Voice control device, voice control method, and vehicle

Abstract

The application provides a voice control device, a voice control method and a vehicle. The voice control device comprises a control and forwarding module configured to send a real control instruction according to a received covert instruction when a wake-up source signal is triggered; and an execution module connected with the control and forwarding module and configured to control a vehicle machine to perform a corresponding action according to the real control instruction. The application sends the real control instruction corresponding to the covert instruction through the control and forwarding module when the wake-up source signal is triggered, and controls the vehicle machine to perform the corresponding action according to the real control instruction through the execution module, so as to realize the low-cost sending of the real control instruction corresponding to the covert instruction, and enable the user to realize the real intention through the wake-up source and the covert instruction in a scene where it is not suitable or inconvenient to display the voice to control the vehicle machine to realize the real intention, improve the flexibility and environmental applicability of the voice control, and accurately execute the hidden demand in the user voice.

Description

Technical Field

[0001] This invention relates to the field of vehicle technology, and in particular to a voice control device, method, and vehicle. Background Technology

[0002] In related technologies, vehicle voice control is usually based on ideographic commands that have the same meaning as the actual commands, or on deep learning algorithms to identify the user's intent in the voice and then execute the corresponding action.

[0003] However, the aforementioned voice control methods based on ideographic commands are not flexible enough and can only be applied to environments where users can easily issue ideographic commands. Voice control methods based on deep learning algorithms are costly, and after training, they can only meet general voice needs and a few specialized needs, failing to accurately recognize the user's "implied meaning" and lacking the ability to recognize non-specific information. Summary of the Invention The present invention aims to solve at least one of the technical problems existing in the prior art.

[0004] Therefore, one object of the present invention is to provide a voice control device that improves the flexibility and environmental adaptability of voice control, can accurately identify and execute hidden needs in user voice, and is low in cost.

[0005] Therefore, the second objective of this invention is to provide a voice control method.

[0006] Therefore, a third objective of the present invention is to provide a vehicle.

[0007] To achieve the above objectives, an embodiment of the first aspect of the present invention provides a voice control device, comprising: a control and forwarding module, configured to issue a real control command based on a received hidden command when a wake-up source signal is triggered, thereby enabling the identification and conversion of the hidden command into a real control command at low cost without relying on intelligent models such as deep learning, allowing users to achieve their true intentions through the wake-up source and the hidden command in scenarios where it is unsuitable or inconvenient to achieve their true intentions through voice control of the vehicle system; and an execution module, connected to the control and forwarding module, configured to control the vehicle system to perform corresponding actions according to the real control command, thereby improving the flexibility and environmental applicability of voice control and accurately executing the hidden needs in the user's voice.

[0008] According to an embodiment of the present invention, the voice control device, based on a control forwarding module and an execution module and their connection relationship, issues a real control command corresponding to the hidden command when the wake-up source signal is triggered, based on the mapping relationship between the wake-up source, the hidden command, and the real control command. This achieves low-cost issuance of real control commands corresponding to the hidden command without relying on intelligent models such as deep learning. This allows users to achieve their true intentions through the wake-up source and the hidden command in scenarios where it is unsuitable or inconvenient to use voice control of the vehicle system. The execution module then controls the vehicle system to perform corresponding actions according to the real control command, thereby improving the flexibility and environmental applicability of voice control and accurately executing the hidden needs in the user's voice.

[0009] In some embodiments, the instruction management module is configured with a mapping relationship between the wake-up source signal, the covert instruction, and the real control instruction. When the wake-up source signal is triggered, it issues the real control instruction based on the covert instruction. This allows for accurate and low-cost identification of the user's hidden needs through the mapping relationship between the wake-up source signal, the covert instruction, and the real control instruction, and their conversion into corresponding instructions. The instruction distribution module, connected to the instruction management module, is configured to issue the real control instruction according to its distribution path upon receiving it. This enables the issuance of real instructions through multiple channels, improving the accuracy and reliability of voice control.

[0010] In some embodiments, the instruction management module includes an instruction management submodule, which sets a single correspondence mapping relationship between the wake-up source signal, the covert instruction, and the real control instruction, so as to achieve low-cost association of the wake-up source, covert instruction, and real control instruction, laying the foundation for accurately identifying hidden needs from user voice and converting them into real control instructions.

