analyzing and inferring the legitimacy of the user (whether it will cause potential theft risks to the vehicle, etc.) layer by layer.

[0012] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, determining the identity of the user includes: capturing a full-body image of the user through a vehicle-mounted camera; extracting features of the clothes worn by the user from the full-body image to obtain style features and corresponding color features of the clothes; and when the style features and the color features match any preset clothes, determining that the identity is the preset identity, and the preset identity is used to wear the preset clothes.

[0013] In the above technical solution, the preset identity is used to provide maintenance services and / or care services for the vehicle. For example, the preset identity is a vehicle maintenance personnel and / or a car washer. Personnel with the preset identity usually need to wear professional work clothes when working to provide physical protection and adapt to the working environment. The style of the work clothes is usually a suit, such as a long-sleeved work suit and a reflective strip labor protection work clothes. The color of the work clothes is usually a dark series, such as navy blue and medium gray. Therefore, the method can accurately infer whether the user's identity is the preset identity based on the characteristics of the clothes worn by the user.

[0014] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, determining the association degree between the user and the vehicle based on the facial image includes: performing feature extraction on the facial image to obtain facial features; determining multiple similarities between the facial features and facial features of multiple users who have ridden in the vehicle; when the minimum similarity among the multiple similarities is greater than a first similarity threshold, determining that the association degree is a preset association degree, and the preset association degree is used to indicate that the user has ridden in the vehicle; when the maximum similarity among the multiple similarities is less than a second similarity threshold, determining that the association degree is not the preset association degree, and the second similarity threshold is less than the first similarity threshold.

[0015] In the above technical solution, the vehicle controller extracts features from the facial image of the user, obtains facial features, and determines multiple similarities between the facial features and the facial features of multiple users who have ridden in the vehicle. When the minimum similarity among the multiple similarities is greater than the first similarity threshold, it indicates that the similarity between the user and relatively dissimilar users among the multiple users is very large, and the similarity between the user and other users is greater. Therefore, the method can accurately determine that the user has ridden in the vehicle and has an intersection with the owner or the owner's family. On the contrary, when the maximum similarity among the multiple similarities is less than the second similarity threshold, it indicates that the similarity between the user and relatively similar users among the multiple users is very small, and the similarity between the user and other users is even smaller. Therefore, the method can accurately determine that the user has not ridden in the vehicle and has no intersection with the owner or the owner's family.

[0016] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the working status of the voice recognition function is determined based on the association degree, including: when the association degree is a preset association degree, adjusting the working status of the voice recognition function from the disabled state to the available state through the voice recognition system; when the association degree is not the preset association degree, sending the facial image to the target terminal, which is a terminal with functional authority to control the vehicle; and determining the working status of the voice recognition function based on the state control instruction of the voice recognition function sent by the target terminal.

[0017] In the above technical solution, when the correlation degree is the preset correlation degree, it indicates that the user has ridden in the vehicle before, and the user has an intersection with the owner or the owner's family. Therefore, the method believes that the user will not pose a potential theft risk to the vehicle, and the voice recognition system adjusts the working state of the voice recognition function from the disabled state to the available state. When the correlation degree is not the preset correlation degree, the vehicle controller cannot infer the legitimacy of the user. The vehicle controller sends the facial image of the user to the target terminal so that the user of the target terminal (such as the owner) makes a legitimacy judgment based on the facial image. Further, the working state of the voice recognition function is determined by the voice recognition system based on the state control instruction of the voice recognition function sent by the target terminal. The above scheme can avoid the situation where the vehicle controller cannot infer the legitimacy of the user based on the logic analysis technology. By judging the legitimacy of the user through the user of the target terminal, the owner can remotely monitor and manage the vehicle through the smart device, thereby improving the intelligence and interconnection of the vehicle.

[0018] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, when the current behavior is a dangerous behavior, after the voice recognition function is controlled to be in a disabled state through the voice recognition system, the method also includes: sending a warning message to the target terminal, the warning message is used to remind users around the vehicle that it may cause a safety hazard to the vehicle; and / or, controlling the voice output device in the vehicle to output an alarm signal; and / or, controlling the emergency flash lights in the vehicle to flash at a preset frequency.

[0019] In the above technical solution, when the current behavior is a dangerous behavior, the voice recognition function is controlled to be in a disabled state. However, after the voice recognition function is in a disabled state, the user may further take other means to attack the vehicle. The method sends an early warning message to the target terminal through the vehicle controller, which enables the user of the target terminal (such as the owner) to be informed that the users around the vehicle may cause safety hazards to the vehicle, so that the owner can take countermeasures in time. And / or, the method controls the voice output device in the vehicle to output an alarm signal or the emergency flash light to flash at a preset frequency through the vehicle controller. This can attract the attention of other people around the vehicle, remind other people that an abnormal situation has occurred, and can also serve to warn the user, thereby preventing theft and protecting property in the vehicle as much as possible.

[0020] In a second aspect, a system for controlling a vehicle is provided, the system comprising a vehicle controller, a battery management system and a voice recognition system:

[0021] In response to a remote start command to the vehicle, the vehicle controller controls the start of a target function of a target vehicle component matching the remote start command, and sends the remote start command to the battery management system;

[0022] The battery management system responds to the remote start command by sending mode reminder information to the voice recognition system through a communication link between the battery management system and the voice recognition system, wherein the mode reminder information is used to remind the vehicle that the vehicle is currently in the remote start mode;

[0023] In response to the mode reminder information, the voice recognition system controls the voice recognition function of the vehicle to be in a disabled state.

