Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar modules or modules having the same or similar functionality throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention. On the contrary, the embodiments of the invention include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.
Fig. 1 is a flowchart illustrating a voice recognition method based on bluetooth connection according to an embodiment of the present invention, which is implemented by a bluetooth device as an example. The method comprises the following steps:
s11: after learning that a user triggers voice recognition, sending a voice recognition request to a gateway device to activate a preset application program on the gateway device, wherein the voice recognition request is sent in a first preset instruction form, and the first preset instruction form is bound with the preset application program, or the voice recognition request is sent through a private wireless link between a Bluetooth device and the preset application program.
The gateway device is, for example, a smart device, such as a mobile phone.
In this embodiment, in order to ensure that the voice recognition request is sent to the preset application program, one way is to modify a standard instruction, for example, the standard instruction is AT + BVRA ═ 1, and the modified preset instruction is represented by AT + XXXX, and only the preset application program can respond to the preset instruction, specifically, the preset application program may register the preset instruction with an operating system of the gateway device, and can respond to the preset instruction. It is understood that, in order to distinguish from subsequent context information, the instruction form corresponding to the voice recognition request may be referred to as a first preset instruction form.
The other mode is as follows: and establishing a private wireless link between the Bluetooth device and the preset application program, and sending the voice recognition request to the preset application program through the private wireless link.
S12: and sending the voice data to be subjected to voice recognition to the preset application program so as to enable the preset application program to perform voice recognition on the voice data after being activated, and obtaining a voice recognition result.
S13: and receiving a voice recognition result sent by the preset application program.
The voice data to be subjected to voice recognition and the corresponding voice recognition result transmitted between the bluetooth device and the preset application program can be transmitted through an SCO audio link of a standard process, or can be transmitted through a private wireless link between the bluetooth device and the preset application program.
In addition, the Bluetooth device can also send scene information of the Bluetooth device to a preset application program so as to realize voice customization. The scene information may be transmitted through a private wireless link, or the scene information may also be transmitted in a second preset instruction form.
Voice service customization is a basic requirement for the differential design of intelligent devices. It is easy to understand that the user instructions faced by a vehicle-mounted hands-free Bluetooth device loaded in a vehicle are mainly related to navigation and routes; and a bluetooth speaker fixedly placed in the living room faces a user instruction, and music playing is more likely to be faced. Similarly, for route navigation, an onboard bluetooth hands-free device can inquire driving routes by default after receiving the inquiry of a user, and a bluetooth headset needs to judge whether the user intends to walk, ride public transport or drive. These all require voice service customization.
However, in the standard bluetooth scheme, there is no instruction to report the attribute of the bluetooth terminal device to the gateway, and the gateway program naturally can only provide a general voice service, and cannot implement differentiation on different devices.
It is understood that, in a scenario where a private wireless link is established between a bluetooth device and a preset application, if information transmitted through the private wireless link includes: if the voice identification request and the scene information are received, the private wireless link can be a single private wireless link, and the single private wireless link is used for transmitting the voice identification request and the scene information; or, the private wireless links may be two, and each private wireless link is used for transmitting the voice recognition request or the scene information. If the information transmitted over the private wireless link includes: the private wireless link can be one, and the private wireless link is used for transmitting the voice recognition request, the scene information and the voice data; or, the number of the private wireless links may be two, one private wireless link is used for transmitting any two items of the voice recognition request, the scene information and the voice data, and the other private wireless link is used for transmitting the remaining one item; or, the number of the private wireless links may be three, and each private wireless link is used for transmitting one of the voice recognition request, the scene information, and the voice data. Accordingly, the flow performed at the gateway side may be as shown in fig. 2. Fig. 2 is a flowchart of a voice recognition method based on bluetooth connection according to another embodiment of the present invention, which is implemented by a gateway device as an example. The method comprises the following steps:
s21: receiving a voice recognition request, wherein the voice recognition request is sent by a Bluetooth device after learning that a user triggers voice recognition, and the voice recognition request is sent in a first preset instruction form, and the first preset instruction form is bound with a preset application program, or the voice recognition request is sent through a private wireless link between the Bluetooth device and the preset application program;
s22: activating a preset application program according to the voice recognition request;
s23: the method comprises the steps of receiving voice data to be subjected to voice recognition sent by Bluetooth equipment, carrying out voice recognition on the voice data by adopting an activated preset application program to obtain a voice recognition result, and sending the voice recognition result to the Bluetooth equipment.
