Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to solve the problem that the prior art cannot guarantee that a user can normally acquire a vehicle-mounted service, the embodiment of the invention provides a vehicle-mounted communication system and a vehicle-mounted communication method.
As shown in fig. 1, the vehicle-mounted communication system provided in the embodiment of the present invention includes: the system comprises a one-touch control device 101, aterminal device 102, an in-vehicle communication device 103, a cloudcomputing platform server 104 and a value-added server (not shown in fig. 1) for providing a value-added service;
the one-key control device 101 is installed on a fixed part of the vehicle and used for establishing connection with theterminal equipment 102 in a direct or short-distance communication mode after a user presses a start key, and driving theterminal equipment 102 to establish connection with the vehicle-mountedcommunication device 103;
for the convenience of user operation, as a preferred embodiment, the fixed part of the vehicle is specifically a steering wheel, however, in the actual using process, the invention does not limit the fixed part of the vehicle, and the fixed part of the vehicle may also be another part on the vehicle, which is convenient for the user to touch, and details are not described here.
In this embodiment, the terminal device may be a vehicle-mounted terminal, a mobile phone, a portable computer, a game machine, a PDA, or the like, and during actual use, the terminal device may also be other device capable of performing wireless or wired communication and having a capability of obtaining value-added services.
In this embodiment, the short-range communication mode may be WiFi, WiMax, bluetooth, infrared, and other proprietary wireless protocols.
Theterminal equipment 102 is used for establishing connection with the vehicle-mountedcommunication device 103 in a direct or short-distance communication mode after establishing connection with the one-key control device 101, receiving the first voice prompt message forwarded by the vehicle-mountedcommunication device 103, playing the first voice prompt message to a user, receiving a voice command for starting value-added service sent by the user according to the first voice prompt message, and transmits the voice command for starting the value added service to the vehicle-mountedcommunication device 103, receives the value added service voice instruction command transmitted by the user, and transmits the value added service voice instruction command to the in-vehicle communication device 103, receives the value added service control information forwarded by the in-vehicle communication device 103, starting the corresponding value-added service according to the value-added service control information, establishing connection with a value-added server providing the value-added service through the vehicle-mountedcommunication device 103, and acquiring the specific value-added service from the value-added server;
the specific value added service may include, but is not limited to, a navigation service, a video/audio playing service, and the like. If the value-added service is the navigation service, the value-added service voice indication command is specifically a voice indication command of a target navigation address; if the value added service is a video and audio playing service, the value added service voice instruction command is specifically a voice instruction command containing target video and audio description information, for example: the voice indication information including the name of the song or video program, or the voice indication information including the name of the singer, etc., will not be described in detail here.
In the embodiment, the direct or short-range communication method used by theterminal device 102 to establish connection with the in-vehicle communication apparatus 103 includes any one or a combination of the following: WiFi, bluetooth, infrared, wired or USB, etc.
The vehicle-mountedcommunication device 103 is used for performing network search after establishing connection with theterminal device 102 to acquire more than one network access mode, acquiring a target network access mode from the more than one network access mode, establishing connection with the cloudcomputing platform server 104 by adopting the target network access mode, receiving first voice prompt information sent by the cloudcomputing platform server 104, forwarding the first voice prompt information to theterminal device 102, receiving a voice command for starting the value-added service sent by theterminal device 102, forwarding the voice command for starting the value-added service to the cloudcomputing platform server 104, receiving value-added service control information sent by the cloudcomputing platform server 104, and forwarding the value-added service control information to theterminal device 102, when theterminal device 102 starts the corresponding value-added service according to the value-added service control information, establishing connection with a value-added server providing the value-added service by adopting a target network access mode;
the cloudcomputing platform server 104 comprises a non-specific person voice recognition module, the cloudcomputing platform server 104 is used for sending first voice prompt information to the vehicle-mountedcommunication device 103, the first voice prompt information is used for indicating a user to input a value-added service type, receiving a voice command for starting the value-added service forwarded by the vehicle-mountedcommunication device 103, analyzing the voice command for starting the value-added service through the non-specific person voice recognition module to obtain a value-added service starting command, starting the corresponding value-added service according to the value-added service starting command, receiving the value-added service voice command forwarded by the vehicle-mountedcommunication device 103, analyzing the value-added service voice command through the non-specific person voice recognition module to obtain indication information related to the value-added service, generating value-added service control information according to the indication information related to the value-added service, and sending the value-added service control information to the vehicle-mountedcommunication device 103 in a short message issuing or mobile.
