Method, system and device for inferring a mobile user's current context and proactively providing assistance

• US 9,015,099 B2
• Filed: 08/14/2012
• Issued: 04/21/2015
• Est. Priority Date: 08/14/2012
• Status: Active Grant

• Current Assignee: SRI International, Inc.
• Original Assignee: SRI International, Inc.
• Inventors: Nitz, Kenneth C., Lincoln, Patrick D., Myers, Karen L., Bui, Hung H., Senanayake, Rukman, Denker, Grit, Mark, William S., Winarsky, Norman D., Weiner, Steven S.
• Primary Examiner(s): Starks, Wilbert L
• Application Number:
  US13/585,008
• Publication Number:
  US 20140052681A1
• Time in Patent Office: 980 Days
• Field of Search: None
• US Class Current: 706/46
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/046 Forward inferencing; Production systems
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages

Abstract

A device, method and system for automatically inferring a mobile user'"'"'s current context includes applying a user activity knowledge base to real-time inputs and stored user-specific information to determine a current situation. Automated reasoning is used to infer a user-specific context of the current situation. Automated candidate actions may be generated and performed in accordance with the current situation and user-specific context.

Claims

1. A method for presenting an automated suggestion at a mobile electronic device, the method comprising, with the mobile electronic device:

by one or more sensors coupled to the mobile electronic device, receiving one or more real-time inputs indicative of an implicit cue regarding a user-specific physical activity in relation to a surrounding physical environment;

by an automated inference engine coupled to the mobile electronic device, accessing the real-time inputs and one more items of previously stored user-specific information;

by the automated inference engine, based on a combination of the one or more real-time inputs and the stored user-specific information, generating a plurality of different user-specific contexts, each user-specific context corresponding to an inferred purpose for the user-specific physical activity;

by the automated inference engine, algorithmically selecting at least one of the plurality of different user-specific contexts;

generating an automated suggestion based on the selected user-specific context; and

presenting the automated suggestion by an output device of the mobile electronic device.

2. The method of claim 1, comprising automatically generating the plurality of different user-specific contexts, wherein one or more of the different user-specific contexts relates to an often-repeated situation and one or more of the different user-specific contexts relates to a not-often-repeated situation.

3. The method of claim 2, comprising determining not to present an automated suggestion in response to the selected user-specific context corresponding to an often-repeated situation.

4. The method of claim 2, comprising presenting the automated suggestion in response to the selected user-specific context corresponding to an often-repeated situation.

5. The method of claim 2, comprising presenting the automated suggestion in response to the selected user-specific context corresponding to a not-often-repeated situation.

6. The method of claim 5, comprising selecting a method of presenting the selected automated suggestion based on the user-specific context corresponding to a not-often-repeated situation and presenting the automated suggestion according to the selected method.

7. The method of claim 2, comprising determining not to present an automated suggestion in response to the selected user-specific context corresponding to a not-often-repeated situation.

8. A computing device comprising at least one processor and computer circuitry coupled to the at least one processor, wherein the computer circuitry is arranged to cause the at least one processor to perform the method of claim 1.

9. At least one machine-accessible storage medium comprising a plurality of instructions that in response to being executed result in a computing device performing the method of claim 1.

21. The method of claim 1, wherein generating the plurality of different user-specific contexts is further based on one more items of non-user-specific information.

10. A method for providing an automated suggestion in response to a current situation pertaining to a location, position, or movement of a person in relation to a physical environment, the method comprising, with a mobile electronic device:

by one or more sensors coupled to the mobile electronic device, receiving one or more real-time inputs indicative of an implicit cue regarding a user-specific physical activity in relation to a surrounding physical environment;

by an automated inference engine coupled to the mobile electronic device, accessing the real-time inputs and one more items of previously stored information;

by the automated inference engine, based on a combination of the one or more real-time inputs and the stored user-specific information, generating a plurality of user-specific contexts, each user-specific context corresponding to a different inferred purpose for the user-specific physical activity;

by the automated inference engine, algorithmically selecting a user-specific context of the plurality of different user-specific contexts;

generating an automated response based on the selected user-specific context; and

by a processor of the mobile electronic device, executing the automated response.

11. The method of claim 10, wherein the execution of the automated response comprises executing an electronic transaction using software at the mobile electronic device.

12. The method of claim 10, wherein the execution of the automated response comprises sending a communication relating to the inferred user-specific context to another electronic device.

13. The method of claim 12, comprising determining, from the selected user-specific context, one or more recipients for the communication and sending the communication to the one or more recipients over an electronic network.

14. The method of claim 10, wherein the execution of the automated response comprises storing data relating to the selected user-specific context in a knowledge base.

15. The method of claim 10, wherein the execution of the automated response comprises receiving one or more other real-time inputs at the mobile electronic device and repeating the accessing, generating, selecting, generating, and executing.

16. The method of claim 15, wherein the execution of the automated response comprises activating a source of real-time inputs to receive the one or more other real-time inputs.

17. The method of claim 10, comprising determining a current level of confidence associated with the selected user-specific context and selecting a method of automatically responding based on the current level of confidence.

18. The method of claim 10, comprising generating a candidate action based on the selected user-specific context;

determining a current level of confidence associated with the candidate action; and

based on the current level of confidence, determining whether to present the candidate action, automatically execute the candidate action, defer the candidate action until a later time, or discard the candidate action.

19. A computing device comprising at least one processor and computer circuitry coupled to the at least one processor, wherein the computer circuitry is arranged to cause the at least one processor to perform the method of claim 10.

20. At least one machine-accessible storage medium comprising a plurality of instructions that in response to being executed result in a computing device performing the method of claim 10.