METHOD AND SYSTEM FOR USER PROFILING FOR CONTENT RECOMMENDATION

• US 20170255862A1
• Filed: 03/01/2016
• Published: 09/07/2017
• Est. Priority Date: 03/01/2016
• Status: Active Grant

• Current Assignee: Verizon Media, Inc. (Verizon Communications Inc.), Yahoo Assets LLC
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Li, Xiang, Lee, Sungjin, Pappu, Aasish, Hu, Yifan, Stent, Amanda
• Granted Patent: US 11,188,830 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/9035 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 30/0631 Item recommendations
• 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 67/306 User profiles

Abstract

The present teaching relates to generating user profiles with semantic knowledge. A first information associated with a user is obtained. One or more entities are identified from the first information. The one or more entities are augmented based on second information to generate a set of augmented entities. The set of augmented entities are clustered into a set of hierarchical clusters. A set of user profiles is generated based on the set of hierarchical clusters so that the user profile is to be used to personalize content recommendation.

Claims

1. A method implemented on a computing device having at least one processor, storage, and a communication platform connected to a network for generating user profiles with semantic knowledge, the method comprising:

obtaining first information associated with a user;

identifying one or more entities from the first information;

augmenting the one or more entities based on second information to generate a set of augmented entities;

clustering the set of augmented entities into a set of hierarchical clusters; and

generating a set of user profiles based on the set of hierarchical clusters so that the user profile is to be used to personalize content recommendation.

2. The method of claim 1, further comprising:

identifying at least one related entity from the second information that relates to the one or more entities; and

adding the at least one related entity to the one or more entities to generate the set of augmented entities,

wherein the second information comprises a knowledge archive of named entities.

3. The method of claim 2, further comprising:

estimating user interests with respect to the set of augmented entities; and

incorporating the user interests with respect to the set of augmented entities into the user profile.

4. The method of claim 3, wherein estimating user interests with respect to the set of augmented entities further comprises:

identifying known user interests with respect to the one or more entities based on semantic relationships between the one or more entities;

estimating inferred user interests with respect to the at least one related entity based on semantic relationships between the at least one related entity and the one or more entities; and

estimating strength of the user interests with respect to the set of augmented entities in accordance with the inferred user interests.

5. The method of claim 4, further comprising:

applying a latent factor model to estimate the user interest, wherein the latent factor model is trained using user interaction data.

6. The method of claim 1, wherein all aspects of user interests are organized in a hierarchical structure to form the set of user profiles and each of the set of user profiles defines an aspect of user interests.

7. A system having at least one processor, storage, and a communication platform for generating user profiles with semantic knowledge, the system comprising:

a user activity analyzer configured to obtain first information associated with a user;

an entity extractor configured to identify one or more entities from the first information;

an entity augmenting module configured to augment the one or more entities based on second information to generate a set of augmented entities;

an entity clustering module configured to cluster the set of augmented entities into a set of hierarchical clusters; and

a user profile generating module configured to generate a set of user profiles based on the set of hierarchical clusters so that the set of user profiles is to be used to personalize content recommendation.

8. The system of claim 7, wherein the entity augmenting module is further configured to:

identify at least one related entity from the second information that relates to the one or more entities; and

add the at least one related entity to the one or more entities to generate the set of augmented entities,

wherein the second information includes semantic knowledge associated with the set of augmented entities.

9. The system of claim 8, further comprises a user interest estimating module configured to:

estimate user interests with respect to the set of augmented entities; and

incorporate the user interests with respect to the set of augmented entities into the user profile.

10. The system of claim 9, wherein the user interest estimating module configured to:

identify known user interests with respect to the one or more entities based on relationships between the one or more entities;

estimate inferred user interests with respect to the at least one related entity based on relationships between the at least one related entity and the one or more entities; and

estimate strength of the user interests with respect to the set of augmented entities in accordance with the inferred user interest.

11. The system of claim 7, wherein each of the set of hierarchical clusters defines a hierarchical relationship among at least part of the set of augmented entities.

12. The system of claim 7, wherein all aspects of user interests are organized in a hierarchical structure to form a user profile, and each of the set of user profiles defines an aspect of user interests.

13. A non-transitory machine-readable medium having information recorded thereon for generating user profiles with semantic knowledge, wherein the information, when read by the machine, causes the machine to perform the following:

obtaining first information associated with a user;

identifying one or more entities from the first information;

augmenting the one or more entities based on second information to generate a set of augmented entities;

clustering the set of augmented entities into a set of hierarchical clusters; and

generating a set of user profiles based on the set of hierarchical clusters so that the set of user profiles is to be used to personalize content recommendation.

14. The medium of claim 13, wherein the information, when read by the machine, causes the machine to further perform the following:

identifying at least one related entity from the second information that relates to the one or more entities; and

adding the at least one related entity to the one or more entities to generate the set of augmented entities,

wherein the second information includes semantic knowledge associated with the set of augmented entities.

15. The medium of claim 14, wherein the information, when read by the machine, causes the machine to further perform the following:

estimating user interests with respect to the set of augmented entities; and

incorporating the user interests with respect to the set of augmented entities into the user profile.

16. The medium of claim 15, wherein the information, when read by the machine, causes the machine to further perform the following:

identifying known user interests with respect to the one or more entities based on relationships between the one or more entities;

estimating inferred user interests with respect to the at least one related entity based on relationships between the at least one related entity and the one or more entities; and

estimating strength of the user interests with respect to the set of augmented entities in accordance with the inferred user interest.

17. The medium of claim 13, wherein each of the set of hierarchical clusters defines a hierarchical relationship among at least part of the set of augmented entities.

18. The medium of claim 13, wherein all aspects of user interests are organized in a hierarchical structure to form the set of user profiles, and each of the set of user profiles defines an aspect of user interests.

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

receiving an input from a user;

generating a set of user profiles based on information associated with the user and a knowledge archive;

augmenting the set of user profiles based on a set of pre-constructed user profiles; and

recommending content to the user in response to the input based on the set of augmented user profiles,

wherein each of the set of user profiles defines an aspect of user interests with respect to a plurality of entities.

20. The method of claim 19, wherein generating a set of user profiles based on information associated with the user and a knowledge archive further comprises:

obtaining first information associated with the user;

identifying one or more entities from the first information;

augmenting the one or more entities based on the knowledge archive to generate a set of augmented entities;

clustering the set of augmented entities into a set of hierarchical clusters; and

generating the set of user profiles based on the set of hierarchical clusters.