Method and system for an online performance service with recommendation module

• US 9,050,537 B2
• Filed: 08/16/2013
• Issued: 06/09/2015
• Est. Priority Date: 02/27/2010
• Status: Active Grant

• Current Assignee: STATS LLC (Stats Holdings LLC)
• Original Assignee: Thuuz, Inc.
• Inventors: Packard, Warren Joseph, Lythcott-Haims, Dan, Barcklay, Robert John
• Primary Examiner(s): TORIMIRO, ADETOKUNBO OLUSEGUN
• Application Number:
  US13/969,437
• Publication Number:
  US 20130337920A1
• Time in Patent Office: 662 Days
• Field of Search: 463/1, 463/20, 463/30, 463/42, 463/40, 705/1, 705/11, 705/14, 273/292
• US Class Current: 1/1
• CPC Class Codes: H04N 21/23418 involving operations for analysing video streams, e.g. detecting features or characteristics television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59
• CPC Class Codes: H04N 21/251 Learning process for intelligent management, e.g. learning user preferences for recommending movies details of learning user preferences for the retrieval of video data in a video database G06F16/739; computer systems using learning methods G06N3/08
• CPC Class Codes: H04N 21/25891 being end-user preferences retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/8126 involving additional data, e.g. news, sports, stocks, weather forecasts

Abstract

A method and system to recommend performances based on the performances'"'"' excitement-level as determined from events and characteristics associated with the performance and a subscriber'"'"'s preference is described herein. A subscriber'"'"'s preference influences the performance type and performance characteristics that are exciting to the subscriber. Recommendations for performances can be sent to the subscriber as a link or direct connection to a location of the online performance. Recommendations of a performance preserve the excitement of the performance by not revealing the score, outcome, or any statistics or commentary that would spoil the natural buildup of excitement from watching the live performance. Performance recommendations may include a start-time and end-time for watching only the exciting portions of the performance. Recommended portions of performances can be ranked to fit within a subscriber'"'"'s customizable viewing-time, so that a subscriber can view only the most exciting portions of performances that fit within a limited time-frame.

Claims

1. A method for recommending online media performances, comprising:

at a server computing system, generating time stamps for the online media performances to indicate a series of discrete events related to a respective performance of the online media performances;

generating, at the server computing system, scoring for a portion of the discrete events of one or more of the online media;

generating, at the server computing system, scoring for the one or more online media performances at least based on the scoring of the portion of discrete events;

generating, at the server computing system, a recommendation message for the one or more online media performances in response to the scoring of the portion of discrete events satisfying criteria, the criteria including one or more subscriber preferences; and

sending the recommendation message from the server computing system to a client.

2. The method of claim 1, wherein the one or more subscriber preferences effect whether an online media performance is recommended to the subscriber.

3. The method of claim 1, wherein the one or more subscriber preferences adjusts a weight applied to a performance datum of the performance data, wherein the weight effects the scoring of the one or more online media performances.

4. The method of claim 1, wherein the recommendation message is based at least in part on available viewing time for the online media performance.

5. A method for recommending media performances, comprising:

at a server computing system, generating time stamps for the media performances to indicate a series of discrete events related to a respective performance of the media performances, the media performances are sports activities;

generating, via the server computing system, scoring for a portion of the discrete events of one or more of the media performances;

generating, via the server computing system, scoring for the one or more media performances at least based on the scoring of the portion of discrete events;

generating, at the server computing system, a recommendation message for the one or more media performances, wherein the recommendation message is at least based on the scoring of the portion of discrete events satisfying criteria of the sports activities; and

sending the recommendation message from the server computing system to a client device.

6. The method of claim 5, wherein an interval spacing of the time stamps varies based on the selected sports activity of the group of sports activities.

7. A method for recommending media performances, comprising:

at a server computing system, generating time stamps for the media performances to indicate a series of discrete events related to a respective performance of the media performances;

generating, at the server computing system, scoring for a portion of the discrete events of one or more of the media performances;

generating, at the server computing system, scoring for the one or more media performances at least based on the scoring of the portion of discrete events;

generating, at the server computing system, a recommendation message for the one or more media performances, wherein the recommendation message is at least based on the scoring of the portion of discrete events; and

sending the recommendation message from the server computing system to a client device, wherein the sending of the recommendation message to the client device includes sending a watch-from-time to indicate a time to begin viewing or recording a discrete event of the one or more discrete events related to the recommended online media performance, wherein the watch-from-time proceeds a peak excitement time of the discrete event.

