Vehicle-mounted voice instruction control method and system, storage medium and electronic device

Abstract

The present disclosure belongs to the technical field of voice control, and provides a vehicle-mounted voice instruction control method, system, storage medium and electronic device. The method comprises: in response to the execution of a first voice task, within the life cycle range of the first voice task, a second voice instruction is directly acquired without triggering a system wake-up instruction; in response to the acquisition of the second voice instruction, the second voice instruction is associated with a preset voice instruction to generate a first association judgment result; if the first association judgment result meets a preset association condition, a vehicle-mounted function device is controlled to execute a second voice task based on the second voice instruction; in response to the change of the voice task execution state of the vehicle-mounted function device being completed, an end signal is generated and fed back; the end signal is used to stop receiving the second voice instruction and wait for the system wake-up instruction to trigger the reception of the voice instruction again. Under the premise of reducing power consumption and protecting privacy, the task execution state of the voice instruction without a wake-up word is changed.

Description

Technical Field

[0001] This disclosure belongs to the field of voice control technology, and in particular relates to a vehicle-mounted voice command control method, system, storage medium and electronic device. Background Technology

[0002] When using voice control, in-vehicle systems typically employ the following voice control schemes: 1. Always-on listening solution: In-vehicle systems require high power consumption to keep the microphone in continuous recording mode. During conversations between users in the car, unexpected voice command control tasks may be triggered, causing the in-vehicle system to execute voice command control incorrectly, and there is also a risk of user privacy leakage.

[0003] 2. Wake-up Word Trigger Scheme: The in-vehicle system requires a wake-up word to trigger the microphone. When a user's voice command is interrupted, or while the in-vehicle system is performing a voice command control task, the user needs to repeat the wake-up word to issue the voice command again or change the voice command. Therefore, voice control interaction is cumbersome, and during the in-vehicle system's voice control tasks, it is impossible to efficiently change voice command control tasks, potentially leading to dangerous situations.

[0004] If the voice control scheme is set to continuously pick up sound for a period of time after the microphone is woken up, the duration of different voice command control tasks will vary, resulting in the microphone picking up sound for too long or too short a time. This means that the voice control of the vehicle system will have the drawbacks of both of the aforementioned schemes.

[0005] In summary, there is an urgent need for an in-vehicle voice command control method that can reduce power consumption and protect privacy while enabling the change of task execution state of voice commands without the need for a wake word. Summary of the Invention

[0006] To address the aforementioned issues, this disclosure provides an in-vehicle voice command control method, system, storage medium, and electronic device.

[0007] This disclosure is achieved through the following technical solution: In a first aspect, embodiments of this disclosure provide a vehicle-mounted voice command control method. In response to the initiation and execution of a first voice task, within the lifecycle of the first voice task, a second voice command is directly acquired without the need for a system wake-up command. Based on the second voice command, the method controls changes in the task execution state of the vehicle-mounted functional device. The control of changes in the task execution state of the vehicle-mounted functional device includes: In response to the acquisition of the second voice command, the second voice command is correlated with a preset voice command to generate a first correlation judgment result; wherein, If the first correlation judgment result meets the preset correlation conditions, then based on the second voice command, the vehicle-mounted functional device is controlled to execute the second voice task; In response to the completion of the voice task execution status change of the in-vehicle functional device, an end signal is generated and fed back; wherein, The termination signal is used to stop receiving the second voice command and wait for the system wake-up command to trigger the reception of the voice command again.

[0008] Furthermore, The step of responding to the acquisition of the second voice command by performing an association determination between the second voice command and a preset voice command to generate a first association determination result includes at least one of the following methods: Method 1: In response to the acquisition of the second voice command, the second voice command is compared with a preset general voice command to determine its correlation, and a general correlation determination result is generated; Method 2: In response to the acquisition of the second voice command, the second voice command is correlated with the preset specific voice command corresponding to the first voice task, and a specific correlation judgment result is generated; Method 3: If the first correlation judgment result does not meet the preset correlation conditions, cache the second voice command until the task execution status change of the vehicle function device is completed.

[0009] Furthermore, The preset association conditions include: If the general correlation determination result between the second voice command and the preset general voice command is that there is a correlation, then the preset correlation condition is met; If the result of the specific correlation judgment between the second voice command and the preset specific voice command corresponding to the first voice task is that there is a correlation, then the preset correlation condition is met.

[0010] Furthermore, In response to the initiation and execution of the second voice task, within the lifecycle of the second voice task, without the need for the system wake-up command, a third voice command is directly acquired, and the execution state of the in-vehicle functional device is controlled based on the third voice command; the control of the execution state of the in-vehicle functional device includes: In response to the acquisition of the third voice command, the third voice command is correlated with the preset voice command to generate a second correlation judgment result; wherein, If the second correlation judgment result meets the preset correlation condition, then based on the third voice command, the vehicle-mounted functional device is controlled to execute the third voice task; In response to the completion of the voice task execution status change of the in-vehicle functional device, an end signal is generated and fed back; wherein... The termination signal is used to stop receiving the third voice command and wait for the system wake-up command to trigger the reception of the voice command again.

