Selecting content for devices specific to a particular user

• US 9,400,871 B1
• Filed: 08/27/2012
• Issued: 07/26/2016
• Est. Priority Date: 08/27/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Hewinson, Philip
• Primary Examiner(s): Abraham, Ahmed
• Application Number:
  US13/595,445
• Time in Patent Office: 1,429 Days
• Field of Search: 707/736, 707/738, 707/740, 707/749, 707/750
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting content for user devices specific to a particular user. The aspects generally relate to providing related content items to a particular user across multiple different user devices, such as mobile devices, tablet computers, desktop computers, and televisions. The selection of the content items for a particular user and the device to which the content items are to be sent are based one or more of the following factors: user history data, subject matter category duration, frequency duration adjustment, behavioral duration adjustment, and device prioritization.

Claims

1. A computer-implemented method performed in a data processing apparatus, comprising:

accessing user history data specifying actions or inactions that are associated with a particular user identifier for a time period, each action or inaction having occurred at a user device associated with the user identifier;

determining, based on the user history data, an origin time specifying a time of occurrence of a given user event, the given user event being a request for content belonging to a particular interest category based on the user history data;

identifying, based at least in part on the user history data and the origin time of the given user event, an interest category duration specifying a bounded period of time of user interest in the particular interest category following the given user event;

receiving, at a particular time during which a user session identified by the user identifier is active, a request to serve a content item with a web page that is related to a different interest category, including receiving a request to serve a content item in a search results page provided in response to a search query that is related to the different interest category;

determining that the particular time is within the bounded period of time of the interest category duration for the particular interest category;

generating a relevance score for a candidate content item that is based, in part, on a difference between the particular time and the origin time of a particular interest category to which the candidate content item belongs, wherein the relevance score for the candidate content item is decreased by a decreased user interest in the particular interest category as the difference between the particular time and the origin time increases;

selecting the content item from the particular interest category rather than the different interest category of the web page based on determining that the particular time is within the bounded period of time of the interest category duration for the particular interest category; and

transmitting, to the user device, data that integrates the selected content item into a the web page that is related to the different interest category.

2. The method of claim 1, wherein at least two user sessions associated with the user identifier are active at the particular time, and wherein the method further comprises:

determining, for each of the user sessions identified by the user identifier and determined to be active at the particular time, a user-specific device at which a corresponding user session is active;

generating a device score for each user-specific device; and

selecting one of the user-specific devices in response to the request based on the device score.

3. The method of claim 2, wherein generating a device score for each user-specific device comprises:

determining a device type of each user-specific device;

generating the device score for each user-specific device based on the device type of the user specific device and the particular time; and

wherein the device score for at least one of the user-specific devices is time dependent and based on the particular time.

4. The method of claim 2, wherein generating the relevance score for the candidate content item comprises generating the relevance score based, in part, on a device type of the selected user-specific device.

5. The method of claim 1, further comprising:

determining, from the user history data, an event frequency from user events for content belonging to the particular interest category; and

adjusting the interest category duration based on the event frequency, wherein the adjustment is inversely proportional to a magnitude of the event frequency.

6. The method of claim 1, further comprising, for the particular interest category:

determining, from the user history data, a behavioral duration from user events for content belonging to the particular interest category; and

windowing the interest category duration based on the behavioral duration, wherein the windowing generates at least two interest category sub-durations that are a proper subset of the interest category duration.

7. A system comprising:

a data processing apparatus; and

a non-transitory computer storage medium encoded with instructions that when executed by the data processing apparatus cause the data processing apparatus to perform operations comprising;

accessing user history data specifying actions or inactions that are associated with a particular user identifier for a time period, each action or inaction having occurred at a user device associated with the user identifier;

determining, based on the user history data, an origin time specifying a time of occurrence of a given user event, the given user event being a request for content belonging to a particular interest category based on the user history data;

identifying, based at least in part on the user history data and the origin time of the given user event, an interest category duration specifying a bounded period of time of user interest in the particular interest category following the given user event;

receiving, at a particular time during which a user session identified by the user identifier is active, a request to serve a content item with a web page that is related to a different interest category, including receiving a request to serve a content item in a search results page provided in response to a search query that is related to the different interest category;

determining that the particular time is within the bounded period of time of the interest category duration for the particular interest category;

generating a relevance score for a candidate content item that is based, in part, on a difference between the particular time and the origin time of a particular interest category to which the candidate content item belongs, wherein the relevance score for the candidate content item is decreased by a decreased user interest in the particular interest category as the difference between the particular time and the origin time increases;

selecting the content item from the particular interest category rather than the different interest category of the web page based on determining that the particular time is within the bounded period of time of the interest category duration for the particular interest category; and

transmitting, to the user device, data that integrates the selected content item into a the web page that is related to the different interest category.

