Vehicle-mounted voice interaction method, device, equipment and medium

Abstract

The invention relates to a vehicle-mounted voice interaction method, device and equipment and a medium, and is applied to the technical field of vehicle-mounted voice control, and the method comprises the steps: obtaining user voice information and wake-up time in response to a vehicle-mounted voice assistant wake-up instruction of a user; performing interaction countdown based on the wake-up time and a preset interaction duration; determining entry time of entering a pre-exit state based on the interactive countdown and the user voice information; determining an absolute detection time based on the entry time; acquiring a user interaction instruction in the deadline detection time in real time; entering a pre-exit state based on the user interaction instruction and the entry time; and executing the pre-quit state and quitting the vehicle-mounted voice assistant after the pre-quit state is executed. The method and the device have the effect of improving the interaction continuity while improving the user experience.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle-mounted voice control, and in particular to a vehicle-mounted voice interaction method, device, equipment and medium. Background Art

[0002] In order to improve the convenience of driving and the safety of driving, more and more cars are equipped with voice interaction services, namely the well-known in-car voice assistants, so that the driver or other passengers can use the required functions through voice interaction with the in-car voice assistant.

[0003] Currently, the continuous conversation time provided by in-vehicle voice assistant suppliers can reach up to 120 seconds. Although this infinite refresh mechanism guarantees the waiting time for the in-vehicle voice assistant to interact with the user to a certain extent, this mechanism also brings about a series of other problems.

[0004] There are certain defects both in terms of user experience and technical implementation. For users, after the in-car voice assistant is awakened, if no exit command is actively issued, the in-car voice assistant will be in standby mode for a long time, which may easily make users feel uncomfortable as if they are being monitored. For technology, long standby time will not only increase the burden on the cloud cache, but also lead to a decrease in the recognition and execution capabilities of the in-car voice assistant. Therefore, how to improve the consistency of interaction while improving the user experience has become an urgent problem to be solved. Summary of the invention

[0005] In order to improve the consistency of interaction while improving user experience, the present application provides an in-vehicle voice interaction method, device, equipment and medium.

[0006] In a first aspect, the present application provides a vehicle-mounted voice interaction method, which adopts the following technical solution:

[0007] A vehicle-mounted voice interaction method, comprising:

[0008] In response to the user's in-vehicle voice assistant wake-up command, obtain the user's voice information and wake-up time;

[0009] Performing an interaction countdown based on the wake-up time and preset interaction duration;

[0010] Determining an entry time to enter a pre-exit state based on the interaction countdown and the user voice information;

[0011] determining a limit detection time based on the entry time;

[0012] Real-time acquisition of user interaction instructions within the absolute detection time;

[0013] Entering a pre-exit state based on the user interaction instruction and the entry time;

[0014] Execute the pre-exit state and exit the in-vehicle voice assistant after the pre-exit state is completed.

[0015] By adopting the above technical solution, a cumulative countdown mode is used in the countdown, and a pre-exit mode is added. When in use, the cumulative timing mechanism avoids the problem that the in-car voice assistant is still in a waiting state for a long time when the user is not using the in-car voice assistant, and reduces the user's discomfort of being continuously monitored. At the same time, the setting of the pre-exit state enables the user to clearly perceive the current state when the in-car voice assistant is about to exit, thereby avoiding the trouble caused by interruption of interaction, and the setting of the pre-exit mechanism enables the in-car voice assistant to maintain a high recognition accuracy and execution efficiency in each interaction, thereby improving the continuity of interaction while improving the user experience.

[0016] Optionally, the determining the entry time to enter the pre-exit state based on the interaction countdown and the user voice information includes:

[0017] Obtaining the execution time of the interaction countdown;

[0018] Detecting whether the user voice information contains an interaction intention;

[0019] If the user voice information contains an interaction intention, pausing the interaction countdown;

[0020] executing the interaction intention;

[0021] After a complete round of the interaction intention is executed, the interaction countdown is resumed;

[0022] Determine the remaining time based on the preset interaction time and the executed time;

[0023] Determining an entry time to enter a pre-exit state based on the remaining time;

[0024] If the user voice information does not include an interaction intention, an entry time to enter a pre-exit state is determined based on the preset interaction duration.

