Predicting the future state of a mobile device user

• US 9,913,120 B2
• Filed: 08/24/2016
• Issued: 03/06/2018
• Est. Priority Date: 10/19/2012
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Johnson, Michael Dudley, Williams, Joshua
• Primary Examiner(s): Meky, Moustafa M
• Application Number:
  US15/246,349
• Publication Number:
  US 20160366573A1
• Time in Patent Office: 559 Days
• CPC Class Codes: G01C 21/3484 Personalized, e.g. from learned user behaviour or user-defined profiles
• CPC Class Codes: G01C 21/3617 using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement
• CPC Class Codes: G01S 5/0027 of actual mobile position, i.e. position determined on mobile
• CPC Class Codes: G08G 1/096888 where input information is obtained using learning systems, e.g. history databases
• CPC Class Codes: G08G 1/20 Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/21 for social networking applications
• CPC Class Codes: H04W 88/02 Terminal devices

Abstract

In one embodiment, a computing system receives an indication of current mobile device usage by a user. The user is also associated with one or more past user states that are accessible to the computing system. The computing system selects a future user state of the user based on a calculated probability of a possible future user state. The possible future user state is calculated based on the current mobile-device usage and the past user states. For each past user states, a weight based on a time delay factor is used. Based on the selected future user state, the operation of a mobile device of the user is adapted at the future time corresponding to the future user state.

Claims

1. A method comprising:

by one or more computing devices, selecting a future user state of a user based on a weighted set of predictor functions, wherein;

each predictor function comprises a machine-learned algorithm trained for a particular possible future user state based on a current user state of the user and one or more past user states of the user, wherein the current user states and past user states are received from a first mobile device of the user;

the selecting the future user state is based on calculated probabilities of possible future user states determined by the weighted set of predictor functions; and

each of the one or more past user states are weighted by a time decay factor, wherein the time decay factor for a particular past user state changes value based on an age of the particular past user state; and

by the one or more computing devices, adapting, at a future time corresponding to the selected future user state, the operation of a second mobile device of the user.

2. The method of claim 1, wherein selecting the future user state is determined by a combination of the weighted set of predictor functions, wherein the combination is determined:

linearly;

as a harmonic mean of the weighted set of predictor functions;

as mean squares of the weighted set of predictor functions;

or

as a geometric mean of the weighted set of predictor functions.

3. The method of claim 1, wherein the selected future user state is associated with the user traveling within a geographical area.

4. The method of claim 1, wherein the past user states of the user comprise one or more of temporal, spatial, modal, or social accessibility of the user.

5. The method of claim 1, wherein the first mobile device and the second mobile device are the same device.

6. The method of claim 1, wherein the selected future user state is associated with a future mobile-device usage by the user.

7. The method of claim 6, wherein adapting the operation of the mobile device of the user further comprises adapting network interaction with the second mobile device at the future time to the future mobile-computing-device usage.

8. The method of claim 1, wherein adapting the operation of the mobile device comprises modifying the interaction of a telecommunications network with the second mobile device to provide wireless connectivity to the mobile device.

9. The method of claim 1, wherein the adapting the operation of the mobile device of the user comprises adapting network interaction with the second mobile device, the adapting comprising automatically selecting social-networking information to push to the second mobile device, wherein the social-networking information is relevant to the selected future user state.

10. The method of claim 1, wherein:

the user is a user of a social-networking system; and

adapting the operation of the second mobile device comprises requesting interaction by the second mobile device with the social-networking system.

11. The method of claim 10, wherein:

the future user state of the user comprises the user traveling within a geographical area at the future time; and

requesting interaction by the second mobile device with the social-networking system comprises automatically selecting social-networking information to push to the second mobile device relevant to the user traveling within the geographical area.

12. The method of claim 10, wherein:

the future user state of the user comprises a location and an activity of the user; and

requesting interaction by the second mobile device with the social-networking system comprises modifying one or more logical operations of a social-networking application on the second mobile device relevant to the location and activity of the user for access by the user at the future time.

13. The method of claim 1, wherein:

the future user state of the user comprises the user commuting; and

adapting the operation of the second mobile device comprises requesting content with lower bandwidth requirements for transmission to the second mobile device while the user is commuting.

14. The method of claim 1, wherein:

the future user state of the user comprises a location of the user; and

adapting the operation of the second mobile device comprises reducing polling of the second mobile device for its geographic location.

15. The method of claim 1, wherein the future time is proximate to a current time.

16. The method of claim 1, wherein the current user state comprises one or more of:

an identifier of the mobile device;

an identifier of an application on the mobile device;

an Internet Protocol (IP) address of the mobile device;

a location of the mobile device;

a vector of movement of the mobile device;

or

a local time reported by the mobile device.

