Inventory early warning agent in a supply chain management system

• US 7,398,232 B2
• Filed: 07/31/2002
• Issued: 07/08/2008
• Est. Priority Date: 11/14/2001
• Status: Expired due to Term

• Current Assignee: SAP SE
• Original Assignee: SAP AG (SAP SE)
• Inventors: Renz, Alexander, Chen, Ye
• Primary Examiner(s): Frenel; Vanel
• Application Number:
  US10/208,180
• Publication Number:
  US 20030225635A1
• Time in Patent Office: 2,169 Days
• Field of Search: 705/28, 705/29, 705 7- 10, 705/22
• US Class Current: 705/28
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/08 Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders

Abstract

An inventory agent operating on software includes instructions operable to cause a programmable processor to receive inventory data relating to stock in an inventory, apply the inventory data to a conditional probabilistic predictive statistical algorithm, calculate a predicted inventory level, and use the calculated predicted inventory level to determine whether to order additional stock for the inventory. The statistical algorithm uses a conditional probabilistic model to process the data. The inventory agent may be implemented in a supply chain management system.

Claims

1. A computer-implemented method comprising:

applying machine learning techniques to historical supply chain data to build a conditional probabilistic model including patterns of behavior related to consumption and replenishment activities in a supply chain;

receiving inventory data relating to stock in an inventory;

applying the inventory data to a conditional probabilistic predictive statistical algorithm, wherein the conditional probabilistic predictive statistical algorithm uses the conditional probabilistic model to process the inventory data and to calculate a predicted inventory level based on a supply prediction and a demand prediction, the supply prediction factoring in variability in supply chain activities;

using the calculated predicted inventory level to determine whether to order additional stock for the inventory; and

automatically ordering a replenishment of the inventory when the calculated predicted inventory level falls below a predetermined minimum.

2. The method of claim 1, wherein the inventory data is generated using a radio-frequency identification device.

3. The method of claim 1, wherein the inventory data is generated upon the sale of the stock in the inventory.

4. The method of claim 1, wherein the inventory data is generated upon the transfer of the stock in the inventory.

5. The method of claim 1, wherein the conditional probabilistic model uses a conditional Gaussian approximation.

6. The method of claim 1, wherein the conditional probabilistic model uses historical inventory data and current inventory data.

7. The method of claim 1, wherein the conditional probabilistic model further calculates an upside 10% confidence bound and a downside 10% confidence bound.

8. The method of claim 7, further comprising:

using the calculated upside 10% confidence bound and the downside 10% confidence bound in determining whether to order additional stock for the inventory.

9. The method of claim 1, wherein the inventory data includes actual cumulative replenishment, forecast cumulative replenishment, actual cumulative consumption, and forecast cumulative consumption data.

10. The method of claim 1, further comprising:

recording data related to inventory consumption and replenishment.

11. The method of claim 10, further comprising:

using the recorded data to calculate cumulative forecast consumption, cumulative forecast replenishment, cumulative actual consumption, and cumulative actual replenishment.

12. The method of claim 11, further comprising instructions operable to use the inventory data with the calculated cumulative forecast consumption, cumulative forecast replenishment, cumulative actual consumption, and cumulative actual replenishment to calculate a second predicted inventory level.

13. The method of claim 1, wherein the inventory agent is implemented in a supply chain management system.

14. A system comprising one or more computer systems and an inventory agent computer coupled to the computer systems over a network, the inventory agent computer being operable to:

apply machine learning techniques to historical supply chain data to build a conditional probabilistic model including patterns of behavior related to consumption and replenishment activities in a supply chain;

receive inventory data relating to stock in an inventory;

apply the inventory data to a conditional probabilistic predictive statistical algorithm, wherein the conditional probabilistic predictive statistical algorithm uses the conditional probabilistic model to process the inventory data and to calculate a predicted inventory level, an upside 10% confidence bound of the predicted inventory level and a downside 10% confidence bound of the predicted inventory level, based on a supply prediction and a demand prediction, the supply prediction factoring in variability in supply chain activities; and

use the calculated predicted inventory level to determine whether to order additional stock for the inventory.

