Generative AI Application Generation via Predefined Functions

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing application development processes require extensive time and cost to learn programming languages and efficient coding, and existing AI-based programming support techniques are limited in generating applications from conversational sentences.

Innovation Solution

A novel information processing apparatus and method that utilizes a generative AI system to generate applications by transmitting sample data and setting information to the AI system, which then requests the execution of predefined functions to generate the application.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If traditional programming methods are used, then applications can be developed with full control over code, but it requires extensive time and cost to learn programming languages and efficient coding

Engineering Contradiction:
ImproveEase of application developmentVSAvoidTime required to learn programming
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The patent introduces a generative AI system as an intermediary between the user and the code generation process. The AI system receives natural language descriptions, sample data, and setting information from users, processes these inputs, and generates complete application codes automatically. This mediator eliminates the need for users to learn programming languages while maintaining full control over application functionality through intuitive natural language interfaces.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical process of manual coding with an automated AI-based system. Instead of requiring users to mechanically input code using keyboards and understand programming syntax, the system uses generative AI to automatically translate natural language descriptions and sample data into executable code, substituting the mechanical coding process with intelligent automation.

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

2Productivity

If AI-based programming support techniques are used, then coding time is reduced, but the ability to generate applications from conversational sentences is limited

Engineering Contradiction:
ImproveApplication generation speedVSAvoidAbility to generate from conversational input
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent makes the AI system universal by enabling it to handle multiple input types and generate diverse application types. The system can process natural language descriptions, sample data files, and setting information combinations to generate various applications including web applications, mobile applications, and desktop applications. This multi-functionality allows the same AI system to adapt to different user needs and input formats, significantly improving both productivity and versatility.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent applies preliminary action by requiring users to provide sample data and setting information before the AI generates the application. This preliminary preparation of structured data and parameters enables the AI to generate more accurate and tailored applications from conversational inputs, improving both generation speed and adaptability to specific user requirements.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If predefined functions are used in the AI system, then application generation becomes more structured and reliable, but the flexibility to handle unique requirements may be reduced

Engineering Contradiction:
ImproveApplication generation reliabilityVSAvoidFlexibility for unique requirements
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent introduces dynamics by allowing the AI system to adaptively select and combine predefined functions based on the specific input data and user requirements. Rather than being rigid, the system dynamically adjusts which predefined functions to use and how to parameterize them, enabling reliable generation for common cases while maintaining flexibility for unique requirements through adaptive function composition.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent uses parameter changes by allowing the AI system to modify parameters of predefined functions based on input sample data and setting information. The system can adjust function parameters to match specific user requirements while maintaining the underlying structured framework, thereby achieving both reliability through predefined functions and flexibility through parameter adaptation.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS20250200340A1Information processing apparatus, application generation system, and application generation method
Publication Date: 2025.06.19 RICOH CO LTD
  • US20250200340A1 patent drawing
  • US20250200340A1 patent drawing
  • US20250200340A1 patent drawing

AI summary

An information processing apparatus is communicably connected with a terminal device and a generative artificial intelligence (AI) system through a network. The information processing apparatus includes processing circuitry. The processing circuitry transmits data based on the sample data to the generative AI system in response to receiving sample data for generating application from the terminal device. The processing circuitry transmits setting information for generating the application and information for calling a predefined function to the generative AI system at least once. The processing circuitry generates the application based on parameters included in the request by executing the predefined function in response to receiving a request for generation of the application from the generative AI system. The request is generated by the generative AI system based on the data, the setting information, and the information for calling the predefined function.