DYNAMIC PERSONALIZED MULTI-TURN INTERACTION OF COGNITIVE MODELS

• US 20190019506A1
• Filed: 07/14/2017
• Published: 01/17/2019
• Est. Priority Date: 07/14/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Abrahams, Faried, Agarwalla, Lalit, Sivakumar, Gandhi
• Granted Patent: US 10,847,148 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06N 5/00 Computing arrangements using knowledge-based models
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
• CPC Class Codes: G10L 2015/225 Feedback of the input speech
• CPC Class Codes: G10L 2015/226 using non-speech characteristics
• CPC Class Codes: G10L 2015/228 of application context

Abstract

Multi-turn conversation systems that are personalized to a user based on insights derived from big data are described. A computer-based conversation system for interacting with a user includes: a CPU, a computer readable memory, and a computer readable storage medium associated with a computer device; and program instructions defining a statement and question framer that is configured to: obtain insights about a user from a big data engine; and generate a response to an input from the user based on the insights and the input. The program instructions are stored on the computer readable storage medium for execution by the CPU via the computer readable memory.

Claims

1-10. -10. (canceled)

11. A computer-based conversation system for interacting with a user, comprising:

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

program instructions defining a statement and question framer that is configured to;

obtain insights about a user from a big data engine; and

generate a response to an input from the user based on the insights and the input;

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

12. The system of claim 11, wherein the insights comprise at least one selected from the group consisting of:

user likes;

user dislikes; and

user opinions.

13. The system of claim 12, wherein the statement and question framer comprises:

a data enrichment and filtering module that filters the insights to determine filtered insights;

a text fragment and construction module that constructs text fragments based on the filtered insights;

an assembly generation module that generates plural sentences from the text fragments; and

a selection module that selects a single one of the plural sentences as the response.

14. The system of claim 13, further comprising program instructions defining a cognitive personalized interaction layer that is configured to:

determine context data based on context analysis of the input; and

pass the determined context data to the statement and question framer.

15. The system of claim 14, wherein the generating the response is additionally based on the determined context data.

16. The system of claim 13, wherein the generating the response is additionally based on at least one selected from the group consisting of:

time data, location data, and external data.

17. The system of claim 13, wherein the response answers a question defined by the input.

18. The system of claim 13, wherein the response includes a question to the user.

19. The system of claim 13, wherein the statement and question framer is configured to:

generate a statement that is not a response to the input; and

output the statement to the user in a push manner.

20. A computer program product for generating conversational responses to user input, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer device to cause the computer device to:

receive an input from a user;

determine context data based on the input;

obtain additional data including time data, location data, and external data;

obtain insights about the user from a big data engine, the insights comprising likes of the user, dislikes of the user, and opinions of the user;

generate a response to the input based on the context data, the insights, and the additional data; and

output the response.