8. The method of claim 7, wherein the sending of the recommendation message includes sending a watch-to-time to indicate a time to stop viewing the one or more discrete events related to the recommended media performance, the watch-to-time to succeed the peak excitement time of the discrete event.

9. The method of claim 8, wherein the scoring of the portion of the discrete events is determined at least based on:

a pacing score, the pacing score determined based on one or more pace values, a closeness score, the closeness score determined based on one or more closeness values, and a novelty score, the novelty score determined based on one or more novelty values.

10. The method of claim 9, wherein a pace value of the one or more pace values is a measure of a tempo or relative rate of change associated with the portion of the discrete events, wherein a closeness value of the one or more closeness values is at least based on a measure of a score margin between two or more scores of the portion of the discrete events, and wherein a novelty value of the one or more novelty values is a measure of uniqueness associated with a portion of the discrete events.

11. A method for recommending one or more online sports presentations of a plurality of online sports presentations to one or more subscribers of an online sports recommendation service, the method comprising:

at a server computing system, generating time stamps for the online sports presentations to indicate a series of discrete events for each respective one of the plurality of online sports presentations;

generating, at the server computing system, scoring for a portion of the discrete events of the plurality of online sports presentations based on game characteristics determined from game data associated with the plurality of online sports presentations;

generating, at the server computing system, scoring for the plurality of online sports presentations at least based on discrete event scores associated with a respective sports presentation of the plurality of online sports presentations;

generating, at the server computing system, generating one or more recommendations for online sports presentations of the plurality of online sports presentations for a subscriber of the one or more subscribers without revealing any statistics or highlights of any recommended performance, wherein the recommendation is at least based on;

the scoring of the portion of discrete events, one or more subscriber preferences, and a watch-from-time, wherein the watch-from-time is based on a peak excitement level associated with one or more of the portions of discrete events; and

sending the one or more recommendations from the server computing system to a client device for the subscriber.

12. The method of claim 11, wherein the game data is statistical data associated with details of the one or more online sports presentations.

13. The method of claim 12, wherein the game data is selected from at least a group consisting of game clock time data, field position data, play type data, player statistic data, and current team score data.

14. The method of claim 13, wherein the game characteristics are at least based on a pacing score, with the pacing score based on one or more pace values, wherein a pace value of the one or more pace values is a measure of a tempo or relative rate of change associated with the portion of the discrete events.

15. The method of claim 13, wherein the game characteristics are at least based on a closeness score, with the closeness score based on one or more closeness values, and wherein a closeness value of the one or more closeness values is a measure of a score margin between two or more scores of the portion of discrete events.

16. The method of claim 13, wherein the game characteristics are at least based on a novelty score, with the novelty score based on one or more novelty values, and wherein a novelty value of the one or more novelty values is a measure of uniqueness associated with an online sports presentation of the one or more online sports presentations.

17. The method of claim 12, wherein the discrete event scores associated with an online sports presentation of the one or more online sports presentations are normalized such that a score of the sports presentation is equal to or less than 100.

18. A recommendation server, comprising:

a communication interface;

a storage device; and

a processor system in communication with the communication interface and the storage device, the processor system generates time stamps for sports presentations to indicate a series of discrete events for each respective one of the sports presentations and generates scoring for at least a portion of the discrete events of the plurality of sports presentations based on game characteristics determined from game data associated with the plurality of sports presentations, the processor system generates one or more recommendations for sports presentations of the plurality of sports presentations wherein the recommendations are at least based on the scoring of the portion of discrete events and one or more subscriber preferences, the processor system sends the one or more recommendations from the recommendation server to a client device associated with the one or more subscriber preferences via the communication interface.

19. The recommendation server of claim 18, wherein:

the processor system generates the one or more recommendations by include a watch-from-time to indicate a time to begin viewing or recording a discrete event of the one or more discrete events related to the sports presentations, wherein the watch-from-time proceeds a peak excitement time of the discrete event.

20. The recommendation server of claim 18, wherein:

wherein the game characteristics are at least based on one or more closeness values, wherein a closeness value of the one or more closeness values is a measure of a score margin between two or more scores of the portion of discrete events.