[0024] In a third aspect, a vehicle is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the vehicle executes the method in the first aspect or any possible implementation of the first aspect.

[0025] In a fourth aspect, a computer-readable storage medium is provided, which stores an executable program code. When the executable program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is a schematic diagram of a scenario of using a vehicle provided in an embodiment of the present application;

[0027] Figure 2 is a schematic flow chart of a method for controlling a vehicle provided in an embodiment of the present application;

[0028] Figure 3 is a flow chart of a method for controlling a vehicle provided in an embodiment of the present application;

[0029] Figure 4 is an interactive diagram of a method for controlling a vehicle provided in an embodiment of the present application;

[0030] Figure 5 is a structural schematic diagram of a system for controlling a vehicle provided in an embodiment of the present application;

[0031] Figure 6 is a structural schematic diagram of another system for controlling a vehicle provided in an embodiment of the present application;

[0032] Figure 7 is a schematic diagram of the structure of a device for controlling a vehicle provided in an embodiment of the present application;

[0033] Figure 8 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] The technical solution in the present application will be described clearly and in detail below in conjunction with the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0035] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0036] Figure 1 It is a schematic diagram of a scenario of using a vehicle provided in an embodiment of the present application.

[0037] For example, Figure 1 As shown, vehicle A is parked in a cold weather environment. If the owner who lives on the third floor of the apartment wants to drive out, the owner usually goes to vehicle A to start vehicle A. However, it is bad for the owner to start vehicle A in a cold weather environment.

[0038] In the related art, a remote start function is provided for the vehicle, which allows the owner to send a remote start command to the vehicle through the target terminal (the owner's mobile phone) to remotely start the vehicle, that is, the owner starts vehicle A on the 3rd floor of the apartment. However, in the related art, when the vehicle is remotely started, the power management system in the vehicle will power on the vehicle normally to meet the power consumption needs of the owner, such as remotely turning on the car air conditioner. Subsequently, the vehicle's on-board system will start along with the start of the power management system. When the on-board system is started, the voice recognition system in the on-board system is also turned on by default. After the voice recognition system is started, it will be in a state of waiting to be awakened. At this time, the distance between the owner and the vehicle is far. If criminals use the voice recognition system to open the door of the vehicle, this may cause the owner to lose property.

[0039] In order to solve the above problems, the present application provides a method for controlling a vehicle to improve the safety of the vehicle owner when the vehicle is remotely started. Figure 2 Steps in .

[0040] Figure 2 It is a schematic flowchart of a method for controlling a vehicle provided in an embodiment of the present application.

[0041] Exemplarily, a method for controlling a vehicle provided in an embodiment of the present application may be executed by a vehicle controller in the vehicle. In a method for controlling a vehicle provided in an embodiment of the present application, the vehicle includes a vehicle controller, a battery management system, and a voice recognition system.

[0042] For example, Figure 2 As shown, the method 200 includes:

[0043] Step 201 : In response to a remote start command for a vehicle, a vehicle controller controls a target function of a target vehicle component matching the remote start command to start.

[0044] It should be understood that the "remote start instruction" in the above step 201 is used to remotely start the target function of the target vehicle component in the vehicle. In some embodiments, the remote start instruction is used to remotely start the cooling function of the vehicle air conditioner.

[0045] In some embodiments, step 201 includes: in response to a remote start command to the vehicle, the on-board communication device in the vehicle forwards the remote start command to the vehicle controller; the vehicle controller forwards the remote start command to the battery management system; the battery management system powers on the vehicle in response to the remote start command; after the vehicle is powered on, the vehicle controller controls the start of a target function of a target vehicle component that matches the remote start command.

[0046] It should be understood that in the above solution, after the vehicle is powered on, the vehicle system in the vehicle is also powered on. In some embodiments, the vehicle system includes a head-up display (HUT) system. In other words, the HUT system will also be powered on. The "vehicle communication equipment" in the above solution can be regarded as T-BOX (Telematics-BOX), and the "vehicle controller" can be regarded as CEM (Central Electronic Module).

[0047] In some embodiments, in response to a remote start command to the vehicle, before the on-board communication device in the vehicle forwards the remote start command to the vehicle controller, the target object sends the remote start command to the vehicle remote server through the target terminal; the vehicle remote server forwards the remote start command to the on-board communication device in the vehicle.

[0048] It should be understood that the "vehicle remote server" in the above solution can be regarded as a telematics service provider (TSP). TSP is used to provide services including navigation, entertainment, information and security in the Internet of Vehicles industry chain, and interact with the vehicle through T-BOX to monitor the vehicle status and remotely control it.

[0049] In some embodiments, the target object is the vehicle owner.

[0050] Step 202: When the target function is activated, the vehicle controller controls the speech recognition function of the vehicle to be in a disabled state through the speech recognition system in the vehicle.

[0051] In some embodiments, step 202 includes: when the target function is activated, the vehicle controller sends the remote start command to the battery management system in the vehicle; the battery management system responds to the remote start command and sends a mode reminder message to the voice recognition system through a communication link with the voice recognition system, and the mode reminder message is used to remind that the vehicle is currently in remote start mode; the voice recognition system responds to the mode reminder message and controls the voice recognition function of the vehicle to be disabled.

[0052] It should be understood that the "communication link" in the above solution is constructed by the CarService service of the operating system of the vehicle system. In some embodiments, the operating system is an Android system.