[0011] Furthermore, The lifecycle of a voice task is: from the moment the voice command is received to initiate the execution of the voice task, to the moment the execution status change of the voice task is completed; the generation and feedback of the end signal includes at least one of the following methods: Method 1: The first voice task of the in-vehicle functional device changes from the in progress state to the completed state, the life cycle of the first voice task ends, and the end signal is generated and fed back. Method 2: The in-vehicle functional device changes from performing the first voice task to performing the second voice task, and the life cycle of the first voice task ends, directly generating and feeding back the end signal; Method 3: The second voice task of the in-vehicle functional device changes from the in progress state to the completed state, and the life cycle of both the first voice task and the life cycle of the second voice task ends, generating and feeding back the end signal; Method 4: The in-vehicle functional device changes from performing the second voice task to performing the third voice task. The life cycle of the second voice task ends, and the end signal is directly generated and fed back. Method 5: The third voice task of the in-vehicle functional device changes from the in progress state to the completed state, and the life cycle of the first voice task, the second voice task and the third voice task all end, generating and feeding back the end signal.

[0012] Furthermore, The in-vehicle voice command control method further includes: In response to the acquisition of the system wake-up command, the reception of voice commands is triggered; wherein, the voice commands include a first voice command and a second voice command; In response to the acquisition of the first voice command, the vehicle-mounted functional device corresponding to the first voice command is controlled to execute the first voice task.

[0013] Secondly, based on the same inventive concept, this disclosure also provides an in-vehicle voice command control system for executing any of the aforementioned in-vehicle voice command control methods. The in-vehicle voice command control system responds to the initiation of the first voice task. Within the lifecycle of the first voice task, it directly acquires the second voice command without the need for a system wake-up command, and controls the change of the task execution state of the in-vehicle functional device based on the second voice command. The in-vehicle voice command control system includes at least: a voice command association module and a task status monitoring module. The voice command association module, in response to the acquisition of the second voice command, performs an association judgment between the second voice command and the preset voice command to generate a first association judgment result; wherein, if the first association judgment result meets the preset association condition, the in-vehicle functional device is controlled to execute a second voice task based on the second voice command; The task status monitoring module generates and feeds back an end signal in response to the completion of the voice task execution status change of the in-vehicle functional device; wherein, the end signal is used to stop receiving the second voice command and wait for the system wake-up command to trigger the reception of the voice command again.

[0014] Furthermore, The system also includes: an in-vehicle voice processing module; The in-vehicle voice processing module, in response to the acquisition of the system wake-up command, triggers the reception of voice commands; wherein, the voice commands include a first voice command and a second voice command; The task status monitoring module also responds to the acquisition of the first voice command by controlling the in-vehicle functional device corresponding to the first voice command to execute the first voice task.

[0015] Thirdly, based on the same inventive concept, the present disclosure also provides a computer-readable storage medium storing one or more programs, which, when executed, can realize the aforementioned vehicle voice command control method.

[0016] Fourthly, based on the same inventive concept, embodiments of this disclosure also provide an electronic device, including a processor, a communication interface, the aforementioned computer-readable storage medium, and a communication bus. The processor, communication interface, and computer-readable storage medium communicate with each other via the communication bus. The processor is used to execute a program stored in the aforementioned computer-readable storage medium.

[0017] In the vehicle-mounted voice command control method of this embodiment, starting from the moment the first voice task is executed, a second voice command is directly acquired without the need for a system wake-up command. The second voice command is then subjected to a correlation determination. Based on the correlation determination result, the execution state of the voice task of the vehicle-mounted functional device is changed. When the change in the execution state of the voice task of the vehicle-mounted functional device is completed, an end signal is generated and fed back, and the acquisition of voice commands ceases. By limiting the acquisition of voice commands without a wake-up word to the lifecycle of the voice task executed by the vehicle-mounted functional device, the task execution state of voice commands can be changed without a wake-up word while reducing the overall power consumption of the vehicle system and protecting the privacy of occupants. This enables rapid and accurate response to real-time voice task change commands issued by the user, reducing the possibility of dangerous situations.

