IP Library Granted Patent US 11,521,079
Granted Patent B2
US 11,521,079 · App. 16/686,756 · Granted Dec 6, 2022

Method and apparatus for triggering the automatic generation of narratives

Inventors: Nathan Nichols (Chicago, IL); Michael Justin Smathers (Chicago, IL); Lawrence Birnbaum (Evanston, IL); Kristian Hammond (Chicago, IL); Lawrence E. Adams (Chicago, IL)
Assignee: Narrative Science Inc.
G06N5/02G06F40/56
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,521,079
App. No.
16/686,756
Granted
Dec 6, 2022
Kind
B2
Abstract

Method and Apparatus for Triggering the Automatic Generation of Narratives Artificial intelligence methods and systems for triggering the generation of narratives are disclosed. Specific embodiments relate to real-time evaluation and automated generation of narrative stories based on received data. For example, data can be tested against data representative of a plurality of story angles to determine whether a narrative story incorporating one or more such story angles is to be automatically generated.

Claims (44)

1. A method for applying artificial intelligence technology to process a data set and automatically generate a narrative story about the data set, the method comprising:

a processor executing a story evaluation program, wherein the story evaluation program executing step comprises computing an evaluation indicator about the data set according to defined metrics, the evaluation indicator indicating whether the narrative story about the data set is to be generated;

the processor triggering an execution of a story generation program in response to the evaluation indicator indicating that the narrative story about the data set is to be generated;

the processor executing the story generation program in response to the triggering step, the story generation program executing step comprising automatically rendering the narrative story about the data set based on an angle data structure that is deemed to appropriately characterize the data set; and

repeating the story evaluation program executing step, the triggering step, and the story generation program executing step with respect to a plurality of data sets to thereby automatically generate a plurality of narrative stories.

2. The method of claim 1 wherein the data sets comprise structured data relating to one or more subjects.

3. The method of claim 2 wherein the angle data structure represents a characterization of data, and wherein the story generation program executing step comprises the processor automatically rendering the narrative story in natural language such that it expresses the characterization represented by the angle data structure.

4. The method of claim 2 wherein the story evaluation program executing step and the story generation program executing step are simultaneously performed by the processor in a pipelined fashion with respect to a plurality of data sets.

5. The method of claim 4 wherein the processor comprises a single processor that performs the story evaluation program executing step, the triggering step, and the story generation program executing step.

6. The method of claim 4 wherein the processor comprises a plurality of processors, and wherein different processors perform the story evaluation program executing step and the story generation program executing step.

7. The method of claim 2 wherein the triggering step comprises the processor generating a story generation request for a computed evaluation indicator that indicates the narrative story about the data set is to be generated.

8. The method of claim 7 wherein the story generation program executing step comprises the processor (1) reading the story generation request and (2) automatically rendering the narrative story in natural language such that it expresses the characterization represented by the angle data structure.

9. The method of claim 7 wherein the triggering step comprises the story evaluation program writing a plurality of story generation requests into a queue and the story generation program reading the story generation requests from the queue.

10. The method of claim 9 wherein the story evaluation program executing step and the story generation program executing step are simultaneously performed by the processor in a pipelined fashion with respect to a plurality of data sets.

11. The method of claim 1 further comprising maintaining a queue that lists a plurality of subjects, each subject having an associated data set, and wherein the story evaluation program executing step comprises the processor (1) reading subjects out of the queue and (2) selecting data sets for evaluation that are associated with the read subjects.

12. The method of claim 1 further comprising:

not rendering the narrative story about the data set if the evaluation indicator for that data set indicates that the narrative story about that data set is not to be generated.

13. The method of claim 2 wherein the structured data comprises a plurality of data elements relating to one or more subjects.

