STRUCTURED LABELING TO FACILITATE CONCEPT EVOLUTION IN MACHINE LEARNING

• US 20150227531A1
• Filed: 02/10/2014
• Published: 08/13/2015
• Est. Priority Date: 02/10/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: KULESZA, TODD DAVID, CHARLES, DENIS XAVIER, CARUANA, RICH, AMERSHI, SALEEMA AMIN, FISHER, DANYEL AHARON
• Granted Patent: US 10,318,572 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/287 Visualization; Browsing
• CPC Class Codes: G06F 16/358 Browsing; Visualisation therefor
• CPC Class Codes: G06F 16/44 Browsing; Visualisation therefor
• CPC Class Codes: G06F 3/04817 using icons graphical or visual programming using iconic symbols G06F8/34
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/0486 Drag-and-drop

Abstract

A system, method, and media are provided for generating a structured labeling graphical user interface. The user interface receives user input that associates multimedia content with categories. The user input may include user-supplied tags that further define the category for the multimedia content. The user-supplied tags are rendered proximate to the categories. In turn, a database logs user events to store, among other things, the categories, the user-supplied tags, time associated with completing the user-supplied tags, and time for associating multimedia content with the categories or tags.

Claims

1. A computer-implemented method for multimedia content labeling, the method comprising:

rendering multimedia content for display to a user in a portion of a graphical user interface; and

receiving user input to associate one of the at least two categories with the rendered multimedia content;

forming a group of multimedia content within at least one of the at least two categories; and

receiving user-supplied tags to describe a concept of the grouped multimedia content.

2. The method of claim 1, further comprising:

providing a prompt for a concept in the graphical user interface, wherein the graphical user interface includes the at least two categories for the prompt such that the at least two categories are selected from yes, no, and could be.

3. The method of claim 1, wherein visual indicators represent a number of multimedia content associated with each group of the at least two categories and are displayed proximate to the at least two categories.

4. The method of claim 3, wherein the visual indicators are thumbnails of the multimedia content or icons.

5. The method of claim 3, wherein the visual indicators are numerical values.

6. The method of claim 3, wherein the visual indicator reveals previews of additional content for the multimedia content in response to a hover command over the visual indicator.

7. The method of claim 1, further comprising:

providing a viewable region in the graphical user interface with multimedia content similar to multimedia content associated with the at least two categories.

8. The method of claim 1, wherein the user input is dragging and dropping a visual representation of the multimedia content onto or near a one of the at least two categories or user-supplied tags.

9. The method of claim 1, wherein the user input may include removing, combining, or adding user-supplied tags to the graphical user interface.

10. The method of claim 1, wherein the user input may include removing, combining, or adding groups within the at least two categories to the graphical user interface.

11. The method of claim 1, further comprising:

storing the user input, categories, and association between the multimedia content and the categories in a database, wherein storing the categories in the database includes storing a number of multimedia content associated with the groups within the at least two categories and a number of multimedia content associated with the user-supplied tags.

12. The method of claim 11, wherein storing the user input in the database includes storing an amount of time that occurs between each input event received from the user.

13. The method of claim 11, wherein storing the user input includes storing a number of revisions made to user-supplied tags or a number of move, combine, add, or delete inputs received for each of the groups within the at least two categories.

14. The method of claim 1, wherein the user input is a gesture or voice command.

15. One or more computer storage media having computer-executable instructions embodied thereon, that when executed, perform a method of generating a structured labeling graphical user interface, the method comprising:

generating a graphical user interface with at least two portions, a first portion for displaying multimedia content and a second portion for assigning the multimedia content to one of at least two categories;

receiving user input for associating multimedia content displayed in the first portion with one of the at least two categories in the second portion of the graphical user interface; and

generating summaries for multimedia content associated with user-supplied tags that correspond to each of the at least two categories, wherein the user-supplied tags receive input that further describe a concept corresponding to the multimedia content associated with one of the at least two categories or the user-supplied tags.

16. The media of claim 15, further comprising:

generating a third portion of the graphical user interface having uncategorized multimedia content that are similar to each other.

17. The media of claim 16, wherein generating summaries for multimedia content further comprises:

forming groups within the at least two categories; and

generating summaries for multimedia content associated with the groups within the at least two categories.

18. The media of claim 15, wherein the graphical user interface is updated to reflect the association between the selected one of the at least two categories and the multimedia content.

19. The media of claim 15, wherein the generated summaries are rendered in a visual representation of the user-supplied tags.

20. A computer system for structured multimedia content labeling that facilitates concept evolution, the system comprising:

a device configured to provide a user interface, wherein the user interface includes at least two categories and one or more user-supplied tags for each of the at least two categories, to render multimedia content for display to a user in a portion of the user interface; and

to receive user input to associate the rendered multimedia content with the at least two categories or the user-supplied tags; and

a database configured to store the user input, categories, user-supplied tags, and association between the multimedia content and the categories or user-supplied tags.