[0053] In some embodiments, the method for constructing the communication link includes: determining the communication interface of the battery management system; constructing the external interface of the voice recognition system; and establishing a logical communication link between the communication interface and the external interface through multiple application program interfaces provided by the CarService service of the operating system.

[0054] In some embodiments, the multiple application program interfaces include a CarPropertyService service interface and a CarConnectionManager service interface, wherein the CarPropertyService service interface is used to read or write the status information of the battery in the battery management system, and the CarConnectionManager service interface is used to manage the connection status between the battery management system and the speech recognition system.

[0055] It should be understood that the "disabled state" in the above scheme means that the vehicle's voice recognition system is currently unavailable and the vehicle cannot be controlled by voice commands.

[0056] In some embodiments, the voice recognition system controls the voice recognition function of the vehicle to be in a disabled state, including: the voice recognition system controls the voice receiver therein to be in a disabled state; or the voice recognition system controls the voice receiver therein to convert the voice signal into a fault signal after receiving the voice signal.

[0057] It should be understood that the "voice receiver is in a disabled state" in the above solution means that the voice receiver does not receive voice signals, which can be achieved by prohibiting the operation of a driver for reading voice signals in the voice receiver. In some embodiments, the voice receiver is a microphone.

[0058] In one possible implementation, the vehicle controller controls the voice recognition function of the vehicle to be in a disabled state through the voice recognition system in the vehicle, including: the vehicle controller detects whether there is a user around the vehicle; when there is a user around the vehicle, the vehicle controller compares the user's current behavior with multiple dangerous behaviors to determine whether the current behavior is a dangerous behavior; when the current behavior is a dangerous behavior, the vehicle controller controls the voice recognition function to be in a disabled state through the voice recognition system.

[0059] It should be understood that the "dangerous behavior" in the above scheme is used to indicate behaviors that pose a potential risk of theft or damage to the vehicle. In some embodiments, the dangerous behavior includes prying open the door or breaking the lock with professional tools, wandering around the vehicle, sticking logo stickers or placing objects such as coins on the windshield of the vehicle, and making small holes in the tires.

[0060] In the above technical solution, the vehicle controller also detects whether there are users around the vehicle. When there are users around the vehicle, the current behavior of the user is compared with multiple dangerous behaviors to determine whether the current behavior is a dangerous behavior. Furthermore, when the current behavior is a dangerous behavior, the voice recognition function is disabled through the voice recognition system. Among them, the dangerous behavior can be prying open the door or lock with professional tools, wandering around the vehicle, and marking the vehicle. This method can prevent unauthorized users (illegal elements) from controlling the vehicle through voice commands and protect the vehicle from potential theft or damage.

[0061] In some embodiments, after the vehicle controller detects whether there is a user around the vehicle, the method 200 further includes: when there is no user around the vehicle, the vehicle controller controls the voice recognition function to be disabled through the voice recognition system.

[0062] In some embodiments, the vehicle controller detects whether there is a user around the vehicle, including: the vehicle controller sends a radar signal outward through a radar sensor in the vehicle; if no reflected signal of the radar signal is received within a preset time period, the vehicle controller determines that there is no user around the vehicle; if a reflected signal of the radar signal is received within a preset time period, the vehicle controller determines that there is an object around the vehicle; if there is an object around the vehicle, the vehicle controller determines whether the object is a user based on the change pattern of the reflected signal.

[0063] It should be understood that other objects except the user have a fixed structure. Therefore, the change pattern of the reflected signal reflected back after being blocked by other objects is relatively stable. However, the change pattern of the reflected signal reflected back after being blocked by the user is unstable.

[0064] In some embodiments, the vehicle controller determines whether the object is a user based on the change pattern of the reflected signal, including: when the change pattern of the reflected signal is a stable pattern, the vehicle controller determines that the object is not a user; when the change pattern of the reflected signal is not a stable pattern, the vehicle controller determines that the object is a user.

[0065] In some embodiments, the vehicle controller compares the current behavior of the user with multiple dangerous behaviors to determine whether the current behavior is a dangerous behavior, including: the vehicle controller compares the current behavior of the user with multiple dangerous behaviors to determine multiple similarities between the current behavior and the multiple dangerous behaviors; when there is a similarity among the multiple similarities that is greater than a third similarity threshold, the vehicle controller determines that the current behavior is a dangerous behavior; when the multiple similarities are all less than a fourth similarity threshold, the vehicle controller determines that the current behavior is not a dangerous behavior, and the fourth similarity threshold is less than the third similarity threshold.

[0066] In some embodiments, the third similarity threshold is 70%, and the fourth similarity threshold is 60%.

[0067] In one possible implementation, when the current behavior is a dangerous behavior, after the vehicle controller controls the voice recognition function to be disabled through the voice recognition system, the method 200 also includes: the vehicle controller sends an early warning message to the target terminal, and the early warning message is used to remind users around the vehicle that it may cause safety hazards to the vehicle; and / or, the vehicle controller controls the voice output device in the vehicle to output an alarm signal; and / or, the vehicle controller controls the emergency flash lights in the vehicle to flash at a preset frequency.

[0068] It should be understood that the "target terminal" in the above solution is a terminal with functional authority to control the vehicle. In some embodiments, the target terminal is a mobile terminal of the owner.

