Large-scale information collection and mining

• US 7,814,035 B2
• Filed: 07/28/2008
• Issued: 10/12/2010
• Est. Priority Date: 11/04/2005
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Mundie, Craig J., Hinrichs, Randy J., Heckerman, David E., Jojic, Nebojsa
• Primary Examiner(s): HOLMES, MICHAEL B
• Application Number:
  US12/180,705
• Publication Number:
  US 20080294465A1
• Time in Patent Office: 806 Days
• Field of Search: 706/20
• US Class Current: 706/20
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• 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: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

The methods/systems described herein facilitate large-scale data collection and aggregation. One exemplary system that facilitates large-scale reporting of health-related data comprises a data collection component, a database and an aggregation component. The data collection component can collect health-related data on a large-scale from a non-selected population. The database can store at least some of the health-related data. The aggregation component can facilitate automatically ascertaining at least one pattern from the health-related data at least in part by applying one or more statistical, data-mining or machine-learning techniques to the database. One exemplary method of extracting health observations from information obtained on a macro-scale comprises receiving information about a plurality of self-selected subjects, pooling the information, mining the pooled information at least in part by employing a data-mining algorithm to infer one or more health observations from the pooled information, and monetizing the one or more health observations.

Claims

1. A system for collecting and mining large amounts of data comprising:

a data collection component that collects data on a large-scale from a non-selected population;

a database that receives the collected data; and

an aggregation component that aggregates the collected data and discerns one or more patterns in the data by applying a machine-learning algorithm to the database.

2. The system of claim 1, wherein the data is health-related data collected from the non-selected population.

3. The system of claim 1, wherein the collected data is one or more of explicit or implicit data.

4. The system of claim 3, wherein the data is explicit data collected from the non-selected population and the pattern is discerned from implicit data that is gathered from the explicit data.

5. The system of claim 1, further comprising a forwarding component that sends the discerned patterns to a third party.

6. The system of claim 1, further comprising a reminder component that sends out one or more reminders to data sources with requests to provide the data to the data collection component.

7. The system of claim 1, wherein the data is anonymous data collected without collecting information identifying a subject associated with the data.

8. The system of claim 1, wherein the discerned pattern is a correlation between a use of a certain medication and a symptom existing among the non-selected population.

9. A method of mining data for discerning one or more patterns comprising:

receiving data from a plurality of data sources associated with one or more self selected subjects;

pooling the received data;

applying a machine learning algorithm to mine the received data; and

discerning one or more patterns existing within the received data.

10. The method of claim 9, wherein the machine learning algorithm mines the data by according different weights to different data.

11. The method of claim 10, wherein data more likely to be accurate is accorded greater weight.

12. The method of claim 9, wherein the machine learning algorithm makes inferences with missing data by applying low-order sufficient statistics.

13. The method of claim 9, wherein the data is collected by tailoring questions to converge on a most valued information.

14. The method of claim 9, further comprising determining whether a user is taking medication as prescribed by automatically acquiring the user'"'"'s prescription medication history and analyzing the user'"'"'s refill history.

15. The method of claim 9, wherein the received data is associated with a user'"'"'s medication and physiological status and the pattern discerns if the medication is producing an intended effect by correlating the medication and physiological status data.

16. The method of claim 15, further comprising, forwarding to the user an alert if it is discerned that the user'"'"'s response to the medication is inadequate.

17. The method of claim 9, further comprising, monetizing the discerned patterns by providing a subscription service wherein an interested party can receive the discerned patterns by paying a subscription fee.

18. A system for mining data related to a non-selected population, comprising:

means for collecting data on a large-scale from the non-selected population;

means for receiving the collected data; and

means for discerning one or more patterns in the data by applying a machine-learning algorithm to the receiving means.

19. The system of claim 18, further comprising means for forwarding the discerned patterns to a third party.

20. The system of claim 18, further comprising means for reminding that sends out one or more reminders to data sources with requests to provide the data to the collecting means.