Predictive router for materials handling

• US 8,086,344 B1
• Filed: 06/04/2008
• Issued: 12/27/2011
• Est. Priority Date: 06/04/2008
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Mishra, Devesh, Young, Eric, Somin, Irina M., Tian, Hong, Al-Kazily, Riyadth F.
• Primary Examiner(s): Crawford, Gene
• Assistant Examiner(s): CUMBESS, YOLANDA R
• Application Number:
  US12/132,824
• Time in Patent Office: 1,301 Days
• Field of Search: None
• US Class Current: 700/216
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 30/0283 Price estimation or determination

Abstract

Systems and computer-implemented methods for predictive routing of item packages within a materials handling facility are disclosed. A predictive router may operate in conjunction with a container recommender, and both may be components of a facility management system. The predictive router may determine a routing destination for an item package dependent, at least in part, on the size and/or dimensions of a container that was recommended for handling the item package. The routing destination may be a shipping line customized for preparation of packed boxes of a particular size or in a particular size range for shipment. An optional scanner may attempt to determine the size of the actual container being used to ship the item package, and the predictive router may update the routing destination if the actual container does not match the recommended container. The predictive router may also consider special handling instructions when determining a routing destination.

Claims

1. A computing system, comprising one or more computing nodes, each of which comprises at least one processor and memory;

wherein the one or more computing nodes are configured to implement a predictive router configured to;

receive an indication of a type of container recommended to handle an item package in a materials handling facility, wherein the item package is associated with an item package identifier;

determine a predicted routing destination for the item package dependent, at least in part, on the recommended container type;

provide an indication of the predicted routing destination to a routing mechanism in the materials handling facility prior to the item package reaching the routing mechanism.

2. The system of claim 1, wherein the predicted routing destination is a shipment preparation line configured to process item packages shipped in containers of the recommended container type.

3. The system of claim 1, wherein the routing mechanism comprises an automated routing system, and wherein said providing comprises providing the indication of the predicted routing destination for the item package to the automated routing system.

4. The system of claim 1, further comprising a memory accessible by the routing mechanism and configured to store the item package identifier and to associate the item package identifier with the predicted routing destination.

5. The system of claim 1, further comprising a memory accessible by the routing mechanism and configured to store the item package identifier and to associate the item package identifier with the recommended container type.

6. The system of claim 1, wherein the predictive router is further configured to:

receive an indication of a container type of an actual container in which the item package is being handled; and

determine if the item package is being handled in a container of the recommended container type.

7. The system of claim 6, further comprising one or more input devices coupled to the one or more computing nodes;

wherein said receiving an indication of the container type of the actual container comprises receiving an identifier of the actual container from the one or more input devices.

8. The system of claim 6, wherein in response to determining that the item package is not being handled in a container of the recommended container type, the predictive router is further configured to:

determine an updated routing destination for the item package dependent, at least in part, on the indication of the container type of the actual container; and

provide an indication of the updated routing destination to the routing mechanism prior to the item package reaching the routing mechanism.

9. The system of claim 8, wherein said providing an indication of the updated routing destination comprises storing the updated routing destination in a memory accessible by the routing mechanism and associating the updated routing destination with the item package.

10. The system of claim 6, wherein in response to determining that the item package is not being handled in a container of the recommended container type, the predictive router is further configured to store the indication of the container type of the actual container in a memory and to associate the indication of the container type of the actual container with the item package.

11. The system of claim 6, wherein in response to determining that the item package is not being handled in a container of the recommended container type, the predictive router is further configured to flag the item package for exception handling.

12. The system of claim 1, wherein the predictive router is further configured to:

attempt to determine a container type of an actual container in which the item package is handled; and

in response to a failure to determine the container type of the actual container, maintaining the predicted routing destination for the item package.

13. The system of claim 1, wherein the predictive router is further configured to:

receive feedback from the predicted routing destination indicating that the item package cannot be processed at the predicted routing destination; and

determine a different routing destination for the item package, wherein the different routing destination comprises an exception handling mechanism for misdirected item packages.