In this embodiment, through the speech recognition request that adopts first preset instruction form, perhaps, through bluetooth equipment and the private wireless link transmission speech recognition request between the preset application, can guarantee to inform specific APP with bluetooth equipment's speech recognition request, realize that speech recognition service binds with specific APP, increase specific APP's flow, increase bluetooth equipment's intellectuality, promote user experience. Furthermore, the customization of the voice service can be realized by sending the scene information of the Bluetooth device to a preset application program.
Fig. 3 is a flowchart illustrating a voice recognition method based on bluetooth connection according to another embodiment of the present invention, which takes the form of a predetermined command as an example of a voice recognition request. The method comprises the following steps:
s31: after learning that the user triggers voice recognition, the Bluetooth device sends a voice recognition request in a first preset instruction form to a preset application program on the gateway device. For example, a button for triggering voice recognition is arranged on the bluetooth device, and after the bluetooth device receives a pressing instruction of a user on the button, the user is informed of triggering voice recognition. In the bluetooth standard protocol flow, after learning that a user triggers voice recognition, the bluetooth device sends a voice recognition request in a standard AT instruction form (AT + BVRA ═ 1) to the gateway device, and in the bluetooth standard protocol flow, any application program supporting voice recognition on the gateway device can respond to the voice recognition request in the standard AT instruction form.
In this embodiment, a voice recognition request in the form of a preset instruction is adopted, the preset instruction form is bound with a preset application program, and only the preset application program can respond to the voice recognition request in the form of the preset instruction.
For example, prior to speech recognition, a pre-set application on the gateway device registers with the operating system of the gateway device the form of instructions to which it can respond. It will be appreciated that the same form of instruction as the default application is also configured on the bluetooth device.
The instruction form to which the preset application can respond includes, for example: voice request messages correspond to a form of instruction, for example, register that it can respond to AT + XXXX.
In addition, in the case where the bluetooth device transmits the scene information, the form of the response-capable instruction for the preset application registration may further include: the instruction format corresponding to the scene information is represented by yyyyy, for example.
After the preset application program registers the information in the operating system of the gateway device, the gateway device can be ensured to send the preset instruction to the preset application program after receiving the preset instruction.
For example, referring to fig. 3, assuming that a module on the bluetooth device that sends the voice recognition request is denoted by CMDRFCOMM and the preset application is denoted by a specific APP, the CMDRFCOMM may send the voice recognition request in the form of a preset instruction (for distinguishing from the subsequent context information, the preset instruction form is referred to as a first preset instruction form) to the gateway device. For example, AT + xxxxxx is transmitted.
After the voice recognition request in the first preset instruction form is sent to the gateway device, the operating system of the gateway device acquires the voice recognition request, and the operating system of the gateway device can know that only a specific APP can respond to the voice recognition request according to the registration information, and then the operating system of the gateway device sends the voice recognition request to the specific APP, so that the CMDRFCOMM sends the voice recognition request in the first preset instruction form to the specific APP.
When a speech recognition request is sent to a particular APP, the particular APP may be activated so that the particular APP can be used for speech recognition.