[0011] In some embodiments, the instruction management module includes a combined instruction management submodule, which is configured with a mapping relationship between at least one wake-up source signal, at least one covert instruction, and the real control instruction, so as to achieve more complex instruction control and better meet the user's personalized voice control needs.

[0012] In some embodiments, the control and forwarding module further includes an identity entry submodule, used to perform identity verification based on the voiceprint signal of the wake-up source signal when the wake-up source signal is received, so as to provide safe and convenient personalized voice control services for more vehicle users.

[0013] In some embodiments, the control and forwarding module further includes a wake-up source submodule, which includes wake-up source information set according to execution priority, so as to enable the vehicle to respond to high-priority voice commands in a timely manner.

[0014] In some embodiments, the control and forwarding module further includes a visual interaction submodule, which is connected to the instruction management module and the execution module respectively, for receiving user operation information, setting instruction management, setting the execution action of the execution module, and setting identity authorization, so as to improve the convenience of users using the voice control function.

[0015] In some embodiments, the voice control device further includes a feedback module connected to the execution module, used to issue feedback information when the execution module performs a corresponding action, so as to provide different feedback information according to different user scenarios.

[0016] To achieve the above objectives, a second aspect of the present invention provides a voice control method, comprising: issuing a real control command based on a received covert instruction when a wake-up source signal is triggered; and controlling the vehicle system to perform corresponding actions based on the real control command.

[0017] According to the voice control method of this invention, when a wake-up source signal is triggered, a real control command corresponding to the hidden command is issued based on the mapping relationship between the wake-up source, the hidden command, and the real control command. This achieves low-cost issuance of real control commands corresponding to the hidden command without relying on intelligent models such as deep learning. This allows users to achieve their true intentions through the wake-up source and the hidden command in scenarios where it is unsuitable or inconvenient to use voice control of the vehicle system. The real control command then controls the vehicle system to perform corresponding actions, thereby improving the flexibility and environmental applicability of voice control and accurately executing the hidden needs expressed in the user's voice.

[0018] To achieve the above objectives, a third aspect of the present invention provides a vehicle including a voice control device as described in any of the above embodiments.

[0019] According to an embodiment of the present invention, in a vehicle based on the control forwarding module and execution module in the aforementioned voice control device, and their connection relationship, when the wake-up source signal is triggered, the control and forwarding module issues a real control command corresponding to the hidden command based on the mapping relationship between the wake-up source, the hidden command, and the real control command. This achieves low-cost issuance of real control commands corresponding to the hidden command without relying on intelligent models such as deep learning. This allows users to achieve their true intentions through the wake-up source and the hidden command in scenarios where it is unsuitable or inconvenient to use voice control of the vehicle system. The execution module then controls the vehicle system to perform corresponding actions according to the real control command, thereby improving the flexibility and environmental applicability of voice control and accurately executing the hidden needs in the user's voice.

[0020] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0021] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1 This is a structural block diagram of a voice control device according to an embodiment of the present invention; Figure 2 This is a system block diagram of a voice control device according to an embodiment of the present invention; Figure 3 This is a structural block diagram of a control and forwarding module according to an embodiment of the present invention; Figure 4 This is a structural block diagram of a feedback module according to an embodiment of the present invention; Figure 5 This is a flowchart of a voice control method according to an embodiment of the present invention; Figure 6 This is a block diagram of an instruction mapping structure according to an embodiment of the present invention; Figure 7 This is a structural block diagram of a vehicle according to an embodiment of the present invention.

[0022] Figure label: 1-Voice control device; 2-Control and forwarding module; 3-Execution module; 4-Function Settings Module; 5-Wake-up Source Module; 6-Covered Command Relationship Management Module; 7-Combined Covered Command Management Module; 8-Identity Entry Module; 9-Door / Window Module; 10-SOS Module; 11-Software Application Module; 12-In-Vehicle Lighting / Audio-Visual Module; 13-Other Execution Modules; 14-Command Distribution Module; 15-Bus Message Module; 16-Internal Communication Module; 17-External Communication Module; 18-Feedback Module; 19-Steering Wheel Module; 20-Voice Module; 21-Surface Command Execution Module; 22-Other Feedback Modules; 23-Visual Interaction Module; 24-Sound Pickup and Monitoring Module; 25-Owner / Driver / Passenger Module; 30 - Command Management Module; 31 - Command Management Submodule; 32 - Combined Command Management Submodule; 33 - Identity Entry Submodule; 34 - Wake-up Source Submodule; 35 - Visual Interaction Submodule; 40 - Hidden command module; 41 - Real command module; 42 - Vehicle-mounted system action module; 43 - Command mapping structure module; 107 - Vehicles. Detailed Implementation The embodiments described with reference to the accompanying drawings are exemplary, and the embodiments of the present invention are described in detail below.

