# US 10,373,102 B2 · System and method to incorporate node fulfillment capacity and capacity utilization in balancing fulfillment load across retail supply networks

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

- Number: US 10,373,102 B2
- Document ID: US10373102B2
- Status: Granted
- Kind: B2
- Application number: 15/087,569
- Filed: 2016-03-31
- Published: 2017-07-20
- Granted: 2019-08-06
- Earliest claimed: 2016-01-16
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Ajay A. Deshpande; Saurabh Gupta; Arun Hampapur; Alan J. King; Ali Koc; Yingjie Li; Xuan Liu; Christopher S. Milite; Brian L. Quanz; Chek Keong Tan; Dahai Xing; Xiaobo Zheng
- Web page: https://patentgrep.com/patent/US10373102B2

## CPC

- G06Q 10/08345: {Pricing}
- G06F 3/0482: Interaction with lists of selectable items, e.g. menus
- G06F 3/04847: Interaction techniques to control parameter settings, e.g. interaction with sliders or dials
- G06F 16/148: {File search processing}
- G06F 16/1734: {Details of monitoring file system events, e.g. by the use of hooks, filter drivers, logs}
- G06F 16/183: {Provision of network file services by network file servers, e.g. by using NFS, CIFS (network file access protocols H04L67/1097)}
- G06F 16/1844: {Management specifically adapted to replicated file systems}
- G06F 16/2365: {Ensuring data consistency and integrity}
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 5/04: Inference or reasoning models
- G06N 5/045: Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
- G06N 20/00: Machine learning
- G06Q 10/06315: {Needs-based resource requirements planning or analysis}
- G06Q 10/0633: Workflow analysis
- G06Q 10/06375: {Prediction of business process outcome or impact based on a proposed change}
- G06Q 10/083: Shipping
- G06Q 10/0833: Tracking
- G06Q 10/0838: {Historical data}
- G06Q 10/0843: {using forecasting or optimisation}
- G06Q 10/087: Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q 10/0875: Itemisation or classification of parts, supplies or services, e.g. bill of materials
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06Q 30/0206: {Price or cost determination based on market factors}
- G06Q 30/0283: Price estimation or determination
- G06Q 30/0284: {Time or distance, e.g. usage of parking meters or taximeters}
- G06Q 30/0635: {replenishment orders; recurring orders}
- H04L 43/0882: Utilisation of link capacity
- H04L 43/16: Threshold monitoring
- G06Q 10/08744: {by distributed inventory management}
- H04L 43/0876: Network utilisation, e.g. volume of load or congestion level
- 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
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A method and system for evaluating node fulfillment capacity in node order assignment. The method includes receiving a current order for node order assignment. The method also includes retrieving data of each node from a plurality of nodes, the retrieved data comprising current capacity utilization, capacity of a current day and capacity of a future day. The method then includes determining a probability of backlog on an expected ship date of each node, the probability of backlog being based on the retrieved current capacity utilization. Further, the method includes automatically converting the probability of backlog, backlog cost, and labor cost of each node into a capacity utilization cost of the each node using a capacity utilization cost model defining a set of predetermined capacity utilization threshold values. Then, the method includes automatically calculating a fulfillment cost of each node of the current order by adding a plurality of costs.

## Claims

### Claim 1

A computer implemented method for evaluating node fulfillment capacity in node order assignment, comprising:
receiving a current order for node order assignment;
retrieving data of each node from a plurality of nodes, the retrieved data of each node comprising current capacity utilization;
determining a probability of backlog on an expected ship date of each node of the plurality of nodes, the probability of backlog being based on the retrieved current capacity utilization;
automatically converting the probability of backlog, backlog cost, and labor cost of each node of the plurality of nodes into a capacity utilization cost of each node of the plurality of nodes using a capacity utilization cost model defining a set of predetermined capacity utilization threshold values;
automatically calculating a fulfillment cost of each node of the plurality of nodes of the current order by adding a plurality of costs, the plurality of costs comprising shipping cost and the capacity utilization cost;
identifying one or more nodes from the plurality of nodes of the current order with the lowest fulfillment cost; and
automatically generating a node order assignment assigning the current order to one of the one or more nodes of the plurality of nodes with the lowest fulfillment cost.

