Method and apparatus for extracting information

1. A method for extracting information, comprising:

receiving and parsing voice information of a user to generate text information corresponding to the voice information;

extracting to-be-recognized contact information from the text information;

acquiring an address book of the user, the address book comprising at least two pieces of contact information;

generating at least two types of matching information based on the to-be-recognized contact information;

determining, for each of the at least two types of matching information, a matching degree between the to-be-recognized contact information and each of the at least two pieces of contact information based on the type of matching information wherein the matching information is a name keyword, and the matching degree is the ratio of a number of words of the contact information identical to the name keyword, to a sum of the number of the words in the contact information and a number words in the name keyword; and

extracting contact information matching the to-be-recognized contact information from the address book based on the determined matching degree,

wherein the method is performed by at least one processor.

2. The method according to claim 1 , wherein the matching information is pinyin corresponding to the to-be-recognized contact information; and

the generating at least two types of matching information based on the to-be-recognized contact information comprises:

determining a first pinyin corresponding to the to-be-recognized contact information; and

determining a second pinyin corresponding to each piece of contact information in the address book.

3. The method according to claim 2 , wherein the determining, for each of the at least two types of matching information, a matching degree between the to-be-recognized contact information and each of the at least two pieces of contact information based on the type of matching information, comprises:

importing, for each piece of contact information in the address book, the first pinyin and the second pinyin corresponding to the each piece of contact information into a pre-established pinyin similarity model to generate a pinyin similarity between the first pinyin and the second pinyin, wherein the pinyin similarity model is used to represent a corresponding relation between the first pinyin, the second pinyin and the pinyin similarity; and

determining the pinyin similarity as the matching degree between the to-be-recognized contact information and the contact information.

4. The method according to claim 2 , wherein the determining, for each of the at least two types of matching information, a matching degree between the to-be-recognized contact information and each of the at least two pieces of contact information based on the type of matching information, comprises:

determining, for each piece of contact information in the address book, an edit distance between the to-be-recognized contact information and the each piece of contact information based on the first pinyin and the second pinyin corresponding to the contact information; and

determining the edit distance as the matching degree between the to-be-recognized contact information and the each piece of contact information.

5. The method according to claim 1 , wherein the matching information is sound wave information corresponding to the to-be-recognized contact information; and

the generating at least two types of matching information based on the to-be-recognized contact information, comprises:

acquiring first sound wave information corresponding to the to-be-recognized contact information; and

acquiring, for each piece of contact information in the address book, second sound wave information corresponding to the each piece of contact information.

6. The method according to claim 5 , wherein the determining, for each of the at least two types of matching information, a matching degree between the to-be-recognized contact information and each of the at least two pieces of contact information based on the type of matching information, comprises:

determining, for each piece of contact information in the address book, a similarity between the first sound wave information and the second sound wave information corresponding to the each piece of contact information as the matching degree between the to-be-recognized contact information and the each piece of contact information.

7. The method according to claim 1 , wherein the matching information is a title keyword; and

the generating at least two types of matching information based on the to-be-recognized contact information, comprises:

extracting a title keyword from the to-be-recognized contact information.

8. The method according to claim 7 , wherein the determining, for each of the at least two types of matching information, a matching degree between the to-be-recognized contact information and each of the at least two pieces of contact information based on the type of matching information, comprises:

acquiring pre-generated title relationship information, wherein the title relationship information is used to indicate an association relationship between titles expressing the same meaning;

acquiring a target title including the same meaning as the title keyword based on the title relationship information; and

selecting, for each piece of contact information in the address book, a maximum matching degree as the matching degree between the to-be-recognized contact information and the each piece of contact information, from a matching degree between the title keyword and the each piece of contact information and a matching degree between the target title and the each piece of contact information.

9. An apparatus for extracting information, the apparatus comprising:

at least one processor; and

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

receiving and parsing voice information of a user to generate text information corresponding to the voice information;

extracting to-be-recognized contact information from the text information;

acquiring an address book of the user, the address book comprising at least two pieces of contact information;

generating at least two types of matching information based on the to-be-recognized contact information;

determining, for each of the at least two types of matching information, a matching degree between the to-be-recognized contact information and each of the at least two pieces of contact information based on the type of matching information wherein the matching information is a name keyword, and the matching degree is the ratio of a number of words of the contact information identical to the name keyword, to a sum of the number of the words in the contact information and a number words in the name keyword; and

extracting contact information matching the to-be-recognized contact information from the address book based on the determined matching degree.

