CONTEXT-AWARE HYPOTHESIS-DRIVEN AGGREGATION OF CROWD-SOURCED EVIDENCE FOR A SUBSCRIPTION-BASED SERVICE

• US 20150310347A1
• Filed: 04/25/2014
• Published: 10/29/2015
• Est. Priority Date: 04/25/2014
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Mukherji, Abhishek, Welbourne, Evan, Tapia, Emmanuel Munguia
• Granted Patent: US 9,648,089 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/306 User profiles

Abstract

A method and system for providing an answer to a subscription-based query service. The method includes acquiring context information and evidence information from one or more electronic devices based on a query. One or more belief values are assigned based on the evidence information and the context information. The belief values are aggregated for determining a score for competing hypotheses using a probabilistic model. Sufficiency of hypotheses is determined based on statistical significance for potential answer information to the query.

Claims

1. A method for providing an answer to a subscription-based query service comprising:

acquiring context information and evidence information from one or more electronic devices based on a query;

assigning one or more belief values based on the evidence information and the context information;

aggregating the belief values for determining a score for competing hypotheses using a probabilistic model; and

determining sufficiency of hypotheses based on statistical significance for potential answer information to the query.

2. The method of claim 1, further comprising:

receiving an initial request for the query based on a subscribed service by the one or more electronic devices;

formulating a context-aware hypothesis that is relevant to the query using the context information and the evidence information from the one or more electronic devices by combining the evidence information and the context information.

3. The method of claim 2, wherein the context data comprises one or more of location information, movement information and time.

4. The method of claim 3, further comprising identifying dependencies among multiple hypotheses for determining the sufficiency of hypotheses.

5. The method of claim 4, wherein the evidence information comprises an aggregation of crowd-sourced content in response to the query.

6. The method of claim 5, wherein the belief values are based on evidence content, the context information and user profile information.

7. The method of claim 6, wherein the user profile information comprises past participation information and accuracy regarding answers to previous queries based on the subscribed service.

8. The method of claim 7, further comprising:

determining when to conclude collection of crowd-sourced evidence information and context information based on a difference between a statistical significance of aggregated hypotheses score and a boundary between a rejection region and an acceptance region.

9. The method of claim 1, wherein the answer information is determined by a cloud-based service and transmitted to the one or more electronic devices.

10. The method of claim 9, wherein the one or more electronic devices comprises mobile electronic devices.

11. The method of claim 10, wherein the mobile electronic devices comprises one or more of:

a mobile telephone, a wearable computing device, a tablet device, and a mobile computing device.

12. A system comprising:

an evidence collector module that aggregates evidence information and context information received from one or more electronic devices and assigns one or more belief values based on the evidence information and the context information;

a hypotheses score aggregator module that aggregates the belief values for determining a score for competing hypotheses using a probabilistic model; and

a sufficiency determiner module that determines sufficiency of hypotheses based on statistical significance for potential answer information to a query based on a subscription of the one or more electronic devices.

13. The system of claim 12, further comprising:

a hypotheses formulator that receives an initial request for the query based on the subscription by the one or more electronic devices, and formulates a context-aware hypothesis that is relevant to the query using the context information and the evidence information from the one or more electronic devices by combining the evidence information and the context information.

14. The system of claim 13, wherein the context information comprises one or more of location information, movement information and time.

15. The system of claim 14, wherein the sufficiency determiner module identifies dependencies among multiple hypotheses for determining the sufficiency of hypotheses.

16. The system of claim 15, wherein the evidence information comprises an aggregation of crowd-sourced content in response to the query.

17. The system of claim 16, wherein the belief values are based on the crowd-sourced content, the context information and user profile information.

18. The system of claim 17, wherein the user profile information comprises past participation information and accuracy regarding answers to previous queries based on a subscribed service.

19. The system of claim 18, wherein the sufficiency determiner module determines when to conclude collection of crowd-sourced evidence information and context information based on a difference between a statistical significance of aggregated hypotheses score and a boundary between a rejection region and an acceptance region.

20. The system of claim 12, wherein the answer information is determined by a cloud-based service and transmitted to the one or more electronic devices over a network.

21. The system of claim 20, wherein the one or more electronic devices comprises mobile electronic devices, wherein the mobile electronic devices comprise one or more of:

a mobile telephone, a wearable computing device, a tablet device, and a mobile computing device.

22. A non-transitory computer-readable medium having instructions which when executed on a computer perform a method comprising:

acquiring context information and evidence information from one or more electronic devices based on a query;

assigning one or more belief values based on the evidence information, the context information, and user profile information;

aggregating the belief values for determining a score for competing hypotheses using a probabilistic model; and

determining sufficiency of hypotheses based on statistical significance for potential answer information to the query.

23. The medium of claim 22, further comprising:

receiving an initial request for the query based on a subscribed service by the one or more electronic devices;

formulating a context-aware hypothesis that is relevant to the query using the context information and the evidence information from the one or more electronic devices by combining the evidence information and the context information.

24. The medium of claim 23, wherein the context information comprises one or more of location information, movement information and time.

25. The medium of claim 24, further comprising identifying dependencies among multiple hypotheses for determining the sufficiency of hypotheses, wherein the evidence information comprises an aggregation of crowd-sourced content in response to the query.

26. The medium of claim 25, wherein the belief values are based on evidence content, the context information and user profile information.

27. The medium of claim 26, wherein the user profile information comprises past participation information and accuracy regarding answers to previous queries based on the subscribed service.

28. The medium of claim 27, further comprising:

determining when to conclude collection of crowd-sourced evidence information and context information based on a difference between a statistical significance of aggregated hypotheses score and a boundary between a rejection region and an acceptance region.

29. The medium of claim 28, wherein the answer information is determined by a cloud-based service and transmitted to the one or more electronic devices over a network.

30. The medium of claim 29, wherein the one or more electronic devices comprises mobile electronic devices, and the mobile electronic devices comprises one or more of:

a mobile telephone, a wearable computing device, a tablet device, and a mobile computing device.