8. The system of claim 7, wherein at least two user sessions associated with the user identifier are active at the particular time, and wherein the instructions cause the data processing apparatus to perform operations further comprising:

determining, for each of the user sessions identified by the user identifier and determined to be active at the particular time, a user-specific device at which a corresponding user session is active;

generating a device score for each user-specific device; and

selecting one of the user-specific devices in response to the request based on the device score.

9. The system of claim 8, wherein generating a device score for each user-specific device comprises:

determining a device type of each user-specific device;

generating the device score for each user-specific device based on the device type of the user specific device and the particular time; and

wherein the device score for at least one of the user-specific devices is time dependent and based on the particular time.

10. The system of claim 8, wherein generating the relevance score for the candidate content item comprises generating the relevance score based, in part, on a device type of the selected user-specific device.

16. The system of claim 7, wherein the instructions cause the data processing apparatus to perform operations further comprising:

determining, from the user history data, an event frequency from user events for content belonging to the particular interest category; and

adjusting the interest category duration based on the event frequency, wherein the adjustment is inversely proportional to a magnitude of the event frequency.

17. The system of claim 7, wherein the instructions cause the data processing apparatus to perform operations further comprising, for the particular interest category:

determining, from the user history data, a behavioral duration from user events for content belonging to the particular interest category; and

windowing the interest category duration based on the behavioral duration, wherein the windowing generates at least two interest category sub-durations that are a proper subset of the interest category duration.

11. A non-transitory computer storage medium encoded with instructions that when executed by data processing apparatus cause the data processing apparatus to perform operations comprising:

accessing user history data specifying actions or inactions that are associated with a particular user identifier for a time period, each action or inaction having occurred at a user device associated with the user identifier;

determining, based on the user history data, an origin time specifying a time of occurrence of a given user event, the given user event being a request for content belonging to a particular interest category based on the user history data;

identifying, based at least in part on the user history data and the origin time of the given user event, an interest category duration specifying a bounded period of time of user interest in the particular interest category following the given user event;

receiving, at a particular time during which a user session identified by the user identifier is active, a request to serve a content item with a web page that is related to a different interest category, including receiving a request to serve a content item in a search results page provided in response to a search query that is related to the different interest category;

determining that the particular time is within the bounded period of time of the interest category duration for the particular interest category;

generating a relevance score for a candidate content item that is based, in part, on a difference between the particular time and the origin time of a particular interest category to which the candidate content item belongs, wherein the relevance score for the candidate content item is decreased by a decreased user interest in the particular interest category as the difference between the particular time and the origin time increases;

selecting the content item from the particular interest category rather than the different interest category based on determining that the particular time is within the bounded period of time of the interest category duration for the particular interest category; and

transmitting, to the user device, data that integrates the selected content item into a the web page that is related to the different interest category.

12. The computer storage medium of claim 11, wherein at least two user sessions associated with the user identifier are active at the particular time, and wherein the instructions cause the data processing apparatus to perform operations further comprising:

determining, for each of the user sessions identified by the user identifier and determined to be active at the particular time, a user-specific device at which a corresponding user session is active;

generating a device score for each user-specific device; and

selecting one of the user-specific devices in response to the request based on the device score.

13. The computer storage medium of claim 12, wherein generating a device score for each user-specific device comprises:

determining a device type of each user-specific device;

generating the device score for each user-specific device based on the device type of the user specific device and the particular time; and

wherein the device score for at least one of the user-specific devices is time dependent and based on the particular time.

14. The computer storage medium of claim 12, wherein generating the relevance score for the candidate content item comprises generating the relevance score based, in part, on a device type of the selected user-specific device.

15. The computer storage medium of claim 11, wherein the instructions cause the data processing apparatus to perform operations further comprising:

determining, from the user history data, an event frequency from user events for content belonging to the particular interest category; and

adjusting the interest category duration based on the event frequency, wherein the adjustment is inversely proportional to a magnitude of the event frequency.