Interaction with a portion of a content item through a virtual assistant

• US 9,672,822 B2
• Filed: 02/22/2013
• Issued: 06/06/2017
• Est. Priority Date: 02/22/2013
• Status: Active Grant

• Current Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Original Assignee: Next IT Corporation (Verint Systems Incorporated)
• Inventors: Brown, Fred A, Miller, Tanya M
• Primary Examiner(s): Hudspeth, David
• Assistant Examiner(s): PATEL, SHREYANS A
• Application Number:
  US13/774,381
• Publication Number:
  US 20140244266A1
• Time in Patent Office: 1,565 Days
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 9/453 Help systems
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

Techniques for interacting with a portion of a content item through a virtual assistant are described herein. The techniques may include identifying a portion of a content item that is relevant to user input and causing an action to be performed related to the portion of the content item. The action may include, for example, displaying the portion of the content item on a smart device in a displayable format that is adapted to a display characteristic of the smart device, performing a task for a user that satisfies the user input, and so on.

Claims

1. A computer-implemented method comprising:

causing, by a computing device, display of information representing a virtual assistant to facilitate a conversation between a user and the virtual assistant;

receiving, by the computing device, speech input from the user of a smart device, the speech input requesting an action associated with a content item;

determining a characteristic of a display of the smart device, the characteristic comprising at least one of a screen dimension or a screen resolution;

based at least in part on the characteristic of the display of the smart device, identifying a portion of the content item that satisfies the speech input;

determining a text size at which textual content within the content item is designed to be viewed;

based at least in part on the text size, processing the portion of the content item to convert the portion of the content item into a format that is associated with a particular legibility level; and

displaying the converted portion of the content item on the display of the smart device, the converted portion of the content item being displayed as a message from the virtual assistant.

2. The computer-implemented method of claim 1, wherein identifying the portion of the content item that satisfies the speech input comprises identifying a portion of the content item that includes a tag related to the speech input.

3. The computer-implemented method of claim 1, wherein the particular legibility level is above a legibility threshold.

4. The computer-implemented method of claim 1, wherein identifying the portion of the content item that satisfies the speech input comprises:

sending the speech input to a remote computing device for processing; and

receiving information from the remote computing device identifying the portion of the content item that satisfies the speech input.

5. The computer-implemented method of claim 1, wherein the portion of the content item comprises at least one of text or one or more images that are relevant to the speech input.

6. The computer-implemented method of claim 1, wherein the content item is initially formatted for a display that is larger in area than the display of the smart device.

7. One or more non-transitory computer-readable storage media storing computer-readable instructions that, when executed, instruct one or more processors to perform operations comprising:

causing output of a conversation user interface via a smart device, the conversation user interface being associated with a virtual assistant;

receiving user input requesting an action associated with a content item;

determining a characteristic of a display of the smart device, the characteristic comprising at least one of a screen dimension or a screen resolution;

based at least in part on the characteristic of the display of the smart device, identifying a portion of the content item that satisfies the user input;

determining a text size at which the portion of the content item is designed to be viewed;

based at least in part on the text size, processing the portion of the content item to convert the portion of the content item into a different format; and

causing display of the converted portion of the content item via the display of the smart device.

8. The one or more non-transitory computer-readable storage media of claim 7, wherein identifying the portion of the content item that satisfies the user input comprises analyzing the content item to determine a portion of the content item that is relevant to the user input.

9. The one or more non-transitory computer-readable storage media of claim 7, wherein identifying the portion of the content item that satisfies the user input comprises identifying a portion of the content item that includes a tag related to the user input.

10. The one or more non-transitory computer-readable storage media of claim 7, wherein the portion of the content item is viewable on the smart device at a legibility level above a particular legibility threshold.

11. The one or more non-transitory computer-readable storage media of claim 7, wherein the content item is initially formatted for a display that is larger in area than the display of the smart device.

12. The one or more non-transitory computer-readable storage media of claim 7, wherein the content item comprises a single web page.

13. A computer-implemented method comprising:

receiving, by a computing device, user input requesting an action associated with a content item;

determining, by the computing device, a characteristic of a display of a smart device, the characteristic comprising at least one of a screen dimension or a screen resolution;

determining, by the computing device, a portion of the content item that satisfies the user input based at least in part on a tag that is associated with the portion of the content item and the characteristic of the display of the smart device, the tag indicating a boundary of the portion of the content item;

determining, by the computing device, a text size at which textual content within the content item is designed to be viewed;

based at least in part on the text size, processing the portion of the content item to convert the portion of the content item into a format that is associated with a particular legibility level; and

utilizing the converted portion of the content item to perform the action requested by the user input, the action being performed at least in part by a virtual assistant.

