Computer network with a performance engineering maturity model system
View Patent ↗Described herein is a performance engineering maturity model (PEMM) system that can be implemented in a computer network to improve upon or overcome performance engineering issues within information technology (IT) systems of organizations.
1 . A system, comprising a performance engineering maturity model (PEMM) system, the PEMM system comprising:
a system frontend component hosted by a client device; and
a system backend component hosted by a server device, the PEMM system configured to enhance a PEMM of information technology (IT) systems of an organization by generating a remediation plan using machine learning that comprises deep learning and an artificial neural network (ANN),
the system backend component comprising:
(i) a stratified sampling engine configured to generate a first input for the ANN by:
executing stratified sampling that comprises generating data associated with knowledgebase tools, methods, and practices, the stratified sampling comprising reducing a size of a sampling of data to an amount where a corresponding standard error of the sampling is below a predetermined threshold in order to reduce processing in the generation of the first input; and
using the data associated with knowledgebase tools, methods, and practices as a basis that comprises groups of data points that are proportional to reduce processing in the generation of the first input:
(ii) a Monte Carlo engine configured to generate a second input for the ANN through Monte Carlo data processing; and
(iii) a machine learning engine, configured to:
receive the first input and the second input for the ANN; and
send an output of the ANN or a derivative thereof, over a computer network, to the system frontend component, the remediation plan comprising the output of the ANN or the derivative thereof.
2 . The system of claim 1 , wherein the machine learning comprises supervised learning.
3 . The system of claim 1 , wherein the machine learning comprises unsupervised learning.
4 . The system of claim 1 , wherein the machine learning comprises semi-supervised learning.
5 . The system of claim 1 , wherein the machine learning comprises reinforcement learning.
6 . The system of claim 1 , wherein the machine learning comprises dimensionality reduction.
7 . The system of claim 1 , wherein the machine learning comprises feature learning.
8 . The system of claim 7 , wherein the feature learning comprises multilayer perceptrons, supervised dictionary learning, or a combination thereof.
9 . A method, comprising:
a client device of a computer network hosting a system frontend component of a performance engineering maturity model (PEMM) system;
a server device of the computer network hosting a system backend component of the PEMM system, the PEMM system configured to enhance a PEMM of information technology (IT) systems of an organization by generating a remediation plan using machine learning that comprises deep learning and an artificial neural network (ANN),
a stratified sampling engine of the system backend component generating a first input for the ANN by:
executing stratified sampling that comprises generating data associated with knowledgebase tools, methods, and practices, the stratified sampling comprising reducing a size of a sampling of data to an amount where a corresponding standard error of the sampling is below a predetermined threshold in order to reduce processing in the generation of the first input; and
using the data associated with knowledgebase tools, methods, and practices as a basis that comprises groups of data points that are proportional to reduce processing in the generation of the first input;
a Monte Carlo engine of the system backend component generating a second input for the ANN through Monte Carlo data processing;
a machine learning engine of the system backend component receiving the first input and the second input for the ANN; and
the machine learning engine sending an output of the ANN or a derivative thereof, over the computer network, to the system frontend component, the remediation plan comprising the output of the ANN or the derivative thereof.
10 . The method of claim 9 , wherein the machine learning comprises supervised learning.
11 . The method of claim 9 , wherein the machine learning comprises unsupervised learning.
12 . The method of claim 9 , wherein the machine learning comprises semi-supervised learning.
13 . The method of claim 9 , wherein the machine learning comprises reinforcement learning.
14 . The method of claim 9 , wherein the machine learning comprises dimensionality reduction.
15 . The method of claim 9 , wherein the machine learning comprises feature learning.
16 . The method of claim 15 , wherein the feature learning comprises multilayer perceptrons, supervised dictionary learning, or a combination thereof.
17 . A computer network, comprising a performance engineering maturity model (PEMM) system, the PEMM system comprising:
a system frontend component hosted by a client device of the computer network; and
a system backend component hosted by a server device of the computer network, the PEMM system configured to enhance a PEMM of information technology (IT) systems of an organization by generating a remediation plan using machine learning that comprises deep learning and an artificial neural network (ANN),
the system backend component comprising:
(i) a stratified sampling engine configured to generate a first input for the ANN by:
executing stratified sampling that comprises generating data associated with knowledgebase tools, methods, and practices, the stratified sampling comprising reducing a size of a sampling of data to an amount where a corresponding standard error of the sampling is below a predetermined threshold in order to reduce processing in the generation of the first input; and
using the data associated with knowledgebase tools, methods, and practices as a basis that comprises groups of data points that are proportional to reduce processing in the generation of the first input;
(ii) a Monte Carlo engine configured to generate a second input for the ANN through Monte Carlo data processing; and
(iii) a machine learning engine, configured to:
receive the first input and the second input for the ANN; and
send an output of the ANN or a derivative thereof, over the computer network, to the system frontend component, the remediation plan comprising the output of the ANN or the derivative thereof.
18 . The computer network of claim 17 , wherein the machine learning comprises supervised learning, unsupervised learning, or semi-supervised learning, or some combination thereof.
19 . The computer network of claim 17 , wherein the machine learning comprises reinforcement learning or dimensionality reduction, or some combination thereof.
20 . The computer network of claim 17 , wherein the machine learning comprises feature learning.