Visualization of a natural language text
This invention is related to visualization of a natural language text, namely, to conversion of such text into a corresponding image, animation, or a three-dimensional scene. The proposed solution provides for a tool set for visualization of such text and automatically obtaining an animated three-dimensional scene. The invention contemplates a method of text visualization comprising the steps of obtaining a natural language text, conducting an automatic semantic breakdown of the language text (parsing) with the purpose of obtaining a structured semantic net, creating a three-dimensional scene on the basis of semantic breakdown results, creating a video clip or a set of pictures using the obtained three-dimensional scenes, and visualization of the obtained video clip or set of images. The invention provides for simultaneous producing video clips by several users according to different scenarios, manual editing a three-dimensional scene and semantic breakdown results, replenishing a library by own content, etc.
1. A method of text visualization comprising the steps of:
providing a natural language text fragment comprising a number of sentences;
conducting a semantic analysis of the text fragment to produce a structured semantic net thereof with a text fragment action sequence;
processing the structured semantic net of the text fragment to generate an initial three-dimensional scene in accordance with the text fragment action sequence;
processing the structured semantic net of the text fragment to generate other three-dimensional scenes according to the text fragment action sequence;
compiling the generated three-dimensional scenes into a video clip or a set of pictures; and
visualizing the video clip or set of pictures.
2. The method according to claim 1 , wherein the text fragment includes a scenario.
3. The method according to claim 1 , further comprising adding a synchronous accompanying sound when producing a video clip.
4. The method according to claim 1 , wherein said conducting a semantic analysis of the whole text fragment comprises the substeps of:
splitting the text fragment into sentences;
numbering words within a sentence;
selecting objects, subjects, actions, and properties in the sentences;
grouping all the words with the help of a notion tree to reduce synonyms to general notions to unambiguously identify objects within the whole text fragment.
5. The method according to claim 1 , further comprising editing the generated three-dimensional scene manually by a user.
6. The method according to claim 1 , wherein the semantic analysis is performed automatically.
7. The method according to claim 6 , further comprising editing the results of the automatic semantic analysis manually by a user.
8. The method according to claim 1 , wherein the semantic analysis is performed manually by a user.
9. A system of transforming a text into animation comprising:
at least one Web-service processing a user request to visualize a natural language text fragment (NLTF);
a semantic analysis service breaking down the NLTF to produce a structured semantic net therefrom;
a meta database;
a scene compiler service creating finished three-dimensional scenes from the structured semantic net and the meta database;
a rendering service generating a video clip or a set of pictures from an aggregation of the three-dimensional scenes; and
a user's apparatus to visualize the video clip or the set of pictures
wherein the at least one Web-service is adapted to take into consideration statistics of the NLTF visualization requests, to accumulate data concerning frequency, time and resource indices calculated in the process of transforming text into animation, and to keep a log of its operation.
10. The system according to claim 9 , wherein the text fragment includes a scenario.
11. The system according to claim 9 , wherein the at least one Web-service is adapted to be authenticated by the user.
12. The system according to claim 9 , wherein it comprises a plurality of Web-services located on at least one machine.
13. The system according to claim 9 , further comprising a sound processor service to generate dialogs, sets of sounds produced during animation of a scene, and a background track.
14. The system according to claim 13 , wherein the sound processor service is combined with the rendering service and the scenes compiler service.
15. The system according to claim 13 , further comprising a component balancer to evaluate system component resources to thereby engage the components accordingly.
16. The system according to claim 15 , wherein the component balancer controls sequential data processing by the semantic analysis service, the scene compiler service, the sound processor service, and the rendering service.
17. The system according to claim 9 , wherein the rendering service is adapted to dub and compress the video clip.