[0018] Other features and advantages of this disclosure will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the disclosure. The objects and other advantages of this disclosure may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart of an in-vehicle voice command control method provided in this embodiment of the present disclosure; Figure 2 Flowchart of another vehicle-mounted voice command control method provided in this embodiment of the present disclosure; Figure 3 A flowchart of another vehicle-mounted voice command control method provided in this embodiment of the present disclosure; Figure 4 This is a schematic diagram of an in-vehicle voice command control method provided in an embodiment of the present disclosure; Figure 5 A block diagram of an in-vehicle voice command control system provided in this disclosure embodiment; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0022] Firstly, Figure 1 A flowchart of an in-vehicle voice command control method provided in this disclosure embodiment is shown below. Figure 1 As shown, this disclosure provides a vehicle-mounted voice command control method. Upon triggering a system wake-up command, it begins receiving voice commands and, in response to the acquisition of a first voice command, initiates the execution of a first voice task. During the execution of the first voice task, it maintains a wake-up state and continues to receive voice commands without requiring a system wake-up command. The vehicle-mounted voice command control method specifically includes: S1: In response to the start of the first voice task, within the lifecycle of the first voice task, the second voice command is obtained directly without the need for a system wake-up command.

[0023] Specifically, during the execution of the first voice task, there is a possibility of changing or canceling it. Therefore, it is necessary to directly receive the second voice command without triggering a system wake-up command, and control the change of the task execution status of the in-vehicle functional device based on the second voice command, so as to achieve timely change or cancellation of the first voice task. The lifecycle of the first voice task is: from the moment the first voice command is received to start the execution of the first voice task, to the moment the change of the execution status of the first voice task is completed. The lifecycle of the first voice task corresponds to the time range during which the second voice command is received directly without the need for a system wake-up word; within this time range, the microphone remains in the recording state and can directly receive the user's voice signal and convert it into voice commands.

[0024] It should be noted that the first voice task can be a task performed by an in-vehicle function device that allows voice control. The first voice task can be triggered by the central control screen, central control buttons, etc. When the first voice task is started, the microphone is directly woken up to receive the user's voice signal without the need for a system wake-up command, and the second voice command is directly obtained.

[0025] In this embodiment of the disclosure, controlling the change of the task execution status of the in-vehicle functional device based on the second voice command specifically includes: S2: In response to the acquisition of the second voice command, the second voice command is correlated with the preset voice command to generate a first correlation judgment result.

[0026] Specifically, since the microphone is continuously recording audio at this time, it may receive audio signals unrelated to the current voice task, resulting in a voice command unrelated to the first voice task. After acquiring the second voice command, it is necessary to determine its relevance to the first voice task. Therefore, the second voice command is compared with preset voice commands to generate a first relevance judgment result. Preset voice commands include preset general voice commands and preset specific voice commands. Preset general voice commands include stop, cancel, and turn off; preset specific voice commands are related to the in-vehicle function devices corresponding to the first voice task. For example, the seat massage function has a preset specific voice command: change mode. The first relevance judgment result includes a general relevance judgment result and a specific relevance judgment result.

[0027] S21: If the first correlation judgment result meets the preset correlation conditions, then based on the second voice command, control the vehicle function device to execute the second voice task.

[0028] Specifically, the semantic association between the second voice command and the preset voice command is determined. For example, if the second voice command is "stop," then the second voice command is associated with preset voice commands such as "stop," "cancel," and "close." In this case, the first association determination result between the second voice command and the preset voice command meets the preset association condition. As another example, if the first voice task is "start the seat massage," and a second voice command is obtained during the execution of the seat massage start task, and the second voice command is "change mode," then it is associated with the preset voice command "change mode." In this case, the first association determination result between the second voice command and the preset voice command meets the preset association condition.

[0029] It should be noted that the second voice command and the preset voice command can be in data form, and the correlation judgment can be made in data form; or the user's voice can be recognized, analyzed and understood, and then semantic representation can be generated to determine the second voice command, which is used to make correlation judgment with the preset voice command; the preset voice command can be pre-stored in the form of data or semantic representation, without further specific restrictions, but it is necessary to ensure that the form of the preset voice command and the second voice command are consistent.

[0030] S3: In response to the completion of the voice task execution status change of the in-vehicle function device, generate and feed back an end signal.

[0031] Specifically, the changes in the execution status of voice tasks of in-vehicle functional devices include at least: 1. The first voice task changes from an executing state to a completed state; 2. The first voice task is changed to the second voice task. Both states correspond to the end of the lifecycle of the first voice task. After receiving the feedback end signal, the in-vehicle voice command control system directly stops the microphone from receiving user voice signals and no longer receives second voice commands.

[0032] In the vehicle-mounted voice command control method of this embodiment, from the moment a first voice command is received to initiate the execution of a first voice task, the microphone continuously receives user voice. Without requiring a system wake-up command, a second voice command is directly acquired. The second voice command is then subjected to a correlation determination. Based on the correlation determination result, the execution state of the vehicle-mounted functional device's voice task is changed. When the change in the execution state of the vehicle-mounted functional device's voice task is completed, an end signal is generated and fed back, the microphone stops receiving user voice, and the second voice command is no longer acquired. By limiting the acquisition of voice commands without a wake-up word to the lifecycle of the vehicle-mounted functional device's voice task execution, the system can achieve wake-up word-free changes to the task execution state of voice commands while reducing overall power consumption and protecting the privacy of occupants. This enables rapid and accurate responses to real-time user-issued voice task change commands, reducing the possibility of dangerous situations.

