Recommending contents using a base profile

• US 10,025,863 B2
• Filed: 10/31/2014
• Issued: 07/17/2018
• Est. Priority Date: 10/31/2014
• Status: Active Grant

• Current Assignee: Yahoo Assets LLC
• Original Assignee: Oath Inc. (Verizon Communications Inc.)
• Inventors: Vasudevan, Sudharsan, Gandhi, Herat, Inturi, Mahesh, Narasimhadevara, Chinmayi, Ailawadi, Sumit
• Primary Examiner(s): Mackes, Kris E
• Assistant Examiner(s): Bui, Thuy T
• Application Number:
  US14/529,415
• Publication Number:
  US 20160125085A1
• Time in Patent Office: 1,355 Days
• Field of Search: 707734
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

A method and system for recommending content to a user whose interest(s) has not been identified is disclosed. A base user profile may be created for association with the user. The base user profile may be created by generating a list of ranked interests of a set of representative users. The list of ranked interests may be generated based on activity information obtained for the set of representative users. Content may be recommended to the user based on the base user profile.

Claims

1. A method for recommending content to a user, the method implemented on a computing device having at least one processor, storage, and a communication interface connected to a network, the method comprising:

determining that interest information does not exist, wherein the interest information identifies one or more interests of the user;

creating a base user profile for the user, the base user profile including information indicating one or more ranked interests of a set of representative users within a time period, wherein creating the base user profile comprises;

selecting the set of representative users based on two or more selection criteria, wherein the two or more selection criteria for selecting the set of representative users includes a threshold of frequency of log-in by the representative users and at least one of predetermined demographics of the representative users or one or more predetermined activities engaged in by the representative users in the selected set;

obtaining activity information of the selected set of representative users, the activity information indicating activities engaged by the set of representative users within the time period; and

analyzing the obtained activity information of the selected set of representative users to determine the one or more ranked interests of the set of representative users within the time period, wherein analyzing the obtained activity information of the selected set of representative users to determine the one or more ranked interests comprises;

extracting individual user activities from the activity information for the individual ones of the representative users in the set;

weighting the extracted individual user activities based on one or more predetermined factors;

aggregating the weighted individual user activities; and

determining the one or more ranked interests based on the aggregated user activities; and

recommending content to the user based on the obtained base user profile.

2. The method of claim 1, wherein analyzing the obtained activity information further comprises categorizing the extracted individual user activities by activity type, activity topic, one or more phrases associated with activity, and/or content viewed during activity, and wherein weighting the extracted individual user activities comprises determining a score for the individual categories of the activities.

3. The method of claim 2, wherein the predetermined factors include a number of times the individual categories of activities occurred, a total or average time period in which the representative users in the selected set engaged in the corresponding individual categories of activities, and an biased score based on the individual ones of the representative users in the selected set that engaged in the corresponding individual categories of activities.

4. The method of claim 1, wherein the activities indicated by the obtained activity information include browsing activities, Email activities, and/or social media activities.

5. The method of claim 1, wherein recommending content to the user based on the obtained base user profile comprises:

extracting one or more interests from the ranked interests indicated by the information included in the base user profile;

obtain a set of candidate content;

analyzing the candidate content based on the one or more interests extracted; and

selecting content for recommendation based on the result of the analysis.

6. The method of claim 1, wherein creating the base user profile further comprising selecting a number of ranked interests for inclusion in the base user profile based on the associated ranks.

7. A system for recommending content to a user, the system comprising:

storage;

a communication interface connected to a network; and

one or more processors programmed to execute one or more computer program instructions that, when executed, cause the one or more processors to;

determine that interest information does not exist, wherein the interest information identifies one or more interests of the user;

create a base user profile for the user, the base user profile including information indicating one or more ranked interests of a set of representative users within a time period, wherein creating the base user profile comprises;

selecting the set of representative users based on two or more selection criteria, wherein the two or more selection criteria for selecting the set of representative users includes a threshold of frequency of log-in by the representative users and at least one of predetermined demographics of the representative users or one or more predetermined activities engaged in by the representative users in the selected set;

obtaining activity information of the selected set of representative users, the activity information indicating activities engaged by the set of representative users within the time period; and

analyzing the obtained activity information of the selected set of representative users to determine the one or more ranked interests of the set of representative users within the time period, wherein analyzing the obtained activity information of the selected set of representative users to determine the one or more ranked interests comprises;

extracting individual user activities from the activity information for the individual ones of the representative users in the set;

weighting the extracted individual user activities based on one or more predetermined factors;

aggregating the weighted individual user activities; and

determining the one or more ranked interests based on the aggregated user activities; and

recommend content to the user based on the obtained base user profile.

8. The system of claim 7, wherein analyzing the obtained activity information further comprises categorizing the extracted individual user activities by activity type, activity topic, one or more phrases associated with activity, and/or content viewed during activity, and wherein weighting the extracted individual user activities comprises determining a score for the individual categories of the activities.

9. The system of claim 7, wherein the predetermined factors include a number of times the individual categories of activities occurred, a total or average time period in which the representative users in the selected set engaged in the corresponding individual categories of activities, and an biased score based on the individual ones of the representative users in the selected set that engaged in the corresponding individual categories of activities.

10. The system of claim 7, wherein the activities indicated by the obtained activity information include browsing activities, Email activities, and/or social media activities.

11. The system of claim 7, wherein the one or more processors are caused to:

extract one or more interests from the ranked interests indicated by the information included in the base user profile;

obtain a set of candidate content;

analyze the candidate content based on the one or more interests extracted; and

select content for recommendation based on the result of the analysis.

12. The system of claim 7, wherein the one or more processors are caused to select a number of ranked interests for inclusion in the base user profile based on the associated ranks of the ranked interests.

13. A non-transitory computer readable medium having recorded thereon information for recommending content to a user wherein the information, when read by a computer, causes the computer to perform the steps of:

determining that interest information does not exist, wherein the interest information identifies one or more interests of the user;

creating a base user profile for the user, the base user profile including information indicating one or more ranked interests of a set of representative users within a time period, wherein creating the base user profile comprises;

selecting the set of representative users based on ee two or more selection criteria, wherein the two or more selection criteria for selecting the set of representative users includes a threshold of frequency of log-in by the representative users and at least one of predetermined demographics of the representative users or one or more predetermined activities engaged in by the representative users in the selected set;

obtaining activity information of the selected set of representative users, the activity information indicating activities engaged by the set of representative users within the time period; and

analyzing the obtained activity information of the selected set of representative users to determine the one or more ranked interests of the set of representative users within the time period, wherein analyzing the obtained activity information of the selected set of representative users to determine the one or more ranked interests comprises;

extracting individual user activities from the activity information for the individual ones of the representative users in the set;

weighting the extracted individual user activities based on one or more predetermined factors;

aggregating the weighted individual user activities; and

determining the one or more ranked interests based on the aggregated user activities; and

recommending content to the user based on the obtained base user profile.

14. The non-transitory medium of claim 13, wherein analyzing the obtained activity information further comprises categorizing the extracted individual user activities by activity type, activity topic, one or more phrases associated with activity, and/or content viewed during activity, and wherein weighting the extracted individual user activities comprises determining a score for the individual categories of the activities.

15. The non-transitory medium of claim 13, wherein the predetermined factors include a number of times the individual categories of activities occurred, a total or average time period in which the representative users in the selected set engaged in the corresponding individual categories of activities, and an biased score based on the individual ones of the representative users in the selected set that engaged in the corresponding individual categories of activities.