A voice control system and method for a vehicle

Abstract

The present invention discloses a voice control system and method for a vehicle, relating to the technical field of assisted driving. The system includes: a target voice engine, a voice framework module, and a voice service module; the target voice engine is configured to obtain a voice command input by a user, process the voice command to obtain semantic data corresponding to the voice command, and send the semantic data to the voice framework module; the voice framework module is configured to convert the semantic data from an initial data format to a target data format by using a preset message protocol to obtain a control command, and send the control command to the voice service module by using socket communication, where the initial data format corresponds to the target voice engine; the voice service module is configured to control the vehicle to perform corresponding operations according to the received control command. In the present invention, cross-platform deployment of the vehicle voice control system can be achieved, and data formats corresponding to different types of voice engines can be shielded, improving the compatibility and scalability of the vehicle voice control system.

Description

Technical Field

[0001] The present invention relates to the technical field of assisted driving, and particularly to a voice control system and method for a vehicle. Background Art

[0002] With the development of assisted driving technology, the intelligent voice control function in vehicles has become increasingly rich. The intelligent voice control system in a vehicle uses an intelligent voice engine to process the user's voice commands. However, different types of intelligent voice engines have different corresponding data structures, and the communication methods of the same type of intelligent voice engine in different application platforms are also different. When expanding the application platform or function of the voice control system, users need to modify a large amount of code to implement the changes in the engine interface or add new interfaces, resulting in low compatibility and scalability of the voice control system. Summary of the Invention

[0003] The present invention provides a voice control system and method for a vehicle, which can shield the data structures of different types of intelligent voice engines and unify the communication methods of intelligent voice engines in different platforms, thereby improving the compatibility and scalability of the voice control system.

[0004] To achieve the above object, the present invention adopts the following technical solutions:

[0005] In a first aspect, the present invention provides a voice control system for a vehicle, which includes a target voice engine, a voice framework module, and a voice service module;

[0006] The target voice engine is configured to obtain the voice command input by the user, process the voice command to obtain the semantic data corresponding to the voice command, and send the semantic data to the voice framework module;

[0007] The voice framework module is configured to convert the semantic data from the initial data format to the target data format by using a preset message protocol to obtain a control command, and send the control command to the voice service module by using the Socket communication method. The initial data format corresponds to the target voice engine;

[0008] The voice service module is configured to control the vehicle to perform corresponding operations according to the received control command.

[0009] In a possible implementation manner, the preset message protocol is Protocol Buffers (Protobuf).

[0010] In a possible implementation, the voice framework module is specifically configured to use a preset message protocol. When the source of the semantic data is the target voice engine, determine that the message type of the semantic data is the control type, and encapsulate the semantic data and the control type into a data packet in the target data format to obtain a control instruction; the voice service module is specifically configured to, when determining that the control instruction includes the message type of the control type, control the vehicle to perform corresponding operations according to the control instruction.

[0011] In a possible implementation, the control instruction further includes an identified controlled device; the voice service module is specifically configured to call the interface corresponding to the identified controlled device and control the device corresponding to the identified controlled device in the vehicle to perform the operation corresponding to the semantic data.

[0012] In a possible implementation, after the voice service module calls the interface corresponding to the identified controlled device and controls the device corresponding to the identified controlled device in the vehicle to perform the operation corresponding to the semantic data, the voice service module is further configured to obtain the function return value corresponding to the operation, and when the source of the function return value is the device corresponding to the identified controlled device, determine that the message type of the function return value is the feedback type, encapsulate the function return value and the feedback type into a feedback data packet in the target data format, and send the feedback data packet to the voice framework module. The function return value is used to indicate the execution situation of the operation; the voice framework module is further configured to receive and store the feedback data packet.

