TW201742424A - Voice wake-up method, apparatus and device - Google Patents

Abstract

A voice wake-up method, apparatus and device. The method comprises: acquiring a voice interaction scenario; determining a corresponding first voice according to the voice interaction scenario; receiving operation information input by a user according to the first voice, and executing a corresponding operation according to the operation information. The apparatus comprises: an acquisition module; a determination module; a voice broadcast module; a receiving module, and a processing module. The device comprises: a processor, an output device, and an input device. Also disclosed is a vehicle-mounted internet operating system, comprising a voice control unit and an operation control unit. The system can guarantee an interactive behaviour between a vehicle and a user, provide the user with rich voice contents, and enhance the intelligence of man-machine interaction and the applicability of the voice wake-up of the vehicle.

Description

Voice arousing method, device and device

The present invention relates to an Internet technology, and more particularly to a voice arousing method, apparatus and apparatus for use in a vehicle.

With the continuous development of the social economy, there are more and more car owners, and people's requirements for vehicles are getting higher and higher. In order to meet the needs of users, major vehicle manufacturers have invested a lot of research and development costs in the wisdom of vehicles, so that vehicles can be more convenient for people's lives.

At present, voice arousal in a vehicle is a common interaction behavior between a vehicle and a user. For example, when a user has an incoming call, the user can answer the call by evoking the in-vehicle voice function without the driver holding the mobile phone, thereby avoiding problems such as dangerous driving.

However, the current voice arousal requires the user to manually evoke, and the targeted object is relatively simple, and the applicability is not high, so that the human-computer interaction is not intelligent enough.

The invention provides a voice arousing method, device and device to solve The prior art voice evoke requires the user to manually evoke, and the object to be targeted is relatively simple, the applicability is not high, and the human-computer interaction is not intelligent enough.

In one aspect, the present invention provides a voice arousing method, including: acquiring a voice interaction scenario; determining a corresponding first voice according to the voice interaction scenario, and broadcasting the first voice to a user, where the first voice is a prompting user The vehicle or the device on the vehicle performs voice interaction; receives operation information of the user according to the first voice input, and performs a corresponding operation according to the operation information.

The voice arousing method provided by the above, obtains a voice interaction scene, and automatically evokes a voice function of the vehicle through the voice interaction scene to broadcast a first voice corresponding to the current voice interaction scene to prompt the user to communicate with the vehicle or the vehicle. The device interacts, so that after receiving the operation information of the user according to the first voice input, the system of the vehicle performs a corresponding operation according to the operation information to ensure the interaction behavior with the user and meet the interaction requirement of the user. The method automatically evokes the voice for the user when acquiring the voice interaction scene, provides the user with rich voice content, facilitates the user to interact with the vehicle, does not require the user to manually trigger the voice interaction function of the vehicle, and improves the human-computer interaction. In addition, the voice interaction scene acquired by the in-vehicle system can correspond to the driving state of the vehicle, and since the driving state of the vehicle is rich, the voice interaction scene corresponding to the driving state of the vehicle is also rich, thereby making the invention It can actively evoke the voice function of the vehicle for different driving states, and improve the language of the vehicle. The applicability of the sound evokes.

As an achievable manner, the receiving user performs the corresponding operation according to the operation information of the first voice input, and the corresponding operation is performed according to the operation information, and specifically includes: receiving a user operation instruction input by the user according to the first voice And determining, according to the user operation instruction, whether the operation of the user is a user operation performed by the user indicated by the first voice; if yes, stopping broadcasting the first voice.

The method prompts the user to perform the user operation performed by the user by using the first voice, and then, after the user performs the user operation according to the instruction of the first voice, determines whether the user operation is the user indicated by the first voice according to the user operation instruction input by the user. The user operation is performed, and when the system of the vehicle detects that the operation performed by the user is a user operation performed by the user indicated by the first voice, the first voice is stopped, so that the user can intuitively know the needs of the vehicle, and the user is timely The abnormality of the vehicle or the improper operation of the user is found, which further improves the user experience.

As an achievable manner, the receiving user performs the corresponding operation according to the operation information of the first voice input, and the corresponding operation is performed according to the operation information, and specifically includes: receiving, by the user, the content input according to the first voice. a second voice, the first voice is used to prompt the user to perform a selection operation on the content prompted by the first voice, the second voice is a selection result of the user, and a corresponding operation is performed according to the second voice.

In this manner, the first voice indicates that the user performs a selection operation on the content prompted by the first voice, thereby obtaining a second voice input by the user according to the first voice, and performing a corresponding operation according to the second voice, so that the human-computer interaction is more The method provided by the embodiment of the present invention can know the potential triggering voice requirement of the user in advance, actively evoke the voice for the user, and prompt the user to wait for an event, thereby preventing the user from forgetting the to-do event, and providing the user with convenience. Further improve the user experience.

As an achievable manner, the acquiring a voice interaction scenario specifically includes: acquiring parameter information related to driving of the vehicle; wherein the parameter information includes external driving environment information, vehicle state information, and user behavior information. At least one type of the voice interaction scene corresponding to the current driving state of the vehicle is determined according to the parameter information.

Optionally, the external driving environment information includes road condition information and/or weather information, and the vehicle status information includes vehicle self-condition information and/or vehicle warning sound information. Optionally, as an achievable manner, the vehicle warning sound information includes a type of the vehicle warning sound or a number of broadcasts of the vehicle warning sound.

The method collects parameter information related to the driving of the vehicle, and determines a voice interaction scene corresponding to the current driving state of the vehicle according to the parameter information, thereby actively arousing the voice function of the vehicle according to the voice interaction scene, and interacting with the user, that is, Through the diversity of parameter information, the diversity of voice interaction scenarios is ensured, which enriches the initiative to arouse traffic workers. The voice function enhances the applicability of the voice arousal of the vehicle.

As an achievable manner, the parameter information includes user behavior information, and the obtaining parameter information related to the driving of the vehicle specifically includes: sending an acquisition instruction to the device storing the user behavior information, where the acquiring instruction carries the Determining an authorization code preset by the user or an identifier of the vehicle; receiving user behavior information sent by the device after verifying the authorization code or the identifier of the vehicle is legal.

The method transmits, by the system of the vehicle (for example, the in-vehicle system), an acquisition instruction carrying the user-predetermined authorization code or the identification of the vehicle to the device storing the user behavior information, so that the device storing the user behavior information is verifying the authorization code or After the identification of the vehicle is legal, the user behavior information is sent to the vehicle's system to ensure the privacy and security of the user behavior information.

As an achievable manner, the parameter information includes user behavior information, and the obtaining parameter information related to the driving of the vehicle specifically includes: receiving user behavior information input by the user.

Optionally, the user behavior information includes a user to-do event.

As an achievable manner, the user to-be-scheduled event includes the moment when the user is to be held, and the user broadcasts the first voice to the user, which specifically includes: Determining a time at which the first voice is broadcast to the user according to an occurrence time of the user pending event; and when the time arrives, broadcasting the first voice to the user.

By determining the moment when the first voice is broadcast, the first voice is broadcast to the user when the time arrives, which can know the potential triggering voice demand of the user in advance, actively evoke the voice for the user, and prompt the user to wait for the event to avoid the user forgetting. The to-do event provides users with convenience and further enhances the user experience.

In another aspect, the present invention provides a voice arousing device, including: an acquisition module, configured to acquire a voice interaction scenario; and a determination module, configured to determine a corresponding first voice according to the voice interaction scenario acquired by the acquisition module The first voice is a voice prompting a user to interact with the vehicle or the device on the vehicle; the voice broadcast module is configured to broadcast the first voice determined by the determining module to the user; The receiving module is configured to receive operation information of the first voice input determined by the user according to the determining module, and the processing module is configured to perform a corresponding operation according to the operation information received by the receiving module.

As an achievable manner, the receiving module is configured to receive a user operation instruction that is input by the user according to the first voice; and the processing module is configured to determine, according to the user operation instruction, Whether the user's operation is performed by the user indicated by the first voice The user operates, and when it is determined that the operation of the user is a user operation performed by the user indicated by the first voice, instructing the voice broadcast module to stop broadcasting the first voice.

As an achievable manner, the receiving module is configured to receive a second voice input by the user according to the content suggested by the first voice, where the first voice is used to prompt the user for the first voice The content of the prompt performs a selection operation, and the second voice is a result of the selection of the user; and the processing module is specifically configured to perform a corresponding operation according to the second voice.

As an achievable manner, the acquiring module includes: acquiring a sub-module, configured to acquire parameter information related to driving of the vehicle; wherein the parameter information includes external driving environment information, vehicle status information, and a user At least one of the behavior information; the determining sub-module, configured to determine, according to the parameter information, a voice interaction scenario corresponding to a current driving state of the vehicle.

As an achievable manner, the external driving environment information includes road condition information and/or weather information, and the vehicle status information includes vehicle self-condition information and/or vehicle warning sound information.

As an achievable manner, the vehicle warning sound information includes a type of the vehicle warning sound or a number of broadcasts of the vehicle warning sound.

As an achievable manner, the parameter information includes user behavior information, and the acquiring sub-module includes: a sending unit, configured to send to the device that stores the user behavior information Obtaining an instruction, the acquiring instruction carries an authorization code preset by the user or an identifier of the vehicle; and a receiving unit, configured to receive, after the device verifies the authorization code or the identifier of the vehicle is legal, User behavior information.

