# US 2019/0244541 A1 · Systems and methods for generating personalized nutritional recommendations

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0244541 A1
- Document ID: US20190244541A1
- Status: Published application
- Kind: A1
- Application number: 16/265,939
- Filed: 2019-02-01
- Published: 2019-08-08
- Earliest claimed: 2013-03-05
- Assignees: Nutrino Health Ltd.
- Applicants: Nutrino Health Ltd.
- Inventors: Yaron Hadad; Jonathon Lipnik; Ido Cohn
- Web page: https://patentgrep.com/patent/US20190244541A1

## CPC

- G09B 19/0092: {Nutrition}
- G16H 20/60: relating to nutrition control, e.g. diets
- G09B: EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS (devices for psychotechnics or for testing reaction times A61B5/16; games, sports, amusements A63; projectors, projector screens G03B)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

An algorithm and method to provide personal recommendations for nutrition based on preferences, habits, medical and activity profiles for users, and constraints. The algorithm can also be fed and takes into account real-time feedback from the user. The method allows creating a personal nutritional schedule based on a set of constraints, which are solved using an optimization algorithm to find the diet best fitting each user. The method also includes analyzing a single user by applying various statistical techniques, enabling the algorithm to infer the user's preferences and updating of the constraints, analyzing and clustering of the general user population based on statistical principles, giving the algorithm insightful information and allowing improved performance by means of “machine-learning,” and creating a list of recommended food items/recipes to help users live a balanced, healthier lifestyle.

## Claims

### Claim 1

A computer-implemented method for assisting with a user's nutritional needs, the method comprising:
obtaining, from a computing device, a plurality of physiological and food consumption inputs associated with the user;
obtaining, from a database, a food ontology comprising information on a plurality of different food items;
generating a plurality of constraints specific to the user based on (1) the plurality of physiological and food consumption inputs and (2) the food ontology, wherein the plurality of constraints comprises (i) health constraints, (ii) nutrient constraints and (iii) dietary norms;
applying the plurality of constraints to an optimization algorithm to generate a graphical visual object representative of a food space; and
determining and recommending one or more optimal diets for the user, based on selection of one or more points on the graphical visual object within the food space that satisfy the plurality of constraints.

### Claim 2 (depends on 1)

The method of claim 1, wherein the computing device comprises a mobile device, a tablet, or a personal computer associated with the user.

### Claim 3 (depends on 2)

The method of claim 2, wherein said method is implemented via a mobile application installed on the mobile device.

### Claim 4 (depends on 1)

The method of claim 1, wherein the plurality of physiological and food consumption inputs associated with the user comprises: (a) historical food consumption data, (b) eating habits, (c) culinary preferences, (d) health or physical goals, (e) a medical profile comprising physical and medical information of the user, or (f) an activity profile comprising an amount or type of physical activities that the user engages in.

### Claim 5 (depends on 1)

The method of claim 1, wherein the food ontology comprises a hierarchical association of each food item to selected groups or categories of foods.

### Claim 6 (depends on 1)

The method of claim 1, wherein the food ontology comprises an association of each food item to a set of meals or meal types.

### Claim 7 (depends on 5)

The method of claim 5, wherein the food ontology comprises a metric system between the plurality of food items and the selected groups or categories of foods.

### Claim 8 (depends on 7)

The method of claim 7, wherein the metric system comprises different distances between the plurality of food items, and the distances are depicted visually within the food space on the graphical visual object.

### Claim 9 (depends on 1)

The method of claim 1, wherein the information on the plurality of different food items comprises nutritional information of each food item.

### Claim 10 (depends on 9)

The method of claim 9, wherein the nutritional information of each food item comprises a nutritional value of the food item, and type or amount of nutrients in the food item.

### Claim 11 (depends on 1)

The method of claim 1, wherein the one or more optimal diets comprises a list of food items recommended to be consumed by the user over a defined time period.

### Claim 12 (depends on 11)

The method of claim 11, further comprising: apportioning the list of food items into a plurality of different meals and recommended eating times.

### Claim 13 (depends on 4)

The method of claim 4, wherein the optimization algorithm is configured to adjust one or more of the constraints based on changes to one or more of the physiological and food consumption inputs.

### Claim 14 (depends on 13)

The method of claim 13, wherein the changes to one or more of the physiological and food consumption inputs are detected or obtained from the computing device.

### Claim 15 (depends on 13)

The method of claim 13, wherein the optimization algorithm is configured to determine, based on the adjustments to the one or more constraints, whether adjustments to the one or more optimal diets for the user is needed, or whether a new optimal diet is needed.

