Patent US10795560

System and method for detection and visualization of anomalous media events
[+] Show Details

US10795560

1. A method for identifying at least one anomalous event (AE) within a sporting event and identifying and displaying the location of the AE and a social media response to the AE, comprising: (16) (8)

receiving AV media data indicative of the sporting event;

identifying the AE within the AV media data;

determining the location of the AE on the actual field of play, an AE time of occurrence, and identifying one or more AE features of the AE;

receiving social media data;

identifying at least one social media response (SMR) related to the AE within the social media data, comprising: analyzing the social media data within a sample window timeframe of the AE time of occurrence;

identifying one or more SMR features of the social media data within the sample window timeframe; and

identifying the SMR having the SMR features that match a predetermined number of the AE features, as the at least one SMR;

determining at least one social media parameter associated with the at least one SMR, wherein the at least one social media parameter comprises at least one of: a total number of the SMRs related to the AE, a sentiment allocation for a plurality sentiments associated with the SMR related to the AE, a sentiment allocation associated with the SMR, social media sources posting

providing a graphic user interface (GUI) showing a virtual version of a field of play and at least one AE graphic on the virtual field of play, the AE graphic comprising a selectable graphical image indicative of the AE and positioned at a location indicative of real time spatial coordinates on the virtual field of play corresponding to the location of the AE on the actual field of play and at least one visual aspect of the AE graphic being indicative of the at least one social media parameter associated with the SMR related to the AE, wherein the at least one visual aspect of the AE graphic comprises at least one of: (i) a size of the AE graphic corresponding to the total number of the SMRs related to the AE and (ii) a shading of the AE graphic corresponding to the sentiment allocation associated with the SMR related to the AE or the allocation of the plurality of social media sources providing the SMRs related to the AE; and

wherein the AE graphic is updated according to the received social media data during the sample window timeframe.

2. The method of claim 1, wherein the determining the at least one social media parameter comprises at least one of: determining an amount of the SMRs corresponding to the AE in the social media data and determining a sentiment of the at least one SMR corresponding to the AE in the social media data. (0)

3. The method of claim 1, further comprising extracting from the AV media data an AV media segment corresponding to the AE, and displaying on the GUI an AV graphic, that, when selected, causes the AV media segment to play on the GUI. (0)

4. The method of claim 1, wherein the AE graphic has user selectable attributes, comprising at least one of: shape and color. (0)

5. The method of claim 1, wherein the GUI is displayed on a mobile device. (0)

6. The method of claim 1, wherein the SMR features comprises a topic that relates to the sporting event. (0)

7. The method of claim 1, wherein the SMR features comprises attributes of an SMR user. (0)

8. The method of claim 1, wherein the SMRs occur during the sporting event. (0)

9. The method of claim 1, wherein the determining the location of the AE on the actual field of play, comprises at least one of: receiving location tracking data from an AE sports object involved with the AE, and analyzing the AV media data to determine the location of an AE sports object involved with the AE. (1) (0)

11. The method of claim 1, wherein the GUI comprises displaying graphics comprising at least one of: Play Field graphic, AE graphic, AE Time Selector, AE Timeline, AE Details, Sentiment Allocation Chart, Social Media Source Allocation Chart, Social Media/Network Posts, Game Metadata, SMR Data Collection, and AE Type/Action Selector. (0)

12. The method of claim 1, wherein the identifying the AE within the AV media data, comprises analyzing at least one of: crowd noise, commentator voice intonation, learned event attributes, commentator language/words, and influencer sources language/words. (0)

13. The method of claim 1, wherein the identifying the AE within the AV media data, comprises using an AE identification model having model parameters. (1) (0)

16. The method of claim 1, wherein the AE features comprises an AE type/action. (0)

17. The method of claim 1, further comprising sending an AE alert message when an AE is detected and predetermined AE alert criteria are satisfied. (1) (0)

19. The method of claim 1, further comprising receiving a setting command from a user and displaying a settings menu configured to receive inputs from a user. (1) (0)

21. The method of claim 1, wherein the social media data is obtained from social media sources, comprising at least one of: Facebook, Twitter, Instagram, Google+, and internet blogs. (0)

34. The method of claim 1 wherein the AE features comprises at least one of: sport, team, players, and action/type, and the SMR features comprises at least one of: topic and attributes. (0)

