WO2024051592A1

WO2024051592A1 - Vehicle control method and control apparatus

Info

Publication number: WO2024051592A1
Application number: PCT/CN2023/116496
Authority: WO
Inventors: 彭超; 李凌飞; 沈波; 肖龙帅; 任亮亮; 张跃; 石子娟; 吴雪晨
Original assignee: 华为技术有限公司
Priority date: 2022-09-05
Filing date: 2023-09-01
Publication date: 2024-03-14
Also published as: CN117711394A

Abstract

The present application relates to the technical field of intelligent terminals, and provides a vehicle control method and control apparatus. The control method comprises: obtaining a voice instruction for controlling a vehicle; determining whether a sound source in respect of the voice instruction is positioned inside the vehicle; and when the sound source is positioned inside the vehicle, controlling the vehicle to execute an operation corresponding to the voice instruction. According to the vehicle control method provided in embodiments of the present application, after the vehicle receives the voice instruction, whether a person giving the voice instruction is located inside the vehicle can be determined, so as to determine whether to execute a control operation corresponding to the voice instruction, such that control over the vehicle is more intelligent, and the use safety of the vehicle can be improved. According to the present application, a user in the vehicle can be helped to effectively avoid control and interference of strangers outside the vehicle on the vehicle, misoperations for the vehicle cannot be caused, and the safety of persons in the vehicle, especially in a rest scene, is further ensured.

Description

Vehicle control method and control device

This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on September 5, 2022, with application number 202211098498.0 and application name "Vehicle Control Method and Control Device", the entire content of which is incorporated into this application by reference. middle.

Technical field

The present application relates to the field of intelligent terminal technology, and in particular, to a vehicle control method and control device.

Background technique

With the continuous improvement of speech recognition accuracy and semantic understanding capabilities, as well as the popularization of automobile networking, it has become more and more common to control vehicles through voice commands, which has brought great convenience to users and improved the user experience.

Currently, when a vehicle is voice controlled, the vehicle's voice collection system collects the voice commands issued by the user, conducts semantic recognition to obtain the voice control commands, and then sends the voice control commands to the control unit to control the vehicle accordingly. Actions.

In the above-mentioned vehicle voice control process, as long as the voice command is collected by the voice collection system, it will perform semantic recognition and execute the recognized control command. For example, if the driver and passengers of the vehicle park the vehicle on the roadside and take a rest in the vehicle, and a person outside the vehicle gives the voice command "open the door", the vehicle will directly control the door opening based on the voice command, but In fact, the drivers and passengers in the car did not want to open the door at this time. Situations like this will cause great safety risks to the personal and property safety of the drivers and passengers in the vehicle.

Contents of the invention

This application provides a vehicle control method and control device, which can control the vehicle more intelligently and improve the safety of the vehicle.

In a first aspect, a vehicle control method is provided, including: obtaining a voice instruction to control the vehicle; determining whether the sound source position of the voice instruction is located inside the vehicle; when the sound source position is located in the vehicle When inside, the vehicle is controlled to perform operations corresponding to the voice instructions.

According to the vehicle control method provided by the embodiment of the present application, after receiving a voice instruction for controlling the vehicle, instead of directly executing the instruction, it first determines whether the sound source position of the voice instruction is located inside the vehicle. The control operation corresponding to the voice command is only executed when the sound source of the voice command is located inside the vehicle. This makes the control of the vehicle more intelligent, improves the safety of the vehicle, and ensures the personal and property safety of passengers in the vehicle. This application can help users in the car effectively avoid control and interference of the vehicle by strangers outside the car, without causing misoperation of the vehicle, further ensuring the safety of people in the car, especially in resting scenes.

Optionally, the voice command can perform status control, media control, air conditioning control, seat control, etc. on the vehicle.

In some cases, the voice command can be opening/closing windows (including sunroofs), opening/closing doors (locking/unlocking doors), opening/closing the trunk, ambient light adjustment, vehicle locking, vehicle ignition/stop, and vehicle speed adjustment. , rearview mirror adjustment and other vehicle status control instructions. In some cases, the voice command can also be media control commands such as opening navigation, adjusting the central control screen, playing music, tuning the radio, answering/making calls, etc. In some cases, the voice command can also be air conditioning control commands such as raising the temperature, lowering the temperature, starting internal circulation, purifying the air in the car, etc. In some cases, the voice command can also be a seat control command such as turning on seat heating, raising/lowering the seat height, moving the seat forward/backward, adjusting the seat back angle, etc.

Optionally, the voice command can also be a wake-up command used to wake up the voice assistant of the vehicle. The wake-up command can be a default command set by the manufacturer. For example, the voice command can be a "little voice command" used to wake up the intelligent voice assistant Xiaoyi. "Yi Xiaoyi" can also be a wake-up command customized by the user according to personal preferences. In some cases, the vehicle's voice assistant can also be in wake-up-free mode, that is, the voice assistant remains awake at all times to ensure that the vehicle can promptly obtain instructions for controlling the vehicle's status such as "open the door", which is convenient for voice control of the vehicle. .

Optionally, various data related to the vehicle can be obtained through sensors such as in-car cameras, exterior cameras, radars, laser rangefinders, or seat pressure sensors, and based on one or more of the various data. Determine whether the sound source location of the voice command is located inside the vehicle. This application does not specifically limit the specific implementation method of determining whether the sound source position of the voice command is located inside the vehicle.

Optionally, the acquired data can be combined with a pre-built-in algorithm to determine whether the sound source is located inside the vehicle.

For example, the above data can be input into a neural network model, which analyzes the data and determines whether the sound source location is inside the vehicle. Among them, the neural network model is obtained by model training with historical data (training data) and a deep learning algorithm. The neural network model can be, for example, a convolutional neural network (CNN) model. The deep learning algorithm can, for example, be Machine learning algorithm or meta learning algorithm.

It is worth mentioning that to determine whether the sound source position of the voice command is located inside the vehicle, in some cases, it is not necessary to determine the specific location of the sound source position, but only needs to determine whether it is located inside the vehicle. The advantage of this is that it can reduce the amount of data required, without setting too many additional sensors, or reduce the working frequency of the sensors; in addition, it can also simplify the calculation process, save the computing power of the processor, and reduce the burden on the processor. performance requirements.

Optionally, it can be determined whether the sound source position of the voice instruction is located inside the vehicle based on one or more of the following data: the audio characteristic data of the voice instruction collected by the microphone, the pickup of the voice instruction collected by the microphone ( Sound pickup) intensity data, in-car image data collected by the in-car camera, in-car sound data collected by the microphone, in-car seat pressure data collected by the seat sensor, in-car vibration data collected by the vibration sensor, touch The touch data of the in-car touch screen collected by the sensor, the vehicle speed data collected by the vehicle speed sensor, the window opening and closing data detected by the glass position detection sensor, the exterior image data collected by the exterior camera, and the radar or laser range finder collection Obstacle data outside the vehicle, etc., but is not limited to this. With the further development of intelligent vehicles and sensor technology, the content and types of the above data can become more.

In a possible implementation, determining whether the sound source position of the voice instruction is located inside the vehicle includes: determining whether the sound source position is located inside the vehicle according to audio characteristics of the voice instruction.

For example, certain characteristic parameters of the audio characteristics of the voice command can be compared with a preset parameter threshold, and whether the sound source position is located inside the vehicle is determined based on the comparison result.

For another example, the acquired audio characteristics can be combined with a pre-built-in algorithm to determine whether the sound source is located inside the vehicle.

Optionally, the audio feature data of the voice instruction can be input into a neural network model, and the neural network model analyzes the feature data and determines whether the sound source position is located inside the vehicle. The neural network model is obtained by model training using historical data (training data) and a deep learning algorithm. The neural network model may be, for example, a CNN model, and the deep learning algorithm may be, for example, a machine learning algorithm or a meta-learning algorithm.

Optionally, the audio characteristics here may include any characteristic parameters such as spectral structure, energy, amplitude, frequency, period, etc., but are not limited to this.

In a possible implementation, the audio features include spectral structure.

After the sound passes through obstacles such as car window glass, the energy in the high-frequency band in the spectrum structure is absorbed, and the high-frequency part will be significantly attenuated. However, the high-frequency spectrum structure of the normal sound emitted in the car that has not passed through obstacles is Some parts will be preserved relatively completely, so under the same circumstances, there will be differences in the spectrum structure between the voice commands issued outside the car and the voice commands issued inside the car. This part of the difference can be used to determine whether the sound source position is located inside the vehicle. The advantage of using the spectrum structure to determine whether the sound source position is located inside the vehicle is that the confirmation method is simple, efficient and easy to implement without resorting to other data, which can reduce the frequency of use of other sensors in the vehicle.

In one possible implementation, determining whether the sound source position of the voice instruction is located inside the vehicle includes: determining the sound source of the voice instruction based on the characteristics of a high-frequency part of the spectrum structure of the voice instruction. Whether the position is located inside the vehicle; when the integrity of the high-frequency part meets the preset conditions, it is determined that the sound source position is located inside the vehicle.

Because after the sound passes through obstacles such as car window glass, the energy in the high-frequency band in the spectrum structure is absorbed, and the high-frequency part will be significantly attenuated. However, the normal sound emitted in the car that has not passed through obstacles has a high-frequency band in the spectrum structure. The high-frequency part will be preserved relatively completely. Therefore, under the same circumstances, the voice commands issued outside the car and the voice commands issued inside the car will have a more obvious difference in the integrity of the high-frequency part. It can be determined by the characteristics of the high-frequency part. Determine whether the sound source position of the voice command is located inside the vehicle, When the integrity of the high-frequency part meets the preset conditions, it is determined that the sound source position is located inside the vehicle. The advantage of determining whether the sound source position is located inside the vehicle through the characteristics of the high-frequency part of the spectrum structure is that the confirmation method is simple, efficient and easy to implement without resorting to other data, which can reduce the frequency of use of other sensors in the vehicle.