As an achievable manner, the parameter information includes user behavior information, and the acquiring sub-module is specifically configured to receive user behavior information input by the user.

As an achievable manner, the user behavior information includes a user to-do event.

As an achievable manner, the user to-be-scheduled event includes a moment when the user's pending event occurs; the voice broadcast module includes: a determining unit, configured to determine, according to the occurrence time of the user pending event Broadcasting the time of the first voice to the user; the broadcast unit is configured to broadcast the first voice to the user when the time determined by the determining unit arrives.

For the beneficial effects of the above-mentioned achievable manners, the beneficial effects of the voice evoking device can be referred to the advantages of the voice evoke method in the above-mentioned various implementation manners, and details are not described herein again.

In another aspect, the present invention provides a voice evoked device, including: a processor, configured to acquire a voice interaction scenario, and determine a corresponding first voice according to the voice interaction scenario; and an output device coupled to the processor, configured to: Broadcasting the first voice to a user, the first voice being a voice prompting a user to interact with the vehicle or a device on the vehicle; An input device, coupled to the processor, for receiving operation information of the user according to the first voice input; the processor is further configured to perform a corresponding operation according to the operation information obtained by the input device.

In an implementation manner, the input device is specifically configured to receive a user operation instruction input by the user according to the first voice; the processor is specifically configured to determine, according to the user operation instruction, the user Whether the operation is a user operation performed by the user indicated by the first voice, and when the user operation is determined to be a user operation performed by the user indicated by the first voice, instructing the output device to stop broadcasting the first voice.

In an implementation manner, the input device is specifically configured to receive a second voice input by the user according to the content suggested by the first voice, where the first voice is used to prompt the user to prompt for the first voice. The content is subjected to a selection operation, and the second voice is a result of the user's selection; the processor is specifically configured to perform a corresponding operation according to the second voice.

As an achievable manner, the input device is further configured to acquire parameter information related to driving of the vehicle; wherein the parameter information includes at least one of external driving environment information, vehicle status information, and user behavior information; The processor is specifically configured to determine, according to the parameter information, a voice interaction scenario corresponding to a current driving state of the vehicle.

As an achievable manner, the external driving environment information includes Traffic information and/or weather information, the vehicle status information includes vehicle self status information and/or vehicle warning sound information.

As an achievable manner, the vehicle warning sound information includes a type of the vehicle warning sound or a number of broadcasts of the vehicle warning sound.

As an achievable manner, the parameter information includes user behavior information, and the output device is further configured to send an acquisition instruction to the device that stores the user behavior information, where the acquisition instruction carries the authorization code preset by the user. Or the identifier of the vehicle; the input device is specifically configured to receive user behavior information that is sent by the device after verifying the authorization code or the identifier of the vehicle is legal.

As an achievable manner, the parameter information includes user behavior information, and the input device is specifically configured to receive user behavior information input by the user.

As an achievable manner, the user behavior information includes a user to-do event.

As an achievable manner, the user to-be-scheduled event includes a moment when the user's pending event occurs; the processor is further configured to: determine to broadcast to the user according to the moment of occurrence of the user's pending event The moment of the first voice; the output device is specifically configured to broadcast the first voice to the user when the time arrives.

For the beneficial effects of the voice evoking device provided by the foregoing achievable manners, reference may be made to the beneficial effects brought by the voice evoking method in the above various achievable manners, and details are not described herein again.

In another aspect, the present invention provides a voice evoking device for a vehicle, including: an onboard processor, an onboard output device, and an onboard input device; the onboard processor is configured to acquire a voice interaction scenario, and according to The voice interaction scenario determines a corresponding first voice; the onboard output device is coupled to the onboard processor, and is configured to broadcast the first voice to a user, where the first voice is a prompting user and the a voice that interacts with the device or the device on the vehicle; the onboard input device is coupled to the onboard processor for receiving operational information of the user according to the first voice input; The processor is further configured to perform a corresponding operation according to the operation information obtained by the onboard input device.

In another aspect, the present invention provides a vehicle-mounted Internet operating system, comprising: a voice control unit, determining a corresponding first voice according to the acquired voice interaction scenario and broadcasting the message to the user; and operating the control unit, according to the operation information acquired by the vehicle input device Controlling the voice evoking system to perform a corresponding operation; wherein the operation information is input to the vehicle input device by the user according to the first voice.

In the present invention, the voice interaction scene corresponding to the current driving state of the vehicle is acquired, and the traffic worker is automatically evoked by the voice interaction scene. The voice function of the user broadcasts the first voice corresponding to the current voice interaction scene to prompt the user to interact with the vehicle or the device on the vehicle, so that the system of the vehicle receives the operation information of the user according to the first voice input. After that, corresponding operations are performed according to the operation information to ensure interaction with the user and meet the interaction requirements of the user. The application automatically evokes the voice for the user when the voice interaction scene is obtained, provides the user with rich voice content, facilitates the user to interact with the vehicle, does not require the user to manually trigger the voice interaction function of the vehicle, and improves the human-computer interaction. In addition, the acquired voice interaction scene may correspond to the driving state of the vehicle. Since the driving state of the vehicle is relatively rich, the voice interaction scene corresponding to the driving state of the vehicle is also rich, thereby enabling the present invention to The different driving states of the vehicle actively evoke the voice function of the vehicle, which improves the applicability of the voice arousal of the vehicle.

S102‧‧‧Steps

S102‧‧‧Steps

S103‧‧‧Steps

S201‧‧‧ steps

S202‧‧‧Steps

S301‧‧‧Steps

S302‧‧‧Steps

S401‧‧‧Steps

S402‧‧‧Steps

S403‧‧‧Steps

S404‧‧‧Steps

S501‧‧‧ steps

S502‧‧‧Steps

S601‧‧‧Steps

S602‧‧‧Steps

S701‧‧‧Steps

S702‧‧‧Steps

S703‧‧‧Steps

S704‧‧‧Steps

S705‧‧‧Steps

S706‧‧‧Steps

10‧‧‧Getting module

11‧‧‧Determining the module

101‧‧‧Get submodules

1011‧‧‧Send unit

1012‧‧‧ Receiving unit

102‧‧‧Determining submodules

12‧‧‧Voice Broadcasting Module

121‧‧‧Determining unit

122‧‧‧ broadcast unit

13‧‧‧ receiving module

14‧‧‧Processing module

20‧‧‧ processor

21‧‧‧Output equipment

22‧‧‧ Input equipment

23‧‧‧Storage

800‧‧‧In-vehicle system

802‧‧‧Processing components

804‧‧‧Storage

806‧‧‧Power components

808‧‧‧Multimedia components

810‧‧‧Audio components

812‧‧‧Input/Output Interface

814‧‧‧Sensor components

816‧‧‧Communication components

820‧‧‧ processor

31‧‧‧Voice Control Unit

32‧‧‧Operation Control Unit

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description of the drawings used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are Some embodiments of the invention may be used to obtain other figures from these figures without departing from the prior art.

1 is a schematic diagram of an optional networking mode of the present invention; FIG. 2 is a schematic flowchart of a voice arousing method according to an embodiment of the present invention; FIG. 3 is a schematic flowchart of a voice arousing method according to an embodiment of the present invention; FIG. 4 is a schematic flowchart of a voice arousing method according to an embodiment of the present invention; FIG. FIG. 6 is a schematic flowchart of a voice arousing method according to an embodiment of the present invention; FIG. 8 is a schematic flowchart of a voice arousing method according to an embodiment of the present invention; FIG. 8 is a schematic diagram of a voice arousing method according to an embodiment of the present invention; FIG. 9 is a schematic structural diagram of a voice arousing device according to an embodiment of the present invention; FIG. 10 is a schematic structural diagram of a voice arousing device according to an embodiment of the present invention; FIG. 11 is a schematic structural diagram of a voice arousing device according to an embodiment of the present invention; FIG. 12 is a schematic structural diagram of a voice arousal device according to an embodiment of the present invention; FIG. 13 is a schematic structural diagram of an in-vehicle system according to an embodiment of the present invention; FIG. 14 is a schematic diagram of an in-vehicle Internet operating system according to an embodiment of the present invention; Schematic diagram of the structure.

Exemplary embodiments will be described in detail herein, examples of which are illustrated in the drawings. When the following description refers to the drawings, the same numerals in the different figures represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with aspects of the invention as detailed in the appended claims.

The vehicle involved in the embodiments of the present invention includes, but is not limited to, an automobile or a motorcycle, an electric car or a motorcycle, an electric bicycle, an electric balance vehicle, a remote control vehicle, and the like, and a small aircraft (for example, an unmanned aerial vehicle, a small person) Aircraft, remotely piloted aircraft, and various variants. The vehicle involved herein may be a single oil road vehicle, a single steam road vehicle, a fuel-air combined vehicle, or a power-assisted electric vehicle. The embodiment of the present invention does not do the type of the vehicle. By definition, the vehicle has a corresponding onboard system. The following embodiments are described by taking a vehicle as an example of a vehicle.