[0023] Language is one of the successful representatives of human civilization and an important tool for transmitting information. Regarding the development of intelligent voice control in vehicles, based on the complexity of commands, it can be roughly divided into short and clear instructions and complex, continuous instructions. The former mainly relies on speech recognition, while the latter's mainstream solutions utilize Natural Language Processing (NLP) to use models and algorithms to process dialogue and speech encoding / decoding. Both methods are intuitive and positive forms of voice control.

[0024] However, referring to natural language dialogue, human communication is actually full of "implied meanings", "codes" and "memes". The language itself often does not express or expect to achieve the same result as its surface meaning. In fact, combined with the special context of past human communication, it can form special connections between seemingly unrelated things.

[0025] Therefore, it is crucial for the in-vehicle infotainment system to be able to "understand the meaning behind the words" and execute actions that convey the deeper meaning of user commands, which is essential for the user experience.

[0026] In related technologies, for example, all in-vehicle voice control commands are ideographic commands with the same meaning as the actual commands. Even if there are "hidden commands," they are based on the operating system or vehicle architecture to realize other content related to the command. For example, the "emergency help" command can trigger SOS (International Distress Signal) linkage, automatically dialing preset contacts and sending the vehicle's real-time location. Alternatively, when the in-vehicle system executes a voice command, it can extend the related actions based on the command.

[0027] However, none of the above voice control methods can be linked with any completely unrelated function, making them unsuitable for various extreme situations in the in-car environment. For example, they are not suitable or convenient to use voice control to achieve real intentions. They do not take into account the psychology of the driver or passengers and lack a certain degree of personalized customization in terms of human-machine interaction.

[0028] For example, intelligent voice is developing rapidly. With the development of deep learning, the accuracy of speech recognition has improved, evolving from template-based isolated word recognition to continuous word recognition based on statistical models. Natural language processing has also significantly increased its ability to process text information and recognize intent. Ecosystem integration and various multi-turn interactive language models provide users with a more intelligent experience.

[0029] However, the aforementioned deep learning-based voice control methods all rely on algorithm optimization and model deployment. If the model is too large, cloud training and data processing need to be designed, resulting in high development and maintenance costs. Language models use massive amounts of data to simulate interaction. After training, the model conforms to the thinking logic of most people and a few specialized logics, lacking flexibility and unable to accurately identify the "implied meaning" of the command issuer. With the development of intelligent tools, the tool attribute is still the primary attribute, and the flexibility and personalized services are relatively low.

[0030] Therefore, the voice control device of this invention, based on the control forwarding module and the execution module and their connection relationship, issues a real control command corresponding to the hidden command when the wake-up source signal is triggered, according to the mapping relationship between the wake-up source, the hidden command, and the real control command. This achieves low-cost issuance of real control commands corresponding to hidden commands without relying on intelligent models such as deep learning. This allows users to achieve their true intentions through the wake-up source and hidden commands in scenarios where it is unsuitable or inconvenient to use voice control of the vehicle system. The execution module then controls the vehicle system to perform corresponding actions based on the real control commands, thereby improving the flexibility and environmental applicability of voice control and accurately executing the hidden needs in the user's voice.

[0031] The following is combined with Figure 1-4 A voice control device according to an embodiment of the present invention is described. For example... Figure 1 The diagram shown is a structural block diagram of a voice control device according to an embodiment of the present invention. The voice control device 1 of this embodiment includes at least 2-a control and forwarding module and 3-an execution module.

