Use of prediction data in monitoring actual production targets

• US 8,989,887 B2
• Filed: 02/10/2010
• Issued: 03/24/2015
• Est. Priority Date: 02/11/2009
• Status: Active Grant

• Current Assignee: Applied Materials Incorporated
• Original Assignee: Applied Materials Incorporated
• Inventors: Stafford, Richard, Norman, David E.
• Primary Examiner(s): Fennema, Robert
• Assistant Examiner(s): STEVENS, THOMAS H
• Application Number:
  US12/703,711
• Publication Number:
  US 20100228376A1
• Time in Patent Office: 1,868 Days
• Field of Search: 700/219, 712/239, 703/22, 708/553, 706/21
• US Class Current: 700/108
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: Y02P 90/80 Management or planning

Abstract

A method and system for the use of prediction data in monitoring actual production targets is described herein. In one embodiment, a process is provided to receive data from a plurality of source systems in a manufacturing facility and generate a prediction pertaining to a future state of the manufacturing facility based on the data received from the plurality of source systems. A recent state of the manufacturing facility is determined based on the data received from the plurality of source systems and a comparison between the recent state and the prediction is facilitated.

Claims

1. A computer-implemented method comprising:

receiving, by a server computer system, data from a plurality of source systems in a semiconductor manufacturing facility;

generating a prediction pertaining to a future state of the semiconductor manufacturing facility based on the data received from the plurality of source systems;

determining a recent state of the semiconductor manufacturing facility based on real-time data received from the plurality of source systems;

facilitating a comparison between the recent state that includes start and complete times of a manufacturing operation for a plurality of lots of a product being fabricated with semiconductor manufacturing equipment during the manufacturing operation and the prediction that pertains to the future state of the semiconductor manufacturing facility including predicted start and complete times of the manufacturing operation for the plurality of lots of the product for a duration of a future time horizon;

populating a prediction data model with the data received from the plurality of source systems; and

populating a real time data model with the real-time data received from the plurality of source systems, wherein the prediction data model is executed to generate the prediction including predicted start and complete times of the manufacturing operation for the plurality of lots of the product for the duration of the future time horizon and the real time data model is executed based on the real-time data to generate the recent state including the start and complete times of the manufacturing operation for the plurality of lots of the product.

2. The method of claim 1, wherein facilitating the comparison comprises:

determining whether a variance between the recent state and the prediction exceeds a threshold; and

providing a notification if the variance exceeds the threshold.

3. The method of claim 1, wherein facilitating the comparison comprises:

providing the prediction and the recent state to a client if a prediction request is received.

4. The method of claim 1, further comprising:

submitting a query to the plurality of source systems, wherein the query is created based on a type of data necessary for generating the prediction.

5. The method of claim 1, further comprising:

submitting a query to the plurality of source systems, wherein the query is created based on a type of data necessary for generating the recent state of the semiconductor manufacturing facility.

6. The method of claim 1, wherein generating the prediction comprises at least one of:

making calculations, forecasting, statistical prediction, trend analysis, and running simulation.

7. The method of claim 1, wherein the prediction includes a predicted state of operations of the semiconductor manufacturing facility for a duration of a time horizon, wherein the predicted state of operations include a future state of equipment in the semiconductor manufacturing facility, a quantity and composition of a product to be manufactured, and a number of operators needed by the semiconductor manufacturing facility to manufacture the product.

8. The method of claim 2, further comprising:

querying the plurality of source systems for additional data if the variance does not exceed the threshold.

9. A computer-implemented method comprising:

receiving, by a client computer, prediction data pertaining to a future state of a semiconductor manufacturing facility from a prediction server, wherein the prediction data pertaining to the future state of the semiconductor manufacturing facility includes predicted start and complete times of a manufacturing operation for a plurality of lots of a product within a fabrication process with semiconductor manufacturing equipment for a duration of a future time horizon;

receiving, by the client computer, recent state data pertaining to a recent state of the semiconductor manufacturing facility including start and complete times of the manufacturing operation for the plurality of lots of the product from the prediction server; and

presenting, with a graphical user interface, the prediction data and the recent state data to a user to indicate a comparison and a variance between the prediction data and the recent state data including a comparison between a predicted start time and a predicted complete time of the manufacturing operation for at least one lot of the plurality of lots of the product with the start time and the complete time of the manufacturing operation for the at least one lot.

