Method and apparatus for providing speech service

1. A method for providing a speech service, comprising:

receiving request information sent by a device, the request information comprising first event information, second event information, third event information and speech information, wherein the first event information is used for indicating a first event occurring on the device when the device sends the request information to locate a function to be enabled according to the first event information, the first event information comprising speech input event information used for instructing a user to input the speech information, the second event information is used for indicating a second event occurring on the device when the device sends the response channel establishing request, and the third event information is used for indicating a third event occurring on the device when the device sends a status report message;

analyzing the speech information, and determining a targeted device;

determining current event information of the targeted device and current status information corresponding to the current event information based on the first event information, the second event information or the third event information;

generating response information according to the current event information of the targeted device, the current status information, a functional interface directory and the speech information; and

sending the response information to the targeted device for the targeted device to perform an operation indicated by the operation instruction.

2. The method according to claim 1 , wherein, before receiving request information sent by a device, the method further comprises:

receiving a response channel establishing request sent by the device, wherein the response channel establishing request is used to request establishing a channel for returning response information to a terminal device and maintaining the established response channel in a connected state; and

receiving the second event information and first status information sent by the device, wherein the first status information is used for indicating a status of the first event.

3. The method according to claim 2 , wherein, before receiving request information sent by a device, the method further comprises:

receiving the functional interface directory sent by the device, wherein the functional interface directory comprises an identifier of at least one of following operation interfaces: a speech input interface, a speech output interface, a speaker control interface, an audio play control interface, an alarm clock setting interface or a screen display interface; and

storing the functional interface directory and an identifier of the device sending the functional interface directory accordingly.

4. The method according to claim 3 , wherein, before generating response information comprising an operation instruction for a targeted device on the basis of the first event information and the speech information, the method further comprises:

receiving the status report message sent by the device, the status report message comprising the third event information and second status information, wherein the second status information is used for indicating a status of the second event.

5. The method according to claim 4 , wherein the request information further comprises third status information used for indicating a status of the first event.

6. The method according to claim 1 , wherein the response information further comprises to-be-played audio information, and the operation instruction comprises an audio play instruction for playing the to-be-played audio information; and

the sending the response information to the targeted device for the targeted device to perform an operation indicated by the operation instruction comprises:

sending the to-be-played audio information and the audio play instruction to the targeted device for the targeted device to call a speech output interface to play the to-be-played audio information according to the audio play instruction.

7. The method according to claim 6 , wherein the response information further comprises to-be-displayed view information, and the operation instruction further comprises a view drawing instruction for drawing the to-be-displayed view information, wherein the view information comprises at least one of the following: an image, a webpage or a video; and

the sending the response information to the targeted device for the targeted device to perform an operation indicated by the operation instruction further comprises:

sending the to-be-displayed view information and the view drawing instruction to the targeted device for the targeted device to call a screen display interface to draw and display the to-be-displayed view information according to the view drawing instruction.

8. An apparatus for providing a speech service, comprising:

at least one processor; and

a memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:

receiving request information sent by a device, the request information comprising first event information, second event information, third event information and speech information, wherein the first event information is used for indicating a first event occurring on the device when the device sends the request information to locate a function to be enabled according to the first event information, the first event information comprising speech input event information used for instructing a user to input the speech information, the second event information is used for indicating a second event occurring on the device when the device sends the response channel establishing request, and the third event information is used for indicating a third event occurring on the device when the device sends a status report message;

analyzing the speech information, and determining a targeted device;

determining current event information of the targeted device and current status information corresponding to the current event information based on the first event information, the second event information or the third event information;

generating response information according to the current event information of the targeted device, the current status information, a functional interface directory and the speech information; and

sending the response information to the targeted device for the targeted device to perform an operation indicated by the operation instruction.

9. The apparatus according to claim 8 , the operations further comprising:

receiving a response channel establishing request sent by the device, wherein the response channel establishing request is used to request establishing a channel for returning response information to a terminal device and maintaining the established response channel in a connected state; and

receiving the second event information and first status information sent by the device, wherein the first status information is used for indicating a status of the first event.

10. The apparatus according to claim 9 , the operations further comprising:

receiving the functional interface directory sent by the device, wherein the functional interface directory comprises an identifier of at least one of following operation interfaces: a speech input interface, a speech output interface, a speaker control interface, an audio play control interface, an alarm clock setting interface or a screen display interface; and

storing the functional interface directory and an identifier of the device sending the functional interface directory accordingly.

11. The apparatus according to claim 10 , the operations further comprising:

receiving the status report message sent by the device, the status report message comprising the third event information and second status information, wherein the second status information is used for indicating a status of the second event.

12. The apparatus according to claim 11 , wherein the request information further comprises third status information used for indicating a status of the first event.

13. The apparatus according to claim 8 , wherein the response information further comprises to-be-played audio information, and the operation instruction comprises an audio play instruction for playing the to-be-played audio information; and

the sending the response information to the targeted device for the targeted device to perform an operation indicated by the operation instruction comprises:

sending the to-be-played audio information and the audio play instruction to the targeted device for the targeted device to call a speech output interface to play the to-be-played audio information according to the audio play instruction.

14. The apparatus according to claim 13 , wherein the response information further comprises to-be-displayed view information, and the operation instruction further comprises a view drawing instruction for drawing the to-be-displayed view information, wherein the view information comprises at least one of the following: an image, a webpage or a video; and

the sending the response information to the targeted device for the targeted device to perform an operation indicated by the operation instruction further comprises:

sending the to-be-displayed view information and the view drawing instruction to the targeted device for the targeted device to call a screen display interface to draw and display the to-be-displayed view information according to the view drawing instruction.

15. A non-transitory computer storage medium storing a computer program, the computer program when executed by one or more processors, causes the one or more processors to perform operations, the operations comprising:

receiving request information sent by a device, the request information comprising first event information, second event information, third event information and speech information, wherein the first event information is used for indicating a first event occurring on the device when the device sends the request information to locate a function to be enabled according to the first event information, the first event information comprising speech input event information used for instructing a user to input the speech information, the second event information is used for indicating a second event occurring on the device when the device sends the response channel establishing request, and the third event information is used for indicating a third event occurring on the device when the device sends a status report message;

analyzing the speech information, and determining a targeted device;

determining current event information of the targeted device and current status information corresponding to the current event information based on the first event information, the second event information or the third event information;

generating response information according to the current event information of the targeted device, the current status information, a functional interface directory and the speech information; and

sending the response information to the targeted device for the targeted device to perform an operation indicated by the operation instruction.