System and techniques for intelligent network design
A system and techniques for intelligent network design allows for capture and conversion of a basic network design, often manually created, into a digital format without duplication of effort. The disclosed techniques provide a faster, more intelligent approach for designing a network by analyzing many thousands of existing network designs and recommending proposed solutions based on user provided objectives. The techniques can generate provider independent code that provides flexibility in supporting arbitrary provider targets. The techniques can also output provider specific code that allow for rapid, efficient deployment of the network. In addition, the technique can output network system architecture designs of varying details that can be customized for the intended audience. The techniques provide for automated importing and updating provider changes to network components, schemas, and application programming interfaces reducing any lag in system design.
1. A computer-implemented method for designing a system architecture performed by one or more processors, the method comprising:
receiving an image of a diagram of a base structure of a network;
extracting a position and a size of a plurality of network components from the diagram;
generating first code data structure that is independent of a service provider using the position and the size of the plurality of network components;
storing the first code data structure to a design database;
calculating a list of two or more network design suggestions comprising network components or configurations by analyzing design data from the first code data structure and one or more previous designs;
providing the list of network design suggestions to a user on a digital design surface in a ranked order;
receiving a selection of a network design from the list of network design suggestions and a specific service provider; and
generating second code that is operational for the specific service provider for the selected network design.
2. The method of claim 1 , further comprising:
storing one or more additional network designs to the design database; and
analyzing the one or more additional stored network designs to inform the list of network design suggestions.
3. The method of claim 2 , wherein the one or more network designs are user-generated.
4. The method of claim 1 , wherein extracting the position and the size of the plurality of network components comprises:
preprocessing the image of the diagram of the base structure of the network;
detecting one or more network architecture objects in the image;
labelling the one or more architecture objects in the image creating an improved network model; and
generating the first code data structure based on the improved network model.
5. The method of claim 4 , further comprising:
storing the improved network model to a database; and
analyzing the improved network model to train an object detector.
6. The method of claim 4 , further comprising providing a suggested label for the one or more architecture objects to the user.
7. The method of claim 1 , further comprising:
importing static design data from one or more public sources via a network; and
storing the static design data to the design database.
8. The method of claim 7 , further comprising:
simulating a plurality of network models using a design assistance model trainer using the stored static design data as translated using the first code data structure;
extracting one or more features of the plurality of network models; and
scoring the plurality of network models to select a recommended model.
9. The method of claim 1 , further comprising scanning the image of the diagram of the base structure of the network using a scanner.
10. The method of claim 1 , wherein extracting a position and a size of a plurality of network components comprises recognizing one or more magnetic markers identifying network components.
11. The method of claim 1 , wherein extracting a position and a size of a plurality of network components comprises employing computer vision techniques to perform the extraction.
12. The method of claim 1 , further comprising preprocessing the image.
13. The method of claim 1 , further comprising:
detecting one or more network architecture objects in the image; and
labelling the one or more architecture objects in the image thereby creating an improved network model.
14. The method of claim 13 , wherein the labelling is automatically performed based on said detecting.
15. A non-transitory, computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
receiving an image of a diagram of a base structure of a network;
extracting a position and a size of a plurality of network components from the diagram;
generating a first code data structure that is independent of a service provider using the position and the size of the plurality of network components;
storing the first code data structure to a design database;
calculating a list of two or more network design suggestions comprising network components or configurations by analyzing design data from the first code data structure and one or more previous designs;
providing the list of network design suggestions to a user on a digital design surface in a ranked order;
receiving a selection of a network design from the list of network design suggestions and a specific service provider; and
generating a second code that is operational for a specific service provider for the selected network design.
16. An intelligent network generation system comprising:
one or more processors; and
one or more memory devices comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving an image of a diagram of a base structure of a network;
extracting a position and a size of a plurality of network components from the diagram;
generating a first code data structure that is independent of a service provider using the position and the size of the plurality of network components;
storing the first code data structure to a design database;
calculating a list of two or more network design suggestions comprising network components or configurations by analyzing design data from the first code data structure and one or more previous designs;
providing the list of network design suggestions to a user on a digital design surface in a ranked order;
receiving a selection of a network design from the list of network design suggestions and a specific service provider; and
generating a second code data structure that is operational for a specific service provider for the selected network design.
17. The intelligent network generation system of claim 16 , further comprising instructions that when executed by the one or more processors, cause the one or more processors to perform operations comprising:
storing one or more additional network designs to the design database; and
analyzing the one or more additional stored network designs to inform the list of network design suggestions.
18. The intelligent network generation system of claim 16 , wherein extracting the position and the size of the plurality of network components comprises:
preprocessing the image of the diagram of the base structure of the network;
detecting one or more network architecture objects in the image;
labelling the one or more architecture objects in the image creating an improved network model; and
generating the first code data structure based on the improved network model.
19. The intelligent network generation system of claim 18 , further comprising instructions that when executed by the one or more processors, cause the one or more processors to perform operations comprising:
storing the improved network model to the design database; and
analyzing the improved network model to train an object detector.
20. The intelligent network generation system of claim 16 , further comprising instructions that when executed by the one or more processors, cause the one or more processors to perform operations comprising:
importing static design data from one or more public sources via a network; and
store the static design data to the design database.