[0013] In a possible implementation, the voice control system of the vehicle further includes a target application program. Before the target voice engine obtains the voice instruction input by the user, the target application program is configured to obtain a wake-up instruction and send the wake-up instruction to the voice service module. The wake-up instruction is used to indicate activating the target voice engine; the voice service module is configured to, when the source of the wake-up instruction is the target application program, determine that the message type of the wake-up instruction is the event type, encapsulate the wake-up instruction and the event type into an activation data packet in the target data format, and send the activation data packet to the voice framework module; the voice framework module is configured to activate the target voice engine according to the received activation data packet.

[0014] In a second aspect, the present invention provides a voice control method for a vehicle, which is applied to the voice control system of the vehicle as described in the first aspect and any of its possible implementations. The method includes:

[0015] The target voice engine obtains the voice instruction input by the user, processes the voice instruction to obtain the semantic data corresponding to the voice instruction, and sends the semantic data to the voice framework module;

[0016] The voice framework module adopts a preset message protocol to convert semantic data from an initial data format into a target data format, obtaining a control instruction, and sends the control instruction to the voice service module in a socket communication manner. The initial data format corresponds to the target voice engine;

[0017] The voice service module controls the vehicle to perform corresponding operations according to the received control instruction.

[0018] In a possible implementation, the preset message protocol is Protocol Buffers.

[0019] In a possible implementation, the voice framework module adopts a preset message protocol to convert semantic data from an initial data format into a target data format, obtaining a control instruction, specifically including: when the source of the semantic data is the target voice engine, the voice framework module adopts the preset message protocol to determine that the message type of the semantic data is the control type, and encapsulates the semantic data and the control type into a data packet in the target data format, obtaining a control instruction; the voice service module controls the vehicle to perform corresponding operations according to the received control instruction, specifically including: when the voice service module determines that the control instruction includes a message type of the control type, it controls the vehicle to perform corresponding operations according to the control instruction.

[0020] In a possible implementation, the control instruction also includes an identified controlled device; the voice service module controls the vehicle to perform corresponding operations according to the received control instruction, specifically including: the voice service module calls the interface corresponding to the identified controlled device to control the device corresponding to the identified controlled device in the vehicle to perform the operation corresponding to the semantic data.

[0021] In a possible implementation, after the voice service module calls the interface corresponding to the identified controlled device to control the device corresponding to the identified controlled device in the vehicle to perform the operation corresponding to the semantic data, the voice control method further includes: the voice service module obtains the function return value corresponding to the operation, and when the source of the function return value is the device corresponding to the identified controlled device, determines that the message type of the function return value is the feedback type, encapsulates the function return value and the feedback type into a feedback data packet in the target data format, and sends the feedback data packet to the voice framework module. The function return value is used to indicate the execution situation of the operation; the voice framework module receives and stores the feedback data packet.

[0022] In a possible implementation, the voice control system of the vehicle further includes a target application. Before the target voice engine obtains the voice command input by the user, the voice control method further includes: the target application obtains a wake-up command and sends the wake-up command to the voice service module. The wake-up command is used to indicate the activation of the target voice engine; when the source of the wake-up command is the target application, the voice service module determines that the message type of the wake-up command is an event type, encapsulates the wake-up command and the event type into an activation data packet in a target data format, and sends the activation data packet to the voice framework module; the voice framework module activates the target voice engine according to the received activation data packet.

[0023] In a third aspect, the present invention provides a vehicle, which includes: a processor and a memory; the memory is used to store computer program code, and the computer program code includes computer instructions; when the processor executes the computer instructions, the vehicle executes the voice control method of the vehicle as described in the second aspect and any one of its possible implementation manners.

[0024] In a fourth aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored. When the computer instructions run on the vehicle, the vehicle executes the voice control method of the vehicle as described in the second aspect and any one of its possible implementation manners.

[0025] In a fifth aspect, the present invention provides a computer program product, which includes computer instructions. When the computer instructions run on the vehicle, the vehicle executes the voice control method of the vehicle as described in the second aspect and any one of its possible implementation manners.