Further, the vehicle-mountedcommunication device 103 may be specifically configured to receive network access mode indication information sent by a user, and acquire a target network access mode from the more than one network access modes according to the network access mode indication information.
Specifically, the vehicle-mountedcommunication device 103 may include a display touch screen, and when more than one network access mode is searched, the searched network access modes are displayed on the display screen in a list form, network access mode indication information triggered by a user through touching a corresponding network access mode on the display screen is received, and a target network access mode is acquired according to the network access mode indication information; the vehicle-mountedcommunication device 103 may also include a voice playing and recording unit, and when more than one network access mode is searched, the searched network access mode is played to the user through the voice playing and recording unit, and the network access mode indication information sent by the user in a voice form is received through the voice playing and recording unit, and the target network access mode is obtained according to the network access mode indication information; the vehicle-mountedcommunication device 103 may further receive network access mode indication information sent by the user through theterminal device 102, and acquire a target network access mode according to the network access mode indication information.
The technical solution provided in the embodiment of the present invention does not limit the specific implementation manner of the vehicle-mountedcommunication device 103 receiving the network access mode indication information sent by the user, and in the actual use process, the vehicle-mountedcommunication device 103 may also receive the network access mode indication information sent by the user in other manners, which is not described in detail herein.
Alternatively, the vehicle-mountedcommunication device 103 may be specifically configured to respectively obtain signal strengths of more than one network access method, and obtain a target network access method from the more than one network access methods according to the signal strengths;
alternatively, the vehicle-mountedcommunication device 103 may be specifically configured to acquire the target network access method from the more than one network access methods according to a preset network access policy.
In this embodiment, the network access policy may be a default network access manner of the vehicle-mountedcommunication device 103, and if the network access policy may be set as a default network access manner of the mobile operator network, the vehicle-mountedcommunication device 103 may access the mobile operator network according to the network access policy when searching for the network access manner of the mobile operator network; the network access policy may also be a network access condition, and for example, the network access policy may be set to access the network in the first searched network access manner, and when the vehicle-mountedcommunication device 103 searches for more than one network access manner, the first searched network access manner may be acquired as the target network access manner according to the network access policy. Of course, in the actual using process, the network access policy may also be set to other forms, which is not described herein.
In this embodiment, in order to further ensure reliable connection between theterminal device 102 and the cloudcomputing platform server 104 on the network side and the value added server providing the value added service, the vehicle-mountedcommunication device 103 may be further configured to periodically detect the signal strength of the target network access manner, reselect a new target network access manner if the signal strength of the target network access manner is smaller than a preset signal strength threshold, and establish connection with the cloudcomputing platform server 104 and the value added server providing the value added service by using the new target network access manner.
According to the vehicle-mounted communication system provided by the embodiment of the invention, a user only needs to press the starting key of the one-key control device arranged on the fixed part of the vehicle, so that the terminal equipment can be connected with the cloud computing platform server on the network side through the vehicle-mounted communication device through the one-key control device, and the value-added service is obtained through a voice control mode, so that the operation steps of the vehicle-mounted service performed by the user are simplified, the user experience of the vehicle-mounted service is improved, and the vehicle-mounted communication system is basically controlled only through a voice command without any manual operation in the driving process. The vehicle-mounted communication device can perform network search, a target network access mode is selected from more than one searched network access modes, and the target network access mode is adopted to establish connection with the cloud computing platform server and the server providing the value-added service, so that the reliability of network connection between the terminal equipment in the vehicle-mounted communication system and the cloud computing platform server and the server providing the value-added service is improved, and the problem that the terminal equipment can only perform information interaction with the server on the network side through the access network provided by a mobile operator in the prior art, and when the network signal of the operator is not good or unavailable, the terminal equipment cannot establish connection with the server on the network side, so that the vehicle-mounted service cannot be obtained is solved. The technical scheme provided by the embodiment of the invention can ensure the normal connection between the terminal equipment and the cloud computing platform server on the network side and the server providing the value-added service, thereby ensuring that the user normally obtains the vehicle-mounted service and improving the vehicle-mounted service experience of the user.