[0025] Optionally, determining the absolute detection time based on the entry time includes:

[0026] Obtain a limit detection duration, and determine a limit detection time based on the entry time and the limit detection duration.

[0027] Optionally, the entering the pre-exit state based on the user interaction instruction and the entry time includes:

[0028] Acquire an instruction execution condition, and determine whether the user interaction instruction is executable based on the instruction execution condition;

[0029] If the user interaction instruction is executable, the semantic validity detection phase is entered;

[0030] Entering a pre-exit state based on the semantic validity detection stage and the entry time;

[0031] If the user interaction instruction is not executable, the pre-exit state is entered after the entry time is reached.

[0032] Optionally, judging whether the user interaction instruction is executable based on the instruction execution condition includes:

[0033] Determine whether the user interaction instruction is empty;

[0034] If the user interaction instruction is empty, determining that the user interaction instruction is not executable;

[0035] If the user interaction instruction is not empty, obtaining the number of characters contained in the user interaction instruction;

[0036] Determining whether the number of characters meets the instruction execution condition;

[0037] If the number of characters meets the instruction execution condition, determining that the user interaction execution is executable;

[0038] If the number of characters does not meet the instruction execution condition, it is determined that the user interaction instruction is not executable.

[0039] Optionally, the entering the pre-exit state based on the semantic validity detection stage and the entry time includes:

[0040] Obtaining the duration of the semantic validity detection phase;

[0041] Modify the entry time based on the stage duration to generate a first time;

[0042] If the user interaction instruction is executed and completed within the stage duration, entering the pre-exit state based on the first time;

[0043] If the user interaction instruction is not executed within the stage duration, the acquisition instruction exceeds the duration;

[0044] Modify the first time based on the duration of the instruction exceeding the time limit to generate a second time;

[0045] The pre-exit state is entered based on the second time.

[0046] Optionally, executing the pre-exit state and exiting the in-vehicle voice assistant after the pre-exit state is completed includes:

[0047] Get the assistant exit prompt animation;

[0048] Turn off the receiving function of the in-vehicle voice assistant and play the assistant exit prompt animation.

[0049] In a second aspect, the present application provides a vehicle-mounted voice interaction device, which adopts the following technical solution:

[0050] A vehicle-mounted voice interaction device, comprising:

[0051] A wake-up command response module is used to respond to the user's in-vehicle voice assistant wake-up command and obtain the user's voice information and wake-up time;

[0052] An interaction duration timing module, used for performing an interaction countdown based on the wake-up time and a preset interaction duration;

[0053] An exit time determination module, used to determine an entry time into a pre-exit state based on the interaction countdown and the user voice information;

[0054] A deadline time determination module, used to determine a deadline detection time based on the entry time;

[0055] An interactive instruction acquisition module, used for acquiring user interactive instructions within the absolute detection time in real time;

[0056] An exit state entry module, used for entering a pre-exit state based on the user interaction instruction and the entry time;

[0057] The vehicle-mounted voice assistant exit module is used to execute the pre-exit state and exit the vehicle-mounted voice assistant after the pre-exit state is executed.

[0058] By adopting the above technical solution, a cumulative countdown mode is used in the countdown, and a pre-exit mode is added. When in use, the cumulative timing mechanism avoids the problem that the in-car voice assistant is still in a waiting state for a long time when the user is not using the in-car voice assistant, and reduces the user's discomfort of being continuously monitored. At the same time, the setting of the pre-exit state enables the user to clearly perceive the current state when the in-car voice assistant is about to exit, thereby avoiding the trouble caused by interruption of interaction, and the setting of the pre-exit mechanism enables the in-car voice assistant to maintain a high recognition accuracy and execution efficiency in each interaction, thereby improving the continuity of interaction while improving the user experience.

