Methods and systems for determining user engagement based on user interactions during different time intervals

• US 10,341,725 B2
• Filed: 12/27/2016
• Issued: 07/02/2019
• Est. Priority Date: 12/27/2016
• Status: Active Grant

• Current Assignee: Rovi Guides, Inc. (Adeia Inc.)
• Original Assignee: Rovi Guides, Inc. (Adeia Inc.)
• Inventors: Maughan, Benjamin H., Stathacopoulos, Paul, Matthews, Sean
• Primary Examiner(s): Kumar, Pankaj
• Assistant Examiner(s): Hicks, Charles N
• Application Number:
  US15/391,548
• Publication Number:
  US 20180184165A1
• Time in Patent Office: 917 Days
• Field of Search: None
• CPC Class Codes: G06F 16/7867 using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
• CPC Class Codes: H04N 21/25883 being end-user demographical data, e.g. age, family status or address arrangements for identifying locations of users in broadcast systems H04H60/52
• 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 21/44218 Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program methods or arrangements for recognising human body or animal bodies or body parts G06V40/10; methods or arrangements for acquiring or recognising human faces, facial parts, facial sketches, facial expressions G06V40/16; methods or arrangements for recognising movements or behaviour G06V40/20; arrangements for identifying users in broadcast systems H04H60/45
• CPC Class Codes: H04N 21/44226 on social networks

Abstract

Systems and methods are described herein for determining a level of user engagement based on user interactions. A media guidance application is configured to retrieve a first record of a first plurality of user inputs, including input type, received during consumption of a media asset. A second time interval, prior to the first time interval, is selected by shifting the first start time and the first end time. A second record of a second plurality of user inputs received during the second time interval, including input type, is retrieved. A first media asset consumed during the first time interval and a second media asset consumed during the second time interval are determined, and the level of user engagement for the first media asset is determined based on the first record and the second record.

Claims

1. A method for determining a level of user engagement based on user interactions, the method comprising:

receiving a first media asset for consumption;

selecting a first time interval based on a first start time and a first end time;

retrieving a first record of a first plurality of user inputs received during the first time interval, wherein the first record indicates an input type for each of the first plurality of user inputs;

selecting a second time interval, prior to the first time interval, by shifting the first start time and the first end time to determine a second start time and a second end time for the second time interval;

retrieving a second record of a second plurality of user inputs received during the second time interval, wherein the second record indicates an input type for each of the second plurality of user inputs;

determining a first frequency of each input type of the first plurality of user inputs during the first time interval;

determining a second frequency of each input type of the second plurality of user inputs during the second time interval;

generating a first metric that describes the first frequency of each input type of the first plurality of user inputs during the first time interval;

generating a second metric that describes the second frequency of each input type of the second plurality of user inputs during the second time interval;

determining that the first media asset is consumed during the first time interval and a second media asset is consumed during the second time interval;

tagging the first media asset with the first metric and the second media asset with the second metric;

determining the level of user engagement for the first media asset based on the tagging by;

comparing the first frequency of each input type in the first plurality of user inputs with a corresponding second frequency of each input type in the second plurality of user inputs;

calculating respective percent differences between the first frequency of each input type in the first plurality of user inputs and the corresponding second frequency in the second plurality of user inputs; and

determining the level of user engagement for the first media asset based on the respective percent differences;

selecting a portion of media to insert into the first media asset based on the level of user engagement for the first media asset; and

inserting the selected portion of media into the first media asset.

2. The method of claim 1, further comprising:

receiving, from a user, the first plurality of user inputs, wherein each user input in the first plurality of user inputs comprises an identification code;

transmitting, to a database, a plurality of queries requesting an input type for each input in the first plurality of user inputs, wherein each query in the plurality of queries includes a respective identification code for each input in the first plurality of user inputs;

receiving, from the database, a respective input type for each input in the first plurality of user inputs; and

storing, for each input in the first plurality of user inputs, an associated input type.

3. The method of claim 1, wherein determining the first frequency of each input type of the first plurality of user inputs during the first time interval comprises:

identifying, for the first plurality of user inputs, a plurality of different input types;

iterating, for each input type in the plurality of different input types, through the first plurality of user inputs; and

updating a respective frequency count for each input type in the plurality of different input types when an input of the first plurality of user inputs matches a respective input type.

4. The method of claim 1, wherein generating the first metric that describes the first frequency of each input type of the first plurality of user inputs during the first time interval comprises generating a vector comprising a data structure that includes a plurality of different input types and a corresponding frequency of user inputs for each input type of the plurality of different input types.

5. The method of claim 1, wherein determining the first media asset consumed during the first time interval comprises:

identifying, based on the first record, one or more media assets that a user consumed during the first interval;

determining, based on the first record, respective amounts of time that the user spent consuming each of the one or more media assets; and

determining the first media asset based on the respective amounts of time.

