Ordering of digital content based on a content model

• US 10,402,441 B1
• Filed: 03/20/2017
• Issued: 09/03/2019
• Est. Priority Date: 09/27/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Eldawy, Mohamed S.
• Primary Examiner(s): Biagini, Christopher
• Application Number:
  US15/464,255
• Time in Patent Office: 897 Days
• CPC Class Codes: G06F 16/437 Administration of user profiles, e.g. generation, initialisation, adaptation, distribution
• CPC Class Codes: G06F 16/4387 by the use of playlists
• CPC Class Codes: H04L 65/60 Network streaming of media packets
• CPC Class Codes: H04L 65/762 at the source reformatting of additional data in video distribution servers H04N21/2355
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/5681 Pre-fetching or pre-delivering data based on network characteristics

Abstract

A method for updating a content playing model for a media content item includes storing the content playing model for the media content item, the content playing model identifying a first plurality of portions of the media content item and specifying one or more statistical values for each of the first plurality of portions of the media content item, identifying a current play sequence of the media content item, the current play sequence including a second plurality of portions of the media content item, and determining that the second plurality of portions of the media content item includes a subset of portions that is not included in the first plurality of portions of the media content item. The method further includes updating the content playing model to identify a third plurality of portions of the media content item and specify one or more statistical values for each of the third plurality of portions of the media content item, wherein the third plurality of portions includes the first plurality of portions of the media content item and the subset of portions from the second plurality of portions of the media content item.

Claims

1. A method for updating a content playing model for a media content item, the method comprising:

storing the content playing model for the media content item, the content playing model identifying a first plurality of portions of the media content item and specifying one or more statistical values for each of the first plurality of portions of the media content item, wherein a statistical value of a corresponding portion of the first plurality of portions indicates a number of times the corresponding portion of the first plurality of portions was played in previous play sequences that include the corresponding portion;

identifying a current play sequence of the media content item, the current play sequence including a second plurality of portions of the media content item;

determining that the second plurality of portions of the media content item includes a subset of portions that is not included in the first plurality of portions of the media content item;

updating, by a processing device, the content playing model to identify a third plurality of portions of the media content item and specify one or more statistical values for each of the third plurality of portions of the media content item, wherein the third plurality of portions includes the first plurality of portions of the media content item and the subset of portions from the second plurality of portions of the media content item, and wherein a statistical value of a corresponding portion of the third plurality of portions indicates a number of times the corresponding portion of the third plurality of portions was played in the previous play sequences and the current play sequence; and

causing a new sequence for providing portions of the media content item to a user device to be determined based on the updated content playing model.

2. The method of claim 1, wherein the content playing model is one of a histogram model, an order of play model, or a decision tree model.

3. The method of claim 2, wherein the decision tree model comprises a plurality of nodes, each node comprising at least one probability, and wherein identifying the current play sequence for the media content item comprises:

obtaining information associated with a user submitting a request for the media content item;

obtaining a plurality of probabilities associated with one or more nodes in the decision tree model, wherein each probability comprises a characteristic; and

selecting the current play sequence for the media content item based on the plurality of probabilities and the information associated with the user.

4. The method of claim 3, wherein selecting the current play sequence for the media content item based on the plurality of probabilities and the information associated with the user comprises:

determining whether the information associated with the user matches a characteristic associated with a probability; and

upon determining that the information associated with the user matches the characteristic associated with the probability, selecting a portion associated with the probability to include in the current play sequence.

5. The method of claim 3, wherein the information associated with the user comprises at least one of a previous portion of the media content item accessed by the user, a characteristic of the user, a location of the user, and a source that directed the user to the media content item.

6. The method of claim 2, wherein the decision tree model comprises a plurality of nodes, each node comprising at least one probability, and wherein identifying the current play sequence for the media content item comprises:

obtaining a portion of the media content item accessed by a user;

obtaining a plurality of probabilities associated with one or more nodes in the decision tree model based on the portion of the digital content; and

selecting the current play sequence for the media content item based on the plurality of probabilities.

7. The method of claim 2, further comprising generating the content playing model that is a decision tree model comprising a plurality of nodes, wherein updating the content playing model comprises:

for a current portion of the media content item in the current play sequence of the media content item, determining whether a current node in the decision tree model comprises an order value that matches an order value associated with the current portion of the media content item and whether a previous node in the decision tree model that leads to the current node is associated with a previous portion of the media content item in the current play sequence; and

updating the decision tree model based on the determining.

8. The method of claim 7, wherein updating the decision tree model based on the determining comprises:

responsive to determining that the current node in the decision tree model comprises the order value that matches the order value associated with the current portion of the media content item and the previous node in the decision tree model that leads to the current node is associated with the previous portion of the media content item in the current play sequence, updating the current node in the decision tree model;

responsive to determining that the current node in the decision tree model comprises the order value that matches the order value associated with the current portion of the media content item and the previous node in the decision tree model that leads to the current node is not associated with the previous portion of the media content item in the current play sequence, creating a new node in the decision tree model, wherein the new node comprises the order value associated with the current portion of the media content item; and

updating the previous node in the decision tree model.

