System and method for providing distributed intelligent assistance

• US 9,122,744 B2
• Filed: 10/11/2011
• Issued: 09/01/2015
• Est. Priority Date: 10/11/2010
• Status: Active Grant

• Current Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Original Assignee: Next IT Corporation (Verint Systems Incorporated)
• Inventors: Spivack, Nova T.
• Primary Examiner(s): Gaffin, Jeffrey A
• Assistant Examiner(s): Kim, David H
• Application Number:
  US13/271,175
• Publication Number:
  US 20120117005A1
• Time in Patent Office: 1,421 Days
• Field of Search: 706/11, 704/257
• US Class Current: 1/1
• 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:

receiving from a client device and displaying on the client device a user inquiry associated with a user, the user inquiry having a linguistic pattern including a verb;

generating a follow up question based on the user inquiry;

displaying on the client device the follow up question;

receiving from the client device and displaying on the client device a follow up answer from the user;

determining a task to be performed at least in part by an intelligent assistant based at least in part on the follow up answer from the user, 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;

causing the task to be performed at least in part by the intelligent assistant; and

generating and displaying on the client device a response regarding the task.

2. The method of claim 1, further comprising:

generating and displaying another follow up question based on the user inquiry and the follow up answer; and

receiving and displaying another follow up answer from the user.

3. The method of claim 2, wherein the generating and displaying the response comprises generating and displaying a response based on the user inquiry, the follow up answer and the other follow up answer.

4. The method of claim 1, wherein the follow up question is a fillable form and the follow up answer is a filled form.

5. The method of claim 1, further comprising:

expanding a display area of the client device automatically to accommodate the user inquiry, the follow up question, the user answer and the response.

6. The method of claim 5, further comprising:

scrolling up and down the display area to display the user inquiry, the follow up question, the user answer and the response.

7. The method of claim 1, wherein the response comprises a hypertext link, and the method further comprises:

receiving a new user inquiry once the hypertext link is selected by the user.

8. The method of claim 1, wherein the user inquiry, the follow up question, the follow up answer, and the response are displayed via at least one of a browser plug-in, a browser input field, a mobile application, a web page, a browser toolbar, a computer application, a computer toolbar, a widget in a website, or an application programming interface (API).

9. The method of claim 1, further comprising:

generating and displaying a result based on the user inquiry and the follow up answer.

10. The method of claim 9, wherein the result comprises at least one content of an answer, a number, a formula, a summary, a recommendation, a list, a table, a statistics, a map, a graph, a picture, a review, an audio, a video, a price, an availability, a feature, an advertisement, a contact, a reference, an excerpt, or a link to a service.

11. The method of claim 9, wherein the result is displayed via a browser plug-in, a browser output field, a mobile application, a web page, a message, an email, a browser toolbar, a computer application, a computer toolbar, a widget in a website, or an application programming interface (API).

12. The method of claim 1, wherein the user inquiry is in at least one of a natural language, a formal language, or a specific syntax language.

13. The method of claim 1, wherein the user inquiry comprises at least one verb of find, search, buy, sell, publish, send, ask, answer, get, offer, compare, like, make, automate, call, set, teach, learn, remember, save, schedule, meet, compute, learn, subscribe, give, put, save, create, post, start, stop, go to, keep, is, modify, alert, book, summarize, endorse, view, help, launch, or a synonym thereof.

14. The method of claim 1, wherein the response is generated at least partially based on a human input.

20. The method of claim 1, wherein the task further comprises a sequence of requests and responses directed to a single goal.

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;

receiving user inquiry from a user;

recognizing a linguistic pattern including a verb from the user inquiry and parsing the user inquiry into a request based on the linguistic pattern including the verb;

obtaining feedback based on the request;

determining a task based at least in part on the feedback, the task including at least one of buying an item or service, selling an item or service, publishing, offering, comparing, or calling;

causing the task to be performed at least in part by an intelligent assistant;

constructing a result regarding the task; and

presenting the result to the user.

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

learning a fact statement based on an artificial intelligence analysis of the user inquiry, the feedback and the result.

17. A non-transitory computer-readable storage medium comprising computer-executable instructions for performing operations comprising:

receiving user inquiry from a user;

recognizing a linguistic pattern including a verb from the user inquiry and parsing the user inquiry into a command based on the linguistic pattern including the verb;

determining a task to be performed at least in part by an intelligent assistant based at least in part on the command, the task including at least one of learning, saving, scheduling, subscribing, posting, starting, stopping, modifying, alerting, booking, or summarizing;

causing the task to be performed at least in part by the intelligent assistant;

constructing a result related to the task; and

presenting the result to the user.

18. The non-transitory computer-readable storage medium of claim 17, wherein the operations further comprise:

receiving additional information from the user via a dialogue or a form; and

updating the command based on the additional information.

19. The non-transitory computer-readable storage medium of claim 17, wherein the operations further comprise:

learning a fact statement based on an artificial intelligence analysis of the user inquiry and the result.