AI Engine Converts Hand-Drawn Diagrams to Visual Programming Logic

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current CRM software automation tools require programming acumen, limiting their user base to those comfortable with programming environments, necessitating increased resources for tasks like automated marketing campaigns.

Innovation Solution

An AI engine-powered mechanism that converts hand-drawn process flow diagrams into visual programming logic within automation building tools, using machine learning for shape recognition and logic flow determination, allowing users to create automated programs without coding.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If automation building tools require programming acumen, then the automation logic can be precisely controlled, but the user base is limited to those comfortable with programming environments

Engineering Contradiction:
Improveease of useVSAvoiduser base
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent introduces an AI engine as an intermediary between the user's natural language input and the automation building tool's programming logic. The AI engine translates user-friendly natural language into executable automation logic, allowing non-programmers to create automated programs without needing programming acumen while maintaining precise control over automation behavior

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the traditional mechanical interaction model (where users manually configure programming logic through complex interfaces) with an AI-based natural language processing system. This substitution eliminates the need for users to learn programming environments while preserving the ability to create sophisticated automation logic

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If development teams are utilized to create automated programs, then the automation logic can be professionally developed, but the resources required increase

Engineering Contradiction:
Improveautomation qualityVSAvoidresources
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

The patent enables end-users to independently create and configure automated programs through natural language interaction with the AI engine, eliminating the need to defer campaign creation to development teams. Users can directly build, modify, and deploy automation logic without requiring professional developers, thereby reducing resource consumption while maintaining automation quality

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The AI engine serves as an intermediary that empowers non-expert users to create professional-quality automation logic without requiring development team involvement. The AI translates simple user intentions into sophisticated automation programs, eliminating the need for external development resources

Inventive Principle:
Principle #24Intermediary (Mediator)

3Ease of operation

If visual programming logic is made more accessible, then non-developers can create automated programs, but the complexity of the system increases

Engineering Contradiction:
Improveuser accessibilityVSAvoidsystem complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent introduces an AI engine as an intermediary layer that handles the complexity of translating natural language into visual programming logic. This intermediary absorbs the system complexity, allowing users to interact through simple natural language while the AI manages the underlying complex transformations to generate executable automation logic

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS10817266B2Converting a captured image to visual programming logic for an automation building tool
Publication Date: 2020.10.27 SALESFORCE INC
  • US10817266B2 patent drawing
  • US10817266B2 patent drawing
  • US10817266B2 patent drawing

AI summary

Described is a mechanism that converts a captured image (e.g. hand drawn image) of a process flow diagram into visual programming logic. The mechanism may analyze the image using a machine learning component to recognize various shapes within the image that correspond to various operations (e.g. nodes of a graph). The mechanism may then determine a process flow within the image (e.g. edges of a graph) based on the position of each shape relative to a top-most shape. The recognized operations and process flow may then be automatically provided to the building tool. The building tool may then display the process flow diagram as visual programming logic for an executable program. Accordingly, the mechanism provides the ability for a user to conveniently create programming logic and forego the process of building a program using only programming code or visual tools.