Further, in this embodiment, the cloudcomputing platform server 104 stores a plurality of broad spectrum speech feature libraries in advance, for example: the system comprises a broad-spectrum voice feature library set according to a place name, a broad-spectrum voice feature library set according to an audio and video name, a broad-spectrum voice feature library set according to a person name and the like. The unspecific person voice recognition module is specifically used for analyzing a voice command for starting the value-added service, extracting first voice characteristic information, searching a first broad-spectrum voice characteristic library according to the first voice characteristic information, and acquiring a value-added service starting command corresponding to the first voice characteristic information; and the voice instruction module is specifically used for analyzing the value added service voice instruction command, extracting second voice characteristic information, searching a second broad-spectrum voice characteristic library according to the second voice characteristic information, and acquiring the value added service related instruction information corresponding to the second voice characteristic information.
The first broad-spectrum speech feature library has first broad-spectrum speech feature information corresponding to the first speech feature information, and the second broad-spectrum speech feature library has second broad-spectrum speech feature information corresponding to the second speech feature information.
The first and second speech feature information may include spectral distribution information of the speech command, time domain waveform information, short-time spectrum of the speech frame, formant frequency and bandwidth, nasal sound joint feature, spectrum correlation feature, pitch feature, power spectrum, frame energy, speech intensity and variation trajectory feature, or may be a combination using one or more of the above feature information.
For example: when the value-added service is a navigation service, the unspecified person voice recognition module analyzes a voice command for starting the navigation service, extracts corresponding first voice characteristic information (such as frequency spectrum distribution information and the like), searches a broad-spectrum voice characteristic library set according to a starting command keyword according to the first voice characteristic information, and obtains a navigation service starting command corresponding to the first voice characteristic information; the unspecified person voice recognition module analyzes the voice indication command of the target navigation address, extracts corresponding second voice characteristic information (such as frequency spectrum distribution information) and searches a broad-spectrum voice characteristic library set according to the place name according to the second voice characteristic information, and the target navigation address corresponding to the second voice characteristic information is obtained from the broad-spectrum voice characteristic library.
Wherein, furthermore, the preferable mode of the navigation service can be also as follows: when a user selects a value-added service of the system as a navigation service, the user sends a voice command (such as 'i want to navigate'), a non-specific voice recognition module analyzes the voice command for starting the navigation service (such as 'i want to navigate'), extracts corresponding first voice characteristic information (such as spectrum distribution information of the voice command 'i want to navigate'), searches a broad-spectrum voice characteristic library set according to a starting command keyword according to the extracted first voice characteristic information, and acquires a navigation service starting command (such as 'i want to navigate') corresponding to the first voice characteristic information from the broad-spectrum voice characteristic library set according to the starting command keyword, so that the corresponding navigation service is further started according to the recognized (namely acquired) voice command (such as 'i want to navigate'); after the navigation service is started, the unspecified person voice recognition module analyzes a voice indication command (such as 'dragon building') of a target navigation address, extracts second voice characteristic information (such as spectrum distribution information) corresponding to the voice indication command (such as 'dragon building'), searches a broad-spectrum voice characteristic library set according to a place name according to the second voice characteristic information, acquires the place name (such as 'dragon building') corresponding to the second voice characteristic information from the broad-spectrum voice characteristic library set according to the place name, and acquires the navigation address (such as the address of the 'dragon building') corresponding to the place name according to the recognized place name.
