Processing

Please wait...

Settings

Settings

1. WO2017136179 - PATTERN MATCHING FOR CONTENT IN DIGITAL MAGAZINE

Note: Text based on automatic Optical Character Recognition processes. Please use the PDF version for legal matters

What is claimed is:

1. A computer-implement method comprising:

receiving user interaction data over a time interval for a user, the user interaction data comprising a plurality of interaction records and timestamps of the interaction records, the interaction records describing interactions between the user and content items on a plurality of topics provided by a digital magazine server and each timestamp corresponding to an interaction record;

segmenting the time interval into a plurality of time periods based on the user interaction data, each interaction record being associated with a time period based on the corresponding timestamp of the interaction record indicating the interaction occurring within the associated time period; for each time period, determining one or more likely topics of interest for the user for the time period based on an analysis of the user interaction data associated with the time period, the analysis comprising: extracting one or more topics from the interaction records associated with the time period; and

determining one or more likely topics of interest for the time period by aggregating the extracted topics

selecting one or more content items of interest to the user for a current time period of the plurality of time periods based on the determined likely topics of interest associated with the current time period; and

sending the selected one or more content items for display to the user during the current time period.

2. The method of claim 1 , wherein segmenting the time interval into a plurality of time periods comprises:

dividing the time interval into a plurality of fixed length time periods, each time period having a predefined fixed length of duration.

3. The method of claim 1 , wherein segmenting the time interval into a plurality of time periods comprises:

dividing the time interval into a plurality of varying length time periods, each time period having varying length of duration.

4. The method of claim 3, wherein dividing the time interval into a plurality of varying length time periods comprises:

grouping the user interaction data into a plurality of clusters, each cluster having interaction records associated with content items on the plurality of topics, each cluster being defined by a pair of boundaries; and dividing the time interval based on the boundaries of the plurality of clusters.

5. The method of claim 4, wherein dividing the time interval into a plurality of varying length time periods further comprises:

grouping the user interaction data into a plurality of clusters, each cluster having interaction records on content items on a topic of the plurality of topics; identifying the time intervals corresponding to each cluster of the plurality of clusters; and

associating the identified time intervals with the corresponding clusters on a same topic of the plurality of topics.

6. The method of claim 1 , wherein selecting one or more content items of interest to the user for the current time period associated with the time of the request comprises:

selecting a plurality of content items as candidate content items from content items provided by the digital magazine server;

comparing the topics of the selected candidate content items with the likely topics of the interest corresponding to the current time period based on the user interaction data; and

selecting one or more content items from the candidate content items in response to a match between the candidate content items and a topic of the likely topics of the interest.

7. The method of claim 6, wherein selecting one or more content items from the candidate content items comprises:

ranking the selected content items; and

selecting a threshold number of content items as the content items of interest for the user for the current time period based on the ranking.

8. The method of claim 1 , wherein segmenting the time interval into a plurality of time periods further comprises:

receiving historical user interaction data over a predefined period of time, the historical user interaction data indicating a history of user interactions with content items on a plurality of topic over the predefined period of time; and

identifying patterns of the historical user interaction data, an identified pattern of historical user interaction data indicating one or more characteristics of reading habits of the user while interacting with the content items associated with the identified partem.

9. The method of claim 1 , wherein content items of interest are selected responsive to a request by the user.

10. The method of claim 1 , further comprising:

recording user interactions with content items provided by the digital magazine server, each user interaction with a content item including the topic of the content item, a timestamp of the interaction, and a type of the interaction.

11. A non-transitory computer readable storage medium storing computer program instructions that, when executed by a computer processor, cause the computer processor to perform the steps of:

receiving user interaction data over a time interval for a user, the user interaction data comprising a plurality of interaction records and timestamps of the interaction records, the interaction records describing interactions between the user and content items on a plurality of topics provided by a digital magazine server and each timestamp corresponding to an interaction record;

segmenting the time interval into a plurality of time periods based on the user interaction data, each interaction record being associated with a time period based on the corresponding timestamp of the interaction record indicating the interaction occurring within the associated time period; for each time period, determining one or more likely topics of interest for the user for the time period based on an analysis of the user interaction data associated with the time period, the analysis comprising: extracting one or more topics from the interaction records associated with the time period; and

determining one or more likely topics of interest by aggregating the extracted topics to;

selecting one or more content items of interest to the user for a current time period of the plurality of time periods based on the determined likely topics of interest associated with the current time period; and

sending the selected one or more content items for display to the user during the current time period.

12. The non-transitory computer readable storage medium of claim 1 1, wherein segmenting the time interval into a plurality of time periods comprises:

dividing the time interval into a plurality of fixed length time periods, each time period having a predefined fixed length of duration.

13. The non-transitory computer readable storage medium of claim 1 1, wherein segmenting the time interval into a plurality of time periods comprises:

dividing the time interval into a plurality of varying length time periods, each time period having varying length of duration.

14. The non-transitory computer readable storage medium of claim 13, wherein dividing the time interval into a plurality of varying length time periods comprises:

grouping the user interaction data into a plurality of clusters, each cluster having interaction records on content items on the plurality of topics, each cluster being defined by a pair of boundaries; and

dividing the time interval based on the boundaries of the plurality of clusters.

15. The non-transitory computer readable storage medium of claim 14, wherein g the time interval into a plurality of varying length time periods comprises:

grouping the user interaction data into a plurality of clusters, each cluster having interaction records on content items on a topic of the plurality of topics; identifying the time intervals corresponding to each cluster of the plurality of clusters; and

associating the identified time intervals with the corresponding clusters on a same topic of the plurality of topics.

16. The non-transitory computer readable storage medium of claim 1 1, wherein selecting one or more content items of interest to the user for the current time period associated with the time of the request comprises:

selecting a plurality of content items as candidate content items from content items provided by the digital magazine server;

comparing the topics of the selected candidate content items with the likely topics of interest corresponding to the current time period based on the user interaction data; and

selecting one or more content items from the candidate content items in response to a match between the candidate content items and a topic of the likely topics of the interest.

17. The non-transitory computer readable storage medium of claim 16, wherein g one or more content items from the candidate content items comprises:

ranking the selected content items; and

selecting a threshold number of content items as the content items of interest for the user for the current time period based on the ranking.

18. The non-transitory computer readable storage medium of claim 1 1, wherein segmenting the time interval into a plurality of time periods further comprises:

receiving historical user interaction data over a predefined period of time, the historical user interaction data indicating a history of user interactions with content items on a plurality of topic over the predefined period of time; and

identifying patterns of the historical user interaction data, an identified pattern of historical user interaction data indicating one or more characteristics of reading habits of the user while interacting with the content items associated with the identified partem.

19. The non-transitory computer readable storage medium of claim 11 , wherein content items of interest are selected responsive to a request by the user.

20. The non-transitory computer readable storage medium of claim 11 , further comprising computer program instructions that, when executed by the computer processor, cause the processor to perform the steps of recording user interactions with content items provided by the digital magazine server, each user interaction with a content item including the topic of the content item, a timestamp of the interaction, and a type of the interaction.