GENERATING STORIES FROM SEGMENTS CLASSIFIED WITH REAL-TIME FEEDBACK DATA

• US 20200134084A1
• Filed: 10/31/2018
• Published: 04/30/2020
• Est. Priority Date: 10/31/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: RAKSHIT, Sarbajit K., KEEN, Martin G., BOSTICK, James E., GANCI, JR., John M.
• Granted Patent: US 11,086,907 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/56 Natural language generation

Abstract

Systems and methods for generating stories from segments classified with real-time feedback data are disclosed. In embodiments, a method includes sending, by a computing device, a story to a user computer device, wherein the story is associated with target story goals; receiving, by the computing device, real-time user feedback data of a consumer of the story; determining, by the computing device, that the real-time feedback data does not match the target story goals; and dynamically modifying, by the computing device, the story based on the determining that the real-time feedback data does not match the target story goals.

Claims

1. A computer-implemented method, comprising:

sending, by a computing device, a story to a user computer device, wherein the story is associated with target story goals;

receiving, by the computing device, real-time user feedback data of a consumer of the story;

determining, by the computing device, that the real-time feedback data does not match the target story goals; and

dynamically modifying, by the computing device, the story based on the determining that the real-time feedback data does not match the target story goals.

2. The computer-implemented method of claim 1, wherein the dynamically modifying the story comprises modifying the story to include one or more alternative subsets of stored content, wherein the one or more alternative subsets includes context data associated with one or more of the target story goals.

3. The computer-implemented method of claim 1, wherein the target story goals include at least one emotion to be invoked in the consumer.

4. The computer-implemented method of claim 1, further comprising:

determining, by the computing device, the target story goals based on user information;

analyzing, by the computing device, classified stored content to determine subsets of the classified stored content that match the target story goals, wherein each of the subsets of the classified stored content include associated context data;

generating, by the computing device, the story using a combination of the subsets of the classified stored content based on the target story goals.

5. The computer-implemented method of claim 4, wherein the user information is selected from the group consisting of:

a category of consumer;

a category of a presenter of the story;

target story content;

an intended emotion of the consumer;

an intended reaction of the consumer; and

combinations thereof.

6. The computer-implemented method of claim 4, further comprising:

generating, by the computing device, a plurality of combinations of subsets, wherein each of the plurality of combinations of subsets is an alternative story; and

presenting, by the computing device, the plurality of combinations and the story to the user computer device for selection.

7. The computer-implemented method of claim 6, further comprising ranking, by the computing device, the plurality of combinations of subsets, wherein the presenting the plurality of combinations comprises presenting the ranking of the plurality of combinations of subsets.

8. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to:

capture, in real-time, user feedback data of consumers of a story during a story session, wherein the story comprises a plurality of story segments;

map consumer emotions derived from the user feedback data to the story segments of the story;

store metadata for each of the story segments in a story database to produce categorized story segments, wherein the metadata is based on the mapping of the consumer emotions; and

generate a story from at least one of the categorized story segments based on the metadata matching a target emotion intended to be invoked by the story.

9. The computer program product of claim 8, further comprising program instructions to cause the computing device to:

identify the consumers; and

determine variations in metadata for each of the story segments for a plurality of different consumer types.

10. The computer program product of claim 8, further comprising program instructions to cause the computing device to:

compare the consumer emotions derived from the user feedback data with historic consumer emotion data in the story database to determine confidence levels for the mapping of the consumer emotions; and

save the confidence levels in the story database.

11. The computer program product of claim 8, further comprising program instructions to cause the computing device to:

determine a subset of the categorized story segments that match target story goals based on the metadata of the categorized story segments; and

generate a plurality of stories based on the subset of categorized story segments, wherein each of the plurality of stories comprises a unique combination of categorized story segments from the subset of categorized story segments.

12. The computer program product of claim 11, further comprising program instructions to cause the computing device to:

present the plurality of stories to a user;

receive a selection of a select story of the plurality of stories from the user; and

send the select story to one or more remote user computer devices.

13. The computer program product of claim 11, further comprising program instructions to cause the computing device to rank each of the plurality of stories based on how well each of the plurality of stories matches the target story goals.

14. The computer program product of claim 11, further comprising program instructions to cause the computing device to determine the target story goals based on user information, wherein the user information is selected from the group consisting of:

a category of consumer;

a category of a presenter of the story;

target story content;

an intended emotion of the consumer;

an intended reaction of the consumer; and

combinations thereof.

15. A system comprising:

a processor, a computer readable memory and a computer readable storage medium associated with a computing device;

program instructions to receive user information including a target emotion to be invoked in a consumer;

program instructions to determine target story goals based on the user information;

program instructions to determine a subset of classified story segments from a plurality of available classified story segments in a story database, wherein the subset of classified story segments match the target story goals; and

program instructions to generate a plurality of stories based on the subset of classified story segments, wherein each of the plurality of stories comprises a unique combination of classified story segments from the subset of classified story segments;

wherein the program instructions are stored on the computer readable storage medium for execution by the processor via the computer readable memory.

16. The system of claim 15, further comprising program instructions to rank each of the plurality of stories based on how well each of the plurality of stories match the target story goals.

17. The system of claim 15, further comprising:

program instructions to send a select story of the plurality of stories to a user computer device; and

program instructions to receive real-time user feedback data of a consumer of the select story.

18. The system of claim 17, further comprising:

program instructions to determine that the real-time feedback data does not match the target story goals; and

program instructions to dynamically modify the select story based on the determining that the real-time feedback data does not match the target story goals.

19. The system of claim 18, wherein modifying the select story is selected from the group consisting of:

modifying the story to include one or more alternative story segments from the subset of classified story segments;

modifying the select story to remove one or more classified story segments of the select story; and

combinations thereof.

20. The system of claim 15, wherein the user information further comprises a selection from the group consisting of:

a category of consumer;

a category of a presenter of the story;

target story content;

an intended reaction of the consumer; and

combinations thereof.