[0069] In the above technical solution, when the current behavior is a dangerous behavior, the voice recognition function is controlled to be in a disabled state. However, after the voice recognition function is in a disabled state, the user may further take other means to attack the vehicle. The method sends an early warning message to the target terminal through the vehicle controller, which enables the user of the target terminal (such as the owner) to be informed that the users around the vehicle may cause safety hazards to the vehicle, so that the owner can take countermeasures in time. And / or, the method controls the voice output device in the vehicle to output an alarm signal or the emergency flash light to flash at a preset frequency through the vehicle controller. This can attract the attention of other people around the vehicle, remind other people that an abnormal situation has occurred, and can also serve to warn the user, thereby preventing theft and protecting property in the vehicle as much as possible.

[0070] In some embodiments, the voice output device is a speaker in the vehicle.

[0071] In some embodiments, the emergency flasher is a hazard warning flasher (double flasher), and the preset frequency is 100 times / min.

[0072] In a possible implementation, the method 200 also includes: when the current behavior is not a dangerous behavior, the vehicle controller determines the identity of the user; when the identity is a preset identity, the vehicle controller adjusts the working state of the voice recognition function from the disabled state to the available state through the voice recognition system, and the preset identity is used to provide maintenance services and / or maintenance services for the vehicle; when the identity is not the preset identity, the vehicle controller captures the user's facial image through the on-board camera, and determines the association between the user and the vehicle based on the facial image, and the association is used to measure whether the user has ridden in the vehicle before; the vehicle controller determines the working state of the voice recognition function based on the association.

[0073] It should be understood that the "preset identity" in the above solution can be regarded as a vehicle maintenance personnel and / or a vehicle beautification personnel. The vehicle maintenance personnel is mainly responsible for necessary maintenance and repair of the vehicle, including repair of the engine, chassis and electrical systems therein. The vehicle beautification personnel is mainly responsible for cleaning, waxing, polishing, coating and other beauty projects of the vehicle's exterior, as well as cleaning and maintenance of the interior.

[0074] It should also be understood that the "working state of the voice recognition function" in the above scheme includes an available state and a disabled state.

[0075] In the above technical solution, when the current behavior is not a dangerous behavior, the vehicle controller further determines the identity of the user. When it is clear that the identity is a preset identity, that is, when the user will not bring danger to the vehicle, the working state of the voice recognition function is adjusted from a disabled state to an available state through the voice recognition system. For example, in a scenario where a car washer is cleaning a vehicle, the car washer may need to control the wipers in the vehicle through voice commands to deeply remove dirt and impurities on the windshield and improve the car washing effect. Therefore, this method can meet the needs of users who really need to use the voice recognition function. When the identity is not a preset identity, the vehicle controller collects the user's facial image through the vehicle camera and determines whether the user has ridden in the vehicle before based on the facial image. In other words, it is indirectly inferred whether the user has an intersection with the owner or the owner's family, and then the working state of the voice recognition function is determined based on the inference result. The method can reasonably determine the working state of the voice recognition function by logically analyzing and inferring the legitimacy of the user (whether it will cause potential theft risks to the vehicle, etc.) layer by layer.

[0076] In one possible implementation, the vehicle controller determines the identity of the user, including: the vehicle controller captures a full-body image of the user through a vehicle-mounted camera; the vehicle controller extracts features of clothing worn by the user from the full-body image to obtain style features and corresponding color features of the clothing; when the style features and the color features match any preset clothing, the vehicle controller determines that the identity is the preset identity, and the preset identity is used to wear the preset clothing.

[0077] It should be understood that the "preset clothing" in the above solution refers to clothing that matches the current season and is worn by a person with the preset identity.

[0078] In the above technical solution, the preset identity is used to provide maintenance services and / or care services for the vehicle. For example, the preset identity is a vehicle maintenance personnel and / or a car washer. Personnel with the preset identity usually need to wear professional work clothes when working to provide physical protection and adapt to the working environment. The style of the work clothes is usually a suit, such as a long-sleeved work suit and a reflective strip labor protection work clothes. The color of the work clothes is usually a dark series, such as navy blue and medium gray. Therefore, the method can accurately infer whether the user's identity is the preset identity based on the characteristics of the clothes worn by the user.

[0079] In some embodiments, a method for determining whether the style feature and the color feature match any preset clothing includes: a vehicle controller determines the similarity between the style feature and style features of multiple preset clothing to obtain multiple style similarities; the vehicle controller determines whether there is at least one candidate style similarity greater than a fifth similarity threshold among the multiple style similarities; when there is at least one candidate style similarity among the multiple style similarities, the vehicle controller determines the similarity between the color feature and the color feature corresponding to the preset clothing of the at least one candidate style similarity to obtain at least one candidate color similarity; the vehicle controller determines the maximum similarity among the at least one candidate color similarity to obtain a target color similarity; when the target color similarity is greater than or equal to a sixth similarity threshold, the vehicle controller determines that the style feature and the color feature match any preset clothing.

[0080] In some embodiments, when the target color similarity is less than the sixth similarity threshold, the vehicle controller determines that the style feature and the color feature do not match multiple preset clothes.

[0081] In one possible implementation, the vehicle controller determines the association between the user and the vehicle based on the facial image, including: the vehicle controller extracts features of the facial image to obtain facial features; the vehicle controller determines multiple similarities between the facial features and facial features of multiple users who have ridden in the vehicle; when the minimum similarity among the multiple similarities is greater than a first similarity threshold, the vehicle controller determines that the association is a preset association, and the preset association is used to indicate that the user has ridden in the vehicle; when the maximum similarity among the multiple similarities is less than a second similarity threshold, the vehicle controller determines that the association is not the preset association, and the second similarity threshold is less than the first similarity threshold.