[0032] Among them, the 2-control and forwarding module is used to issue real control commands based on the received covert instructions when the wake-up source signal is triggered, specifically: like Figure 2The diagram shows a system block diagram of a voice control device according to an embodiment of the present invention. The 2-control and forwarding module is generally handled by the multimedia host, mainly including the function settings of the concealed command voice system, specific command distribution, and visual human-computer interaction with the user. The 4-function setting module is used to manage the overall wake-up chain, wake-up commands, wake-up mapping relationships, and identity authentication and recording. Within the 4-function setting module, there is a 5-wake-up source module. The monitoring does not involve real-time monitoring of all in-vehicle voices, but rather monitoring specific wake-up sources. Upon detecting a wake-up source, subsequent command monitoring is triggered. Specific wake-up sources can be set in the wake-up source module. The 24-voice pickup and monitoring module is used for voice pickup and monitoring inside the cabin, for real-time monitoring of wake-up sources and receiving subsequent voice commands. Concealed commands are special voice commands that hide other commands that need to be executed. They can be input by the user in advance. The language and corresponding actual function are a shared "secret" between the concealed command mapping relationship setter and the vehicle's execution end. The wake-up source signal is the signal triggered upon receiving a wake-up source. When the wake-up source signal is triggered, the 2-control and forwarding module issues the real control command based on the received hidden command. For example, the wake-up source is set in the 5-wake-up source module, and the 24-voice pickup and monitoring module monitors the wake-up source and receives subsequent voice commands in real time. After the wake-up source is detected, the wake-up source signal is triggered and subsequent voice commands are received. The 2-control and forwarding module issues the real control command after receiving the hidden command in the voice command. This achieves the recognition and conversion of hidden commands into real control commands without relying on intelligent models such as deep learning, and at low cost. This allows users to achieve their real intentions through the wake-up source and hidden commands in scenarios where it is not suitable or convenient to control the vehicle system through voice display.

[0033] 3-Execution Module, connected to 2-Control and Forwarding Module, is used to control the vehicle's infotainment system to perform corresponding actions based on actual control commands. The 3-Execution Module is the specific execution module for hidden commands, including the in-vehicle ECU (Electronic Control Unit) controller, software application functions, services, audio-visual systems, etc. The ECU is one of several key components in a car, responsible for controlling the vehicle's driving status and implementing various functions. For example, such as... Figure 2 As shown, the 3-execution module may include: 9- The door / window module, as an example of an execution module, specifically represents the ECU controller that interacts via the vehicle bus; 10- The SOS module, as an example of an execution module, specifically represents the function of interacting with the outside world through the collaboration of multiple controllers. SOS can be an in-vehicle self-help rescue system, an emergency system that quickly seeks rescue assistance when the vehicle malfunctions, is involved in an accident, or encounters danger or emergencies; 11- The software application module, as an example of an execution module, specifically represents the function of interacting with software applications through internal communication; 12- The in-vehicle lighting / audio-visual module, as an example of an execution module, specifically represents a system composed of a set of controllers of the same type; 13- The remaining execution modules are the other execution modules supported by the vehicle's infotainment system. 3- The execution module connects to 2- The control and forwarding module. Based on the various sub-modules in 3- The execution module, upon receiving real control commands, controls the vehicle's infotainment system to perform corresponding actions to fulfill the user's true intentions, such as making a rescue call, thereby improving the flexibility and environmental adaptability of voice control and accurately executing the hidden needs in the user's voice.

[0034] According to embodiments of the present invention, the voice control device, based on a control forwarding module and an execution module, and their connection relationship, issues a real control command corresponding to the hidden command when the wake-up source signal is triggered, based on the mapping relationship between the wake-up source, the hidden command, and the real control command. This achieves low-cost issuance of real control commands corresponding to the hidden command without relying on intelligent models such as deep learning. This allows users to achieve their true intentions through the wake-up source and the hidden command in scenarios where it is unsuitable or inconvenient to use voice control of the vehicle system. The execution module then controls the vehicle system to perform corresponding actions based on the real control command, thereby improving the flexibility and environmental applicability of voice control and accurately executing the hidden needs expressed in the user's voice.

[0035] In some embodiments, such as Figure 3 The diagram shown is a structural block diagram of the control and forwarding module according to an embodiment of the present invention. The 30-instruction management module has a mapping relationship between wake-up source signals, covert instructions, and real control instructions, and is used to issue real control instructions according to the covert instructions when the wake-up source signal is triggered; the 14-instruction distribution module is connected to the 30-instruction management module and is used to issue real control instructions according to the actual control instruction's distribution path when receiving real control instructions.