[0059] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0060] An electronic device comprises a processor, wherein the processor is coupled to a memory;

[0061] The processor is used to execute the computer program stored in the memory so that the electronic device executes the computer program of the in-vehicle voice interaction method described in any one of the first aspects.

[0062] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0063] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute the in-vehicle voice interaction method described in any one of the first aspects.

[0064] In summary, this application includes the following beneficial technical effects:

[0065] A cumulative countdown mode is used for the countdown, and a pre-exit mode is added. When in use, the cumulative timing mechanism avoids the problem that the in-car voice assistant is still in a waiting state for a long time when the user is not using the in-car voice assistant, reducing the user's discomfort of being continuously monitored. At the same time, the setting of the pre-exit state enables the user to clearly perceive the current state when the in-car voice assistant is about to exit, thereby avoiding the trouble caused by interrupted interaction. The setting of the pre-exit mechanism enables the in-car voice assistant to maintain a high recognition accuracy and execution efficiency in each interaction, thereby improving the continuity of interaction while improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a flow chart of an in-vehicle voice interaction method provided in an embodiment of the present application.

[0067] Figure 2 It is a structural block diagram of a vehicle-mounted voice interaction device provided in an embodiment of the present application.

[0068] Figure 3 It is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] The present application is further described in detail below in conjunction with the accompanying drawings.

[0070] The embodiment of the present application provides a vehicle-mounted voice interaction method, which can be executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a desktop computer, etc., but is not limited thereto.

[0071] Figure 1 A flowchart of an in-vehicle voice interaction method provided in an embodiment of the present application.

[0072] like Figure 1 As shown, the main process of the method is described as follows (steps S101 to S107):

[0073] Step S101, in response to the user's in-vehicle voice assistant wake-up command, obtain the user's voice information and wake-up time.

[0074] In this embodiment, after the user sends a wake-up command to the in-vehicle voice assistant, the in-vehicle voice assistant will be awakened and respond, and the user will also send relevant voice commands to the in-vehicle voice assistant. The user's voice information after the wake-up command is collected as the user's voice information, and the time after the in-vehicle voice assistant is awakened is collected as the wake-up time.

[0075] Step S102: performing an interaction countdown based on the wake-up time and the preset interaction duration.

[0076] In this embodiment, an interaction duration is set, that is, the waiting time of the vehicle voice assistant after being awakened. The user can interact with the vehicle voice assistant within the preset interaction duration. After exceeding the preset interaction duration, the vehicle voice assistant will end the interaction support. When the user wakes up the vehicle voice assistant, the countdown begins, and the second corresponding to the wake-up time is used as the first second of the countdown. For example, the wake-up time is one o'clock and the preset interaction duration is 30 seconds. When the countdown is performed, one o'clock is recorded as 1 second or 30 seconds. When one o'clock is recorded as 1 second, the countdown ends at 30 seconds. When one o'clock is recorded as 30 seconds, the countdown ends at 1 second. It should be noted that the broadcast time corresponding to the first response of the vehicle voice assistant during the countdown will be included in the countdown. The preset interaction duration is generally set to 15 seconds, 30 seconds and 60 seconds, and can also be set to 20 seconds, 40 seconds, etc. according to actual needs. Whether the countdown is clockwise or counterclockwise needs to be set according to actual needs. The specific timing method and preset interaction duration are not specifically limited here.

[0077] Step S103: determining an entry time to enter a pre-exit state based on the interaction countdown and the user voice information.

[0078] For step S103, obtain the executed time of the interaction countdown; detect whether the user voice information contains the interaction intention; if the user voice information contains the interaction intention, pause the interaction countdown; execute the interaction intention; resume the interaction countdown after executing a complete round of interaction intention; determine the remaining time based on the preset interaction time and the executed time; determine the entry time to enter the pre-exit state based on the remaining time; if the user voice information does not contain the interaction intention, determine the entry time to enter the pre-exit state based on the preset interaction time.