14. The computer-implemented method of claim 13, further comprising:

before determining the portion of the content item that satisfies the user input, performing speech recognition to convert the user input into a format that is understood by the computing device,

wherein determining the portion of the content item that satisfies the user input comprises utilizing the converted user input to determine the portion of the content item that satisfies the user input.

15. The computer-implemented method of claim 13, wherein determining the portion of the content item that satisfies the user input comprises determining a portion of the content item that is tagged as being relevant to a particular request, the particular request being the same as the user input or having a threshold amount of similarity to the user input.

16. The computer-implemented method of claim 13, wherein the portion of the content item is converted to displayable content that is formatted for a display that has one or more dimensions below a particular value.

17. The computer-implemented method of claim 13, wherein the action comprises displaying the converted portion of the content item on the smart device.

18. The computer-implemented method of claim 13, wherein the action comprises at least one of performing a task for a user based at least in part on the converted portion of the content item, displaying the converted portion of the content item, or displaying information associated with the converted portion of the content item.

19. One or more non-transitory computer-readable storage media storing computer-readable instructions that, when executed, instruct one or more processors to perform the method of claim 13.

20. A system comprising:

one or more processors; and

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

causing display of information representing a virtual assistant to facilitate a conversation between a user and the virtual assistant;

receiving speech input of the user of a smart device, the speech input requesting an action;

determining a characteristic of a display of the smart device, the characteristic comprising at least one of a screen dimension or a screen resolution;

based at least in part on the characteristic of the display of the smart device, identifying a portion of a content item that satisfies the speech input;

determining a text size at which textual content within the content item is designed to be viewed;

based at least in part on the text size, processing the portion of the content item to convert the portion of the content item into a format that is associated with a particular legibility level; and

causing display of the converted portion of the content item on the display of the smart device, the converted portion of the content item being displayed as a message from the virtual assistant.

21. The system of claim 20, wherein identifying the portion of the content item that satisfies the speech input comprises identifying a portion of the content item that includes a tag related to the speech input.

22. The system of claim 20, wherein the particular legibility level is above a legibility threshold.

23. The system of claim 20, wherein identifying the portion of the content item that satisfies the speech input comprises:

sending the speech input to a remote computing device for processing; and

receiving information from the remote computing device identifying the portion of the content item that satisfies the speech input.

24. The system of claim 20, wherein the portion of the content item comprises at least one of text or one or more images that are relevant to the speech input.

25. The system of claim 20, wherein the content item is initially formatted for a display that is larger in area than the display of the smart device.

26. A system comprising:

one or more processors; and

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

receiving user input requesting an action;

determining a characteristic of a display of a smart device, the characteristic comprising at least one of a screen dimension or a screen resolution;

identifying a portion of a content item that satisfies the user input based at least in part on a tag that is associated with the portion of the content item and the characteristic of the display of the smart device;

determining a text size at which textual content within the content item is designed to be viewed;

based at least in part on the text size, processing the portion of the content item to convert the portion of the content item into a format that is associated with a predetermined legibility level; and

utilizing the converted portion of the content item to perform the action, the action being performed at least in part by a virtual assistant.

27. The system of claim 26, wherein the portion of the content item is converted to displayable content that is formatted for a display that has one or more dimensions below a predetermined value.

28. The system of claim 26, wherein the predetermined legibility level is above a legibility threshold.

29. The system of claim 26, wherein identifying the portion of the content item that satisfies the user input comprises:

sending the user input to a remote computing device for processing; and

receiving information from the remote computing device identifying the portion of the content item that satisfies the user input.

30. A computer-implemented method comprising:

providing, by a computing device, a virtual assistant via a smart device to interface with a user;

causing, by the computing device, the virtual assistant to solicit input from the user;

upon causing the virtual assistant to solicit input from the user, receiving input from the user requesting an action associated with a content item;

determining a characteristic of a display of the smart device, the characteristic comprising at least one of a screen dimension or a screen resolution;

based at least in part on the characteristic of the display of the smart device, identifying a portion of the content item that satisfies the input;

determining a size at which the portion of the content item is designed to be displayed;

based at least in part on the size, processing the portion of the content item to convert the portion of the content item into a different format; and

causing, by the computing device, the virtual assistant to display the converted portion of the content item.

31. The computer-implemented method of claim 30, wherein the display of the smart device has a display area that is smaller than a display area of a desktop computer.

32. The computer-implemented method of claim 30, wherein the content item comprises a single web page.

33. The computer-implemented method of claim 30, wherein the portion of the content item is displayed within a user interface associated with the virtual assistant.