Decision support system for order prioritization

1. A method comprising:

establishing an artificial neural network, the artificial neural network comprising plurality of computing devices communicatively coupled over a network;

training each computing device of the artificial neural network using sets of historical product order data;

generating a function, using the artificial neural network, that maps product order data for an historical product order to its observed cycle time;

calculating, using the function generated by the artificial neural network, a cycle time for a product order of a plurality of product orders, the cycle time comprising an amount of time to manufacture each product associated with a product order, wherein the cycle time is calculated based on inputs comprising

product order type; and

a plurality of component counts, wherein a component count comprises of the number of units of a component used to manufacture the product of the product order;

calculating a priority index for the product order using an analytic hierarchy process, wherein alternatives evaluated by the analytic hierarchy process comprise the plurality of product orders and criteria of the analytic hierarchy process comprise a plurality of product order attributes, each criterion having a priority value;

determining a first order priority of the product order based on the priority index;

determining that a status of the product order attributes associated with the product order has changed;

determining that the first order priority of the product order is invalid in response to determining that the status of the product order attributes associated with the product order has changed;

calculating a revised priority index for the product order using the analytic hierarchy process, wherein calculating the revised priority index comprises adjusting the priority value of one or more criterion of the product order in the analytic hierarchy process;

determining a revised order priority for the product order based on the revised priority index;

simulating an event based manufacturing model using a plurality of computing devices communicatively coupled over a network, wherein each computing device is configured to perform functions that simulate one of a manufacturing station and a worker in a manufacturing environment based on a plurality of inputs that are based on real data, the plurality of inputs comprising

the revised order priority of the product order,

a second set of attributes for the product order comprising product type, product model, and a plurality of component counts;

manufacturing capacity and inventory data relating to the product order, and

production time data of historical product orders;

determining a second order priority and completion time of the product order based on results of the simulation of the event based manufacturing model; and

determining a shipping date for the product order based on the second order priority and completion time.

2. The method of claim 1 , wherein determining a revised order priority of the product order further comprises revising the order priority for one or more other product orders.

3. The method of claim 1 , wherein the artificial neural network is trained using historical product order data comprising cycle time, product order type, and a plurality of component counts, wherein a component count consists of the number of units of a component used to manufacture the product of the product order.

4. The method of claim 1 , wherein the plurality of product order attributes comprises order type, cut-off date, cycle time, critical customer issues, pending time, and requested ship date.

5. The method of claim 1 , wherein the manufacturing capacity and inventory data relating to the product order comprises lead time and a plurality of component inventory counts, wherein a component inventory count comprises of the available number of units of a component used to manufacture the product of the product order.

6. The method of claim 1 , wherein the production time data of historical product orders comprise assembly time, testing time, visual inspection time, and packaging time.

7. The method of claim 1 , wherein determining a shipping date for the product order further comprises adjusting the shipping date for one or more other product orders.

8. An order prioritization apparatus comprising:

a cycle time calculation module that:

establishes an artificial neural network, the artificial neural network comprising plurality of computing devices communicatively coupled over a network;

trains each computing device of the artificial neural network using sets of historical product order data;

generates a function, using the artificial neural network, that maps product order data for an historical product order to its observed cycle time; and

calculates, using the function generated by the artificial neural network, a cycle time for a product order of a plurality of product orders, the cycle time comprising an amount of time to manufacture each product associated with a product order, wherein the cycle time is calculated based on inputs comprising

product order type; and

a plurality of component counts, wherein a component count comprises of the number of units of a component used to manufacture the product of the product order;

a priority determination module that:

calculates a priority index for the product order using an analytic hierarchy process, wherein alternatives evaluated by the analytic hierarchy process comprise the plurality of product orders and criteria of the analytic hierarchy process comprise a plurality of product order attributes, each criterion having a priority value; and

determines a first order priority of the product order based on the priority index;

a validation module that:

determines that a status of the product order attributes associated with the product order has changed; and

determines that the first order priority of the product order is invalid in response to determining that the status of the product order attributes associated with the product order has changed, wherein the priority determination module calculates a revised priority index for the product order using the analytic hierarchy process, wherein calculating the revised priority index comprises adjusting the priority value of one or more criterion of the product order in the analytic hierarchy process, and determines a revised order priority for the product order based on the revised priority index;