[0036] In an embodiment, such as Figure 2 and Figure 3As shown, the 30-instruction management module is used for single-cycle instruction management and / or multi-round or multi-segment trigger instruction management. It has a mapping relationship between wake-up source signals, covert instructions, and real control instructions. When the wake-up source signal is triggered, based on the mapping relationship, the real control instruction is issued according to the covert instruction. This enables accurate and low-cost identification of the user's hidden needs through the mapping relationship between the wake-up source signal, covert instructions, and real control instructions, and converts them into corresponding instructions.

[0037] After the 2-Control and Forwarding module receives the concealed command and parses it through the mapping relationship to obtain the real command, the 14-Command Distribution Module distributes the real command according to the actual control command's distribution path, transmitting it to the final receiving end in multiple ways. The 14-Command Distribution Module includes, but is not limited to: the 15-Bus Message Module, which distributes commands through in-vehicle bus message interaction; the 16-Internal Communication Module, which distributes commands through non-bus-based methods within the cockpit, such as inter-chip internal bus communication and wireless communication; and the 17-External Communication Module, which distributes commands through satellite communication or other methods that allow communication with the outside world. Through the 14-Command Distribution Module and its connections, the real commands are distributed through multiple channels, improving the accuracy and reliability of voice control. In some embodiments, such as Figure 3 As shown, the 30-instruction management module includes: the 31-instruction management sub-module, which has a single mapping relationship between wake-up source signals, covert instructions, and real control instructions.

[0038] In an embodiment, such as Figure 2 and Figure 3 As shown, the 31-command management submodule, such as the 6-hidden command relationship management module, is used for single command management. It is a set of mapping relationships, including surface commands and their hidden commands. When setting up, the car owner needs to specify the command execution priority. The mapping relationship also includes a single corresponding mapping relationship between wake-up source signals, hidden commands, and real control commands, so as to achieve low-cost association of wake-up sources, hidden commands, and real control commands, laying the foundation for accurately identifying hidden needs from user voice and converting them into real control commands.

[0039] In some embodiments, such as Figure 3 As shown, the 30-instruction management module includes: the 32-combined instruction management submodule, which is configured with a mapping relationship between at least one wake-up source signal, at least one covert instruction, and a real control instruction.

[0040] In an embodiment, such as Figure 2 and Figure 3As shown, the 32-combination instruction management submodule has a mapping relationship between at least one wake-up source signal, at least one hidden instruction, and real control instructions. It is used for multi-round or multi-segment triggering instruction management and has a more complex mapping relationship, including multiple surface instructions and multiple hidden instructions, in order to achieve more complex instruction control and better meet the user's personalized voice control needs.

[0041] In some embodiments, such as Figure 3 As shown, the 2-control and forwarding module also includes: 33-identity entry submodule, which is used to perform identity authentication based on the voiceprint signal of the wake-up source signal when the wake-up source signal is received.

[0042] In an embodiment, such as Figure 2 and Figure 3 As shown, the 33-identity entry submodule, such as the 8-identity entry module, is operated by the car owner to enter their voice. The role includes the car owner or authorized personnel, which is used for role authentication on the vehicle's system. When a wake-up source signal is received, the identity and permissions are determined based on the voiceprint signal of the wake-up source signal. The authentication method can be determined by voiceprint, so as to provide safe and convenient personalized voice control services for more people using the vehicle.

[0043] In some embodiments, such as Figure 2 As shown, the 2-control and forwarding module also includes: 34-wake-up source submodule, which includes wake-up source information set according to execution priority.

[0044] In this embodiment, the user sets the priority of the wake-up source information in the 34-wake-up source submodule according to their own usage needs, so that the vehicle can respond to high-priority voice commands in a timely manner.

[0045] In some embodiments, such as Figure 2 As shown, the 2-control and forwarding module also includes: 35-visual interaction sub-module, which is connected to the 14-instruction management module and the 3-execution module respectively, and is used to receive user operation information, perform instruction management settings, execution module execution action settings and identity authorization settings.