10. The apparatus according to claim 9 , wherein the matching information is pinyin corresponding to the to-be-recognized contact information; and

the generating at least two types of matching information based on the to-be-recognized contact information comprises:

determining a first pinyin corresponding to the to-be-recognized contact information; and

determining a second pinyin corresponding to each piece of contact information in the address book.

11. The apparatus according to claim 10 , wherein the determining, for each of the at least two types of matching information, a matching degree between the to-be-recognized contact information and each of the at least two pieces of contact information based on the type of matching information, comprises:

importing, for each piece of contact information in the address book, the first pinyin and the second pinyin corresponding to the each piece of contact information into a pre-established pinyin similarity model to generate a pinyin similarity between the first pinyin and the second pinyin, wherein the pinyin similarity model is used to represent a corresponding relation between the first pinyin, the second pinyin and the pinyin similarity; and

determining the pinyin similarity as the matching degree between the to-be-recognized contact information and the contact information.

12. The apparatus according to claim 10 , wherein the determining, for each of the at least two types of matching information, a matching degree between the to-be-recognized contact information and each of the at least two pieces of contact information based on the type of matching information, comprises:

determining, for each piece of contact information in the address book, an edit distance between the to-be-recognized contact information and the each piece of contact information based on the first pinyin and the second pinyin corresponding to the contact information; and

determining the edit distance as the matching degree between the to-be-recognized contact information and the each piece of contact information.

13. The apparatus according to claim 9 , wherein the matching information is sound wave information corresponding to the to-be-recognized contact information; and

the generating at least two types of matching information based on the to-be-recognized contact information, comprises:

acquiring first sound wave information corresponding to the to-be-recognized contact information; and

acquiring, for each piece of contact information in the address book, second sound wave information corresponding to the each piece of contact information.

14. The apparatus according to claim 13 , wherein the determining, for each of the at least two types of matching information, a matching degree between the to-be-recognized contact information and each of the at least two pieces of contact information based on the type of matching information, comprises:

determining, for each piece of contact information in the address book, a similarity between the first sound wave information and the second sound wave information corresponding to the each piece of contact information as the matching degree between the to-be-recognized contact information and the each piece of contact information.

15. The apparatus according to claim 9 , wherein the matching information is a title keyword; and

the generating at least two types of matching information based on the to-be-recognized contact information, comprises:

extracting a title keyword from the to-be-recognized contact information.

16. The apparatus according to claim 15 , wherein the determining, for each of the at least two types of matching information, a matching degree between the to-be-recognized contact information and each of the at least two pieces of contact information based on the type of matching information, comprises:

acquiring pre-generated title relationship information, wherein the title relationship information is used to indicate an association relationship between titles expressing the same meaning;

acquiring a target title including the same meaning as the title keyword based on the title relationship information; and

selecting, for each piece of contact information in the address book, a maximum matching degree as the matching degree between the to-be-recognized contact information and the each piece of contact information, from a matching degree between the title keyword and the each piece of contact information and a matching degree between the target title and the each piece of contact information.

17. A non-transitory computer medium, comprising a computer program, wherein the program, when executed by a processor, causes the processor to perform operations, the operations comprising:

receiving and parsing voice information of a user to generate text information corresponding to the voice information;

extracting to-be-recognized contact information from the text information;

acquiring an address book of the user, the address book comprising at least two pieces of contact information;

generating at least two types of matching information based on the to-be-recognized contact information;

determining, for each of the at least two types of matching information, a matching degree between the to-be-recognized contact information and each of the at least two pieces of contact information based on the type of matching information, wherein the matching information is a name keyword, and the matching degree is the ratio of a number of words of the contact information identical to the name keyword, to a sum of the number of the words in the contact information and a number words in the name keyword; and

extracting contact information matching the to-be-recognized contact information from the address book based on the determined matching degree.