DYNAMIC ADJUSTMENT OF USER PROFILES FOR BUNDLED APPLICATIONS
A method and apparatus for dynamic adjustment of user profiles for a bundled application is disclosed. Multi-dimensional characteristic attributes of a plurality of players may be tracked and utilized to improve player experience, player retention, and detect abnormal behavior in game play. Player performance and interest may be assessed in real-time. Game independent characteristic attributes are defined for player profiles and are used to adjust a player's experience or preference level based on gaming results such as win-loss scores. Characteristic weights for a player's characteristic attributes are also defined. Methods and apparatus to select game sessions and players with similar interests or experiences are also disclosed. Methods for detecting abnormal patterns in game session behavior are also disclosed. Methods and apparatus for allowing users to opt out of the calibrations process are also disclosed.
1 . A method performed by a server for dynamically adjusting a user profile stored on the server and utilized by a plurality of applications run on a plurality of user devices connected to the server over a network, the method comprising:
determining a user vector which includes a plurality of user attributes including at least one user skill attribute characterizing a user based on one or more interactions that the user has with another user or an Artificial Intelligence (AI);
determining a characteristic weight vector which includes a plurality of characteristic weights characterizing an application of the plurality of applications, wherein at least one of the plurality of characteristic weights corresponds to one of the at least one user skill attribute; and
generating an observation based on the user vector and the characteristic weight.
2 . The method of claim 1 , wherein the observation comprises a projected result of an execution of the application.
3 . The method of claim 2 , further comprising:
determining an actual result of the execution of the application; and
on a condition that the actual result differs from the projected result by a threshold, updating the at least one user skill attribute.
4 . The method of claim 1 , further comprising adjusting the at least one user skill attribute dynamically based on application or user data generated during an interaction by the user with the application.
5 . The method of claim 4 , wherein the application or user data comprises in-application metrics or win/loss statistics.
6 . The method of claim 1 , wherein generating the observation comprises projecting the user vector and the characteristic weight vector.
7 . The method of claim 1 , wherein the observation comprises a compatibility of the user with the application.
8 . The method of claim 1 , wherein the observation comprises a compatibility of the user with another user.
9 . The method of claim 1 , wherein the observation comprises an abnormal event within the application.
10 . The method of claim 1 , wherein the user vector characterizes at least one skill, interest, or preference of the user.
11 . A server configured to dynamically adjust a user profile for bundled applications, the server comprising:
a processor and a non-transitory computer readable medium in communication with the processor; wherein the processor comprises:
circuitry configured to determine a user vector which includes a plurality of user attributes including at least one user skill attribute characterizing a user based on one or more interactions that the user has with another user or an Artificial Intelligence (AI);
circuitry configured to determine a characteristic weight vector which includes a plurality of characteristic weights characterizing an application, wherein at least one of the plurality of characteristic weights corresponds to one of the at least one user skill attribute; and
circuitry configured to generate an observation based on the user vector and the characteristic weight.
12 . The server of claim 11 , wherein generating the observation comprises projecting a result of an execution of the application.
13 . The server of claim 12 , further comprising:
circuitry configured to determine an actual result of the execution of the application; and
circuitry configured, on a condition that the actual result differs from the projected result by a threshold, to update the at least one user skill attribute.
14 . The server of claim 11 , further comprising circuitry configured to adjust the at least one user skill attribute dynamically based on application or user data generated during an interaction by the user with the application.
15 . The server of claim 14 , wherein the application or user data comprises in-application metrics or win/loss statistics.
16 . The server of claim 11 , wherein generating the observation comprises projecting the user vector and the characteristic weight vector.
17 . The server of claim 11 , wherein the observation comprises a compatibility of the user with the application.
18 . The server of claim 11 , wherein the observation comprises a compatibility of the user with another user.
19 . The server of claim 11 , wherein the observation comprises an abnormal event within the application.
20 . The server of claim 11 , wherein the user vector characterizes at least one skill, interest, or preference of the user.