15. The system of claim 14, further comprising instructions to generate the inventory data upon receipt from a radio-frequency identification device.

16. The system of claim 14, further comprising instructions to generate the inventory data upon the sale of the stock in the inventory.

17. The system of claim 14, further comprising instructions to generate the inventory data upon the transfer of the stock in the inventory.

18. The system of claim 14, wherein the conditional probabilistic model uses a conditional Gaussian approximation.

19. The system of claim 14, further comprising instructions to use historical inventory data and current inventory data in the conditional probabilistic model.

20. The system of claim 14, further comprising instructions to use the calculated upside 10% confidence bound and the downside 10% confidence bound in determining whether to order additional stock for the inventory.

21. The system of claim 14, wherein the inventory data includes actual cumulative replenishment, forecast cumulative replenishment, actual cumulative consumption, and forecast cumulative consumption data.

22. The system of claim 14, further comprising instruction operable to cause the inventory agent computer to order a replenishment of the inventory.

23. The system of claim 14, further comprising instructions operable to record data related to inventory consumption and replenishment.

24. The system of claim 23, further comprising instructions operable to use the recorded data to calculate cumulative forecast consumption, cumulative forecast replenishment, cumulative actual consumption, and cumulative actual replenishment.

25. The system of claim 24, further comprising instructions operable to use the inventory data with the calculated cumulative forecast consumption, cumulative forecast replenishment, cumulative actual consumption, and cumulative actual replenishment to calculate a second predicted inventory level.

26. The system of claim 14, wherein the inventory agent computer is implemented in a supply chain management system.

27. A machine readable medium having instructions therein which when executed by a computer cause the computer to perform a set of operations comprising:

applying machine learning techniques to historical supply chain data to build a conditional probabilistic model including patterns of behavior related to consumption and replenishment activities in a supply chain;

receiving inventory data relating to stock in an inventory;

applying the inventory data to a conditional probabilistic predictive statistical algorithm, wherein the conditional probabilistic predictive statistical algorithm uses the conditional probabilistic model to process the inventory data and to calculate a predicted inventory level based on a supply prediction and a demand prediction, the supply prediction factoring in variability in supply chain activities;

using the calculated predicted inventory level to determine whether to order additional stock for the inventory; and

automatically ordering a replenishment of the inventory when the calculated predicted inventory level indicates a likely undesirable variation in inventory.

28. The machine readable medium of claim 27, wherein the inventory data is generated using a radio-frequency identification device.

29. The machine readable medium of claim 27, wherein the inventory data is generated upon the sale of the stock in the inventory.

30. The machine readable medium of claim 27, wherein the inventory data is generated upon the transfer of the stock in the inventory.

31. The machine readable medium of claim 27, wherein the conditional probabilistic model uses a conditional Gaussian approximation.

32. The machine readable medium of claim 27, wherein the conditional probabilistic model uses historical inventory data and current inventory data.

33. The machine readable medium of claim 27, wherein the conditional probabilistic model further calculates an upside 10% confidence bound and a downside 10% confidence bound.

34. The machine readable medium of claim 33, further comprising instructions to use the calculated upside 10% confidence bound and the downside 10% confidence bound in determining whether to order additional stock for the inventory.

35. The machine readable medium of claim 27, wherein the inventory data includes actual cumulative replenishment, forecast cumulative replenishment, actual cumulative consumption, and forecast cumulative consumption data.

36. The machine readable medium of claim 27, further comprising instructions operable to record data related to inventory consumption and replenishment.

37. The machine readable medium of claim 36, further comprising instructions operable to use the recorded data to calculate cumulative forecast consumption, cumulative forecast replenishment, cumulative actual consumption, and cumulative actual replenishment.

38. The machine readable medium of claim 37, further comprising instructions operable to use the inventory data with the calculated cumulative forecast consumption, cumulative forecast replenishment, cumulative actual consumption, and cumulative actual replenishment to calculate a second predicted inventory level.

39. The machine readable medium of claim 27, wherein the inventory agent is implemented in a supply chain management system.