# US 12,008,592 B1 · Strategic and tactical intelligence in dynamic segmentation

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

- Number: US 12,008,592 B1
- Document ID: US12008592B1
- Status: Granted
- Kind: B1
- Application number: 17/738,495
- Filed: 2022-05-06
- Granted: 2024-06-11
- Earliest claimed: 2021-05-07
- Assignees: Blue Yonder Group, Inc.
- Applicants: Blue Yonder Group, Inc.
- Inventors: Ganesh Muthusamy; Phani Bulusu; Rashid Puthiyapurayil; Abhishek Singh
- Web page: https://patentgrep.com/patent/US12008592B1

## CPC

- G06Q 30/0204: Market segmentation
- G06F 16/215: Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
- G06F 18/2137: based on criteria of topology preservation, e.g. multidimensional scaling or self-organising maps
- G06N 20/00: Machine learning
- G06Q 10/0633: Workflow analysis
- G06Q 10/0637: Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A system and method for performing tactical segmentation including a supply chain network having a tactical segmentation planner, an inventory system, a transportation network, supply chain entities and a computer. The computer performs multi-dimension segmentation on input data by computing feature importance to generate multi-dimensional segments, assigns policy parameters to the supply chain network based on the generated multi-dimensional segments, trains a machine learning model by applying a cyclic boosting process to the standardized features data, where the cyclic boosting process iteratively learns relationships associated with the generated multi-dimensional segments, stores the machine learning model in a database, performs multi-dimension segmentation based on the stored machine learning model, determines whether data drift has occurred in the input data and in response to determining that data drift has occurred, repeats the perform, assign, trains steps, and stores an updated machine learning model in the database.

## Claims

### Claim 1

A system for performing tactical segmentation, comprising:
a supply chain network comprising a tactical segmentation planner, an inventory system, a transportation network and one or more supply chain entities, the strategic segmentation planner further comprising a computer and a database, the computer comprising a memory and a processor, the computer configured to autonomously:
perform multi-dimension segmentation on input data by computing feature importance to generate multi-dimensional segments;
assign policy parameters to the supply chain network based on the generated multi-dimensional segments;
train a machine learning model by applying a cyclic boosting process to the standardized features data, wherein the cyclic boosting process iteratively learns relationships associated with the generated multi-dimensional segments;
store the machine learning model in the database;
perform multi-dimension segmentation based on the stored machine learning model;
determine whether data drift has occurred in the input data; and
in response to determining that data drift has occurred, repeat the perform, assign, and train steps, and store an updated machine learning model in the database.

### Claim 2 (depends on 1)

The system of claim 1, wherein the computer is further configured to:
assign policy parameters to the supply chain network comprising one or more parameters selected from a group consisting of: a minimum order quantity, a maximum order quantity, a discount, a step-size order quantity, and batch quantity rules.

### Claim 3 (depends on 1)

The system of claim 1, wherein the computer is further configured to:
cleanse the input data by:
converting the input data from one data storage format into another data storage format;
copying one or more pre-discovered features stored in the input data into cleansed data; or
removing one or more pre-discovered features stored in the input data.

### Claim 4 (depends on 2)

The system of claim 2, wherein the input data further comprises:
data relating to supply chain entities, supply chain plans, transactions, shipments between supply chain entities, past sales, past demand, purchase data, promotions or events of one or more products.

### Claim 5 (depends on 1)

The system of claim 1, wherein the computer is further configured to:
generate a graphical user interface display visualizing one or more relative importance scores for one or more features.

### Claim 6 (depends on 1)

The system of claim 1, wherein the computer is further configured to:
drop one or more features associated with relative importance scores lower than a defined threshold.

### Claim 7 (depends on 3)

The system of claim 3, wherein cleansing the input data further comprises:
select a representative sample of data; and
perform a dimensionality reduction on the representative sample of data.

### Claim 8

A computer-implemented method for autonomously performing tactical segmentation, comprising:
performing, by a computer comprising a memory and a processor, the computer connected to a database, multi-dimension segmentation on input data by computing feature importance to generate multi-dimensional segments;
assigning, by the computer, policy parameters to the supply chain network based on the generated multi-dimensional segments;
training, by the computer, a machine learning model by applying a cyclic boosting process to the standardized features data, wherein the cyclic boosting process iteratively learns relationships associated with the generated multi-dimensional segments; store the machine learning model in the database;
performing, by the computer, multi-dimension segmentation based on the stored machine learning model;
determining autonomously, by the computer, whether data drift has occurred in the input data; and
in response to autonomously determining that data drift has occurred, repeating, by the computer, the performing, assigning and training steps, and storing an updated machine learning model in the database.

### Claim 9 (depends on 8)

The computer-implemented method of claim 8, further comprising:
assigning policy parameters to the supply chain network comprising one or more parameters selected from a group consisting of: a minimum order quantity, a maximum order quantity, a discount, a step-size order quantity, and batch quantity rules.

### Claim 10 (depends on 8)

The computer-implemented method of claim 8, further comprising:
cleansing, by the computer, the input data by:
converting the input data from one data storage format into another data storage format;
copying one or more pre-discovered features stored in the input data into cleansed data; or
removing one or more pre-discovered features stored in the input data.

### Claim 11 (depends on 9)

The computer-implemented method of claim 9, wherein the input data further comprises:
data relating to supply chain entities, supply chain plans, transactions, shipments between supply chain entities, past sales, past demand, purchase data, promotions or events of one or more products.

### Claim 12 (depends on 8)

The computer-implemented method of claim 8, further comprising:
generating, by the computer, a graphical user interface display visualizing one or more relative importance scores for one or more features.

### Claim 13 (depends on 8)

The computer-implemented method of claim 8, further comprising:
dropping, by the computer, one or more features associated with relative importance scores lower than a defined threshold.

### Claim 14 (depends on 10)

The computer-implemented method of claim 10, wherein cleansing the input data further comprises:
selecting, by the computer, a representative sample of data; and
performing, by the computer, a dimensionality reduction on the representative sample of data.

### Claim 15

A non-transitory computer-readable medium embodied with software for performing strategic segmentation, the software when executed using one or more computers is autonomously configured to:
perform multi-dimension segmentation on input data by computing feature importance to generate multi-dimensional segments;
assign policy parameters to the supply chain network based on the generated multi-dimensional segments;
train a machine learning model by applying a cyclic boosting process to the standardized features data, wherein the cyclic boosting process iteratively learns relationships associated with the generated multi-dimensional segments store the machine learning model in the database;
perform multi-dimension segmentation based on the stored machine learning model;
determine whether data drift has occurred in the input data; and
in response to determining that data drift has occurred, repeat the perform, assign, and train steps, and store an updated machine learning model in the database.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, the software further configured to:
assign policy parameters to the supply chain network comprising one or more parameters selected from a group consisting of: a minimum order quantity, a maximum order quantity, a discount, a step-size order quantity, and batch quantity rules.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, the software further configured to:
cleanse the input data by transforming the amount of data corresponding to the workflow depth by:
converting the input data from one data storage format into another data storage format;
copying one or more pre-discovered features stored in the input data into cleansed data; or
removing one or more pre-discovered features stored in the input data.

### Claim 18 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein the input data further comprises:
data relating to supply chain entities, supply chain plans, transactions, shipments between supply chain entities, past sales, past demand, purchase data, promotions or events of one or more products.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, the software further configured to:
generate a graphical user interface display visualizing one or more relative importance scores for one or more features.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, the software further configured to:
drop one or more features associated with relative importance scores lower than a defined threshold.