For example, the high-frequency part of the spectrum structure can be input into a pre-trained neural network model (such as a CNN model). The neural network model analyzes and calculates the spectrum structure, and finally outputs a judgment of whether the sound source position is located inside the vehicle. result.

In a possible implementation, determining whether the sound source position of the voice instruction is located inside the vehicle includes: determining whether the sound source position is based on the pickup intensity of the voice instruction by a microphone of the vehicle. Located inside said vehicle.

The closer the microphone is to the sound source of the voice command, the stronger the pickup (sound pickup) intensity of the voice command will be, that is, the volume of the picked-up voice command will be greater, so the pickup intensity of the microphone can reflect the voice command. The distance from the sound source location can be used to determine whether the sound source location is inside the vehicle based on the pickup intensity. For example, the specific location of the sound source location, or the specific orientation of the sound source location, can be determined based on the pickup intensity of the voice command by the microphone, and then it can be further determined whether the sound source location is located inside the vehicle.

Alternatively, the vehicle may be equipped with only one microphone, and whether the sound source position is located inside the vehicle may be determined based on the pickup intensity of the voice command by the only microphone.

Optionally, a vehicle may usually be equipped with multiple microphones, and the sound source location can be determined based on the pickup strength of each of the multiple microphones for voice commands, combined with a preset algorithm (such as a trained neural network model). Located inside the vehicle. The plurality of microphones can be installed in the car. For example, they can be centrally installed near the center console of the vehicle in the form of a microphone array, or they can be distributed at different seats in the car. The plurality of microphones may also include at least one external microphone for picking up voices outside the vehicle, so that the user can perform voice interaction with the vehicle outside the vehicle and obtain a better vehicle experience.

Optionally, the vehicle is equipped with multiple in-vehicle microphones. In this case, based on the pickup strength of each of the multiple in-vehicle microphones for voice commands, combined with a preset algorithm, it can be directly determined whether the sound source position is located inside the vehicle. Alternatively, it is also possible to first determine the specific location of the sound source (i.e., specific coordinates), the direction of the sound source, the distance to each microphone, and other information, and then indirectly determine whether the sound source is located inside the vehicle through the above information.

In a possible implementation, determining whether the sound source position is located inside the vehicle based on the pickup intensity of the voice instruction by a microphone of the vehicle includes: based on the pickup intensity of the voice instruction by multiple microphones. The pickup intensity determines the orientation of the sound source location; based on the orientation, it is determined whether the sound source location is located inside the vehicle.

In some cases, such as an insufficient number of microphones or an unsatisfactory relative position between the sound source and the microphone, it may not be possible to accurately determine the specific location of the sound source based on the pickup intensity, or greater processor computing power is required. In this case, you can The orientation of the sound source is determined based on the pickup intensity of the voice command by a pair of microphones, and with the help of a preset algorithm or logic, it is determined whether the sound source is located inside the vehicle through the orientation.

Optionally, after determining the orientation of the sound source location, it is further determined that there are no seats inside the vehicle at this orientation. At this time, it can be determined that the sound source location is located outside the vehicle. For example, if the microphone is installed on the center console of the car and the direction points to the front of the vehicle, there are no seats in the car space at this direction and cannot accommodate passengers. Therefore, it can be determined that the sound source is located outside the vehicle. .

Optionally, after determining the orientation of the sound source location, it is further determined whether the car window at this orientation is closed. For example, if the car window has a strong sound insulation effect and the current car window is completely closed, it can be determined that the sound source location is inside the vehicle.

Optionally, after determining the orientation of the sound source location, further determine the distribution of people inside and outside the vehicle at this orientation, and determine whether the sound source location is located inside the vehicle based on the distribution of people. For example, if there are no people inside the vehicle at this orientation, it can be determined that the sound source is located outside the vehicle; or, if there are no people outside the vehicle at this orientation, it can be determined that the sound source is located inside the vehicle; Alternatively, if there are people both inside and outside the vehicle at this location, you can use other data from the sensor to determine whether the sound source is located inside the vehicle.

In a possible implementation, it is determined whether the sound source position is located inside the vehicle through at least one of the following information: the audio characteristics of the voice instruction; the response of the vehicle's microphone to the voice instruction. Picking intensity; the distribution of people inside the vehicle; the distribution of people within the preset range outside the vehicle; the driving speed of the vehicle; the opening and closing of the windows of the vehicle.

In some implementations, multiple factors can be combined to determine whether the sound source location of the voice command is located in the car. In some implementations, the spectral structure of the aforementioned voice command can be combined with the pickup intensity to determine whether the sound source position of the voice command is located in the car. For example, through the spectrum structure of the voice command, it is determined that the preservation integrity of the high-frequency part is poor, combined with the weak pickup intensity of the voice command, it is jointly determined that the sound source position of the voice command is outside the car; for another example, this can be Two different factors set priorities. When the results determined by the two factors are different, the result determined by the factor with higher priority shall prevail. Other methods that combine multiple factors can also refer to the examples here.

In some cases, whether the sound source is located inside the vehicle can be determined by the distribution of people inside the vehicle. At this time, relevant data can be obtained through detection devices such as in-car cameras, seat pressure sensors, touch sensors, vibration sensors, magnetometers, and infrared sensors, and based on this data, it can be determined whether there are passengers in the car, their orientation or specific location , the specific seats of the passengers and other personnel distribution information, and finally determine whether the sound source position is located inside the vehicle based on the personnel distribution information.

Optionally, if the personnel distribution information indicates that there are currently no drivers or passengers in the vehicle, it may be determined that the sound source location is located outside the vehicle rather than inside.

Optionally, if the personnel distribution information indicates that there are drivers and passengers in the current vehicle, other information (such as any one or more of the aforementioned types of data) can be used to jointly determine whether the sound source position is located inside the vehicle.

For example, at this time, the determination can be further made in combination with the audio feature data of the voice command collected by the microphone or the pickup (sound pickup) intensity data of the voice command collected by the microphone, which will be further described below.

In some cases, whether the sound source is located inside the vehicle can be determined by the distribution of people outside the vehicle. At this time, relevant data can be obtained through detection devices such as cameras, radars, and laser rangefinders outside the vehicle, and based on this data, it can be determined whether there are people within the preset range near the outside of the vehicle, as well as personnel distribution information such as their orientation or specific location. Finally, it is determined whether the sound source is located inside the vehicle based on the personnel distribution information.

This preset range can be determined based on the sound pickup capability of the microphone equipped in the vehicle. The stronger the sound pickup capability, it means that voice commands issued by people at a greater distance may also be picked up, so the preset range should also be larger. The manufacturer can reasonably set the preset range based on the specific configuration of the microphone before the vehicle leaves the factory.

Optionally, if the person distribution information indicates that there are no people within the current preset range outside the vehicle, it can be determined that the sound source position is located inside the vehicle.

Optionally, if the personnel distribution information indicates that there are people within the current preset range outside the vehicle, then other information (such as any one or more of the aforementioned types of data) can be used to jointly determine whether the sound source location is located Vehicle interior.

In some cases, the driving speed of the vehicle can be used to determine whether the sound source is located inside the vehicle. When the vehicle's driving speed reaches a certain value, for example, the driving speed is greater than or equal to 80 kilometers per hour (km/h), even if the window is wide open, it may not be able to pick up the voice outside the car. Therefore, if the microphone picks up the When the voice command for controlling the vehicle is received, it can be determined that the sound source position of the voice command is located inside the vehicle.

Optionally, when the driving speed of the vehicle is greater than or equal to the preset vehicle speed threshold, it may be determined that the sound source position of the voice command is located inside the vehicle. The vehicle speed threshold can be 60 to 100km/h, for example, 70km/h or 80km/h. The manufacturer can reasonably set the vehicle speed threshold based on the microphone's sound pickup ability before the vehicle leaves the factory.

Optionally, when the vehicle's driving speed is less than the vehicle speed threshold, other information (such as any one or more of the aforementioned types of data) can be used to jointly determine whether the sound source position is located inside the vehicle.

For example, when the vehicle's driving speed is less than the speed threshold and greater than the preset lower threshold (for example, 25km/h), if all the windows of the vehicle are closed, the relatively fast vehicle speed plus the glass Due to the blocking effect, the microphone in the car may not be able to pick up the voice command outside the car, so it can be determined that the sound source position of the voice command is located inside the vehicle.

In some cases, it can be determined whether the sound source is located inside the vehicle through the opening and closing of the vehicle's windows. Relevant data can be obtained through the window position detection sensor to determine the current status (ie, opening and closing status) of each window of the vehicle, for example, it can be fully open, half open, or fully closed. Car window glass has a certain sound insulation effect. When the car window is closed, the microphone in the car may not be able to accurately pick up the voice commands outside the car. However, when the car window is opened, the microphone in the car can pick up the voice commands outside the car. Voice command, so it can determine whether the sound source is located inside the vehicle based on the opening and closing of the vehicle's windows.

Optionally, when all the windows of the vehicle are completely closed, it means that the microphone cannot receive the voice outside the vehicle at this time, and it can be determined that the sound source position of the voice command is located inside the vehicle. The vehicle can be, for example, some high-end cars, and its sound insulation effect is particularly outstanding.

In a possible implementation, the voice instruction includes a wake-up instruction, and controlling the vehicle to perform operations corresponding to the voice instruction includes: waking up a voice assistant of the vehicle.

In a possible implementation, controlling the vehicle to perform operations corresponding to the voice instructions includes: performing semantic recognition on the voice instructions to obtain control instructions; and performing operations on the vehicle according to the control instructions. control.