[0082] It should be understood that in the above scheme, for private vehicles, the multiple users usually ride in the vehicle more than once, and in the process of the multiple users interacting with the vehicle, the vehicle inevitably collects facial images of these users; for passenger vehicles, in order to ensure the driving safety of passengers (any of the multiple users), the vehicle will collect facial images of the passengers after the passengers are seated.

[0083] In the above technical solution, the vehicle controller extracts features from the facial image of the user, obtains facial features, and determines multiple similarities between the facial features and the facial features of multiple users who have ridden in the vehicle. When the minimum similarity among the multiple similarities is greater than the first similarity threshold, it indicates that the similarity between the user and relatively dissimilar users among the multiple users is very large, and the similarity between the user and other users is greater. Therefore, the method can accurately determine that the user has ridden in the vehicle and has an intersection with the owner or the owner's family. On the contrary, when the maximum similarity among the multiple similarities is less than the second similarity threshold, it indicates that the similarity between the user and relatively similar users among the multiple users is very small, and the similarity between the user and other users is even smaller. Therefore, the method can accurately determine that the user has not ridden in the vehicle and has no intersection with the owner or the owner's family.

[0084] In some embodiments, the first similarity threshold is 90%, and the second similarity threshold is 50%.

[0085] In one possible implementation, the vehicle controller determines the working state of the voice recognition function based on the correlation degree, including: when the correlation degree is a preset correlation degree, the vehicle controller adjusts the working state of the voice recognition function from the disabled state to the available state through the voice recognition system; when the correlation degree is not the preset correlation degree, the vehicle controller sends the facial image to the target terminal, which is a terminal with functional authority to control the vehicle; the vehicle controller determines the working state of the voice recognition function based on the state control instruction for the voice recognition function sent by the target terminal.

[0086] It should be understood that the "state control instruction" in the above solution is used to control the working state of the voice recognition function, and the state control instruction is used to instruct to adjust the working state of the voice recognition function to a disabled state or an available state.

[0087] In the above technical solution, when the correlation degree is the preset correlation degree, it indicates that the user has ridden in the vehicle before, and the user has an intersection with the owner or the owner's family. Therefore, the method believes that the user will not pose a potential theft risk to the vehicle, and the voice recognition system adjusts the working state of the voice recognition function from the disabled state to the available state. When the correlation degree is not the preset correlation degree, the vehicle controller cannot infer the legitimacy of the user. The vehicle controller sends the facial image of the user to the target terminal so that the user of the target terminal (such as the owner) makes a legitimacy judgment based on the facial image. Further, the working state of the voice recognition function is determined by the voice recognition system based on the state control instruction of the voice recognition function sent by the target terminal. The above scheme can avoid the situation where the vehicle controller cannot infer the legitimacy of the user based on the logic analysis technology. By judging the legitimacy of the user through the user of the target terminal, the owner can remotely monitor and manage the vehicle through the smart device, thereby improving the intelligence and interconnection of the vehicle.

[0088] In some embodiments, the vehicle controller determines the working state of the voice recognition function based on the state control instruction for the voice recognition function sent by the target terminal, including: when the state control instruction is used to indicate that the working state of the voice recognition function is adjusted to a disabled state, the vehicle controller determines that the voice recognition function is in a disabled state; when the state control instruction is used to indicate that the working state of the voice recognition function is adjusted to an available state, the vehicle controller determines that the working state of the voice recognition function is adjusted from the disabled state to the available state.

[0089] Figure 3 It is a flowchart of a method for controlling a vehicle provided in an embodiment of the present application.

[0090] For example, Figure 3As shown, the vehicle controller detects whether there is a user around the vehicle. If there is no user around the vehicle, the vehicle controller controls the voice recognition function to be in a disabled state through the voice recognition system. If there is a user around the vehicle, the vehicle controller compares the current behavior of the user with multiple dangerous behaviors to determine whether the current behavior is a dangerous behavior; if the current behavior is a dangerous behavior, the vehicle controller controls the voice recognition function to be in a disabled state through the voice recognition system. If the current behavior is not a dangerous behavior, the vehicle controller determines the identity of the user; if the identity is a preset identity, the vehicle controller adjusts the working state of the voice recognition function from the disabled state to the available state through the voice recognition system. If the identity is not the preset identity, the vehicle controller collects the facial image of the user through the vehicle camera, and determines the association between the user and the vehicle based on the facial image. If the association is a preset association, the vehicle controller adjusts the working state of the voice recognition function from the disabled state to the available state through the voice recognition system. In the case where the correlation degree is not the preset correlation degree, the vehicle controller sends the facial image to the target terminal, and in the case where the state control instruction sent by the target terminal is used to instruct the working state of the voice recognition function to be adjusted to a disabled state, the vehicle controller controls the voice recognition function to be in a disabled state through the voice recognition system. In the case where the state control instruction sent by the target terminal is used to instruct the working state of the voice recognition function to be adjusted to an enabled state, the vehicle controller adjusts the working state of the voice recognition function from the disabled state to the enabled state through the voice recognition system.

[0091] In some embodiments, after step 202, the vehicle controller detects a vehicle unlocking signal after a preset time and sends a normal start instruction to the battery management system; the battery management system responds to the normal start instruction, and the battery management system sends mode adjustment information to the voice recognition system through a communication link with the voice recognition system, and the mode adjustment information is used to remind the vehicle that it should currently exit the remote start mode; the voice recognition system controls the working state of the vehicle's voice recognition function from a disabled state to an enabled state in response to the mode adjustment information.

