Neural Network Food Personalization via SME Knowledge Transfer
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Amateur food preparers face challenges in finding personalized recipes that meet their specific preferences due to inconsistent information across sources and the inability of conventional methods to scale SME knowledge effectively across the population.
Innovation Solution
A method and system that determine user food-related preferences, collect dietary inputs from SMEs, and generate personalized food parameters using machine learning techniques to provide tailored meal options, leveraging vector representations of food data and neural networks for scalable food personalization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional recipe sources are used, then information is available to amateur food preparers, but the information is inconsistent and requires preexisting specialized knowledge to navigate
Solution Approach 1:
The patent introduces a neural network model as an intermediary between SME knowledge and amateur food preparers. The model translates specialized SME knowledge into personalized recipe recommendations that are consistent and easily accessible to users without requiring them to have preexisting specialized knowledge.
Solution Approach 2:
The system creates a digital copy of SME knowledge through training a neural network model on SME inputs. This copy enables scalable dissemination of expert knowledge across the population of amateur food preparers without requiring direct access to SMEs.
2Adaptability or versatility
If one-on-one recommendations from SMEs are provided, then personalized food advice is obtained, but the approach scales poorly to the population of amateur food preparers
Solution Approach 1:
The neural network model serves as a universal system that can provide personalized recommendations to multiple users simultaneously. It generalizes SME knowledge across the population, enabling one system to perform the function of multiple individual SME consultations at scale.
Solution Approach 2:
By creating a digital copy of SME knowledge in the form of a trained neural network, the system enables scalable dissemination of personalized recommendations without requiring multiple individual SMEs to serve each user.
3Adaptability or versatility
If detailed recipe information is sought from multiple sources, then comprehensive options are found, but the search process is time-consuming and requires specialized knowledge
Solution Approach 1:
The system performs preliminary action by pre-training the neural network model on comprehensive SME knowledge before users need recommendations. When users seek recipes, the pre-trained model can immediately provide personalized recommendations without requiring users to conduct time-consuming searches or apply specialized knowledge.
Solution Approach 2:
The system incorporates user feedback (preferences, selections, ratings) to continuously improve and personalize recommendations. This feedback loop enables the system to adapt to individual user needs while providing comprehensive recipe options without requiring users to manually search multiple sources.
Data Source
AI summary
A method for improving food-related personalized for a user including determining food-related preferences associated with a plurality of users to generate a user food preferences database; collecting dietary inputs from a subject matter expert (SME) at an SME interface associated with the user food preferences database; determining personalized food parameters for the user based on the user food-related preferences and the dietary inputs; receiving feedback associated with the personalized food parameters from the user; and updating the user food preferences database based on the feedback.