Method and apparatus for verifying information

1. A method for verifying information, the method comprising:

establishing and storing a corresponding relationship between values of attributes and QA (question-and-answer) elements each comprising a question and an answer, each of the values of the attributes comprising a value of age and a value of gender, and each of the QA elements corresponding to the value of the attribute;

determining a value of an attribute of a user, based on voiceprint information of the user acquired previously, the attribute comprising gender and age of the user;

determining, from the corresponding relationship, the value of the attribute matching the value of the attribute of the user;

determining the QA element corresponding to the determined value matching the value of attribute of the user as a target combination of question and answer;

acquiring the target combination of question and answer;

sending the question in the target combination of question and answer to a terminal device;

recording a voice of the user and acquiring to-be-confirmed voice information based on the recorded voice;

receiving the to-be-confirmed voice information sent by the terminal device, and recognizing the to-be-confirmed voice information to generate a to-be-confirmed answer;

determining that the to-be-confirmed voice information is verified, in response to determining that the to-be-confirmed answer matches the answer in the target combination of question and answer; and

determining that the user passes a voice verification, in response to determining that the to-be-confirmed answer matches the answer in the target combination of question and answers;

wherein the method is performed by at least one processor.

2. The method for verifying information according to claim 1 , wherein after the receiving to-be-confirmed voice information sent by the terminal device, the method further comprises:

extracting voiceprint characteristic information from the to-be-confirmed voice information, and determining a similarity between the voiceprint characteristic information and pre-stored voiceprint characteristic information of the user.

3. The method for verifying information according to claim 2 , wherein the recognizing the to-be-confirmed voice information to generate a to-be-confirmed answer comprises:

performing speech recognition on the to-be-confirmed voice information to generate an answer string in response to determining that the similarity is less than or equal to a preset similarity threshold, and defining the answer string as the to-be-confirmed answer.

4. The method for verifying information according to claim 1 , wherein after the recognizing the to-be-confirmed voice information to generate a to-be-confirmed answer, the method further comprises:

comparing the to-be-confirmed answer with the answer in the target combination of question and answer; and

determining, in response to determining that the to-be-confirmed answer is identical to the answer in the target combination of question and answer or the similarity between the to-be-confirmed answer and the answer in the target combination of question and answer is greater than or equal to a preset answer similarity threshold, that the to-be-confirmed answer matches the answer in the target combination of question and answer.

5. The method for verifying information according to claim 1 , wherein the question in the QA element may be a binary question; and

the QA element comprises at least one of: the combination of question and answer entered by the user pre-stored on the terminal device, the combination of question and answer in a given knowledge database, or the combination of question and answer about information of an item purchased by the user.

6. An apparatus for verifying information, 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:

establishing and storing a corresponding relationship between values of attributes and QA (question-and-answer) elements each comprising a question and an answer, each of the values of the attributes comprising a value of age and a value of gender, and each of the QA elements corresponding to the value of the attribute;

determining a value of an attribute of a user, based on voiceprint information of the user acquired previously, the attribute comprising gender and age of the user;

determining, from the corresponding relationship, the value of the attribute matching the value of the attribute of the user;

determining the QA element corresponding to the determined value matching the value of attribute of the user as a target combination of question and answer;

acquiring the target combination of question and answer;

sending the question in the target combination of question and answer to a terminal device;

recording a voice of the user and acquiring to-be-confirmed voice information based on the recorded voice;

receiving the to-be-confirmed voice information sent by the terminal device, and recognizing the to-be-confirmed voice information to generate a to-be-confirmed answer;

determining that the to-be-confirmed voice information is verified, in response to determining that the to-be-confirmed answer matches the answer in the target combination of question and answer; and

determining that the user passes a voice verification, in response to determining that the to-be-confirmed answer matches the answer in the target combination of question and answers.

7. The apparatus for verifying information according to claim 6 , wherein after the receiving to-be-confirmed voice information sent by the terminal device, the operations further comprise:

extracting voiceprint characteristic information from the to-be-confirmed voice information, and determining a similarity between the voiceprint characteristic information and pre-stored voiceprint characteristic information of the user.

8. The apparatus for verifying information according to claim 7 , wherein the recognizing the to-be-confirmed voice information to generate a to-be-confirmed answer comprises:

performing speech recognition on the to-be-confirmed voice information to generate an answer string in response to determining that the similarity is less than or equal to a preset similarity threshold, and defining the answer string as the to-be-confirmed answer.

9. The apparatus for verifying information according to claim 6 , wherein after the recognizing the to-be-confirmed voice information to generate a to-be-confirmed answer, the operations further comprise:

comparing the to-be-confirmed answer with the answer in the target combination of question and answer; and

determining, in response to determining that the to-be-confirmed answer is identical to the answer in the target combination of question and answer or the similarity between the to-be-confirmed answer and the answer in the target combination of question and answer is greater than or equal to a preset answer similarity threshold, that the to-be-confirmed answer matches the answer in the target combination of question and answer.

10. The apparatus for verifying information according to claim 6 , wherein the question in QA element may be a binary question; and

the QA element comprises at least one of: the combination of question and answer entered by the user pre-stored on the terminal device, the combination of question and answer in a given knowledge database, or the combination of question and answer about information of an item purchased by the user.

11. A non-transitory computer-readable 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:

establishing and storing a corresponding relationship between values of attributes and QA (question-and-answer) elements each comprising a question and an answer, each of the values of the attributes comprising a value of age and a value of gender, and each of the QA elements corresponding to the value of the attribute;

determining a value of an attribute of a user, based on voiceprint information of the user acquired previously, the attribute comprising gender or age of the user;

determining, from the corresponding relationship, the value of the attribute matching the value of the attribute of the user;

determining the QA element corresponding to the determined value matching the value of attribute of the user as a target combination of question and answer;

acquiring the target combination of question and answer;

sending the question in the target combination of question and answer to a terminal device;

recording a voice of the user and acquiring to-be-confirmed voice information based on the recorded voice;

receiving the to-be-confirmed voice information sent by the terminal device, and recognizing the to-be-confirmed voice information to generate a to-be-confirmed answer;

determining that the to-be-confirmed voice information is verified, in response to determining that the to-be-confirmed answer matches the answer in the target combination of question and answer; and

determining that the user passes a voice verification, in response to determining that the to-be-confirmed answer matches the answer in the target combination of question and answers.

12. The method for verifying information according to claim 2 , wherein the voiceprint characteristic information comprises at least one of: a degree of retroflexion characteristic parameter, a vocal cord characteristic parameter, an oral cavity characteristic parameter, or a nasal sound characteristic parameter.