Granted Patent B2

US 12,513,374 · App. 18/536,487 · Granted Dec 30, 2025

Inventors: Pedro Afonso Rodrigues Santos (Ovar, PT); Irenel Lopo Da Silva (Santa Tecla, AO); Nicolas Francisco Lori (Almada, PT); Jose Manuel Ferreira Machado (Guimarães, PT)

Assignee: Universidade Do Minho

H04N21/8547G06F16/75G06F40/10

Abstract

Claims (29)

1 . A computer-implemented method to generate a database for synchronization of a text, a video or audio media—individually or in combination—with a video stream to be generated using said database, comprising the steps of:

receiving an input text comprising a screenplay or other structured script document;

splitting the input text into text segments by detecting line breaks, tabs, spaces, text columns, or combinations thereof in the formatted document;

clustering the text segments into at least one text group, wherein each text group represents a movie scene, time of day, action line, dialogue line, character, musical score, sound effect, or a combination thereof as extracted from the screenplay;

labelling each text segment with a sequential timestamp; and,

storing each text segment with the label on a data record;

wherein the input text is split for each line break, tab, space, text column, or their combination;

wherein a text group comprises at least one text segment;

wherein the text group comprises a time interval label;

wherein the time interval of the text group corresponds to the duration of at least a portion of a video or audio media and is usable by a 3D animation and video editing tool to position corresponding video, audio, and subtitle elements automatically on the timeline.

2 . The method according to the previous claim 1 , wherein the time interval label of a text group comprises the timestamp of the first text segment and the timestamp of the last text segment as stored in the database tables.

3 . The method according to claim 1 wherein the time interval label of a text group is provided by a user through a video editing of the 3D animation software.

4 . Method according to claim 1 wherein the text group represents a movie scene, a time of day, an action line, a dialogue line, a character, a musical score, a sound effect, or a combination of any of the previous.

5 . Method according to claim 1 wherein the database comprises only one text group.

6 . Method according to claim 1 wherein the input text is generated from a speech or narration by a user to text.

7 . Method according to claim 1 further comprising a pre-processing step of the input text, preferably by converting a docx, pdf, or txt file.

8 . Method according to claim 1 wherein the input text is a screenplay.

9 . The computer-implemented method, according to claim 1 , wherein a user selects a frame from the video or audio media;

identifying a timestamp of said frame;

retrieving from said database the text group which comprises that timestamp; and,

outputting the text group related with the selected frame.

10 . Method according to the previous claim 9 , further comprising:

receiving a text input from a user;

adding the text input to a text group.

11 . Method according to claim 1 further comprising:

receiving an audio media from a user;

overlapping the received audio media with at least a portion of the audio of the video on said timestamp.

12 . A system to generate a database for synchronization of a text, a video or an audio media, comprising an electronic data processor configured to carry out the method of claim 1 .

13 . A computer program product stored in a non-transitory computer readable medium comprising computer instructions that, when executed by the processor, carry out the method according to claim 1 .

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (17)