Method and apparatus for recognizing voice

1. A method for recognizing voice, the method comprising:

receiving voice information sent by a user through a terminal, and acquiring simultaneously a user identifier of the user;

recognizing the voice information to obtain a first recognized text;

determining a word information set stored in association with the user identifier of the user based on the user identifier of the user, wherein word information in the word information set comprises a historical character string inputted by the user through an input method application, an input result corresponding to the historical character string, and a candidate result corresponding to the historical character string, the input result corresponding to the historical character string being a text actually inputted by the user for the historical character string, the candidate result corresponding to the historical character string being a text pushed by the input method application for the historical character string;

processing the first recognized text based on word information in the determined word information set to obtain a second recognized text, wherein the processing comprises: determining that the first recognized text comprises the candidate result corresponding to the historical character string in the word information set; and replacing the candidate result corresponding to the historical character string with the input result corresponding to the historical character string, in response to determining the first recognized text comprising the candidate result corresponding to the historical character string in the word information set; and

sending the second recognized text to the terminal,

wherein the method is performed by at least one processor.

2. The method according to claim 1 , the method further comprising:

receiving input record information sent by a target terminal used by the user, wherein the input record information is generated by the target terminal upon detecting an input result of an input character string inputted by the user through an input method application being inconsistent with a candidate result provided by the input method application for the input character string, and the input record information comprises the user identifier of the user, the input result of the input character string inputted by the user through the input method application, and the candidate result provided by the input method application for the input character string; and

storing the input result of the input character string inputted by the user through the input method application and the candidate result provided by the input method application for the input character string in the input record information into the word information set associated with the user identifier of the user.

3. An apparatus for recognizing voice, the apparatus 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 voice information sent by a user through a terminal, and acquiring simultaneously a user identifier of the user;

recognizing the voice information to obtain a first recognized text;

determining a word information set stored in association with the user identifier of the user based on the user identifier of the user, wherein word information in the word information set comprises a historical character string inputted by the user through an input method application, an input result corresponding to the historical character string, and a candidate result corresponding to the historical character string, the input result corresponding to the historical character string being a text actually inputted by the user for the historical character string, the candidate result corresponding to the historical character string being a text pushed by the input method application for the historical character string;

processing the first recognized text based on word information in the determined word information set to obtain a second recognized text, wherein the processing comprises: determining that the first recognized text comprises the candidate result corresponding to the historical character string in the word information set; and replacing the candidate result corresponding to the historical character string with the input result corresponding to the historical character string, in response to determining the first recognized text comprising the candidate result corresponding to the historical character string in the word information set; and

sending the second recognized text to the terminal.

4. The apparatus according to claim 3 , the operations further comprising:

receiving input record information sent by a target terminal used by the user, wherein the input record information is generated by the target terminal upon detecting an input result of an input character string inputted by the user through an input method application being inconsistent with a candidate result provided by the input method application for the input character string, and the input record information comprises the user identifier of the user, the input result of the input character string inputted by the user through the input method application, and the candidate result provided by the input method application for the input character string; and

storing the input result of the input character string inputted by the user through the input method application and the candidate result provided by the input method application for the input character string in the input record information into the word information set associated with the user identifier of the user.

5. 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 voice information sent by a user through a terminal, and acquiring simultaneously a user identifier of the user;

recognizing the voice information to obtain a first recognized text;

determining a word information set stored in association with the user identifier of the user based on the user identifier of the user, wherein word information in the word information set comprises a historical character string inputted by the user through an input method application, an input result corresponding to the historical character string, and a candidate result corresponding to the historical character string, the input result corresponding to the historical character string being a text actually inputted by the user for the historical character string, the candidate result corresponding to the historical character string being a text pushed by the input method application for the historical character string;

processing the first recognized text based on word information in the determined word information set to obtain a second recognized text, wherein the processing comprises: determining that the first recognized text comprises the candidate result corresponding to the historical character string in the word information set; and replacing the candidate result corresponding to the historical character string with the input result corresponding to the historical character string, in response to determining the first recognized text comprising the candidate result corresponding to the historical character string in the word information set; and

sending the second recognized text to the terminal.