That is to say, when it is determined that the sound source is located inside the vehicle, the voice command will be semantically parsed to generate the corresponding control command. When it is determined that the sound source is not located inside the vehicle (that is, outside the vehicle), the voice command may not be processed. The instructions are semantically parsed, which helps save the computing power of the processor.

In a possible implementation, the method further includes: controlling the vehicle not to execute the voice instruction when the sound source position is located outside the vehicle.

When it is determined that the sound source position is not located inside the vehicle, that is, it is determined that the sound source position is located outside the vehicle, it means that the voice command may have been spoken by someone outside the vehicle (such as a stranger, a passerby, or a criminal) and accidentally picked up by the microphone. At this time, the voice command may not be semantically recognized or executed, that is, the voice command may not be responded to, thereby improving the safety of vehicle control and ensuring the personal and property safety of passengers in the vehicle.

In a possible implementation, the method further includes: when the sound source position is located outside the vehicle, if it is determined that the preset trigger condition is met, controlling the vehicle to execute a command corresponding to the voice command. operate.

That is to say, if it is determined that the sound source is located outside the vehicle, further determination can be made, and based on the determination result, it is decided whether to execute the operation corresponding to the control instruction, instead of directly not executing the voice instruction as in the previous embodiment. Specifically, if the trigger condition is met, the vehicle is controlled to perform an operation corresponding to the control instruction; if the trigger condition is not met, the voice instruction is not executed. Through the above settings, on the premise of improving the safety of vehicle voice control, it can also increase the control flexibility, which is beneficial to improving the user experience.

Optionally, the triggering conditions can be pre-set by the manufacturer, or can be set by the user. For example, the user can set the conditions based on the scenarios in which the user may voice control the vehicle outside the vehicle.

Optionally, the triggering condition may be that the electronic key of the vehicle is located near the vehicle, the vehicle owner is determined to be located near the vehicle through the positioning function of a mobile terminal such as a mobile phone, a special time period (such as commuting and get off work hours), or the vehicle enters a specific mode (for example, Camping mode), etc., this application does not limit this.

Take the trigger condition that the vehicle's electronic key is located near the vehicle as an example. If the vehicle can establish a Bluetooth connection with the electronic key, it can be determined that the electronic key is near the vehicle, that is, it is determined that the owner of the vehicle may also be located near the vehicle. At this time, the trigger condition is satisfied, the vehicle can be controlled to perform operations corresponding to the control instruction.

In a possible implementation, the method further includes: when the sound source is located outside the vehicle, sending inquiry information as to whether to execute the voice command.

In the embodiment of the present application, when it is determined that the sound source position of the voice command is located outside the vehicle, an inquiry message is sent as to whether to execute the voice command, instead of directly not executing the voice command as in the previous embodiment. The control method provided by the embodiments of this application can not only improve the safety of vehicle voice control, but also increase the control flexibility, which is beneficial to improving the user experience.

Optionally, the query information here may be sound information, image information, text information, etc.

For example, the inquiry information here can be a voice inquiry information whether to execute the voice command issued through the vehicle's speaker device, or it can be displayed on the central control screen, instrument screen or heads up display (HUD) device inside the vehicle. image query information, this application does not limit this.

In a second aspect, a vehicle control device is provided, including: an acquisition unit, used to acquire a voice instruction for controlling the vehicle; a determination unit, used to determine whether the sound source position of the voice instruction is located inside the vehicle; A control unit, when the sound source is located inside the vehicle, is used to control the vehicle to perform operations corresponding to the voice instructions.

In a possible implementation, the determining unit is specifically configured to determine whether the sound source position is located inside the vehicle according to the audio characteristics of the voice instruction.

In a possible implementation, the audio features include spectral structure.

In a possible implementation, the determining unit is specifically configured to: determine whether the sound source position of the voice command is located inside the vehicle according to the characteristics of the high-frequency part in the spectrum structure of the voice command; when the high-frequency part When the integrity of the frequency part meets the preset conditions, it is determined that the sound source position is located inside the vehicle.

In a possible implementation, the determining unit is specifically configured to determine whether the sound source position is located inside the vehicle according to the pickup intensity of the voice command by the vehicle's microphone.

In a possible implementation, the determining unit is specifically configured to: pick up the voice instruction based on multiple microphones. The intensity determines the orientation of the sound source location; based on the orientation, it is determined whether the sound source location is located inside or outside the vehicle.

In a possible implementation, the determining unit determines whether the sound source position is located inside the vehicle through at least one of the following information: audio characteristics of the voice instruction; The pickup intensity of the voice command; the distribution of people inside the vehicle; the distribution of people within the preset range outside the vehicle;

The driving speed of the vehicle; the opening and closing conditions of the windows of the vehicle.

In a possible implementation, the voice command includes a wake-up command, and the control unit is specifically configured to wake up the voice assistant of the vehicle.

In a possible implementation, the control unit is specifically configured to: perform semantic analysis on the voice instructions to obtain control instructions; and control the vehicle according to the control instructions.

In a possible implementation, when the sound source is located outside the vehicle, the control unit is further configured to control the vehicle not to execute the voice instruction.

In a possible implementation, when the sound source is located outside the vehicle, if it is determined that the preset trigger condition is met, the control unit is further configured to: control the vehicle to execute the voice command. Corresponding operations.

In a possible implementation, the control device further includes: a sending unit configured to send query information on whether to execute the voice command when the sound source is located outside the vehicle.

In a third aspect, a vehicle control device is provided, including at least one processor, the at least one processor being coupled to a memory, reading and executing instructions in the memory, to implement any one of the foregoing first aspects. possible implementation methods.

Optionally, the control device further includes the memory.

In a fourth aspect, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium. When the computer program is run on a computer, any one of the possible implementations of the first aspect can be realized. method provided.

In a fifth aspect, a chip system is provided, including a processor for calling and running a computer program from a memory, so that the computer installed with the chip system executes any of the possible implementation methods provided in the first aspect. method.

In a sixth aspect, a computer program product is provided. The computer program product includes: computer program code. When the computer program code is run on a computer, it causes the computer to execute any implementation method in the first aspect. provided method.

It should be noted that the above computer program code can be stored in whole or in part on the first storage medium, where the first storage medium can be packaged together with the processor, or can be packaged separately from the processor. This application does not specifically limit this. .

A seventh aspect provides a vehicle, including the vehicle control device provided by any of the possible implementations of the second aspect and the third aspect.

It can be understood that the vehicle control device provided in the second and third aspects, the computer-readable storage medium provided in the fourth aspect, the chip system provided in the fifth aspect, the computer program product provided in the sixth aspect, the computer program product provided in the seventh aspect, The vehicles are all used to execute the control method provided in the first aspect. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods provided above, and will not be described again here.

Description of the drawings

Figure 1 is a schematic diagram of an application scenario provided by an embodiment of the present application.

Figure 2 is a logic block diagram of the current voice control of the vehicle.

Figure 3 is a functional block diagram of a vehicle provided by an embodiment of the present application.

FIG. 4 is a schematic flowchart of an example of a vehicle control method provided by an embodiment of the present application.

FIG. 5 is a schematic diagram of an application scenario of the control method shown in FIG. 4 .

Figure 6 is a schematic diagram of the propagation process of control instructions.

FIG. 7 is a schematic flowchart of another example of a vehicle control method provided by an embodiment of the present application.

FIG. 8 is a schematic diagram of an application scenario of the control method shown in FIG. 7 .

FIG. 9 is a schematic flowchart of another example of a vehicle control method provided by an embodiment of the present application.

FIG. 10 is a schematic diagram of an application scenario of the control method shown in FIG. 9 .

FIG. 11 is a schematic block diagram of a vehicle control device provided by an embodiment of the present application.

FIG. 12 is a schematic structural diagram of a vehicle control device provided by an embodiment of the present application.

Detailed ways

The technical solutions in this application will be described below with reference to the accompanying drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of the embodiments.

In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures and technologies are provided to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

The term "comprising" as used herein indicates the presence of described features, integers, steps, operations, elements and/or components but does not exclude the presence of one or more other features, integers, steps, operations, elements, components and/or collections thereof existence or addition. The terms “including,” “includes,” “having,” and variations thereof all mean “including but not limited to,” unless otherwise specifically emphasized.

Hereinafter, the terms “first” and “second” are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of indicated technical features. Therefore, features defined as "first" and "second" may explicitly or implicitly include one or more of these features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

The term "and/or" in this article is just an association relationship that describes related objects, indicating that three relationships can exist. For example, A and/or B can mean: A exists alone, A and B exist simultaneously, and they exist alone. B these three situations. In addition, the character "/" in this article generally indicates that the related objects are an "or" relationship.

Figure 1 is a schematic diagram of an application scenario provided by an embodiment of the present application. As shown in Figure 1, the application scenario includes a vehicle 11 with a driver 12 inside. If the vehicle 11 turns on the voice control function, the drivers and passengers, including the driver 12, can control the vehicle through voice commands. For example, the driver 12 can set the navigation or change the frequency modulation through voice commands while driving, without having to look at the center console for manual operations. On the one hand, this can free up the driver's hands. On the other hand, the driver does not need to look at the center console to perform manual operations, which will not distract his attention during driving and will help improve driving safety.

Figure 2 is a logic block diagram of the current voice control of the vehicle. As shown in Figure 2, in the current vehicle voice control process, the vehicle's voice collection system 21 collects the voice instructions issued by the user, performs semantic recognition to obtain the voice control instructions, and then sends the voice control instructions to the control unit 22. The control unit 22 will form a control instruction that can be recognized by the control object 23 based on the voice control instruction, and control the control object 23 according to the control instruction to control the vehicle to perform corresponding actions.

