Non-conformance analysis using an associative memory learning agent

• US 9,053,159 B2
• Filed: 02/09/2009
• Issued: 06/09/2015
• Est. Priority Date: 02/09/2009
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Quadracci, Leonard J., Warn, Brian
• Primary Examiner(s): Alam, Hosain
• Assistant Examiner(s): HARPER, ELIYAH STONE
• Application Number:
  US12/368,024
• Publication Number:
  US 20100205212A1
• Time in Patent Office: 2,311 Days
• Field of Search: 707/999.104, 707/776, 707/769
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

According to an embodiment, a non-conformance analysis system may include at least one information storage tool that stores previously generated non-conformance information; a data mining tool that retrieves specific attributes of the previously generated non-conformance information stored in the at least one information storage tool; an associative memory subsystem that is populated with information involving a plurality of entity types, with each entity type including at least one entity, to form an associative memory; and a user input device that enables a user to input a non-conformance query into the associative memory subsystem, that causes the associative memory subsystem to generate all of the entity types and entities that include information useful for investigating the non-conformance query.

Claims

1. A system, comprising:

an associative memory subsystem including a plurality of matrices pertaining to different non-conformances in a platform, each matrix including related entity values and attributes, the subsystem including at least one processor for providing raw, unfiltered correlations between each matrix relative to each of the other matrices; and

a user interface for inputting a free text query to the associative memory subsystem and displaying identified entity values in order of relevance;

wherein the at least one processor of the associative memory subsystem uses the free text query to filter the raw correlations to identify those entity values most strongly correlated with the free text query.

2. The system of claim 1, further comprising a data mining tool for retrieving the attributes and the entity values from historical data about past aircraft non-conformances and provides the attributes and the entity values to said associative memory subsystem.

3. The system of claim 2, wherein the associative memory subsystem ranks the identified entity values in order or relevance.

4. The system of claim 2, further comprising a plurality of additional information tools each in communication with said data mining tool, each one of said additional information tools providing information having different attributes and entity values to said associative memory subsystem.

5. A method comprising:

accessing an associative memory subsystem including a plurality of matrices pertaining to different non-conformances in a platform, each matrix including related entity values and attributes, the subsystem providing raw, unfiltered correlations between each matrix relative to the other matrices;

using a free text query to filter the raw correlations to identify those entity values most strongly correlated with the free text query; and

displaying the identified entity values according to how well the identified entity values are correlated with the free text query.

6. The method of claim 5, further comprising performing finding the attributes and entity values in historical data about past aircraft non-conformances.

7. The method of claim 5, further comprising ranking the identified entity values in order or relevance.

9. The method of claim 5, wherein the nonconformances relate to issues during and after assembly of the platform.

10. The method of claim 9, wherein at least some of the matrices describe a non-conformance using different vernacular.

8. A method comprising:

performing data mining on historical data;

using associative memory to store a plurality of matrices, the matrices pertaining to different aircraft non-conformances, each matrix including related entity values and attributes that were mined from the historical data, the associative memory providing raw, unfiltered correlations between each matrix relative to the other matrices;

using a free text query to filter the raw correlations to identify those entity values most strongly correlated with the free text query; and

displaying the identified entity values in order of relevance.