Personalized user-categorized recommendations

• US 10,635,733 B2
• Filed: 06/20/2017
• Issued: 04/28/2020
• Est. Priority Date: 05/05/2017
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Sun, Yanfeng, Michelis, Alexandre Bernard Raymond, Sacheti, Arun Kumar, Lin, Emily, Hirano, Ryuichi, Leung, Vincent Kin-Wah
• Primary Examiner(s): Wilson, Kimberly L
• Application Number:
  US15/627,963
• Publication Number:
  US 20180322206A1
• Time in Patent Office: 1,043 Days
• Field of Search: 707732
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence
• CPC Class Codes: G06F 16/9038 Presentation of query results
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Methods and systems for providing targeted recommendations are provided. A user model is generated from user data. Feed candidates are generated based on the user model. The generated feed candidates are ranked on a predetermined scale. At least one targeted recommendation from the ranked feed candidates. The at least one targeted recommendation feed is provided to a user associated with the user data.

Claims

1. A computer-implemented method for providing targeted recommendations, comprising:

receiving profile data input from a plurality of user interfaces, the received profile data indicating a plurality of users'"'"' interests and being representative of topics of interest of the plurality of users;

generating groups of users based on at least one common interest topic within the received user profile data among the plurality of users;

generating a topic specific profile of a user based on that user'"'"'s profile data and at least one of the common interest topics of the user;

generating non-personalized topic feeds based on a search locating content associated with one or more of the common interest topics;

generating personalized topic feed candidates filtered from the generated non-personalized topic feeds based on the user'"'"'s generated topic specific profile;

ranking the generated personalized topic feed candidates based on a closeness of the generated personalized topic feed candidates to the user'"'"'s topics of interest and

displaying one or more of the generated personalized topic feed candidates to the user in an ascending ranked order.

2. The method of claim 1, wherein generating the user topic specific profile comprises generating one or more user vectors from the user profile data.

3. The method of claim 2, wherein the one or more user vectors comprises:

mapping the user profile data to text;

generating one or more bigrams from the text; and

generating the one or more user vectors from the bigrams.

4. The method of claim 2, wherein generating the user topic specific profile comprises generating a self-organizing map comprising the one or more user vectors.

5. The method of claim 4, further comprising dynamically updating the self-organizing map.

6. The method of claim 5, wherein updating the self-organizing map comprises including at least one new user vector into the self-organizing map, the at least one new user vector corresponding to a new interest associated with the user.

7. The method of claim 1, further comprising ranking the personalized topic feed candidates on a predetermined scale.

8. The method of claim 1, wherein the user profile data comprises a user category created by a user.

9. The method of claim 8, further comprising discontinuing displaying the one or more of the generated personalized topic feed candidates upon deletion of the user category.

10. A system for providing targeted recommendations, the system comprising:

at least one processing device; and

at least one computer readable data storage medium storing instructions that, when executed by the at least one processing device, cause the at least one processing device to;

receive profile data input from a plurality of user interfaces, the received profile data indicating a plurality of users'"'"' interests and being representative of topics of interest of the plurality of users;

generate groups of users based on at least one common interest topic within the received user profile data among the plurality of users;

generate a topic specific profile of a user based on that user'"'"'s profile data and at least one of the common interest topics of the user;

generate non-personalized topic feeds based on a search locating content associated with one or more of the common interest topics;

generate personalized topic feed candidates filtered from the generated non-personalized topic feeds based on the user'"'"'s generated topic specific profile;

rank the generated personalized topic feed candidates based on a closeness of the generated personalized topic feed candidates to the user'"'"'s topics of interest; and

displaying one or more of the generated personalized topic feed candidates to the user in an ascending ranked order.

11. The system of claim 10, wherein instructions that, when the instructions executed by the at least one processing device, cause the at least one processing device to:

rank the generated personalized topic feed candidates on a predetermined scale; and

determine the one or more generated personalized topic feed candidates to be displayed based on the rank.

12. The system of claim 10, wherein the instructions when executed by the at least one processing device cause the at least one processing device to:

generate a task specific profile of the user;

generate a non-personalized topic feed based on the task specific profile; and

generate the personalized topic feed candidates from the non-personalized topic feed based on the user task specific profile.

13. The system of claim 12, wherein the instructions when executed by the at least one processing device cause the at least one processing device to:

map a user task from the user profile data to the task specific profile.

14. The system of claim 10, wherein the instructions when executed by the at least one processing device cause the at least one processing device to:

map the user data to text;

generate one or more bigrams for the text; and

generate the user topic specific profile from the bigrams, the user topic specific profile comprising one or more vectors generated from the one or more bigrams.

15. Computer readable storage media including computer readable instructions, which when executed by a processing unit is operative to:

receive profile data input from a plurality of user interfaces, the received profile data indicating a plurality of users'"'"' interests and being representative of topics of interest of the plurality of users;

generate groups of users based on at least one common interest topic within the received user profile data among the plurality of users;

generate a topic specific profile of a user based on that user'"'"'s profile data and at least one of the common interest topics of the user;

generate non-personalized topic feeds based on a search locating content associated with one or more of the common interest topics;

generate personalized topic feed candidates filtered from the generated non-personalized topic feeds based on the user'"'"'s generated topic specific profile;

rank the generated personalized topic feed candidates based on a closeness of the generated personalized topic feed candidates to the user'"'"'s topics of interest; and

displaying one or more of the generated personalized topic feed candidates to the user in an ascending ranked order.

16. The computer readable storage media of claim 15, wherein the computer readable instructions when executed by the processing unit is further operative to:

generate a user group comprising a plurality of users associated with a topic;

generate a topic specific profile;

generate a non-personalized topic feed; and

generate the personalized topic feed candidates for the user from the non-personalized topic feeds.

17. The computer readable storage media of claim 16, wherein the computer readable instructions when executed by the processing unit is further operative to:

map the user into the user group.

18. The computer readable storage media of claim 16, wherein the computer readable instructions when executed by the processing unit is further operative to:

discontinue displaying the one or more of the generated personalized topic feed candidates upon deletion of a user category from the user profile data.

19. The computer readable storage media of claim 15, wherein the computer readable instructions when executed by the processing unit is further operative to:

create a self-organizing map comprising the user'"'"'s topic specific profile.

20. The computer readable storage media of claim 19, wherein the computer readable instructions when executed by the processing unit is further operative to:

dynamically update the self-organizing map based on a feedback from the user for the provided at least one targeted recommendation.