For another example: when the value-added service is video-audio on-demand service, the unspecified person voice recognition module analyzes a voice command for starting the video-audio on-demand service, extracts corresponding first voice characteristic information (such as frequency spectrum distribution information and the like), searches a broad-spectrum voice characteristic library set according to a starting command keyword according to the first voice characteristic information, and acquires a navigation service starting command corresponding to the first voice characteristic information; the unspecific person voice recognition module analyzes the voice instruction command containing the target video and audio description information, extracts corresponding second voice feature information (such as frequency spectrum distribution information) and searches a broad spectrum voice feature library set according to the video and audio description information according to the second voice feature information, and video and audio description information corresponding to the second voice feature information is obtained from the broad spectrum voice feature library.
Wherein, further, the preferred mode of the video-on-demand service may be: when the value added service selected by the user is video-audio on-demand service, after the user sends a voice command (such as watching video), the unspecified person voice recognition module analyzes the voice command (such as watching video) for starting the video-audio on-demand service, extracts first voice characteristic information (such as spectrum distribution information) corresponding to the voice command (such as watching video) of the video-audio on-demand service, searches a broad-spectrum voice characteristic library set according to a starting command keyword according to the first voice characteristic information, and acquires a starting video-audio on-demand service command (such as watching video) corresponding to the first voice characteristic information from the broad-spectrum voice characteristic library set according to the starting command keyword so as to start the corresponding video-audio on-demand service; after the video-on-demand service is started, the unspecified person voice recognition module analyzes a voice indication command containing target video-audio description information (such as 'love of hawthorn tree'), extracts second voice characteristic information (such as spectrum distribution information) corresponding to the voice indication command (such as 'love of hawthorn tree'), searches a broad spectrum voice characteristic library set according to the video-audio description information according to the second voice characteristic information, acquires the video-audio description information (such as 'love of hawthorn tree') corresponding to the second voice characteristic information from the broad spectrum voice characteristic library set according to the video-audio description information, and then acquires service information (such as 'love of hawthorn tree' of a playable movie) corresponding to the video-audio description information.
It should be noted that the broad-spectrum speech feature library provided in this embodiment is a set of broad-spectrum speech features extracted by collecting sounds of places, various people and the people in the whole china under different environments (different noise backgrounds), and the broad-spectrum speech feature library only depends on information of the existing "speech feature library" and does not depend on a speech feature training result of a certain person. The advantages are that: (1) the selected sample of the broad spectrum speech feature library is extensive and includes human utterances from different regions of different countries of the world. For example, in China, the pronunciation of people in almost every province, county, town and region in China is selected, people in different regions in the country are divided into several categories, such as the North China, the northeast China, the Minnan language region, the Guangdong language region and the like, the Mandarin spoken by people in different regions has local dialects with different characteristics, and after the people are classified respectively, the people in the regions with basically similar local dialects pronunciations are classified into one category, so that the completeness of a sample is considered, and the construction of a database is also considered to generate redundant information as little as possible; (2) extracting voice characteristic information of sounds or voice commands under different environments (noise backgrounds), such as voice commands generated after an automobile engine is started, voice commands generated under the conditions of wind dryness and fetal noises generated after an automobile window is opened, voice commands generated under the conditions of interference such as sudden plug-in of other people and the like, voice commands generated after the engine is closed and the like; (3) the broad-spectrum speech feature library comprises a Mandarin feature library and a local dialect feature library, wherein the local dialect library comprises a Minnan language library, a Guangdong language library, a Shanghai language library and the like.
At least one of the above-mentioned situations, such as situations of people in different regions or situations in different environments, has been considered in the first and/or second voice feature information, i.e., the first and/or second voice feature information is voice feature information extracted based on voice or voice commands of people in different regions, or the first and/or second voice feature information is voice feature information extracted based on voice or voice commands of people in different environments. This improves the recognition rate of voice commands to users or drivers in different regions.
