Method and apparatus for localized adaptation of client devices based on correlation or learning at remote server

• US 8,775,573 B2
• Filed: 05/22/2008
• Issued: 07/08/2014
• Est. Priority Date: 06/15/2006
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Ebling, Maria Rene, Jerome, William Francis, Misra, Archan, Mohomed, Iqbal I.
• Primary Examiner(s): THIAW, CATHERINE B
• Application Number:
  US12/125,464
• Publication Number:
  US 20080222246A1
• Time in Patent Office: 2,238 Days
• Field of Search: 709/203, 709217-225, 600/300, 455417-420
• US Class Current: 709/220
• CPC Class Codes: A61B 2560/0271 using a remote monitoring unit
• CPC Class Codes: A61B 5/002 Monitoring the patient using a local or closed circuit, e.g. in a room or building A61B5/0017 takes precedence
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/14532 for measuring glucose, e.g. by tissue impedance measurement
• CPC Class Codes: A61B 5/1495 Calibrating or testing of in-vivo probes
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: H04L 67/04 specially adapted for terminals or networks with limited capabilities; specially adapted for terminal portability
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04L 67/125 involving control of end-device applications over a network

Abstract

Techniques are disclosed for localized adaptation of client devices based on correlation or learning at a remote server. For example, a method for modifying a behavior of a client device in a data collection system, wherein the client device collects data and transmits data to a server, includes the following steps. The client device transmits data to the server. The server uses at least a portion of the data received from the client device to generate information that represents a modification to a behavior of the client device. The server device transmits the generated information to the client device. The client device subsequently alters the behavior of the client device based on the information received from the server.

Claims

1. A method for modifying a behavior of a client device in a data collection system wherein the client device collects data and transmits data to a server, the method comprising the steps of:

the client device transmitting data to the server;

the server using at least a portion of the data received from the client device to generate information that is used to modify a target behavior of the client device, wherein said generated information comprises contextual information that is not locally available to the client device and which is relevant to modifying the target behavior of the client device, wherein the contextual information comprises context data about a user of the client device, wherein the context data comprises information about a condition of the user or the user'"'"'s environment, which dynamically varies and is unknown or unavailable to the client device;

the server device transmitting the generated information with said contextual information to the client device; and

the client device subsequently modifying the target behavior of the client device based on the generated information received from the server at times when the client device is connected to the server and based on the generated information that was previously received from the server at times when the client device is disconnected from the server,

wherein the client device modifies the target behavior by using the contextual information received from the server to determine one or more locally stored rules on the client, which are triggered, modified or invalidated based on the contextual information,

wherein each of the one or more locally stored rules include a predicate component that specifies a contextual condition under which the rule is considered valid, and an action component that specifies a resulting behavior of the client device,

wherein the contextual information is used by the client device to determine which of a plurality of locally available predicate or action components of the locally stored rules is applicable at a given time, and select a predicate or action component of a given one of the locally stored rules that is determined to be applicable at the given time.

2. The method of claim 1, wherein the data transmitted to the server comprises one or more data samples.

3. The method of claim 2, wherein the data transmitted to the server comprises modified statistics of the one or more data samples.

4. The method of claim 2, wherein the data transmitted to the server comprises compressed versions of the one or more data samples.

5. The method of claim 1, further comprising the step of the server determining at least one pattern from at least a portion of the data received from the client device.

6. The method of claim 1, wherein the generated information comprises a command to modify, activate or deactivate a rule stored a-priori at the client device.

7. The method of claim 1, wherein the generated information comprises a generated rule.

8. The method of claim 7, wherein the generated rule comprises a predicate which expresses at least one temporal pattern associated with the data collected by the client device.

9. The method of claim 7, wherein the generated rule comprises a predicate which expresses characteristics of data expected to be collected by the client device.

10. The method of claim 7, wherein the generated rule comprises action which expresses a modification to an interface of the client device.

11. The method of claim 7, wherein the generated rule comprises an action which expresses a generation of specific content on the client device.

12. The method of claim 7, wherein the generated rule comprises an action which expresses a modification to a behavior or content of a specific application resident on the client device.

13. The method of claim 7, wherein the generated rule comprises an action which expresses a transmission, suppression of transmission, or compression of one or more collected data samples.

14. The method of claim 7, wherein the generated rule comprises an action which expresses a data transformation.

15. The method of claim 14, wherein the data transformation comprises at least one of an averaging operation, an outlier elimination operation, a compression operation, a filtering operation, a discrete coefficient representation.

16. The method of claim 7, wherein the step of the server generating a rule further comprises eliminating from a predicate of the rule any attribute that cannot be locally determined by the client device.

17. The method of claim 7, wherein the step of the server generating a rule further comprises specifying at least one of removal of an existing rule, refinement of an existing rule, and specification of a new rule.

18. The method of claim 1, wherein the server also uses context data to generate information that represents a modification to a behavior of the client device.

19. The method of claim 18, wherein the context data comprises data representative of context pertaining to an attribute of a user associated with the client device.

20. The method of claim 18, wherein the context data comprises data representative of external context of one or more other individuals or entities.

21. The method of claim 1, further comprising the client monitoring device resources and adjusting behavior based thereon.

