Virtual Tasting Systems and Methods
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for creating new food products and recipes require significant experimentation and human tasting, which are expensive, time-consuming, and limited by the chef's experience, necessitating a more efficient and cost-effective method to access a wider universe of ingredients.
Innovation Solution
The development of systems and methods that utilize a food processing unit (FPU) to evaluate objective properties of ingredients and predict user responses, allowing for the creation of new recipes with minimal human tasting, including the ability to replace animal products, allergens, and expensive ingredients, and provide a virtual tasting experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional human tasting and experimentation methods are used to create new food products, then the quality and reliability of taste evaluation is improved, but the time consumption and cost increase significantly
Solution Approach 1:
The patent introduces a machine learning model as an intermediary between ingredient composition and taste evaluation. The model is trained on human tasting data and then used to predict taste outcomes for new ingredient combinations, eliminating the need for extensive human tasting while preserving evaluation quality
Solution Approach 2:
The system performs preliminary training of the machine learning model using existing human tasting data before actual product development. This preliminary action creates a predictive tool that can evaluate new ingredient combinations without requiring new human tasting sessions, thus reducing time consumption while maintaining reliability
2Reliability
If experienced chefs create new recipes based on personal experience, then the culinary quality and flavor profile are improved, but the scope of ingredient combinations is limited
Solution Approach 1:
The machine learning model serves multiple functions: it can evaluate traditional ingredient combinations that chefs would create, but also assess novel combinations that chefs might not consider. The system universalizes the taste evaluation capability across both conventional and innovative ingredient pairings, expanding versatility while maintaining culinary quality through the same predictive framework
3Measurement precision
If extensive human tasting tests are conducted to evaluate new food products, then the accuracy of user preference prediction is improved, but the cost and resource requirements increase
Solution Approach 1:
The system creates a computational copy of human taste evaluation capabilities through the machine learning model. This copy is trained on human tasting data and then used to predict user preferences for new ingredient combinations, eliminating the need for extensive human resources while maintaining prediction accuracy
Solution Approach 2:
The machine learning model performs self-evaluation of ingredient combinations by predicting user preferences without requiring actual human tasting. The system serves its own evaluation needs through the predictive model, reducing dependency on human resources while maintaining measurement precision through the trained algorithm
Data Source
AI summary
Example virtual tasting systems and methods are described. In one implementation, a virtual tasting system identifies multiple food products, multiple tasters, and multiple questions. The virtual tasting system then identifies a full set of quadruplets of the form: first food product, second food product, taster, question. A subset of quadruplets from the full set of quadruplets are then identified. The virtual tasting system then measures a value associated with each quadruplet from the subset of quadruplets. The virtual tasting system then outputs estimated values associated with every triplet in a full set of triplets of the form: food product, taster, question.