However, the inventor of the present application discovered during practice that in some cases, the voice command picked up by the vehicle's voice collection system cannot actually be directly executed. If the voice command is directly executed, it may cause the vehicle to malfunction. operation, thus causing hidden dangers to the personal and property safety of the drivers and passengers in the vehicle.

For example, as shown in Figure 1, if the driver and passengers of the vehicle 11 park the vehicle 11 on the roadside and take a rest in the car, and at this time, if the person 13 outside the vehicle shouts a voice command of "open the door", the vehicle 11 will Directly control the door opening according to the voice command. This provides an opportunity for people 13 outside the vehicle to take advantage of, causing hidden dangers to the personal and property safety of the drivers and passengers in the vehicle.

For another example, as shown in Figure 1, if the vehicle 11 is driving slowly on a crowded urban road, and a person 13 outside the vehicle shouts the voice command "open the door", the vehicle 11 will directly control the vehicle according to the voice command. The car door opens. At this time, because the door has been opened (unlocked), children sitting in the back seat may be at risk of falling from the car.

To sum up, with the current vehicle voice control method, the voice commands obtained by the vehicle are not differentiated. Whether the voice commands come from inside or outside the vehicle, they will be executed, which may cause misoperation of the vehicle. Causing hidden dangers to the personal and property safety of the drivers and passengers in the vehicle.

Based on the above problems, embodiments of the present application provide a vehicle control method. After the vehicle receives a voice command, it can determine whether the person who issued the voice command is located inside the vehicle, thereby deciding whether to perform the control operation corresponding to the voice command. , thus making the control of the vehicle more intelligent and improving the safety of the vehicle. This application can help users in the car effectively avoid control and interference of the vehicle by strangers outside the car, without causing misoperation of the vehicle, further ensuring the safety of people in the car, especially in resting scenes.

The vehicle control method provided by the embodiment of the present application is applied in the vehicle, or in other devices with the function of controlling the vehicle (such as cloud servers, mobile phone terminals, etc.). The vehicle may specifically be an internal combustion locomotive, an intelligent electric vehicle or a hybrid vehicle, or the vehicle may also be a vehicle of other power types, which is not limited in the embodiments of the present application.

The vehicle may be an autonomous vehicle, which may be a vehicle with partial autonomous driving capabilities, or may be Therefore, a vehicle with all autonomous driving functions, that is to say, the vehicle’s autonomous driving level can refer to the classification standards of the Society of Automotive Engineers (SAE), which is divided into no automation (L0), driving support ( L1), partial automation (L2), conditional automation (L3), high automation (L4) or complete automation (L5). A vehicle or other device (such as a cloud server, a mobile phone terminal, etc.) can implement the vehicle control method provided by the embodiments of the present application through its components (including hardware and software), and determine whether the sound source position of the voice command used to control the vehicle is located Inside the vehicle, that is, it determines whether the person who spoke the voice command is located inside or outside the vehicle, and decides whether to perform the control operation corresponding to the voice command based on the judgment result, thereby making the control of the vehicle more intelligent and improving the safety of the vehicle. safety, and ensure the personal and property safety of passengers in the vehicle.

As a specific example, the vehicle may be the vehicle 100 in FIG. 3 , which is a functional block diagram of the vehicle 100 provided by the embodiment of the present application.

As shown in FIG. 3 , vehicle 100 may include various subsystems such as travel system 102 , sensor system 104 , control system 106 , one or more peripheral devices 108 as well as power supply 110 , computer system 112 and user interface 116 . Alternatively, vehicle 100 may include more or fewer subsystems, and each subsystem may include multiple elements. Additionally, each subsystem and element of vehicle 100 may be interconnected via wires or wirelessly.

The travel system 102 may include components that provide powered motion for the vehicle 100 . In one embodiment, the propulsion system 102 may include an engine 118 , an energy source 119 , a transmission 120 and wheels 121 . The engine 118 may be an internal combustion engine, an electric motor, an air compression engine, or a combination of other types of engines, such as a hybrid engine composed of a gasoline engine and an electric motor, or a hybrid engine composed of an internal combustion engine and an air compression engine. Engine 118 converts energy source 119 into mechanical energy.

Examples of energy sources 119 include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electricity. Energy source 119 may also provide energy to other systems of vehicle 100 .

Transmission 120 may transmit mechanical power from engine 118 to wheels 121 . Transmission 120 may include a gearbox, differential, and driveshaft.

In one embodiment, the transmission device 120 may also include other components, such as a clutch. Among other things, the drive shaft may include one or more axles that may be coupled to one or more wheels 121 .

Sensor system 104 may include a number of sensors that sense information about the environment surrounding vehicle 100 .

For example, the sensor system 104 may include a positioning system 122 (the positioning system may be a GPS system, a Beidou system, or other positioning systems), an inertial measurement unit (IMU) 124, a radar 126, a laser rangefinder 128, and Camera 130.

Positioning system 122 may be used to estimate the geographic location of vehicle 100 . The IMU 124 is used to sense changes in position and orientation of the vehicle 100 based on inertial acceleration. In one embodiment, IMU 124 may be a combination of accelerometer and gyroscope. Radar 126 may utilize radio signals to sense objects within the environment surrounding vehicle 100 . In some embodiments, in addition to sensing the object, the radar 126 may also be used to sense the speed and/or heading of the object, such as millimeter wave radar or lidar. Laser rangefinder 128 may utilize laser light to sense objects in the environment in which vehicle 100 is located. In some embodiments, laser rangefinder 128 may include one or more laser sources, laser scanners, and one or more detectors, among other system components. Camera 130 may be used to capture multiple images of the surrounding environment of vehicle 100 . The camera 130 may be a static camera or a video camera, or may be a visual perception camera. The surrounding environment can be detected through radar 126, laser range finder 128 or camera 130 to determine whether there are people around the vehicle.

The sensor system 104 also includes sensors of internal systems of the vehicle 100 , including, for example, sensors of an advanced driving assistance system (ADAS). In the embodiment of the present application, the sensors of the internal system of the vehicle 100 include sensors such as seat pressure sensor 1041, in-vehicle camera 1042, touch sensor 1043, vibration sensor 1044, and vehicle speed sensor. The seat pressure sensor 1041 can be used to monitor the pressure data on each seat in the car, the in-car camera 1042 can be used to capture multiple images of the occupants in the car and multiple images of the in-car environment, and the touch sensor 1043 can be used to monitor the center of the car. Touch data on the display screen of the control unit, vibration sensor 1044 is used to capture vibration data occurring in the vehicle. The processor can determine whether there is a passenger in the vehicle and the specific location of the passenger based on at least one of the pressure data, image, touch data, vibration data, etc. The vehicle speed sensor is used to monitor the vehicle's speed data to determine whether the vehicle is stationary.

In addition, sensors for vehicle internal systems can also include air quality sensors, fuel gauges, oil temperature gauges, etc. One or more sensor data collected by these sensors can be used to detect objects and their corresponding characteristics (position, shape, temperature, velocity). degree, etc.), this detection and identification is key to achieving safe operation of the vehicle 100 and ensuring the safety of the vehicle occupants.

Control system 106 controls the operation of vehicle 100 and its components. Control system 106 may include various elements, including steering system 132 , throttle 134 , braking unit 136 , computer vision system 140 , line control system 142 , and obstacle avoidance system 144 .

Steering system 132 is operable to adjust the forward direction of vehicle 100 . For example, in one embodiment it may be a steering wheel system.

Throttle 134 is used to control the operating speed of engine 118 and thereby the speed of vehicle 100 .

The braking unit 136 is used to control the deceleration of the vehicle 100 . Braking unit 136 may use friction to slow wheel 121 . In other embodiments, braking unit 136 may convert kinetic energy of wheel 121 into electrical current. The braking unit 136 may also take other forms to slow down the rotation speed of the wheels 121 to control the speed of the vehicle 100 .

In the embodiment of the present application, the computer vision system 140 can process and analyze the images captured by the camera 130 and the in-vehicle camera 1042 to identify the distribution of people in the surrounding environment outside the vehicle 100 and the distribution of people inside the vehicle. . Among them, the distribution of people outside the vehicle includes information such as whether there are people within the preset range outside the vehicle, the location or orientation of people outside the vehicle, and other information. The distribution of people in the car includes information such as whether there are people in the car, the location or orientation of the people in the car, and which seat(s) the people in the car are sitting in. The computer vision system 140 can use at least one of a human body recognition algorithm, a structure from motion (SFM) algorithm, video tracking, and other computer vision technologies to complete environment mapping, tracking objects, estimating the speed of objects, and determining Operations such as the current conditions inside and outside the car.

The route control system 142 is used to determine the driving route of the vehicle 100 . In some embodiments, route control system 142 may combine sensor data from sensor system 104 and data from one or more predetermined maps to determine a route for vehicle 100 .

Obstacle avoidance system 144 is used to identify, evaluate, and avoid or otherwise negotiate potential obstacles in the environment of vehicle 100 .

Of course, in one example, control system 106 may additionally or alternatively include components in addition to those shown and described. Alternatively, some of the components shown above may be reduced.

Vehicle 100 interacts with external sensors, other vehicles, other computer systems, or users through peripheral devices 108 . Peripheral devices 108 may include a wireless communication system 146 , an onboard computer 148 , a microphone 150 and a speaker 152 .

In some embodiments, peripheral device 108 provides a means for a user of vehicle 100 to interact with user interface 116 . For example, onboard computer 148 may provide information to a user of vehicle 100 . The user interface 116 may also operate the onboard computer 148 to receive user input. The onboard computer 148 can be operated via a touch screen. In other cases, peripheral device 108 may provide a means for vehicle 100 to communicate with other devices located within the vehicle. For example, microphone 150 may receive audio (eg, voice commands or other audio input) from a user of vehicle 100 . Similarly, speakers 152 may output audio to a user of vehicle 100 .