22. A method, for use in a client device, for modifying a behavior of the client device in a data collection system wherein the client device collects data and transmits data to a server, the method comprising the steps of:

transmitting data to the server such that the server is able to use at least a portion of the data received from the client device to generate information that is used to modify a target behavior of the client device, wherein said generated information comprises contextual information that is not locally available to the client device and which is relevant to modifying the target behavior of the client device, wherein the contextual information comprises context data about a user of the client device, wherein the context data comprises information about a condition of the user or the user'"'"'s environment, which dynamically varies and is unknown or unavailable to the client device; and

subsequently modifying the target behavior of the client device based on the generated information received from the server at times when the client device is connected to the server and based on the generated information that was previously received from the server at times when the client device is disconnected from the server,

wherein the client device modifies the target behavior by using the contextual information received from the server to determine one or more locally stored rules on the client, which are triggered, modified or invalidated based on the contextual information,

wherein each of the one or more locally stored rules include a predicate component that specifies a contextual condition under which the rule is considered valid, and an action component that specifies a resulting behavior of the client device,

wherein the contextual information is used by the client device to determine which of a plurality of locally available predicate or action components of the locally stored rules is applicable at a given time, and select a predicate or action component of a given one of the locally stored rules that is determined to be applicable at the given time.

23. The method of claim 22, wherein the generated information comprises a command to modify, activate or deactivate a rule stored a-priori at the client device.

24. The method of claim 22, wherein the generated information comprises context data that affects a rule stored a-priori at the client device.

25. The method of claim 22, wherein the generated information comprises a generated rule.

26. The method of claim 22, further comprising the client monitoring device resources and adjusting behavior based thereon.

27. A method, for use in a server, for modifying a behavior of a client device in a data collection system wherein the client device collects data and transmits

data to the server, the method comprising the steps of:

receiving data from the client device;

using at least a portion of the data received from the client device to generate information that is used to modify a target behavior of the client device, wherein said generated information comprises contextual information that is not locally available to the client device and which is relevant to modifying the target behavior of the client device, wherein the contextual information comprises context data about a user of the client device, wherein the context data comprises information about a condition of the user or the user'"'"'s environment, which dynamically varies and is unknown or unavailable to the client device; and

transmitting the information with said contextual information to the client device such that the client device is able to subsequently modify the target behavior of the client device based on the generated information received from the server at times when the client device is connected to the server and based on the generated information that was previously received from the server at times when the client device is disconnected from the server,

wherein the contextual information is usable by the client device to locally determine one or more locally stored rules on the client, which are triggered, modified or invalidated based on the contextual information,

wherein each of the one or more locally stored rules include a predicate component that specifies a contextual condition under which the rule is considered valid, and an action component that specifies a resulting behavior of the client device,

wherein the contextual information is used by the client device to determine which of a plurality of locally available predicate or action components of the locally stored rules is applicable at a given time, and select a predicate or action component of a given one of the locally stored rules that is determined to be applicable at the given time.

28. The method of claim 27, wherein the generated information comprises a command to modify, activate or deactivate a rule stored a-priori at the client device.

29. The method of claim 27, wherein the generated information comprises context data that affects a rule stored a-priori at the client device.

30. The method of claim 27, wherein the generated information comprises a generated rule.

31. The method of claim 27, wherein the client monitors device resources and adjusts behavior based thereon.

32. The method of claim 27, wherein the server also uses context data to generate information that represents a modification to a behavior of the client device.

33. Apparatus for use in a data collection system, comprising:

a client device configured to;

(i) transmit data to a server such that the server is able to use at least a portion of the data received from the client device to generate information that is used to modify a target behavior of the client device, wherein said generated information comprises contextual information that is not locally available to the client device and which is relevant to modifying the target behavior of the client device, wherein the contextual information comprises context data about a user of the client device, wherein the context data comprises information about a condition of the user or the user'"'"'s environment, which dynamically varies and is unknown or unavailable to the client device; and

(ii) subsequently modify the target behavior of the client device based on the generated information received from the server at times when the client device is connected to the server and based on the generated information that was previously received from the server at times when the client device is disconnected from the server,

wherein the client device modifies the target behavior by using the contextual information received from the server to locally determine one or more locally stored rules on the client, which are triggered, modified or invalidated based on the contextual information,

wherein each of the one or more locally stored rules include a predicate component that specifies a contextual condition under which the rule is considered valid, and an action component that specifies a resulting behavior of the client device, wherein the contextual information is used by the client device to determine which of a plurality of locally available predicate or action components of the locally stored rules is applicable at a given time, and select a predicate or action component of a given one of the locally stored rules that is determined to be applicable at the given time.

34. Apparatus for use in a data collection system, comprising:

a server configured to;

(i) receive data from a client device;

(ii) use at least a portion of the data received from the client device to generate information that is used to modify a target behavior of the client device, wherein said generated information comprises contextual information that is not locally available to the client device and which is relevant to modifying the target behavior of the client device;

wherein the contextual information comprises context data about a user of the client device, wherein the context data comprises information about a condition of the user or the user'"'"'s environment, which dynamically varies and is unknown or unavailable to the client device; and

(iii) transmit the generated information with said contextual information to the client device such that the client device is able to subsequently modify the target behavior of the client device based on the generated information received from the server at times when the client device is connected to the server and based on the generated information that was previously received from the server at times when the client device is disconnected from the server,

wherein the contextual information is usable by the client device to determine one or more locally stored rules on the client, which are triggered, modified or invalidated based on the contextual information,

wherein each of the one or more locally stored rules include a predicate component that specifies a contextual condition under which the rule is considered valid, and an action component that specifies a resulting behavior of the client device,

wherein the contextual information is used by the client device to determine which of a plurality of locally available predicate or action components of the locally stored rules is applicable at a given time, and select a predicate or action component of a given one of the locally stored rules that is determined to be applicable at the given time.