Applied artificial intelligence technology for narrative generation based on analysis communication goals

Patent metadata

Field	Value
Publication number	US-10699079-B1
Application number	US-201816047800-A
Country	US
Kind code	B1
Filing date	Jul 27, 2018
Priority date	Feb 17, 2017
Publication date	Jun 30, 2020
Grant date	Jun 30, 2020

Abstract

Artificial intelligence (AI) technology can be used in combination with composable communication goal statements to facilitate a user's ability to quickly structure story outlines using “analyze” communication goals in a manner usable by an NLG narrative generation system without any need for the user to directly author computer code. This AI technology permits NLG systems to determine the appropriate content for inclusion in a narrative story about a data set in a manner that will satisfy a desired analysis communication goal such that the narratives will express various ideas that are deemed relevant to a given analysis communication goal.

First claim

What is claimed is:

1. A method of applying artificial intelligence to generate a narrative story from structured data according to a narrative generation process, the structured data comprising a plurality of data values associated with a plurality of data parameters, the method comprising:
a processor processing a communication goal statement in coordination with (i) a set of narrative analytics associated with the communication goal statement and (ii) an ontology, wherein the ontology comprises a plurality of ontological objects that define a knowledge base about the structured data for the narrative generation process, wherein the ontological objects include a plurality of entities, and wherein the communication goal statement corresponds to a communication goal for analyzing a specified group of entities within the ontology;
wherein the processing step comprises:
parameterizing the associated set of narrative analytics based on a plurality of the data parameters, wherein the parameterized set of narrative analytics includes group size characterization analytics; and
executing the parameterized set of narrative analytics with respect to the structured data and the ontology, wherein the executing step includes (1) determining a size characteristic for the specified entity group based on the group size characterization analytics as applied to the structured data, and (2) selectively processing the structured data as a function of the determined size characteristic to determine at least one idea for inclusion in the narrative story; and

a processor generating a narrative story about the structured data based on the executing step, wherein the narrative story expresses the determined at least one idea in natural language and satisfies the communication goal corresponding to the communication goal statement.

2. The method of claim 1 wherein the ontological objects further comprise a plurality of attributes associated with the entities, and wherein the communication goal statement corresponds to a communication goal for analyzing the specified entity group by a specified attribute.

3. The method of claim 1 wherein the ontological objects further comprise a plurality of attributes associated with the entities, and wherein the communication goal statement corresponds to a communication goal for analyzing the specified entity group by a specified first attribute and a specified second attribute.

4. The method of claim 1 wherein the ontological objects further comprise a plurality of attributes associated with the entities, and wherein the communication goal statement corresponds to a communication goal for analyzing the specified entity group by a change in a specified attribute over a specified time.

5. The method of claim 1 wherein the communication goal statement corresponds to a communication goal for analyzing the specified entity group by a specified characterization.

6. The method of claim 1 wherein the associated set of narrative analytics includes a parameterized conditional outcome framework.

7. The method of claim 6 wherein the conditional outcome framework comprises a plurality of conditional outcome data structures, wherein each conditional outcome data structure is associated with at least one condition, wherein a plurality of the conditional outcome data structures are linked with a plurality of idea data structures, each idea data structure representing an idea to be expressed in a narrative story;
wherein the executing step further includes a processor (1) determining which of the conditional outcome data structures is applicable to the structured data based on the conditions associated with the conditional outcome data structures, and (2) selecting an idea data structure that is linked with the determined conditional outcome data structure as the determined at least one idea; and
wherein the generating step includes a processor expressing the idea represented by the selected idea data structure in the narrative story.

8. The method of claim 7 wherein the conditional outcome framework comprises a plurality of the conditional outcome data structures arranged in a hierarchical relationship where at least one conditional outcome data structure is associated with a plurality of additional conditional outcome data structures.

9. The method of claim 7 further comprising:
a processor adjusting at least one link between an idea data structure and a conditional outcome data structure in response to an input.

10. The method of claim 7 further comprising:
a processor adjusting at least one of the conditions associated with a conditional outcome data structure in response to an input.

11. The method of claim 6 wherein the group size characterization analytics comprise a plurality of conditional outcome data structures corresponding to different characterizations for a size of the specified entity group.

12. The method of claim 6 wherein the conditional outcome framework comprises a plurality of conditional outcome data structures corresponding to different characterizations for a distribution of members of the specified entity group with respect to values of an attribute specified by the communication goal statement.

13. The method of claim 1 wherein the processing step further includes:
a processor selecting a set of narrative analytics from a plurality of sets of narrative analytics based on the communication goal statement.

14. An artificial intelligence apparatus for generating a narrative story from structured data according to a narrative generation process, the structured data comprising a plurality of data values associated with a plurality of data parameters, the apparatus comprising:
a processor configured to:
process a communication goal statement in coordination with (i) a set of narrative analytics associated with the communication goal statement and (ii) an ontology, wherein the ontology comprises a plurality of ontological objects that define a knowledge base about the structured data for the narrative generation process, wherein the ontological objects include a plurality of entities, and wherein the communication goal statement corresponds to a communication goal for analyzing a specified group of entities within the ontology, wherein as part of the process operation the processor is further configured to (1) parameterize the associated set of narrative analytics based on a plurality of the data parameters, wherein the parameterized set of narrative analytics includes group size characterization analytics, and (2) execute the parameterized set of narrative analytics with respect to the structured data and the ontology by (i) determining a size characteristic for the specified entity group based on the group size characterization analytics as applied to the structured data, and (ii) selectively processing the structured data as a function of the determined size characteristic to determine at least one idea for inclusion in the narrative story, and
generate a narrative story about the structured data based on the execution operation wherein the narrative story expresses the determined at least one idea in natural language and satisfies the communication goal corresponding to the communication goal statement.

15. The apparatus of claim 14 wherein the ontological objects further comprise a plurality of attributes associated with the entities, and wherein the communication goal statement corresponds to a communication goal for analyzing the specified entity group by a specified attribute.

16. The apparatus of claim 14 wherein the ontological objects further comprise a

Assignees

• Narrative Science Inc

Inventors

• Paley Andrew R
• Nichols Nathan D
• Trahan Matthew L
• Lewis Meza Maia
• Pham Michael Tien Thinh
• Truong Charlie M

Classifications

• G06N5/041

  Abduction · CPC title

• G06N5/022

  Knowledge engineering; Knowledge acquisition · CPC title

• G06N3/006

  based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] · CPC title

• G06F40/35

  Discourse or dialogue representation · CPC title

• G06F40/237

  Lexical tools · CPC title