### Claim 2 (depends on 1)

The method of claim 1, wherein the retrieved data of each node further comprising backlog data, capacity of a current day, and capacity of a future day.

### Claim 3 (depends on 2)

The method of claim 2, further comprising automatically calculating an actual capacity utilization on the expected ship date of each node of the plurality of nodes, the actual capacity utilization being based on the retrieved current capacity utilization, the capacity of a current day, the capacity of a future day, and the backlog data and wherein the capacity utilization cost model further uses the actual capacity utilization in determining the probability of backlog.

### Claim 4 (depends on 3)

The method of claim 3, wherein the actual capacity utilization is calculated by adding the result of the backlog divided by the capacity of a current day to the current capacity utilization, when the capacity of a current day is enough to fulfill the current order, and the actual capacity utilization is calculated by backlog on an expected ship date divided by the capacity of the expected ship day, the backlog on an expected ship date being calculated by adding the result of the current capacity utilization multiplied by the capacity of a current day to the backlog, and subtracting the result of the capacity of each day before the expected ship date multiplied by the backlog days of the current order before the expected ship date, when the capacity of a current day is not enough to fulfill the current order.

### Claim 5 (depends on 1)

The method of claim 1, wherein the probability of backlog is calculated by historical data of backlogged orders at the current capacity utilization divided by historical data of total orders at the current capacity utilization.

### Claim 6 (depends on 1)

The method of claim 1, wherein the probability of backlog is further based on hours left in the current day.

### Claim 7 (depends on 1)

The method of claim 1, further comprising determining a number of days of backlog on an expected ship date of each node of the plurality of nodes, the number of days of backlog being based on the retrieved current capacity utilization and wherein the capacity utilization cost model further considers the number of days of backlog in determining the capacity utilization cost of each node of the plurality of nodes.

### Claim 8

A computer system for determining node order assignment, comprising:
a memory; and
a processor configured to:
receiving a current order for node order assignment;
retrieving data of each node from a plurality of nodes, the retrieved data of each node comprising current capacity utilization;
determining a probability of backlog on an expected ship date of each node of the plurality of nodes, the probability of backlog being based on the retrieved current capacity utilization;
automatically converting the probability of backlog, backlog cost, and labor cost of each node of the plurality of nodes into a capacity utilization cost of each node of the plurality of nodes using a capacity utilization cost model defining a set of predetermined capacity utilization threshold values;
automatically calculating a fulfillment cost of each node of the plurality of nodes of the current order by adding a plurality of costs, the plurality of costs comprising shipping cost and the capacity utilization cost;
identifying one or more nodes from the plurality of nodes of the current order with the lowest fulfillment cost; and
automatically generating a node order assignment assigning the current order to one of the one or more nodes of the plurality of nodes with the lowest fulfillment cost.

### Claim 9 (depends on 8)

The computer system of claim 8, wherein the retrieved data further comprising backlog data, capacity of a current day, and capacity of a future day and further comprising automatically calculating an actual capacity utilization on the expected ship date of each node of the plurality of nodes, the actual capacity utilization being based on the retrieved current capacity utilization, the capacity of a current day, the capacity of a future day, and the backlog data and wherein the capacity utilization cost model further uses the actual capacity utilization in determining the probability of backlog.

### Claim 10 (depends on 9)

The computer system of claim 9, wherein the actual capacity utilization is calculated by adding the result of the backlog divided by the capacity of a current day to the current capacity utilization, when the capacity of a current day is enough to fulfill the current order, and the actual capacity utilization is calculated by backlog on an expected ship date divided by the capacity of the expected ship day, the backlog on an expected ship date being calculated by adding the result of the current capacity utilization multiplied by the capacity of a current day to the backlog, and subtracting the result of the capacity of each day before the expected ship date multiplied by the backlog days of the current order before the expected ship date, when the capacity of a current day is not enough to fulfill the current order.