17. The method of claim 1, wherein:

the user is a user of a social-networking system, the social-networking system comprising a graph that comprises a plurality of nodes and a plurality of edges connecting the nodes, at least one node in the graph corresponding to the user; and

the past user states comprise social-networking information from the graph associated with the user.

18. The method of claim 1, wherein predicting the future user state of the user comprises one or more of:

regression analysis of the current user state or the past user states;

decision-tree analysis of the current user state or the past user states;

neural-network analysis of the current user state or the past user states;

or

expert-system analysis of the current user state or the past user states.

19. The method of claim 1, wherein the processors are further operable when executing the instructions to:

receive an indication of the current user state, wherein the current user state comprises a current mobile-device usage by the user; and

access information about the one or more past user states of the user.

20. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

select a future user state of the a user based on a weighted set of predictor functions, wherein;

each predictor function comprises a machine-learned algorithm trained for a particular possible future user state based on a current user state of the user and one or more past user states of the user, wherein the current user states and past user states are received from a first mobile device of the user;

the selecting the future user state is based on calculated probabilities of possible future user states determined by the weighted set of predictor functions; and

each of the one or more past user states are weighted by a time decay factor, wherein the time decay factor for a particular past user state changes value based on an age of the particular past user state; and

adapt, at a future time corresponding to the selected future user state, the operation of a second mobile device of the user.

21. A system comprising:

one or more processors; and

a memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to;

select a future user state of the a user based on a weighted set of predictor functions, wherein;

each predictor function comprises a machine-learned algorithm trained for a particular possible future user state based on a current user state of the user and one or more past user states of the user, wherein the current user states and past user states are received from a first mobile device of the user;

the selecting the future user state is based on calculated probabilities of possible future user states determined by the weighted set of predictor functions; and

each of the one or more past user states are weighted by a time decay factor, wherein the time decay factor for a particular past user state changes value based on an age of the particular past user state; and

adapt, at a future time corresponding to the selected future user state, the operation of a second mobile device of the user.

22. The system of claim 21, wherein selecting the future user state is determined by a combination of the weighted set of predictor functions, wherein the combination is determined:

linearly;

as a harmonic mean of the weighted set of predictor functions;

as mean squares of the weighted set of predictor functions;

or

as a geometric mean of the weighted set of predictor functions.

23. The system of claim 21, wherein the selected future user state is associated with the user traveling within a geographical area.

24. The system of claim 21, wherein the past user states of the user comprise one or more of temporal, spatial, modal, or social accessibility of the user.

25. The system of claim 21, wherein the first mobile device and the second mobile device are the same device.

26. The system of claim 21, wherein the selected future user state is associated with a future mobile-device usage by the user.

27. The system of claim 26, wherein adapting the operation of the mobile device of the user further comprises adapting network interaction with the second mobile device at the future time to the future mobile-computing-device usage.

28. The system of claim 21, wherein adapting the operation of the mobile device comprises modifying the interaction of a telecommunications network with the second mobile device to provide wireless connectivity to the mobile device.

29. The system of claim 21, wherein the adapting the operation of the mobile device of the user comprises adapting network interaction with the second mobile device, the adapting comprising automatically selecting social-networking information to push to the second mobile device, wherein the social-networking information is relevant to the selected future user state.

30. The system of claim 21, wherein:

the user is a user of a social-networking system; and

adapting the operation of the second mobile device comprises requesting interaction by the second mobile device with the social-networking system.

31. The system of claim 30, wherein:

the future user state of the user comprises the user traveling within a geographical area at the future time; and

requesting interaction by the second mobile device with the social-networking system comprises automatically selecting social-networking information to push to the second mobile device relevant to the user traveling within the geographical area.

32. The system of claim 30, wherein:

the future user state of the user comprises a location and an activity of the user; and

requesting interaction by the second mobile device with the social-networking system comprises modifying one or more logical operations of a social-networking application on the second mobile device relevant to the location and activity of the user for access by the user at the future time.

33. The system of claim 21, wherein:

the future user state of the user comprises the user commuting; and

adapting the operation of the second mobile device comprises requesting content with lower bandwidth requirements for transmission to the second mobile device while the user is commuting.

34. The system of claim 21, wherein:

the future user state of the user comprises a location of the user; and

adapting the operation of the second mobile device comprises reducing polling of the second mobile device for its geographic location.

35. The system of claim 21, wherein the future time is proximate to a current time.

36. The system of claim 21, wherein the current user state comprises one or more of:

an identifier of the mobile device;

an identifier of an application on the mobile device;

an Internet Protocol (IP) address of the mobile device;

a location of the mobile device;

a vector of movement of the mobile device;

or

a local time reported by the mobile device.

37. The system of claim 21, wherein:

the user is a user of a social-networking system, the social-networking system comprising a graph that comprises a plurality of nodes and a plurality of edges connecting the nodes, at least one node in the graph corresponding to the user; and

the past user states comprise social-networking information from the graph associated with the user.