S32: and the preset application program on the gateway equipment establishes an SCO audio link with the Bluetooth equipment according to the voice recognition request. Only the preset application program can respond to the voice recognition request in the first preset instruction form, so that the voice recognition request in the first preset instruction form can be guaranteed to be sent to the preset application program, and the preset application program initiates establishment of an audio link with the Bluetooth device after receiving the voice recognition request. When an audio link is established, an SCO audio link is established, for example, using standard bluetooth protocol procedures.
For example, referring to fig. 3, assuming that the module on the bluetooth device that establishes the standard audio link is denoted HFP, then a particular APP establishes an SCO audio link with HFP.
S33: the Bluetooth device sends voice data to be subjected to voice recognition to a preset application program through an SCO audio link.
For example, after knowing that the user can speak, the user can speak to the bluetooth device, and the bluetooth device records the voice of the user and takes the recorded voice as voice data to be subjected to voice recognition.
After retrieving the voice data, the HFP may send the voice data to the particular APP over the SCO audio link.
S34: and the Bluetooth device sends the scene information in the form of the second preset instruction to the preset application program.
The bluetooth device may be configured with corresponding context information from the factory, where the context information indicates, for example: the Bluetooth device is a vehicle-mounted Bluetooth device or a Bluetooth device belonging to an intelligent home. Therefore, the bluetooth device can acquire scene information according to the factory configuration information of the bluetooth device. Of course, it can be understood that a sensor may be further disposed in the bluetooth device, and the sensor detects the surrounding environment of the bluetooth device, so as to obtain the scene information.
After the context information is obtained, the CMDRFCOMM may send the context information to a specific APP in a preset instruction form. It is to be understood that, in order to distinguish from the instruction form of the voice recognition request, the preset instruction form corresponding to the scene information may be referred to as a second preset instruction form.
For example, the CMDRFCOMM sends the context information in the form of the second preset instruction to the OS of the gateway device, and the OS learns that the specific APP can respond to the instruction according to the registration information, and therefore, the OS sends the context information in the form of the second preset instruction to the specific APP again.
In this embodiment, the data transmitted by the bluetooth device to the preset application program includes not only the voice data but also the scene information, so as to implement the voice customization.
S35: and the preset application program performs voice recognition on the voice data according to the scene information to obtain a voice recognition result, and sends the voice recognition result to the Bluetooth equipment through the SCO audio link.
For example, the scene information indicates that the bluetooth device is a vehicle-mounted bluetooth device, and during voice recognition, the driving route related to the voice data may be obtained specifically.
Voice service customization is a basic requirement for the differential design of intelligent devices. It is easy to understand that the user instructions faced by a vehicle-mounted hands-free Bluetooth device loaded in a vehicle are mainly related to navigation and routes; and a bluetooth speaker fixedly placed in the living room faces a user instruction, and music playing is more likely to be faced. Similarly, for route navigation, an onboard bluetooth hands-free device can inquire driving routes by default after receiving the inquiry of a user, and a bluetooth headset needs to judge whether the user intends to walk, ride public transport or drive. These all require voice service customization.
After the specific APP obtains the speech recognition result, the speech recognition result is sent to HFP through the previously established SCO audio link.
In the embodiment, the voice recognition request is modified into the preset instruction form, so that the voice recognition request can be sent to the preset application program, the binding of the voice recognition service and the specific application program is realized, and the specific application program, the Bluetooth equipment and the user are facilitated. In addition, scene information is sent to a preset application program through the Bluetooth device, and customization of voice recognition service can be achieved.
Fig. 4 is a flowchart illustrating a voice recognition method based on bluetooth connection according to another embodiment of the present invention, in which a bluetooth device sends a voice recognition request and scene information to a preset application program through a private wireless link, and voice data to be subjected to voice recognition is transmitted through a standard SCO audio link. The private wireless link in this embodiment is specifically represented by a private control link. The method comprises the following steps:
s41: the Bluetooth device establishes a private control link with a preset application program.