The voice arousing method, device and device according to the embodiment of the present invention may be applied to the networking mode shown in FIG. 1. The network architecture in FIG. 1 may include an in-vehicle system of a vehicle and a wireless network. The in-vehicle system may be provided with a user operation interface. Alternatively, the user operation interface may be a voice interface for user input, or an interface for receiving a user-triggered operation command, such as a flash drive interface, a USB interface, and a seat belt. Insert the mouth and so on. The vehicle can be connected to a wireless network. Alternatively, the wireless network can be a 2G network, a 3G network, a 4G network or a 5G network, or a Wireless Fidelity (WIFI) network. Optionally, the wireless network may also be an Internet of Things or a car network. The specific type or specific form of the network is not limited in the embodiment of the present invention, as long as it can provide an interface for the vehicle to access and obtain data. . The in-vehicle system can access different network servers, such as a mail server, a newsletter server, a cloud server, etc., and only three servers are shown in FIG. 1, but are not limited thereto.

Optionally, the method according to the embodiment of the present invention may be an in-vehicle system. Alternatively, the in-vehicle system may be a system integrated with a vehicle on a vehicle, such as a car navigation system and/or an in-vehicle entertainment system. It may also be a system containing a vehicle and other equipment such as sensors, which can interact with the vehicle and the user. The embodiment of the present invention does not limit the specific content of the in-vehicle system, as long as it can actively evoke the voice function of the vehicle. In the following embodiments, the execution subject is an in-vehicle system, but the execution subject of the embodiment of the present invention is not limited thereto.

The voice arousing method, device and device according to the embodiments of the present invention are directed to solving the technical problem that the voice arousal in the prior art requires the user to manually evoke, and the targeted object is relatively simple, the applicability is not high, and the human-computer interaction is not intelligent enough. .

The technical solutions of the present invention will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other for the same or Similar concepts or processes may not be described in some embodiments.

FIG. 2 is a schematic flowchart diagram of a voice arousing method according to an embodiment of the present invention. The embodiment is directed to the in-vehicle system proactively broadcasting the first voice corresponding to the current voice interaction scenario to the user according to the determined voice interaction scenario, and executing the operation information input by the user according to the content prompted by the first voice. Corresponding operations to ensure active interaction with the user, providing users with a convenient and specific process. As shown in FIG. 2, the method may include: S101: Acquire a voice interaction scenario.

Specifically, the vehicle is a vehicle, and the voice interaction scenario involved in the embodiment of the present invention may be a scenario that can actively trigger the in-vehicle system to evoke the voice function to broadcast the voice to the user and interact with the user. Optionally, the voice interaction scenario may be a scenario in which the in-vehicle system can actively perform a corresponding operation to the user voice prompting, for example, actively prompting the user to notify the user of abnormal information (eg, the trunk of the vehicle is not closed) to enable the user to eliminate the abnormality of the vehicle. Voice scene. Optionally, the voice interaction scenario may also be that the in-vehicle system actively searches for the potential voice interaction requirement of the user by learning or acquiring some parameter information related to the driving of the vehicle (for example, the vehicle often passes through a certain geographic location), and actively initiates a prompt to the user or The scene of inquiring and interacting with the user, for example, the user usually starts at home at 8:00, and goes to the convenience store to buy the breakfast at 8:30, and the in-vehicle system can learn the location information of the vehicle to the vehicle, when the user 8 When you start, you can ask the user if you want to go to the convenience store to buy breakfast at 8:30, and then take the initiative to navigate the convenience store to the user according to the user's voice response. Actively play soothing music for the user. For example, the in-vehicle system can log in the user's mailbox server to obtain some mails of the user after authorization by the user. If there is a user in a mail to drive to a certain place at a certain time, the vehicle system can be after the user gets on the vehicle. Proactively initiate a voice inquiry to the user, that is, ask the user whether to go to the place to have a meeting, thereby performing a corresponding operation according to the obtained user's voice answer. That is, the technical solution related to the embodiment of the present invention does not require the user to manually trigger the voice interaction function of the vehicle, but the different voice interaction scenarios automatically evoke the voice for the user, and provide the user with rich voice content, which is convenient for the user to interact with the vehicle. To improve the intelligence of human-computer interaction.

Optionally, the voice interaction scenario in the embodiment of the present invention may be determined in any manner. For example, the voice interaction scenario may be determined by using a running state of the vehicle. The driving state of the vehicle may be the surrounding environment information of the vehicle, the vehicle speed of the vehicle, etc., or may be whether there is a user operation inside the vehicle, whether the vehicle itself has an unsafe factor, or the like, and the type of the driving state of the vehicle is not in the embodiment of the present invention. Make a limit. Optionally, different vehicle driving states may correspond to different voice interaction scenarios, and regardless of the driving state of the vehicle, the vehicle system may actively evoke the vehicle as long as the vehicle system can acquire the voice interaction scene corresponding to the driving state of the vehicle. The voice function, that is, the voice interaction scenario that automatically evokes the voice function of the vehicle in the embodiment of the present invention is rich and has high applicability. Of course, the voice interaction scenario is determined by the driving state of the vehicle. The embodiment of the present invention is not limited thereto.

S102: Determine a corresponding first voice according to the voice interaction scenario, And broadcasting the first voice to the user, the first voice being a voice prompting the user to interact with the vehicle or the device on the vehicle.

Specifically, after the in-vehicle system obtains the voice interaction scenario, the first voice corresponding to the voice interaction scenario may be determined. Optionally, the in-vehicle system may pre-establish a mapping relationship between different voice interaction scenarios and different broadcast voices. Once the in-vehicle system determines the voice interaction scenario corresponding to the current driving state, the in-vehicle system actively broadcasts the first message to the user. voice. Optionally, the form of the voice interaction scenario may be an information form, so the in-vehicle system may perform keyword recognition on the voice interaction scenario, and compose the identified keyword into a first voice through a voice synthesis technology, and broadcast the message to the user. The method for determining the first voice according to the acquired voice interaction scenario is not limited in the embodiment of the present invention.

It should be noted that the voice content of the first voice is a voice content that prompts the user to interact with the vehicle or the device on the vehicle. The “interaction” referred to herein may be a voice interaction between the user and the vehicle or the device on the vehicle. It may also be a manually operated interaction of the user with the vehicle or equipment on the vehicle, and may also be other ways of interaction of the user with the vehicle or equipment on the vehicle. Optionally, the device on the vehicle may be a car radio, a driving recorder or other in-vehicle device.

S103: Receive operation information of the user according to the first voice input, and perform a corresponding operation according to the operation information.

Specifically, after the user receives the first voice broadcast by the in-vehicle system, the corresponding user operation is performed according to the content of the first voice, and the user operation may be a voice input of the user, which may be a manual operation of the user. When the car After receiving the operation information input by the user, the loading system performs corresponding operations according to the operation information to ensure interaction with the user and meet the interaction requirements of the user.

The voice evoke method provided by the embodiment of the present invention obtains a voice interaction scenario, and automatically evokes the voice function of the vehicle through the voice interaction scenario to broadcast the first voice corresponding to the current voice interaction scenario to prompt the user to communicate with the vehicle or the traffic. The device on the tool interacts, so that after receiving the operation information of the user according to the first voice input, the system of the vehicle performs a corresponding operation according to the operation information to ensure interaction with the user and satisfy the interaction of the user. Claim. The method provided by the embodiment of the present invention automatically evokes a voice for a user when acquiring a voice interaction scenario, and provides a rich voice content for the user, so that the user can interact with the device on the vehicle or the vehicle without requiring the user to manually trigger the traffic. The voice interaction function of the tool improves the intelligence of human-computer interaction; in addition, the voice interaction scene acquired above can correspond to the driving state of the vehicle, and the determined voice interaction scene is also made due to the rich driving state of the vehicle. It is richer, and thus enables the present invention to actively evoke the voice function of the vehicle for different vehicle driving states, thereby improving the applicability of the voice arousal of the vehicle.

FIG. 3 is a schematic flowchart diagram of a voice arousing method according to an embodiment of the present invention. This embodiment relates to a specific process for acquiring a voice interaction scenario. On the basis of the embodiment shown in FIG. 2, further, as shown in FIG. 3, the foregoing S101 may specifically include: S201: acquiring parameter information related to driving of the vehicle; The parameter information includes at least one of external driving environment information, vehicle status information, and user behavior information.

Specifically, the vehicle is a vehicle, and the external driving environment information may be external driving environment information, the vehicle status information may be vehicle status information, and the vehicle's own status information may be vehicle condition information. The vehicle warning tone information may be vehicle warning tone information. Therefore, the in-vehicle system can obtain parameter information related to the driving of the vehicle in real time, and the parameter information may include at least one of external driving environment information, vehicle status information, and user behavior information. Optionally, the external driving environment information includes road condition information and/or weather information, and the vehicle status information includes vehicle condition information and/or vehicle warning sound information, and the user behavior information may include a user's pending event, and may further include a user An operation of the vehicle (for example, the user inserts a flash drive into the USB interface of the vehicle), and may also include a certain behavior habit of the user (for example, the user is accustomed to doing the same thing at a certain time).

