AUTOMATED COLLABORATIVE ANNOTATION OF CONVERGED WEB CONFERENCE OBJECTS

• US 20130311177A1
• Filed: 05/16/2012
• Published: 11/21/2013
• Est. Priority Date: 05/16/2012
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bastide, Paul R., Loredo, Robert E., Broomhall, Matthew E., Lu, Fang, LeBlanc, Ralph E. Jr.
• Granted Patent: US 9,225,936 B2
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04L 12/1827 Network arrangements for conference optimisation or adaptation
• CPC Class Codes: H04N 7/15 Conference systems

Abstract

A methodology may be provided that automatically annotates web conference application sharing (e.g., sharing scenes and/or slides) based on voice and/or web conference data. In one specific example, a methodology may be provided that threads the annotations and assigns authorship to the correct resources.

Claims

1. A method implemented in a computer system for annotating during a web conference, wherein the web conference is carried out via a web conference application in which at least one page of a presentation is shared remotely between at least two people during the web conference, the method comprising:

receiving, with the computer system, spoken input from at least one of the two people;

transcribing, with the computer system, the received spoken input into transcribed text;

analyzing, with the computer system, the page to identify a location of at least one feature of the page;

correlating, with the computer system, at least one text element from the transcribed text to the feature of the page; and

annotating, with the computer system, the page by displaying in the vicinity of the location of the feature the correlated text element.

2. The method of claim 1, wherein the at least two people comprise at least one presenter and at least one attendee.

3. The method of claim 2, wherein:

the receiving, with the computer system, the spoken input from at least one of the two people comprises;

(a) receiving, with the computer system, spoken input from the presenter; and

(b) receiving, with the computer system, spoken input from the attendee;

the transcribing, with the computer system, the received spoken input into transcribed text comprises;

(a) transcribing, with the computer system, the received spoken input from the presenter into transcribed presenter text; and

(b) transcribing, with the computer system, the received spoken input from the attendee into transcribed attendee text;

the correlating, with the computer system, at least one text element from the transcribed text to the feature of the page comprises;

(a) correlating, with the computer system, at least one text element from the transcribed presenter text to the feature of the page; and

(b) correlating, with the computer system, at least one text element from the transcribed attendee text to the feature of the page; and

the annotating, with the computer system, the page by displaying in the vicinity of the location of the feature the correlated text element comprises;

(a) annotating, with the computer system, the page by displaying in the vicinity of the location of the feature the correlated text element from the transcribed presenter text; and

(b) annotating, with the computer system, the page by displaying in the vicinity of the location of the feature the correlated text element from the transcribed attendee text.

4. The method of claim 1, wherein:

the analyzing, with the computer system, the page to identify the location of at least one feature of the page comprises;

(a) analyzing, with the computer system, the page to identify a first location of a first feature of the page; and

(b) analyzing, with the computer system, the page to identify a second location of a second feature of the page;

the correlating, with the computer system, at least one text element from the transcribed text to the feature of the page comprises;

(a) correlating, with the computer system, a first text element from the transcribed text to the first feature of the page; and

(b) correlating, with the computer system, a second text element from the transcribed text to the second feature of the page; and

the annotating, with the computer system, the page by displaying in the vicinity of the location of the feature the correlated text element comprises;

(a) annotating, with the computer system, the page by displaying in the vicinity of the location of the first feature the correlated first text element; and

(b) annotating, with the computer system, the page by displaying in the vicinity of the location of the second feature the correlated second text element.

5. The method of claim 1, wherein the page comprises one of a slide and a scene.

6. The method of claim 1, wherein the location is an X-Y coordinate location.

7. The method of claim 1, wherein the vicinity of the location of the feature is overlaid on top of the feature.

8. The method of claim 1, wherein the correlation between the text element to the feature of the page is an exact correlation.

9. The method of claim 1, wherein the feature is selected from the group including:

(a) a name;

(b) a shape; and

(c) a content.

10. The method of claim 1, wherein the steps are carried out in the order recited.

11. A computer readable storage medium, tangibly embodying a program of instructions executable by the computer for annotating during a web conference, wherein the web conference is carried out via a web conference application in which at least one page of a presentation is shared remotely between at least two people during the web conference, the program of instructions, when executing, performing the following steps:

receiving, with the computer, spoken input from at least one of the two people;

transcribing, with the computer, the received spoken input into transcribed text;

analyzing, with the computer, the page to identify a location of at least one feature of the page;

correlating, with the computer, at least one text element from the transcribed text to the feature of the page; and

annotating, with the computer, the page by displaying in the vicinity of the location of the feature the correlated text element.

