Automatic asset selection and creation system and method

1. A method comprising:

a) receiving, at a deployment computer, a client request message comprising a plurality of established parameters and established values for the established parameters, and inquiry parameters and inquiry values for the inquiry parameters from a client computer;

b) for each model of a plurality of models stored in a database, determining, by the deployment computer, if a model in the plurality of models is a suitable model based on a likelihood value;

c) generating, by the deployment computer, one or more client response messages comprising one or more assets created by one or more suitable models; and

d) transmitting, by the deployment computer, the one or more client response messages comprising the one or more assets to the client computer, and wherein the method further comprises:

determining, by the deployment computer, whether or not to create a new model based on the client request message;

after determining to create the new model, determining, by the deployment computer, a summation value based on the established values, the inquiry values, and additional data; and

storing, by the deployment computer, the new model determined based on the summation value into the database.

2. The method of claim 1 further comprising:

retrieving, by the deployment computer, the plurality of models from the database.

3. The method of claim 1 further comprising:

determining, by the deployment computer, the likelihood value for each model of the plurality of models based on the established values, and the inquiry values.

4. The method of claim 1 , wherein the plurality of models is a plurality of machine learning models.

5. The method of claim 1 further comprising:

determining, by the deployment computer, one or more assets from an asset repository corresponding to the one or more suitable models; and

providing, by the deployment computer, access to the one or more assets to the client computer.

6. The deployment computer of claim 1 , wherein the plurality of models is a plurality of machine learning models.

7. A method comprising:

a) receiving, at a deployment computer, a client request message comprising a plurality of established parameters and established values for the established parameters, and inquiry parameters and inquiry values for the inquiry parameters from a client computer;

b) for each model of a plurality of models stored in a database, determining, by the deployment computer, if a model in the plurality of models is a suitable model based on a likelihood value;

c) generating, by the deployment computer, one or more client response messages comprising one or more assets created by one or more suitable models; and

d) transmitting, by the deployment computer, the one or more client response messages comprising the one or more assets to the client computer, wherein the method further comprises:

determining, by the deployment computer, the likelihood value for each model of the plurality of models based on the established values, and the inquiry values; and

for each model of the plurality of models, comparing the likelihood value to a predetermined threshold; and

for each model of the plurality of models, determining if the model is suitable if the likelihood value exceeds the predetermined threshold.

8. The method of claim 7 , wherein the likelihood value is in a range of 0-100.

9. A deployment computer comprising:

a processor;

a memory device; and

a computer-readable medium coupled to the processor, the computer-readable medium comprising code executable by the processor for implementing a method comprising:

a) receiving a client request message comprising a plurality of established parameters and established values for the established parameters, and inquiry parameters and inquiry values for the inquiry parameters from a client computer;

b) for each model of a plurality of models stored in a database, determining if a model in the plurality of models is a suitable model based on a likelihood value;

c) generating one or more client response messages comprising one or more assets created by one or more suitable models; and

d) transmitting the one or more client response messages comprising the one or more assets to the client computer, and wherein the computer-readable medium further comprises:

a request service module operatively coupled to the processor;

a model determination module operatively coupled to the processor;

a model characterization module operatively coupled to the processor; and

an execution module operatively coupled to the processor.

10. The deployment computer of claim 9 , wherein the method further comprises:

retrieving, by the deployment computer, the plurality of models from the database.

11. The deployment computer of claim 9 , wherein the method further comprises:

determining, by the deployment computer, the likelihood value for each model of the plurality of models based on the established values, and the inquiry values.

12. The deployment computer of claim 11 , wherein the method further comprises:

for each model of the plurality of models, comparing the likelihood value to a predetermined threshold; and

for each model of the plurality of models, determining if the model is suitable if the likelihood value exceeds the predetermined threshold.

13. The deployment computer of claim 12 , wherein the predetermined threshold is in a range of 0-100.

14. The deployment computer of claim 9 , wherein the method further comprises:

determining, by the deployment computer, one or more assets from an asset repository corresponding to the one or more suitable models; and

providing, by the deployment computer, access to the one or more assets to the client computer.

15. A deployment computer comprising:

a processor;

a memory device; and

a computer-readable medium coupled to the processor, the computer-readable medium comprising code executable by the processor for implementing a method comprising:

a) receiving a client request message comprising a plurality of established parameters and established values for the established parameters, and inquiry parameters and inquiry values for the inquiry parameters from a client computer;

b) for each model of a plurality of models stored in a database, determining if a model in the plurality of models is a suitable model based on a likelihood value;

c) generating one or more client response messages comprising one or more assets created by one or more suitable models; and

d) transmitting the one or more client response messages comprising the one or more assets to the client computer, and wherein the method further comprises:

determining, by the deployment computer, whether or not to create a new model based on the client request message;

after determining to create the new model, determining, by the deployment computer, a summation value based on the established values, the inquiry values, creation probability values, and additional data; and

storing, by the deployment computer, the new model determined based on the summation value into the database.

16. A method comprising:

generating, by a client computer, a client request message comprising a plurality of established parameters and values for the established parameters, and inquiry parameters and values for the inquiry parameters;

transmitting, by the client computer, the client request message to a deployment computer, wherein the deployment computer, for each model of a plurality of models stored in a database, determines if a model in the plurality of models is a suitable model based on a likelihood value, and generates one or more client response messages comprising one or more assets created by one or more suitable models; and

receiving, by the client computer, the one or more client response messages from the deployment computer,

wherein the deployment computer further determines whether or not to create a new model based on the client request message, determines a summation value based on the values for the established parameters, the values for the inquiry parameters, and creation probability values, and stores the new model determined based on the summation value into the database.

17. The method of claim 16 , wherein the likelihood value is determined based on at least a historic decision value, wherein the historic decision value is associated with the client computer.