# US 10,824,401 B2 · Method and system for automated creation of graphical user interfaces

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,824,401 B2
- Document ID: US10824401B2
- Status: Granted
- Kind: B2
- Application number: 16/398,513
- Filed: 2019-04-30
- Published: 2019-10-31
- Granted: 2020-11-03
- Earliest claimed: 2018-04-30
- Assignees: Mphasis Limited
- Applicants: Mphasis Limited
- Inventors: Jai Ganesh; Rajendrakumar Mishra; Archisman Majumdar
- Web page: https://patentgrep.com/patent/US10824401B2

## CPC

- G06F 8/34: Graphical or visual programming
- G06F 9/451: Execution arrangements for user interfaces
- G06F 8/30: Creation or generation of source code
- G06F 8/35: model driven
- G06F 8/427: {Parsing}
- G06F 16/958: Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
- G06N 5/02: Knowledge representation; Symbolic representation
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method and system for automated creation of graphical user interface applications is provided. The invention provides for provisioning, management and scaling of hardware and software required for the graphical user interface applications by a single action on a command interface of a user terminal, based on a voice command provided by the user.

## Claims

### Claim 1

A system for automated end-to-end creation of graphical user interface applications via a single action on a user terminal, the system comprising:
a memory storing program instructions;
a processor executing the program instructions stored in the memory;
a conversational interface in communication with the processor and configured to convert a command received from end-users into a text description, wherein the command is based on parameters provided via the conversational interface for creating a graphical user interface;
a parsing engine in communication with the processor and configured to parse the text description to obtain one or more attributes using one or more keywords;
a design engine in communication with the processor and configured to:
generate one or more webpage template images based on the one or more attributes retrieved from the parsing engine using a Generative Adversarial Network (GAN), the GAN is trained on a set of captions and webpage templates associated with one or more ports of a website;
analyse the one or more attributes through an iterative training process of the GAN to create a training set and network configurations for generating the webpage template images, wherein the generated webpage template images are indistinguishable from actual webpage template images;
assemble the generated webpage templates based on a predetermined format to regenerate the webpage template images in a machine identifiable format; and
generate a code in a predetermined format for the generated webpage template images; and
an architecture builder in communication with the processor and configured to create hardware and software configurations based on analysis of the one or more attributes retrieved from the parsing engine for generating and deploying software and hardware for creating the graphical user interface.

### Claim 2 (depends on 1)

The system of claim 1, wherein the conversational interface is configured to verify parameters included in the command with pre-stored parameters stored in a repository and prompt the end-users to provide missing parameters.

### Claim 3 (depends on 2)

The system of claim 2, wherein the conversational interface is configured to retrieve default values of mandatory parameters from the repository if the missing parameters include the mandatory parameters.

### Claim 4 (depends on 3)

The system of claim 3, wherein the conversational interface modifies the text description with values of the mandatory parameters.

### Claim 5 (depends on 1)

The system of claim 1, wherein the one or more keywords are stored in a knowledge base and include content representative at least of look and feel, hardware and infrastructural requirements for deployment of the graphical user interface, and wherein the knowledge base is updated with a list of keywords each time a text description is parsed to obtain one or more attributes.

### Claim 6 (depends on 1)

The system of claim 1, wherein the design engine comprises a text to image generator configured to create the training set and the network configurations based on the iterative training process of the GAN including a set of captions and webpage templates associated with one or more ports of a website for generating the webpage image templates that resemble actual webpage templates.

### Claim 7 (depends on 1)

The system of claim 1, wherein the design engine comprises an image to design generator configured to assemble the generated webpage template images based on the predetermined format to regenerate the generated webpage template images in the machine identifiable format for obtaining accurate shapes of images in the generated webpage templates.

### Claim 8 (depends on 7)

The system of claim 7, wherein the design engine includes a design to code generator configured to generate a code for the regenerated webpage templates based on a predetermined format and encode the generated and regenerated webpage templates images to an intermediate representation and translate the intermediate representation to a sequence of tags, wherein the intermediate representation and sequence of tags are generated using the created training set of the GAN and are updated each time the code is generated for the webpage template images.

### Claim 9 (depends on 1)

The system of claim 1, wherein the architecture builder generates a set of information for provisioning software stack on the hardware based on the created hardware configurations, and generate containers for the webpage template images retrieved from the design engine, and the provisioning software stack.

### Claim 10 (depends on 1)

The system of claim 1, wherein the architecture builder creates an architecture definition based on the analysis of the one or more attributes and creates the hardware configurations based on the architecture definition.

### Claim 11 (depends on 10)

The system of claim 10, wherein the architecture definition includes key-value pairs associated with the created hardware configurations and are stored in a storage.

### Claim 12 (depends on 9)

The system of claim 9, wherein the architecture builder triggers generation of the provisioning software stack based on the key-value pairs.

### Claim 13 (depends on 9)

The system of claim 9, wherein the architecture builder generates the containers to create executable programs, libraries, and settings for deploying the graphical user interface.

### Claim 14

A method for automated end-to-end creation of graphical user interface applications via a single action on a user terminal, the method comprising:
converting a command received from end-users into a text description, wherein the command is based on parameters provided via the conversational interface for creating a graphical user interface;
parsing the text description to obtain one or more attributes using one or more keywords;
generating one or more webpage template images based on the one or more attributes retrieved from the parsing engine using a Generative Adversarial Network (GAN), the GAN is trained on a set of captions and webpage templates associated with one or more ports of a website;
analysing the one or more attributes through an iterative training process of the GAN to create a training set and network configurations for generating the webpage template images, wherein the generated webpage template images are indistinguishable from actual webpage template images;
assembling the generated webpage templates based on a predetermined format to-regenerate the webpage template images in a machine identifiable format;
generating a code in a predetermined format for the generated webpage template images; and
creating hardware and software based on analysis of the one or more attributes for creating and deploying the graphical user interface.

### Claim 15 (depends on 14)

The method of claim 14, wherein the method comprises verifying parameters included in the command with pre-stored parameters stored in a repository and prompting the end-users to provide missing parameters.

### Claim 16 (depends on 14)

The method of claim 14, wherein the method comprises retrieving default values of mandatory parameters from a repository if the missing parameters include the mandatory parameters.

### Claim 17 (depends on 14)

The method of claim 14, wherein the method comprises modifying the text description with values of the mandatory parameters.

### Claim 18 (depends on 14)

The method of claim 14, wherein the method comprises creating hardware configurations based on an analysis of the one or more attributes and generating a set of information for provisioning software stack on the hardware based on the created hardware configurations.

### Claim 19 (depends on 18)

The method of claim 18, wherein key-value pairs associated with the created hardware configurations are generated and are stored in a storage.

### Claim 20 (depends on 18)

The method of claim 18, the method comprises generating containers for the webpage template images and the provisioning software stack, wherein the containers are generated to create executable programs, libraries, and settings for deploying the graphical user interface.

### Claim 21 (depends on 14)

The method of claim 14, wherein the method comprises encoding the generated and regenerated webpage templates images to an intermediate representation and translating the intermediate representation to a sequence of tags, wherein the intermediate representation and sequence of tags are generated using the created training set of the GAN and are updated each time the code is generated for the webpage template images.