Computer-implemented systems and methods for efficient structuring of time series data

Patent metadata

Field	Value
Publication number	US-9244887-B2
Application number	US-201213548282-A
Country	US
Kind code	B2
Filing date	Jul 13, 2012
Priority date	Jul 13, 2012
Publication date	Jan 26, 2016
Grant date	Jan 26, 2016

Abstract

Systems and methods are provided for analyzing through one-pass of unstructured time stamped data of a physical process. A distribution of time-stamped unstructured data is analyzed to identify a plurality of potential hierarchical structures for the unstructured data. A hierarchical analysis of the potential hierarchical structures is performed to determine an optimal frequency and a data sufficiency metric for the potential hierarchical structures. One of the potential hierarchical structures is selected as a selected hierarchical structure based on the data sufficiency metrics. The unstructured data is structured according to the selected hierarchical structure and the optimal frequency associated with the selected hierarchical structure, where said structuring of the unstructured data is performed via a single pass though the unstructured data. The identified statistical analysis of the physical process is performed using the structured data.

First claim

It is claimed:

1. A computer-implemented method comprising:
analyzing, using a time series engine, a distribution of unstructured time-stamped data to identify a plurality of potential time series data hierarchies for structuring the unstructured time-stamped data,
wherein a potential time series data hierarchy is a framework for structuring the data using of multiple time series, and
wherein the time series engine is at a server layer of a time series computing system;

performing, using the time series engine, an analysis of the plurality of potential time series data hierarchies, wherein performing the analysis of the plurality of potential time series data hierarchies includes determining an optimal time series frequency and a data sufficiency metric for each of the plurality of potential time series data hierarchies;
comparing data sufficiency metrics for the plurality of potential time series data hierarchies;
selecting a hierarchy of the plurality of potential time series data hierarchies based on the comparison of the data sufficiency metrics;
structuring the unstructured time-stamped data into structured time-stamped data according to the hierarchy and the optimal time series frequency,
wherein structuring the transformed time-stamped data into the structured time-stamped data is performed using a single pass of the unstructured time-stamped data through the time series engine;

computing a plurality of transformations of the structured time-stamped data using the single pass of the structured time-stamped data through the time series engine;
transforming the structured time-stamped data into transformed time-stamped data according to the plurality of transformations; and
providing, using an application programming interface, the transformed time-stamped data for visual presentation.

2. The method of claim 1 , further comprising:
deriving a time series using the transformed time-stamped data; and
analyzing the derived time series using one or more time series analysis functions.

3. The method of claim 2 , further comprising:
comparing the derived time series to a time series of interest to identify a similar portion of the derived time series; and
extracting the similar portion of the derived time series, wherein a selected time series analysis function operates on the extracted similar portion.

4. The method of claim 2 , further comprising:
identifying a characteristic of the derived time series; and
selecting a data model for a time series analysis function based on the identified characteristic, wherein the time series analysis function is performed using the selected data model, and wherein the identified characteristic is a seasonal pattern, a trend pattern, a growth pattern, or a delay pattern.

5. The method of claim 2 , wherein a time series analysis function is applied to the derived time series, and wherein the time series analysis function comprises a forecasting function.

6. The method of claim 5 , wherein the derived time series are provided to a forecasting application for forecasting using the time series analysis function.

7. The method of claim 1 , wherein the unstructured time-stamped data is analyzed by applying a seasonality test, an intermittency test, or a trending data test.

8. The method of claim 1 , wherein the unstructured time-stamped data is analyzed by applying a user defined test.

9. The method of claim 1 , further comprising:
providing a first portion of the derived time series to a first processor for performing a statistical analysis; and
providing a second portion of the derived time series to a second processor for performing the 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.

10. The method of claim 1 , further comprising:
selecting additional hierarchies of the plurality of potential time series data hierarchies based on the comparison of the data sufficiency metrics; and
structuring the unstructured time-stamped data into structured time-stamped data according to the additional hierarchies and the optimal time series frequency, wherein structuring the unstructured time-stamped data using a hierarchy of the additional hierarchies is executed with a corresponding process thread.

11. The method of claim 1 , further comprising:
outputting, using the time series engine, information corresponding to the structured data, wherein outputting the information is performed using the single pass of the time stamped unstructured data.

12. The method of claim 1 , further comprising:
generating, using the time series engine, an electronic representation of the structured data using the single pass of the time stamped unstructured data.

13. The method of claim 1 , wherein analyzing the distribution of the unstructured time-stamped data includes performing a time frequency analysis on the unstructured data using the time series engine.

14. The method of claim 1 , wherein analyzing the distribution of the unstructured time-stamped data includes performing a data aggregation frequency analysis on the unstructured data using the time series engine.

15. The method of claim 1 , wherein analyzing the distribution of the unstructured time-stamped data includes performing a cluster analysis of the unstructured data using the time series engine.

16. The method of claim 1 , wherein determining an optimal time series frequency includes aggregating the unstructured time-stamped data into aggregated time-stamped data using the time series engine, and wherein the aggregating is performed using a potential hierarchical structure and a plurality of candidate frequencies for the potential hierarchical structure.

17. The method of claim 16 , wherein determining a data sufficiency metric uses the aggregated time-stamped data.

18. The method of claim 1 , further comprising:
providing a recommendation according to the analysis of the plurality of potential time series data hierarchies, wherein the recommendation is provided using a graphical user interface; and
receiving user input associated with the recommendation, wherein the unstructured time-stamped data is structured according to the user input.

19. A system 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:
analyzing, using a time series engine, a distribution of unstructured time-stamped data to identify a plurality of potential time series data hierarchies for structuring the unstructured time-stamped data,
wherein a potential time series data hierarchy is a framework for structuring the data through use of multiple time series, and
wherein the time series engine is at a server layer of a time series computing system;

performing, using the time series engine, an analysis of the plurality of potential time series data hierarchies, wherein performing the analysis of the plurality of potential time series data hierarchies includes determining an optimal time series frequency and a data sufficiency metric for each of the plurality of potential time series data hierarchies;
comparing data sufficiency metrics for the plurality of potential time series data hierarchies;
selecting a hierarchy of the plurality of potential time series data hierarchies based on the comparison of the data sufficiency metrics;
structuring the unstructured time-stamped data into structured time-stamped

Assignees

• Leonard Michael James
• Crowe Keith Eugene
• Christian Stacey M
• Beeman Jennifer Leigh Sloan
• Elsheimer David Bruce
• Blair Edward Tilden
• Sas Inst Inc

Inventors

• Leonard Michael James
• Crowe Keith Eugene
• Christian Stacey M
• Beeman Jennifer Leigh Sloan
• Elsheimer David Bruce
• Blair Edward Tilden

Classifications

• G06F11/3452

  Performance evaluation by statistical analysis · CPC title

• G06Q10/04

  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 title

• G06F16/258

  Data format conversion from or to a database · CPC title

• G06F17/18 Primary

  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 title

• G06F17/30569

  Physics · mapped topic