Apparatus, method and medium detecting landmarks with a mobile device

• US 20070276591A1
• Filed: 05/24/2007
• Published: 11/29/2007
• Est. Priority Date: 05/26/2006
• Status: Active Grant

• Current Assignee: Industry Academic Cooperation Foundation, Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Lea, Jong-ho, Lee, Yong-beom, Ryu, Hee-seob, Cho, Sung-bae
• Granted Patent: US 8,442,754 B2
• Time in Patent Office: Days
• US Class Current: 701/207
• CPC Class Codes: G06F 16/437 Administration of user profiles, e.g. generation, initialisation, adaptation, distribution
• CPC Class Codes: H04M 1/72448 with means for adapting the functionality of the device according to specific conditions
• CPC Class Codes: H04M 2250/10 including a GPS signal receiver
• CPC Class Codes: H04M 2250/60 logging of communication history, e.g. outgoing or incoming calls, missed calls, messages or URLs logging of telephone numbers H04M1/56, H04M1/57
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services

Abstract

An apparatus, method and medium detecting landmarks with a mobile device. The apparatus includes a storage unit to store rules of landmarks that correspond to connection relations among items representing a user'"'"'s living patterns, an analysis unit to statistically analyze the collected log information representing a current living pattern of the user, a landmark probability inferring unit to infer in probability the landmarks according to the analyzed log information based on the stored rules, and a landmark selection unit to select a final landmark by mutually analyzing the stored rules and the inferred landmarks.

Claims

1. An apparatus detecting landmarks with a mobile device, the apparatus comprising:

a storage unit to store rules of landmarks that correspond to connection relations among items representing a user'"'"'s living patterns;

an analysis unit to statistically analyze collected log information representing a current living pattern of the user;

a landmark probability inferring unit to infer in probability the landmarks according to the analyzed log information based on the stored rules; and

a landmark selection unit to select a final landmark by mutually analyzing the stored rules and the inferred landmarks.

2. The apparatus of claim 1, wherein the log information comprises at least one of external data received from an outside, internal data generated internally, and data being referred to from an external storage place.

3. The apparatus of claim 2, wherein the external data is position information, and the internal data comprises at least one of a call, an SMS message, photographing, playback of a multimedia file, a state of an appliance, and a user'"'"'s profile.

4. The apparatus of claim 1, wherein the analysis unit statistically analyzes the collected log information based on pre-processing functions.

5. The apparatus of claim 1, wherein the landmark probability inferring unit infers the landmarks through modularized Bayesian networks.

6. The apparatus of claim 5, wherein the modularized Bayesian networks have a mutually complementary relation with one another.

7. The apparatus of claim 5, wherein the modularized Bayesian network has a hierarchical structure.

8. The apparatus of claim 5, wherein the landmark probability inferring unit calculates probability values of the landmarks by using the analyzed log information as evidence of the modularized Bayesian networks, calculates connection relations and connection intensities among the modularized Bayesian networks by reusing the landmarks of which the probability values have been calculated and the log contexts as the evidence of the modularized Bayesian networks, and extracts a significant connection path among connection paths among the modularized Bayesian networks based on the connection intensities.

9. The apparatus of claim 8, wherein the landmark selection unit determines the connection intensities according to results of calculating NoisyOR weight values.

10. The apparatus of claim 1, wherein the landmark selection unit selects the landmarks having the probability values which are larger than a specified threshold value among the landmarks inferred by the landmark probability inferring unit.

11. A method detecting landmarks with a mobile device, the method comprising:

storing rules of landmarks that correspond to connection relations among items representing a user'"'"'s living patterns;

statistically analyzing collected log information representing a current living pattern of the user;

inferring in probability the landmarks according to the analyzed log information based on the stored rules; and

selecting a final landmark by mutually analyzing the stored rules and the inferred landmarks.

12. The method of claim 11, wherein the log information comprises at least one of external data received from an outside, internal data generated internally, and data being referred to from an external storage place.

13. The method of claim 12, wherein the external data is position information, and the internal data comprises at least one of a call, an SMS message, photographing, playback of a multimedia file, a state of an appliance, and a user'"'"'s profile.

14. The method of claim 11, wherein the collected log information is statistically analyzed based on pre-processing functions.

15. The method of claim 11, wherein the inferring in probability of the landmarks comprises inferring the landmarks through modularized Bayesian networks.

16. The method of claim 15, wherein the modularized Bayesian networks have a mutually complementary relation with one another.

17. The method of claim 15, wherein the modularized Bayesian network has a hierarchical structure.

18. The method of claim 15, wherein the inferring of the landmarks through modularized Bayesian networks comprises:

calculating probability values of the landmarks using the log contexts at the current time point as evidence of the modularized Bayesian networks;

calculating connection relations and connection intensities among the modularized Bayesian networks by reusing the landmarks of which the probability values have been calculated and the log contexts as the evidence of the modularized Bayesian networks; and

extracting a significant connection path among connection paths among the modularized Bayesian networks based on the connection intensities.

19. The method of claim 18, wherein the calculating of the connection intensities comprises calculating NoisyOR weight values.

20. The method of claim 11, wherein the selecting of a final landmark comprises selecting the landmarks having probability values which are larger than a specified threshold value among the inferred landmarks.

21. At least one medium comprising computer readable code to control at least one processing element to implement a method detecting landmarks with a mobile device, the method comprising:

storing rules of landmarks that correspond to connection relations among items representing a user'"'"'s living patterns;

statistically analyzing collected log information representing a current living pattern of the user;

inferring in probability the landmarks according to the analyzed log information based on the stored rules; and

selecting a final landmark by mutually analyzing the stored rules and the inferred landmarks.

22. The medium of claim 21, wherein the log information comprises at least one of external data received from an outside, internal data generated internally, and data being referred to from an external storage place.

23. The medium of claim 22, wherein the external data is position information, and the internal data comprises at least one of a call, an SMS message, photographing, playback of a multimedia file, a state of an appliance, and a user'"'"'s profile.

24. The medium of claim 21, wherein the collected log information is statistically analyzed based on pre-processing functions.

25. The medium of claim 21, wherein the inferring in probability of the landmarks comprises inferring the landmarks through modularized Bayesian networks.

26. The medium of claim 25, wherein the modularized Bayesian networks have a mutually complementary relation with one another.

27. The medium of claim 25, wherein the modularized Bayesian network has a hierarchical structure.

28. The medium of claim 25, wherein the inferring of the landmarks through modularized Bayesian networks comprises:

calculating probability values of the landmarks using the log contexts at the current time point as evidence of the modularized Bayesian networks;

calculating connection relations and connection intensities among the modularized Bayesian networks by reusing the landmarks of which the probability values have been calculated and the log contexts as the evidence of the modularized Bayesian networks; and

extracting a significant connection path among connection paths among the modularized Bayesian networks based on the connection intensities.

29. The medium of claim 28, wherein the calculating of the connection intensities comprises calculating NoisyOR weight values.

30. The medium of claim 21, wherein the selecting of a final landmark comprises selecting the landmarks having probability values which are larger than a specified threshold value among the inferred landmarks.