Computer-Implemented Systems and Methods for Time Series Exploration

• US 20140019088A1
• Filed: 07/13/2012
• Published: 01/16/2014
• Est. Priority Date: 07/13/2012
• Status: Active Grant

• Current Assignee: SAS Institute Incorporated
• Original Assignee: Edward Tilden Blair, Jerzy Michal Brzezicki, Kannukuzhiyil Kurien Kurien, Michael James Leonard, Sujatha Pothireddy, Udo V. Sglavo
• Inventors: LEONARD, Michael James, BLAIR, Edward Tilden, BRZEZICKI, Jerzy Michal, SGLAVO, Udo V., TOMAR, Ranbir Singh, KURIEN, Kannukuzhiyil Kurien, POTHIREDDY, Sujatha, NATH, Rajib, MULEY, Vilochan Suresh
• Granted Patent: US 9,087,306 B2
• Time in Patent Office: Days
• US Class Current: 702/178
• CPC Class Codes: G06F 16/34 Browsing; Visualisation therefor
• CPC Class Codes: G06F 17/10 Complex mathematical operations function generation by table look-up G06F1/03; evaluation of elementary functions by calculation G06F7/544
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Systems and methods are provided for analyzing unstructured time stamped data of a physical process in order to generate structured hierarchical data for a hierarchical time series analysis application. A plurality of time series analysis functions are selected from a functions repository. Distributions of time stamped unstructured data are analyzed to identify a plurality of potential hierarchical structures for the unstructured data with respect to the selected time series analysis functions. Different recommendations for the potential hierarchical structures for each of the selected time series analysis functions are provided, where the selected time series analysis functions affect what types of recommendations are to be provided, and the unstructured data is structured into a hierarchical structure according to one or more of the recommended hierarchical structures, where the structured hierarchical data is provided to an application for analysis using one or more of the selected time series analysis functions.

Claims

1. A computer-implemented method of analyzing unstructured time stamped data of a physical process in order to generate structured hierarchical data for a hierarchical time series analysis application, said method comprising:

selecting, using one or more data processors, a plurality of time series analysis functions from a functions repository;

analyzing, using the one or more data processors, distributions of time stamped unstructured data to identify a plurality of potential hierarchical structures for the unstructured data with respect to the selected time series analysis functions;

providing, using the one or more data processors, different recommendations for the potential hierarchical structures for each of the selected time series analysis functions, wherein the selected time series analysis functions affect what types of recommendations are to be provided; and

structuring, using the one or more data processors, the unstructured data into a hierarchical structure according to one or more of the recommended hierarchical structures, wherein the structured hierarchical data is provided to an application for analysis using one or more of the selected time series analysis functions.

2. The method of claim 1 further comprising:

performing a hierarchical analysis of the potential hierarchical structures to determine an optimal frequency and a data sufficiency metric for a particular one of the time series analysis functions, wherein performing a hierarchical analysis for a potential hierarchical structure includes;

aggregating the unstructured data according to the potential hierarchical structure and according to a plurality of candidate frequencies;

determining the optimal frequency for the potential hierarchical structure by;

analyzing a distribution of data across the aggregations for each candidate frequency to determine a candidate frequency data sufficiency metric; and

selecting the optimal frequency based on the candidate frequency data sufficiency metrics; and

determining the data sufficiency metric for the potential hierarchical structure based on the candidate frequency data sufficiency metric associated with the selected optimal frequency; and

selecting one of the potential hierarchical structures as a selected hierarchical structure for the particular time series analysis function based on the data sufficiency metrics for the potential hierarchical structures, wherein the unstructured data is structured according to the selected hierarchical structure and the optimal frequency associated with the selected hierarchical structure.

3. The method of claim 1, further comprising:

analyzing the structured hierarchical data using one or more of the selected time series analysis functions.

4. The method of claim 1, further comprising:

comparing the structured hierarchical data to a time series of interest to identify a similar portion of the structured hierarchical data; and

extracting the similar portion of the structured data, wherein a selected time series analysis function operates on the extracted similar portion.

5. The method of claim 1, further comprising:

analyzing the structured hierarchical data to identify a characteristic of the structured hierarchical data; and

selecting a data model for a selected time series analysis function based on the identified characteristic, wherein the selected time series analysis function is performed using the selected data model.

6. The method of claim 5, wherein the characteristic is a seasonal pattern, a trend pattern, a growth pattern, or a delay pattern.

7. The method of claim 1, further comprising:

performing a transformation or reduction on the structured hierarchical data; and

generating a visualization of the transformed or reduced structured hierarchical data.