[0026] The voice control system of the vehicle provided by the embodiments of the present invention includes a target voice engine, a voice framework module, and a voice service module; the target voice engine is used to obtain the voice command input by the user, process the voice command to obtain semantic data corresponding to the voice command, and send the semantic data to the voice framework module; the voice framework module is used to convert the semantic data from the initial data format to the target data format by using a preset message protocol to obtain a control command, and send the control command to the voice service module by using socket communication. The initial data format corresponds to the target voice engine; the voice service module is used to control the vehicle to perform corresponding operations according to the received control command. Since the types of the target voice engines are different, the initial data formats are also different, and the communication methods in different platforms are also different. In the present invention, the control command in the target data format customized by the preset message protocol is transmitted through a unified socket communication method, which can realize the cross-platform deployment of the voice control system of the vehicle, and can shield the initial data formats corresponding to different types of target voice engines, thereby improving the compatibility and scalability of the voice control system of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 Schematic diagram of the system architecture of a voice control system for a vehicle provided by an embodiment of the present invention;

[0028] Figure 2 Internal interaction diagram of a voice control system for a vehicle provided by an embodiment of the present invention. Detailed implementation manners

[0029] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present invention.

[0030] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present disclosure, unless otherwise specified, the meaning of "a plurality" is two or more. Additionally, the use of "based on" or "according to" means open and inclusive, because a process, step, calculation, or other action "based on" or "according to" one or more of the stated conditions or values may in practice be based on additional conditions or values beyond those stated.

[0031] To solve the problems of low compatibility and scalability of the voice control system, an embodiment of the present invention provides a voice control system and method for a vehicle. The voice control system of the vehicle includes a target voice engine, a voice framework module, and a voice service module; the target voice engine is used to obtain a voice command input by a user, process the voice command to obtain semantic data corresponding to the voice command, and send the semantic data to the voice framework module; the voice framework module is used to convert the semantic data from an initial data format to a target data format using a preset message protocol to obtain a control command, and send the control command to the voice service module using socket communication. The initial data format corresponds to the target voice engine; the voice service module is used to control the vehicle to perform corresponding operations according to the received control command. Since the types of the target voice engines are different, the initial data formats are also different, and the communication methods in different platforms are also different. In the present invention, the control command in the target data format customized by the preset message protocol is transmitted through a unified socket communication method, which can realize cross-platform deployment of the voice control system of the vehicle and can shield the initial data formats corresponding to different types of target voice engines, thereby improving the compatibility and scalability of the voice control system of the vehicle.

[0032] Figure 1This is a schematic diagram of the system architecture of a possible voice control system for a vehicle provided by an embodiment of the present invention. As Figure 1 shown, the vehicle voice control system may include an operating system platform, a target voice engine, a voice framework module, a voice service module, and a target application.

[0033] Among them, the operating system platform is an essential system software for the vehicle and the soul of the entire vehicle. Common operating systems may include Windows operating system, Linux operating system, Android operating system, etc.

[0034] The target voice engine is used to perform voice processing on the voice data in the vehicle to obtain corresponding semantic data. And different types of voice engines are supported to be installed in the same vehicle of the present invention. The target voice engine may include multiple modules for performing different functions during the voice processing process.

[0035] The voice framework module and the voice service module may be two modules set in the application framework layer. Of course, these two modules may also be set in other layers of the software system, and the present invention does not limit this here. The voice framework module adapts the interfaces of multiple different types of voice engines and is mainly used to encapsulate data. The communication method between the voice framework module and the voice service module is Socket, and a preset message protocol is used to transmit data between the voice framework module and the voice service module. This preset message protocol may be Protobuf.

[0036] The target application may be a smart voice assistant. The target application can communicate with the voice service module through the Android Interface Definition Language (AIDL). The target application can be used to obtain a wake-up instruction, which is used to indicate the activation of the target voice engine and is also used to display voice instructions.