14. The system of claim 1, wherein the predictive router is further configured to:

receive feedback from the predicted routing destination indicating that the item package cannot be processed at the predicted routing destination and comprising an indication of a container type of an actual container in which the item package is being handled; and

determine a different routing destination for the item package, wherein the different routing destination is a shipment preparation line configured to process item packages shipped in containers of the container type of the actual container.

15. The system of claim 1, wherein said determining a predicted routing destination for the item package is further dependent on special handling instructions associated with the item package.

16. The system of claim 1,

wherein the one or more computing nodes are further configured to implement a routing performance analyzer configured to:

receive a request for a routing performance report;

access a data store to obtain routing related data; and

generate the routing performance report dependent on the routing related data;

wherein the routing related data comprises one or more of;

a recommended container type associated with one or more item packages, an actual container type associated with one or more item packages, a routing destination associated with one or more item packages, an updated routing destination associated with one or more item packages, special handling instructions associated with one or more item packages, and a list of items associated with one or more item packages; and

wherein the routing performance report comprises one or more of;

a number, percentage, or trend of item packages shipped in containers of a given container type;

a number, percentage, or trend of item packages shipped in a container of a recommended container type;

a number, percentage, or trend of item packages for which a predicted routing destination was updated;

a number, percentage, or trend of item packages for which an actual container type was determined;

a number, percentage, or trend of misdirected item packages;

a throughput of a shipment preparation line; and

a number, percentage, or trend of item packages for which a container type recommendation was determined to be incorrect.

17. The system of claim 1, wherein the one or more computing nodes are further configured to implement a container recommender configured to recommend a container type for an item package dependent on item dimension values or weight values currently associated with each item in the item package.

18. A method, comprising:

performing by a computer;

receiving an indication of a type of container recommended to handle an item package in a materials handling facility, wherein the item package is associated with an item package identifier;

determining a predicted routing destination for the item package dependent, at least in part, on the recommended container type;

providing an indication of the predicted routing destination to a routing mechanism in the materials handling facility prior to the item package reaching the routing mechanism.

19. The method of claim 18, wherein the predicted routing destination is a shipment preparation line configured to process item packages shipped in containers of the recommended container type.

20. The method of claim 18, further comprising:

storing the item package identifier in a memory accessible by the routing mechanism; and

associating the item package identifier with the predicted routing destination in the memory.

21. The method of claim 18, further comprising:

receiving an indication of a container type of an actual container in which the item package is being handled;

determining if the item package is being handled in a container of the recommended container type; and

in response to determining that the item package is not being handled in a container of the recommended container type;

determining an updated routing destination for the item package dependent, at least in part, on the indication of the container type of the actual container; and

providing an indication of the updated routing destination to the routing mechanism prior to the item package reaching the routing mechanism.

22. The method of claim 21, further comprising, in response to determining that the item package is not being handled in a container of the recommended container type, flagging the item package for exception handling.

23. The method of claim 18, further comprising:

attempting to determine a container type of an actual container in which the item package is handled; and

in response to a failure to determine the container type of the actual container, maintaining the predicted routing destination for the item package.

24. The method of claim 18, further comprising:

receiving feedback from the predicted routing destination indicating that the item package cannot be processed at the predicted routing destination; and

determining a different routing destination for the item package.

25. The method of claim 18, wherein said determining a predicted routing destination for the item package is further dependent on special handling instructions associated with the item package.

26. The method of claim 18, further comprising:

receiving a request for a routing performance report;

accessing a data store to obtain routing related data; and

generating the routing performance report dependent on the routing related data;

wherein the routing related data comprises one or more of;

a recommended container type associated with one or more item packages, an actual container type associated with one or more item packages, a routing destination associated with one or more item packages, an updated routing destination associated with one or more item packages, special handling instructions associated with one or more item packages, and a list of items associated with one or more item packages; and

wherein the routing performance report comprises one or more of;

a number, percentage, or trend of item packages shipped in containers of a given container type;

a number, percentage, or trend of item packages shipped in a container of a recommended container type;

a number, percentage, or trend of item packages for which a predicted routing destination was updated;

a number, percentage, or trend of item packages for which an actual container type was determined;

a number, percentage, or trend of misdirected item packages;

a throughput of a shipment preparation line; and

a number, percentage, or trend of item packages for which a container type recommendation was determined to be incorrect.

