# US 2020/0394257 A1 · Predictive query processing for complex system lifecycle management

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0394257 A1
- Document ID: US20200394257A1
- Status: Published application
- Kind: A1
- Application number: 16/443,077
- Filed: 2019-06-17
- Published: 2020-12-17
- Earliest claimed: 2019-06-17
- Assignees: The Boeing Company
- Applicants: The Boeing Company
- Inventors: Robert SANTOSO; Keith Pete Cai; Jay J. Patel
- Web page: https://patentgrep.com/patent/US20200394257A1

## CPC

- G06F 40/157: using dictionaries or tables
- G06F 16/90324: {using system suggestions}
- G06F 16/90328: {using search space presentation or visualization, e.g. category or range presentation and selection}
- G06F 16/90335: {Query processing}
- G06F 16/9035: Filtering based on additional data, e.g. user or group profiles
- G06F 16/93: Document management systems
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

The present disclosure provides for predictive query processing for complex system lifecycle management by identifying a seed document including natural language text describing an issue with a complex system; creating a synthesized document for the seed document by: removing portions of the seed document determined to satisfy filtering rules; identifying a first term set included in the natural language text that map to terminology identified in a data dictionary; extracting term-order data based on locations of the first term set in the natural language text; and including the first term set and the term-order data in the synthesized document; identifying, from a corpus of historic electronic documents, a first document set that are related to the seed document based on the term-order data included in the synthesized document; and outputting at least a portion of the first set of historic electronic documents.

## Claims

### Claim 1

A method, comprising:
identifying a seed electronic document including natural language text describing an issue with a complex system;
creating a synthesized document for the seed electronic document by:
removing a portion of the seed electronic document that is determined to satisfy a predefined filtering rule;
identifying a first set of terms included in the natural language text that map to terminology identified in a data dictionary;
extracting term-order data based on locations of the first set of terms in the natural language text; and
including the first set of terms and the term-order data in the synthesized document;
identifying, from a corpus of historic electronic documents, a first set of historic electronic documents that are related to the seed electronic document based on the term-order data included in the synthesized document; and
outputting at least a portion of the first set of historic electronic documents.

### Claim 2 (depends on 1)

The method of claim 1, wherein synthesizing the seed electronic document further comprises categorizing terms included in the first set of terms; and
wherein extracting the term-order data includes determining relationships between the terms based on categories assigned to the terms and a relative order of the terms in the natural language text.

### Claim 3 (depends on 2)

The method of claim 2, wherein the terms are categorized into one or more of the categories, and wherein the categories include:
locational terms;
temporal terms;
part identity terms;
standard identity terms;
issue subject terms;
solution identity terms;
action predicate terms; and
modifier terms.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
in response to receiving user selection of a given historic electronic document of the first set of historic electronic documents, updating a machine learning model used to extract the term-order data based on the user selection.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
analyzing the historic electronic documents;
identifying an additional term included in the historic electronic documents at a predefined frequency of use; and
adding the additional term to the terminology stored in the data dictionary.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
identifying a second set of terms included in the natural language text that map to a predefined format matching rule; and
including the second set of terms in the synthesized document, wherein extracting the term-order data is further based on locations of the second set of terms in the natural language text.

### Claim 7 (depends on 6)

The method of claim 6, wherein the predefined format matching rule identifies one of a part number or a standard.

### Claim 8 (depends on 1)

The method of claim 1, further comprising: ranking the first set of historic electronic documents for display on a requesting device based on a relevancy score assigned according to the term-order data.

### Claim 9 (depends on 8)

The method of claim 8, further comprising: ranking a second set of historic electronic documents for display on the requesting device in combination with the first set of historic electronic documents based on a relevancy score assigned according to the term-order data.

### Claim 10 (depends on 1)

The method of claim 1, wherein identifying the first set of historic electronic documents that are related to the seed electronic document further comprises:
clustering the historic electronic documents based on historic term-order data associated with the historic electronic documents;
determining which clusters of the historic electronic documents the seed electronic document belongs to based on the term-order data; and
categorizing the historic electronic documents that belong to the clusters that the seed electronic document is determined to belong to as match electronic documents to the seed electronic document, wherein match electronic documents are determined to be related to the seed electronic document.