9. A non-transitory computer readable storage medium having instructions that, when executed by a processing device, cause the processing device to perform operations comprising:

storing a content playing model for a media content item, the content playing model identifying a first plurality of portions of the media content item and specifying one or more statistical values for each of the first plurality of portions of the media content item, wherein a statistical value of a corresponding portion of the first plurality of portions indicates a number of times the corresponding portion of the first plurality of portions was played in previous play sequences that include the corresponding portion;

identifying a current play sequence of the media content item, the current play sequence including a second plurality of portions of the media content item;

determining that the second plurality of portions of the media content item includes a subset of portions that is not included in the first plurality of portions of the media content item;

updating the content playing model to identify a third plurality of portions of the media content item and specify one or more statistical values for each of the third plurality of portions of the media content item, wherein the third plurality of portions includes the first plurality of portions of the media content item and the subset of portions from the second plurality of portions of the media content item, and wherein a statistical value of a corresponding portion of the third plurality of portions indicates a number of times the corresponding portion of the third plurality of portions was played in the previous play sequences and the current play sequence; and

causing a new sequence for providing portions of the media content item to a user device to be determined based on the updated content playing model.

10. The non-transitory computer readable storage medium of claim 9, wherein the content playing model is one of a histogram model, an order of play model, or a decision tree model.

11. The non-transitory computer readable storage medium of claim 10, wherein the decision tree model comprises a plurality of nodes, each node comprising at least one probability, and wherein identifying the current play sequence for the media content item comprises:

obtaining information associated with a user submitting a request for the media content item;

obtaining a plurality of probabilities associated with one or more nodes in the decision tree model, wherein each probability comprises a characteristic; and

selecting the current play sequence for the media content item based on the plurality of probabilities and the information associated with the user.

12. The non-transitory computer readable storage medium of claim 11, wherein selecting the current play sequence for the media content item based on the plurality of probabilities and the information associated with the user comprises:

determining whether the information associated with the user matches a characteristic associated with a probability; and

upon determining that the information associated with the user matches the characteristic associated with the probability, selecting a portion associated with the probability to include in the current play sequence.

13. The non-transitory computer readable storage medium of claim 11, wherein the information associated with the user comprises at least one of a previous portion of the media content item accessed by the user, a characteristic of the user, a location of the user, and a source that directed the user to the media content item.

14. The non-transitory computer readable storage medium of claim 10, wherein the decision tree model comprises a plurality of nodes, each node comprising at least one probability, and wherein identifying the current play sequence for the media content item comprises:

obtaining a portion of the media content item accessed by a user;

obtaining a plurality of probabilities associated with one or more nodes in the decision tree model based on the portion of the digital content; and

selecting the current play sequence for the media content item based on the plurality of probabilities.

15. The non-transitory computer readable storage medium of claim 10, further comprising generating the content playing model that is a decision tree model comprising a plurality of nodes, wherein updating the content playing model comprises:

for a current portion of the media content item in the current play sequence of the media content item, determining whether a current node in the decision tree model comprises an order value that matches an order value associated with the current portion of the media content item and whether a previous node in the decision tree model that leads to the current node is associated with a previous portion of the media content item in the current play sequence; and

updating the decision tree model based on the determining.

16. The non-transitory computer readable storage medium of claim 15, wherein updating the decision tree model based on the determining comprises:

responsive to determining that the current node in the decision tree model comprises the order value that matches the order value associated with the current portion of the media content item and the previous node in the decision tree model that leads to the current node is associated with the previous portion of the media content item in the current play sequence, updating the current node in the decision tree model;

responsive to determining that the current node in the decision tree model comprises the order value that matches the order value associated with the current portion of the media content item and the previous node in the decision tree model that leads to the current node is not associated with the previous portion of the media content item in the current play sequence, creating a new node in the decision tree model, wherein the new node comprises the order value associated with the current portion of the media content item; and

updating the previous node in the decision tree model.

17. A computing device comprising:

a memory; and

a processing device, coupled to the memory, to;

store the content playing model for the media content item, the content playing model identifying a first plurality of portions of the media content item and specifying one or more statistical values for each of the first plurality of portions of the media content item, wherein a statistical value of a corresponding portion of the first plurality of portions indicates a number of times the corresponding portion of the first plurality of portions was played in previous play sequences that include the corresponding portion;

identify a current play sequence of the media content item, the current play sequence including a second plurality of portions of the media content item;

determine that the second plurality of portions of the media content item includes a subset of portions that is not included in the first plurality of portions of the media content item;

update the content playing model to identify a third plurality of portions of the media content item and specify one or more statistical values for each of the third plurality of portions of the media content item, wherein the third plurality of portions includes the first plurality of portions of the media content item and the subset of portions from the second plurality of portions of the media content item, and wherein a statistical value of a corresponding portion of the third plurality of portions indicates a number of times the corresponding portion of the third plurality of portions was played in the previous play sequences and the current play sequence; and

cause a new sequence for providing portions of the media content item to a user device to be determined based on the updated content playing model.

18. The computing device of claim 17, wherein the content playing model is one of a histogram model, an order of play model, or a decision tree model.

19. The computing device of claim 18, wherein the decision tree model comprises a plurality of nodes, each node comprising at least one probability, and wherein to identify the current play sequence for the media content item, the processing device is to:

obtain information associated with a user submitting a request for the media content item;

obtain a plurality of probabilities associated with one or more nodes in the decision tree model, wherein each probability comprises a characteristic; and

select the current play sequence for the media content item based on the plurality of probabilities and the information associated with the user.

20. The computing device of claim 19, wherein to select the current play sequence for the media content item based on the plurality of probabilities and the information associated with the user, the processing device is to:

determine whether the information associated with the user matches a characteristic associated with a probability; and

upon determining that the information associated with the user matches the characteristic associated with the probability, select a portion associated with the probability to include in the current play sequence.

21. The computing device of claim 19, wherein the information associated with the user comprises at least one of a previous portion of the media content item accessed by the user, a characteristic of the user, a location of the user, and a source that directed the user to the media content item.