12. The computer readable storage medium of claim 11, wherein the at least two people comprise at least one presenter and at least one attendee.

13. The computer readable storage medium of claim 12, wherein:

the receiving, with the computer, the spoken input from at least one of the two people comprises;

(a) receiving, with the computer, spoken input from the presenter; and

(b) receiving, with the computer, spoken input from the attendee;

the transcribing, with the computer, the received spoken input into transcribed text comprises;

(a) transcribing, with the computer, the received spoken input from the presenter into transcribed presenter text; and

(b) transcribing, with the computer, the received spoken input from the attendee into transcribed attendee text;

the correlating, with the computer, at least one text element from the transcribed text to the feature of the page comprises;

(a) correlating, with the computer, at least one text element from the transcribed presenter text to the feature of the page; and

(b) correlating, with the computer, at least one text element from the transcribed attendee text to the feature of the page; and

the annotating, with the computer, the page by displaying in the vicinity of the location of the feature the correlated text element comprises;

(a) annotating, with the computer, the page by displaying in the vicinity of the location of the feature the correlated text element from the transcribed presenter text; and

(b) annotating, with the computer, the page by displaying in the vicinity of the location of the feature the correlated text element from the transcribed attendee text.

14. The computer readable storage medium of claim 11, wherein:

the analyzing, with the computer, the page to identify the location of at least one feature of the page comprises;

(a) analyzing, with the computer, the page to identify a first location of a first feature of the page; and

(b) analyzing, with the computer, the page to identify a second location of a second feature of the page;

the correlating, with the computer, at least one text element from the transcribed text to the feature of the page comprises;

(a) correlating, with the computer, a first text element from the transcribed text to the first feature of the page; and

(b) correlating, with the computer, a second text element from the transcribed text to the second feature of the page; and

the annotating, with the computer, the page by displaying in the vicinity of the location of the feature the correlated text element comprises;

(a) annotating, with the computer, the page by displaying in the vicinity of the location of the first feature the correlated first text element; and

(b) annotating, with the computer, the page by displaying in the vicinity of the location of the second feature the correlated second text element.

15. The computer readable storage medium of claim 11, wherein the steps are carried out in the order recited.

16. A computer-implemented web conference system in which at least one page of a presentation is shared remotely between at least two people during a web conference, the system comprising:

an input element configured to receive spoken input from at least one of the two people;

a transcription element configured to transcribe the spoken input into transcribed text;

an analysis element configured to analyze the page to identify a location of at least one feature of the page;

a correlation element configured to correlate at least one text element from the transcribed text to the feature of the page; and

an annotation element configured to annotate the page by displaying in the vicinity of the location of the feature the correlated text element.

17. The system of claim 16, wherein the at least two people comprise at least one presenter and at least one attendee.

18. The system of claim 17, wherein:

the input element is configured to;

(a) receive spoken input from the presenter; and

(b) receive spoken input from the attendee;

the transcription element is configured to;

(a) transcribe the received spoken input from the presenter into transcribed presenter text; and

(b) transcribe the received spoken input from the attendee into transcribed attendee text;

the correlation element is configured to;

(a) correlate at least one text element from the transcribed presenter text to the feature of the page; and

(b) correlate at least one text element from the transcribed attendee text to the feature of the page; and

the annotation element is configured to;

(a) annotate the page by displaying in the vicinity of the location of the feature the correlated text element from the transcribed presenter text; and

(b) annotate the page by displaying in the vicinity of the location of the feature the correlated text element from the transcribed attendee text.

19. The system of claim 16, wherein:

the analysis element is configured to;

(a) analyze the page to identify a first location of a first feature of the page; and

(b) analyze the page to identify a second location of a second feature of the page;

the correlation element is configured to;

(a) correlate a first text element from the transcribed text to the first feature of the page; and

(b) correlate a second text element from the transcribed text to the second feature of the page; and

the annotation element is configured to;

(a) annotate the page by displaying in the vicinity of the location of the first feature the correlated first text element; and

(b) annotate the page by displaying in the vicinity of the location of the second feature the correlated second text element.

20. The system of claim 16, wherein the steps are carried out in the order recited.