Method and system for providing recipes for cooking

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing cooking devices lack an efficient method to provide users with a vast array of creative and tailored recipes, often relying on limited downloadable options from the internet or social networks.

Innovation Solution

A method utilizing a trained recipe generator, which can be pre-trained and fine-tuned, to generate new recipes based on user triggers, such as voice requests or specific ingredient preferences, and adapt to user feedback and preferences.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If recipes are downloaded from the Internet or social networks, then the cooking device can provide pre-existing recipes to users, but the number of available recipes is limited

Engineering Contradiction:
Improvenumber of available recipesVSAvoidtailoring to individual user preferences
Core Design Contradiction:
Quantity of substanceVSAdaptability or versatility

Solution Approach 1:

The system enables the cooking device to generate recipes autonomously using an AI model, eliminating the need to rely on externally downloaded recipes. The device serves itself by creating unlimited custom recipes based on user preferences, ingredients, and dietary requirements, thus resolving the contradiction between quantity and adaptability

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The AI model dynamically adjusts recipe parameters such as ingredients, cooking methods, and flavor profiles based on user feedback and preferences. This allows the system to generate infinitely varied recipes tailored to individual users, transforming the static recipe database into a dynamic, adaptive system

Inventive Principle:
Principle #35Parameter changes

2Productivity

If a trained recipe generator is used to generate creative recipes, then a vast number of recipes can be generated easily, but the system complexity increases

Engineering Contradiction:
Improverecipe generation efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

An AI language model acts as an intermediary between the user's simple input (e.g., desired ingredients or dietary preferences) and the complex task of recipe creation. The model handles the computational complexity internally while presenting simple, user-friendly interactions, thus maintaining high productivity without increasing perceived device complexity

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The complex AI recipe generation functionality is extracted as a separate software module or service that can be integrated into the cooking device. This modular approach allows the core cooking device to remain relatively simple while incorporating advanced recipe generation capabilities through a dedicated component

Inventive Principle:
Principle #2Taking out (Extraction)

3Adaptability or versatility

If the recipe generator is trained using thousands of recipes from the Internet, then the generator can provide suitable recipes for any taste and occasion, but data processing requirements increase

Engineering Contradiction:
Improvecoverage of tastes and occasionsVSAvoiddata processing energy consumption
Core Design Contradiction:
Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The AI model is pre-trained offline on extensive recipe databases before being deployed on the cooking device. This preliminary training phase, which requires significant computational resources, is performed separately using powerful servers or cloud infrastructure. Once trained, the model can operate efficiently on the device with minimal energy consumption, resolving the contradiction between comprehensive adaptability and low energy usage during operation

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4566493A1Method and system for providing recipes for cooking
Publication Date: 2025.06.11 BSH HAUSGERATE GMBH
  • EP4566493A1 patent drawingFigure 1~2
  • EP4566493A1 patent drawingFigure 3~4
  • EP4566493A1 patent drawingFigure 5~6

AI summary

The present invention relates to a method (M1, M2) for providing recipes (VR, TR) for cooking to a user (N1, N2, N3) of a cooking device (10), a related data processing program product, a control unit (1) of the cooking device, a related central entity (50) and a system (80). The method comprises the steps of providing a trained recipe generator and/or training a recipe generator (S1, S11); receiving a trigger, especially a request, a query or a prompt, from the user of the cooking device (U1, U11); generating, based on the trigger, a new recipe using the recipe generator (S3, U13); and providing the new recipe to the user (U4, U14).