[0046] In an embodiment, such as Figure 2 and Figure 3 As shown, the 35-visual interaction submodule, such as the 23-visual interaction module, can provide a user-friendly UI for receiving user operation information, setting command management, setting execution actions of the execution module, and setting identity authorization. Specifically, for example, the car owner can set the mapping relationship, the execution actions of each controller in the mapping relationship, function authorization, identity entry, and other interactions to improve the convenience of the user's voice control function.

[0047] In some embodiments, such as Figure 4 The diagram shown is a structural block diagram of a feedback module according to an embodiment of the present invention. The voice control device further includes: an 18-feedback module, connected to the 3-execution module, used to issue feedback information when the 3-execution module performs a corresponding action.

[0048] In an embodiment, such as Figure 2 and Figure 3 As shown, 18-feedback modules, such as the feedback module for hidden commands, are used to provide feedback information indicating that a command has been issued, including but not limited to: 19-steering wheel module, as one example of a feedback module, is for scenarios where the command issuer is the driver, and can provide feedback on the issuance of the command through steering wheel vibration, etc.; 20-voice module, as one example of a feedback module, is for scenarios involving voice interaction, directly indicating that the command has been issued through the vehicle's voice system or a prompt tone; 21-surface command execution module, as one example of a feedback module, is for scenarios where the hidden command is hidden under a surface command, and the actual command directly corresponding to its semantics is executed, indicating that the hidden command has also been issued; 22-other feedback modules are the remaining feedback modules supported by the vehicle's system. The 18-feedback modules enable the provision of different feedback information based on different user scenarios. For example, for the execution feedback of a hidden command, the corresponding actual command will be executed directly.

[0049] According to embodiments of the present invention, the voice control device, based on a control forwarding module and an execution module, and their connection relationship, issues a real control command corresponding to the hidden command when the wake-up source signal is triggered, based on the mapping relationship between the wake-up source, the hidden command, and the real control command. This achieves low-cost issuance of real control commands corresponding to the hidden command without relying on intelligent models such as deep learning. This allows users to achieve their true intentions through the wake-up source and the hidden command in scenarios where it is unsuitable or inconvenient to use voice control of the vehicle system. The execution module then controls the vehicle system to perform corresponding actions based on the real control command, thereby improving the flexibility and environmental applicability of voice control and accurately executing the hidden needs expressed in the user's voice.

[0050] The following is for reference. Figure 5 The voice control method of the present invention is described in an embodiment.

[0051] like Figure 5 The diagram shows a flowchart of a voice control method according to an embodiment of the present invention. The voice control method of this embodiment includes: issuing a real control command based on a received covert instruction when a wake-up source signal is triggered; and controlling the vehicle system to perform corresponding actions according to the real control command. For example, the voice control method includes at least steps S50-S62.

[0052] Step S50: Sound is emitted to trigger the wake-up source.

[0053] Step S51: A voice wake-up source is detected.

[0054] Step S52: Determine voice authentication. If successful, proceed to step S54; otherwise, proceed to step S53.

[0055] Step S53, End.

[0056] Step S54, hidden command matching.

[0057] Step S55, instruction distribution.

[0058] Step S56, emergency call.

[0059] Step S57: Call the police for help.

[0060] Step S58: The exterior lights flash for help.

[0061] Step S59: Start recording in the car.

[0062] Step S60: The steering wheel vibrates.

[0063] Step S61, instruction execution feedback.

[0064] Step S62, End.

[0065] Among them, such as Figure 6 The diagram shown is a block diagram of the instruction mapping structure according to an embodiment of the present invention. A complete set of covert instruction mapping relationships must include the wake-up source in the 5-wake-up source module, 40-covert instruction, 41-real instruction, and 42-vehicle system action. For longer statements, the first two need to be set by the user to match the degree of the statement, and the degree of the statement match must not be less than 80%.

[0066] The wake-up source can be a simple, uncommon noun, a special phrase, or a special statement. The longer the wake-up source statement, the higher the algorithm requirements for the system's monitoring module. 40- Covert instructions are specific covert instructions, spoken directly by the user, and can be special greetings, special commands, etc. 41- Real instructions are parsed by the vehicle-mounted control and forwarding module and mapped to specific command requirements, which can be distributed to specific execution terminals through various methods. 42- Vehicle motion is the action execution terminal after the vehicle-mounted system receives the real instructions, including executing the real instructions and providing feedback actions indicating that the instructions have been issued. For example: The wake-up source is a watermelon, the corresponding covert command is "The weather is nice", the corresponding real command is "call for help 1", and the corresponding vehicle movement is to dial 110 and mute the speaker and / or the steering wheel vibration.