For example, if the default application registers and listens to the operating system of the gateway device for the characteristic information of the wireless link, such as registering a specific UUID, and additionally, the same UUID is configured on the bluetooth device, the bluetooth device may initiate a request for a private control link using the UUID, and since only the default application registers and listens to the UUID, the default application may establish the private control link with the bluetooth device.
For example, referring to fig. 4, the predetermined application is represented by a specific APP, and the module on the bluetooth device that establishes the private control link with the predetermined application is represented by CMDRFCOMM, so the CMDRFCOMM may establish the private control link with the specific APP.
S42: and after learning that the user triggers voice recognition, the Bluetooth device sends a voice recognition request to a preset application program through the private control link.
For example, a button for triggering voice recognition is arranged on the bluetooth device, and after the bluetooth device receives a pressing instruction of a user on the button, the user is informed of triggering voice recognition. Thereafter, the CMDRFCOMM may send a voice recognition request to the particular APP over the private control link. In addition, the specific APP in fig. 4 may also feed back a response message to the CMDRFCOMM.
When a speech recognition request is sent to a particular APP, the particular APP may be activated so that the particular APP can be used for speech recognition.
S43: the specific APP establishes an SCO audio link with the bluetooth device.
Wherein, as shown in fig. 4, the module that establishes a standard audio link with a specific APP is denoted by HFP. A particular APP, upon receiving a voice recognition request, may initiate an SCO audio link that establishes the bluetooth standard with HFP. The specific establishment process can be referred to as a standard bluetooth protocol process.
S44: the bluetooth device transmits voice data to be recognized to a preset application program through the SCO audio link.
For example, after knowing that the user can speak, the user can speak to the bluetooth device, and the bluetooth device records the voice of the user and takes the recorded voice as voice data to be subjected to voice recognition.
After retrieving the voice data, the HFP may send the voice data to the particular APP over the SCO audio link.
S45: and the Bluetooth device sends the scene information to a preset application program through a private control link.
The bluetooth device may be configured with corresponding context information from the factory, where the context information indicates, for example: the Bluetooth device is a vehicle-mounted Bluetooth device or a Bluetooth device belonging to an intelligent home. Therefore, the bluetooth device can acquire scene information according to the factory configuration information of the bluetooth device. Of course, it can be understood that a sensor may be further disposed in the bluetooth device, and the sensor detects the surrounding environment of the bluetooth device, so as to obtain the scene information.
After obtaining the context information, the CMDRFCOMM may send the context information to the specific APP via the private control link.
S46: and the preset application program performs voice recognition on the voice data according to the scene information to obtain a voice recognition result, and sends the voice recognition result to the Bluetooth equipment through the SCO audio link.
For example, after receiving the voice data and the scene information, the specific APP performs voice recognition on the voice data according to the scene information to obtain a voice recognition result, and sends the voice recognition result to the HFP.
For example, the scene information indicates that the bluetooth device is a vehicle-mounted bluetooth device, and during voice recognition, the driving route related to the voice data may be obtained specifically.
Voice service customization is a basic requirement for the differential design of intelligent devices. It is easy to understand that the user instructions faced by a vehicle-mounted hands-free Bluetooth device loaded in a vehicle are mainly related to navigation and routes; and a bluetooth speaker fixedly placed in the living room faces a user instruction, and music playing is more likely to be faced. Similarly, for route navigation, an onboard bluetooth hands-free device can inquire driving routes by default after receiving the inquiry of a user, and a bluetooth headset needs to judge whether the user intends to walk, ride public transport or drive. These all require voice service customization.
In this embodiment, by establishing a private control link between the bluetooth device and the preset application program, it can be ensured that the voice recognition request is sent to the preset application program, binding of the voice recognition service and the specific application program is achieved, and the specific application program, the bluetooth device, and the user are facilitated. In addition, scene information is sent to a preset application program through the Bluetooth device, and customization of voice recognition service can be achieved. In addition, audio data transmission can be realized through an audio link of a standard process.