[0079] In this embodiment, a pre-exit state is set. When entering the pre-exit state, the vehicle voice assistant will no longer receive the user's voice input information. After the pre-exit state ends, the vehicle voice assistant will be closed, thereby ending this interaction. The pre-exit state will start to execute after the interaction countdown ends. After the vehicle voice assistant is awakened, the execution time of the interaction countdown is obtained in real time, that is, the time the vehicle voice assistant has been awakened, and it is detected whether the user voice information contains the interaction intention. The interaction intention is a specific voice instruction and other operations that can be executed by the vehicle voice assistant. Effective voice information. If the user voice information contains the interaction intention, the interaction countdown is paused and the interaction intention is executed. After a complete round of interaction intention is executed, the interaction countdown continues, and the remaining time is calculated according to the preset interaction time and the executed time. The entry time to enter the pre-exit state can be obtained according to the remaining time. If the user voice information does not contain the interaction intention, the interaction countdown is always performed, and the entry time to enter the pre-exit state is directly determined by the preset interaction time.

[0080] Step S104, determining a limit detection time based on the entry time.

[0081] With respect to step S104, the absolute detection duration is obtained, and the absolute detection time is determined based on the entry time and the absolute detection duration.

[0082] In this embodiment, a deadline detection time is set, and corresponding response processing can be performed according to the actual situation within the deadline detection time. First, the deadline detection time is determined, and then the deadline detection time is moved forward based on the entry time. The time obtained after the move is the deadline detection time. If the deadline detection time is 3 seconds, it will be moved forward by 3 seconds based on the entry time, that is, the first second of the last 3 seconds of the interaction countdown will be used as the deadline detection time.

[0083] Step S105, obtaining user interaction instructions within the limit detection time in real time.

[0084] In this embodiment, the user interaction instructions within the absolute detection time are acquired in real time. The user interaction instructions here include two situations. The first situation is that the user interaction instruction is empty, that is, the user has not generated any voice information. The second situation is that the user interaction instruction is not empty, that is, the user has generated voice information. Different execution methods are set for the user interaction instructions in the two situations.

[0085] Step S106: entering a pre-exit state based on the user interaction instruction and the entry time.

[0086] For step S106, the instruction execution condition is obtained, and whether the user interaction instruction is executable is determined based on the instruction execution condition; if the user interaction instruction is executable, the semantic validity detection phase is entered; based on the semantic validity detection phase and the entry time, the pre-exit state is entered; if the user interaction instruction is not executable, the pre-exit state is entered after the entry time is reached.

[0087] In this embodiment, after obtaining the user interaction instruction, the instruction execution condition is obtained, and whether the user interaction instruction can be executed is determined based on the instruction execution condition. If the user interaction instruction can be executed, the semantic validity detection phase will be entered, and the pre-exit state will be entered in combination with the semantic validity detection phase and the entry time. If the user interaction instruction cannot be executed, the pre-exit state will be directly entered according to the entry time.

[0088] Furthermore, judging whether the user interaction instruction can be executed according to the instruction execution conditions is as follows: judging whether the user interaction instruction is empty; if the user interaction instruction is empty, judging that the user interaction instruction is not executable; if the user interaction instruction is not empty, obtaining the number of characters contained in the user interaction instruction; judging whether the number of characters meets the instruction execution conditions; if the number of characters meets the instruction execution conditions, judging that the user interaction instruction is executable; if the number of characters does not meet the instruction execution conditions, judging that the user interaction instruction is not executable.