### Claim 16 (depends on 1)

The method of claim 1, wherein the optimization algorithm is configured to dynamically modify the one or more optimal diets depending on how closely the user is following the recommended diet(s).

### Claim 17 (depends on 1)

The method of claim 1, wherein the optimization algorithm is configured to dynamically modify the one or more optimal diets depending on how the user's feedback on the recommended diet(s), wherein the user's feedback is provided via the computing device.

### Claim 18 (depends on 1)

The method of claim 1, wherein the graphical visual object representative of the food space is configured to be displayed on the computing device of the user or other computing devices.

### Claim 19 (depends on 18)

The method of claim 18, wherein the selection of the one or more points on the graphical visual object within the food space is enabled by using the computing device(s) to select the one or more points.

### Claim 20 (depends on 1)

The method of claim 1, wherein the food space comprises an N+1 dimensional space for N number of food items.

### Claim 21 (depends on 1)

The method of claim 1, wherein the food space comprises a curved and/or elevation map representing the user's taste in different foods.

### Claim 22 (depends on 1)

The method of claim 1, wherein different points within the food space represent different diets or combinations of foods.

### Claim 23 (depends on 22)

The method of claim 22, wherein a height of a specific point within the food space represents the user's degree of liking or preference for a diet associated with the specific point.

### Claim 24 (depends on 22)

The method of claim 22, wherein the graphical visual object comprises different visual shadings for points located at different heights within the food space.

### Claim 25 (depends on 1)

The method of claim 1, further comprising:
determining and recommending a different optimal diet for the user each time a diet recommendation is requested by the user.

### Claim 26 (depends on 25)

The method of claim 25, wherein the different optimal diets are based on stochastic selection of different points within the food space that satisfy the plurality of constraints.

### Claim 27 (depends on 4)

The method of claim 4, wherein the culinary preferences comprise a diversity factor input by the user for one or more of the food items.

### Claim 28 (depends on 1)

The method of claim 1, wherein the plurality of constraints comprise linear and/or nonlinear constraints.

### Claim 29 (depends on 1)

The method of claim 1, wherein said method is configured to assist a plurality of users with their nutritional needs, the method further comprising:
clustering the plurality of users to define a plurality of groups having different dietary preferences or needs; and
associating each user with a group that is closest to said user, to thereby generate a nutritional crowd sourcing platform.

### Claim 30 (depends on 29)

The method of claim 29, wherein the nutritional crowd sourcing platform comprises trends, insights, and food recommendations that are provided to the users in the plurality of groups based on their different dietary preferences or needs.

### Claim 31 (depends on 29)

The method of claim 29, wherein the plurality of users are clustered into and associated with different groups using K-near neighbor (K-NN), collaborative filtering, a Bayesian network, or matrix factorization.

### Claim 32 (depends on 1)

The method of claim 1, wherein the optimization algorithm is configured to calculate a probability of the user's preference for a specific food item based on changes that the user makes to the one or more recommended optimal diets.

### Claim 33

A system for assisting a plurality of users with their nutritional needs, the system comprising:
a server in communication with a plurality of computing devices and a database; and
a memory storing instructions that, when executed by the server, causes the server to perform operations comprising:
obtaining, from each of the computing devices, a plurality of physiological and food consumption inputs associated with a user of the corresponding computing device;
obtaining, from the database, a food ontology comprising information on a plurality of different food items;
generating, for each of the users, a plurality of constraints specific to the user based on (1) the plurality of physiological and food consumption inputs and (2) the food ontology, wherein the plurality of constraints comprises (i) health constraints, (ii) nutrient constraints and (iii) dietary norms;
applying the plurality of constraints to an optimization algorithm to generate a graphical visual object representative of a food space; and
determining and recommending one or more optimal diets for each of the users, based on selection of one or more points on the graphical visual object within the food space that satisfy the plurality of constraints.

### Claim 34

A non-transitory computer-readable medium including instructions that, when executed by a server, cause the server to perform operations comprising:
obtaining, from each of a plurality of computing devices, a plurality of physiological and food consumption inputs associated with a user of the corresponding computing device;
obtaining, from the database, a food ontology comprising information on a plurality of different food items;
generating, for each of the users, a plurality of constraints specific to the user based on (1) the plurality of physiological and food consumption inputs and (2) the food ontology, wherein the plurality of constraints comprises (i) health constraints, (ii) nutrient constraints and (iii) dietary norms;
applying the plurality of constraints to an optimization algorithm to generate a graphical visual object representative of a food space; and
determining and recommending one or more optimal diets for each of the users, based on selection of one or more points on the graphical visual object within the food space that satisfy the plurality of constraints.