[0033] In some examples, the preset voice commands include preset general voice commands and preset specific voice commands; in response to the acquisition of the second voice command, the second voice command is correlated with the preset voice command to generate a first correlation judgment result, specifically including at least one of the following methods: Method 1: In response to the acquisition of the second voice command, the second voice command is compared with preset general voice commands to determine their correlation, generating a general correlation result. The preset general voice commands include stop, cancel, and close, applicable to all in-vehicle functional devices executing the first voice task. These in-vehicle functional devices include air conditioning, seats, windows, and other in-vehicle comfort equipment. If the general correlation result between the second voice command and the preset general voice commands indicates a correlation, the preset correlation condition is met, and the in-vehicle functional device is controlled to execute the second voice task based on the second voice command. Understandably, the preset general voice commands are pre-set and pre-stored in the in-vehicle voice command control system.

[0034] Method 2: In response to the acquisition of the second voice command, the second voice command is correlated with the preset specific voice command corresponding to the first voice task, generating a specific correlation judgment result. The preset specific voice command corresponds to the in-vehicle function device corresponding to the first voice task. For example, if the in-vehicle function device is a seat and the first voice task is to activate the massage function, the preset specific voice command includes changing the mode; if the in-vehicle function device is an air conditioner and the first voice task is to activate the air conditioner, the preset specific voice commands include raising the temperature and lowering the fan speed. If the specific correlation judgment result between the second voice command and the preset specific voice command corresponding to the first voice task shows a correlation, then the preset correlation condition is met, and based on the second voice command, the in-vehicle function device is controlled to execute the second voice task. Understandably, the preset specific voice commands corresponding to the voice-controlled in-vehicle function devices can be pre-set and pre-stored in the in-vehicle voice command control system.

[0035] Furthermore, during the process of determining the association between the second voice command and the preset voice command, both methods can be executed simultaneously: that is, a general association determination result and a specific association determination result can be generated simultaneously. If either result meets the preset association conditions, the in-vehicle functional device is controlled to execute the second voice task based on the second voice command. Alternatively, a general association determination result can be generated first; if the general association determination result does not meet the preset association conditions, a specific association determination result is then generated; or, a specific association determination result can be generated first; if the specific association determination result does not meet the preset association conditions, a general association determination result is then generated. The specific order of determining the association between the second voice command and the preset general and preset specific voice commands can be pre-configured according to the characteristics of different in-vehicle functional devices.

[0036] Method 3: If the first correlation judgment result does not meet the preset correlation conditions, cache the second voice command until the task execution status change of the in-vehicle function device is completed.

[0037] Specifically, when neither the general correlation judgment result nor the specific correlation judgment result meets the preset correlation conditions, the second voice command is cached. Since the microphone continuously picks up audio within the lifecycle of the first voice task, subsequent second voice commands are processed first. These re-acquired second voice commands are then correlated with the preset voice commands to prevent erroneous or missed second voice commands from the user, ensuring timely execution of the second voice task. Once the task execution status of the in-vehicle function device changes, the second voice command is no longer cached and is cleared. During this process, only the correlation judgment of the second voice command is performed; no other parsing is performed. The timely clearing of the second voice command after the task execution status change effectively protects user conversation privacy during continuous microphone recording.

[0038] Furthermore, when the in-vehicle voice command control system is idle, it can invoke cached second voice commands to interact with the user, asking if the second voice command corresponds to an additional voice task. If the user confirms that the second voice command corresponds to an additional voice task, the additional voice task is placed in the task queue to await execution. Alternatively, it can directly determine whether the cached second voice command corresponds to an additional voice task, and if it is, place it directly in the task queue to await execution. Interaction methods with the user include voice queries and pop-up queries. For example, if the first voice task is to activate the zero-gravity mode of the seat, and the second voice command, which does not meet the preset association conditions, is to play music, the music playback command is cached. When the in-vehicle voice command control system is idle, the user is asked if they want to play music. When the user confirms, it is designated as an additional voice task and placed in the task queue. After the execution status of the first voice task of the in-vehicle function device changes, music playback begins. Alternatively, it can directly determine whether the cached second voice command corresponds to an additional voice task that can be controlled by voice, and if it is, place it directly in the task queue to await execution. Understandably, placing the additional voice task in the task queue and executing it after the execution status of the first voice task of the in-vehicle function device has changed does not affect the timely clearing of the second voice command corresponding to the additional voice task after the execution status of the in-vehicle function device has changed.

[0039] In some examples, Figure 2 A flowchart of another in-vehicle voice command control method provided in this disclosure embodiment is shown below. Figure 2 As shown, if the first correlation judgment result meets the preset correlation conditions, then based on the second voice command, after controlling the in-vehicle functional device to execute the second voice task, it includes: S1': In response to the start of the second voice task, the third voice command is obtained directly within the lifecycle of the second voice task without the need for a system wake-up command.

