Estimating demand for a supply chain according to order lead time

• US 7,827,049 B2
• Filed: 04/29/2004
• Issued: 11/02/2010
• Est. Priority Date: 05/12/2003
• Status: Active Grant

• Current Assignee: Blue Yonder Group, Inc. (Panasonic Holdings Corporation)
• Original Assignee: i2 Technologies US Incorporated (Panasonic Holdings Corporation)
• Inventors: Dogan, Koray, Raman, Ramesh, Najmi, Adeel
• Primary Examiner(s): Boswell; Beth V
• Assistant Examiner(s): Fleischer; Mark A
• Application Number:
  US10/836,002
• Publication Number:
  US 20040230473A1
• Time in Patent Office: 2,378 Days
• Field of Search: 705/10, 705/7
• US Class Current: 705/7.31
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/063 Operations research, analysis or management
• CPC Class Codes: G06Q 10/06315 Needs-based resource requirements planning or analysis
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities

Abstract

In one embodiment, estimating demand for a supply chain includes accessing a probability distribution for expected order lead time of the supply chain. The supply chain has nodes including a starting node and an ending node and a path from the starting node to the ending node. The probability distribution for expected order lead time describes ending node demand for the ending node versus order lead time. The path is divided into order lead time segments, and the order lead time segments are associated with the probability distribution for expected order lead time by associating each order lead home segment with a corresponding order lead time range of the probability distribution for expected order lead time. A demand percentage is estimated for each order lead time segment in accordance with the probability distribution for expected order lead time in order to estimate demand for the supply chain. Each demand percentage describes a percentage of a total ending node demand associated with the corresponding order lead time segment.

Claims

1. A computer-implemented method estimating demand for a supply chain, comprising:

generating, using a computer, a probability distribution of order lead time based on an order lead time profile of the supply chain comprising a plurality of nodes including a starting node and ending node and a path from the starting node to the ending node, the probability distribution of order lead time describing ending node demand of the ending node;

dividing, using the computer, the path into a plurality of order lead time segments by establishing a plurality of cumulative cycle times of the plurality of nodes, each cumulative cycle time comprising a time difference between a time an item arrives at the corresponding node and a time the item is available to leave the ending node considering all required processing cycle times;

associating, by the computer, the plurality of order lead time segments with the probability distribution of order lead time; and

determining, using the computer, a demand percentage of each order lead time segment in accordance with a range of endpoints of each order lead time segment in order to estimate demand of the supply chain, each demand percentage describing a percentage of a total ending node demand associated with the corresponding order lead time segment.

2. The method of claim 1, further comprising:

generating a plurality of probability distributions of order lead time options, each probability distribution of order lead time option associated with one of a plurality of categories;

identifying one of the plurality of categories that corresponds to a customer of the supply chain; and

selecting a probability distribution of order lead time option associated with the identified category as the probability distribution of order lead time.

3. The method of claim 1, further comprising modifying the probability distribution of order lead time to reflect a predicted change of ending node demand.

4. The method of claim 1, wherein dividing the path into the plurality of order lead time segments comprises:

determining an order lead time segment comprising a difference between a first cumulative cycle time of a first node and a second cumulative cycle time of a second node.

5. The method of claim 1, wherein determining the demand percentage of each order lead time segment in accordance with the probability distribution of order lead time in order to estimate demand of the supply chain comprises:

selecting an order lead time segment defined by a first point and a second point;

identifying a first ending node demand corresponding to the first point according to the probability distribution of order lead time;

identifying a second ending node demand corresponding to the second point according to the probability distribution of order lead time; and

calculating a demand percentage of the order lead time segment according to the first ending node demand and the second ending node demand.

6. The method of claim 1, further comprising calculating an inventory at each node of the plurality of nodes according to the demand percentages of the plurality of nodes.

7. The method of claim 1, further comprising calculating an inventory at each node of the plurality of nodes according to the demand percentages of the plurality of nodes by repeating the following of at least a subset of the plurality of nodes:

selecting a node of the subset of the plurality of nodes;

establishing the demand percentage of the order lead time segment associated with the selected node; and

determining an inventory of the selected node that satisfies the demand percentage.