The microphone 150 can pick up sounds inside the car and can also pick up sounds outside the car. When the car windows are not closed or the sounds outside the car are loud, the microphone 150 can also accurately pick up various sounds outside the car, including voice commands for controlling the vehicle.

The microphone 150 may be composed of multiple microphone units. The multiple microphone units may be disposed near the center console to form a microphone array, or may be distributed next to each seat in the car. At least one of them may also be disposed on On the outer wall of the car (outside the car) to pick up the sound outside the car.

For example, when the user issues a voice instruction for voice control of the vehicle, whether the sound source position is located inside the vehicle can be determined by the pickup intensity of the voice instruction by the microphone 150 . Specifically, the orientation or position of the sound source position can be determined based on the pickup intensity of the voice instructions by multiple microphone units, and whether the sound source position is located inside the vehicle can be determined based on the orientation or position.

Wireless communication system 146 may wirelessly communicate with one or more devices directly or via a communication network. For example, wireless communication system 146 may use 3G cellular communications, such as CDMA, EVDO, GSM/GPRS, or 4G cellular communications, such as LTE. Or 5G cellular communications. The wireless communication system 146 can communicate with a wireless local area network (WLAN) using WiFi. In some embodiments, wireless communication system 146 may utilize infrared links, Bluetooth, or ZigBee to communicate directly with the device. Other wireless protocols, such as various vehicle communication systems. For example, wireless communication system 146 may include one or more dedicated short range communications (DSRC) devices, which may include communication between vehicles and/or roadside stations. public and/or private data communications.

Power supply 110 may provide power to various components of vehicle 100 . In one embodiment, the power source 110 may be a rechargeable lithium Ion, sodium-ion or lead-acid batteries. One or more packs of such batteries may be configured as a power source to provide power to various components of the vehicle 100 . In some embodiments, power source 110 and energy source 119 may be implemented together, such as in some all-electric vehicles.

Some or all functions of vehicle 100 are controlled by computer system 112 . Computer system 112 may include at least one processor 113 that executes instructions 115 stored in a non-transitory computer-readable medium such as data storage device 114. Computer system 112 may also be a plurality of computing devices that control individual components or subsystems of vehicle 100 in a distributed manner.

Processor 113 may be any conventional processor, such as a commercially available central processing unit (CPU). Alternatively, the processor may be a dedicated device such as an application specific integrated circuit (ASIC) or other hardware-based processor. Although FIG. 1 functionally illustrates processor 113, data storage 114, and other elements of computer system 112 in the same block, one of ordinary skill in the art will understand that processor 113, computer system 112, or data Storage device 114 may actually include multiple processors, computers, or memories that are not stored within the same physical enclosure. For example, the memory may be a hard drive or other storage medium located in a housing different from computer system 112 . Thus, a reference to a processor or computer will be understood to include a reference to a collection of processors or computers or memories that may or may not operate in parallel. Rather than using a single processor to perform the steps described herein, some components, such as the steering component and the deceleration component, may each have its own processor that only performs calculations related to component-specific functionality. .

In various aspects described herein, the processor may be located remotely from the vehicle and in wireless communication with the vehicle. In other aspects, some of the processes described herein are performed on a processor disposed within the vehicle and others are performed by a remote processor, including taking the steps necessary to perform a single maneuver.

In some embodiments, data storage 114 may contain instructions 115 (eg, program logic) that may be executed by processor 113 to perform various functions of vehicle 100 , including those described above. Data storage 114 may also contain additional instructions, including sending data to, receiving data from, interacting with, and/or performing operations on one or more of travel system 102 , sensor system 104 , control system 106 , and peripherals 108 Control instructions.

In addition to instructions 115, the data storage device 114 may store data such as road maps, route information, vehicle position, direction, speed and other such vehicle data, as well as other information. This information may be used by vehicle 100 and computer system 112 during operation of vehicle 100 in autonomous, semi-autonomous and/or manual modes.

For example, in the embodiment of the present application, the data storage device 114 obtains the voice instructions for controlling the vehicle collected by the microphone 150 from the sensor system 104 or other components of the vehicle 100, the distribution information of people in the vehicle, the distribution information of people outside the vehicle, and the vehicle Status information and other information. The voice command can be issued by a person inside the vehicle or by a person outside the vehicle. The distribution information of people in the car includes whether there are people in the car, the orientation or specific location of the people in the car. The distribution information of people outside the vehicle includes whether there are people within the preset range outside the vehicle, the orientation or specific location of the people outside the vehicle. Vehicle status information includes vehicle driving speed, window opening and closing status and other information. The data storage device 114 can store the above-mentioned related information. In this way, the processor 113 can determine whether the sound source position of the voice instruction is located inside the vehicle based on the above information. If it is determined that the sound source position of the voice command is located inside the vehicle, the vehicle 100 may be further controlled to perform operations corresponding to the voice command.

User interface 116 for providing information to or receiving information from a user of vehicle 100 . Optionally, user interface 116 may include one or more input/output devices within a collection of peripheral devices 108 , such as wireless communications system 146 , onboard computer 148 , microphone 150 , and speaker 152 .

Computer system 112 may control functions of vehicle 100 based on input received from various subsystems (eg, travel system 102 , sensor system 104 , and control system 106 ) and from user interface 116 . For example, computer system 112 may utilize input from control system 106 to control steering system 132 to avoid obstacles detected by sensor system 104 and obstacle avoidance system 144 . In some embodiments, computer system 112 is operable to provide control of many aspects of vehicle 100 and its subsystems.

Alternatively, one or more of these components described above may be installed separately or associated with vehicle 100 . For example, data storage device 114 may exist partially or completely separate from vehicle 100 . The components described above may be communicatively coupled together in wired and/or wireless manners.

Optionally, the above components are just examples. In actual applications, the components in each of the above modules may be added or deleted according to actual needs. Figure 1 should not be understood as limiting the embodiments of the present application.

In the embodiment of the present application, a self-driving car, such as the vehicle 100 above, can detect the voice command based on the audio characteristics of the voice command collected by the microphone 150, the pickup intensity of the voice command by the microphone 150, the distribution of people inside the vehicle, and the preset conditions outside the vehicle. Information such as the distribution of people within the range, the driving speed of the vehicle, the opening and closing of the vehicle's windows, etc. are used to determine whether the sound source position of the voice command is located inside the vehicle.

Further, the vehicle 100 as an autonomous vehicle or the computing device associated with it (such as the computer system 112, the computer vision system 140, and the data storage device 114 in FIG. 3) can determine whether to execute the control corresponding to the voice instruction based on the judgment result. operate. For example, when it is determined that the sound source position is inside the vehicle, the vehicle is controlled to perform operations corresponding to the voice instructions. For another example, when it is determined that the sound source position is not located inside the vehicle (that is, the sound source position is located outside the vehicle), the voice command may not be executed at this time; or, it may be further determined whether the preset trigger condition is met. When the trigger condition is When satisfied, the vehicle is controlled to perform operations corresponding to the voice command; when not satisfied, the voice command is not executed; or, an inquiry message is sent to the user as to whether to execute the voice command.

In addition to providing instructions for instructing the self-driving car to perform emergency communications, the computing device may also provide instructions for modifying the status of various devices within the vehicle 100 so that the self-driving car follows given emergency control measures and controls various devices within the vehicle. status to ensure the safety of the vehicle occupants.

The above-mentioned vehicle 100 can be a car, a truck, a train, an engineering vehicle, a motorcycle, a bus, a boat, an airplane, a helicopter, a lawn mower, an entertainment vehicle, a playground vehicle, construction equipment, a tram, a golf cart, a train, and trolleys, etc., the embodiments of this application are not particularly limited.

Based on the structure of the vehicle 100 provided in FIG. 3 and combined with the vehicle control method provided by the embodiment of the present application, the following continues to conduct a detailed analysis and solution of the technical problems raised in the present application.

Referring to FIG. 4 , FIG. 4 is a schematic flowchart of a vehicle control method 400 provided by an embodiment of the present application. The control method 400 can be applied to the vehicle 100 shown in FIG. 3 . For example, the execution subject of the control method 400 can be the vehicle 100 or a processor or chip in the vehicle 100 ; it can also be applied to other devices capable of controlling the vehicle 100 (such as In cloud servers, mobile terminals, etc.), for example, the execution subject of the control method 400 may be the cloud server or a processor or chip inside the cloud server. The control method 400 may include the following steps 410 to 440.

Step 410: Obtain voice instructions for controlling the vehicle.

With the gradual improvement of the level of intelligence, vehicles (such as smart cars) are usually equipped with microphones and other sound pickup devices, which can collect voice, for example, they can obtain voice instructions for controlling the vehicle, and they can also obtain useless information such as chat content. . Microphones can not only collect speech inside the car, but also often outside the car (especially when the windows are open). Therefore, the voice command can be issued by a driver or passenger in the car (such as a driver or a passenger who takes the seat later) or by a person outside the car. In some cases, the voice command can also be issued by smart devices with voice broadcast functions such as robots and smart speakers. This application does not specifically limit this.

The voice command can control the vehicle. After the vehicle collects the voice command, it performs semantic recognition and generates corresponding control instructions, and controls related control objects through the control instructions. This application does not limit which aspect of voice command is specifically controlled. Optionally, the voice command can perform status control, media control, air conditioning control, seat control, etc. on the vehicle.

Step 420: Determine whether the sound source position of the voice command is located inside the vehicle.