Further, the broad-spectrum speech feature library also comprises a foreign language library, wherein the foreign language library comprises mainstream foreign language libraries such as an English library, a French library, a German library and a Japanese library. The system also has a feature library automatic recognition module which is used for analyzing the voice command sent by the user to distinguish the feature library corresponding to the voice command and automatically selecting the corresponding feature library. Therefore, the user can use the languages of different countries to send out voice commands in a mixed mode, the languages can be used in a mixed mode without being screened in advance, and the automatic recognition module of the library feature library can automatically recognize whether the voice commands are Chinese or foreign languages.
The broad-spectrum voice feature library established by the method is arranged in the cloud computing platform server, so that the dependence on a system of terminal equipment is reduced, the terminal equipment in front of a speaker is used as sound or voice command acquisition equipment, and the acquired sound or voice command data is transmitted to a background server group such as the cloud computing platform server for identification, so that high-performance identification calculation under a multi-server cluster architecture can be performed, and the large-scale voice feature library can be used without the voice identification capability of the terminal equipment.
In this embodiment, 95% of the voice information may be recognized by the unspecified person voice recognition module, in order to ensure that 100% of the voice information of the user can be recognized, and further improve the user experience of the vehicle-mounted service, optionally, as shown in fig. 1, the cloudcomputing platform server 104 may further include an unspecified person voice recognition manual agent module, where the unspecified person voice recognition manual agent module is configured to, when the unspecified person voice recognition module cannot recognize the voice command for starting the value-added service, and obtain a corresponding value-added service command, and/or, when the unspecified person voice recognition module cannot recognize the value-added service voice instruction command, and obtain the instruction information related to the value-added service.
As shown in fig. 2, an embodiment of the present invention further provides a vehicle-mounted communication method, including:
step 201, after a user presses a start key of a one-key control device, the one-key control device establishes connection with a terminal device in a direct or short-distance communication mode, wherein the one-key control device is arranged on a fixed part of a vehicle;
for the convenience of user operation, as a preferred embodiment, the fixed part of the vehicle is specifically a steering wheel, however, in the actual using process, the invention does not limit the fixed part of the vehicle, and the fixed part of the vehicle may also be another part on the vehicle, which is convenient for the user to touch, and details are not described here.
In this embodiment, the terminal device may be a vehicle-mounted terminal, a mobile phone, a portable computer, a game machine, a PDA, or the like, and during actual use, the terminal device may also be other device capable of performing wireless or wired communication and having a capability of obtaining value-added services.
In this embodiment, the short-range communication mode may be WiFi, WiMax, bluetooth, infrared, and other proprietary wireless protocols.
202, the terminal equipment establishes connection with the vehicle-mounted communication device in a direct or short-distance communication mode;
in this embodiment, the direct or short-range communication method used by the terminal device to establish connection with the vehicle-mounted communication apparatus includes any one or a combination of the following: WiFi, bluetooth, infrared, wired or USB, etc.
Step 203, the vehicle-mounted communication device carries out network search to acquire more than one network access mode, acquires a target network access mode from the more than one network access modes, and establishes connection with a cloud computing platform server by adopting the target network access mode;
in this embodiment, the vehicle-mounted communication device may directly search for available networks in the surrounding environment to obtain more than one network access mode; the vehicle-mounted communication device can also search the communication equipment with the network access function, acquire more than one network access mode adopted by the communication equipment with the network access function, and perform network access through the communication equipment in the subsequent network access process. Of course, in the actual using process, the vehicle-mounted communication device may also obtain more than one network access manner through other manners, which is not described in detail herein.
In this embodiment, the vehicle-mounted communication device may acquire the target network access mode from more than one network access modes through a plurality of methods, for example: the vehicle-mounted communication device can receive network access mode indication information sent by a user and acquire a target network access mode from more than one network access modes according to the network access mode indication information; for another example: the vehicle-mounted communication device can respectively acquire the signal intensity of the more than one network access modes and acquire a target network access mode from the more than one network access modes according to the signal intensity; the following steps are repeated: the vehicle-mounted communication device can acquire a target network access mode from more than one network access modes according to a preset network access strategy.