[0040] Specifically, for some in-vehicle functional devices, there is a need to change or adjust tasks multiple times. Therefore, when the in-vehicle device changes from the first voice task to the second voice task, the end signal is not generated and fed back temporarily, so that the microphone continues to keep picking up sound. Within the life cycle of the second voice task, the third voice command can be obtained directly without the triggering of the system wake-up command.

[0041] Furthermore, the change of task execution status of in-vehicle functional devices based on third-party voice commands specifically includes: S2': In response to the acquisition of the third voice command, the third voice command is compared with the preset voice command to determine the correlation and generate a second correlation result.

[0042] Understandably, the method of determining the correlation between the third voice command and the preset voice command to generate a second correlation result is the same as the method of determining the correlation between the second voice command and the preset voice command to generate a first correlation result, and will not be elaborated here.

[0043] S21': If the second correlation judgment result meets the preset correlation conditions, then based on the third voice command, control the vehicle function device to execute the third voice task.

[0044] Understandably, the second correlation judgment result between the third voice command and the preset voice command here meets the preset correlation condition, which is the same method as the first correlation judgment result between the second voice command and the preset voice command mentioned above. Therefore, it will not be elaborated here.

[0045] It should be noted that the second correlation judgment result also includes general correlation judgment results and specific correlation judgment results. Furthermore, third voice commands whose second correlation judgment results do not meet the preset correlation conditions are cached until the task execution status change of the in-vehicle functional device is completed.

[0046] S3': In response to the completion of the voice task execution status change of the in-vehicle functional device, generate and feed back an end signal.

[0047] Specifically, the changes in the execution status of voice tasks in in-vehicle functional devices include at least: 1. The second voice task changes from an execution state to a completed state; 2. The second voice task changes from execution to execution of a third voice task; both states correspond to the end of the lifecycle of the second voice task. After receiving the feedback end signal, the in-vehicle voice command control system directly stops the microphone from receiving user voice signals and no longer acquires third voice commands.

[0048] In some examples, the lifecycle of a voice task is: from the moment a voice command is received to initiate the execution of the voice task, until the moment the execution state change of the voice task is completed; in response to the completion of the voice task execution state change by the in-vehicle functional device, an end signal is generated and fed back, specifically including at least one of the following methods: Method 1: The first voice task of the in-vehicle function device changes from an in progress state to a completed state, the lifecycle of the first voice task ends, and an end signal is generated and fed back. For example: the first voice task is to activate zero gravity mode. Within the lifecycle of activating zero gravity mode, if no second voice command is obtained that meets the preset association conditions according to the first correlation judgment result, then zero gravity mode is activated, the lifecycle of the first voice task ends, an end signal is generated and fed back, and the end signal is used to stop receiving the second voice command and wait for the system wake-up command to trigger the reception of voice commands again.

[0049] Method 2: The in-vehicle function device changes from executing the first voice task to executing the second voice task. The lifecycle of the first voice task ends, and an end signal is directly generated and fed back. Continuing with the example of the first voice task being to activate zero gravity mode, within the lifecycle of activating zero gravity mode, if a second voice command is obtained that meets the preset association conditions based on the first correlation judgment result, and the second voice command is the opposite of the first voice command (stop command), then the state changes from activating zero gravity mode to stopping activation and restoring the seat to its original state. When zero gravity mode is stopped, i.e., when the first voice task changes to the second voice task, the lifecycle of the first voice task ends, and an end signal is generated and fed back. The end signal is used to stop receiving the second voice command and wait for the system wake-up command to trigger the reception of voice commands again.

[0050] Method 3: The second voice task of the in-vehicle function device changes from an in progress state to a completed state, and the lifecycles of both the first and second voice tasks end, generating and feeding back an end signal. For example: The first voice task is to turn on the air conditioner. Within the lifecycle of turning on the air conditioner, a second voice command is obtained that meets the preset association conditions based on the first correlation judgment result. The second voice task is to raise the temperature. For the air conditioner, turning it on takes a period of time, while adjusting the temperature can be completed very quickly based on the command signal. The lifecycle of raising the temperature is shorter than the lifecycle of turning on the air conditioner; that is, the lifecycle of the second voice task is shorter than the lifecycle of the first voice task. In this case, it is necessary to directly obtain voice commands within the lifecycle of the first voice task. Therefore, an end signal is generated and fed back only after the in-vehicle function device changes from executing the first voice task to executing the second voice task, the second voice task changes from an in progress state to a completed state, and the lifecycles of both the first and second voice tasks end.

[0051] Method 4: The in-vehicle function device changes from executing the second voice task to executing the third voice task. The lifecycle of the second voice task ends, and an end signal is directly generated and fed back. For example, if the third voice command is a stop command, the in-vehicle function device changes from executing the second voice task to stopping the execution of the second voice task. The lifecycle of the second voice task ends, and an end signal is directly generated and fed back.

