Method and system for expansion to everyday language by using word vectorization technique based on social network content
Provided is a method and system for expanding to an everyday language using a word vectorization technique based on social network content. A content providing method includes collecting social network content on the Internet; expanding corresponding content information to a word set of words included in the social network content with respect to target content that is to be serviced to a client; and providing the target content to the client with respect to user information associated with the client using the word set.
1. A computer implemented content providing method, comprising:
loading a program code stored in a program file for the content providing method;
constructing at least one keyword database for converting a word to a mathematical vector form based on social network content, the at least one keyword database each including a vector table of words and a vector conversion matrix;
converting corresponding content information associated with a target content to a vector form, the corresponding content information including a target keyword, a category name associated with the target content, or a combination thereof;
selecting one or more of the at least one keyword database corresponding to the target content to be serviced;
expanding the converted corresponding content information to an everyday language-based word set by referring to the selected one or more of the at least one keyword database, with respect to target content to be serviced; and
providing the target content to a client in response to the client inputting an input keyword that belongs to the everyday language-based word set.
2. The method of claim 1 , wherein the constructing comprises:
collecting the social network content;
pre-processing the social network content using a natural language processing technique; and
generating the at least one keyword database that includes the vector table and the vector conversion matrix by vectorizing a result of the pre-processing.
3. The method of claim 2 , wherein the collecting comprises:
classifying the social network content based on one or more classification criteria; and
constructing the at least one keyword database based on the one or more classification criteria.
4. The method of claim 2 , wherein the expanding comprises:
registering the target content and the corresponding content information;
converting the corresponding content information to the mathematical vector form by referring to the at least one keyword database; and
expanding the converted corresponding content information to the everyday language-based word set by extracting similar words having a semantic similarity in a vector space through the at least one keyword database.
5. The method of claim 1 , wherein the constructing comprises constructing the at least one keyword database based on one or more classification criteria of the social network content.
6. The method of claim 5 , wherein the at least one keyword database includes a plurality of databases, each of the plurality of databases representing a characteristic corresponding to the one or more classification criteria of the social network content.
7. The method of claim 1 , wherein the constructing comprises updating the at least one keyword database by periodically collecting the social network content.
8. The method of claim 1 , wherein the expanding comprises:
registering the target content and the corresponding content information;
converting the corresponding content information to the mathematical vector form by referring to the at least one keyword database; and
expanding the converted corresponding content information to the everyday language-based word set by extracting similar words having a semantic similarity in a vector space through the at least one keyword database.
9. The method of claim 1 , wherein the providing comprises:
transferring the everyday language-based word set; and
transferring the target content to the client in response to the input keyword from the client belonging to the everyday language-based word set.
10. A non-transitory computer-readable recording medium storing instructions that, when executed by a processor, cause the processor to implement a content providing method in conjunction with a computer system, the content providing method comprising:
loading a program code stored in a program file for the content providing method;
constructing at least one keyword database for converting a word to a mathematical vector form based on social network content, the at least one keyword database each including a vector table of words and a vector conversion matrix;
converting corresponding content information associated with a target content to a vector form, the corresponding content information including a target keyword, a category name associated with the target content, or a combination thereof;
selecting one or more of the at least one keyword database corresponding to the target content to be serviced;
expanding the converted corresponding content information to an everyday language-based word set by referring to the selected one or more of the at least one keyword database; and
providing the target content to a client in response to the client inputting an input keyword that belongs to the everyday language-based word set.
11. A computer-implemented content providing system, comprising:
at least one processor configured to execute non-transitory computer-readable instructions,
wherein the at least one processor is configured to,
load a program code stored in a program file for the content providing method,
construct at least one keyword database for converting a word to a mathematical vector form based on social network content, the at least one keyword database each including a vector table of words and a vector conversion matrix,
converting corresponding content information associated with a target content to a vector form, the corresponding content information including a target keyword, a category name associated with the target content, or a combination thereof,
selecting one or more of the at least one keyword database corresponding to the target content to be serviced,
expand the converted corresponding content information to an everyday language-based word set by referring to the selected one or more of the at least one keyword database, with respect to target content to be serviced, and
provide the target content to a client in response to the client inputting an input keyword that belongs to the everyday language-based word set.
12. The system of claim 11 , wherein the at least one processor is configured to construct the at least one keyword database by,
collecting the social network content,
pre-processing the social network content using a natural language processing technique, and
generating the at least one keyword database that includes the vector table and the vector conversion matrix by vectorizing a result of the pre-processing.
13. The system of claim 12 , wherein the at least one processor is configured to collect the social network content by,
classifying the social network content based on one or more classification criteria, and
constructing the at least one keyword database based on the one or more classification criteria.
14. The system of claim 12 , wherein the at least one processor is configured to expand the corresponding content information to the everyday language-based word set by,
registering the target content and the corresponding content information,
converting the corresponding content information to the mathematical vector form by referring to the at least one keyword database, and
expanding the converted corresponding content information to the everyday language-based word set by extracting similar words having a semantic similarity in a vector space through the at least one keyword database.
15. The system of claim 11 , wherein the at least one processor is configured to construct the at least one keyword database by constructing the at least one keyword database based on one or more classification criteria of the social network content.
16. The system of claim 15 , wherein the at least one keyword database includes a plurality of databases, each of the plurality of databases representing a characteristic corresponding to the one or more classification criteria of the social network content.
17. The system of claim 11 , wherein the at least one processor is configured to construct the at least one keyword database by updating the at least one keyword database by periodically collecting the social network content.
18. The system of claim 11 , wherein the at least one processor is configured to expand the corresponding content information to the everyday language-based word set by,
registering the target content and the corresponding content information,
converting the corresponding content information to the mathematical vector form by referring to the at least one keyword database, and
expanding the converted corresponding content information to the everyday language-based word set by extracting similar words having a semantic similarity in a vector space through the at least one keyword database.
19. The system of claim 11 , wherein the at least one processor is configured to provide the target content to the client by,
transferring the everyday language-based word set, and
transferring the target content to the client in response to the input keyword from the client belonging to the everyday language-based word set.