Step 204, the cloud computing platform server sends first voice prompt information to the terminal equipment through the vehicle-mounted communication device, wherein the first voice prompt information is used for indicating a user to input a value-added service type;
step 205, the terminal device plays the first voice prompt message to the user, receives a voice command for starting the value-added service sent by the user according to the first voice prompt message, and sends the voice command for starting the value-added service to the cloud computing platform server through the vehicle-mounted communication device;
step 206, the cloud computing platform server analyzes the voice command for starting the value-added service by adopting a non-specific human voice recognition technology to obtain a value-added service starting command, and starts a corresponding value-added server according to the value-added service starting command so that the value-added server provides specific value-added service;
step 207, the terminal equipment receives a value added service voice instruction command sent by a user, and sends the value added service voice instruction command to a cloud computing platform server through the vehicle-mounted communication device;
step 208, the cloud computing platform server analyzes the value-added service voice indication command by adopting a non-specific person voice recognition technology, acquires indication information related to the value-added service, generates value-added service control information according to the indication information related to the value-added service, and sends the value-added service control information to the terminal equipment through the vehicle-mounted communication device in a mode of sending a short message or establishing a mobile data channel;
and 209, the terminal equipment starts the corresponding value-added service according to the value-added service control information, establishes connection with a server providing the value-added service through the vehicle-mounted communication equipment, and acquires the value-added service from the server, wherein the vehicle-mounted communication equipment establishes connection with the server providing the value-added service in a target network access mode.
In order to further ensure reliable connection between the terminal device and the cloud computing platform server on the network side and the server providing the value added service, the vehicle-mounted communication method provided by the embodiment of the invention may further include: the vehicle-mounted communication device periodically detects the signal intensity of the target network access mode, if the signal intensity of the target network access mode is smaller than a preset signal intensity threshold value, a new target network access mode is selected again, and connection is established between the new target network access mode and the cloud computing platform server and the server providing the value added service.
Further, the step of analyzing the value added service voice instruction command by using the unspecified person voice recognition technology in the vehicle-mounted communication method to obtain the instruction information related to the value added service may include: the cloud computing platform server analyzes the value-added service voice indication command, extracts second voice characteristic information, searches a second broad-spectrum voice characteristic library according to the second voice characteristic information, and acquires the value-added service related indication information corresponding to the second voice characteristic information from the second broad-spectrum voice characteristic library.
The first and second speech feature information may include spectral distribution information of the speech command, time domain waveform information, short-time spectrum of the speech frame, formant frequency and bandwidth, nasal sound joint feature, spectrum correlation feature, pitch feature, power spectrum, frame energy, speech intensity and variation trajectory feature, or may be a combination using one or more of the above feature information.
It should be noted that the broad-spectrum speech feature library provided in this embodiment is a set of broad-spectrum speech features extracted by collecting sounds of places, various people and the people in the whole china under different environments (different noise backgrounds), and the broad-spectrum speech feature library only depends on information of the existing "speech feature library" and does not depend on a speech feature training result of a certain person.
The advantages are that: (1) the selected sample of the broad spectrum speech feature library is extensive and includes human utterances from different regions of different countries of the world. For example, in China, the pronunciation of people in almost every province, county, town and region in China is selected, people in different regions in the country are divided into several categories, such as the North China, the northeast China, the Minnan language region, the Guangdong language region and the like, the Mandarin spoken by people in different regions has local dialects with different characteristics, and after the people are classified respectively, the people in the regions with basically similar local dialects pronunciations are classified into one category, so that the completeness of a sample is considered, and the construction of a database is also considered to generate redundant information as little as possible; (2) extracting voice characteristic information of sounds or voice commands under different environments (noise backgrounds), such as voice commands generated after an automobile engine is started, voice commands generated under the conditions of wind dryness and fetal noises generated after an automobile window is opened, voice commands generated under the conditions of interference such as sudden plug-in of other people and the like, voice commands generated after the engine is closed and the like; (3) the broad-spectrum speech feature library comprises a Mandarin feature library and a local dialect feature library, wherein the local dialect library comprises a Minnan language library, a Guangdong language library, a Shanghai language library and the like.
