Method for in-database feature selection for high-dimensional inputs

Patent metadata

Field	Value
Publication number	US-10467226-B2
Application number	US-201615139672-A
Country	US
Kind code	B2
Filing date	Apr 27, 2016
Priority date	Apr 27, 2016
Publication date	Nov 5, 2019
Grant date	Nov 5, 2019

Abstract

A system, method, and computer-readable medium for performing in-database operations, comprising: presenting an automation interface to a user, the user interface automation interface enabling a user to select one or more key performance indicators; instantiating an in-database processing operation, the in-database processing operation performing feature selection from a high dimensional parameter space; executing at least one database statement within the storage system to derive a subset of diagnostic parameters from the high dimensional parameter space.

First claim

What is claimed is:

1. A computer-implementable method for performing in-database operations on parameters associated with complex manufacturing processes, comprising:
presenting an automation interface to a user, the automation interface enabling a user to select one or more key performance indicators;
instantiating an in-database processing operation, the in-database processing operation performing feature selection from a high dimensional parameter space, wherein database statements are executed in parallel to derive a subset of diagnostic parameters from the high dimensional parameter space; and
displaying results showing the subset of diagnostic parameters and strength of relationship to the one or more key performance indicators;
wherein the in-database processing operation performing feature selection comprises:
determining one or more key performance indicators containing at least one of discrete values and continuous measurements; and
constructing the database statements using a common query language and capabilities of a storage system;
wherein the discrete values and continuous measurements trace quality issues associated with the complex manufacturing process;
wherein deriving the subset of diagnostic parameters comprises performing a feature selection operation for each of a plurality of selected parameters;
wherein the feature selection operation comprises linear feature selection operations and nonlinear feature selection operations;
wherein the linear feature selection operations and the nonlinear feature selection operations are performed for the discrete values and continuous measurements.

2. The method of claim 1 , further comprising:
distributing the at least one database statement across a plurality of nodes of the storage system; and,
executing the at least one database statement at each of the plurality of nodes of the storage system.

3. The method of claim 1 , wherein:
deriving the subset of diagnostic parameters comprises performing a feature selection operation for each of a plurality of key performance indicators.

4. A system comprising for performing in-database operations on parameters associated with complex manufacturing processes:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations and comprising instructions executable by the processor and configured for:
presenting an automation interface to a user, the automation interface enabling a user to select one or more key performance indicators;
instantiating an in-database processing operation, the in-database processing operation performing feature selection from a high dimensional parameter space, wherein
database statements are executed in parallel to derive a subset of diagnostic parameters from the high dimensional parameter space; and
displaying results showing the subset of diagnostic parameters and strength of relationship to the one or more key performance indicators;
wherein the in-database processing operation performing feature selection comprises:
determining one or more key performance indicators containing at least one of discrete values and continuous measurements; and
constructing the database statements using a common query language and capabilities of a storage system;
wherein the discrete values and continuous measurements to trace quality issues associated with the complex manufacturing process;
wherein deriving the subset of diagnostic parameters comprises performing a feature selection operation for each of a plurality of selected parameters,
wherein the feature selection operation comprises linear feature selection operations and nonlinear feature selection operations;
wherein the linear feature selection operations and the nonlinear feature selection operations are performed for the discrete values and continuous measurements.

5. The system of claim 4 , wherein the instructions are further configured for:
distributing the at least one database statement across a plurality of nodes of the storage system; and,
executing the at least one database statement at each of the plurality of nodes of the storage system.

6. The system of claim 4 , wherein:
deriving the subset of diagnostic parameters comprises performing a feature selection operation for each of a plurality of key performance indicators.

7. A non-transitory, computer-readable storage medium embodying computer program code for performing in-database operations on parameters associated with complex manufacturing processes, the computer program code comprising computer executable instructions configured for:
presenting an automation interface to a user, automation interface enabling a user to select one or more key performance indicators;
instantiating an in-database processing operation, the in-database processing operation performing feature selection from a high dimensional parameter space, wherein
database statements are executed in parallel to derive a subset of diagnostic parameters from the high dimensional parameter space; and
displaying results showing the subset of diagnostic parameters and strength of relationship to the one or more key performance indicators;
wherein the in-database processing operation performing feature selection comprises:
determining one or more key performance indicators containing at least one of discrete values and continuous measurements; and
constructing the database statements using a common query language and capabilities of a storage system;
wherein the discrete values and continuous measurements trace quality issues associated with the complex manufacturing process;
wherein deriving the subset of diagnostic parameters comprises performing a feature selection operation for each of a plurality of selected parameters;
wherein the feature selection operation comprises linear feature selection operations and nonlinear feature selection operations;
wherein the linear feature selection operations and the nonlinear feature selection operations are performed for the discrete values and continuous measurements.

8. The non-transitory, computer-readable storage medium of claim 7 , wherein the instructions are further configured for:
distributing the at least one database statement across a plurality of nodes of the storage system; and,
executing the at least one database statement at each of the plurality of nodes of the storage system.

9. The non-transitory, computer-readable storage medium of claim 7 , wherein:
deriving the subset of diagnostic parameters comprises performing a feature selection operation for each of a plurality of key performance indicators.

Assignees

• Tibco Software Inc

Inventors

• Hill Thomas
• Rastunkov Vladimir S
• Butler George R

Classifications

• G06F16/2428 Primary

  Query predicate definition using graphical user interfaces, including menus and forms (G06F16/2423 takes precedence) · CPC title