Systems for dynamically generating and presenting narrative content

• US 9,146,904 B2
• Filed: 08/19/2013
• Issued: 09/29/2015
• 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:
  US13/969,834
• Publication Number:
  US 20140114647A1
• Time in Patent Office: 771 Days
• Field of Search: 704/1, 704/9, 704/10
• US Class Current: 1/1
• 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, based on a statistic indicative of a tone associated with an event, a narrative tone type;

select, based on a narrative content type associated with the event, a narrative template that includes a set of phrases;

select, based on the selected narrative tone type, a phrase variation from a set of phrase variations associated with a first phrase from the set of phrases;

select, based on the selected narrative tone type, a phrase variation from a set of phrase variations associated with a second phrase from the set of phrases;

send a signal indicative of a narrative content portion that includes the phrase variation associated with the first phrase and the phrase variation associated with the second phrase; and

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

2. The non-transitory processor-readable medium of claim 1, wherein the event is a business event.

3. The non-transitory processor-readable medium of claim 1, wherein 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 event.

5. The non-transitory processor-readable medium of claim 1, wherein the event is receipt of a financial report.

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.

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 method, comprising:

selecting, based on a narrative content type associated with a first event, a narrative template that includes a set of phrases;

selecting, based on a narrative tone type that is based on a statistic associated with the first event, a first phrase variation from a set of phrase variations associated with a phrase from the set of phrases;

sending, at a first time, a signal indicative of a first narrative content portion that includes the first phrase variation associated with the phrase;

selecting, based on a narrative content type associated with a second event, the narrative template;

selecting, in response to selecting the first phrase variation and based on the narrative tone type, a second phrase variation from a set of phrase variations associated with the phrase from the set of phrases, the second phrase variation being different from the first phrase variation;

sending, at a second time after the first time, a signal indicative of a second narrative content portion associated with the second event and that includes the second phrase variation associated with the phrase; and

sending, at a third time after the second time, a signal such that the second narrative content portion is output to a display.

9. The method of claim 8, wherein each phrase variation from the plurality of phrase variations is associated with a predefined author style.

10. The method of claim 8, wherein the narrative tone type is determined based on at least one of:

a recent performance of a first participant in the first event;

a recent performance of a second participant in the first event;

a ranking of the first participant;

a ranking of the second participant; and

a physical location of the first event.

11. The method of claim 8, wherein the narrative tone type is at least one of:

positive;

negative;

confident;

pessimistic;

optimistic;

or

apathetic.

12. The method of claim 8, wherein the first phrase is a sentence and the second phrase is a paragraph.

13. The method of claim 8, wherein the narrative template is selected based at least in part on user input.

14. The method of claim 8, wherein the statistic includes prior performance data associated with a participant of the first event.

15. An apparatus, comprising:

a processor to be operatively coupled to a memory and to execute a content generation module; and

the content generation module to receive an instruction to define a content portion,

the content generation module to select, based on a statistic indicative of a tone, a narrative tone type,

the content generation module to select, a narrative template that includes a set of phrases,

the content generation module to select, based on the narrative tone type, a phrase variation from a set of phrase variations associated with a first phrase from the set of phrases to define a first selected phrase,

the content generation module to select, based on the narrative tone type, a phrase variation from a set of phrase variations associated with a second phrase from the set of phrases to define a second selected phrase,

the content generation module to send a signal indicative of the content portion that includes the first selected phrase and the second selected phrase,

the content generation module to send a signal such that the narrative content portion is output to a display.

16. The apparatus of claim 15, wherein the content generation module is configured to receive the instruction in response to one of:

a termination of an event;

or

a predetermined schedule.

17. The apparatus of claim 15, wherein the content portion is one of:

an event summary;

an event recap;

or

an event preview.

18. The apparatus of claim 15, wherein the statistic is associated with a virtual event.

19. The apparatus of claim 18, wherein the statistic is based on a real-world event associated with the virtual event.

20. The apparatus of claim 15, wherein the content generation module to send a signal indicative of the content portion in response to an e-mail request.