Granted Patent B2

US 12,393,638 · App. 18/780,685 · Granted Aug 19, 2025

Inventors: Qihong Shao (Clyde Hill, WA); Josh Viktorov (Needham, MA); Doosan Jung (Lakewood, CO); Gurvinder Singh (San Jose, CA); Matthew R. Engle (Plano, TX); David C. White, Jr. (St. Petersburg, FL)

Assignee: CISCO TECHNOLOGY, INC.

G06F16/9535G06F16/906G06N5/022

Abstract

Claims (52)

1. A method comprising:

obtaining user activity of a plurality of users across a plurality of user sessions;

determining a plurality of personas by clustering similar user activity across the plurality of user sessions;

mining a plurality of sequential patterns in a first set of user activity data associated with a first persona of the plurality of personas;

obtaining a current set of user activity data from a current user session of a user among the plurality of users; and

dynamically updating a user interface of a user device of the user based on the first persona for the current user session.

2. The method of claim 1 , further comprising:

determining at least one predictive rule associated with the first persona, the at least one predictive rule comprising an initial activity among the first set of user activity data and at least one subsequent activity in the first set of user activity data;

dynamically determining a user objective for the user based on associating the current set of user activity data with the first persona; and

facilitating the user objective based on the at least one predictive rule associated with the first persona.

3. The method of claim 2 , wherein dynamically updating comprises adjusting the user interface of the user device for the user to facilitate the at least one subsequent activity of the at least one predictive rule after detecting the initial activity.

4. The method of claim 1 , wherein dynamically updating comprises further adjusting the user interface of the user device of the user based on determining the current set of user activity data is associated with a second persona.

5. The method of claim 1 , further comprising tracking which persona among the plurality of personas is associated with a particular user among the plurality of users for each user session among the plurality of user sessions that are associated with the particular user.

6. The method of claim 1 , wherein determining the plurality of personas by clustering similar user activity across the plurality of user sessions comprises:

selecting a number k of personas in the plurality of personas based on a predetermined number of expected personas; and

clustering the user activity across the plurality of user sessions with a k-means clustering algorithm.

7. The method of claim 1 , wherein at least one subsequent activity in the first set of user activity data is within a predetermined time window of initial activity among the first set of user activity data.

8. An apparatus comprising:

a network interface configured to communicate with computing devices in a network; and

a processor coupled to the network interface, the processor configured to perform operations including:

obtaining, via the network interface, user activity of a plurality of users across a plurality of user sessions;

determining a plurality of personas by clustering similar user activity across the plurality of user sessions;

mining a plurality of sequential patterns in a first set of user activity data associated with a first persona of the plurality of personas;

obtaining a current set of user activity data from a current user session of a user among the plurality of users; and

dynamically updating a user interface of a user device of the user based on the first persona for the current user session.

9. The apparatus of claim 8 , wherein the processor is further configured to perform operations including:

determining at least one predictive rule associated with the first persona, the at least one predictive rule comprising an initial activity among the first set of user activity data and at least one subsequent activity in the first set of user activity data;

dynamically determining a user objective for the user based on associating the current set of user activity data with the first persona; and

facilitating the user objective based on the at least one predictive rule associated with the first persona.

10. The apparatus of claim 9 , wherein the processor is configured to perform the dynamically updating by adjusting the user interface of the user device for the user to facilitate the at least one subsequent activity of the at least one predictive rule after detecting the initial activity.

11. The apparatus of claim 8 , wherein the processor is configured to perform the dynamically updating by further adjusting the user interface of the user device of the user based on determining the current set of user activity data is associated with a second persona.

12. The apparatus of claim 8 , wherein the processor is further configured to perform tracking which persona among the plurality of personas is associated with a particular user among the plurality of users for each user session among the plurality of user sessions that are associated with the particular user.

13. The apparatus of claim 8 , wherein the processor is configured to perform determining the plurality of personas by:

selecting a number k of personas in the plurality of personas based on a predetermined number of expected personas; and

clustering the user activity across the plurality of user sessions with a k-means clustering algorithm.

14. The apparatus of claim 8 , wherein at least one subsequent activity in the first set of user activity data is within a predetermined time window of initial activity among the first set of user activity data.

15. One or more non-transitory computer readable storage media encoded with software comprising computer executable instructions that, when the software is executed on a computing device, is operable to cause a processor of the computing device to perform operations including:

obtaining user activity of a plurality of users across a plurality of user sessions;

determining a plurality of personas by clustering similar user activity across the plurality of user sessions;

mining a plurality of sequential patterns in a first set of user activity data associated with a first persona of the plurality of personas;

obtaining a current set of user activity data from a current user session of a user among the plurality of users; and

dynamically updating a user interface of a user device of the user based on the first persona for the current user session.

16. The one or more non-transitory computer readable storage media of claim 15 , wherein the software is further operable to cause the processor to perform:

determining at least one predictive rule associated with the first persona, the at least one predictive rule comprising an initial activity among the first set of user activity data and at least one subsequent activity in the first set of user activity data;

dynamically determining a user objective for the user based on associating the current set of user activity data with the first persona; and

facilitating the user objective based on the at least one predictive rule associated with the first persona.

17. The one or more non-transitory computer readable storage media of claim 16 , wherein the software is further operable to cause the processor to perform the dynamically updating by adjusting the user interface of the user device for the user to facilitate the at least one subsequent activity of the at least one predictive rule after detecting the initial activity.

18. The one or more non-transitory computer readable storage media of claim 15 , wherein the software is further operable to cause the processor to perform the dynamically updating comprises by adjusting the user interface of the user device of the user based on determining the current set of user activity data is associated with a second persona.

19. The one or more non-transitory computer readable storage media of claim 15 , wherein the software is further operable to cause the processor to perform tracking which persona among the plurality of personas is associated with a particular user among the plurality of users for each user session among the plurality of user sessions that are associated with the particular user.

20. The one or more non-transitory computer readable storage media of claim 15 , wherein the software is further operable to cause the processor to perform determining the plurality of personas by clustering similar user activity across the plurality of user sessions including:

selecting a number k of personas in the plurality of personas based on a predetermined number of expected personas; and

clustering the user activity across the plurality of user sessions with a k-means clustering algorithm.

Assignments (1)

Continuity (2)

References Cited (29)