[0089] In this embodiment, a preliminary judgment is first made to determine whether the user interaction instruction is an empty instruction. If the user interaction instruction is an empty instruction, it means that there is no executable user interaction instruction, and the user interaction instruction is judged as unexecutable. If the user interaction instruction is not an empty instruction, it means that there may be an executable user interaction instruction. Further judgment will be made based on the user interaction instruction, and the number of characters contained in the user interaction instruction will be collected. The instruction execution condition includes a character number threshold. When the number of characters is less than the character threshold, it indicates that the number of characters does not meet the execution condition, and the user interaction instruction is judged to be unexecutable. When the number of characters is greater than or equal to the character threshold, it indicates that the number of characters meets the execution condition, and the user interaction instruction is judged to be executable.

[0090] Furthermore, entering the pre-exit state in combination with the semantically valid detection stage and the entry time is specifically as follows: obtaining the stage duration of the semantically valid detection stage; modifying the entry time based on the stage duration to generate a first time; if the user interaction instruction is completed within the stage duration, entering the pre-exit state based on the first time; if the user interaction instruction is not completed within the stage duration, obtaining the instruction excess time; modifying the first time based on the instruction excess time to generate a second time; and entering the pre-exit state based on the second time.

[0091] In this embodiment, a stage duration is set for the semantic validity detection stage. During the stage duration, the on-board voice assistant performs semantic detection on the user interaction instruction. If it is detected that the semantics of the user interaction instruction is valid, the user interaction instruction will be executed. At this time, there will still be two situations. The first situation is that the execution can be completed within the stage duration, and the second situation is that the execution cannot be completed within the stage duration. In the first situation, the execution can be completed within the stage duration, including the execution of a complete round of interaction, and also including the failure of the interaction execution or the inability to be executed. However, since these two situations are detected by the on-board voice assistant, they are both counted as a successful execution. When entering the pre-exit state, it is only necessary to adjust the entry time according to the stage duration to generate a first time. The pre-exit state is entered according to the first time. The adjustment method of the entry time is the same as the above adjustment method, and it can be shifted according to the length of time, which will not be repeated here. In the second case, it is necessary to increase the instruction excess time based on the stage time, that is, after obtaining the first time, continue to perform time shift processing backward based on the first time to obtain the second time, and enter the pre-exit state according to the second time.

[0092] Step S107, executing the pre-exit state and exiting the in-vehicle voice assistant after the pre-exit state is completed.

[0093] For step S107, obtain the assistant exit prompt animation; turn off the receiving function of the in-vehicle voice assistant, and play the assistant exit prompt animation.

[0094] In this embodiment, in order to enable the user to clearly perceive the working status of the in-vehicle voice assistant, a dynamic prompt will be accompanied when executing the pre-exit state, that is, when the in-vehicle voice assistant turns off the receiving function, the assistant exit prompt animation will be played, wherein the assistant exit prompt animation can be a simple dynamic picture, a simple sound effect, or a dynamic combination of dynamic pictures and sound effects, etc., as long as it can serve as an exit prompt effect for the user, the specific animation form is not specifically limited here.

[0095] Figure 2 A structural block diagram of a vehicle-mounted voice interaction device 200 provided in an embodiment of the application.

[0096] like Figure 2 As shown, the vehicle-mounted voice interaction device 200 mainly includes:

[0097] A wake-up command response module 201 is used to respond to the user's in-vehicle voice assistant wake-up command and obtain the user's voice information and wake-up time;

[0098] An interaction duration timing module 202 is used to count down the interaction based on the wake-up time and the preset interaction duration;

[0099] An exit time determination module 203, used to determine an entry time into a pre-exit state based on an interaction countdown and user voice information;

[0100] A deadline time determination module 204, configured to determine a deadline detection time based on an entry time;

[0101] An interactive instruction acquisition module 205 is used to acquire user interactive instructions within a limit detection time in real time;

[0102] An exit state entry module 206, for entering a pre-exit state based on a user interaction instruction and an entry time;

[0103] The vehicle voice assistant exit module 207 is used to execute a pre-exit state and exit the vehicle voice assistant after the pre-exit state is executed.