Optionally, the road condition information may include whether the road is congested, or whether a traffic accident occurs on the road ahead or whether there is a surveillance camera in the road section, and the vehicle condition information may include information about the vehicle's own facilities, such as whether the engine is faulty or the brake pad. Whether the information is good or not, the above warning sound information of the vehicle may include volume information of the warning sound of the vehicle, tone information of the warning sound of the vehicle, and the like. Optionally, the vehicle warning tone information may also be a type of vehicle warning tone or a number of broadcasts of the vehicle warning tone.

Optionally, when the parameter information is road condition information, the vehicle system can establish a communication with the traffic road monitoring server through the wireless network shown in FIG. Connect to obtain traffic information, and also obtain traffic information through radio broadcast; optionally, when the above parameter information is weather information, the vehicle system can obtain weather information through the network server in the wireless network shown in FIG. When the above parameter information is the vehicle condition information, the vehicle system can obtain the vehicle condition information through the vehicle's own different sensors or software detection; when the above parameter information is the vehicle warning sound information, the vehicle system can be obtained through the cooperation of the vehicle audio and the processor. The vehicle warning sound information.

Optionally, when the parameter information includes the user behavior information, the specific manner in which the in-vehicle system obtains the user behavior information may include two possible implementation manners, as follows: The first possible implementation manner: Referring to FIG. 4, The S201 may specifically include: S301: Send an acquisition instruction to a device that stores the user behavior information, where the acquisition instruction carries an authorization code preset by the user or an identifier of the vehicle. Alternatively, the identification of the vehicle may be the identity of the vehicle.

Specifically, the device for storing user behavior information may be a user terminal, and may be various servers in the network, such as a mailbox server, a short message server, a cloud server, and the like. Optionally, the user may pre-configure the vehicle with an authorization code, and authorize the vehicle to obtain the behavior information of the user from the device that stores the user behavior information. Optionally, the user does not need to configure an authorization code for the vehicle, and the user can register or reserve the identifier of the vehicle in the device that stores the user behavior information, and when the vehicle corresponding to the identifier accesses the device that stores the user behavior information, You can save information about user behavior Get information about the user's behavior in the device. Based on this, the in-vehicle system can request to obtain user behavior information by sending an acquisition instruction to the device that stores the user behavior information.

S302: Receive user behavior information that is sent by the device after verifying the authorization code or the identifier of the vehicle is legal.

Specifically, after the device storing the user behavior information receives the acquisition instruction of the vehicle, the device performs the corresponding legal judgment according to the content carried in the acquisition instruction, that is, determines whether the authorization code in the acquisition instruction is a pre-configured authorization code or a judgment of the user. Obtain whether the identification of the vehicle carried in the instruction is the identification of the vehicle authorized by the user. When the device storing the user behavior information determines that the authorization code in the acquisition instruction or the identification of the vehicle is legal, the user behavior information can be sent to the in-vehicle system to ensure the privacy of the user behavior information.

The second possible implementation mode: the in-vehicle system can directly receive user behavior information input by the user.

In this possible implementation, the in-vehicle system can provide a user input interface to the user. The user input interface can be a device access interface, a voice input interface, or a handwriting interface of the display screen. Therefore, the user can insert a device that stores his own behavior information or a device such as a flash drive into the device access interface, so that the vehicle system can read the user behavior information, or obtain the voice input by the user through the voice input interface. The corresponding speech recognition technology obtains the user behavior information, and can also obtain the user behavior information of the user's handwriting input through the handwriting interface.

So far, through the first possible implementation or the second The implementation of the vehicle, the in-vehicle system can obtain user behavior information.

S202: Determine, according to the parameter information, a voice interaction scenario corresponding to a current driving state of the vehicle.

Specifically, after the in-vehicle system obtains the parameter information, the in-vehicle system can determine the current vehicle driving state, and thereby determine the voice interaction scenario corresponding to the current driving state of the vehicle. Optionally, the in-vehicle system may determine, by using a preset first mapping relationship, a voice interaction scenario corresponding to a current driving state of the vehicle, where the first mapping relationship may include different parameter information, different vehicle driving states, and different voice interaction scenarios. Correspondence between them. The embodiment of the present invention does not limit the manner of the voice interaction scenario corresponding to the current driving state of the vehicle according to the parameter information, as long as the voice interaction scenario corresponding to the current driving state of the vehicle can be determined according to the parameter information.

The voice arousing method provided by the embodiment of the present invention collects parameter information related to the driving of the vehicle, and determines a voice interaction scene corresponding to the current driving state of the vehicle according to the parameter information, thereby actively arousing the voice of the vehicle according to the voice interaction scene. Function to interact with the user. The technical solution of the embodiment of the invention ensures the diversity of the voice interaction scene through the diversity of the parameter information, thereby enriching the manner of actively arousing the voice function of the vehicle, and improving the applicability of the voice arousal of the vehicle.

FIG. 5 is a schematic flowchart diagram of a voice arousing method according to an embodiment of the present invention. The embodiment relates to a specific process in which the user inputs a user operation instruction to the in-vehicle system according to the content indicated by the first voice, and the in-vehicle system determines whether to stop broadcasting the first voice according to the user operation instruction. In the above implementation On the basis of the example, further, as shown in FIG. 5, the foregoing S103 may specifically include: S401: Receive a user operation instruction input by the user according to the first voice.

Specifically, the first voice in the embodiment is used to instruct the user to perform a corresponding user operation. Therefore, after the user receives the first voice broadcast by the in-vehicle system, the user operation indicated by the first voice is performed according to the first voice. For the in-vehicle system, after the user performs the user operation, the in-vehicle system can detect the operation instruction corresponding to the user operation through an interaction interface between the vehicle and the user, or an interaction interface between the device and the user on the vehicle. .

For example, when the user does not wear a seat belt during the running of the vehicle, a beep sound is sounded inside the vehicle (the beep sound is a vehicle warning sound), that is, the current vehicle running state is a beep sound, and the in-vehicle system determines that the vehicle travel state corresponds to The voice interaction scenario is a seat belt prompting scenario, and the in-vehicle system determines that the first voice corresponding to the scenario is “Please fasten the seat belt” according to the seat belt prompting scenario, and broadcasts to the user; when the user receives the first voice The seat belt is fastened according to the content of the first voice, whereby the in-vehicle system can detect the operation of the user through the seat belt insertion port provided by the vehicle, and then obtain the operation instruction corresponding to the user operation as “inserted seat belt ".

For another example, when the user does not close the left side door during the running of the vehicle, the inside of the vehicle will also sound a beep sound (the beep sound may be different from the type of the beep sound in the above example), that is, the current vehicle running state is a beep sound. When the sound is activated, the in-vehicle system determines that the voice interaction scene corresponding to the driving state of the vehicle is the left side door abnormal scene, and the in-vehicle system determines that the first voice corresponding to the scene is “please close the left side door” according to the door abnormal scene, and broadcasts to the user. After the user receives the first voice, the left door is closed according to the content of the first voice, so that the vehicle system can detect the operation of the user through the door detection interface provided by the vehicle, and then obtain the corresponding operation of the user. The operation instruction is "closed door".

In either of the above manners, when the current vehicle driving state is the beep sound, the in-vehicle system can determine the voice interaction scene corresponding to the current vehicle driving state, and then determine the first voice corresponding to the voice interaction scene, that is, through the text to The method of the text to speech (TTS) prompts the user to the clear voice content, and the user does not know the meaning of the beep sound when the user sounds the beep sound in the car. The solution of the embodiment of the invention can make the user intuitively and effectively know. The meaning of the beep sound improves the user experience. Optionally, the in-vehicle system can distinguish the voice interaction scene corresponding to the sounding of the warning sound of the vehicle by the type of the warning sound of the vehicle or the number of warning sounds of the vehicle, for example, when the warning sound of the vehicle is “drip”, the in-vehicle system determines The corresponding voice interaction scene should be a seat belt prompt scene. When the vehicle warning sound is “哒哒”, the vehicle system determines that the corresponding voice interaction scene is a door abnormal scene.

It should be noted that, for the above-mentioned beep, the in-vehicle system broadcasts the intuitive first voice to the user as an example. Optionally, when the vehicle is in a state of other abnormality in the vehicle, for example, the vehicle's oil quantity is low, the vehicle's engine is overheated, the vehicle's glass water is exhausted, etc., the vehicle system may also Determining a corresponding voice interaction scenario according to the current driving state, so as to play a first voice corresponding to the voice interaction scenario to the user, to prompt the user to perform the operation of the user indicated by the first voice, so that the user can intuitively and effectively obtain the vehicle The demand is convenient for the user to discover the abnormality of the vehicle or the improper operation of the user in time, thereby further improving the user experience.

S402: Determine, according to the user operation instruction, whether the operation of the user is a user operation performed by a user indicated by the first voice. If yes, execute S403, and if no, execute S404.

S403: Stop broadcasting the first voice.

S404: Play the first voice according to a preset period.

Specifically, after the in-vehicle system detects the user operation instruction, it is determined, according to the user operation instruction, whether the operation currently performed by the user is a user operation performed by the user indicated by the first voice; when the in-vehicle system detects that the operation currently performed by the user is When the voice indicates the user operation performed by the user, the in-vehicle system stops broadcasting the first voice. When the in-vehicle system detects that the operation currently performed by the user is not the user operation performed by the user indicated by the first voice, the in-vehicle system plays the preset period. The first voice may be the first voice played once every few seconds. Optionally, when the driving state of the vehicle for which the first voice is directed is a beep sound, when the in-vehicle system detects that the operation currently performed by the user is not the user operation performed by the user indicated by the first voice, the device may repeatedly repeat the sound. Beep sound.

