Method and terminal for implementing speech control
A terminal for implementing speech control records a correspondence between a first keyword text and a second keyword text. When a user inputs a speech, the terminal sends, to a first server for semantic parsing and logical parsing, the speech input by the user. Then, when the first server returns a parsing failure, the terminal obtains a parsed text returned by the first server, replaces the second keyword in the parsed text with the first keyword based on the correspondence, and then sends, to the first server, the text obtained after the replacement.
1. A first terminal, comprising:
a processor; and
a memory coupled to the processor and storing one or more programs that, when executed by the processor, cause the first terminal to be configured to:
record a correspondence between a standard keyword and a non-standard keyword;
send, to a second terminal, a first control command corresponding to the standard keyword when the first terminal receives a first speech input, wherein the first speech input comprises the standard keyword; and
when the first terminal receives a second speech input that comprises the non-standard keyword:
parse the second speech input to recognize the non-standard keyword;
search the correspondence to identify the second terminal when the first terminal recognizes the non-standard keyword; and
send, to the second terminal, a second control command.
2. The first terminal of claim 1 , wherein the one or more programs further cause the first terminal to be configured to record the correspondence when the first terminal detects an operation of modifying the standard keyword to correspond to the non-standard keyword.
3. The first terminal of claim 1 , wherein the one or more programs further cause the first terminal to be configured to:
generate first parsed text by parsing the first speech input;
send the first parsed text to a cloud server; and
receive the first control command from the cloud server.
4. The first terminal of claim 1 , wherein the one or more programs further cause the first terminal to be configured to:
generate first parsed text by parsing the second speech input;
generate second parsed text according to the correspondence, wherein the second parsed text has a same meaning as the first parsed text and comprises the standard keyword;
send the second parsed text to a server; and
receive the second control command from the server after sending the second parsed text to the server.
5. The first terminal of claim 1 , wherein the one or more programs further cause the first terminal to be configured to:
generate first parsed text by parsing the second speech input;
send the first parsed text to a server;
receive parsing failure information from the server;
generate second parsed text according to the correspondence, wherein the second parsed text has a same meaning as the first parsed text and comprises the standard keyword;
send the second parsed text to the server; and
receive the second control command from the server after sending the second parsed text to the server.
6. The first terminal of claim 1 , wherein the first terminal is a smart household device or a mobile phone.
7. The first terminal of claim 1 , wherein the standard keyword is a standard name of the second terminal.
8. The first terminal of claim 1 , wherein the non-standard keyword comprises a personalized keyword of a user of the first terminal.
9. A speech control system, comprising:
a second terminal; and
a first terminal communicatively coupled to the second terminal and configured to:
record a correspondence between a standard keyword and a non-standard keyword;
send, to the second terminal, a first control command corresponding to the standard keyword when the first terminal receives a first speech input, wherein the first speech input comprises the standard keyword; and
when the first terminal receives a second speech input that comprises the non-standard keyword:
parse the second speech input to recognize the non-standard keyword;
search the correspondence to identify the second terminal when the first terminal recognizes the non-standard keyword; and
send, to the second terminal, a second control command, and
wherein the second terminal is configured to perform a function based on the second control command.
10. The speech control system of claim 9 , wherein the first terminal is further configured to record the correspondence when the first terminal detects an operation of modifying the standard keyword to correspond to the non-standard keyword.
11. The speech control system of claim 9 , further comprising a server communicatively coupled to the first terminal, wherein the first terminal is further configured to:
generate first parsed text by parsing the first speech input; and
send the first parsed text to the server, and
wherein the server is configured to:
generate the first control command by parsing the first parsed text; and
send the first control command to the first terminal.
12. The speech control system of claim 9 , further comprising a server communicatively coupled to the first terminal, wherein the first terminal is further configured to:
generate first parsed text by parsing the second speech input;
generate second parsed text according to the correspondence, wherein the second parsed text has a same meaning as the first parsed text and comprises the standard keyword; and
send the second parsed text to the server, and
wherein the server is configured to:
generate the second control command by parsing the second parsed text; and
send the second control command to the first terminal.
13. The speech control system of claim 9 , further comprising a server communicatively coupled to the first terminal, wherein the first terminal is further configured to:
generate first parsed text by parsing the second speech input;
send the first parsed text to the server;
generate second parsed text according to the correspondence when the first terminal receives parsing failure information from the server, wherein the second parsed text has a same meaning as the first parsed text and comprises the standard keyword; and
send the second parsed text to the server, and
wherein the server is configured to:
send parsing failure information to the first terminal when the server fails to parse the second parsed text; and
send, to the first terminal, the second control command when the server successfully parses the second parsed text.
14. The speech control system of claim 13 , wherein the server is a cloud server.
15. The speech control system of claim 9 , wherein the first terminal is a smart household device or a mobile phone.
16. The speech control system of claim 9 , wherein the second terminal is a home appliance device or a car.
17. The speech control system of claim 9 , wherein the standard keyword is a standard name of the second terminal.
18. The speech control system of claim 9 , wherein the non-standard keyword comprises a personalized keyword of a user of the terminal.
19. A method implemented by a first terminal, the method comprising:
recording a correspondence between a standard keyword and a non-standard keyword;
sending, to a second terminal, a first control command corresponding to the standard keyword when the first terminal receives a first speech input, wherein the first speech input comprises the standard keyword; and
when the first terminal receives a second speech input that comprises the non-standard keyword:
parsing the second speech input to recognize the non-standard keyword;
searching the correspondence to identify the second terminal when the first terminal recognizes the non-standard keyword; and
sending, to the second terminal, a second control command.