8. A system of estimating demand of a supply chain, comprising:

a database configured to store a probability distribution of order lead time based on an order lead time profile of the supply chain comprising a plurality of nodes including a starting node and an ending node and a path from the starting node to the ending node, the probability distribution of order lead time describing ending node demand of the ending node versus order lead time; and

a computer system coupled with the database and configured to;

divide the path into a plurality of order lead time segments by establishing a plurality of cumulative cycle times of the plurality of nodes, each cumulative cycle time comprising a time difference between a time an item arrives at the corresponding node and a time the item is available to leave the ending node considering all required processing cycle times;

associate the plurality of order lead time segments with the probability distribution of order lead time; and

determine a demand percentage of each order lead time segment in accordance with a range of endpoints of each order lead time segment in order to estimate demand of the supply chain, each demand percentage describing a percentage of a total ending node demand associated with the corresponding order lead time segment.

9. The system of claim 8, the computer system further configured to:

generate a plurality of probability distributions of order lead time options, each probability distribution of order lead time option associated with one of a plurality of categories;

identify one of the plurality of categories that corresponds to a customer of the supply chain; and

select a probability distribution of order lead time option associated with the identified category as the probability distribution of order lead time.

10. The system of claim 8, the computer system further configured to modify the probability distribution of order lead time to reflect a predicted change of ending node demand.

11. The system of claim 8, the computer system further configured to divide the path into the plurality of order lead time segments by:

determining an order lead time segment comprising a difference between a first cumulative cycle time of a first node and a second cumulative cycle time of a second node.

12. The system of claim 8, the computer system further configured to determine the demand percentage of each order lead time segment in accordance with the probability distribution of order lead time in order to estimate demand of the supply chain by:

selecting an order lead time segment defined by a first point and a second point;

identifying a first ending node demand corresponding to the first point according to the probability distribution of order lead time;

identifying a second ending node demand corresponding to the second point according to the probability distribution of order lead time; and

calculating a demand percentage of the order lead time segment according to the first ending node demand and the second ending node demand.

13. The system of claim 8, the computer system further configured to calculate an inventory at each node of the plurality of nodes according to the demand percentages of the plurality of nodes.

14. The system of claim 8, the computer system further configured to calculate an inventory at each node of the plurality of nodes according to the demand percentages of the plurality of nodes by repeating the following of at least a subset of the plurality of nodes:

selecting a node of the subset of the plurality of nodes;

establishing the demand percentage of the order lead time segment associated with the selected node; and

determining an inventory of the selected node that satisfies the demand percentage.

15. A computer-readable non-transitory medium embodied with software for estimating demand of a supply chain, the software when executed using a computer is configured to:

generate a probability distribution of order lead time based on an order lead time profile of the supply chain comprising a plurality of nodes including a starting node and an ending node and a path from the starting node to the ending node, the probability distribution of order lead time describing ending node demand of the ending node versus order lead time;

divide the path into a plurality of order lead time segments by establishing a plurality of cumulative cycle times of the plurality of nodes, each cumulative cycle time comprising a time difference between a time an item arrives at the corresponding node and a time the item is available to leave the ending node considering all required processing cycle times;

associate the plurality of order lead time segments with the probability distribution of order lead time; and

determine a demand percentage of each order lead time segment in accordance with a range of each order lead time segment in order to estimate demand of the supply chain, each demand percentage describing a percentage of a total ending node demand associated with the corresponding order lead time segment.

16. The computer-readable non-transitory medium of claim 15, wherein the software is further configured to:

generate a plurality of probability distributions of order lead time options, each probability distribution of order lead time option associated with one of a plurality of categories;

identify one of the plurality of categories that corresponds to a customer of the supply chain; and

select a probability distribution of order lead time option associated with the identified category as the probability distribution of order lead time.

17. The software computer-readable non-transitory medium of claim 15, wherein the software is further configured to modify the probability distribution of order lead time to reflect a predicted change of ending node demand.

18. The computer-readable non-transitory medium of claim 15, wherein the software is configured to divide the path into the plurality of order lead time segments by:

determining an order lead time segment comprising a difference between a first cumulative cycle time of a first node and a second cumulative cycle time of a second node.