[0067] The wake-up source is a flamingo, the corresponding covert command is "There are often traffic police here", the corresponding real command is "call for help 2", the corresponding vehicle movement is to dial 110 and mute the speaker, and / or, start recording, the in-car camera starts recording, and / or, the steering wheel vibrates / the vehicle's voice says: "Xiao Di also thinks the weather is very good".

[0068] The wake-up source is fear, the corresponding covert command is "I am very timid", the corresponding real command is "the exterior lights are flashing for help", the corresponding vehicle movement is "the exterior lights are flashing for help", and / or, the instrument panel reports a brake malfunction, and the voice prompts that there is a driving risk.

[0069] The wake-up source is "Don't hurt me," the corresponding hidden command is "The car windows are not very flexible," the corresponding real command is "Close the car doors / windows," the corresponding vehicle movement is to close the car windows, but the driver can still operate to open the car doors / windows, and / or, the steering wheel vibrates.

[0070] The wake-up source is Wei Rui, and the corresponding hidden command is that the "open" button here is not working well. The corresponding real command is to close the car door / window. The corresponding vehicle movement is to close the window, and the driver's side button control is also ineffective, and / or the steering wheel vibrates.

[0071] The wake-up source is that there are no traffic lights here. The corresponding hidden command is to turn on the air conditioning to 37 degrees Celsius. No, it is 27 degrees Celsius. The corresponding real command is to turn on the air conditioning to 27 degrees Celsius. And / or, trigger the 37th real command / close the windows. The corresponding vehicle movement is to turn on the air conditioning and adjust it to 27 degrees Celsius. And / or, execute the 37th real command (for example, the 37th command is to close the windows).

[0072] The wake-up source is my premonition that the roads will be very congested today. The corresponding real-world command is that the map displays the road segment in red, the vehicle's movement is simulated by the map application to display road congestion and suggest that it is not advisable to travel, and / or, the steering wheel vibrates.

[0073] How is your driving skill? The corresponding hidden command is "There are no outsiders here." The corresponding real command is "Turn on the recording device." The corresponding vehicle movement is "Turn on the recording device" and / or "Steering wheel vibration."

[0074] The mapping relationship between wake-up source, 40-covert instruction, and 41-real instruction can be one-to-one, one-to-many, or many-to-one, and depends on the execution order from wake-up source to 40-covert instruction to 41-real instruction; 41-real instruction and 42-vehicle motion action are one-to-one, and are the execution order from 41-real instruction to 42-vehicle machine action. Specifically, the wake-up source is first triggered by the owner / driver / passenger's voice. After the sound pickup and monitoring device detects the wake-up source, it performs voice authentication. If authentication fails, the process ends. If authentication is successful, it begins listening for covert commands triggered by the owner's voice. Upon receiving the commands, the control and forwarding module performs command matching. If the commands are in a pre-set mapping relationship, they are distributed to the specific execution module and the feedback module. Taking a distress call scenario as an example, the vehicle's execution end includes ECALL (Emergency Call), flashing exterior lights to call for help, and in-vehicle recording. In particular, for external interactions, subsequent external interactions need to be executed. ECALL is a vehicle alarm system mainly used to automatically or manually trigger an alarm in case of an emergency to quickly contact rescue services. In-vehicle interactions need to provide feedback to the feedback module after the command is executed and notify the user that the command has been issued. The process ends after the user is aware of the instruction.