[0092] It should be understood that the "working state of the vehicle's voice recognition function is adjusted from a disabled state to an enabled state" in the above solution can be understood as a state in which the voice recognition system enters a voice waiting state to recognize a key wake-up word instruction. In other words, the voice recognition system can recognize the user's wake-up word and then control the state of the vehicle.

[0093] In some embodiments, the vehicle unlock signal includes at least one of a vehicle unlock signal when a vehicle door is opened, a vehicle unlock signal when a user is in the main driver's seat, a vehicle unlock signal when the gear is changed from the parking gear to the driving gear, and a vehicle unlock signal when the accelerator pedal is pressed.

[0094] In some embodiments, after the voice recognition system controls the working state of the voice recognition function of the vehicle from a disabled state to an enabled state in response to the mode adjustment information, the method 200 also includes: the vehicle controller receives a first voice signal of a user around the vehicle through a microphone in the voice recognition system; the vehicle controller preprocesses the first voice signal to obtain a preprocessed voice signal; the vehicle controller sends the preprocessed voice signal to a wake-up word detection model, and the wake-up word detection model detects whether the preprocessed voice signal contains a preset wake-up word; when the preprocessed voice signal contains a preset wake-up word, the voice recognition system is activated; the microphone in the voice recognition system receives a second voice signal of the user and converts the second voice signal into a digital signal; the voice recognition system extracts features from the digital signal to obtain voice features; based on the voice features, the voice recognition system converts the second voice signal into a text signal and recognizes the voice control instructions therein; the voice recognition system converts the voice control instructions into operation instructions related to the vehicle; the vehicle controller controls the corresponding vehicle components to perform corresponding actions based on the operation instructions.

[0095] In some embodiments, the preprocessing includes preprocessing operations such as noise reduction and gain adjustment.

[0096] In some embodiments, the preset wake-up word includes "Hey Sirii".

[0097] In some embodiments, the speech recognition system extracts Mel-frequency cepstral coefficients from the digital signal.

[0098] It should be understood that the Mel-frequency cepstral coefficients in the above solution refer to the perceptual characteristics of human ears to speech.

[0099] In some embodiments, the speech recognition system converts the second speech signal into a text signal through a semantic recognition model and recognizes the voice control instructions therein.

[0100] In some embodiments, the semantic recognition model is a Transformer model.

[0101] Figure 4 It is an interactive diagram of a method for controlling a vehicle provided in an embodiment of the present application.

[0102] For example, Figure 4As shown, the target object sends a remote start instruction to a vehicle remote server (TSP) through a target terminal; the TSP forwards the remote start instruction to the vehicle-mounted communication device (T-BOX) in the vehicle; the T-BOX forwards the remote start instruction to the vehicle controller (CEM) in the vehicle; the CEM forwards the remote start instruction to the battery management system in the vehicle. The battery management system responds to the remote start instruction and powers on the vehicle; after the vehicle is powered on, the CEM controls the target function of the target vehicle component that matches the remote start instruction to start. After the vehicle is powered on, the head-up display system (HUT) in the vehicle is turned on, the voice recognition system in the vehicle is turned on, and the battery management system responds to the remote start instruction and sends a mode reminder message to the HUT through a communication link with the voice recognition system, and the mode reminder message is used to remind that the vehicle is currently in a remote start mode. The HUT forwards the mode reminder message to the voice recognition system. In response to the mode reminder message, the voice recognition system controls the voice recognition function of the vehicle to be disabled.

[0103] It should be understood that the HUT system is a vehicle system, and the HUT system includes a voice recognition system. Therefore, when the battery management system sends mode reminder information to the voice recognition system through the communication link between the battery management system and the voice recognition system, the mode reminder information will first pass through the HUT system, and then be forwarded by the HUT system to the voice recognition system.

[0104] Exemplarily, after a preset time, the vehicle controller detects a vehicle unlocking signal of an open door and sends a normal start command to the battery management system; the battery management system responds to the normal start command and sends mode adjustment information to the HUT through a communication link with the voice recognition system, and the mode adjustment information is used to remind the vehicle to exit the remote start mode. The HUT forwards the mode adjustment information to the voice recognition system. The voice recognition system controls the working state of the vehicle's voice recognition function from a disabled state to an enabled state in response to the mode adjustment information.

[0105] Figure 5 It is a structural schematic diagram of a system for controlling a vehicle provided in an embodiment of the present application.

[0106] For example, Figure 5 As shown, the system 500 includes a vehicle controller 501, a battery management system 502 and a speech recognition system 503:

[0107] In response to the remote start command to the vehicle, the vehicle controller 501 controls the start of a target function of a target vehicle component matching the remote start command, and sends the remote start command to the battery management system 502;

[0108] In response to the remote start instruction, the battery management system 502 sends a mode reminder message to the voice recognition system 503 through a communication link between the voice recognition system 503 , where the mode reminder message is used to remind that the vehicle is currently in the remote start mode;

[0109] In response to the mode reminder information, the voice recognition system 503 controls the voice recognition function of the vehicle to be in a disabled state.