Fig. 5 is a flowchart illustrating a voice recognition method based on bluetooth connection according to another embodiment of the present invention, in which a bluetooth device sends a voice recognition request and scene information to a preset application program through a private wireless link, and voice data to be subjected to voice recognition is also transmitted through the private wireless link. In this embodiment, it is assumed that the private wireless link for transmitting the voice recognition request and the context information is referred to as a private control link, and the private wireless link for transmitting the voice data is referred to as a private audio link. The method comprises the following steps:
s51: the Bluetooth device establishes a private control link with a preset application program.
For example, if the default application registers and listens to the operating system of the gateway device for the characteristic information of the wireless link, such as registering a specific UUID, and additionally, the same UUID is configured on the bluetooth device, the bluetooth device may initiate a request for a private control link using the UUID, and since only the default application registers and listens to the UUID, the default application may establish the private control link with the bluetooth device.
For example, referring to fig. 5, the predetermined application is represented by a specific APP, and the module on the bluetooth device that establishes the private control link with the predetermined application is represented by a CMDRFCOMM, so the CMDRFCOMM may establish the private control link with the specific APP.
S52: and after learning that the user triggers voice recognition, the Bluetooth device sends a voice recognition request to a preset application program through the private control link.
For example, a button for triggering voice recognition is arranged on the bluetooth device, and after the bluetooth device receives a pressing instruction of a user on the button, the user is informed of triggering voice recognition. Thereafter, the CMDRFCOMM may send a voice recognition request to the particular APP over the private control link. In addition, the specific APP in fig. 5 may also feed back a response message to the CMDRFCOMM.
When a speech recognition request is sent to a particular APP, the particular APP may be activated so that the particular APP can be used for speech recognition.
S53: a particular APP establishes a private audio link with a bluetooth device.
Therein, as shown in fig. 5, the module for establishing a private audio link with a specific APP is denoted by audiorfomm. A particular APP, upon receiving a speech recognition request, may initiate establishment of a private audio link with the audiofonm.
For example, a particular APP initiates the establishment of a private audio link with a bluetooth device via another UUID that is different from the private control link.
S54: the bluetooth device sends voice data to be recognized to a preset application program through a private audio link.
For example, after knowing that the user can speak, the user can speak to the bluetooth device, and the bluetooth device records the voice of the user and takes the recorded voice as voice data to be subjected to voice recognition.
After obtaining the voice data, the audiorfomm may send the voice data to the particular APP over the SCO audio link.
S55: and the Bluetooth device sends the scene information to a preset application program through a private control link.
The bluetooth device may be configured with corresponding context information from the factory, where the context information indicates, for example: the Bluetooth device is a vehicle-mounted Bluetooth device or a Bluetooth device belonging to an intelligent home. Therefore, the bluetooth device can acquire scene information according to the factory configuration information of the bluetooth device. Of course, it can be understood that a sensor may be further disposed in the bluetooth device, and the sensor detects the surrounding environment of the bluetooth device, so as to obtain the scene information.
After obtaining the context information, the CMDRFCOMM may send the context information to the specific APP via the private control link.
It can be understood that, in this embodiment, the context information and the voice recognition request are transmitted in a private control link as an example, the audiorfomm may also send the obtained voice data and context information to a specific APP through a private audio link, or the context information, the voice recognition request, and the voice data are all transmitted in the same wireless link.
S56: and the preset application program performs voice recognition on the voice data according to the scene information to obtain a voice recognition result, and sends the voice recognition result to the Bluetooth equipment through the private audio link.
For example, after receiving the voice data and the context information, the specific APP performs voice recognition on the voice data according to the context information to obtain a voice recognition result, and sends the voice recognition result to the audiorfomm.
For example, the scene information indicates that the bluetooth device is a vehicle-mounted bluetooth device, and during voice recognition, the driving route related to the voice data may be obtained specifically.
