System and method for predictive analysis of technology infrastructure requirements
Various examples are directed to computer-implemented systems and methods for predictive analysis of technology infrastructure capacity requirements. A method includes receiving a product roadmap input indicating technological requirements of an enterprise, and analyzing the product roadmap input to locate and extract capacity data from the product roadmap input. Using machine learning, technology infrastructure capacity requirements are predicted for the enterprise based on the capacity data. The technology infrastructure capacity requirements are validated, and technological resources are determined to meet the technology infrastructure capacity requirements. When the technology infrastructure capacity requirements are validated, the technological resources are automatically provisioned to meet the technology infrastructure capacity requirements.
1 . A computer-implemented method comprising: receiving, by a computer system, a product roadmap input indicating technological requirements of an enterprise;
analyzing, by the computer system, the product roadmap input to locate and extract capacity data from the product roadmap input;
predicting, by the computer system using machine learning including a machine learning model, technology infrastructure capacity requirements for the enterprise based on the capacity data;
retraining, by the computer system, the machine learning model based on training data using a closed loop system, wherein the predicted technology infrastructure capacity requirements obtained using the machine learning model during operation are used to improve the training data:
generating, by the computer system, a revised machine learning model using the improved training data:
validating, using the computer system, the technology infrastructure capacity requirements using the revised machine learning model;
determining, by the computer system, technological resources to meet the technology infrastructure capacity requirements; and
when the technology infrastructure capacity requirements are validated, automatically provisioning, by the computer system, the technological resources to meet the technology infrastructure capacity requirements.
2 . The computer-implemented method of claim 1 , further comprising:
displaying, on a graphical user interface in communication with the computer system, a list of the technology infrastructure capacity requirements.
3 . The computer-implemented method of claim 1 , further comprising:
displaying, on a graphical user interface in communication with the computer system, a list of the technological resources to meet the infrastructure capacity requirements.
4 . The computer-implemented method of claim 1 , wherein analyzing the product roadmap input to locate and extract capacity data includes using a programmable bot to locate and extract the capacity data.
5 . The computer-implemented method of claim 1 , wherein automatically provisioning the technological resources includes updating one or more files in a git repository.
6 . The computer-implemented method of claim 1 , further comprising:
comparing, by the computer system, a cost of the technological resources to a quota threshold; and
providing, by the computer system, an alert to a user of the computer system based on the comparison.
7 . The computer-implemented method of claim 1 , wherein predicting technology infrastructure capacity requirements for the enterprise based on the capacity data includes predicting technology infrastructure capacity requirements based on user demand.
8 . The computer-implemented method of claim 1 , wherein using machine learning includes using a machine learning model including one or more of a long short-term memory (LSTM) network, bidirectional encoder representations from transformers (BERT), natural language processing (NLP), or an artificial intelligence (AI)-based knowledge tree.
9 . The computer-implemented method of claim 1 , further comprising:
receiving, by the computer system, additional input from a user generated by text entry into a plurality of boxes on an interactive interface.
10 . A system comprising: a computing system comprising one or more processors and a data storage system in communication with the one or more processors, wherein the data storage system comprises instructions thereon that, when executed by the one or more processors, causes the one or more processors to:
receive a product roadmap input indicating technological requirements of an enterprise;
analyze the product roadmap input to locate and extract capacity data from the product roadmap input;
predict, using machine learning including a machine learning model, technology infrastructure capacity requirements for the enterprise based on the capacity data;
retrain the machine learning model based on training data using a closed loop system,
wherein the predicted technology infrastructure capacity requirements obtained using the machine learning model during operation are used to improve the training data, generate a revised machine learning model using the improved training data, validate the technology infrastructure capacity requirements using the revised machine learning model:
determine technological resources to meet the technology infrastructure capacity requirements; and
when the technology infrastructure capacity requirements are validated, automatically provision the technological resources to meet the technology infrastructure capacity requirements.
11 . The system of claim 10 , wherein the machine learning includes a machine learning model including a neural network.
12 . The system of claim 11 , wherein the neural network includes a long short-term memory (LSTM) network.
13 . The system of claim 10 , wherein the machine learning includes bidirectional encoder representations from transformers (BERT).
14 . The system of claim 10 , wherein the machine learning includes natural language processing (NLP).
15 . The system of claim 10 , wherein the machine learning includes an artificial intelligence (AI)-based knowledge tree.
16 . A non-transitory computer-readable storage medium, the non- transitory computer-readable storage medium including instructions that, when executed by computers, cause the computers to perform operations of: receiving a product roadmap input indicating technological requirements of an enterprise:
analyzing the product roadmap input to locate and extract capacity data from the product roadmap input;
predicting, using machine learning including a machine learning model, technology infrastructure capacity requirements for the enterprise based on the capacity data;
retraining the machine learning model based on training data using a closed loop system, wherein the predicted technology infrastructure capacity requirements obtained using the machine learning model during operation are used to improve the training data,
generating a revised machine learning model using the improved training data:
validating the technology infrastructure capacity requirements using the revised machine learning model;
determining technological resources to meet the technology infrastructure capacity requirements; and
when the technology infrastructure capacity requirements are validated, automatically provisioning the technological resources to meet the technology infrastructure capacity requirements.
17 . The non-transitory computer-readable storage medium of claim 16 , wherein analyzing the product roadmap input to locate and extract capacity data includes using a programmable bot to locate and extract the capacity data.
18 . The non-transitory computer-readable storage medium of claim 16 , wherein automatically provisioning the technological resources includes updating one or more files in a git repository.
19 . The non-transitory computer-readable storage medium of claim 16 , wherein the medium further includes instructions that, when executed by computers, cause the computers to perform operations of:
comparing a cost of the technological resources to a quota threshold; and
providing an alert to a user of the computers based on the comparison.
20 . The non-transitory computer-readable storage medium of claim 16 , wherein predicting technology infrastructure capacity requirements for the enterprise based on the capacity data includes predicting technology infrastructure capacity requirements based on user demand.