27. The method of claim 18, further comprising, prior to said receiving:

determining a recommended type of container for the item package dependent on item dimension values or weight values currently associated with each item in the item package; and

storing an indication of the recommended container type in a data store;

wherein said receiving comprises obtaining the indication of the recommended container type from the data store.

28. A non-transitory, computer-readable storage medium storing program instructions that when executed on one or more computers cause the one or more computers to perform:

receiving an indication of a type of container recommended to handle an item package in a materials handling facility, wherein the item package is associated with an item package identifier;

determining a predicted routing destination for the item package dependent, at least in part, on the recommended container type;

providing an indication of the predicted routing destination to a routing mechanism in the materials handling facility prior to the item package reaching the routing mechanism.

29. The storage medium of claim 28, wherein the predicted routing destination is a shipment preparation line configured to process item packages shipped in containers of the recommended container type.

30. The storage medium of claim 28, wherein when executed on the one or more computers the program instructions further cause the one or more computers to perform:

storing the item package identifier in a memory accessible by the routing mechanism; and

associating the item package identifier with the predicted routing destination in the memory.

31. The storage medium of claim 28, wherein when executed on the one or more computers the program instructions further cause the one or more computers to perform:

receiving an indication of a container type of an actual container in which the item package is being handled;

determining if the item package is being handled in a container of the recommended container type; and

in response to determining that the item package is not being handled in a container of the recommended container type;

determining an updated routing destination for the item package dependent, at least in part, on the indication of the container type of the actual container; and

providing an indication of the updated routing destination to the routing mechanism prior to the item package reaching the routing mechanism.

32. The storage medium of claim 31, wherein when executed on the one or more computers the program instructions further cause the one or more computers to perform, in response to determining that the item package is not being handled in a container of the recommended container type, flagging the item package for exception handling.

33. The storage medium of claim 28, wherein when executed on the one or more computers the program instructions further cause the one or more computers to perform:

attempting to determine a container type of an actual container in which the item package is handled; and

in response to a failure to determine the container type of the actual container, maintaining the predicted routing destination for the item package.

34. The storage medium of claim 28, wherein when executed on the one or more computers the program instructions further cause the one or more computers to perform:

receiving feedback from the predicted routing destination indicating that the item package cannot be processed at the predicted routing destination; and

determining a different routing destination for the item package.

35. The storage medium of claim 28, wherein said determining a predicted routing destination for the item package is further dependent on special handling instructions associated with the item package.

36. The storage medium of claim 28, wherein when executed on the one or more computers the program instructions further cause the one or more computers to perform:

receiving a request for a routing performance report;

accessing a data store to obtain routing related data; and

generating the routing performance report dependent on the routing related data;

wherein the routing related data comprises one or more of;

a recommended container type associated with one or more item packages, an actual container type associated with one or more item packages, a routing destination associated with one or more item packages, an updated routing destination associated with one or more item packages, special handling instructions associated with one or more item packages, and a list of items associated with one or more item packages; and

wherein the routing performance report comprises one or more of;

a number, percentage, or trend of item packages shipped in containers of a given container type;

a number, percentage, or trend of item packages shipped in a container of a recommended container type;

a number, percentage, or trend of item packages for which a predicted routing destination was updated;

a number, percentage, or trend of item packages for which an actual container type was determined;

a number, percentage, or trend of misdirected item packages;

a throughput of a shipment preparation line; and

a number, percentage, or trend of item packages for which a container type recommendation was determined to be incorrect.

37. The storage medium of claim 28, wherein when executed on the one or more computers the program instructions further cause the one or more computers to perform, prior to said receiving:

determining the recommended type of container for the item package dependent on item dimension values or weight values currently associated with each item in the item package; and

storing an indication of the recommended container type in a memory;

wherein said receiving comprises obtaining the indication of the recommended container type from the memory.