System and method for generating content corresponding to an event

Patent metadata

Field	Value
Publication number	US-10180974-B2
Application number	US-201414487801-A
Country	US
Kind code	B2
Filing date	Sep 16, 2014
Priority date	Sep 16, 2014
Publication date	Jan 15, 2019
Grant date	Jan 15, 2019

Abstract

Systems and methods for generating content corresponding to an event are provided. A method for generating content corresponding to an event, comprises defining a plurality of sub-events of the event, classifying one or more actual occurrences in the event into one or more of the sub-events, monitoring behavior of one or more users to determine areas of the event of interest to the one or more users, linking the one or more users to the one or more classified actual occurrences based on the areas of the event of interest, and generating content for the one or more classified actual occurrences.

First claim

What is claimed is:

1. A method for generating content corresponding to an event, comprising:
defining a plurality of sub-events of the event, wherein the plurality of sub-events include a plurality of occurrences that may occur within and during the event;
identifying one or more actual occurrences occurring during the event;
classifying at least one of the one or more actual occurrences as one or more active sub-events;
monitoring behavior of one or more users to determine interest of the one or more users in the one or more active sub-events, wherein the monitoring comprises:
obtaining at least one of line of sight data and gesture data for the one or more users from one or more sensors positioned separate from the one or more users and to capture at least one of the line of sight data and the gesture data for the one or more users; and
determining that the one or more users are observing the one or more active sub-events based on at least one of the line of sight data and the gesture data, wherein the line of sight data is based on a tracked gaze of the one or more users and the gesture data is based on a tracked gesture of the one of more users toward a particular location in a venue where the one or more active sub-events are occurring;

linking, based on the determining, each of the one or more users to a corresponding active sub-event that the one or more users have been determined to be observing;
generating content for the one or more active sub-events;
wherein the content comprises a description that is generated in response to and describes an actual activity occurring in real time in the one or more active sub-events, and a video accompanying the description;
wherein the one or more users are directly observing the actual activity;
wherein the generating of the content for the one or more active sub-events comprises:
retrieving and analyzing details of the activity occurring in real time in the one or more active sub-events;
automatically generating the description of the activity occurring in real time in the one or more active sub-events based on the retrieved and analyzed details, wherein the description comprises a verbal audio description of the actual activity that the one or more users are observing; and
automatically generating the video accompanying the description, wherein the video includes at least one of a replay from one or more previous events and a video of the activity occurring in real time in the one or more active sub-events, and wherein the video is modified to include at least one of highlighted and deemphasized portions; and

outputting to each of the one or more users, the content of the corresponding active sub-event that the one or more users have been determined to be observing in an audio and video stream;
wherein the steps of the method are performed by a computer system comprising a memory and at least one processor coupled to the memory.

2. The method according to claim 1 , wherein the outputting comprises automatically transmitting over at least one communication network the content to respective devices of the one or more users.

3. The method according to claim 1 , further comprising analyzing at least one of the line of sight data and the gesture data to determine the one or more active sub-events that the one or more users are observing.

4. The method according to claim 3 , further comprising incorporating statistical models into the analyzing.

5. The method according to claim 4 , wherein the statistical models include an interest history of the one or more users, and data on current active sub-events determined as being observed by multiple users.

6. The method according to claim 1 , wherein monitoring the behavior of the one or more users further comprises obtaining at least one of directional data and movement data for the one or more users from an electronic device on the one or more users.

7. The method according to claim 1 , wherein monitoring the behavior of the one or more users further comprises obtaining at least one of a textual input and a voice input from the one or more users to determine the one or more active sub-events that the one or more users are observing.

8. The method according to claim 1 , further comprising tracking the one or more actual occurrences with one or more additional sensors to acquire data about the one or more actual occurrences, wherein the classifying includes comparing the one or more tracked actual occurrences with the plurality of sub-events to match the one or more tracked actual occurrences with one or more defined sub-events.

9. A system for generating content corresponding to an event, comprising:
a tracking module executed via at least one processor operatively connected to a memory, wherein the tracking module comprises:
a sub-event tracker capable of:
defining a plurality of sub-events of the event, wherein the plurality of sub-events include a plurality of occurrences that may occur within and during the event;
identifying one or more actual occurrences occurring during the event; and
classifying at least one of the one or more actual occurrences as one or more active sub-events; and

an interest tracker capable of monitoring behavior of one or more users to determine interest of the one or more users in the one or more active sub-events, wherein the monitoring comprises:
obtaining at least one of line of sight data and gesture data for the one or more users from one or more sensors positioned separate from the one or more users and to capture at least one of the line of sight data and the gesture data for the one or more users; and
determining that the one or more users are observing the one or more active sub-events based on at least one of the line of sight data and the gesture data, wherein the line of sight data is based on a tracked gaze of the one or more users and the gesture data is based on a tracked gesture of the one of more users toward a particular location in a venue where the one or more active sub-events are occurring;

an analysis module executed via at least one processor operatively connected to a memory, the analysis module comprising a linking module capable of linking, based on the determining, each of the one or more users to a corresponding active sub-event that the one or more users have been determined to be observing;
a content generation module executed via at least one processor operatively connected to a memory and capable of generating content for the one or more active sub-events;
wherein the content comprises a description that is generated in response to and describes an activity occurring in real time in the one or more active sub-events, and a video accompanying the description;
wherein the one or more users are directly observing the actual activity;
wherein the generating of the content for the one or more active sub-events comprises:
retrieving and analyzing details of the activity occurring in real time in the one or more active sub-events;
automatically generating the description of the activity occurring in real time in the one or more active sub-events based on the retrieved and analyzed details, wherein the description comprises a verbal audio description of the actual activity that the one or more users are observing; and
automatically generating the video accompanying the description, wherein the video includes at least one of a replay from one or more previous events and a video of the activity occurring in real time in the one or more active sub-events, and wherein the video is modified to include at least one of highlighted and deemphasized portions; and

an output module executed via at least one processor operatively connected to a memory and capable of out

Assignees

• IBM

Inventors

• Aravkin Aleksandr Y
• Cardonha Carlos H
• Caskey Sasha P
• Kanevsky Dimitri
• Sainath Tara N

Classifications

• G06F17/30598 Primary

  Physics · mapped topic

• H04L67/12

  specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks · CPC title

• H04L67/22

  Electricity · mapped topic

• H04L67/535 Primary

  Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34) · CPC title

• G06F16/285 Primary

  Clustering or classification · CPC title