[0075] It is understood that the voice control method of this invention can be implemented based on the aforementioned voice control device. Users can flexibly configure the links and modules to achieve covert control of the vehicle system via voice. The covert commands generated by this method are more specific and controllable, applicable only to the mapping relationship between the user and the vehicle system. Furthermore, there is no need to deliberately avoid the connection between the "trigger function form" and the "target function," allowing for some correlation. This can result in executing both surface commands and covert commands, or independently executing only real commands. Moreover, it does not perform timing judgments on multiple trigger sources; it listens for covert commands from trigger sources, executes them upon acquisition, and provides feedback to the driver, broadening its application scenarios. The form of the covert commands is user-defined, not conflicting with the direction of intelligent voice control systems, offering strong compatibility and scalability, and perfectly matching user habits. Compared to the slow development and high cost of truly interactive in-vehicle intelligent voice systems, such as language model development, computing power, and deployment resources, it can meet some voice control needs at a low cost. It also makes up for the fact that even the best interactive intelligent voice algorithms still struggle to perfectly match the user's frequency and accurately understand the deeper meaning of language.

[0076] According to the voice control method of this invention, when a wake-up source signal is triggered, a real control command corresponding to the hidden command is issued based on the mapping relationship between the wake-up source, the hidden command, and the real control command. This achieves low-cost issuance of real control commands corresponding to the hidden command without relying on intelligent models such as deep learning. This allows users to achieve their true intentions through the wake-up source and the hidden command in scenarios where it is unsuitable or inconvenient to use voice control of the vehicle system. The real control command then controls the vehicle system to perform corresponding actions, thereby improving the flexibility and environmental applicability of voice control and accurately executing the hidden needs expressed in the user's voice.

[0077] like Figure 7 The diagram shown is a structural block diagram of a vehicle according to an embodiment of the present invention. The vehicle control device 107 of this embodiment includes a voice control device as described in any of the above embodiments.

[0078] According to the 107-vehicle of the present invention, based on the control forwarding module and execution module in the 1-voice control device, and their connection relationship, when the wake-up source signal is triggered, the control and forwarding module issues a real control command corresponding to the hidden command according to the mapping relationship between the wake-up source, the hidden command, and the real control command. This achieves low-cost issuance of real control commands corresponding to the hidden command without relying on intelligent models such as deep learning. This allows users to achieve their true intentions through the wake-up source and the hidden command in scenarios where it is unsuitable or inconvenient to use voice control of the vehicle system. The execution module then controls the vehicle system to perform corresponding actions according to the real control command, thereby improving the flexibility and environmental applicability of voice control and accurately executing the hidden needs in the user's voice.

[0079] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example.

[0080] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A voice control device, characterized in that, include: The control and forwarding module is used to issue real control commands based on the received covert instructions when the wake-up source signal is triggered. The execution module, connected to the control and forwarding module, is used to control the vehicle system to perform corresponding actions according to the actual control commands.

2. The voice control device according to claim 1, characterized in that, The control and forwarding module includes: The instruction management module is configured with a mapping relationship between the wake-up source signal, the covert instruction, and the real control instruction. It is used to issue the real control instruction according to the covert instruction when the wake-up source signal is triggered. The instruction distribution module, connected to the instruction management module, is used to distribute the actual control instruction according to the distribution path of the actual control instruction when it receives the actual control instruction.

3. The voice control device according to claim 2, characterized in that, The instruction management module includes: The instruction management submodule is configured with a single mapping relationship between the wake-up source signal, the covert instruction, and the real control instruction.

4. The voice control device according to claim 2, characterized in that, The instruction management module includes: The combined instruction management submodule is configured with a mapping relationship between at least one of the wake-up source signals, at least one of the covert instructions, and the real control instructions.

5. The voice control device according to claim 1, characterized in that, The control and forwarding module also includes: The identity entry submodule is used to perform identity verification based on the voiceprint signal of the wake-up source signal when the wake-up source signal is received.

6. The voice control device according to claim 1, characterized in that, The control and forwarding module also includes: The wake-up source submodule includes wake-up source information set according to execution priority.

7. The voice control device according to claim 1, characterized in that, The control and forwarding module also includes: The visual interaction submodule is connected to both the instruction management module and the execution module. It is used to receive user operation information, perform instruction management settings, set the execution actions of the execution module, and set identity authorization.

8. The voice control device according to claim 1, characterized in that, The voice control device also includes: The feedback module, connected to the execution module, is used to send feedback information when the execution module performs a corresponding action.

9. A voice control method, characterized in that, include: When the wake-up source signal is triggered, a real control command is issued based on the received covert instruction; The vehicle system is controlled to perform corresponding actions according to the actual control commands.

10. A vehicle, characterized in that, include: The voice control device as described in any one of claims 1-8.

Images