[0104] As an optional implementation of this embodiment, the exit time determination module 203 is specifically used to obtain the executed time of the interaction countdown; detect whether the user voice information contains the interaction intention; if the user voice information contains the interaction intention, pause the interaction countdown; execute the interaction intention; resume the interaction countdown after executing a complete round of interaction intention; determine the remaining time based on the preset interaction time and the executed time; determine the entry time to enter the pre-exit state based on the remaining time; if the user voice information does not contain the interaction intention, determine the entry time to enter the pre-exit state based on the preset interaction time.

[0105] As an optional implementation of this embodiment, the deadline time determination module 204 is specifically used to obtain the deadline detection duration, and determine the deadline detection time based on the entry time and the deadline detection duration.

[0106] As an optional implementation of this embodiment, the exit state entry module 206 includes:

[0107] An execution condition acquisition module is used to acquire the instruction execution condition and determine whether the user interaction instruction is executable based on the instruction execution condition;

[0108] The detection phase entry module is used to enter the semantic validity detection phase;

[0109] A first state entry module, for entering a pre-exit state based on a semantically valid detection stage and an entry time;

[0110] The second state entry module is used to enter the pre-exit state after reaching the entry time.

[0111] In this optional embodiment, the execution condition acquisition module is specifically used to determine whether the user interaction instruction is empty; if the user interaction instruction is empty, it is determined that the user interaction instruction is not executable; if the user interaction instruction is not empty, the number of characters contained in the user interaction instruction is obtained; it is determined whether the number of characters meets the instruction execution condition; if the number of characters meets the instruction execution condition, it is determined that the user interaction is executable; if the number of characters does not meet the instruction execution condition, it is determined that the user interaction instruction is not executable.

[0112] In this optional embodiment, the first state entry module is specifically used to obtain the stage duration of the semantic validity detection stage; modify the entry time based on the stage duration to generate a first time; if the user interaction instruction is completed within the stage duration, enter the pre-exit state based on the first time; if the user interaction instruction is not completed within the stage duration, obtain the instruction excess time; modify the first time based on the instruction excess time to generate a second time; and enter the pre-exit state based on the second time.

[0113] As an optional implementation of this embodiment, the in-vehicle voice assistant exit module 207 is specifically used to obtain the assistant exit prompt animation; turn off the receiving function of the in-vehicle voice assistant, and play the assistant exit prompt animation.

[0114] In one example, the module in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0115] For another example, when the modules in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0116] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0117] Figure 3 This is a structural block diagram of an electronic device 300 provided in an embodiment of the present application.

[0118] like Figure 3 As shown, the electronic device 300 includes a processor 301 and a memory 302 , and may further include an information input / information output (I / O) interface 303 , one or more of a communication component 304 , and a communication bus 305 .

[0119] The processor 301 is used to control the overall operation of the electronic device 300 to complete all or part of the steps of the above-mentioned vehicle voice interaction method; the memory 302 is used to store various types of data to support the operation of the electronic device 300, and these data may include, for example, instructions for any application or method used to operate on the electronic device 300, and data related to the application. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0120] The I / O interface 303 provides an interface between the processor 301 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 304 is used for wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 104 can include: Wi-Fi components, Bluetooth components, NFC components.

[0121] The electronic device 300 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the in-vehicle voice interaction method given in the above embodiment.

[0122] The communication bus 305 may include a path to transmit information between the above components. The communication bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 305 may be divided into an address bus, a data bus, a control bus, etc.

[0123] The electronic device 300 may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc., and may also be servers, etc.

[0124] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned in-vehicle voice interaction method are implemented.

[0125] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0126] The terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0127] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. A vehicle-mounted voice interaction method, characterized in that: include: In response to the user's in-vehicle voice assistant wake-up command, obtain the user's voice information and wake-up time; Performing an interaction countdown based on the wake-up time and preset interaction duration; Determining an entry time to enter a pre-exit state based on the interaction countdown and the user voice information; determining a limit detection time based on the entry time; Real-time acquisition of user interaction instructions within the absolute detection time; Entering a pre-exit state based on the user interaction instruction and the entry time; Execute the pre-exit state and exit the in-vehicle voice assistant after the pre-exit state is completed.