The voice arousing method provided by the embodiment of the present invention prompts the user to perform a user operation performed by the user through the first voice, and then, after the user performs the user operation according to the instruction of the first voice, according to the user operation finger input by the user The user is judged whether the operation of the user is a user operation performed by the user indicated by the first voice, and the first voice is stopped when the system of the vehicle detects that the operation performed by the user is a user operation performed by the user indicated by the first voice. The method provided by the embodiment of the invention can enable the user to intuitively know the needs of the vehicle, and facilitate the user to timely discover the abnormality of the vehicle or the improper operation of the user, thereby further improving the user experience.

FIG. 6 is a schematic flowchart diagram of a voice arousing method according to an embodiment of the present invention. The embodiment relates to a specific process in which the user inputs a second voice to the in-vehicle system according to the content suggested by the first voice, and the in-vehicle system interacts with the user according to the second voice. In this embodiment, the first voice is used to prompt the user to perform a selection operation on the content prompted by the first voice, and the second voice is a selection result of the user. On the basis of the foregoing embodiment, further, as shown in FIG. 6, the foregoing S103 may specifically include: S501: Receive a second voice input by the user according to the content suggested by the first voice.

Specifically, the first voice in the embodiment is used to prompt the user to perform a selection operation on the content prompted by the first voice. Therefore, after the user receives the first voice broadcasted by the in-vehicle system, the user selects according to the content suggested by the first voice, and inputs the selection result to the in-vehicle system by means of voice, and the selection result is the second voice. For example, when the in-vehicle system determines that the voice interaction scene corresponding to the current driving state is the driving mode prompting scene, the in-vehicle system broadcasts the first voice “whether the driving mode is switched to the economic mode” to the user, and the user may input the selection result for the first voice. , for example, the user can be an input "Yes" or "No, I have to choose comfort mode." For another example, suppose that the parameter information acquired by the in-vehicle system is a user pending event, and the event to be held by the user is “Nine-point driving to the airport”, and the first voice determined by the in-vehicle system is “Do you drive to the airport now?” When the user starts the vehicle, the in-vehicle system broadcasts the first voice, prompting the user to do the event.

S502: Perform a corresponding operation according to the second voice.

Specifically, after receiving the second voice input by the user, the in-vehicle system determines an operation corresponding to the second voice according to a matching internal mechanism, and then performs the operation to ensure interaction between the vehicle and the user. Continuing with the example illustrated in S501 as an example, assuming that the second voice input by the user is “No, I want to select a comfort mode”, the in-vehicle system can learn the content of the second voice through the voice recognition technology, and then according to the second voice. The content switches the driving mode to the comfort mode to meet the user's interaction with the vehicle.

Optionally, when the parameter information acquired by the in-vehicle system is a user to-do event, and the user to-do event includes a moment of occurrence of the user to-do event, after the in-vehicle system determines the first voice corresponding to the parameter information, as shown in FIG. As shown in FIG. 7 , the foregoing broadcasting the first voice to the user may include: S601: Determine, according to the moment of occurrence of the user to-be-scheduled event, a moment to broadcast the first voice to the user.

S602: Broadcast the first voice to the user when the time arrives.

Specifically, the user includes a user when the on-board system acquires a user pending event. When the to-be-occurrence event occurs, the in-vehicle system can determine the time at which the first voice is broadcast to the user according to the occurrence time, and when the time arrives, broadcast the first voice to the user. Optionally, if the time at which the first voice is broadcasted when the vehicle is started has not arrived, the first voice does not need to be broadcast to the user, and the first voice is broadcasted when the time arrives, or the time when the first voice is broadcasted If the vehicle has not been activated yet, the in-vehicle system can transmit the first voice to the user's terminal, and broadcast the first voice to the user through the user's terminal, so as to prompt the user.

In order to more clearly introduce the solution of the embodiment, a specific example is given below. Referring to the example diagram shown in FIG. 8, in FIG. 8, it is assumed that the parameter information acquired by the in-vehicle system is a user to-do event, and the user to-do event includes At the moment when the to-be-created event occurs, the user's pending event is "the user's small X has a meeting at the A position at 9 o'clock", and the on-board system determines that the first speech is broadcasted at 8:30, the first determined by the in-vehicle system. The voice is "After half an hour there is a meeting in the A position, it is expected to arrive in 20 minutes, now whether to go." As shown in FIG. 8, the method specifically includes: S701: The in-vehicle system determines the parameter information as “the user small X has a meeting at the A position at 9 o'clock”.

S702: The in-vehicle system determines, according to the parameter information, that the voice interaction scenario corresponding to the current driving state is “9 points have a meeting in the A position”.

S703: The in-vehicle system determines, according to the voice interaction scenario, that the time for playing the first voice is 8:30.

S704: When the in-vehicle system arrives at 8:30, the first voice is broadcast to the user. "After half an hour, there is a meeting in the A position, and it is expected to arrive in 20 minutes. Whether to go now."

S705: The user inputs the second voice “Yes, go now” to the in-vehicle system according to the first voice.

S706: The in-vehicle system broadcasts "OK, now navigation for you to the A location".

Optionally, when the user is driving, it is assumed that the vehicle system collects another parameter information in real time, and the parameter information is assumed to be road condition information, and the road condition information is “the road congestion ahead”, and the vehicle system determines the voice corresponding to the current driving state. The interaction scenario is a “congested scenario”, and the in-vehicle system determines that the first voice corresponding to the congestion scenario is “front congestion, may go late to the A location, and notify the conference initiator that the phone is small Y”, so that the user receives the first voice. The second voice can be selected and input to the in-vehicle system. If the second voice is “Yes”, the in-vehicle system can initiate a call request to the conference initiator according to the second voice.

The voice evoke method provided by the embodiment of the present invention, the first voice indicates that the user performs a selection operation on the content prompted by the first voice, thereby obtaining a second voice input by the user according to the first voice, and performing corresponding according to the second voice. The operation is to make the human-computer interaction more intelligent; and the method provided by the embodiment of the present invention can know the potential triggering voice requirement of the user in advance, actively evoke the voice for the user, and prompt the user to wait for the event, and prevent the user from forgetting to do. Events provide users with convenience and further enhance the user experience.

Hereinafter, a voice arousing device according to one or more embodiments of the present invention will be described in detail. The voice evoking device can be implemented on the basis of the vehicle In the infrastructure, it can also be implemented in an interactive system of vehicles and wireless networks. Those skilled in the art will appreciate that the voice arousing device can be constructed using commercially available hardware components configured by the steps taught by the present solution. For example, the processor component (or processing module, processing unit, determining module, etc.) can be implemented using components such as a microcontroller, a microcontroller, a microprocessor, and the like from companies such as Texas Instruments, Intel Corporation, and ARM Corporation.

The following is an embodiment of the apparatus of the present invention, which can be used to carry out the method embodiments of the present invention. For details not disclosed in the embodiment of the device of the present invention, please refer to the method embodiment of the present invention.

FIG. 9 is a schematic structural diagram of a voice arousing device according to an embodiment of the present invention. The voice arousing device may be implemented by a combination of software, hardware, or both. As shown in FIG. 9, the voice arousing device includes: an acquisition module 10, a determination module 11, a voice broadcast module 12, a receiving module 13, and a processing module 14.

The obtaining module 10 is configured to obtain a voice interaction scenario, and the determining module 11 is configured to determine a corresponding first voice according to the voice interaction scenario acquired by the acquiring module 10, where the first voice is a prompting user. a voice that interacts with the device or the device on the vehicle; the voice broadcast module 12 is configured to broadcast the first voice determined by the determining module 11 to the user; and the receiving module 13 is configured to: Receiving operation information of the first voice input determined by the user according to the determining module 11; the processing module 14 is configured to receive according to the receiving module 13 The operation information performs the corresponding operation.

The voice arousal device provided by the embodiment of the present invention may perform the foregoing method embodiments, and the implementation principle and technical effects thereof are similar, and details are not described herein again.

In a possible implementation manner of the embodiment of the present invention, the receiving module 13 is specifically configured to receive a user operation instruction that is input by the user according to the first voice; the processing module 14 is specifically configured to be used according to the Determining, by the user operation instruction, whether the operation of the user is a user operation performed by the user indicated by the first voice, and determining that the operation of the user is a user operation performed by the user indicated by the first voice The voice broadcast module 12 stops broadcasting the first voice.

In another possible implementation manner of the embodiment of the present invention, the receiving module 13 is configured to receive a second voice input by the user according to the content suggested by the first voice, where the first voice is used to prompt the user. Performing a selection operation on the content suggested by the first voice, the second voice is a selection result of the user; and the processing module 14 is specifically configured to perform a corresponding operation according to the second voice.