[0037] In a specific implementation, when a user in the vehicle performs voice control, the microphone in the vehicle can obtain the user's voice instruction and send the voice instruction to the operating system platform of the voice control system. The operating system platform sends the voice instruction to the target voice engine. The target voice engine can process the voice instruction to obtain semantic data and send the semantic data to the voice framework module. The voice framework module can use the preset message protocol to convert the semantic data from the initial data format to the target data format to obtain a control instruction, and send the control instruction to the voice service module by using the Socket communication method. The voice service module can control the vehicle to perform corresponding operations according to the received control instruction through a framework layer interface (such as carlib) designed specifically for in-vehicle functions.

[0038] Figure 2 The figure is an internal interaction schematic diagram of a possible voice control system for a vehicle provided by an embodiment of the present invention. As Figure 2 shown, the target voice engine is used to obtain a voice command input by a user, process the voice command to obtain semantic data corresponding to the voice command, and send the semantic data to the voice framework module.

[0039] Specifically, the operating system platform can obtain the voice input by the user, thereby generating a voice command, and send the voice command to the target voice engine. The target voice engine can convert the voice command into corresponding text information through Automatic Speech Recognition (ASR), and then convert the text information into semantic data corresponding to the voice command through Natural Language Understanding (NLU), and send the semantic data to the voice framework module.

[0040] It can be understood that the data formats used by different types of target voice engines when sending semantic data are different.

[0041] The voice framework module is used to convert the semantic data from the initial data format to the target data format by using a preset message protocol to obtain a control command, and send the control command to the voice service module by using Socket communication. The initial data format corresponds to the target voice engine.

[0042] Among them, the voice framework module adapts interfaces corresponding to a variety of different types of voice engines and can be compatible with a variety of different voice engines.

[0043] The preset message protocol can be a method for serializing structured data that is language-independent, platform-independent, extensible, and customizable, such as Protobuf, Extensible Markup Language (XML), or JavaScript Object Notation (JASON). The target data format is customized in the preset message protocol, and the semantic data in a variety of initial data formats sent by different types of target voice engines can be converted into control commands in the same target data format.

[0044] To facilitate understanding of the implementation method of the definition of the data format by protobuf, taking the preset message protocol as Protobuf as an example, a possible implementation method can be as follows:

[0045] message ACPMessage{

[0046] MsgType msgType = 1;

[0047] Destination destination = 2;

[0048] string msg = 3;

[0049] map<string, string> params = 4;

[0050] }

[0051] Among them, ACP in the above code is the full name of AISpeechService Communication Protobuf, which is used to indicate the message protocol for communication between the custom voice framework module and the voice service module based on Protobuf in the present invention. In the ACP protocol, multiple message types MsgType of message data and the controlled device Destination are customized. MsgType indicates the source of the data, and Destination indicates the identifier of the controlled device. When a new voice command needs to be added, only MsgType and Destination need to be extended, and the transmitted data content is only the append of the binary stream.

[0052] In a possible implementation, in the ACP protocol, it can be defined that when the source of the message data is the target voice engine, the message type is the control type. Based on this, the voice framework module can adopt a preset message protocol. When the source of the semantic data is the target voice engine, determine that the message type of the semantic data is the control type, and encapsulate the semantic data and the control type into a data packet in the target data format to obtain a control instruction.

[0053] Furthermore, the voice framework module can send the control instruction to the voice service module in the way of Socket communication.

[0054] Among them, the voice framework module can specifically use Unix Domain Socket for inter-process communication. Unix Domain Socket is also called Inter Process Communication Socket (IPCSocket), which is used to implement inter-process communication on the same host. It does not need to go through the network protocol stack, does not need to pack and unpack, calculate checksums, maintain sequence numbers for responses, etc., but only copies the data from one process to another process.

[0055] The voice service module is used to control the vehicle to perform corresponding operations according to the received control instruction.

[0056] In a possible implementation, the voice service module is specifically configured to control the vehicle to perform corresponding operations according to the control instruction when it is determined that the control instruction includes a message type of a control type.