14. The method of claim 2 wherein the one or more subjects is a company or a plurality of companies.

15. The method of claim 2 wherein the data sets comprise stock price information about a plurality of companies.

16. A computer program product for applying artificial intelligence technology to process a data set and automatically generate a narrative story about the data set, the computer program product comprising:

a plurality of processor-executable instructions resident on a non-transitory computer-readable storage medium, the instructions configured, upon execution by a computer system, to cause the computer system to:

execute a story evaluation program, wherein the story evaluation program execution comprises a computation of an evaluation indicator about the data set according to defined metrics, the evaluation indicator indicating whether the narrative story about the data set is to be generated;

trigger an execution of a story generation program in response to the evaluation indicator indicating that the narrative story about the data set is to be generated;

execute the story generation program in response to the trigger operation, wherein the story generation program execution is configured to automatically render the narrative story about the data set based on an angle data structure that is deemed to appropriately characterize the data set; and

repeat the story evaluation program execution, the trigger operation, and the story generation program execution with respect to a plurality of data sets to thereby automatically generate a plurality of narrative stories.

17. The computer program product of claim 16 wherein the data sets comprise structured data relating to one or more subjects.

18. The computer program product of claim 17 wherein the angle data structure represents a characterization of data, and wherein the instructions corresponding to the story generation program execution are further configured, upon execution by the computer system, to cause the computer system to:

automatically render the narrative story in natural language such that it expresses the characterization represented by the angle data structure.

19. The computer program product of claim 17 wherein the instructions are further configured, upon execution by the computer system, to cause the computer system to:

execute the story evaluation program and the story generation program simultaneously in a pipelined fashion with respect to the data sets.

20. The computer program product of claim 16 wherein the instructions are further configured, upon execution by the computer system, to cause the computer system to not render the narrative story about the data set if the evaluation indicator for that data set indicates that the narrative story about that data set is not to be generated.

21. The computer program product of claim 16 wherein the data sets comprise a plurality of data elements relating to one or more subjects.

22. The computer program product of claim 21 wherein the one or more subjects is a company or a plurality of companies.

23. An apparatus for applying artificial intelligence technology to process a data set and automatically generate a narrative story about the data set, the apparatus comprising:

a processor configured to:

execute a story evaluation program to compute an evaluation indicator about the data set according to defined metrics, the evaluation indicator indicating whether the narrative story about the data set is to be generated;

trigger an execution of a story generation program in response to the evaluation indicator indicating that the narrative story about the data set is to be generated;

execute the story generation program in response to the trigger operation, wherein the story generation program execution is configured to automatically render the narrative story about the data set based on an angle data structure that is deemed to appropriately characterize the data set; and

repeat the story evaluation program execution, the trigger operation, and the story generation program execution with respect to a plurality of data sets to thereby automatically generate a plurality of narrative stories.

24. The apparatus of claim 23 wherein the data sets comprise structured data relating to one or more subjects.

25. The apparatus of claim 23 wherein the processor comprises a plurality of processors.

26. The apparatus of claim 23 wherein the data sets comprise a plurality of data elements relating to one or more subjects.

27. The apparatus of claim 26 wherein the one or more subjects is a company or a plurality of companies.

Assignments (4)
CHANGE OF NAME Recorded Mar 25, 2024
From: NARRATIVE SCIENCE INC.
To: NARRATIVE SCIENCE LLC
Reel/Frame 066884/0001 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 25, 2024
From: NARRATIVE SCIENCE LLC
To: SALESFORCE, INC.
Reel/Frame 067218/0449 →
SECURITY INTEREST Recorded Feb 24, 2020
From: NARRATIVE SCIENCE INC.
To: CIBC BANK USA
Reel/Frame 051904/0293 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 18, 2019
From: NICHOLS, NATHAN; SMATHERS, MICHAEL JUSTIN; BIRNBAUM, LAWRENCE; HAMMOND, KRISTIAN; ADAMS, LAWRENCE E.
To: NARRATIVE SCIENCE INC.
Reel/Frame 051038/0040 →
Continuity (9)
Continuation 14961018 · Dec 7, 2015
Continuation 14090021 · Nov 26, 2013
Continuation 13186346 · Jul 19, 2011
Continuation In Part 12986996 · Jan 7, 2011
Continuation In Part 12986981 · Jan 7, 2011
Continuation In Part 12986972 · Jan 7, 2011
Continuation In Part 13738609 · Jan 10, 2013
Continuation 12779683 · May 13, 2010
Related Publication 20200082276A1 · Mar 12, 2020
Cited By (11)
US 12,248,461 US 12,288,039 US 12,314,674 US 12,423,525 US 12,462,114 US 12,468,694 US 12,505,093 US 12,608,416 US 12,614,042 US 12,632,445 US 12,681,997