# US 10,503,480 B2 · Correlation based instruments discovery

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

- Number: US 10,503,480 B2
- Document ID: US10503480B2
- Status: Granted
- Kind: B2
- Application number: 15/303,661
- Filed: 2014-04-30
- Published: 2017-02-09
- Granted: 2019-12-10
- Earliest claimed: 2014-04-30
- Assignees: Ent. Services Development Corporation LP
- Applicants: Ent. Services Development Corporation LP; Vinu Pillai
- Inventors: Vinu Pillai
- Web page: https://patentgrep.com/patent/US10503480B2

## CPC

- G06Q 10/10: Office automation; Time management
- G06F 8/20: Software design
- G06F 8/35: model driven
- G06F 16/9024: {Graphs; Linked lists (G06F16/9027 takes precedence)}
- G06F 40/237: Lexical tools
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

According to an example, correlation based instruments discovery may include extracting text from content identified as being related to instruments for implementing machine readable instructions based products. An identified content object graph model having subjects and features may be generated. A product specifications object graph model having subjects and features may be generated based upon product specifications related to a machine readable instructions based product that is to be implemented. The subjects and features in the identified content object graph model that correspond to the subjects and features in the product specifications object graph model may be correlated and scored. Subjects and features from the identified content object graph model that include respective highest scores for matching subjects and features from the product specifications object graph model may be selected to identify a subset of the content that is related to instruments for implementing the machine readable instructions based product.

## Claims

### Claim 1

A method for correlation based instruments discovery, the method comprising:
extracting text from content identified as being related to instruments for implementing machine readable instructions based products;
generating, by a processor, an identified content object graph model having first subjects and features, the first subjects and features being extracted from the text of the content;
generating a product specifications object graph model based upon product specifications related to a machine readable instructions based product that is to be implemented, the product specifications object graph model having second subjects and features;
correlating the first subjects and features in the identified content object graph model that correspond to the second subjects and features in the product specifications object graph model, wherein the correlating includes generating a word arrangement of the first and second subjects and features;
scoring correlations produced by the correlating, wherein the scoring includes calculating distances between words in the word arrangement; and
selecting the first subjects and features from the identified content object graph model that include respective highest scores for matching the second subjects and features from the product specifications object graph model to identify a subset of the content that is related to instruments for implementing the machine readable instructions based product.

### Claim 2 (depends on 1)

The method of claim 1, wherein extracting text from the content identified as being related to the instruments for implementing machine readable instructions based products further comprises:
using a crawler to extract the text from the content identified as being related to the instruments for implementing machine readable instructions based products.

### Claim 3 (depends on 1)

The method of claim 1, wherein extracting text from the content identified as being related to the instruments for implementing machine readable instructions based products further comprises:
extracting text from the content identified as being related to the instruments for implementing machine readable instructions based products from internal enterprise sources, external enterprise sources, and social media sources.

### Claim 4 (depends on 3)

The method of claim 3, wherein the internal enterprise sources include sources related to at least one of instrument specifications, instrument inventories, and product assets.

### Claim 5 (depends on 3)

The method of claim 3, wherein the external enterprise sources include sources related to at least one of product specification websites, vendor portals, product documentation, product forums, framework specifications, and knowledge management websites.

### Claim 6 (depends on 3)

The method of claim 3, wherein the social media sources include sources related to at least one of blogs, forums, and knowledge management systems.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
performing subjectivity and feature extraction on the extracted text from the identified content to generate the identified content object graph model having the first subjects and features.

### Claim 8 (depends on 7)

The method of claim 7, wherein performing the subjectivity and feature extraction on the extracted text from the identified content to generate the identified content object graph model having the first subjects and features further comprises:
performing implicit and explicit feature extraction on the extracted text from the identified content to generate the identified content object graph model having the first subjects and features.

### Claim 9 (depends on 1)

The method of claim 1, further comprising:
performing subjectivity and feature extraction on text from the product specifications to generate the product specifications object graph model having the second subjects and features.

### Claim 10 (depends on 9)

The method of claim 9, wherein performing the subjectivity and feature extraction on text from the product specifications to generate the product specifications object graph model having the second subjects and features further comprises:
performing implicit and explicit feature extraction on the text from the product specifications to generate the product specifications object graph model having the second subjects and features.

### Claim 11 (depends on 1)

The method of claim 1, wherein scoring correlations of the first subjects and features in the identified content object graph model that correspond to the second subjects and features in the product specifications object graph model further comprises:
determining a degree of match between the first subjects and features in the identified content object graph model and the second subjects and features in the product specifications object graph model.

### Claim 12 (depends on 1)

The method of claim 1, wherein the identified content object graph model links the first subjects and features from the extracted text from the identified content.

### Claim 13

A correlation based instruments discovery apparatus comprising:
a processor; and
a memory storing machine readable instructions that when executed by the processor cause the processor to:
identify content related to instruments for implementing computer products from internal enterprise sources, external enterprise sources, and social media sources;
extract text from the identified content;
perform subjectivity, and implicit and explicit feature extraction on the extracted text from the identified content to generate an identified content object graph model;
receive product specifications related to a computer product that is to be implemented;
extract text from the product specifications;
perform subjectivity, and implicit and explicit feature extraction on the text from the product specifications to generate a product specifications object graph model;
identify first subjects and features in the identified content object graph model
that correspond to second subjects and features in the product specifications object graph model;
correlate the first subjects and features in the identified content object graph model to the second subjects and features in the product specifications object graph model, wherein the correlate includes to generate a word arrangement of the first and second subjects and features;
score correlations produced by the correlating, wherein the score correlations includes to calculate distances between words in the word arrangement; and
select the first subjects and features from the identified content object graph model that include respective predetermined scores for matching the second subjects and features from the product specifications object graph model to identify a subset of the identified content that is related to instruments for implementing the computer product.

### Claim 14 (depends on 13)

The correlation based instruments discovery apparatus according to claim 13, wherein the respective predetermined scores represent the highest scores.

### Claim 15

A non-transitory computer readable medium having stored thereon machine readable instructions to provide correlation based instruments discovery, the machine readable instructions, when executed, cause a processor to:
identify content related to instruments for implementing computer products from internal enterprise sources, external enterprise sources, and social media sources;
extract text from the identified content;
perform, by a processor, subjectivity, and implicit and explicit feature extraction on the extracted text from the identified content to generate an identified content object graph model;
receive product specifications related to a computer product that is to be implemented;
extract text from the product specifications;
perform subjectivity, and implicit and explicit feature extraction on the text from the product specifications to generate a product specifications object graph model;
identify first subjects and features in the identified content object graph model that correspond to second subjects and features in the product specifications object graph model;
correlate the first subjects and features in the identified content object graph model to the second subjects and features in the product specifications object graph model, wherein the correlate includes to generate a word arrangement of the first and second subjects and features;
score correlations produced by the correlate, wherein the score includes determining a degree of match between the first subjects and features in the identified content object graph model and the second subjects and features in the product specifications object graph model, and wherein the score correlations includes to calculate distances between words in the word arrangement; and
select the first subjects and features from the identified content object graph model that include respective highest scores for matching the second subjects and features from the product specifications object graph model to identify a subset of the identified content that is related to instruments for implementing the computer product.