Here, the sound source location of the voice command is the location of the person or device that speaks the voice command. Determining whether the sound source position of the voice command is located inside the vehicle may be determining whether the person who spoke the voice command is located inside the vehicle.

Here, the inside of the vehicle is opposite to the outside of the vehicle. When it is determined that the sound source position of the voice command is not located inside the vehicle, it is equivalent to determining that the sound source position of the voice command is located outside the vehicle.

In some cases, the vehicle interior may refer to the interior of the cab. For example, in passenger vehicles such as cars, off-road vehicles, and buses, the cabs are equipped with seats for passengers in addition to seats for the driver. Therefore, the vehicle interior of a passenger car such as a sedan is clearly defined as the interior of the vehicle body including the seats. For engineering vehicles such as trucks (such as pickup trucks), trucks, cranes, and excavators, in addition to the cab, they usually also have spaces such as buckets, compartments, or buckets for hauling goods or construction. This part of the space is included in this application. Counted as vehicle exterior. For example, if a person speaks the voice command on the bucket of a forklift, it can be determined that the sound source position of the voice command is located outside the vehicle.

With the gradual improvement of the level of intelligence, vehicles are equipped with an increasing number of sensors (such as ADAS sensors), such as in-car cameras, exterior cameras, radars or seat pressure sensors. Various sensors related to the vehicle can be learned through the sensors. According to one or more kinds of data, whether the sound source position of the voice command is located inside the vehicle can be determined. That is, this application does not specifically limit the specific implementation method of determining whether the sound source position of the voice command is located inside the vehicle.

The following lists a variety of methods for determining whether the sound source position is located inside the vehicle. In actual application, any one of the multiple methods, or a combination of multiple methods, can be used to comprehensively determine whether the sound source position is located inside the vehicle. When multiple methods are used to comprehensively determine whether the sound source position is located inside the vehicle, the multiple methods can be determined at the same time, and the final result can be output through multiple determination results; or, the multiple methods can also be based on a certain priority. In order, when one or more of the previous methods can accurately determine the result, the subsequent methods do not need to be executed, thus saving processor computing power.

FIG. 5 is a schematic diagram of an application scenario of the control method 400 shown in FIG. 4 . As shown in part (a) of Figure 5, a person 50 outside the car (for example, the car owner) shouts the voice command "fold the rearview mirror", and the microphone 51 inside the car collects the voice command. , it can be determined through the data collected by the vehicle's interior camera 52 or seat sensor 53 that there are no drivers or passengers in the vehicle at this time. At this time, it can be determined that the sound must come from outside the vehicle (no need to open the exterior camera for further confirmation) , that is, it is determined that the sound source position of the voice command is located outside the vehicle rather than inside.

As shown in part (b) of Figure 5, the person 50 in the car (for example, the driver) speaks the voice command "open the window". After the microphone 51 in the car collects the voice command, the voice command can be Through the data detected by the vehicle's exterior camera 54, radar, laser rangefinder and other devices, it is determined that there are no people within the preset range outside the vehicle at this time. At this time, it can be determined that the sound must come from inside the vehicle (no need to open the interior of the vehicle additionally). The camera further confirms), that is, it is determined that the sound source position of the voice command is located inside the vehicle. Only one exterior camera 54 is shown in the figure. In practical applications, multiple exterior cameras 54 can be set up along the periphery of the vehicle body to obtain a 360-degree panoramic image of the exterior periphery of the vehicle body, which facilitates more efficient and accurate determination of exterior presets. Is there anyone within range.

As shown in part (c) of Figure 5 , the person 50 in the car (for example, the driver) speaks the voice command "Adjust the temperature in the car to 22 degrees Celsius", and the microphone 51 in the car collects the voice command. After the voice command, the vehicle speed data obtained by the vehicle speed sensor can be used to determine that the current vehicle speed is 110km/h, which is greater than the preset vehicle speed threshold of 75km/h. At this time, the microphone 51 cannot pick up the voice outside the vehicle, so the voice command can be determined. The sound source location is inside the vehicle.

In some cases, the audio characteristics of the voice command can be used to determine whether the sound source location is located inside the vehicle. After sound passes through obstacles, some of its own audio characteristics (such as waveform and energy) will be affected, and the audio characteristics will change. In other words, if the same person speaks the same voice command inside and outside the car at the same time, the audio characteristics of the two will be different after being picked up by the microphone. difference. At this time, it can be determined whether the sound source position is located inside the vehicle through this change or difference in the audio characteristics.

As a specific example, Figure 6 is a schematic diagram of the propagation process of control instructions. As shown in FIG. 6 , a microphone 61 is provided inside the vehicle, and the vehicle window 62 is in a completely closed state. At this time, the person 60 outside the car speaks the voice command "open the door" outside the car. This voice command propagates in the air in the form of sound waves, and needs to pass through the car body including the window glass. Enter the car and eventually reach microphone 61. Due to the absorption and refraction of sound waves by the car body, the audio characteristics of the voice command change, that is, the characteristic parameters of the sound wave 63 before passing through and the sound wave 64 after passing through in Figure 6 may be slightly different. According to the audio characteristics of the voice command picked up by the microphone 61 and combined with a preset algorithm (such as a neural network model), it can be determined that the sound source position of the voice command is located outside the car, that is, the person speaks the voice command from outside the car.

Optionally, the voice feature may include a spectrum structure, and whether the sound source position is located inside the vehicle may be determined based on the acquired spectrum structure of the voice instruction. After the sound passes through obstacles such as car window glass, the energy in the high-frequency band in the spectrum structure is absorbed, and the high-frequency part will be significantly attenuated. However, the high-frequency spectrum structure of the normal sound emitted in the car that has not passed through obstacles is Some parts will be preserved relatively completely, so under the same circumstances, there will be differences in the spectrum structure between the voice commands issued outside the car and the voice commands issued inside the car. This part of the difference can be used to determine whether the sound source position is located inside the vehicle. The advantage of using the spectrum structure to determine whether the sound source position is located inside the vehicle is that the confirmation method is simple, efficient and easy to implement without resorting to other data, which can reduce the frequency of use of other sensors in the vehicle.

For example, the spectral structure can be input into a pre-trained neural network model (such as a CNN model). The neural network model analyzes and calculates the spectral structure, and finally outputs a judgment result of whether the sound source position is located inside the vehicle.

In some cases, it can be determined whether the sound source position of the voice command is located inside the vehicle based on the characteristics of the high-frequency part in the spectrum structure of the voice command. When the integrity of the high-frequency part meets the preset conditions, it is determined that the sound source position is located inside the vehicle.

Because after the sound passes through obstacles such as car window glass, the energy in the high-frequency band in the spectrum structure is absorbed, and the high-frequency part will be significantly attenuated. However, the normal sound emitted in the car that has not passed through obstacles has a high-frequency band in the spectrum structure. The high-frequency part will be preserved relatively completely. Therefore, under the same circumstances, the voice commands issued outside the car and the voice commands issued inside the car will have a more obvious difference in the integrity of the high-frequency part. It can be determined by the characteristics of the high-frequency part. Determine whether the sound source position of the voice command is located inside the vehicle. When the integrity of the high-frequency part meets the preset conditions, it is determined that the sound source position is located inside the vehicle. The advantage of determining whether the sound source position is located inside the vehicle through the characteristics of the high-frequency part of the spectrum structure is that the confirmation method is simple, efficient and easy to implement without resorting to other data, which can reduce the frequency of use of other sensors in the vehicle.

Step 430: When it is determined that the sound source position is inside the vehicle, control the vehicle to perform operations corresponding to the voice instructions.

When it is determined in step 420 that the sound source is located inside the vehicle, it is determined that the sound source is a voice command issued by a driver or passenger in the vehicle. At this time, the vehicle can be controlled to perform corresponding operations based on the voice command. In some cases, the voice command may be a wake-up command used to wake up the voice assistant of the vehicle, such as "Xiaoyi Xiaoyi", in which case the voice assistant of the vehicle can be woken up. In some cases, the voice command can be a control command for status control, media control, air conditioning control, and seat control of the vehicle. In this case, the corresponding control object can be controlled to perform the corresponding operation.

Wherein, controlling the vehicle to perform operations corresponding to the voice instructions specifically includes: performing semantic recognition on the acquired voice instructions to obtain control instructions, and controlling the vehicle accordingly according to the control instructions.

That is to say, when it is determined that the sound source is located inside the vehicle, the voice command will be semantically parsed to generate the corresponding For control instructions, when it is determined that the sound source position is not located inside the vehicle (that is, outside the vehicle), the semantic analysis of the voice instruction may not be performed, which is beneficial to saving the computing power of the processor.

Step 440: When it is determined that the sound source position is not located inside the vehicle, control the vehicle not to execute the voice command.

Specifically, when it is determined in step 420 that the sound source position is not located inside the vehicle, that is, it is determined that the sound source position is located outside the vehicle, it means that the voice command may have been spoken by someone outside the vehicle (such as a stranger, a passerby, or a criminal) and is accidentally picked up by the microphone. At this time, the voice command does not need to be semantically recognized and the voice command is not executed, that is, the voice command is not responded to. This can improve the safety of vehicle control and ensure the safety of the passengers in the car. Property safety is ensured.

According to the vehicle control method 400 provided by the embodiment of the present application, after receiving a voice command for controlling the vehicle, instead of directly executing the command, it first determines whether the sound source position of the voice command is located inside the vehicle. When determining The control operation corresponding to the voice command is only executed when the sound source position of the voice command is located inside the vehicle. This makes the control of the vehicle more intelligent, improves the safety of the vehicle, and ensures the personal and property safety of passengers in the vehicle. This application can help users in the car effectively avoid control and interference of the vehicle by strangers outside the car, without causing misoperation of the vehicle, further ensuring the safety of people in the car, especially in resting scenes.