[0057] In this embodiment, the voice control system of the vehicle includes a target voice engine, a voice framework module, and a voice service module; the target voice engine is configured to obtain a voice instruction input by a user, process the voice instruction to obtain semantic data corresponding to the voice instruction, and send the semantic data to the voice framework module; the voice framework module is configured to convert the semantic data from an initial data format to a target data format by using a preset message protocol to obtain a control instruction, and send the control instruction to the voice service module by using a socket communication method. The initial data format corresponds to the target voice engine; the voice service module is configured to control the vehicle to perform corresponding operations according to the received control instruction. Since the types of the target voice engines are different, the initial data formats are also different, and the communication methods in different platforms are also different. In this embodiment, the control instruction in the target data format customized by the preset message protocol is transmitted by a unified socket communication method, which can realize cross-platform deployment of the voice control system of the vehicle and can shield the initial data formats corresponding to different types of target voice engines, thereby improving the compatibility and scalability of the voice control system of the vehicle.

[0058] Optionally, the control instruction further includes an identified controlled device; the voice service module is specifically configured to call an interface corresponding to the identified controlled device to control the device corresponding to the identified controlled device in the vehicle to perform an operation corresponding to the semantic data.

[0059] It can be understood that the voice service module can directly call the interface corresponding to the identified controlled device by using an interface call method, so as to control the device corresponding to the identified controlled device in the vehicle to perform an operation corresponding to the semantic data.

[0060] Optionally, after the voice service module calls the interface corresponding to the identified controlled device to control the device corresponding to the identified controlled device in the vehicle to perform an operation corresponding to the semantic data, the voice service module is further configured to obtain a function return value corresponding to the operation, and when the source of the function return value is the device corresponding to the identified controlled device, determine that the message type of the function return value is a feedback type, encapsulate the function return value and the feedback type into a feedback data packet in the target data format, and send the feedback data packet to the voice framework module. The function return value is used to indicate the execution situation of the operation; the voice framework module is further configured to receive and store the feedback data packet.

[0061] It can be understood that in the ACP protocol, it can be defined that when the source of the message data is the device corresponding to any identified controlled device, the message type is a feedback type.

[0062] Specifically, the voice service module is further configured to obtain the function return value corresponding to the operation, and when the source of the function return value is the device corresponding to the controlled device identifier, determine that the message type of the function return value is the feedback type, encapsulate the function return value and the feedback type into a feedback data packet in the target data format, and send the feedback data packet to the voice framework module, where the function return value is used to indicate the execution situation of the operation.

[0063] Further, the voice framework module is further configured to receive and store the feedback data packet.

[0064] In this embodiment, the function return value used to indicate the execution situation of the operation is also transmitted using a preset message protocol, so that the user can accurately and conveniently know the execution situation of the voice command.

[0065] Optionally, the voice control system of the vehicle further includes a target application. Before the target voice engine obtains the voice command input by the user, the target application is configured to obtain a wake-up command and send the wake-up command to the voice service module. The wake-up command is used to indicate activating the target voice engine; the voice service module is configured to determine that the message type of the wake-up command is the event type when the source of the wake-up command is the target application, encapsulate the wake-up command and the event type into an activation data packet in the target data format, and send the activation data packet to the voice framework module; the voice framework module is configured to activate the target voice engine according to the received activation data packet.

[0066] It can be understood that in the ACP protocol, it can be defined that when the source of the message data is the target application, the message type is the event type.

[0067] Specifically, before the target voice engine obtains the voice command input by the user, the target application is configured to obtain a wake-up command and send the wake-up command to the voice service module. The wake-up command is used to indicate activating the target voice engine; the voice service module is configured to determine that the message type of the wake-up command is the event type when the source of the wake-up command is the target application, encapsulate the wake-up command and the event type into an activation data packet in the target data format, and send the activation data packet to the voice framework module; the voice framework module is configured to activate the target voice engine according to the received activation data packet.

[0068] Of course, the voice control system of the vehicle provided in the embodiment of the present invention includes but is not limited to the above modules.

