System and method for providing distributed intelligent assistance

• US 10,210,454 B2
• Filed: 08/27/2015
• Issued: 02/19/2019
• Est. Priority Date: 10/11/2010
• Status: Active Grant

• Current Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Original Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Inventors: Spivack, Nova T
• Primary Examiner(s): Gonzales, Vincent
• Application Number:
  US14/837,282
• Publication Number:
  US 20150363697A1
• Time in Patent Office: 1,272 Days
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/0485 Scrolling or panning
• CPC Class Codes: G06F 40/134 Hyperlinking
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition

Abstract

A system and a method for a service engine providing distributed intelligent assistance to a user are described herein. The method comprising steps of receiving and displaying a user inquiry from the user, the user inquiry having a linguistic pattern including a verb; generating and displaying a follow up question based on the user inquiry; receiving and displaying a follow up answer from the user; and generating and displaying a response based on the user inquiry and the follow up answer.

Claims

1. A method comprising:

causing a conversation user interface to be displayed via a display associated with a mobile device to enable a conversation between an intelligent assistant and a user associated with the mobile device, wherein the intelligent assistant is computer-implemented;

receiving, by a computer system, natural language input of the user during the conversation;

processing, by the computer system, the natural language input to identify a linguistic pattern of terms including a verb in the natural language input;

determining, by the computer system, an intent of the natural language input based at least in part on the linguistic pattern of terms in the natural language input;

based at least in part on the intent of the natural language input and an index for locating services that are relevant to the intent, determining, by the computer system, to send the natural language input to a human for human input, the human input comprising a response to the natural language input, wherein the human is different than the user associated with the device;

based at least in part on to send the natural language input for the human input, sending the natural language input to a device associated with the human to request that the human provide the human input;

receiving, by the computer system, the human input; and

providing, by the computer system, the response to the user via the conversation user interface, the response being represented within the conversation user interface as originating from the intelligent assistant.

2. The method of claim 1, further comprising:

monitoring activities of the user or another user when interacting with the intelligent assistant; and

determining a response to subsequently received natural language input based on the activities.

3. The method of claim 1, further comprising:

providing a follow up question to the natural language input via a fillable form;

receiving a follow up answer from the user via the fillable form, the follow up answer comprising a filled form; and

providing the follow up answer to the device associated with the human.

4. The method of claim 1, further comprising:

determining a location of the user; and

determining another response for the conversation based at least in part on the location of the user.

5. The method of claim 1, further comprising:

identifying a profile associated with the user; and

determining another response for the conversation based at least in part on the profile associated with the user.

6. The method of claim 1, further comprising:

identifying history data indicating previous interactions of the user with the intelligent assistant; and

determining another response for the conversation based at least in part on the history data.

7. The method of claim 1, wherein the processing the natural language input includes parsing the natural language input into the linguistic pattern of terms.

8. One or more non-transitory computer-readable media storing computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

causing a conversation user interface to be displayed to enable a conversation between an intelligent assistant and a user, the conversation user interface being associated with the intelligent assistant, wherein the intelligent assistant is computer-implemented;

receiving user input during the conversation;

based on a linguistic pattern of terms including a verb in the user input and on an index for locating services that are relevant to the user input, determining to route the conversation to a human to formulate a response, wherein the human is different than the user;

based at least in part on determining to route the conversation to the human to formulate the response, sending the user input to a computing device associated with the human to request that the human respond to the user input;

receiving input from the human regarding the user input;

determining a response based at least in part on the input from the human; and

causing the response to be displayed within the conversation user interface that is associated with the intelligent assistant.

9. The one or more non-transitory computer-readable media of claim 8, wherein the response indicates that a task has been performed to satisfy the user input, the task including at least one of buying an item or service, selling an item or service, publishing, sending a message, offering, comparing, making, automating, calling, setting, learning, saving, scheduling, subscribing, posting, starting, stopping, modifying, alerting, booking, or summarizing.

10. The one or more non-transitory computer-readable media of claim 8, wherein the operations further comprise:

monitoring activities of the human; and

determining a response to subsequently received user input based on the activities.

11. The one or more non-transitory computer-readable media of claim 8, wherein the operations further comprise:

providing a follow up question to the user input;

receiving a follow up answer from the user; and

providing the follow up answer to the device associated with the human.

12. The one or more non-transitory computer-readable media of claim 8, wherein the operations further comprise:

determining a location of the user; and

wherein the determining the response includes determining the response based at least in part on the location of the user.

13. The one or more non-transitory computer-readable media of claim 8, wherein the operations further comprise:

identifying a profile associated with the user; and

wherein the determining the response includes determining the response based at least in part on the profile associated with the user.

14. The one or more non-transitory computer-readable media of claim 8, wherein the operations further comprise:

identifying history data indicating previous interactions of the user with the intelligent assistant; and

wherein the determining the response includes determining the response based at least in part on the history data.

15. A system comprising:

one or more processors; and

memory communicatively coupled to the one or more processors and configured to store instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising;

providing a conversation user interface for an intelligent assistant to enable a conversation with a user, wherein the intelligent assistant is computer-implemented;

receiving user input for the user;

determining, based on a linguistic pattern of terms including a verb in the user input and on an index for locating services that are relevant to the user input, to send the user input to a computing device associated with a human that is associated with the intelligent assistance, wherein the human is different than the user;

causing the user input to be sent to the computing device associated with the human that is associated with the intelligent assistant;

receiving input from the human regarding the user input;

determining a response based at least in part on the input from the human; and

providing the response within the conversation user interface as originating from the intelligent assistant.

16. The system of claim 15, wherein the operations further comprise:

monitoring activities of the user or another user when interacting with the intelligent assistant; and

determining a response to subsequently received user input based on the activities.

17. The system of claim 15, wherein the operations further comprise:

determining a location of the user; and

wherein the determining the response includes determining the response based at least in part on the location of the user.

18. The system of claim 15, wherein the operations further comprise:

identifying a profile associated with the user; and

wherein the determining the response includes determining the response based at least in part on the profile associated with the user.

19. The system of claim 15, wherein the operations further comprise:

identifying history data indicating previous interactions of the user with the intelligent assistant; and

wherein the determining the response includes determining the response based at least in part on the history data.

20. The system of claim 15, wherein the operations further comprise:

connecting to an account for the user that is associated with a social networking site; and

performing a particular task for the user based at least in part on the account for the user;

wherein the response indicates that the particular task was performed for the user.