Taking the scene shown in Figure 1 as an example, the driver and passengers of vehicle 11 parked the vehicle 11 on the roadside and took a rest in the car. At this time, the person 13 outside the vehicle shouted the voice command of "open the door". Since the vehicle 11 applied The control method 400 provided by the embodiment of the present application enables the vehicle 11 to first determine that the sound source position of the voice command is located outside the vehicle according to the preset determination logic. At this time, the vehicle 11 will not execute the voice command, that is, it will not open the door. Car doors, thus ensuring the personal and property safety of passengers in the car.

Referring to FIG. 7 , FIG. 7 is a schematic flowchart of a vehicle control method 700 provided by an embodiment of the present application. The control method 700 may include the following steps 710 to 750. For step 710, step 730 and step 750, reference may be made to the descriptions of step 410, step 430 and step 440 in the foregoing embodiments respectively. Different parts will be emphasized here.

Step 710: Obtain voice instructions for controlling the vehicle.

Step 720: Determine whether the sound source is located inside the vehicle based on the microphone's pickup intensity of the voice command.

Specifically, the closer the microphone is to the sound source of the voice command, the stronger the pickup (sound pickup) intensity of the voice command will be, that is, the volume of the picked-up voice command will be greater, so the microphone will pick up the voice command. The intensity can reflect the distance from the sound source location. Based on the pickup intensity, it can be determined whether the sound source location is inside the vehicle. For example, the specific location of the sound source location, or the specific orientation of the sound source location, can be determined based on the pickup intensity of the voice command by the microphone, and then it can be further determined whether the sound source location is located inside the vehicle.

In some cases, the vehicle may be equipped with only one microphone, and whether the sound source position is located inside the vehicle can be determined by the pickup intensity of the voice command by the only microphone. Figure 8 is a schematic diagram of the application scenario of the control method shown in Figure 7. As shown in part (a) of Figure 8, the vehicle is equipped with an in-vehicle microphone 81 located in the vehicle. The in-vehicle microphone 81 is located adjacent to the driving position and is the vehicle's the only microphone. The in-car microphone 81 can only accurately pick up sounds within a small range of the surrounding area. After the in-car microphone 81 receives the voice command "turn on the seat heating function" and determines that the pickup intensity of the voice command exceeds the threshold, it is determined that the voice command should be from a person in the driving seat relatively close to the in-car microphone 81 80 is issued, that is, it is determined that the sound source location is in the car. At this time, the vehicle can execute the voice command, that is, turn on the seat heating function to heat the seat.

In some cases, the vehicle may usually be equipped with multiple microphones. The pickup strength of each of the multiple microphones for voice commands can be used in conjunction with a preset algorithm (such as a trained neural network model) to determine whether the sound source location is Located inside the vehicle. The plurality of microphones can be installed in the car. For example, they can be centrally installed near the center console of the vehicle in the form of a microphone array, or they can be distributed at different seats in the car. The plurality of microphones may also include at least one external microphone for picking up voices outside the vehicle, so that the user can perform voice interaction with the vehicle outside the vehicle and obtain a better vehicle experience.

Optionally, as shown in part (b) of Figure 8 , the vehicle is equipped with at least one in-vehicle microphone 81 and at least one external microphone 82. When the person 80 outside the vehicle speaks the voice command of "open the trunk", The in-vehicle microphone 81 and the out-of-vehicle microphone 82 pick up the voice of the instruction at the same time. At this time, the pickup intensity of the out-of-vehicle microphone 82 is significantly greater than that of the in-vehicle microphone 81, so it can be determined that the sound source position (that is, the position of the person 80) is located in the vehicle. Externally, this instruction does not need to be executed.

Optionally, the vehicle is equipped with multiple in-vehicle microphones. In this case, whether the sound source position is located inside the vehicle can be directly determined based on the pickup strength of each of the multiple in-vehicle microphones 81 for voice commands in combination with a preset algorithm. Alternatively, it is also possible to first determine the specific location of the sound source (i.e., specific coordinates), the direction of the sound source, the distance to each microphone, and other information, and then indirectly determine whether the sound source is located inside the vehicle through the above information.

For example, as shown in part (c) of FIG. 8 , the vehicle is equipped with three in-vehicle microphones 81 distributed at different seats in the vehicle. The connection lines of these three in-vehicle microphones 81 generally form an isosceles triangle structure. The person 80 in the middle seat of the back row speaks the voice command "Move the rear seat backwards", and the three in-car microphones 81 pick up the voice command with roughly the same intensity, then it can be determined that the sound source position is adjacent to the triangle. The central position, that is, the position of the sound source (ie, the position of the person 80) can be determined to be located inside the vehicle.

Step 730: If it is determined that the sound source is located inside the vehicle, control the vehicle to perform operations corresponding to the control instruction.

Step 740, if it is determined that the sound source is located outside the vehicle, it is determined whether the preset trigger condition is met. If the trigger condition is met, step 730 is entered, that is, the vehicle is controlled to perform operations corresponding to the control instruction.

Step 750: If the trigger condition is not met, the voice command is not executed.

Here, the trigger conditions can be preset by the manufacturer, or can be set by the user. For example, the user can set the conditions based on the scenarios in which the user may voice control the vehicle outside the vehicle.

Referring to FIG. 9 , FIG. 9 is a schematic flowchart of a vehicle control method 900 provided by an embodiment of the present application. The control method 900 may include the following steps 910 to 960. For step 910, step 940 and step 950, reference may be made to the descriptions of step 410, step 420 and step 430 in the foregoing embodiments respectively. Different parts will be emphasized here.

Step 910: Obtain voice instructions for controlling the vehicle.

Step 920: Determine the orientation of the sound source location based on the pickup intensity of the voice command by each of the multiple microphones.

Step 930: Determine whether the sound source is located inside the vehicle based on the direction of the sound source.

Specifically, in some cases, such as an insufficient number of microphones or an unsatisfactory relative position between the sound source and the microphone, it may not be possible to accurately determine the specific location of the sound source based on the pickup intensity, or a large processor computing power may be required. At this time, the orientation of the sound source position can be determined based on the pickup intensity of the voice command by a pair of microphones, and with the help of a preset algorithm or logic, it can be determined whether the sound source position is located inside the vehicle through the orientation.

FIG. 10 is a schematic diagram of an application scenario of the control method 900 shown in FIG. 9 . In conjunction with Figure 9 and Figure 10, in this embodiment of the present application, step 930 specifically includes:

Step 931: Determine whether there is a person inside the vehicle at the orientation. If not, determine that the sound source is located outside the vehicle. At this time, step 960 is entered to send a query message asking whether to execute the voice command; if so, step 932 is entered.

As shown in part (a) of Figure 10 , the in-car microphone 81 is installed near the center console of the vehicle. The direction of the sound source position can first be determined based on the pickup intensity of the voice command by the in-car microphone 81 as indicated by the dotted arrow in the figure. At this time, if it is determined with the help of data collected by the in-vehicle camera 83, the seat pressure sensor 84, etc. that there is no one in the car at this direction, it can be determined that the sound source position is outside the vehicle, for example, it can be outside the vehicle. The person 80 located at this location speaks the voice command.

Step 932: Determine whether there is a person outside the vehicle at the orientation. If not, determine that the sound source position is inside the vehicle. At this time, step 950 is entered to control the vehicle to perform the control operation corresponding to the voice command; if so, indicate that the sound source is located inside the vehicle. There are people both inside and outside the vehicle in the direction. At this time, further judgment needs to be made with the help of other data, and step 940 can be entered.

As shown in part (b) of Figure 10 , the in-car microphone 81 is installed near the center console of the vehicle. The direction of the sound source position can first be determined based on the pickup intensity of the voice command by the in-car microphone 81 as indicated by the dotted arrow in the figure. At this time, if it is determined that there is no person outside the vehicle in this direction with the help of data collected by the exterior camera 85, radar or laser range finder, it can be determined that the sound source position is inside the vehicle, for example, it can be the vehicle The person 80 in the main driving position speaks the voice command.

As shown in part (c) of Figure 10 , if it is determined that there is a person in the car at this orientation using the data collected by the in-car camera 83, the seat pressure sensor 84, etc., and, with the help of the outside camera 85, If the data collected by radar or laser range finder determines that there are people outside the vehicle at this location, it is still not possible to determine whether the sound source is located inside the vehicle. Therefore, it is necessary to further combine other methods (data) to make further judgments. This article The application does not specifically limit the other methods here. For example, step 940 may be entered.

Step 940: Determine whether the sound source position is located in the vehicle according to the audio characteristics. If yes, proceed to step 950 to control the vehicle to perform a control operation corresponding to the voice command; if not, proceed to step 960 to send an inquiry message as to whether to execute the voice command. For how to determine whether the sound source position is located in the vehicle based on the audio characteristics in step 940, please refer to the relevant description of step 420 mentioned above, and will not be described again here.

In this embodiment of the present application, when it is determined that the sound source position of the voice command is located outside the vehicle, step 960 is entered to send an inquiry message as to whether to execute the voice command, instead of directly not executing the voice command as in the previous embodiment. The control method provided by the embodiment of the present application can not only improve the safety of vehicle voice control, but also increase the control flexibility, which is beneficial to improving the user experience.

For example, when a person outside the vehicle speaks the voice command "Open the window", the vehicle uses built-in judgment logic to determine that the voice command comes from outside the vehicle. At this time, the speaker device in the car can broadcast "Do you need to open the window?" ?" inquiry information, if you get a positive reply from the person in the car through the touch screen or voice assistant, for example, the driver says "Yes, open the window", then you can perform the "open window" operation at this time, and if the driver If the driver says "Don't open the window" or no further reply is received, the operation of "opening the window" does not need to be performed.

