System and method to calculate procurement of assets

• US 8,032,401 B2
• Filed: 07/18/2007
• Issued: 10/04/2011
• Est. Priority Date: 07/18/2007
• Status: Expired due to Fees

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Choubey, Suresh K.
• Primary Examiner(s): Champagne; Luna
• Application Number:
  US11/779,632
• Publication Number:
  US 20090024491A1
• Time in Patent Office: 1,539 Days
• Field of Search: None
• US Class Current: 705/7.11
• 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 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 30/0645 Rental transactions; Leasing transactions

Abstract

A system and method to calculate a mode of procurement of at least one asset is provided. The system comprises a tracking element operable to generate a signal representative of a location of the at least one asset, and a controller in communication with the at least one tracking element. The controller includes a processor operable to execute program instructions representative of the acts of measuring a utilization of the at least one asset having a unique identifier over at least one time interval, calculating a projected need of the at least one asset over a predetermined future time interval dependent on the utilization of the at least one asset, calculating a mode of procurement of the projected need of the at least one asset dependent on the projected need of the at least one asset, and displaying the mode of procurement to the user.

Claims

1. A system to calculate a mode of procurement of at least one asset, the system comprising:

at least one tracking element operable to generate a signal representative of a location of the at least one asset; and

a controller in communication with the at least one tracking element, the controller including a processor in communication with a memory, the processor operable to execute a plurality of program instructions stored in the memory, the plurality of program instructions representative of the acts of;

measuring a utilization of the at least one asset having a unique identifier over at least one time interval;

calculating a projected need of the at least one asset over a predetermined future time interval based upon the measured utilization of the at least one asset over the at least one time interval;

calculating a mode of procurement of the at least one asset based upon the projected need of the at least one asset using a recurrent neural network algorithm which comprises calculating automatically adjustable empirical weights using back-propagation, wherein back-propagation comprises using a predetermined error of historical input values to produce a historical outcome;

adopting the automatically adjustable empirical weights into the recurrent neural algorithm; and

displaying the mode of procurement to the user;

wherein the act of calculating the projected need is based upon at least one parameter from the group comprising an upgrade factor of switching from an existing asset to a new asset, a predicted useful life of the at least one asset, a business adjustment factor representative of a business direction indicative of expansion of patient services in view of local competition, and a patient increase factor (PIF) representative of a projected increase in patient care.

2. The system of claim 1, wherein the act of measuring the utilization of the at least one asset includes calculating at least one average utilization of the at least one asset over a predetermined time period on a continuous basis, and wherein the mode of procurement includes one of the group consisting of a purchase of the at least one asset and a rental of the at least one asset.

3. The system of claim 1, wherein the act of calculating the mode of procurement of the at least one asset further comprises using a plurality of parameter values of projected utilization of the at least one asset over different time intervals.

4. The system of claim 1, wherein an outcome of the recurrent neural network algorithm is a binary value representative of the mode of procurement of the at least one asset.

5. The system of claim 1, the plurality of program instructions further representative of the acts of:

testing whether the recurrent neural network algorithm produces an outcome of the mode of procurement within a predetermined error of other historically known outcomes of the mode of procurement correlated to other historically known needs of the at least one asset.

6. The system of claim 1, the plurality of program instructions further representative of the acts of:

comparing the projected need of the at least one asset of a first user to the measured utilization of at least one other asset by a second user, the second user different than the first user and the at least one other asset of a same type as the at least one asset of the first user.

7. The system of claim 1, wherein the act of calculating the projected need of the at least one asset over the predetermined future time interval is based upon a trend of utilization of the at least one asset calculated over a predetermined historical time interval.

8. The system of claim 1, wherein the act of calculating the mode of procurement of the at least one asset is based upon at least one parameter of the group comprising a rental cost, a purchase cost, and a depreciation rate of the at least one asset over the future time interval.

9. The system of claim 1, wherein the act of calculating a mode of procurement includes executing a procurement algorithm that includes at least one parameter of the group consisting of a measured utilization of the at least one asset and a predicted business direction of services correlated with utilization of the at least one asset.

10. A computer implemented method of calculating a mode of procurement of at least one asset having at least one tracking element, the method comprising the acts of:

communicating with the at least one tracking element for the at least one asset to identify a location of the at least one asset via at least one programmed computer;

measuring a utilization of the at least one asset having a unique identifier over at least one time interval;

calculating a projected need of the at least one asset over a predetermined future time interval based upon the measured utilization of the at least one asset;

calculating a mode of procurement of the at least one asset based upon the projected need of the at least one asset using a recurrent neural network algorithm which comprises calculating automatically adjustable empirical weights using back-propagation, wherein back-propagation comprises using a predetermined error of historical input values to produce a historical outcome;

adopting the automatically adjustable weights into the recurrent neural algorithm; and

displaying on a computer display the mode of procurement to the user;

wherein the act of calculating the projected need is based upon at least one parameter from the group comprising an upgrade factor of switching from an existing asset to a new asset, a predicted useful life of the at least one asset, a business adjustment factor representative of a business direction indicative of expansion of patient services in view of local competition, and a patient increase factor (PIF) representative of a projected increase in patient care.

11. The method of claim 10, wherein the act of measuring the utilization of the at least one asset includes calculating at least one average utilization of the at least one asset over a predetermined time period on a continuous basis, and wherein the mode of procurement includes one of the group comprising a purchase of the at least one asset and a rental of the at least one asset.

12. The method of claim 10, wherein the act of calculating the mode of procurement of the at least one asset further comprises using a plurality of parameters of projected utilization of the least one asset over different time intervals.

13. The method of claim 10, wherein an outcome of the recurrent neural network algorithm is a binary value representative of a mode of procurement of the at least one asset.

14. The method of claim 10, the method further including the act of testing whether the recurrent neural network algorithm produces an outcome of the mode of procurement within a predetermined error of other historically known outcomes of the mode of procurement correlated to other historically known needs of the at least one asset.

15. The method of claim 10, the method further including the act of comparing the projected need of the at least one asset of a first user to the measured utilization of at least another asset by a second user, the second user different than the first user and the at least another asset of a same type as the at least one asset of the first user.

16. The method of claim 10, wherein the act of calculating the projected need of the at least one asset over the predetermined future time interval is based upon a trend of utilization of the at least one asset calculated over a predetermined historical time interval.