10. The method of claim 9, wherein presenting comprises:

generating the graphical user interface (GUI) illustrating the predicted state of the semiconductor manufacturing facility based on the prediction data;

determining whether a duration of time has ended; and

updating the GUI based on the recent state data to include the recent factory state of the semiconductor manufacturing facility if the duration of time has not ended.

11. The method of claim 9, wherein presenting comprises:

generating a report based on the prediction data and the recent state data, wherein the report provides real-time information identifying one or more alerts related to operations of the semiconductor manufacturing facility.

12. The method of claim 11, further comprising:

determining whether the report is to be updated; and

updating data in the report if the report is to be updated, wherein updating is based on the recent state data that is associated with the semiconductor manufacturing facility.

13. The method of claim 11, further comprising:

determining whether data represented in the report is to be exported; and

exporting the data in the report if the data is to be exported.

14. The method of claim 11, further comprising:

determining whether data represented in the report is to be cleared; and

clearing the data in the report if the data is to be cleared.

15. A non-transitory computer-readable storage medium comprising executable instructions to cause a processor to perform operations, the instructions comprising:

receiving, by a server computer system, data from a plurality of source systems in a semiconductor manufacturing facility;

generating a prediction pertaining to a future state of the semiconductor manufacturing facility based on the data received from the plurality of source systems;

determining a recent state of the semiconductor manufacturing facility based on real-time data received from the plurality of source systems;

facilitating a comparison between the recent state that includes start and complete times of a manufacturing operation for a plurality of lots of a product being fabricated with semiconductor manufacturing equipment during the manufacturing operation and the prediction that pertains to the future state of the semiconductor manufacturing facility including predicted start and complete times of the manufacturing operation for the plurality of lots of the product for a duration of a future time horizon;

populating a prediction data model with the data received from the plurality of source systems; and

populating a real time data model with the real-time data received from the plurality of source systems, wherein the prediction data model is executed to generate the prediction including predicted start and complete times of the manufacturing operation for the plurality of lots of the product for the duration of the future time horizon and the real time data model is executed based on the real-time data to generate the recent state including the start and complete times of the manufacturing operation for the plurality of lots of the product.

16. The non-transitory computer-readable storage medium of claim 15, wherein facilitating the comparison comprises:

providing the prediction and the recent state to a client if a prediction request is received.

17. A non-transitory computer-readable storage medium comprising executable instructions to cause a processor to perform operations, the instructions comprising:

receiving prediction data pertaining to a future state of a semiconductor manufacturing facility from a prediction server, wherein the prediction data pertaining to the future state of the semiconductor manufacturing facility includes predicted start and complete times of a manufacturing operation for a plurality of lots of a product within a fabrication process with semiconductor manufacturing equipment for a duration of a future time horizon;

receiving recent state data from the prediction server; and

presenting, with a graphical user interface, the prediction data and the recent state data to a user to indicate a comparison and a variance between the prediction data and the recent state data including a comparison between a predicted start time and a predicted complete time of the manufacturing operation for at least one lot of the plurality of lots of the product with the start time and the complete time of the manufacturing operation for the at least one lot, wherein the recent state data includes start and complete times of the manufacturing operation for the plurality of lots of the product.

18. A computer system comprising:

a memory; and

a processor configurable by instructions stored in the memory to;

receive data from a plurality of source systems in a semiconductor manufacturing facility;

generate a prediction pertaining to a future state of the semiconductor manufacturing facility based on the data received from the plurality of source systems;

determine a recent state of the semiconductor manufacturing facility based on real-time data received from the plurality of source systems;

facilitate a comparison between the recent state that includes start and complete times of a manufacturing operation for a plurality of lots of a product being fabricated with semiconductor manufacturing equipment during the manufacturing operation and the prediction that pertains to the future state of the semiconductor manufacturing facility including predicted start and complete times of the manufacturing operation for the plurality of lots of the product for a duration of a future time horizon;

populate a prediction data model with the data received from the plurality of source systems; and

populate a real time data model with the real-time data received from the plurality of source systems, wherein the prediction data model is executed to generate the prediction including predicted start and complete times of the manufacturing operation for the plurality of lots of the product for the duration of the future time horizon and the real time data model is executed based on the real-time data to generate the recent state including the start and complete times of the manufacturing operation for the plurality of lots of the product.

19. The computer system of claim 18, wherein the processor is further configurable to:

determine whether a variance between the recent state and the prediction exceeds a threshold; and

provide a notification if the variance exceeds the threshold.