[0110] The beneficial effect of the above system solution is that the vehicle controller responds to the remote start command of the vehicle and controls the start of the target function of the target vehicle component matching the remote start command. In this way, the user's need to remotely start the target function in the vehicle can be met. In addition, the vehicle controller sends the remote start command to the battery management system, so that the battery management system knows that the vehicle is currently in remote start mode, and then sends the remote start mode to the voice recognition system through the communication link between the battery management system and the voice recognition system. In this way, after the voice recognition system receives that the vehicle is currently in remote start mode, the voice recognition function can be disabled. In other words, the method uses the message communication method between the power management system and the voice recognition system to transmit to the voice recognition system whether the current vehicle is in remote start mode or in normal start mode through the power management system, so that the voice recognition system can know in real time the working state (disabled state or available state) that the current voice recognition function should be in. In the remote start mode, the voice recognition function is in a disabled state to avoid the problem of the vehicle being awakened by criminals, thereby avoiding the risk of criminals using the voice recognition system to attack the vehicle, resulting in the loss of property in the vehicle. Therefore, the method can improve the safety of users using the vehicle.

[0111] Figure 6 It is a schematic diagram of the structure of another system for controlling a vehicle provided in an embodiment of the present application.

[0112] For example, Figure 6 As shown, the system 600 is based on the system 500, and a vehicle-mounted communication device 601 in the vehicle is added;

[0113] Optionally, in response to a remote start command to the vehicle, the on-board communication device 601 in the vehicle forwards the remote start command to the vehicle controller 501; the vehicle controller 501 forwards the remote start command to the battery management system 502; the battery management system 502 powers on the vehicle in response to the remote start command; after the vehicle is powered on, the vehicle controller 501 controls the start of a target function of a target vehicle component that matches the remote start command.

[0114] Figure 7 It is a structural schematic diagram of a device for controlling a vehicle provided in an embodiment of the present application.

[0115] For example, Figure 7 As shown, the device 700 includes:

[0116] A first control module 701 is used to control the activation of a target function of a target vehicle component matching the remote activation command in response to a remote activation command for the vehicle;

[0117] The second control module 702 is used to control the voice recognition function of the vehicle to be in a disabled state through the voice recognition system in the vehicle when the target function is activated.

[0118] Optionally, the device 700 also includes: a detection module, used to detect whether there is a user around the vehicle; the device 700 also includes: a determination module, used to compare the user's current behavior with multiple dangerous behaviors when there is a user around the vehicle, and determine whether the current behavior is a dangerous behavior; the first control module 701 is specifically used to control the voice recognition function to be disabled through the voice recognition system when the current behavior is a dangerous behavior.

[0119] Optionally, the determination module is also used to determine the identity of the user when the current behavior is not a dangerous behavior; the device 700 also includes: an adjustment module, used to adjust the working state of the voice recognition function from the disabled state to the available state through the voice recognition system when the identity is a preset identity, and the preset identity is used to provide maintenance services and / or maintenance services for the vehicle; the determination module is also used to: when the identity is not the preset identity, collect the facial image of the user through the vehicle-mounted camera, and determine the association between the user and the vehicle based on the facial image, and the association is used to measure whether the user has ridden in the vehicle before; based on the association, determine the working state of the voice recognition function.

[0120] Optionally, the device 700 also includes: a collection module, used to collect a full-body image of the user through a vehicle-mounted camera; the determination module, specifically used to: extract features of the clothes worn by the user from the full-body image to obtain style features and corresponding color features of the clothes; when the style features and the color features match any preset clothes, determine that the identity is the preset identity, and the preset identity is used to wear the preset clothes.

[0121] Optionally, the determination module is further specifically used to: perform feature extraction on the facial image to obtain facial features; determine multiple similarities between the facial features and facial features of multiple users who have ridden in the vehicle; when the minimum similarity among the multiple similarities is greater than a first similarity threshold, determine that the correlation is a preset correlation, and the preset correlation is used to indicate that the user has ridden in the vehicle; when the maximum similarity among the multiple similarities is less than a second similarity threshold, determine that the correlation is not the preset correlation, and the second similarity threshold is less than the first similarity threshold.

[0122] Optionally, the adjustment module is specifically used to: when the association degree is a preset association degree, adjust the working state of the voice recognition function from the disabled state to the available state through the voice recognition system; the device 700 also includes: a sending module, specifically used to: when the association degree is not the preset association degree, send the facial image to the target terminal, the target terminal is a terminal with functional authority to control the vehicle; the determination module is also specifically used to determine the working state of the voice recognition function based on the state control instruction of the voice recognition function sent by the target terminal.

[0123] Optionally, when the current behavior is a dangerous behavior, after the voice recognition function is controlled to be in a disabled state by the voice recognition system, the sending module is also used to: send a warning message to the target terminal, the warning message is used to remind users around the vehicle that it may cause safety hazards to the vehicle; and / or, the first control module 701 is also used to control the voice output device in the vehicle to output an alarm signal; and / or, the first control module 701 is also used to control the emergency flash lights in the vehicle to flash at a preset frequency.

[0124] Figure 8 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application.

[0125] For example, Figure 8 As shown, the vehicle 800 includes: a memory 801 and a processor 802, wherein the memory 801 stores an executable program code 803, and the processor 802 is used to call and execute the executable program code 803 to perform a method for controlling a vehicle.

[0126] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor, wherein the memory stores an executable program code, and the processor is used to call and execute the executable program code to execute a method for controlling a vehicle provided in an embodiment of the present application.

[0127] In this embodiment, the functional modules of the device can be divided according to the above method example. For example, each functional module can be corresponded, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0128] In the case of dividing each functional module according to each function, the device may also include a first control module, a second control module, a sending module, an adjustment module, a detection module, a collection module, a determination module, and an output module, etc. It should be noted that all relevant contents involved in the above method embodiments can be referred to the functional description of the corresponding functional modules, which will not be repeated here.