### Claim 11

A system, comprising:
a processor; and
a memory storage device, including instructions that when performed by the processor perform an operation comprising:
identifying a seed electronic document including natural language text describing an issue with a complex system;
creating a synthesized document for the seed electronic document by:
removing a portion of the seed electronic document that is determined to satisfy a predefined filtering rule;
identifying a first set of terms included in the natural language text that map to terminology identified in a data dictionary;
extracting term-order data based on locations of the first set of terms in the natural language text; and
including the first set of terms and the term-order data in the synthesized document;
identifying, from a corpus of historic electronic documents, a first set of historic electronic documents that are related to the seed electronic document based on the term-order data included in the synthesized document; and
outputting at least a portion of the first set of historic electronic documents.

### Claim 12 (depends on 11)

The system of claim 11, wherein the operation further comprises:
categorizing terms included in the first set of terms; and
wherein extracting the term-order data includes determining relationships between the terms based on categories assigned to the terms and a relative order of the terms in the natural language text.

### Claim 13 (depends on 11)

The system of claim 11, wherein the operation further comprises:
in response to receiving user selection of a given historic electronic document of the first set of historic electronic documents, updating a machine learning model used to extract the term-order data based on the user selection.

### Claim 14 (depends on 11)

The system of claim 11, wherein the operation further comprises:
ranking the first set of historic electronic documents for display on a requesting device based on a relevancy score assigned according to the term-order data.

### Claim 15 (depends on 11)

The system of claim 11, wherein identifying the first set of historic electronic documents that are related to the synthesized document further comprises:
clustering the historic electronic documents based on historic term-order data associated with the historic electronic documents;
determining which clusters of the historic electronic documents the seed electronic document belongs to based on the term-order data; and
categorizing the historic electronic documents that belong to the clusters that the seed electronic document is determined to belong to as match electronic documents to the seed electronic document, wherein match electronic documents are determined to be related to the seed electronic document.

### Claim 16

A computer readable storage medium including instructions that when performed by a computer processor enable the computer processor to:
identify a seed electronic document including natural language text describing an issue with a complex system;
create a synthesized document, for the seed electronic document wherein to create the synthesized document the instructions further enable the computer processor to:
remove a portion of the seed electronic document that is determined to satisfy a predefined filtering rule;
identify a first set of terms included in the natural language text that map to terminology identified in a data dictionary;
extract term-order data based on locations of the first set of terms in the natural language text; and
include the first set of terms and the term-order data in the synthesized document;
identify, from a corpus of historic electronic documents, a first set of historic electronic documents that are related to the seed electronic document based on the term-order data included in the synthesized document; and
output at least a portion of the first set of historic electronic documents.

### Claim 17 (depends on 16)

The computer readable storage medium of claim 16, wherein the instructions, when performed, further enable to processor to:
categorize terms included in the first set of terms; and
wherein extracting the term-order data includes determining relationships between the terms based on categories assigned to the terms and a relative order of the terms in the natural language text.

### Claim 18 (depends on 16)

The computer readable storage medium of claim 16, wherein the instructions, when performed, further enable to processor to:
in response to receiving user selection of a given historic electronic document of the first set of historic electronic documents, update a machine learning model used to extract the term-order data based on the user selection.

### Claim 19 (depends on 16)

The computer readable storage medium of claim 16, wherein the instructions, when performed, further enable to processor to:
rank the first set of historic electronic documents for display on a requesting device based on a relevancy score assigned according to the term-order data.

### Claim 20 (depends on 16)

The computer readable storage medium of claim 16, wherein to identify the first set of historic electronic documents that are related to the seed electronic document, the instructions further enable the computer processor to:
cluster the historic electronic documents based on historic term-order data associated with the historic electronic documents;
determine which clusters of the historic electronic documents the seed electronic document belongs to based on the term-order data; and
categorize the historic electronic documents that belong to the clusters that the seed electronic document is determined to belong to as match electronic documents to the seed electronic document, wherein match electronic documents are determined to be related to the seed electronic document.