[0052] Method 5: The third voice task of the in-vehicle function device changes from an in progress state to a completed state, and the lifecycles of the first, second, and third voice tasks all end, generating and feeding back an end signal. Continuing with Method 3, which generates and feeds back an end signal, and taking the first voice task as turning on the air conditioner as an example, if the second correlation judgment result is a third voice command that meets the preset correlation conditions, the third voice task is to lower the fan speed. After the lifecycle of lowering the fan speed ends, there is still a possibility that the lifecycle of turning on the air conditioner has not ended, or that the lifecycles of lowering the fan speed and raising the temperature overlap. To ensure that the microphone can maintain wake-up-free reception of user voice signals during the adjustment of the air conditioner status, the third voice task of the in-vehicle function device changes from an in progress state to a completed state, and the lifecycles of the first, second, and third voice tasks all end before generating and feeding back an end signal.

[0053] Understandably, in-vehicle devices may simultaneously perform two or more non-conflicting tasks of different types, such as turning on the air conditioner, adjusting the temperature, and adjusting the fan speed. During the transition from executing a preceding voice command to executing a subsequent voice command, the lifecycle and execution state of the preceding voice command are not interrupted; the subsequent voice command is only superimposed within the lifecycle of the preceding voice command. From a system or hardware perspective, this can be understood as follows: the in-vehicle device begins working upon activation by the first corresponding voice command. During the lifecycle of the preceding voice command, it can continuously receive and execute subsequent voice commands. Only when the lifecycles of all voice commands have ended will it return a final task completion signal to the in-vehicle voice command control system. At this point, the in-vehicle voice command control system generates and feeds back an end signal, causing the microphone to stop receiving user voice signals. For safety reasons, some in-vehicle functional devices will immediately stop working and return to their original state after receiving a second voice task that is the opposite of the first voice task and completing the task status change. At the same time as switching the task status, they will return a task completion signal to the in-vehicle voice command control system. The in-vehicle voice command control system will generate and feed back an end signal, causing the microphone to stop receiving user voice signals.

[0054] In some examples, Figure 3 A flowchart of another vehicle-mounted voice command control method provided in this disclosure embodiment is shown below. Figure 3 As shown, the in-vehicle voice command control method also includes: S01: In response to the acquisition of the system wake-up command, the reception of voice commands is triggered.

[0055] Specifically, the voice commands include a first voice command and a second voice command. The system wake-up command is used to activate the microphone from low-power mode to recording mode; once the microphone is in recording mode, it can receive the user's voice signal and convert the voice signal into a voice command.

[0056] S02: In response to the acquisition of the first voice command, control the in-vehicle functional device corresponding to the first voice command to execute the first voice task.

[0057] It should be noted that the first, second, and third voice commands and the first, second, and third voice tasks in the embodiments of this disclosure are only limited to the order between voice commands and voice tasks, and are not necessarily limited to being the first, second, and third voice commands or voice tasks in the entire process.

[0058] Example 1: Let's take activating the zero-gravity mode of the seat as an example. Figure 4 This is a schematic diagram of an in-vehicle voice command control method provided in an embodiment of the present disclosure, as shown below. Figure 4 As shown. In response to the acquisition of the system wake-up command, the reception of voice commands is triggered; the voice commands include a first voice command and a second voice command.

[0059] In response to the acquisition of the first voice command, the system controls the corresponding in-vehicle function device to execute the first voice task. The first voice command is to activate the zero-gravity mode of the seat. The seat begins to switch from the current mode to the zero-gravity mode, and this switching process takes a period of time.

[0060] In response to the initiation and execution of the first voice task, the second voice command is directly obtained within the lifecycle of the first voice task without the need for a system wake-up command. The lifecycle of the first voice task is as follows: from the moment the first voice command is obtained and execution of the first voice task begins, to the moment the execution state change of the first voice task is completed; and from the moment the seat switches from the current mode to zero gravity mode, to the moment the switch to zero gravity mode is completed or stops. During the time from when the seat switches from the current mode to zero gravity mode, to the moment the switch to zero gravity mode is completed or stops, the second voice command can be obtained directly without a system wake-up command; that is, the user can directly issue a voice command to trigger a system response without a wake-up word.

[0061] In response to the acquisition of a second voice command, the second voice command is correlated with a preset voice command to generate a first correlation judgment result. During the lifecycle of the first voice task, when the second voice command is directly acquired, it is correlated with a preset voice command, which includes commands such as stop, cancel, and turn off. Within the lifecycle of the first voice task, the user may need to stop the seat's zero-gravity mode at any time for comfort or safety reasons. In this case, the user can directly issue a voice command to stop the adjustment without a wake-up word. Simultaneously, since the microphone continuously picks up sound during this period, there may be interference with the voice signal. Therefore, the second voice command and the preset voice command are correlated to generate a first correlation judgment result. When the second voice command is to stop the adjustment, the second voice command and the preset voice command are correlated. At this time, the first correlation judgment result meets the preset correlation conditions. Based on the second voice command, the seat is controlled to stop switching to zero-gravity mode and can be restored to the original mode. It is understood that the first voice task is a continuous process; when this task is stopped, the system can directly restore the state before the execution of the first voice task.

