Recipe Preparation Time Estimation via Feature Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing recipes lack standardization and accuracy in providing total preparation times, as they vary with cooking skill and are impractical to determine empirically due to numerous ingredient and technique combinations, making it difficult to estimate preparation times for large numbers of recipes.
Innovation Solution
A system that infers total preparation times by identifying preparation features in recipe steps, using a preparation time model trained on known recipes to estimate times, and combines these features to provide accurate and user-preferable recipe recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If preparation times are determined experimentally for each recipe, then accuracy of preparation time estimation is improved, but the complexity and feasibility of the system deteriorates due to the large number of possible ingredient and technique combinations
Solution Approach 1:
The patent segments the recipe preparation process into distinct preparation steps, each associated with specific preparation features (ingredients, techniques, equipment). This segmentation allows the system to estimate preparation times by combining times of individual steps rather than determining the entire recipe experimentally, reducing system complexity while maintaining accuracy.
Solution Approach 2:
The patent creates a universal preparation time estimation model that can handle various ingredient combinations, cooking techniques, and equipment types through a single integrated system. The model uses preparation features from different domains (ingredients, techniques, equipment) and combines them using a preparation time model, making the system applicable to diverse recipes without requiring separate experimental determination for each combination.
2Ease of operation
If preparation times are standardized across all recipes, then ease of operation and comparison is improved, but the reliability of the times deteriorates because preparation times vary with cooking skill level
Solution Approach 1:
The patent applies local quality by estimating preparation times at the step level based on specific preparation features (ingredients, techniques, equipment) rather than applying a single standardized time across all recipes. This allows the system to provide reliable time estimates tailored to each specific recipe's characteristics while maintaining consistency in how times are calculated and presented.
3Productivity
If mathematical models are used to determine preparation times, then productivity is improved, but the measurement precision deteriorates for preparation steps that do not follow mathematical relationships
Solution Approach 1:
The patent applies partial action by using mathematical models only for preparation steps that have identifiable quantitative relationships (such as cooking times based on weight or volume), while using alternative methods for steps that do not follow mathematical relationships. The system combines results from both approaches, ensuring productivity through mathematical modeling where applicable while maintaining precision through adaptive methods where needed.
Data Source
AI summary
Embodiments infer a total preparation time of a recipe. A recipe including preparation steps describing how to prepare a food item is obtained. A recipe server identifies preparation features in the preparation steps, where the preparation features represent portions of the preparations steps that are correlated with time to prepare the recipe. The recipe server obtains preparation times associated with the preparation features and combines these preparation times to estimate to total preparation time of the recipe. The estimated total preparation time is stored or transmitted to a client device in response to a request for the recipe. The estimated total preparation time is used to filter recipes sent in response to a request for recipes, where the request specifies a criterion based on total preparation time. The estimated total preparation time is used to select recipes for recommendation to a user based on that user's preferences.