Further, on the basis of the foregoing embodiment shown in FIG. 9, FIG. 10 is a schematic structural diagram of a voice arousing device according to an embodiment of the present invention. In FIG. 10, the acquisition module 10 includes: an acquisition sub-module 101, configured to acquire parameter information related to driving of a vehicle; wherein the parameter information includes external driving environment information, vehicle status information, and a user. At least one of the behavioral information; The determining sub-module 102 is configured to determine, according to the parameter information, a voice interaction scenario corresponding to a current driving state of the vehicle.

Optionally, the external driving environment information includes road condition information and/or weather information, and the vehicle status information includes vehicle self-condition information and/or vehicle warning sound information. Optionally, the vehicle warning sound information includes a type of the vehicle warning sound or a number of broadcasts of the vehicle warning sound.

Optionally, the parameter information includes the user behavior information, and the method further includes: the sending unit 1011, configured to: send, by the sending unit 1011, an acquiring instruction to the device that stores the user behavior information, where The obtaining instruction carries the authorization code preset by the user or the identifier of the vehicle; and the receiving unit 1012 is configured to receive user behavior information that is sent by the device after verifying the authorization code or the identifier of the vehicle is legal.

Optionally, the parameter information includes user behavior information, and the obtaining sub-module 101 is specifically configured to receive user behavior information input by the user.

Optionally, the user behavior information includes a user to-do event.

Optionally, the foregoing user to-be-scheduled event includes a moment when the user's pending event occurs. Referring to FIG. 11 , a schematic structural diagram of a voice evoking device according to an embodiment of the present invention is provided. In FIG. 11, the voice broadcast module 12 may include: a determining unit 121, configured to determine, according to an occurrence time of the user to-be-scheduled event, a time to broadcast the first voice to the user; the broadcast unit 122, Used for the determination determined by the determining unit 121 When the time arrives, the first voice is broadcast to the user.

The voice arousal device provided by the embodiment of the present invention may perform the foregoing method embodiments, and the implementation principle and technical effects thereof are similar, and details are not described herein again.

FIG. 12 is a schematic diagram of a hardware structure of a voice arousing device according to an embodiment of the present invention. The voice arousing device may be integrated in the in-vehicle system in the above embodiment, or may be a stand-alone in-vehicle system. As shown in FIG. 12, the voice arousing device can include a processor 20, an output device 21, an input device 22, a storage 23, and at least one communication bus 24. The communication bus 24 is used to implement a communication connection between components. The storage 23 may include a high speed RAM storage, and may also include a non-volatile storage NVM, such as at least one disk storage, in which various programs may be stored for performing various processing functions and implementing the method of the embodiment. step.

Optionally, the processor 20 can be, for example, a central processing unit (CPU), an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), and a programmable logic. Implemented by a device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor, or other electronic component coupled to the input device 22 and the output device via an in-vehicle line or wireless connection twenty one.

Optionally, the input device 22 may include multiple input devices, for example, at least one of a user-oriented user interface, a device-oriented device interface, and a transceiver. Optionally, the device-oriented device interface may be a wired interface for data transmission between the device and the device, or may be used for data or command transmission between the device and the device. The hardware insertion interface (such as a USB interface, a serial port, an interface between the body hardware devices, etc.); optionally, the user-oriented user interface can be, for example, a user-oriented control button or a voice for receiving voice input. The input device and the touch sensing device (such as a touch screen with a touch sensing function, a touch panel, etc.) for receiving the user's touch input; optionally, the transceiver may be a radio frequency transceiver chip with a communication function, a baseband processing chip, and a transceiver. Antennas, etc. The voice arousing device in the embodiment of the present invention is a universal voice arousing device, which can be applied to any control system or control device or other type of device. Optionally, the output device 21 may be a corresponding output interface or a voice playback device or a transceiver with a communication function.

Alternatively, the voice arousing device may be a voice arousing device for a vehicle, for example, may be a voice arousing device for a vehicle, a voice arousing device for an aircraft, a voice arousing device for a waterway vehicle, and the like. Regarding the specific content of the voice-activated device for the vehicle, the present invention provides another embodiment for introduction. Please refer to the following embodiments, which will not be described in detail herein.

In the embodiment of the present invention, the processor 20 is configured to acquire a voice interaction scenario, and determine a corresponding first voice according to the voice interaction scenario. The output device 21 is coupled to the processor 20, and is configured to broadcast to the user. a first voice, the first voice being a voice prompting a user to interact with the vehicle or a device on the vehicle; an input device 22 coupled to the processor 20 for receiving a user according to the Operational information of the first voice input; The processor 20 is further configured to perform a corresponding operation according to the operation information obtained by the input device 22.

The voice evoke device provided by the embodiment of the present invention can perform the foregoing method embodiments, and the implementation principle and technical effects are similar, and details are not described herein again.

Optionally, the input device 22 is configured to receive a user operation instruction that is input by the user according to the first voice; and the processor 20 is configured to determine, according to the user operation instruction, the operation of the user. Whether it is a user operation performed by the user indicated by the first voice, and when determining that the operation of the user is a user operation performed by the user indicated by the first voice, instructing the output device 21 to stop broadcasting the first voice.

Optionally, the input device 22 is configured to receive a second voice input by the user according to the content suggested by the first voice, where the first voice is used to prompt the user to prompt the content for the first voice. Performing a selection operation, the second voice is a result of the user's selection; the processor 20 is specifically configured to perform a corresponding operation according to the second voice.

Optionally, the input device 22 is further configured to acquire parameter information related to driving of the vehicle; wherein the parameter information includes at least one of external driving environment information, vehicle status information, and user behavior information; The processor 20 is specifically configured to determine, according to the parameter information, a voice interaction scenario corresponding to a current driving state of the vehicle.

Optionally, the external driving environment information includes road condition information and/or Weather information, the vehicle status information includes vehicle self status information and/or vehicle warning sound information. Optionally, the vehicle warning sound information includes a type of the vehicle warning sound or a number of broadcasts of the vehicle warning sound.

Optionally, the parameter information includes user behavior information, and the output device 21 is further configured to send an acquisition instruction to the device that stores the user behavior information, where the acquisition instruction carries the authorization code or the preset preset by the user. The input device 22 is specifically configured to receive user behavior information that is sent by the device after verifying the authorization code or the identifier of the vehicle is legal.

Optionally, the parameter information includes user behavior information, and the input device 22 is specifically configured to receive user behavior information input by the user.

Optionally, the user behavior information includes a user to-do event.

Optionally, the user to-be-scheduled event includes a moment when the user's pending event occurs; the processor 20 is further configured to: determine to broadcast the first to the user according to the moment of occurrence of the user pending event a moment of a voice; the output device 21 is specifically configured to broadcast the first voice to the user when the time arrives.

The voice evoke device provided by the embodiment of the present invention can perform the foregoing method embodiments, and the implementation principle and technical effects are similar, and details are not described herein again.

FIG. 13 is a block diagram of an in-vehicle system according to an embodiment of the present invention. The in-vehicle system 800 can be a device that integrates multiple functions, such as For example, the in-vehicle system may be an on-board computer, a car machine, or the like, and the in-vehicle system may include the above-described voice arousing device.

Referring to Figure 13, the in-vehicle system 800 can include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, and a sensor component. 814, and a communication component 816.

Processing component 802 typically controls the overall operation of in-vehicle system 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. Processing component 802 can include one or more processors 820 to execute instructions to perform all or part of steps S101 through S706 in the voice arousing method described above. In addition, processing component 802 can include one or more modules to facilitate interaction between component 802 and other components. For example, processing component 802 can include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

The storage 804 is configured to store various types of data to support operation at the onboard system 800. Examples of such materials include instructions for any application or method operating on the in-vehicle system 800, contact information, phone book data, messages, pictures, movies, and the like. The storage 804 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, Disk or CD.

Power component 806 provides power to various components of in-vehicle system 800. Power component 806 can include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for in-vehicle system 800.

The multimedia component 808 includes a screen that provides an output interface between the in-vehicle system 800 and a user. In some embodiments, the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor may sense not only the boundary of the touch or sliding action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 can also include a front camera.

The audio component 810 is configured to output and/or input an audio signal. For example, the audio component 810 includes a microphone (MIC) that is configured to receive an external audio signal when the in-vehicle system 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may be further stored in the storage 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting an audio signal.

The I/O interface 812 provides an interface between the processing component 802 and the peripheral interface module. The peripheral interface module can be a click wheel, a button, or the like. These buttons may include, but are not limited to, a volume button, a start button, and a lock button.

Sensor assembly 814 includes one or more sensors for providing on-board system 800 with various aspects of status assessment. In some embodiments, the Sensor assembly 814 may also include an acceleration sensor, a gyro sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

Communication component 816 is configured to facilitate wired or wireless communication between in-vehicle system 800 and other devices. The in-vehicle system 800 can access a wireless network based on communication standards such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, communication component 816 receives broadcast signals or broadcast associated information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the in-vehicle system 800 can be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), A programming gate array (FPGA), controller, microcontroller, microprocessor, or other electronic component implementation for performing the voice arousing method described above.

Based on the above description of the universal voice evoking device in FIG. 12, the present invention further provides another embodiment. The present embodiment specifically discloses a voice evoking device for a vehicle. Alternatively, the voice arousing device may be integrated in the central control system of the vehicle, for example, may be integrated in the in-vehicle system involved in the above embodiments. Alternatively, the in-vehicle system may be a system integrated with a vehicle on a vehicle, such as a car navigation The system and/or the in-vehicle entertainment system may also be a system including a vehicle and other devices of the vehicle such as sensors. Optionally, the voice arousing device for the vehicle includes but is not limited to: a vehicle device, an additional control device after the vehicle leaves the factory, and the like.