2. The method according to claim 1, characterized in that The determining of the entry time into the pre-exit state based on the interaction countdown and the user voice information includes: Obtaining the execution time of the interaction countdown; Detecting whether the user voice information contains an interaction intention; If the user voice information contains an interaction intention, pausing the interaction countdown; executing the interaction intention; After a complete round of the interaction intention is executed, the interaction countdown is resumed; Determine the remaining time based on the preset interaction time and the executed time; Determining an entry time to enter a pre-exit state based on the remaining time; If the user voice information does not include an interaction intention, an entry time to enter a pre-exit state is determined based on the preset interaction duration.

3. The method according to claim 1, characterized in that: Determining the absolute detection time based on the entry time includes: Obtain a limit detection duration, and determine a limit detection time based on the entry time and the limit detection duration.

4. The method according to claim 1, characterized in that: The entering the pre-exit state based on the user interaction instruction and the entry time comprises: Acquire an instruction execution condition, and determine whether the user interaction instruction is executable based on the instruction execution condition; If the user interaction instruction is executable, the semantic validity detection phase is entered; Entering a pre-exit state based on the semantic validity detection stage and the entry time; If the user interaction instruction is not executable, the pre-exit state is entered after the entry time is reached.

5. The method according to claim 4, characterized in that The determining whether the user interaction instruction is executable based on the instruction execution condition includes: Determine whether the user interaction instruction is empty; If the user interaction instruction is empty, determining that the user interaction instruction is not executable; If the user interaction instruction is not empty, obtaining the number of characters contained in the user interaction instruction; Determining whether the number of characters meets the instruction execution condition; If the number of characters meets the instruction execution condition, determining that the user interaction execution is executable; If the number of characters does not meet the instruction execution condition, it is determined that the user interaction instruction is not executable.

6. The method according to claim 4, characterized in that The entering the pre-exit state based on the semantic validity detection stage and the entry time comprises: Obtaining the duration of the semantic validity detection phase; Modify the entry time based on the stage duration to generate a first time; If the user interaction instruction is executed and completed within the stage duration, entering the pre-exit state based on the first time; If the user interaction instruction is not executed within the stage duration, the acquisition instruction exceeds the duration; Modify the first time based on the duration of the instruction exceeding the time limit to generate a second time; The pre-exit state is entered based on the second time.

7. The method according to claim 1, characterized in that The executing the pre-exit state and exiting the in-vehicle voice assistant after the pre-exit state is executed includes: Get the assistant exit prompt animation; Turn off the receiving function of the in-vehicle voice assistant and play the assistant exit prompt animation.

8. A vehicle-mounted voice interaction device, characterized in that: include: A wake-up command response module is used to respond to the user's in-vehicle voice assistant wake-up command and obtain the user's voice information and wake-up time; An interaction duration timing module, used for performing an interaction countdown based on the wake-up time and a preset interaction duration; An exit time determination module, used to determine an entry time into a pre-exit state based on the interaction countdown and the user voice information; A deadline time determination module, used to determine a deadline detection time based on the entry time; An interactive instruction acquisition module, used for acquiring user interactive instructions within the absolute detection time in real time; An exit state entry module, used for entering a pre-exit state based on the user interaction instruction and the entry time; The vehicle-mounted voice assistant exit module is used to execute the pre-exit state and exit the vehicle-mounted voice assistant after the pre-exit state is executed.

9. An electronic device, characterized in that: comprising a processor coupled to a memory; The processor is configured to execute a computer program stored in the memory, so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The method comprises a computer program or an instruction, which, when executed on a computer, causes the computer to execute the method according to any one of claims 1 to 7.

Images