Apparatus and method for creating video on basis of interactive natural language processing

1 . An apparatus for creating a video based on interactive natural language processing, comprising:

a template database configured to store one or more template videos for each of a plurality of unit stories, wherein the template database is further configured to store a plurality of complex elements, each complex element comprising a combination of a plurality of items of division information and specific template videos matched to a single unit story;

a natural language processing (NLP) unit configured to perform natural language processing;

a scenario input unit configured to receive a user scenario;

a scenario dividing unit configured to divide the user scenario in accordance with content through natural language processing performed by the natural language processing unit into a plurality of sections in correspondence to the unit stories;

a section matching unit configured to match and set at least one template video stored in the template database to each of the plurality of sections by the unit stories;

an interactive selecting unit configured to, when a complex element corresponds to a specific section: propose the plurality of items of division information included in the complex element to a user terminal; perform natural language processing on a natural language answer received from the user terminal in response to the proposed items; and identify and set a specific template video connected to the division information selected by the user to the specific section; and

a video combining-creating unit configured to create a user video for the user scenario by connecting a plurality of template videos respectively matched and set to the plurality of sections.

2 . The apparatus of claim 1 , further comprising:

a video personalizing unit configured to personalize the template videos matched to the sections by: extracting content, which is not present in the division information, from a result of the natural language processing of the user scenario or the user's natural language answer; and changing a visual attribute of the template video to correspond to the extracted content in cooperation with the interactive selecting unit.

3 . The apparatus of claim 1 , further comprising:

a character creating-combining unit configured to create a user character using a user picture provided by the user and to combine the user character with the template video.

4 . The apparatus of claim 1 , further comprising:

a video database configured to store and manage the user video created by the video combining unit; and

a video external linking unit configured to provide the user video stored in the video database to an external service server or the user terminal.

5 . The apparatus of claim 1 , wherein the division information comprises of one or more of an image with dark clouds in the sky, an image with cirri in the sky, or an image with cumuli in the sky.

6 . The apparatus of claim 1 , wherein the division information comprises of an image with dark clouds in the sky, an image with cirri in the sky, and an image with cumuli in the sky.

7 . A method for creating a video based on interactive natural language processing, the method comprising:

storing, in a template database, one or more template videos for each of a plurality of unit stories, wherein the template database stores a plurality of complex elements matched with a combination of a plurality of items of division information and template videos for the unit stories;

receiving a user scenario through a scenario input unit;

performing natural language processing on the user scenario through a natural language processing (NLP) unit;

dividing the user scenario in accordance with content into a plurality of sections in correspondence to the unit stories based on a result of the natural language processing;

matching at least one template video stored in the template database to each of the plurality of sections by the unit stories;

when a complex element corresponds to a section, identifying selected division information by: presenting the plurality of items of division information to a user terminal; processing a natural language answer received from the user terminal; and setting a template video connected to the identified division information to the corresponding section; and

generating a user video for the user scenario by connecting the template videos respectively matched to the plurality of sections.

8 . The method of claim 7 , further comprising:

personalizing, by a video personalizing unit, the template videos matched to the sections by changing the template videos in accordance with a user request in cooperation with the interactive selecting unit.

9 . The method of claim 7 , further comprising:

generating, by a character generation unit, a user character using a user image provided by the user; and

combining the user character with the template videos matched to the plurality of sections.

10 . The apparatus of claim 7 , wherein the division information comprises of one or more of an image with dark clouds in the sky, an image with cirri in the sky, or an image with cumuli in the sky.

11 . A non-transitory computer-readable recording medium having recorded thereon computer-executable instructions that, when executed by a computer, cause the computer to perform a method for creating a video on the basis of interactive natural language processing, the method comprising:

storing, in a template database, one or more template videos for each of a plurality of unit stories, wherein the template database stores a plurality of complex elements matched with a combination of a plurality of items of division information and template videos for the unit stories;

receiving a user scenario through a scenario input unit;

performing natural language processing on the user scenario through a natural language processing unit;

dividing the user scenario in accordance with content into a plurality of sections in correspondence to the unit stories based on a result of the natural language processing;

matching at least one template video stored in the template database to each of the plurality of sections by the unit stories;

when a complex element corresponds to a section, identifying selected division information by: presenting the plurality of items of division information to a user terminal; processing a natural language answer received from the user terminal; and setting a template video connected to the identified division information to the corresponding section; and

generating a user video for the user scenario by connecting the template videos respectively matched to the plurality of sections.