[0062] Furthermore, if the second voice command corresponding to the voice signal received by the microphone does not meet the preset association condition in the first correlation judgment result with the preset voice command, the second voice command can be temporarily stored until the task execution status change of the vehicle function device is completed.

[0063] In response to the completion of a voice task execution status change in the in-vehicle functional device, an end signal is generated and fed back. When the seat's task status changes from "on zero-gravity mode" to "off switching," the voice task execution status change of the in-vehicle functional device is completed, the lifecycle of the first voice task ends, and an end signal is generated and fed back. After receiving the feedback end signal, the in-vehicle voice command control system directly stops the microphone from receiving user voice signals and does not acquire second voice commands.

[0064] The in-vehicle voice command control method in this embodiment of the present disclosure, by limiting the acquisition of voice commands without wake words to the life cycle of the in-vehicle functional device executing voice tasks, can achieve the task execution state of voice commands without wake words while reducing the overall power consumption of the in-vehicle system and protecting the privacy of the people in the vehicle. This enables a rapid and accurate response to the voice task change commands issued by the user in real time, reducing the possibility of dangerous situations.

[0065] Secondly, Figure 5 A block diagram of an in-vehicle voice command control system provided in this disclosure embodiment is shown below. Figure 5As shown, based on the same inventive concept, this disclosure also provides an in-vehicle voice command control system for executing any of the aforementioned in-vehicle voice command control methods. The in-vehicle voice command control system responds to the initiation of a first voice task. Within the lifecycle of the first voice task, it directly acquires a second voice command without requiring a system wake-up command, and controls the change of the task execution state of the in-vehicle functional device based on the second voice command. The in-vehicle voice command control system includes at least: a voice command association module and a task status monitoring module. The voice command association module responds to the acquisition of the second voice command by performing an association judgment between the second voice command and a preset voice command, and generates a first association judgment result. If the first association judgment result meets the preset association conditions, the in-vehicle functional device is controlled to execute the second voice task based on the second voice command. The task status monitoring module generates and feeds back an end signal in response to the completion of the voice task execution status change of the in-vehicle functional device; the end signal is used to stop receiving the second voice command and wait for the system wake-up command to trigger the reception of the voice command again.

[0066] In some examples, the in-vehicle voice command control system also includes: an in-vehicle voice processing module; The in-vehicle voice processing module responds to the acquisition of the system wake-up command by triggering the reception of voice commands; these voice commands include a first voice command and a second voice command. The in-vehicle voice processing module includes a microphone. The task status monitoring module feeds back an end signal to the in-vehicle voice processing module to mute the microphone, putting it into a low-power mode, awaiting the next wake-up.

[0067] The task status monitoring module also responds to the acquisition of the first voice command, controls the vehicle-mounted functional device corresponding to the first voice command, and executes the first voice task.

[0068] Thirdly, based on the same inventive concept, the present disclosure also provides a computer-readable storage medium storing one or more programs, which, when executed, can realize the aforementioned vehicle voice command control method.

[0069] Fourthly, Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure, such as... Figure 6 As shown, based on the same inventive concept, this disclosure also provides an electronic device, including a processor, a communication interface, the aforementioned computer-readable storage medium, and a communication bus. The processor, communication interface, and computer-readable storage medium communicate with each other via the communication bus. The processor is used to execute a program stored in the aforementioned computer-readable storage medium.

[0070] It should be noted that the electrical connection between the above-mentioned units does not necessarily mean that the lines are directly connected. Indirect connection can be used, as long as the purpose of this disclosure is achieved, it can be applied to the embodiments of this disclosure.

[0071] Although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A vehicle-mounted voice command control method, characterized in that, In response to the start of the first voice task, within the lifecycle of the first voice task, the second voice command is directly obtained without the need for a system wake-up command, and the change of the task execution status of the in-vehicle functional device is controlled based on the second voice command. The changes in the task execution status of the control vehicle-mounted functional equipment include: In response to the acquisition of the second voice command, the second voice command is correlated with a preset voice command to generate a first correlation judgment result; wherein, If the first correlation judgment result meets the preset correlation conditions, then based on the second voice command, the vehicle-mounted functional device is controlled to execute the second voice task; In response to the completion of the voice task execution status change of the in-vehicle functional device, an end signal is generated and fed back; wherein, The termination signal is used to stop receiving the second voice command and wait for the system wake-up command to trigger the reception of the voice command again.