Specifically, the voice arousing device for a vehicle may include: an onboard input device, an onboard processor, an onboard output device, and other additional devices. It should be noted that the airborne in the "airborne input device", "airborne output device", and "airborne processor" according to the embodiments of the present invention may be an "vehicle input device" carried on a vehicle, "Vehicle output device" and "vehicle processor" may also be "onboard input device", "onboard output device", "onboard processor" carried on the aircraft, or may be carried on other types of vehicles. The above device does not limit the meaning of "airborne" in the embodiment of the present invention. Taking the vehicle as an example, the onboard input device may be an in-vehicle input device, the onboard processor may be an onboard processor, or the onboard output device may be an onboard output device.

The onboard processor can use various application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs) depending on the type of vehicle being installed. ), Field Programmable Gate Array (FPGA), central processing unit (CPU), controller, microcontroller, microprocessor or other electronic component implementation and used to perform the above methods. The onboard processor is coupled to the onboard input device and the onboard output device via an in-vehicle line or wireless connection. According to the method in the embodiment corresponding to Figures 2 to 8 above, the airborne The processor is configured to obtain a voice interaction scenario, and determine a corresponding first voice according to the voice interaction scenario.

The above-mentioned onboard output device may be an interface capable of interacting with a user (eg, a voice broadcast device, a speaker, a headset, etc.) depending on the type of vehicle installed, or may be established with a user's handheld device or the like. A wirelessly transmitted transceiver that can be coupled to the onboard input device and the onboard processor via an in-vehicle line or wirelessly. According to the method in the embodiment corresponding to the foregoing Figures 2 to 8, the onboard output device is configured to broadcast the first voice to the user, the first voice being a prompting user and the vehicle or the vehicle The voice that the device interacts with.

The above-described onboard input device may include a variety of input devices depending on the type of vehicle being installed, for example, may include at least one of a user-facing in-vehicle user interface, a device-oriented in-vehicle device interface, and a transceiver. Optionally, the device-oriented device interface may be a wired interface for data transmission between the device and the device (for example, a connection interface with a driving recorder on a center console of the vehicle, and a center console of the vehicle The interface between the doors, the hardware interface between the vehicle's center console and the car air conditioner, or a hardware plug-in interface for data transmission between the device and the device (such as USB interface, serial port, etc.) And may also be a seat belt socket of a vehicle, an interface between a hardware device such as a vehicle engine and other control devices, etc.; optionally, the user-oriented vehicle user interface may be, for example, a steering wheel control button for a vehicle, Central control button for large vehicles or small vehicles, voice input for receiving voice input Equipment (for example, a microphone placed on the steering wheel or operating rudder, a central sound collection device, etc.), and a touch-sensing device (such as a touch screen with touch sensing function, a touchpad, etc.) that the user receives the user's touch input; The transceiver may be a radio frequency transceiver chip having a communication function in a vehicle, a baseband processing chip, and a transceiver antenna. According to the method in the embodiment corresponding to FIG. 2 to FIG. 8 , the onboard input device is configured to receive operation information of the user according to the first voice input, and the onboard processor is further configured to perform according to the onboard input. The operation information obtained by the device performs a corresponding operation.

Further, the above-mentioned on-board processor may also be used in all or part of the steps in the embodiment of the present invention in the push method of the above-mentioned message, and details are not described herein again.

A computer/processor readable storage medium, wherein the storage medium stores program instructions for causing the computer/processor to execute: acquiring a voice interaction scene; determining a corresponding number according to the voice interaction scene a voice, and broadcasting the first voice to a user, the first voice being a voice prompting a user to interact with the vehicle or a device on the vehicle; receiving an operation of the user according to the first voice input Information, and perform corresponding operations according to the operation information.

Optionally, the receiving user performs the corresponding operation according to the operation information of the first voice input, and according to the operation information, specifically: receiving a user operation instruction input by the user according to the first voice; Determining, according to the user operation instruction, whether the operation of the user is a user operation performed by the user indicated by the first voice; if yes, stopping broadcasting the first voice.

Optionally, the receiving user performs the corresponding operation according to the operation information of the first voice input, and the corresponding operation is performed according to the operation information, and specifically includes: receiving a second voice input by the user according to the content suggested by the first voice The first voice is used to prompt the user to perform a selection operation on the content prompted by the first voice, the second voice is a selection result of the user, and a corresponding operation is performed according to the second voice.

Optionally, the acquiring the voice interaction scenario corresponding to the current driving state of the vehicle specifically includes: acquiring parameter information related to driving of the vehicle; wherein the parameter information includes external driving environment information, vehicle status information, and user At least one of the behavior information; determining a voice interaction scenario corresponding to the current driving state of the vehicle according to the parameter information.

Optionally, the external driving environment information includes road condition information and/or weather information, and the vehicle status information includes vehicle self-condition information and/or vehicle warning sound information. Optionally, the vehicle warning sound information includes a type of the vehicle warning sound or a number of broadcasts of the vehicle warning sound.

Optionally, the parameter information includes user behavior information, and the obtaining parameter information related to the driving of the vehicle includes: Sending an acquisition instruction to a device storing the user behavior information, where the acquisition instruction carries an authorization code preset by the user or an identifier of the vehicle; and receiving the device to verify the authorization code or the vehicle Identifies the user behavior information sent after being legal.

Optionally, the parameter information includes user behavior information, and the obtaining parameter information related to the driving of the vehicle specifically includes: receiving user behavior information input by the user.

Optionally, the user behavior information includes a user to-do event.

Optionally, the user to-be-scheduled event includes the moment when the user's pending event occurs, and the reporting the first voice to the user, specifically: determining, according to the occurrence time of the user pending event, determining the location Describe a moment when the user broadcasts the first voice; when the time arrives, broadcast the first voice to the user.

The above readable storage medium may 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, Disk or CD.

Based on the above embodiments, the present invention also provides an in-vehicle internet operating system. It can be understood by those skilled in the art that the in-vehicle Internet operating system can manage and control the hardware of the hardware or the in-vehicle system of the voice arousing device shown in FIG. 12 or FIG. 13 or the The hardware of the voice evoking device of the vehicle and the computer program of the software resource involved in the present invention are software running directly on the voice evoking device or the voice evoking device for the vehicle or the above-mentioned vehicle system of FIG. . The operating system may be an interface between the user and the voice arousing device or the voice arousing device for the vehicle, or may be an interface between the hardware and other software.

The in-vehicle Internet operating system provided by the present invention can interact with other modules or functional devices on the vehicle to control the functions of the corresponding modules or functional devices.

Specifically, taking the vehicle in the above embodiment as a vehicle and the voice arousing device as a vehicle on the vehicle as an example, based on the development of the vehicle-mounted Internet operating system and the vehicle communication technology provided by the present invention, the vehicle is no longer independent of the communication network. Outside the road, vehicles can be connected to a server or a network server to form a network to form an in-vehicle Internet. The in-vehicle Internet system can provide voice communication services, location services, navigation services, mobile Internet access, vehicle emergency rescue, vehicle data and management services, and in-vehicle entertainment services.

The structure of the in-vehicle Internet operating system provided by the present invention is described in detail below. FIG. 14 is a schematic structural diagram of an in-vehicle Internet operating system according to an embodiment of the present invention. As shown in FIG. 14, the operating system provided by the present invention includes: a voice control unit 31, which determines a corresponding first voice according to the acquired voice interaction scenario and broadcasts to the user; and the operation control unit 32 performs operations according to the vehicle input device. Capital The control voice arousal system performs a corresponding operation; wherein the operation information is input to the vehicle input device by the user according to the first voice.

Specifically, the voice evoke system in this embodiment may include a part of the hardware of the voice evoking device in the above embodiment, and may include, for example, the processor and the output device in the above embodiment. The voice evoking system can also be integrated in the above-mentioned vehicle Internet operating system, and can also be used as a system for assisting the vehicle Internet operating system to perform corresponding functional operations.

The voice control unit 31 can control the voice arousing system to determine a voice interaction scenario corresponding to the current driving state according to at least one type of parameter information of the collected outside driving environment information, the vehicle state information, and the user behavior information. Optionally, the voice interaction scenario may be acquired by the voice control unit 31, or may be controlled by the voice control unit 31 by the voice arousing system.

In addition, the in-vehicle input device in this embodiment may include the input device in the foregoing embodiment, that is, after the voice control unit 31 controls the voice arousing system to broadcast the first voice to the user, the user inputs the operation information to the in-vehicle input device according to the first voice. Thus, the operation control unit 32 can control the voice evoking system to perform a corresponding operation according to the operation information.

Further, the in-vehicle Internet operating system may control the corresponding components to perform the above-mentioned FIG. 2 to FIG. 8 through the above-mentioned voice control unit 31 and the operation control unit 32, or on the basis of the above two units, in combination with other units. Methods.