[0069] Another embodiment of the present invention further provides a vehicle voice control method, which is applied to the vehicle voice control system in the above embodiment. The method includes:

[0070] The target voice engine obtains the voice command input by the user, processes the voice command to obtain the semantic data corresponding to the voice command, and sends the semantic data to the voice framework module;

[0071] The voice framework module uses a preset message protocol to convert the semantic data from the initial data format to the target data format to obtain a control command, and sends the control command to the voice service module by means of socket communication. The initial data format corresponds to the target voice engine;

[0072] The voice service module controls the vehicle to perform corresponding operations according to the received control command.

[0073] Optionally, the preset message protocol is Protocol Buffers.

[0074] Optionally, the voice framework module uses a preset message protocol to convert the semantic data from the initial data format to the target data format to obtain a control command, specifically including: when the source of the semantic data is the target voice engine, the voice framework module determines that the message type of the semantic data is the control type by using the preset message protocol, and encapsulates the semantic data and the control type into a data packet in the target data format to obtain a control command; the voice service module controls the vehicle to perform corresponding operations according to the received control command, specifically including: when the voice service module determines that the message type of the control command includes the control type, it controls the vehicle to perform corresponding operations according to the control command.

[0075] Optionally, the control command also includes the controlled device identifier; the voice service module controls the vehicle to perform corresponding operations according to the received control command, specifically including: the voice service module calls the interface corresponding to the controlled device identifier to control the device corresponding to the controlled device identifier in the vehicle to perform the operation corresponding to the semantic data.

[0076] Optionally, after the voice service module calls the interface corresponding to the controlled device identifier to control the device corresponding to the controlled device identifier in the vehicle to perform the operation corresponding to the semantic data, the voice control method further includes: the voice service module obtains the function return value corresponding to the operation, and when the source of the function return value is the device corresponding to the controlled device identifier, determines that the message type of the function return value is the feedback type, encapsulates the function return value and the feedback type into a feedback data packet in the target data format, and sends the feedback data packet to the voice framework module. The function return value is used to indicate the execution situation of the operation; the voice framework module receives and stores the feedback data packet.

[0077] Optionally, the voice control system of the vehicle further includes a target application. Before the target voice engine obtains the voice command input by the user, the voice control method further includes: the target application obtains a wake-up command and sends the wake-up command to the voice service module. The wake-up command is used to indicate the activation of the target voice engine; when the source of the wake-up command is the target application, the voice service module determines that the message type of the wake-up command is an event type, encapsulates the wake-up command and the event type into an activation data packet in a target data format, and sends the activation data packet to the voice framework module; the voice framework module activates the target voice engine according to the received activation data packet.

[0078] The voice control method of the vehicle provided by the embodiments of the present invention is applied to the voice control system of the vehicle in the above embodiments, so the same effects as those of the above voice control system of the vehicle can be achieved.

[0079] Another embodiment of the present invention further provides a vehicle, which includes: a processor and a memory; the memory is used to store computer program code, and the computer program code includes computer instructions; when the processor executes the computer instructions, the vehicle executes the voice control method of the vehicle as shown in the above method embodiments.

[0080] Another embodiment of the present invention further provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions run on the vehicle, the vehicle executes the voice control method of the vehicle as shown in the above method embodiments.

[0081] Another embodiment of the present invention further provides a computer program product, which includes computer instructions. When the computer instructions run on the vehicle, the vehicle executes the voice control method of the vehicle as shown in the above method embodiments.

[0082] As described above, the above are only the specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A voice control system for a vehicle, characterized in that, The voice control system includes a target voice engine, a voice framework module and a voice service module; The target speech engine is used to obtain the speech instruction input by the user, process the speech instruction, obtain the semantic data corresponding to the speech instruction, and send the semantic data to the speech framework module; different types of target speech engines use different data formats when sending semantic data; The speech framework module is used to convert the semantic data from an initial data format to a target data format using a preset message protocol, obtain a control instruction, and send the control instruction to the speech service module using a socket communication method, wherein the initial data format corresponds to the target speech engine; the speech framework module is adapted to interfaces corresponding to a plurality of different types of speech engines; The preset message protocol defines a target data format for converting semantic data in a plurality of initial data formats sent by different types of target speech engines into control instructions in the same target data format; The voice service module is used to control the vehicle to perform corresponding operations according to the received control instructions.