2. The method according to claim 1, characterized in that, The step of responding to the acquisition of the second voice command by performing an association determination between the second voice command and a preset voice command to generate a first association determination result includes at least one of the following methods: Method 1: In response to the acquisition of the second voice command, the second voice command is compared with a preset general voice command to determine its correlation, and a general correlation determination result is generated; Method 2: In response to the acquisition of the second voice command, the second voice command is correlated with the preset specific voice command corresponding to the first voice task, and a specific correlation judgment result is generated; Method 3: If the first correlation judgment result does not meet the preset correlation conditions, cache the second voice command until the task execution status change of the vehicle function device is completed.

3. The method according to claim 1 or 2, characterized in that, The preset association conditions include: If the general correlation determination result between the second voice command and the preset general voice command is that there is a correlation, then the preset correlation condition is met; If the result of the specific correlation judgment between the second voice command and the preset specific voice command corresponding to the first voice task is that there is a correlation, then the preset correlation condition is met.

4. The method according to claim 1, characterized in that, In response to the start of the second voice task, within the lifecycle of the second voice task, the third voice command is directly obtained without the need for the system wake-up command, and the change of the task execution status of the vehicle function device is controlled based on the third voice command. The changes in the task execution status of the control vehicle-mounted functional equipment include: In response to the acquisition of the third voice command, the third voice command is correlated with the preset voice command to generate a second correlation judgment result; wherein, If the second correlation judgment result meets the preset correlation condition, then based on the third voice command, the vehicle-mounted functional device is controlled to execute the third voice task; In response to the completion of the voice task execution status change of the in-vehicle functional device, an end signal is generated and fed back; wherein... The termination signal is used to stop receiving the third voice command and wait for the system wake-up command to trigger the reception of the voice command again.

5. The method according to claim 1 or 4, characterized in that, The lifecycle of a voice task is: from the moment the voice command is received to initiate the execution of the voice task, to the moment the execution status change of the voice task is completed; the generation and feedback of the end signal includes at least one of the following methods: Method 1: The first voice task of the in-vehicle functional device changes from the in progress state to the completed state, the life cycle of the first voice task ends, and the end signal is generated and fed back. Method 2: The in-vehicle functional device changes from performing the first voice task to performing the second voice task, and the life cycle of the first voice task ends, directly generating and feeding back the end signal; Method 3: The second voice task of the in-vehicle functional device changes from the in progress state to the completed state, and the life cycle of both the first voice task and the life cycle of the second voice task ends, generating and feeding back the end signal; Method 4: The in-vehicle functional device changes from performing the second voice task to performing the third voice task. The life cycle of the second voice task ends, and the end signal is directly generated and fed back. Method 5: The third voice task of the in-vehicle functional device changes from the in progress state to the completed state, and the life cycle of the first voice task, the second voice task and the third voice task all end, generating and feeding back the end signal.

6. The method according to claim 1, characterized in that, The in-vehicle voice command control method further includes: In response to the acquisition of the system wake-up command, the reception of voice commands is triggered; wherein, the voice commands include a first voice command and a second voice command; In response to the acquisition of the first voice command, the vehicle-mounted functional device corresponding to the first voice command is controlled to execute the first voice task.

7. A vehicle-mounted voice command control system, used to execute the vehicle-mounted voice command control method according to any one of claims 1-6, characterized in that, The vehicle-mounted voice command control system responds to the initiation and execution of the first voice task. Within the lifecycle of the first voice task, it directly acquires the second voice command without the need for the system wake-up command, and controls the change of the task execution status of the vehicle-mounted functional device based on the second voice command. The vehicle-mounted voice command control system includes at least: a voice command association module and a task status monitoring module. The voice command association module, in response to the acquisition of the second voice command, performs an association judgment between the second voice command and the preset voice command to generate a first association judgment result; wherein, if the first association judgment result meets the preset association condition, the in-vehicle functional device is controlled to execute a second voice task based on the second voice command; The task status monitoring module generates and feeds back an end signal in response to the completion of the voice task execution status change of the in-vehicle functional device; wherein, the end signal is used to stop receiving the second voice command and wait for the system wake-up command to trigger the reception of the voice command again.

8. The system according to claim 7, characterized in that, The system also includes: an in-vehicle voice processing module; The in-vehicle voice processing module, in response to the acquisition of the system wake-up command, triggers the reception of voice commands; wherein, the voice commands include a first voice command and a second voice command; The task status monitoring module also responds to the acquisition of the first voice command by controlling the in-vehicle functional device corresponding to the first voice command to execute the first voice task.

9. A computer-readable storage medium storing one or more programs, characterized in that, When one or more programs are executed, the vehicle voice command control method according to any one of claims 1-6 can be implemented.

10. An electronic device, comprising a processor, a communication interface, a computer-readable storage medium as described in claim 9, and a communication bus; wherein, The processor, communication interface, and computer-readable storage medium communicate with each other via a communication bus; Its features are, The processor is used to execute programs stored in a computer-readable storage medium.

Images