Voice service customization is a basic requirement for the differential design of intelligent devices. It is easy to understand that the user instructions faced by a vehicle-mounted hands-free Bluetooth device loaded in a vehicle are mainly related to navigation and routes; and a bluetooth speaker fixedly placed in the living room faces a user instruction, and music playing is more likely to be faced. Similarly, for route navigation, an onboard bluetooth hands-free device can inquire driving routes by default after receiving the inquiry of a user, and a bluetooth headset needs to judge whether the user intends to walk, ride public transport or drive. These all require voice service customization.
In this embodiment, by establishing a private control link between the bluetooth device and the preset application program, it can be ensured that the voice recognition request is sent to the preset application program, binding of the voice recognition service and the specific application program is achieved, and the specific application program, the bluetooth device, and the user are facilitated. In addition, scene information is sent to a preset application program through the Bluetooth device, and customization of voice recognition service can be achieved. In addition, audio data transmission may be achieved over a private audio link.
Fig. 6 is a schematic structural diagram of a voice recognition apparatus based on bluetooth connection according to another embodiment of the present invention, which may be located on a bluetooth device. The apparatus 60 comprises:
the first sending module 61 is configured to send a voice recognition request to the gateway device after learning that a user triggers voice recognition, so as to activate a preset application program on the gateway device, where the voice recognition request is sent in a first preset instruction form, and the first preset instruction form is bound with the preset application program, or the voice recognition request is sent through a private wireless link between the bluetooth device and the preset application program.
The gateway device is, for example, a smart device, such as a mobile phone.
In this embodiment, in order to ensure that the voice recognition request is sent to the preset application program, one way is to modify a standard instruction, for example, the standard instruction is AT + BVRA ═ 1, and the modified preset instruction is represented by AT + XXXX, and only the preset application program can respond to the preset instruction, specifically, the preset application program may register the preset instruction with an operating system of the gateway device, and can respond to the preset instruction. It is understood that, in order to distinguish from subsequent context information, the instruction form corresponding to the voice recognition request may be referred to as a first preset instruction form.
The other mode is as follows: and establishing a private wireless link between the Bluetooth device and the preset application program, and sending the voice recognition request to the preset application program through the private wireless link.
A second sending module 62, configured to send voice data to be subjected to voice recognition to the preset application program, so that the preset application program performs voice recognition on the voice data after being activated, and a voice recognition result is obtained;
and the receiving module 63 is configured to receive the voice recognition result sent by the preset application program.
The voice data to be subjected to voice recognition and the corresponding voice recognition result transmitted between the bluetooth device and the preset application program can be transmitted through an SCO audio link of a standard process, or can be transmitted through a private wireless link between the bluetooth device and the preset application program.
In some embodiments, referring to fig. 7, the apparatus 60 further comprises:
a third sending module 64, configured to send scene information to which the bluetooth device belongs to the preset application program, so that after the preset application program is activated, voice recognition is performed on the voice data according to the scene information.
The scene information may be transmitted through a private wireless link, or the scene information may also be transmitted in a second preset instruction form.
Voice service customization is a basic requirement for the differential design of intelligent devices. It is easy to understand that the user instructions faced by a vehicle-mounted hands-free Bluetooth device loaded in a vehicle are mainly related to navigation and routes; and a bluetooth speaker fixedly placed in the living room faces a user instruction, and music playing is more likely to be faced. Similarly, for route navigation, an onboard bluetooth hands-free device can inquire driving routes by default after receiving the inquiry of a user, and a bluetooth headset needs to judge whether the user intends to walk, ride public transport or drive. These all require voice service customization.
However, in the standard bluetooth scheme, there is no instruction to report the attribute of the bluetooth terminal device to the gateway, and the gateway program naturally can only provide a general voice service, and cannot implement differentiation on different devices.