a simulation module that:

simulates an event based manufacturing module using a plurality of computing devices communicatively coupled over a network, wherein each computing device is configured to perform functions that simulate one of a manufacturing station and a worker in a manufacturing environment based on a plurality of inputs that are based on real data, the plurality of inputs comprising

the revised order priority of the product order,

a second set of attributes for the product order comprising product type, product model, and a plurality of component counts;

manufacturing capacity and inventory data relating to the product order, and

production time data of historical product orders; and

determines a second order priority and completion time of the product order based on results of the simulation of the event based manufacturing model; and

a scheduling module that determines a shipping date for the product order based on the second order priority and completion time,

wherein at least a portion of the cycle time calculation module, the priority determination module, the validation module, the simulation module, and the scheduling module comprise one or more of hardware and executable code, the executable code stored on one or more computer readable storage media.

9. The apparatus of claim 8 , wherein determining a revised order priority of the product order further comprises revising the order priority for one or more other product orders.

10. The apparatus of claim 8 , wherein the artificial neural network is trained using historical product order data comprising cycle time, product order type, and a plurality of component counts, wherein a component count consists of the number of units of a component used to manufacture the product of the product order.

11. The apparatus of claim 8 , wherein the plurality of product order attributes comprises order type, cut-off date, cycle time, critical customer issues, pending time, and requested ship date.

12. The apparatus of claim 8 , wherein the manufacturing capacity and inventory data relating to the product order comprises lead time and a plurality of component inventory counts, wherein a component inventory count comprises of the available number of units of a component used to manufacture the product of the product order.

13. The apparatus of claim 8 , wherein the production time data of historical product orders comprise assembly time, testing time, visual inspection time, and packaging time.

14. The apparatus of claim 8 , wherein determining a shipping date for the product order further comprises adjusting the shipping date for one or more other product orders.

15. The apparatus of claim 8 , further comprising a server, the server comprising one or more of the cycle time calculation module, the priority determination module, the simulation module, and the scheduling module.

16. A computer program product for order prioritization, the computer program product comprising a non-transitory computer readable storage medium having program code embodied therein, the program code readable/executable by a processor to:

establish an artificial neural network, the artificial neural network comprising plurality of computing devices communicatively coupled over a network;

train each computing device of the artificial neural network using sets of historical product order data;

generate a function, using the artificial neural network, that maps product order data for an historical product order to its observed cycle time;

calculate, using the function generated by the artificial neural network, a cycle time for a product order of a plurality of product orders, the cycle time comprising an amount of time to manufacture each product associated with a product order, wherein the cycle time is calculated based on inputs comprising

product order type; and

a plurality of component counts, wherein a component count comprises of the number of units of a component used to manufacture the product of the product order;

calculate a priority index for the product order using an analytic hierarchy process, wherein alternatives evaluated by the analytic hierarchy process comprise the plurality of product orders and criteria of the analytic hierarchy process comprise a plurality of product order attributes, each criterion having a priority value;

determine a first order priority of the product order based on the priority index;

determine that a status of the product order attributes associated with the product order has changed;

determine that the first order priority of the product order is invalid in response to determining that the status of the product order attributes associated with the product order has changed;

calculate a revised priority index for the product order using the analytic hierarchy process, wherein calculating the revised priority index comprises adjusting the priority value of one or more criterion of the product order in the analytic hierarchy process;

determine a revised order priority for the product order based on the revised priority index;

simulating an event based manufacturing model using a plurality of computing devices communicatively coupled over a network, wherein each computing device is configured to perform functions that simulate one of a manufacturing station and a worker in a manufacturing environment based on a plurality of inputs that are based on real data, the plurality of inputs comprising

the revised order priority of the product order,

a second set of attributes for the product order comprising product type, product model, and a plurality of component counts;

manufacturing capacity and inventory data relating to the product order, and

production time data of historical product orders;

determining a second order priority and completion time of the product order based on results of the simulation of the event based manufacturing model; and

determine a shipping date for the product order based on the second order priority and completion time.

17. The computer program product of claim 16 , wherein the artificial neural network is trained using historical product order data comprising cycle time, product order type, and a plurality of component counts, wherein a component count consists of the number of units of a component used to manufacture the product of the product order.