The vehicle control method provided by the embodiment of the present application is described in detail above with reference to FIGS. 1 to 10 , and the device of the embodiment of the present application is described in detail below with reference to FIGS. 11 and 12 . It should be understood that the devices shown in Figures 11 and 12 can implement one or more steps in the method flows shown in Figures 4, 7 and 9. To avoid repetition, they will not be described in detail here.

FIG. 11 is a schematic block diagram of a vehicle control device 1100 provided by an embodiment of the present application. As shown in FIG. 11 , the control device 1100 includes an acquisition unit 1110 , a determination unit 1120 and a control unit 1130 .

Obtaining unit 1110, used to obtain voice instructions for controlling the vehicle;

Determining unit 1120, used to determine whether the sound source position of the voice instruction is located inside the vehicle;

The control unit 1130 is configured to control the vehicle to perform operations corresponding to the voice instructions when the sound source is located inside the vehicle.

Optionally, the determining unit 1120 is specifically used to:

Whether the sound source position is located inside the vehicle is determined based on the audio characteristics of the voice instruction.

Optionally, the audio features include spectral structure.

Optionally, the determining unit 1120 is specifically configured to: determine whether the sound source position of the voice command is located inside the vehicle according to the characteristics of the high-frequency part in the spectrum structure of the voice command; when the integrity of the high-frequency part When the preset conditions are met, OK The sound source location is located inside the vehicle.

Optionally, the determining unit 1120 is specifically used to:

Whether the sound source position is located inside the vehicle is determined based on the pickup intensity of the voice command by the vehicle's microphone.

Optionally, the determining unit 1120 is specifically used to:

Determine the orientation of the sound source location based on the pickup intensity of the voice command by multiple microphones;

Whether the sound source position is located inside or outside the vehicle is determined based on the orientation.

Optionally, the determining unit 1120 determines whether the sound source position is located inside the vehicle through at least one of the following information:

The audio characteristics of the voice command;

The pickup intensity of the voice command by the vehicle's microphone;

The distribution of people inside the vehicle;

The distribution of people within the preset range outside the vehicle;

The driving speed of the vehicle;

The opening and closing conditions of the vehicle's windows.

Optionally, the voice instruction includes a wake-up instruction, and the control unit 1130 is specifically configured to:

Wake up the vehicle's voice assistant.

Optionally, the control unit 1130 is specifically used to:

Perform semantic analysis on the voice instructions to obtain control instructions;

The vehicle is controlled according to the control instructions.

Optionally, when the sound source is located outside the vehicle, the control unit 1130 is also used to:

The vehicle is controlled not to execute the voice command.

Optionally, when the sound source position is located outside the vehicle, if it is determined that the preset trigger condition is met, the control unit 1130 is also used to:

The vehicle is controlled to perform operations corresponding to the voice instructions.

Optionally, the control device also includes:

The sending unit 1140 is configured to send query information on whether to execute the voice command when the sound source is located outside the vehicle.

Specifically, the control device 1100 may correspond to the vehicle or the device (such as a cloud server) that controls the vehicle in the methods 400, 700, and 900 according to the embodiments of the present application, or a chip configured in the vehicle or the vehicle control device. The control device 1100 may include various units for executing the methods performed by the vehicle in FIGS. 4 , 7 and 9 . Moreover, each unit and the above-mentioned other operations and/or functions in the control device 1100 are respectively to implement the corresponding processes of the method 400, the method 700 and the method 900. The specific process of each unit performing the above-mentioned corresponding steps is in the method 400, the method 700 and the method. It has been explained in detail in 900 and will not be repeated here for the sake of brevity.

FIG. 12 is a schematic structural diagram of a vehicle control device 1200 provided by an embodiment of the present application. The control device 1200 may be a vehicle or a vehicle control device, or may be a chip or circuit provided in the vehicle or a vehicle control device. As shown in Figure 12, the control device 1200 includes: a processor 1210, a memory 1220 and a communication interface 1230. Instructions are stored in the memory 1220, and the processor 1210 is used to execute the instructions in the memory 1220. When the instructions are executed, the processor 1210 is used to execute the method provided by the above method embodiment, and the processor 1210 is also used to control The communication interface 1230 communicates with the outside world.

Further, the processor 1210, the memory 1220 and the communication interface 1230 can communicate with each other through internal connection channels to transmit control and/or data signals.

Further, the memory 1220 can be integrated in the processor 1210 or can be provided separately from the processor 1210 .

Specifically, the control device 1200 can be used to execute each step in the methods 400, 700 and 900 in FIGS. Modules of the method executed by the vehicle of method 400, method 700 and method 900 in 9. Moreover, each module in the control device 1200 and the above-mentioned other operations and/or functions are to implement the corresponding processes of the method 400, the method 700 and the method 900 in FIG. 4, FIG. 7 and FIG. 9 respectively. The specific process of each module performing the above corresponding steps has been described in detail in method 400, method 700, and method 900, and will not be described again for the sake of brevity.

Embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium includes a computer program that, when run on a computer, causes the computer to execute the method provided by the above method embodiment.

Embodiments of the present application also provide a computer program product containing instructions, which when the computer program product is run on a computer, causes the computer to execute the method provided by the above method embodiment.

Embodiments of the present application also provide a chip system, including a memory and a processor. The memory is used to store a computer program. The processor is used to call and run the computer program from the memory, so that the network device installed with the chip system executes the above. Methods provided by method embodiments.

The chip system may include an input circuit or interface for sending information or data, and an output circuit or interface for receiving information or data.

It should be understood that in the embodiments of the present application, the processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), or dedicated integrated processors. Circuit (application specific integrated circuit, ASIC), off-the-shelf programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

It should also be understood that the memory in the embodiments of the present application may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Among them, non-volatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable programmable read-only memory (erasable PROM, EPROM), electrically removable memory. Erase electrically programmable read-only memory (EPROM, EEPROM) or flash memory. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of illustration, but not limitation, many forms of random access memory (RAM) are available, such as static random access memory (static RAM (SRAM)), dynamic random access memory (DRAM), synchronous dynamic random access memory (RAM) Access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous connection dynamic random access memory access memory (synchlink DRAM, SLDRAM) and direct memory bus random access memory (direct rambus RAM, DR RAM).

Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each specific application, but such implementations should not be considered beyond the scope of this application.

Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be described again here.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, and the indirect coupling or communication connection of the devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, each unit can exist physically alone, or two or more units can be integrated into one unit.

If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage media include: U disk, mobile Various media that can store program code include hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk.

The above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application. should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

A vehicle control method, characterized by including:

Get voice commands to control the vehicle;

Determine whether the sound source position of the voice command is located inside the vehicle;

When the sound source is located inside the vehicle, the vehicle is controlled to perform an operation corresponding to the voice instruction.
The control method according to claim 1, wherein determining whether the sound source position of the voice command is located inside the vehicle includes:

Whether the sound source position is located inside the vehicle is determined based on the audio characteristics of the voice instruction.
The control method according to claim 2, characterized in that the audio characteristics include spectral structure.
The control method according to claim 3, wherein determining whether the sound source position of the voice command is located inside the vehicle includes:

Determine whether the sound source position of the voice command is located inside the vehicle according to the characteristics of the high-frequency part in the spectrum structure of the voice command;

When the integrity of the high-frequency part meets the preset condition, it is determined that the sound source position is located inside the vehicle.
The control method according to any one of claims 1 to 4, wherein determining whether the sound source position of the voice command is located inside the vehicle includes:

Whether the sound source position is located inside the vehicle is determined based on the pickup intensity of the voice command by the vehicle's microphone.
The control method according to claim 5, wherein determining whether the sound source position is located inside the vehicle according to the pickup intensity of the voice command by the vehicle's microphone includes:

Determine the orientation of the sound source location based on the pickup intensity of the voice command by multiple microphones;

Determine whether the sound source position is located inside the vehicle according to the orientation.
The control method according to claim 1, characterized in that whether the sound source position is located inside the vehicle is determined through at least one of the following information:

The audio characteristics of the voice command;

The pickup intensity of the voice command by the vehicle's microphone;

The distribution of people inside the vehicle;

The distribution of people within the preset range outside the vehicle;

The driving speed of the vehicle;

The opening and closing conditions of the vehicle's windows.
The control method according to any one of claims 1 to 7, wherein the voice command includes a wake-up command, and controlling the vehicle to perform operations corresponding to the voice command includes:

Wake up the vehicle's voice assistant.
The control method according to any one of claims 1 to 8, wherein the controlling the vehicle to perform operations corresponding to the voice instructions includes:

Perform semantic recognition on the voice instructions to obtain control instructions;

The vehicle is controlled according to the control instructions.
The control method according to any one of claims 1-9, characterized in that the method further includes:

When the sound source position is located outside the vehicle, the vehicle is controlled not to execute the voice command.
The control method according to any one of claims 1-9, characterized in that the method further includes:

When the sound source is located outside the vehicle, if it is determined that the preset trigger condition is met, the vehicle is controlled to perform an operation corresponding to the voice command.
The control method according to any one of claims 1-9, characterized in that the method further includes:

When the sound source is located outside the vehicle, query information is sent as to whether to execute the voice command.
A vehicle control device, characterized by comprising at least one processor, the at least one processor being coupled to a memory, reading and executing instructions in the memory, to implement any one of claims 1 to 12 The control method described in the item.
A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium. When the computer program is run on a computer, it causes the computer to execute any one of claims 1 to 12. The control method described in the item.
A chip system, characterized in that it includes a processor for calling and running a computer program from a memory, so that the computer installed with the chip system executes the control method according to any one of claims 1 to 12.
A vehicle, characterized by comprising the vehicle control device according to claim 13.