It is understood that, in a scenario where a private wireless link is established between a bluetooth device and a preset application, if information transmitted through the private wireless link includes: if the voice identification request and the scene information are received, the private wireless link can be a single private wireless link, and the single private wireless link is used for transmitting the voice identification request and the scene information; or, the private wireless links may be two, and each private wireless link is used for transmitting the voice recognition request or the scene information. If the information transmitted over the private wireless link includes: the private wireless link can be one, and the private wireless link is used for transmitting the voice recognition request, the scene information and the voice data; or, the number of the private wireless links may be two, one private wireless link is used for transmitting any two items of the voice recognition request, the scene information and the voice data, and the other private wireless link is used for transmitting the remaining one item; or, the number of the private wireless links may be three, and each private wireless link is used for transmitting one of the voice recognition request, the scene information, and the voice data.
When the voice recognition request message is transmitted over the private wireless link, the apparatus may further include: and the link establishing module is used for establishing a private wireless link between the Bluetooth device and a preset application program. For example, if the default application registers and listens to the operating system of the gateway device for the characteristic information of the wireless link, such as registering a specific UUID, and additionally, the same UUID is configured on the bluetooth device, the bluetooth device may initiate a request for a private control link using the UUID, and since only the default application registers and listens to the UUID, the default application may establish the private control link with the bluetooth device. In addition, when the voice data is also transmitted through the private wireless link, the private wireless link may be divided into a private control link and a private audio link, the private control link is used to transmit the voice request message and the scene information, and the private audio link is used to transmit the audio data, where the private control link is established first, and the preset application initiates establishment of the private audio connection after the bluetooth device sends the voice request message to the preset application. The private control link and the private audio link may be established through different UUIDs.
Fig. 8 is a schematic structural diagram of a voice recognition apparatus based on bluetooth connection according to another embodiment of the present invention, which may be located on a gateway device. The apparatus 80 comprises:
the first receiving module 81 is configured to receive a voice recognition request, where the voice recognition request is sent by a bluetooth device after learning that a user triggers voice recognition, where the voice recognition request is sent in a first preset instruction form, and the first preset instruction form is bound with a preset application program, or the voice recognition request is sent through a private wireless link between the bluetooth device and the preset application program;
an activation module 82, configured to activate a preset application program according to the voice recognition request;
the recognition module 83 is configured to receive voice data to be subjected to voice recognition sent by the bluetooth device, perform voice recognition on the voice data by using an activated preset application program to obtain a voice recognition result, and send the voice recognition result to the bluetooth device.
In some embodiments, referring to fig. 9, the apparatus 80 further comprises:
a second receiving module 84, configured to receive scene information that the bluetooth device belongs to and is sent by the bluetooth device;
the recognition module 83 is configured to perform speech recognition on the speech data by using an activated preset application program to obtain a speech recognition result, and includes:
and performing voice recognition on the voice data according to the scene information by adopting an activated preset application program to obtain a voice recognition result.
For specific content, reference may be made to related descriptions in the method embodiments, and details are not described herein again.
Correspondingly, fig. 10 is a schematic structural diagram of a speech recognition system based on bluetooth connection according to another embodiment of the present invention. The system 100 includes: an apparatus 101 located on the bluetooth device and an apparatus 102 located on the gateway device, where the apparatus 101 located on the bluetooth device may refer to fig. 6 or fig. 7 specifically, and the apparatus 102 located on the gateway device may refer to fig. 8 or fig. 9 specifically.
In this embodiment, through the speech recognition request that adopts first preset instruction form, perhaps, through bluetooth equipment and the private wireless link transmission speech recognition request between the preset application, can guarantee to inform specific APP with bluetooth equipment's speech recognition request, realize that speech recognition service binds with specific APP, increase specific APP's flow, increase bluetooth equipment's intellectuality, promote user experience. Furthermore, the customization of the voice service can be realized by sending the scene information of the Bluetooth device to a preset application program.
It should be noted that the terms "first," "second," and the like in the description of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present invention, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.