[0129] It should be understood that the device provided in this embodiment is used to execute the above-mentioned method of controlling a vehicle, and thus can achieve the same effect as the above-mentioned implementation method.

[0130] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to a vehicle, the processing module may be used to control and manage the actions of the vehicle. The storage module may be used to support the vehicle in executing related executable program codes, etc.

[0131] The processing module may be a processor or a controller, which may implement or execute various exemplary logic blocks, modules and circuits shown in conjunction with the disclosure of the present application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.

[0132] In addition, the device provided in the embodiments of the present application may specifically be a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a method for controlling a vehicle provided in the above embodiments.

[0133] This embodiment also provides a computer-readable storage medium, in which an executable program code is stored. When the executable program code is run on a computer, the computer executes the above-mentioned related method steps to implement a method for controlling a vehicle provided in the above embodiment.

[0134] This embodiment also provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement a method for controlling a vehicle provided in the above embodiment.

[0135] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.

[0136] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0137] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0138] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for controlling a vehicle, characterized in that: The method comprises: In response to a remote start command for a vehicle, controlling a target function of a target vehicle component matching the remote start command to start; In a case where the target function is activated, a voice recognition function of the vehicle is controlled to be in a disabled state through a voice recognition system in the vehicle.

2. The method according to claim 1, characterized in that The step of controlling the voice recognition function of the vehicle to be in a disabled state by using a voice recognition system in the vehicle includes: Detecting whether there is a user around the vehicle; In the case where there is a user around the vehicle, comparing the current behavior of the user with a plurality of dangerous behaviors to determine whether the current behavior is a dangerous behavior; In a case where the current behavior is a dangerous behavior, the voice recognition function is controlled to be in a disabled state through the voice recognition system.

3. The method according to claim 2, characterized in that The method further comprises: In a case where the current behavior is not a dangerous behavior, determining the identity of the user; In the case where the identity is a preset identity, adjusting the working state of the voice recognition function from the disabled state to the enabled state through the voice recognition system, and the preset identity is used to provide maintenance service and / or servicing service for the vehicle; In the case where the identity is not the preset identity, a facial image of the user is collected by a vehicle-mounted camera, and a correlation between the user and the vehicle is determined based on the facial image, where the correlation is used to measure whether the user has ridden in the vehicle before; Based on the degree of association, a working state of the speech recognition function is determined.

4. The method according to claim 3, characterized in that The determining the identity of the user comprises: Collecting a full-body image of the user through a vehicle-mounted camera; Extracting features of the clothes worn by the user from the full-body image to obtain style features and corresponding color features of the clothes; In the case where the style feature and the color feature match any preset clothing, the identity is determined to be the preset identity, and the preset identity is used to wear the preset clothing.

5. The method according to claim 3, characterized in that: The determining the degree of association between the user and the vehicle based on the facial image includes: Extracting features from the facial image to obtain facial features; determining a plurality of similarities between the facial feature and facial features of a plurality of users who have ridden in the vehicle; When the minimum similarity among the multiple similarities is greater than a first similarity threshold, determining the association degree to be a preset association degree, wherein the preset association degree is used to indicate that the user has ridden in the vehicle; In the case that the maximum similarity among the multiple similarities is smaller than a second similarity threshold, it is determined that the association degree is not the preset association degree, and the second similarity threshold is smaller than the first similarity threshold.

6. The method according to claim 3, characterized in that: The determining the working state of the speech recognition function based on the association degree includes: When the correlation degree is a preset correlation degree, adjusting the working state of the speech recognition function from the disabled state to the enabled state; In a case where the degree of association is not the preset degree of association, sending the facial image to a target terminal, the target terminal being a terminal having a functional authority to control the vehicle; Based on the state control instruction of the speech recognition function sent by the target terminal, the working state of the speech recognition function is determined.

7. The method according to claim 2, characterized in that In the case where the current behavior is a dangerous behavior, after controlling the voice recognition function to be in a disabled state through the voice recognition system, the method further includes: Sending a warning message to a target terminal, the warning message is used to remind users around the vehicle that a potential safety hazard may be caused to the vehicle; and / or, controlling a voice output device in the vehicle to output an alarm signal; and / or, The emergency flasher in the vehicle is controlled to flash at a preset frequency.

8. A system for controlling a vehicle, characterized in that: The system includes a vehicle controller, a battery management system and a voice recognition system: In response to a remote start command for the vehicle, the vehicle controller controls a target function of a target vehicle component matching the remote start command to start, and sends the remote start command to the battery management system; The battery management system responds to the remote start instruction by sending mode reminder information to the voice recognition system through a communication link between the battery management system and the voice recognition system, wherein the mode reminder information is used to remind the vehicle that the vehicle is currently in the remote start mode; In response to the mode reminder information, the voice recognition system controls the voice recognition function of the vehicle to be in a disabled state.

9. A vehicle, characterized in that: The vehicle comprises: A memory for storing executable program codes; A processor, configured to call and run the executable program code from the memory, so that the vehicle executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an executable program code, and when the executable program code is executed, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • System and method for on-demand passive entry disable

    CN107054294A

  • Voice operated device for vehicle

    JP2004217101A

  • Information provision system, terminal device, information provision server, information provision method, and program

    JP2015215433A

  • Smartkey System having a function to recognition sounds of users

    KR1020170100722A

  • Vehicle control system

    US20120078443A1