Systems for dynamically generating and presenting narrative content

• US 8,515,737 B2
• Filed: 04/06/2011
• Issued: 08/20/2013
• Est. Priority Date: 04/06/2010
• Status: Active Grant

• Current Assignee: STATS LLC (Stats Holdings LLC)
• Original Assignee: Automated Insights, Inc. (Stats Holdings LLC)
• Inventors: Allen, Robert C
• Primary Examiner(s): Godbold, Douglas
• Application Number:
  US13/081,052
• Publication Number:
  US 20110246182A1
• Time in Patent Office: 867 Days
• Field of Search: 704/1, 704/9, 704/10
• US Class Current: 704/9
• CPC Class Codes: G06F 40/10 Text processing natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40
• CPC Class Codes: G06F 40/186 Templates
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management

Abstract

In some embodiments, a non-transitory processor-readable medium stores code representing instructions that when executed cause a processor to select a narrative content template based at least in part on a predetermined content type associated with a real-world and/or virtual event. The code further represents instructions that when executed cause the processor to select a narrative tone type. The code further represents instructions that when executed cause the processor to, for each phrase included in an ordered set of phrases associated with the narrative content template, select, based at least in part on the narrative tone type, a phrase variation from a set of phrase variations associated with that phrase, and define, based on the selected phrase variation and at least one datum from a set of data, a narrative content portion associated with the real-world event. The code further represents instructions that when executed cause the processor to output, at a display, the narrative content portion.

Claims

1. A non-transitory processor-readable medium storing code representing instructions that when executed cause a processor to:

select a narrative template based at least in part on a predetermined content type associated with a real-world event;

select a narrative tone type based at least in part on a tone associated with the real-world event; and

for each phrase included in an ordered set of phrases associated with the narrative template;

select, based at least in part on the narrative tone type, a phrase variation from a set of phrase variations associated with that phrase;

define, based on the selected phrase variation and at least one datum from a set of data, a narrative content portion associated with the real-world event; and

send a signal such that the narrative content portion is output at a display.

2. The non-transitory processor-readable medium of claim 1, wherein the narrative tone type is selected based at least in part on at least one of:

a portion of the narrative template;

the set of data;

the predetermined content type; and

a calculation based at least in part on one or more contextual factors associated with the real-world event.

3. The non-transitory processor-readable medium of claim 1, wherein the narrative template is one of a set of narrative templates associated with the predetermined content type, and

the narrative template is selected based at least in part on a pseudo-random selection process.

4. The non-transitory processor-readable medium of claim 1, wherein the narrative template includes text content associated with a theme, the theme being associated with the real-world event.

5. The non-transitory processor-readable medium of claim 1, wherein the real-world event is a sporting event including at least two opponents.

6. The non-transitory processor-readable medium of claim 1, wherein the narrative tone type is selected based at least in part on a recent performance of at least one of:

a sports team; and

an athlete.

7. The non-transitory processor-readable medium of claim 1, wherein the code further represents instructions that when executed cause the processor to:

store, at a memory, the narrative content portion.

8. A non-transitory processor-readable medium storing code representing instructions that when executed cause a processor to:

receive a sports event identifier (ID) associated with a sports event;

receive a first participant ID associated with the sports event ID;

receive a second participant ID associated with the sports event ID;

receive a statistic value associated with the first participant ID; and

define, based on a content template, a content portion including;

a name of a first participant associated with the first participant ID;

a name of a second participant associated with the second participant ID;

the statistic value; and

text associated with the sports event, the text based at least in part on a plurality of text elements associated with the content template, each text element from the plurality of text elements being associated with a preselected narrative tone, the preselected narrative tone being based at least in part on a tone associated with the sports event.

9. The non-transitory processor-readable medium of claim 8, wherein each text element from the plurality of text elements is associated with a predefined author style.

10. The non-transitory processor-readable medium of claim 8, wherein the preselected narrative tone is determined based on at least one of:

a recent performance of the first participant;

a recent performance of the second participant;

a ranking of the first participant;

a ranking of the second participant; and

a physical location of the sports event.

11. The non-transitory processor-readable medium of claim 8, wherein the preselected narrative tone is at least one of:

confident;

pessimistic;

optimistic;

or

apathetic.

12. The non-transitory processor-readable medium of claim 8, wherein each text element from the plurality of text elements is one of:

a phrase;

a sentence;

or

a paragraph.

13. A method, comprising:

receiving an instruction to define a narrative content portion based at least in part on an event;

receiving, from a database, a plurality of data associated with the event;

selecting, based on a narrative tone type that is based on the event, a narrative content template including a plurality of variable identifiers;

defining the narrative content portion based at least in part on a combination of;

a text portion of the narrative content template, the text portion being based on the narrative tone type; and

for each variable identifier from the plurality of variable identifiers, a datum from the plurality of data associated with that variable identifier; and

sending a signal such that the narrative content portion is output at a display.

14. The method of claim 13, wherein each variable identifier from the plurality of variable identifiers is included at a predefined position within the text portion of the narrative content template, the defining further including:

writing, to a memory and in sequence,

     1) each character from the text portion of the narrative content template and

     2) each datum from the plurality of data based on the variable identifier from the plurality of variable identifiers with which the datum is associated.

15. The method of claim 13, wherein the event is at least one of:

a news event;

a weather event;

a financial event;

or

a sports event.

16. The method of claim 13, wherein the plurality of data is received in substantially real-time.

17. The method of claim 13, wherein the narrative content portion is one of:

an event summary;

an event recap;

or

an event preview.

18. The method of claim 13, wherein the narrative content template is selected based at least in part on user input.

19. The method of claim 13, wherein the plurality of data includes prior performance data associated with an event participant.

20. The method of claim 13, wherein the instruction is received in response to one of:

a termination of the event;

or

a predetermined schedule.

21. The method of claim 13, wherein the narrative content template is associated with a current event and the plurality of data is associated with a historical event.

22. The method of claim 13, wherein the narrative content portion is associated with an in-progress event.

23. The method of claim 13, wherein the narrative content template is associated with a player performance during an in-progress sporting event, and the plurality of data is associated with historical statistics associated with the player.

24. The method of claim 13, wherein the narrative content portion is output in response to an e-mail request.

25. The method of claim 13, wherein the narrative content portion is associated with a virtual event.

26. The method of claim 13, wherein the narrative content template is associated with a virtual event and the plurality of data is associated with a real-world event, the plurality of variable identifiers being selectively associated with the narrative content template.

27. The method of claim 13, wherein the plurality of variable identifiers are selectively associated with a narrative content template based on a user input.