Finally, it should be noted that the above embodiments are only for explaining the technical solutions of the present invention, and are not limited thereto; although the present invention is described with reference to the foregoing embodiments. The detailed description is made clear, and those skilled in the art should understand that the technical solutions described in the foregoing embodiments may be modified, or some or all of the technical features may be equivalently replaced; and these modifications or replacements, The essence of the corresponding technical solutions is not deviated from the scope of the technical solutions of the embodiments of the present invention.

Claims (35)

A voice arousing method includes: acquiring a voice interaction scenario; determining a corresponding first voice according to the voice interaction scenario, and broadcasting the first voice to a user, where the first voice is prompting a user and a vehicle or the traffic The device on the tool performs voice interaction; receives operation information of the user according to the first voice input, and performs a corresponding operation according to the operation information. According to the method of claim 1, wherein the receiving user performs the corresponding operation according to the operation information of the first voice input and according to the operation information, specifically: receiving the user according to the first And a user operation instruction input by the voice; determining, according to the user operation instruction, whether the operation of the user is a user operation performed by the user indicated by the first voice; if yes, stopping broadcasting the first voice. According to the method of claim 1, wherein the receiving user performs the corresponding operation according to the operation information of the first voice input and according to the operation information, specifically: receiving the user according to the first The second voice input by the content suggested by the voice, the first voice is used to prompt the user to perform a selection operation on the content prompted by the first voice, and the second voice is a selection result of the user; according to the second The voice performs the corresponding operation. The party according to any one of claims 1 to 3 of the patent application scope The method of obtaining the voice interaction scenario includes: acquiring parameter information related to driving of the vehicle; wherein the parameter information includes at least one of external driving environment information, vehicle state information, and user behavior information. And determining, according to the parameter information, a voice interaction scenario corresponding to a current driving state of the vehicle. The method of claim 4, wherein the outside driving environment information comprises road condition information and/or weather information, the vehicle status information including vehicle self status information and/or vehicle warning sound information. The method of claim 5, wherein the vehicle warning sound information includes a type of the vehicle warning tone or a number of broadcasts of the vehicle warning tone. The method of claim 4, wherein the parameter information includes user behavior information, and the obtaining parameter information related to driving of the vehicle specifically includes: sending an acquisition instruction to a device storing the user behavior information. And the obtaining instruction carries the authorization code preset by the user or the identifier of the vehicle; and receiving user behavior information sent by the device after verifying the authorization code or the identifier of the vehicle is legal. The method of claim 4, wherein the parameter information includes user behavior information, and the obtaining parameter information related to driving of the vehicle includes: Receive user behavior information entered by the user. The method of claim 7 or 8, wherein the user behavior information comprises a user pending event. The method of claim 9, wherein the user to-be-scheduled event includes a moment when the user is to be held, and the broadcasting the first voice to the user, specifically: according to the user At the moment of occurrence of the to-be-created event, determining a time at which the first voice is broadcast to the user; and when the time arrives, broadcasting the first voice to the user. A voice evoking device includes: an obtaining module, configured to acquire a voice interaction scenario; and a determining module, configured to determine a corresponding first voice according to the voice interaction scenario acquired by the acquiring module, where the first voice is a voice prompting the user to interact with the vehicle or the device on the vehicle; the voice broadcast module is configured to broadcast the first voice determined by the determining module to the user; and the receiving module is configured to receive And the processing module is configured to perform a corresponding operation according to the operation information received by the receiving module. The device of claim 11, wherein the receiving module is configured to receive a user operation instruction input by a user according to the first voice; The processing module is configured to determine, according to the user operation instruction, whether the operation of the user is a user operation performed by a user indicated by the first voice, and determine that the operation of the user is the first When the voice indicates the user operation performed by the user, the voice broadcast module is instructed to stop broadcasting the first voice. The device of claim 11, wherein the receiving module is configured to receive a second voice input by the user according to the content suggested by the first voice, where the first voice is used to prompt the user Performing a selection operation on the content suggested by the first voice, where the second voice is a result of the user's selection; and the processing module is specifically configured to perform a corresponding operation according to the second voice. The device according to any one of the preceding claims, wherein the obtaining module comprises: an obtaining sub-module for acquiring parameter information related to driving of the vehicle; wherein the parameter The information includes at least one of the external driving environment information, the vehicle status information, and the user behavior information; and the determining sub-module is configured to determine, according to the parameter information, a voice interaction scenario corresponding to the current driving state of the vehicle. The device of claim 14, wherein the outside driving environment information comprises road condition information and/or weather information, the vehicle status information including vehicle own status information and/or vehicle warning sound information. According to the device of claim 15, wherein The vehicle warning tone information includes a type of the vehicle warning tone or a number of broadcasts of the vehicle warning tone. The device of claim 14, wherein the parameter information includes user behavior information, and the acquiring sub-module includes: a sending unit, configured to send an acquisition instruction to a device that stores the user behavior information The obtaining instruction carries the authorization code preset by the user or the identifier of the vehicle; and the receiving unit is configured to receive the user behavior sent by the device after verifying the authorization code or the identifier of the vehicle is legal News. The device of claim 14, wherein the parameter information includes user behavior information, and the obtaining sub-module is specifically configured to receive user behavior information input by the user. The device of claim 17 or 18, wherein the user behavior information comprises a user pending event. The device of claim 19, wherein the user to-do event includes a moment when the user is to be held; the voice broadcast module includes: a determining unit, configured to perform according to the user a moment when the event occurs, determining a time at which the first voice is broadcast to the user; and a broadcast unit configured to broadcast the first voice to the user when the time determined by the determining unit arrives. A voice evoking device includes: a processor, configured to acquire a voice interaction scenario, and according to the voice communication Determining a corresponding first voice; an output device coupled to the processor, configured to broadcast the first voice to a user, the first voice being a prompting user and the vehicle or the vehicle a voice that the device interacts with; an input device coupled to the processor, configured to receive operation information of the user according to the first voice input; the processor is further configured to use the operation information obtained by the input device Perform the appropriate action. The device according to claim 21, wherein the input device is specifically configured to receive a user operation instruction input by a user according to the first voice; and the processor is specifically configured to operate according to the user Directing, determining whether the operation of the user is a user operation performed by a user indicated by the first voice, and indicating the output when determining that the operation of the user is a user operation performed by a user indicated by the first voice The device stops broadcasting the first voice. The device according to claim 21, wherein the input device is configured to receive a second voice input by the user according to the content suggested by the first voice, where the first voice is used to prompt the user to target The content suggested by the first voice performs a selecting operation, and the second voice is a result of the user's selection; and the processor is specifically configured to perform a corresponding operation according to the second voice. According to any one of claims 21 to 23, The device, wherein the input device is further configured to acquire parameter information related to driving of the vehicle; wherein the parameter information includes at least one of external driving environment information, vehicle status information, and user behavior information; The device is specifically configured to determine, according to the parameter information, a voice interaction scenario corresponding to a current driving state of the vehicle. The device of claim 24, wherein the outside driving environment information comprises road condition information and/or weather information, the vehicle status information including vehicle own status information and/or vehicle warning sound information. The device of claim 25, wherein the vehicle warning sound information includes a type of the vehicle warning tone or a number of broadcasts of the vehicle warning tone. The device of claim 24, wherein the parameter information includes user behavior information; the output device is further configured to send an acquisition instruction to a device that stores the user behavior information, where the acquisition instruction carries The user preset preset authorization code or the identifier of the vehicle; the input device is specifically configured to receive user behavior information that is sent by the device after verifying the authorization code or the identifier of the vehicle is legal. The device of claim 24, wherein the parameter information includes user behavior information, and the input device is specifically configured to receive user behavior information input by the user. According to the device of claim 27 or 28, The user behavior information includes a user pending event. The device of claim 29, wherein the user pending event includes a moment of occurrence of the user pending event; the processor is further configured to: according to the moment when the user is to be held, Determining a time at which the first voice is broadcast to the user; the output device is specifically configured to broadcast the first voice to the user when the time arrives. A voice evoke device for a vehicle, comprising: an onboard processor, an onboard output device, and an onboard input device; the onboard processor is configured to acquire a voice interaction scenario, and determine a corresponding according to the voice interaction scenario a first voice; the onboard output device coupled to the onboard processor for broadcasting the first voice to a user, the first voice being a prompting user with the vehicle or the vehicle The on-board input device is coupled to the onboard processor for receiving operation information of the user according to the first voice input; the onboard processor is further configured to The operation information obtained by the onboard input device performs a corresponding operation. A voice arousing device for a vehicle according to claim 31, wherein the onboard input device comprises at least one of a user-facing in-vehicle user interface, a device-oriented in-vehicle device interface, and a transceiver. A voice arousal device for a vehicle according to claim 32, wherein the user-oriented vehicle user bread One or more of the following: a central console control button; a steering wheel control button; a voice receiving device; a touch sensing device. The voice arousing device for a vehicle according to any one of claims 31 to 33, wherein the on-board processor is further configured to perform any one of the above-mentioned claims 2 to 10 The method described in the item. An in-vehicle Internet operating system, comprising: a voice control unit, determining a corresponding first voice according to the acquired voice interaction scenario and broadcasting the message to the user; and operating the control unit to control the voice arousing system to perform corresponding according to the operation information acquired by the vehicle input device The operation information is that the user inputs to the in-vehicle input device according to the first voice.