Device for determining potential future interests to be introduced into profile(s) of user(s) of communication equipment(s)

• US 9,251,525 B2
• Filed: 09/24/2010
• Issued: 02/02/2016
• Est. Priority Date: 10/16/2009
• Status: Active Grant

• Current Assignee: Alcatel-Lucent SA (Nokia Corporation)
• Original Assignee: Alcatel-Lucent SA (Nokia Corporation)
• Inventors: Picault, Jerome, Kostadinov, Dimitre Davidov, Bouzid, Makram
• Primary Examiner(s): Shiferaw, Eleni
• Assistant Examiner(s): GIDDINS, NELSON S
• Application Number:
  US13/502,191
• Publication Number:
  US 20120265816A1
• Time in Patent Office: 1,957 Days
• Field of Search: 709/204, 706 45- 62
• US Class Current: 1/1
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: H04L 67/30 Profiles
• CPC Class Codes: H04L 67/303 Terminal profiles
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04N 21/44213 Monitoring of end-user related data arrangements for monitoring the users' behaviour or opinions in broadcast systems H04H60/33
• CPC Class Codes: H04N 21/466 Learning process for intelligent management, e.g. learning user preferences for recommending movies services using the results of monitoring in broadcast systems H04H60/61

Abstract

A device (D) is intended for determining potential interests of users (U1-U3) that are clients of at least one network operator, each user being associated to a profile defining at least his interests. This device (D) comprises i) a tracking means (TM) arranged for analyzing the profile of at least one user (U1) to determine new real interest(s) it contains and for storing an identifier representative of a determined new real interest of this user (U1) in correspondence with a first date at which it has been considered as a new real interest into his profile, and ii) a recommendation means (RM) arranged for analyzing the first dates of a user (U1) to determine a time ordered sequence of interests preceding a determined new real interest, and for comparing this determined user interest sequence to at least one other sequence of interests of at least one other user (U2) to predict at least one potential future interest for this user (U1), to be introduced into his profile.

Claims

1. A device for determining potential interests of users that are clients of at least one network operator, the users being associated with profiles defining the interests of the users, the device comprising:

a processor; and

memory storing instructions that, when executed, cause the device to;

analyze at least one profile of at least one user to determine new real interests associated with the at least one profile by determining the consumption of content items of said at least one user that are related to an interest contained in the profile of said at least one user and considering the interest is a new real interest when said determined consumption of the related content items is greater than a chosen threshold;

store an identifier representative of a determined new real interest of said at least one user in correspondence with a first date at which it has been considered as a new real interest into the at least one profile of said at least one user;

analyze one or more first dates of said at least one user to determine a time ordered sequence of interests preceding a determined new real interest; and

compare the determined user interest sequence to at least one other sequence of interests of at least one other user to predict at least one potential future interest for said at least one user, to be introduced into the at least one profile of said at least one user.

2. The device according to claim 1, wherein said memory stores further instructions to compare said determined user interest sequence to at least one other sequence of interests, determined into a graph of interests built from the interests of other users, to predict at least one potential future interest of said at least one user.

3. The device according to claim 2, wherein said memory stores further instructions to build and update said interest graph from the stored real interests of said users.

4. The device according to claim 1, wherein said memory stores further instructions to build and update an interest graph which models the evolution of interests over time for a plurality of users.

5. The device according to claim 1, wherein said memory stores further instructions to build and update an auxiliary interest graph, which models the evolution of interests over time for one user, then aggregates said auxiliary interest graph with auxiliary interest graphs, built for other users, to produce an interest graph.

6. The device according to claim 4, wherein said memory stores further instructions to build and update a directed and weighted interest graph G(V, W), where V is a set of nodes representing respectively said user interests, and W is a set of directed edges representing a transition from a user interest to another user interest.

7. The device according to claim 6, wherein said memory stores further instructions to assign a weight to said directed edges, the weights being defined by a table establishing a correspondence between the users and an elapsed time between the appearances of first and second consecutive real interests.

8. The device according to claim 4, wherein said memory stores further instructions to update said interest graph when said device has determined a new real interest of a user.

9. The device according to claim 6, wherein said memory stores further instructions to determine at least one statistical metric from said weights assigned to said directed edges and for using each determined statistical metric with heuristics to suggest interests adapted to a chosen applicative context and then to predict at least one potential future interest for said user from said suggested interests.

10. The device according to claim 9, wherein at least one statistical metric is representative of the relevance between two interests.

11. The device according to claim 9, wherein at least one statistical metric is representative of the frequency of a transition between two interests.

12. The device according to claim 1, wherein said memory stores further instructions to consider that the first date of an interest is the date at which the device detects that a content item consumption related to said interest is greater than said chosen threshold.

13. The device according to claim 1, wherein said memory stores further instructions to determine a favorable date for introducing said potential future interest into the profile of said user.

14. The device according to claim 1, wherein said memory stores further instructions to store a second date in correspondence with an interest identifier, a user identifier and a first date when the interest strength of a user interest is smaller than the chosen threshold and the user interest is not a real interest for the user.

15. Network equipment for at least one communication network, said network equipment comprising a device according to claim 1 and configured to work in a centralized manner to predict potential future interests for a plurality of users.

16. Communication equipment for a user that is connected to at least one communication network, wherein said communication equipment comprises a device according to claim 1 and is configured to predict potential future interests for said user.

17. A method of determining potential interests of users that are clients of at least one network operator, the users being associated with profiles defining the interests of the users, the method comprising:

analyzing at least one profile of at least one user to determine new real interests associated with the at least one profile by determining the consumption of content items of said at least one user that are related to an interest contained in the profile of said at least one user and considering the interest is a new real interest when said determined consumption of the related content items is greater than a chosen threshold;

storing an identifier representative of a determined new real interest of said at least one user in correspondence with a first date at which it has been considered as a new real interest into the at least one profile of said at least one user;

analyzing one or more first dates of said at least one user to determine a time ordered sequence of interests preceding a determined new real interest; and

comparing the determined user interest sequence to at least one other sequence of interests of at least one other user to predict at least one potential future interest for said at least one user, to be introduced into the at least one profile of said at least one user.

18. The method according to claim 17, further comprising comparing said determined user interest sequence to at least one other sequence of interests, determined into a graph of interests built from the interests of other users, to predict at least one potential future interest of said at least one user.

19. The method according to claim 17, further comprising building and updating said interest graph from the stored real interests of said users.

20. The method according to claim 17, further comprising building and updating an interest graph which models the evolution of interests over time for a plurality of users.