Intelligent action recommendation

• US 10,318,639 B2
• Filed: 02/03/2017
• Issued: 06/11/2019
• Est. Priority Date: 02/03/2017
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Fleischman, Thomas J., Krystek, Paul N., Kwatra, Shikhar
• Primary Examiner(s): Pham, Thierry L
• Application Number:
  US15/423,776
• Publication Number:
  US 20180226069A1
• Time in Patent Office: 858 Days
• Field of Search: 704 9, 704257, 704275
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06Q 10/101 Collaborative creation, e.g. joint development of products or services
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Intelligent action recommendation in a conversation monitors content of a conversation among at least two participants in real time. An overall goal of the conversation that represents a motivation for at least one of the participants to engage in the conversation is identified. The overall goal of the conversation is to be achieved upon termination of the conversation. At least one conversational input relevant to the monitored content and having a likelihood of advancing the conversation to successful achievement of the overall goal of the conversation is identified. The identified conversational input is communicated to at least one of the participants in the conversation.

Claims

1. A method for intelligent action recommendation in a conversation, the method comprising using a monitoring and analysis system executing on a computing system to:

monitor content of a conversation among at least two participants in real time, the monitoring and analysis system separate from and independent of the conversation, the participants and user devices associated with the participants and used to conduct the conversation;

identify an overall goal that is to be achieved among the participants using the conversation and an overall interaction goal among the participants, the overall goal comprising an intermediate step in the overall interaction goal and representing a motivation for at least one of the participants to engage in the conversation, the overall goal and the overall interaction goal generated by at least one of the participants independent of the monitoring and analysis system prior to initiation of the conversation, the overall goal to be achieved upon termination of the conversation;

identify at least one conversational input relevant to the monitored content and comprising a likelihood of advancing the conversation to successful achievement of the overall goal; and

communicate the conversational input to at least one of the participants in the conversation.

2. The method of claim 1, wherein monitoring content of the conversation comprises capturing at least one of oral communications among the participants, written communications among the participants, video of an environment containing at least one of the participants and physiological data for one or more participants.

3. The method of claim 1, wherein monitoring content of the conversation comprises:

capturing oral communications among the participants; and

using natural language processing to analyze the oral communications.

4. The method of claim 1, wherein the conversational input comprises text to be exchanged in writing, text to be spoken, a recommended conversational tone, physical gestures or combinations thereof.

5. The method of claim 1, wherein identifying that at least one conversational input further comprises:

identifying at plurality of conversational inputs, each conversational input comprising an associated likelihood of advancing the conversation to successful achievement of the overall goal of the conversation; and

selecting the conversational inputs having the highest likelihood of advancing the conversation to successful achievement of the overall goal of the conversation.

6. The method of claim 1, wherein identifying the at least one conversational input further comprises using a history of conversations among the plurality of participants to identify the at least one conversation input.

7. The method of claim 6, wherein the method further comprises using the monitoring and analysis system to maintain the history of conversations among the plurality of participants, the history of conversations among the plurality of participants comprising at least one of monitored content, overall goals of the conversations, exchanged conversational inputs with associated likelihoods of advancing the conversation to successful achievement of the overall goal of the conversation and results of the exchanged conversational inputs.

8. The method of claim 1, wherein:

the method further comprises using the monitoring and analysis system to identify a next objective to be accomplish in the conversation to advance the conversation toward the overall goal of the conversation; and

identifying the at least one conversational input further comprises identifying the at least one conversational input to achieve the next objective.

9. The method of claim 1, wherein the monitoring and analysis engine uses the monitored content of the conversation to determine an effect of the communicated conversational input on achieving the overall goal of the conversation.

