Systems and methods for generating content for a screenplay
Systems and methods are disclosed herein for generating content based on format-specific screenplay parsing techniques. The techniques generate and present content by generating new dynamic content structures to generate content segments for output on electronic devices. In one disclosed technique, a first instance of a first character name is identified from the screenplay document. A first set of character data following the first instance of the first character name from the screenplay document and preceding an instance of a second character name from the screenplay document is then identified. Upon identification of the first set of character data, a content structure including an object is generated. The object includes attribute table entries based on the first set of character data. A content segment is generated for output based on the content structure (e.g., a 3D animation of the first character interacting within a scene).
1. A method comprising:
in response to identifying a first instance of a name in a document:
extracting a first text of the document positioned between the identified first instance of the name and an instance of a different name in the document;
generating a time-based content structure comprising an object in an attribute table, wherein the object corresponds to the name;
modifying the time-based content structure to add a first temporal mapping to the object that corresponds to the name, wherein the first temporal mapping indicates that a first attribute applies to the object for a duration of a first time period, wherein the first attribute is based on the first text;
in response to identifying a second instance of the name in a document:
extracting a second text of the document positioned between the identified second instance of the name and an instance of a different name in the document;
modifying the time-based content structure, to add a second temporal mapping to the object that corresponds to the name, wherein the second temporal mapping indicates that a second attribute applies to the object for a duration of a second time period, wherein the second attribute is based on the second text; and
generating for output a content segment based on the time-based content structure, wherein the content segment includes one or more of image content, video content, and audio content based on referencing the first and second mappings and applying the first and second attributes to the object during the first and second time periods.
2. The method of claim 1 , comprising:
identifying with a linguistics processing engine at least one of an action, a state, an absolute location, a relative location, an absolute motion, and a relative motion based on the first text or the second text of the document over the first time period or the second time period, wherein the temporal mapping of the name or the different name is further mapped to the at least one of the action, the state, the absolute location, the relative location, the absolute motion, and the relative motion.
3. The method of claim 2 , comprising:
identifying with the linguistics processing engine each of the action, the state, the absolute location, the relative location, the absolute motion, and the relative motion based on the first text or the second text of the document over the first time period or the second time period, wherein the mapping of the name or the different name is further mapped to each of the action, the state, the absolute location, the relative location, the absolute motion, and the relative motion.
4. The method of claim 1 , wherein the first attribute or the second attribute is an action, and the temporal mapping includes a value indicative of a rate or a degree of the action.
5. The method of claim 1 , wherein the temporal mapping includes the first temporal mapping at the first point in the document representing the first time, and the second temporal mapping at the second point in the document representing the second time later than the first time, and one or more of an action, a state, an absolute location, a relative location, an absolute motion, and a relative motion is determined based on the first temporal mapping and the second temporal mapping.
6. The method of claim 5 , wherein the temporal mapping includes the first temporal mapping at the first point in the document representing the first time, and the second temporal mapping at the second point in the document representing the second time later than the first time, and each of the action, the state, the absolute location, the relative location, the absolute motion, and the relative motion is determined based on the first temporal mapping and the second temporal mapping.
7. The method of claim 1 , wherein the name or the different name is identified based on parsing the document based on a formatting type of the document.
8. The method of claim 7 , wherein the formatting type includes one or more of an indentation, a font type, a font style, a spacing, a paragraph style, a heading, formatting metadata, and a formatting indicator.
9. The method of claim 1 , wherein the document is a screenplay, wherein the object represents one of a character, a location, an object interacting with a character, an object interacting with the location, and a character interacting with the location, and wherein the name or the different name corresponds with the object.
10. The method of claim 1 , wherein the content segment is generated by one or more of combining, replacing, mixing, and matching one or more of the object, an action, a setting, an effect, the image content, the video content, and the audio content from one or more previously stored content structures to create a new content structure, which is then rendered as a new content segment.
11. A system comprising:
communications circuitry configured to access a document from a database; and
control circuitry configured to:
in response to identifying a first instance of a name in a document:
extract a first text of the document positioned between the identified first instance of the name and an instance of a different name in the document;
generate a time-based content structure comprising an object in an attribute table, wherein the object corresponds to the name;
modify the time-based content structure to add a first temporal mapping to the object that corresponds to the name, wherein the first temporal mapping indicates that a first attribute applies to the object for a duration of a first time period, wherein the first attribute is based on the first text;
in response to identifying a second instance of the name in a document:
extract a second text of the document positioned between the identified second instance of the name and an instance of a different name in the document;
modify the time-based content structure, to add a second temporal mapping to the object that corresponds to the name, wherein the second temporal mapping indicates that a second attribute applies to the object for a duration of a second time period, wherein the second attribute is based on the second text; and
generate for output a content segment based on the time-based content structure, wherein the content segment includes one or more of image content, video content, and audio content based on referencing the first and second mappings and applying the first and second attributes to the object during the first and second time periods.
12. The system of claim 11 , the control circuitry further configured to:
identify with a linguistics processing engine at least one of an action, a state, an absolute location, a relative location, an absolute motion, and a relative motion based on the first text or the second text of the document over the first time period or the second time period, wherein the temporal mapping of the name is further mapped to the at least one of the action, the state, the absolute location, the relative location, the absolute motion, and the relative motion.
13. The system of claim 12 , the control circuitry further configured to:
identify with the linguistics processing engine each of the action, the state, the absolute location, the relative location, the absolute motion, and the relative motion based on the first text or the second text of the document over the first time period or the second time period, wherein the mapping of the name is further mapped to each of the action, the state, the absolute location, the relative location, the absolute motion, and the relative motion.
14. The system of claim 11 , wherein the first attribute or the second attribute is an action, and the temporal mapping includes a value indicative of a rate or a degree of the action.
15. The system of claim 11 , wherein the temporal mapping includes the first temporal mapping at the first point in the document representing the first time, and the second temporal mapping at the second point in the document representing the second time later than the first time, and one or more of an action, a state, an absolute location, a relative location, an absolute motion, and a relative motion is determined based on the first temporal mapping and the second temporal mapping.
16. The system of claim 15 , wherein the temporal mapping includes the first temporal mapping at the first point in the document representing the first time, and the second temporal mapping at the second point in the document representing the second time later than the first time, and each of the action, the state, the absolute location, the relative location, the absolute motion, and the relative motion is determined based on the first mapping and the second temporal mapping.
17. The system of claim 11 , wherein the name is identified based on parsing the document based on a formatting type of the document.
18. The system of claim 17 , wherein the formatting type includes one or more of an indentation, a font type, a font style, a spacing, a paragraph style, a heading, formatting metadata, and a formatting indicator.
19. The system of claim 11 , wherein the document is a screenplay, wherein the object represents one of a character, a location, an object interacting with a character, an object interacting with the location, and a character interacting with the location, and wherein the name corresponds with the object.
20. The system of claim 11 , wherein the content segment is generated by one or more of combining, replacing, mixing, and matching one or more of the object, an action, a setting, an effect, the image content, the video content, and the audio content from one or more previously stored content structures to create a new content structure, which is then rendered as a new content segment.