8. The method of claim 1, wherein the time series analysis functions include forecasting functions.

9. The method of claim 8, wherein the structured hierarchical data is provided to a forecasting application for forecasting using one or more of the forecasting functions.

10. The method of claim 1, wherein said analyzing includes applying a seasonality test, an intermittency test, or a trending data test to the time stamped unstructured data.

11. The method of claim 1, wherein said analyzing includes applying a user defined test or a business objective test to the time stamped unstructured data.

12. The method of claim 1, further comprising:

providing a first portion of the structured hierarchical data to a first processor for performing the identified statistical analysis; and

providing a second portion of the structured hierarchical data to a second processor for performing the identified statistical analysis, wherein the first portion and the second portion are based upon a portion of a hierarchy in which the first portion and the second portion reside.

13. The method of claim 1, wherein the recommendations include a segmenting recommendation for the potential hierarchical structures based on a user defined criteria or a statistical analysis criteria, wherein the unstructured data is structured based on the segmenting recommendation.

14. A system for analyzing unstructured time stamped data of a physical process in order to generate structured hierarchical data for a hierarchical time series analysis application, comprising:

one or more processors;

one or more computer-readable storage mediums containing instructions configured to cause the one or more processors to perform operations including;

selecting a plurality of time series analysis functions from a functions repository;

analyzing distributions of time stamped unstructured data to identify a plurality of potential hierarchical structures for the unstructured data with respect to the selected time series analysis functions;

providing different recommendations for the potential hierarchical structures for each of the selected time series analysis functions, wherein the selected time series analysis functions affect what types of recommendations are to be provided; and

structuring the unstructured data into a hierarchical structure according to one or more of the recommended hierarchical structures, wherein the structured hierarchical data is provided to an application for analysis using one or more of the selected time series analysis functions.

15. The system of claim 14, wherein the operations further include:

performing a hierarchical analysis of the potential hierarchical structures to determine an optimal frequency and a data sufficiency metric for a particular one of the time series analysis functions, wherein performing a hierarchical analysis for a potential hierarchical structure includes;

aggregating the unstructured data according to the potential hierarchical structure and according to a plurality of candidate frequencies;

determining the optimal frequency for the potential hierarchical structure by;

analyzing a distribution of data across the aggregations for each candidate frequency to determine a candidate frequency data sufficiency metric; and

selecting the optimal frequency based on the candidate frequency data sufficiency metrics; and

determining the data sufficiency metric for the potential hierarchical structure based on the candidate frequency data sufficiency metric associated with the selected optimal frequency; and

selecting one of the potential hierarchical structures as a selected hierarchical structure for the particular time series analysis function based on the data sufficiency metrics, wherein the unstructured data is structured according to the selected hierarchical structure and the optimal frequency associated with the selected hierarchical structure.

16. The system of claim 14, wherein the operations further include:

analyzing the structured hierarchical data using one or more of the selected time series analysis functions.

17. The system of claim 14, wherein the operations further include:

comparing the structured data to a time series of interest to identify a similar portion of the structured data; and

extracting the similar portion of the structured data, wherein the identified statistical analysis is performed on the extracted portion of the structured data.

18. The system of claim 14, wherein the operations further include:

analyzing the structured data to identify a characteristic of the structured data; and

selecting a data model for the identified statistical analysis based on the identified characteristic, wherein statistical analysis is performed using the selected data model.

19. The system of claim 18, wherein the characteristic is a seasonal pattern, a trend pattern, a growth pattern, or a delay pattern.

20. The system of claim 14, wherein the operations further include:

performing a transformation or reduction on the structured data; and

generating a visualization of results of the statistical analysis.

21. The system of claim 14, wherein the recommendations include a segmenting recommendation for the potential hierarchical structures based on a user defined criteria or a statistical analysis criteria, wherein the unstructured data is structured based on the segmenting recommendation.

22. A computer program product for analyzing unstructured time stamped data of a physical process in order to generate structured hierarchical data for a hierarchical time series analysis application, tangibly embodied in a machine-readable non-transitory storage medium, including instructions configured to cause a data processing system to:

select a plurality of time series analysis functions from a functions repository;

analyze distributions of time stamped unstructured data to identify a plurality of potential hierarchical structures for the unstructured data with respect to the selected time series analysis functions;

provide different recommendations for the potential hierarchical structures for each of the selected time series analysis functions, wherein the selected time series analysis functions affect what types of recommendations are to be provided; and

structure the unstructured data into a hierarchical structure according to one or more of the recommended hierarchical structures, wherein the structured hierarchical data is provided to an application for analysis using one or more of the selected time series analysis functions.