22. A method for identifying at least one anomalous event (AE) within a sporting event and identifying and displaying at least one of the time and location of the AE and a social media response (SMR) related to the AE, comprising: (7) (8)

receiving AV media data indicative of the sporting event;

identifying the AE within the AV media data, the location of the AE on the actual field of play, an AE time of occurrence, and one or more AE features of the AE;

receiving social media data;

identifying one or more SMR features of the social media data within the sample window timeframe; and

identifying the SMR having the SMR features that match a predetermined number of the AE features, as the at least one SMR;

determining at least one social media parameter associated with the at least one SMR, wherein the at least one social media parameter comprises at least one of: a total number of the SMRs related to the AE, a sentiment allocation for a plurality of sentiments associated with the SMR related to the AE, a sentiment allocation associated with the SMR, social media sources posting the SMRs related to the AE, and an allocation of a plurality of social media sources providing the SMRs related to the AE; and

providing a graphic user interface (GUI) showing:

(i) a virtual version of the field of play and at least one AE graphic on the virtual field of play, the AE graphic comprising a selectable graphical image indicative of the AE and positioned at a location indicative of real-time spatial coordinates on the virtual field of play corresponding to the location of the AE on the actual field of play and at least one visual aspect of the AE graphic being indicative of the at least one social media parameter associated with the SMR related to the AE, wherein the at least one visual aspect of the AE graphic comprises at least one of: (i) a size of the AE graphic corresponding to the total number of the SMRs related to the AE and (ii) a shading of the AE graphic corresponding to the sentiment allocation associated with the SMR related to the AE or the allocation of the plurality of social media sources providing the SMRs related to the AE; and

(ii) an AE timeline having the at least one AE graphic positioned along the AE timeline corresponding to the AE time of occurrence; and

23. The method of claim 22 wherein the AE identification model comprises at least one of: a factor sum equation and a machine learning model. (0)

24. The method of claim 22 wherein the machine learning model comprises a Support Vector Machine (SVM). (0)

25. The method of claim 22, further comprising adjusting the model parameters in the AE identification model based on performance. (0)

26. The method of claim 22, further comprising sending an alert message when an AE is detected and AE alert criteria are satisfied. (0)

32. The method of claim 22, wherein the AE features comprises an AE type/action. (0)

33. The method of claim 22 wherein the identifying the AE in the media data comprises: (0) (2)

36. The method of claim 22 wherein the AE features comprises at least one of: sport, team, players, and action/type, and the SMR features comprises at least one of: topic and attributes. (0)

27. A method for identifying at least one anomalous event (AE) within a sporting event and identifying and displaying the time of the AE and a social media response (SMR) related to the AE, comprising: (5) (6)

receiving AV media data indicative of the sporting event;

identifying the AE within the AV media data, the location of the AE on the actual field of play, an AE time of occurrence, and one or more AE features of the AE;

receiving social media data;

identifying at least one SMR related to the AE within the social media data, comprising: analyzing the social media data within a sample window timeframe of the AE time of occurrence;

identifying one or more SMR features of the social media data within the sample window timeframe; and

identifying the SMR having the SMR features that match a predetermined number of the AE features, as the at least one SMR;

determining at least one social media parameter associated with the at least one SMR, wherein the at least one social media parameter comprises at least one of: a total number of the SMRs related to the AE, a sentiment allocation for a plurality of sentiments associated with the SMR related to the AE, a sentiment allocation associated with the SMR, social media sources posting the SMRs related to the AE, and an allocation of a plurality of social media sources providing the SMRs related to the AE;

providing a graphic user interface (GUI) showing a virtual version of a field of play and at least one AE graphic on the virtual field of play, the AE graphic comprising a selectable graphical image indicative of the AE and positioned at a location indicative of real-time spatial coordinates on the virtual field of play corresponding to the location of the AE on the actual field of play and at least one visual aspect of the AE graphic being indicative of the at least one social media parameter associated with the SMR related to the AE, wherein the at least one visual aspect of the AE graphic comprises at least one of: (i) a size of the AE graphic corresponding to the total number of the SMRs related to the AE and (ii) a shading of the AE graphic corresponding to the sentiment allocation associated with the SMR related to the AE or the allocation of the plurality of social media sources providing the SMRs related to the AE; wherein the interface (GUI) also showing an AE timeline and the at least one AE graphic positioned along the AE timeline corresponding to the AE time of occurrence; and

wherein the AE graphic is updated according to the received social media data during the sample window timeframe.

28. The method of claim 27, wherein the determining at least one social media parameter, comprises at least one of: determining an amount of the SMRs related to the AE in the social media data and determining a sentiment of the at least one SMR related to the AE in the social media data. (0)

29. The method of claim 27, wherein the AE graphic has user selectable attributes, comprising at least one of: shape and color. (0)

30. The method of claim 27, wherein the GUI is displayed on a mobile device. (0)

31. The method of claim 27, wherein the SMR features comprises a topic that relates to the sporting event. (0)

35. The method of claim 27 wherein the AE features comprises at least one of: sport, team, players, and action/type, and the SMR features comprises at least one of: topic and attributes. (0)

View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >

Patent US10795560

System and method for detection and visualization of anomalous media events

Patent Matrix® Search