19. The computer-readable non-transitory medium of claim 15, wherein the software is further configured to determine the demand percentage of each order lead time segment in accordance with the probability distribution of order lead time in order to estimate demand of the supply chain by:

selecting an order lead time segment defined by a first point and a second point;

identifying a first ending node demand corresponding to the first point according to the probability distribution of order lead time;

identifying a second ending node demand corresponding to the second point according to the probability distribution of order lead time; and

calculating a demand percentage of the order lead time segment according to the first ending node demand and the second ending node demand.

20. The computer-readable non-transitory medium of claim 15, wherein the software is further configured to calculate an inventory at each node of the plurality of nodes according to the demand percentages of the plurality of nodes.

21. The computer-readable non-transitory medium of claim 15, wherein the software is further configured to calculate an inventory at each node of the plurality of nodes according to the demand percentages of the plurality of nodes by repeating the following of at least a subset of the plurality of nodes:

selecting a node of the subset of the plurality of nodes;

establishing the demand percentage of the order lead time segment associated with the selected node; and

determining an inventory of the selected node that satisfies the demand percentage.

22. A system of estimating demand of a supply chain, comprising:

means for generating a probability distribution of order lead time based on an order lead time profile of the supply chain comprising a plurality of nodes including a starting node and an ending node and a path from the starting node to the ending node, the probability distribution of order lead time describing ending node demand of the ending node versus order lead time, the probability distribution of order lead time generated from an order lead time profile;

means for dividing the path into a plurality of order lead time segments by establishing a plurality of cumulative cycle times of the plurality of nodes, each cumulative cycle time comprising a time difference between a time an item arrives at the corresponding node and a time the item is available to leave the ending node considering all required processing cycle times;

means for associating the plurality of order lead time segments with the probability distribution of order lead time; and

means for determining a demand percentage of each order lead time segment in accordance with a range of each order lead time segment in order to estimate demand of the supply chain, each demand percentage describing a percentage of a total ending node demand associated with the corresponding order lead time segment.

23. A computer-implemented method estimating demand of a supply chain, comprising:

accessing, by a computer, a description of a supply chain comprising a plurality of nodes including a starting node and an ending node and a path from the starting node to the ending node;

generating, by the computer, a plurality of probability distributions of order lead time options, each probability distribution of order lead time option associated with one of a plurality of categories;

identifying, by the computer, one of the plurality of categories that corresponds to a customer of the supply chain;

selecting, by the computer, a probability distribution of order lead time option associated with the identified category as a probability distribution of order lead time, the probability distribution of order lead time describing ending node demand of the ending node of the supply chain versus order lead time;

modifying, by the computer, the probability distribution of order lead time to reflect a predicted change of the ending node demand;

dividing, by the computer, the path into a plurality of order lead time segments by;

establishing, by the computer, a plurality of cumulative cycle times of the plurality of nodes, each cumulative cycle time comprising a time difference between a time item arrives at the corresponding node and a time the item is available to leave the ending node considering all required processing cycle times and distribution cycle times; and

determining, by the computer, an order lead time segment comprising a difference between a first cumulative cycle time of a first node and a second cumulative cycle time of a second node;

associating, by the computer, the plurality of order lead time segments with the probability distribution of order lead time;

determining, by the computer, a demand percentage of each order lead time segment in order to estimate demand of the supply chain, each demand percentage describing a percentage of a total ending node demand associated with the corresponding order lead time segment, the demand percentage estimated by;

selecting, by the computer, an order lead time segment defined by a first point and a second point;

identifying, by the computer, a first ending node demand corresponding to the first point according to the probability distribution of order lead time;

identifying, by the computer, a second ending node demand corresponding to the second point according to the probability distribution of order lead time; and

calculating, by the computer, a demand percentage of the order lead time segment according to the first ending node demand and the second ending node demand; and

calculating, by the computer, an inventory at each node of the plurality of nodes according to the demand percentages of the plurality of nodes by repeating the following of at least a subset of the plurality of nodes;

selecting, by the computer, a node of the subset of the plurality of nodes;

establishing, by the computer, the demand percentage of the order lead time segment associated with the selected node; and

determining, by the computer, an inventory of the selected node that satisfies the demand percentage.