Further, the broad-spectrum speech feature library also comprises a foreign language library, wherein the foreign language library comprises mainstream foreign language libraries such as an English library, a French library, a German library and a Japanese library. The system also has a feature library automatic recognition module which is used for analyzing the voice command sent by the user to distinguish the feature library corresponding to the voice command and automatically selecting the corresponding feature library. Therefore, the user can use the languages of different countries to send out voice commands in a mixed mode, the languages can be used in a mixed mode without being screened in advance, and the automatic recognition module of the library feature library can automatically recognize whether the voice commands are Chinese or foreign languages.
At least one of the above-mentioned situations, such as situations of people in different regions or situations in different environments, has been considered in the first and/or second voice feature information, i.e., the first and/or second voice feature information is voice feature information extracted based on voice or voice commands of people in different regions, or the first and/or second voice feature information is voice feature information extracted based on voice or voice commands of people in different environments. This improves the recognition rate of voice commands to users or drivers in different regions.
In this embodiment, 95% of the voice information may be recognized through a non-human-specific voice recognition technology, and in order to ensure that 100% of the voice information of the user can be recognized and further improve the user experience of the vehicle-mounted service, optionally, the vehicle-mounted service method based on voice command control provided in the embodiment of the present invention may further include:
when the cloud computing platform server can not recognize the voice command for starting the value-added service through the unspecified person voice recognition technology, the cloud computing platform server recognizes the voice command for starting the value-added service through the unspecified person voice recognition artificial seat module to obtain a corresponding value-added service starting command and/or,
when the cloud computing platform server cannot recognize the value-added service voice indication command through the unspecific person voice recognition technology, the cloud computing platform server recognizes the value-added service voice indication command through the unspecific person voice recognition artificial seat module to acquire the indication information related to the value-added service.
The specific implementation of the vehicle-mounted service method based on voice command control provided by the embodiment of the present invention can be described in the vehicle-mounted communication system provided by the embodiment of the present invention as shown in fig. 1, and details are not described here.
According to the vehicle-mounted communication method provided by the embodiment of the invention, a user only needs to press the starting key of the one-key control device arranged on the fixed part of the vehicle, so that the terminal equipment can be connected with the cloud computing platform server on the network side through the vehicle-mounted communication device through the one-key control device, and the value-added service is obtained through a voice control mode, so that the operation steps of the vehicle-mounted service performed by the user are simplified, the user experience of the vehicle-mounted service is improved, and the vehicle-mounted communication method basically does not need to perform any manual operation in the driving process and only performs control through a voice command. The vehicle-mounted communication device can perform network search, a target network access mode is selected from more than one searched network access modes, and the target network access mode is adopted to establish connection with the cloud computing platform server and the server providing the value-added service, so that the reliability of network connection between the terminal equipment in the vehicle-mounted communication system and the cloud computing platform server and the server providing the value-added service is improved, and the problem that the terminal equipment can only perform information interaction with the server on the network side through the access network provided by a mobile operator in the prior art, and when the network signal of the operator is not good or unavailable, the terminal equipment cannot establish connection with the server on the network side, so that the vehicle-mounted service cannot be obtained is solved. The technical scheme provided by the embodiment of the invention can ensure the normal connection between the terminal equipment and the cloud computing platform server on the network side and the server providing the value-added service, thereby ensuring that the user normally obtains the vehicle-mounted service and improving the vehicle-mounted service experience of the user.
The vehicle-mounted communication system and the method provided by the embodiment of the invention can be applied to vehicles such as automobiles and the like.