10. A non-transitory computer-readable storage medium containing a computer-readable code that when read by a computer causes the computer to perform a method for intelligent action recommendation in a conversation, the method comprising using a monitoring and analysis system executing on a computing system to:

monitor content of a conversation among at least two participants in real time, the monitoring and analysis system separate from and independent of the conversation, the participants and user devices associated with the participants and used to conduct the conversation;

identify an overall goal that is to be achieved among the participants using the conversation and an overall interaction goal among the participants, the overall goal comprising an intermediate step in the overall interaction goal and representing a motivation for at least one of the participants to engage in the conversation, the overall goal to be achieved upon termination of the conversation, the overall goal and the overall interaction goal generated by at least one of the participants independent of the monitoring and analysis system prior to initiation of the conversation;

identify at least one conversational input relevant to the monitored content and comprising a likelihood of advancing the conversation to successful achievement of the overall goal; and

communicate the conversational input to at least one of the participants in the conversation.

11. The non-transitory computer-readable storage medium of claim 10, wherein monitoring content of the conversation comprises capturing at least one of oral communications among the participants, written communications among the participants, video of an environment containing at least one of the participants and physiological data for one or more participants.

12. The non-transitory computer-readable storage medium of claim 10, wherein monitoring content of the conversation comprises:

capturing oral communications among the participants; and

using natural language processing to analyze the oral communications.

13. The non-transitory computer-readable storage medium of claim 10, wherein the conversational input comprises text to be exchanged in writing, text to be spoken, a recommended conversational tone, physical gestures or combinations thereof.

14. The non-transitory computer-readable storage medium of claim 10, wherein identifying that at least one conversational input further comprises:

identifying at plurality of conversational inputs, each conversational input comprising an associated likelihood of advancing the conversation to successful achievement of the overall goal of the conversation; and

selecting the conversational inputs having the highest likelihood of advancing the conversation to successful achievement of the overall goal of the conversation.

15. The non-transitory computer-readable storage medium of claim 10, wherein identifying the at least one conversational input further comprises using a history of conversations among the plurality of participants to identify the at least one conversation input.

16. The non-transitory computer-readable storage medium of claim 15, wherein the method further comprises using the monitoring and analysis system to maintain the history of conversations among the plurality of participants, the history of conversations among the plurality of participants comprising at least one of monitored content, overall goals of the conversations, exchanged conversational inputs with associated likelihoods of advancing the conversation to successful achievement of the overall goal of the conversation and results of the exchanged conversational inputs.

17. The non-transitory computer-readable storage medium of claim 10, wherein:

the method further comprises using the monitoring and analysis system to identify a next objective to be accomplish in the conversation to advance the conversation toward the overall goal of the conversation; and

identifying the at least one conversational input further comprises identifying the at least one conversational input to achieve the next objective.

18. The non-transitory computer-readable storage medium of claim 10, wherein the monitoring and analysis system uses the monitored content of the conversation to determine an effect of the communicated conversational input on achieving the overall goal of the conversation.

19. A computing system for intelligent action recommendation in a conversation, the computing system comprising a monitoring and analysis system comprising:

monitoring modules to monitor content of a conversation among at least two participants in real time;

a conversation goal determination module to identify an overall goal that is to be achieved among the participants using the conversation and an overall interaction goal among the participants, the overall goal comprising an intermediate step in the overall interaction goal and representing a motivation for at least one of the participants to engage in the conversation, the overall goal and overall interaction goal generated by at least one of the participants independent of the monitoring and analysis system prior to initiation of the conversation, the overall goal to be achieved upon termination of the conversation;

an objective and conversational input determination module to identify at least one conversational input relevant to the monitored content and to determine a likelihood of advancing the conversation to successful achievement of the overall goal for the at least one conversational input; and

communication modules to communicate the conversational input to at least one of the participants in the conversation;

wherein the monitoring and analysis system is separate from and independent of the conversation, the participants and user devices associated with the participants and used to conduct the conversation.

20. The computing system of claim 19, wherein:

the objective and conversational determination module is further configured to identify a next objective to be accomplish in the conversation to advance the conversation toward the overall goal of the conversation; and

the objective and conversational determination module identifies the at least one conversational input to achieve the next objective.