6. The method of claim 1, further comprising:

generating a shifting time by applying a multiplier to the first start time;

determining a third time interval by shifting the first start time and the first end time by the shifting time; and

updating the second metric with a third plurality of user inputs received during the third time interval.

7. The method of claim 1, wherein tagging the first media asset with the first metric comprises:

generating a data structure for storing the first metric, wherein the data structure includes a first field for each input type associated with the first metric and a second field for a frequency corresponding to a respective input type that is associated with the first metric; and

storing with metadata associated with the first media asset a link to the data structure.

8. The method of claim 1, wherein the first plurality of user inputs comprises inputs generated by a first user and the second plurality of user inputs comprises inputs generated by a plurality of users that are similar to the first user.

9. The method of claim 8, further comprising identifying the plurality of users that are similar to the first user based on at least one of demographics and media content preferences.

10. A system for determining a level of user engagement based on user interactions, the system comprising:

memory; and

control circuitry configured to;

receive a first media asset for consumption;

select a first time interval based on a first start time and a first end time;

retrieve a first record of a first plurality of user inputs received during the first time interval, wherein the first record indicates an input type for each of the first plurality of user inputs;

select a second time interval, prior to the first time interval, by shifting the first start time and the first end time to determine a second start time and a second end time for the second time interval;

retrieve a second record of a second plurality of user inputs received during the second time interval, wherein the second record indicates an input type for each of the second plurality of user inputs;

determine a first frequency of each input type of the first plurality of user inputs during the first time interval;

determine a second frequency of each input type of the second plurality of user inputs during the second time interval;

generate a first metric that describes the first frequency of each input type of the first plurality of user inputs during the first time interval;

generate a second metric that describes the second frequency of each input type of the second plurality of user inputs during the second time interval;

determine that the first media asset is consumed during the first time interval and a second media asset is consumed during the second time interval;

tag the first media asset with the first metric and the second media asset with the second metric;

determine the level of user engagement for the first media asset based on the tagging by;

comparing the first frequency of each input type in the first plurality of user inputs with a corresponding second frequency of each input type in the second plurality of user inputs;

calculating respective percent differences between the first frequency of each input type in the first plurality of user inputs and the corresponding second frequency in the second plurality of user inputs; and

determining the level of user engagement for the first media asset based on the respective percent differences;

select a portion of media to insert into the first media asset based on the level of user engagement for the first media asset; and

insert the selected portion of media into the first media asset.

11. The system of claim 10, wherein the control circuitry is further configured to:

receive, from a user, the first plurality of user inputs, wherein each user input in the first plurality of user inputs comprises an identification code;

transmit, to a database, a plurality of queries requesting an input type for each input in the first plurality of user inputs, wherein each query in the plurality of queries includes a respective identification code for each input in the first plurality of user inputs;

receive, from the database, a respective input type for each input in the first plurality of user inputs; and

store, for each input in the first plurality of user inputs, an associated input type.

12. The system of claim 10, wherein the control circuitry is configured, when determining the first frequency of each input type of the first plurality of user inputs during the first time interval, to:

identify, for the first plurality of user inputs, a plurality of different input types;

iterate, for each input type in the plurality of different input types, through the first plurality of user inputs; and

update a respective frequency count for each input type in the plurality of different input types when an input of the first plurality of user inputs matches a respective input type.

13. The system of claim 10, wherein the control circuitry is configured, when generating the first metric that describes the first frequency of each input type of the first plurality of user inputs during the first time interval, to generate a vector comprising a data structure that includes a plurality of different input types and a corresponding frequency of user inputs for each input type of the plurality of different input types.

14. The system of claim 10, wherein the control circuitry is configured, when determining the first media asset consumed during the first time interval, to:

identify, based on the first record, one or more media assets that a user consumed during the first interval;

determine, based on the first record, respective amounts of time that the user spent consuming each of the one or more media assets; and

determine the first media asset based on the respective amounts of time.

15. The system of claim 10, wherein the control circuitry is further configured to:

generate a shifting time by applying a multiplier to the first start time;

determine a third time interval by shifting the first start time and the first end time by the shifting time; and

update the second metric with a third plurality of user inputs received during the third time interval.

16. The system of claim 10, wherein the control circuitry is configured, when tagging the first media asset with the first metric, to:

generate a data structure for storing the first metric, wherein the data structure includes a first field for each input type associated with the first metric and a second field for a frequency corresponding to a respective input type that is associated with the first metric; and

store with metadata associated with the first media asset a link to the data structure.

17. The system of claim 10, wherein the first plurality of user inputs comprises inputs generated by a first user and the second plurality of user inputs comprises inputs generated by a plurality of users that are similar to the first user.

18. The system of claim 17, wherein the control circuitry is further configured to identify the plurality of users that are similar to the first user based on at least one of demographics and media content preferences.