Further, the following preferably provides a specific structure of the in-vehicle communication device 103 used in the above-described in-vehicle communication system and method:
as shown in fig. 3 to 7, the vehicle-mounted communication apparatus provided by the embodiment of the present invention is provided in the vehicle-mounted communication system (shown in fig. 1) described above, and includes a first communication unit 301, a second communication unit 303, a search unit 302, and a bus controller (shown in fig. 7):
the first communication unit 301 establishes connection with the terminal device in a direct or short-distance communication mode;
in this embodiment, the direct or short-range communication method adopted by the first communication unit 301 may include any one or a combination of the following: WiFi, bluetooth, infrared, wired or USB, etc., preferably, the first communication unit 301 may be one or a combination of a bluetooth connection module, a WiFi connection module, an infrared connection module and a wired network module shown in fig. 7, so that the apparatus establishes a connection with the terminal device through the bluetooth, WiFi, infrared or wired access manner.
Of course, in the actual using process, the direct or short-distance communication mode adopted by the first communication unit 301 may also be other situations, and details are not described here.
The searching unit (or the signal searching unit) 302 performs network searching to obtain more than one network access modes, and obtains a target network access mode from the more than one network access modes, where the more than one network access modes are preferably a WiFi module (WLAN interface) and a 3G module (SIM card interface) as shown in fig. 7, the WiFi module (WLAN interface) is a WiFi internet module with a WLAN interface, and the 3G module (SIM card interface) is a 3G internet module with a SIM card interface;
the second communication unit 303 establishes a connection with a network server to be communicated with the terminal device by using the target network access method acquired by the search unit (or the signal search unit) 302, preferably, the second communication unit 303 may be a WiFi module (WLAN interface) or a 3G module (SIM card interface) shown in fig. 7, so that the terminal device establishes a connection and communicates with an external network server through the WiFi module (WLAN interface) or the 3G module of the apparatus;
and a bus controller for controlling the first communication unit 301 to establish a connection with a terminal device, controlling the search unit 302 to perform a network search, and controlling the second communication unit 303 to establish a connection with the network server.
Further, as shown in fig. 3, the searching unit 302 may further obtain more than one network access method used by the terminal device connected to the first communication unit 301.
Further, as shown in fig. 3, the searching unit 302 may also search for a communication device with a network access function, and establish a connection with the communication device with the network access function through the first communication unit 301, so as to acquire one or more network access manners adopted by the communication device with the network access function.
Further, as shown in fig. 4, the vehicle-mounted communication apparatus may further include:
the display touch screen 304 displays more than one network access mode acquired by the search unit 302, receives network access mode indication information generated by a user touching the network access mode at a corresponding position on the display touch screen 304, and sends the network access mode indication information to the search unit 302;
the searching unit 302 acquires the target network access mode according to the network access mode indication information sent by the display touch screen 304.
Further, as shown in fig. 5, the vehicle-mounted communication apparatus may further include:
the audio playing and recording unit 305 plays the more than one network access modes acquired by the searching unit 302 in a voice form, receives network access mode indication information sent by the user in a voice form, and sends the network access mode indication information to the searching unit 302, wherein the network access mode indication information includes a target network access mode selected by the user.
Further, as shown in fig. 6, the vehicle-mounted communication apparatus may further include:
the detecting unit 306 periodically detects the model strength of the target network access mode acquired by the searching unit 302, and instructs the searching unit 302 to reselect a new target network access mode if the signal strength of the target network access mode is smaller than a preset signal strength threshold;
the second communication unit 303 reestablishes a connection with the network server to be communicated with the terminal device by using the new target network access method acquired by the search unit 302.
Although it is still known, it should be repeated that various identical or similar structures and operation steps thereof existing in the vehicle-mounted communication system and method in the above embodiments are mutually used, that is, device components in the vehicle-mounted communication system may be operated by using corresponding operation steps in the vehicle-mounted communication method, and corresponding operation steps in the vehicle-mounted communication method may also be completed by using corresponding device components in the vehicle-mounted communication system. Such as a non-human-specific voice feature library in a vehicle-mounted communication system, and corresponding non-human-specific voice feature recognition voice commands in the method. Similarly, the vehicle-mounted communication device shown in fig. 3-7 is also fully applicable to the vehicle-mounted communication system and method shown in fig. 1 or 2.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.