### Claim 11 (depends on 8)

The computer system of claim 8, wherein the probability of backlog is calculated by historical data of backlogged orders at the current capacity utilization divided by historical data of total orders at the current capacity utilization.

### Claim 12 (depends on 8)

The computer system of claim 8, wherein the probability of backlog is further based on hours left in the current day.

### Claim 13 (depends on 8)

The computer system of claim 8, further comprising determining a number of days of backlog on an expected ship date of each node of the plurality of nodes, the number of days of backlog being based on the retrieved current capacity utilization and wherein the capacity utilization cost model further considers the number of days of backlog in determining the capacity utilization cost of each node of the plurality of nodes.

### Claim 14 (depends on 8)

The computer system of claim 8, wherein the capacity of a current day is collected from a planned daily capacity database, the current capacity utilization is based on a node unit assignment database, the backlog data is collected from a backlog database, the backlog cost is collected from a backlog cost database, the labor cost is collected from a labor cost database, and the predetermined capacity utilization threshold is collected from a capacity utilization target range database.

### Claim 15

A non-transitory article of manufacture tangibly embodying computer readable instructions, which when implemented, cause a computer to perform the steps of a method for determining node order assignment, comprising:
receiving a current order for node order assignment;
retrieving data of each node from a plurality of nodes, the retrieved data of each node comprising current capacity utilization;
determining a probability of backlog on an expected ship date of each node of the plurality of nodes, the probability of backlog being based on the retrieved current capacity utilization;
automatically converting the probability of backlog, backlog cost, and labor cost of each node of the plurality of nodes into a capacity utilization cost of each node of the plurality of nodes using a capacity utilization cost model defining a set of predetermined capacity utilization threshold values;
automatically calculating a fulfillment cost of each node of the plurality of nodes of the current order by adding a plurality of costs, the plurality of costs comprising shipping cost and the capacity utilization cost;
identifying one or more nodes from the plurality of nodes of the current order with the lowest fulfillment cost; and
automatically generating a node order assignment assigning the current order to one of the one or more nodes of the plurality of nodes with the lowest fulfillment cost.

### Claim 16 (depends on 15)

A non-transitory article of manufacture of claim 15, wherein the retrieved data further comprising backlog data, capacity of a current day, and capacity of a future day and further comprising automatically calculating an actual capacity utilization on the expected ship date of each node of the plurality of nodes, the actual capacity utilization being based on the retrieved current capacity utilization, the capacity of a current day, the capacity of a future day and the backlog data and wherein the capacity utilization cost model further uses the actual capacity utilization in determining the probability of backlog.

### Claim 17 (depends on 16)

A non-transitory article of manufacture of claim 16, wherein the actual capacity utilization is calculated by adding the result of the backlog divided by the capacity of a current day to the current capacity utilization, when the capacity of a current day is enough to fulfill the current order, and the actual capacity utilization is calculated by backlog on an expected ship date divided by the capacity of the expected ship day, the backlog on an expected ship date being calculated by adding the result of the current capacity utilization multiplied by the capacity of a current day to the backlog, and subtracting the result of the capacity of each day before the expected ship date multiplied by the backlog days of the current order before the expected ship date, when the capacity of a current day is not enough to fulfill the current order.

### Claim 18 (depends on 15)

A non-transitory article of manufacture of claim 15, wherein the probability of backlog is calculated by historical data of backlogged orders at the current capacity utilization divided by historical data of total orders at the current capacity utilization.

### Claim 19 (depends on 15)

A non-transitory article of manufacture of claim 15, wherein the probability of backlog is further based on hours left in the current day.

### Claim 20 (depends on 15)

A non-transitory article of manufacture of claim 15, further comprising determining a number of days of backlog on an expected ship date of each node of the plurality of nodes, the number of days of backlog being based on the retrieved current capacity utilization and wherein the capacity utilization cost model further considers the number of days of backlog in determining the capacity utilization cost of each node of the plurality of nodes.