2. The voice control system of a vehicle according to claim 1, wherein, The preset message protocol is a protocol buffer.

3. The vehicle voice control system according to claim 1 or 2, characterized in that: The voice framework module is specifically used to adopt the preset message protocol, when the source of the semantic data is the target voice engine, determine that the message type of the semantic data is a control type, and encapsulate the semantic data and the control type into a data packet in the target data format to obtain the control instruction; The voice service module is specifically used to control the vehicle to perform a corresponding operation according to the control instruction when it is determined that the control instruction includes the message type of the control type.

4. The voice control system of a vehicle according to claim 1 or 2, characterized in that, The control instruction also includes the controlled device identification; The voice service module is specifically used to call the interface corresponding to the controlled device identifier to control the device corresponding to the controlled device identifier in the vehicle to perform the operation corresponding to the semantic data.

5. The voice control system of a vehicle according to claim 4, wherein After the voice service module calls the interface corresponding to the controlled device identifier to control the device corresponding to the controlled device identifier in the vehicle to perform the operation corresponding to the semantic data, The voice service module is further used to obtain a function return value corresponding to the operation, and when the source of the function return value is the device corresponding to the controlled device identifier, determine that the message type of the function return value is a feedback type, encapsulate the function return value and the feedback type into a feedback data packet in the target data format, and send the feedback data packet to the voice framework module, wherein the function return value is used to indicate the execution status of the operation; The voice framework module is also used to receive and store the feedback data packet.

6. The voice control system of a vehicle according to claim 1 or 2, characterized in that, The vehicle voice control system further includes a target application program. Before the target voice engine acquires the voice command input by the user, The target application is used to obtain a wake-up instruction and send the wake-up instruction to the voice service module, wherein the wake-up instruction is used to instruct to activate the target voice engine; The voice service module is configured to, when the source of the wake-up instruction is the target application, determine that the message type of the wake-up instruction is an event type, encapsulate the wake-up instruction and the event type into an activation data packet in the target data format, and send the activation data packet to the voice framework module; The voice framework module is configured to activate the target voice engine according to the received activation data packet.

7. A voice control method for a vehicle, characterized in that, Applied to the voice control system of a vehicle as described in any one of claims 1-6, comprising: The target voice engine obtains a voice instruction input by a user, processes the voice instruction to obtain semantic data corresponding to the voice instruction, and sends the semantic data to the voice framework module; different types of target voice engines use different data formats when sending semantic data; The voice framework module uses a preset message protocol to convert the semantic data from the initial data format to the target data format to obtain a control instruction, and sends the control instruction to the voice service module in a socket communication manner. The initial data format corresponds to the target voice engine; the voice framework module adapts interfaces corresponding to multiple different types of voice engines; the target data format is defined customarily in the preset message protocol for converting semantic data in multiple initial data formats sent by different types of target voice engines into control instructions in the same target data format; The voice service module controls the vehicle to perform corresponding operations according to the received control instruction.

8. The voice control method for a vehicle according to claim 7, wherein, The preset message protocol is Protocol Buffers.

9. A vehicle, characterized in that, The vehicle includes: a processor and a memory; the memory is used for storing computer program code, and the computer program code includes computer instructions; when the processor executes the computer instructions, the vehicle executes the voice control method of the vehicle as described in any one of claims 7 or 8.

10. A computer-readable storage medium, characterized in that, Including computer instructions, when the computer instructions run on the vehicle, the vehicle is caused to execute the voice control method of the vehicle as described in claim 7 or 8.

Images