Granted Patent B2

US 12,620,323 · App. 17/517,772 · Granted May 5, 2026

Inventor: Kenneth Neumann (Lakewood, CO)

Assignee: KPN INNOVATIONS, LLC

G09B19/0092G06F16/90335G16H20/60G16H50/20

Abstract

Claims (71)

1 . A system for self-fulfillment of a dietary request, the system comprising:

at least a server, wherein the at least a server is designed and configured to:

receive an alimentary instruction set as a function of a dietary request, wherein

receiving the alimentary instruction set comprises:

parsing the alimentary instruction set into a plurality of tokens;

storing the plurality of tokens as one or more chains;

assigning an alimentary label to one or more of the plurality of tokens using a Hidden Markov Model; and

generating an alimentary instruction set descriptor by converting one or more alimentary labels into narrative language by retrieving one or more elements of narrative language from a table associating alimentary labels with elements of narrative language;

generate at least a self-fulfillment instruction set, the self-fulfillment instruction set comprising a data structure identifying a plurality of self-fulfilling actions a user can take to self-fulfill a suggested nourishment requirement, as a function of at least a self-fulfillment action, wherein generating the at least a self-fulfillment instruction set comprises:

receiving training data including a plurality of data entries, each data entry of the plurality of data entries including at least an alimentary instruction and at least a correlated self-fulfillment action datum;

training a machine-learning model as a function of the training data; and

generating the at least a self-fulfillment instruction set as a function of the alimentary instruction set and the machine-learning model;

generating a query as a function of at least an instruction of the self-fulfillment instruction set;

querying a web index as a function of the query by classifying, using an index classifier, the user to a physiologically linked web index, and querying the physiologically linked web index, wherein the index classifier is iteratively trained with elements of physiological data sets correlated to user cohort labels, wherein the server is configured to continuously generate, using a feature learning algorithm implementing a clustering analysis, cohort labels, using a feature learning algorithm, when a threshold number of physiological data sets fails to converge within a threshold distance of existing clusters;

receiving a search result corresponding to the query; and

modifying the at least an instruction as a function of the search result;

receive at least an entry containing an alimentary self-fulfillment action; and

generate a modified self-fulfillment instruction set as a function of the alimentary self-fulfillment action.

2 . The system of claim 1 , wherein receiving the alimentary instruction set further comprises:

receiving at least a dietary request; and

generating the alimentary instruction set as a function of the at least a dietary request.

3 . The system of claim 1 , wherein generating the modified self-fulfillment instruction set further comprises:

generating a modified alimentary instruction set as a function of the alimentary self-fulfillment action; and

generating the at least a self-fulfillment instruction set as a function of the modified alimentary instruction set.

4 . The system of claim 3 , wherein generating the at least a self-fulfillment instruction set as a function of the modified alimentary instruction set further comprises generating the at least a self-fulfillment instruction set as a function of the modified alimentary instruction set and the machine-learning model.

5 . The system of claim 1 , wherein generating the modified self-fulfillment instruction set further comprises generating the modified self-fulfillment instruction set as a function of the alimentary self-fulfillment action and the machine-learning model.

6 . The system of claim 1 , wherein the server is further configured to generate the self-fulfillment instruction set by:

generating a loss function of user specific variables; and

minimizing the loss function.

7 . The system of claim 6 , wherein a user specific variable further comprises an ingredient standard request.

8 . The system of claim 6 , wherein a user specific variable further comprises an ingredient requirement request.

9 . A method of self-fulfillment of a dietary request, the method comprising:

receiving, by at least a server, an alimentary instruction set as a function of a dietary request, wherein receiving the alimentary instruction set comprises:

parsing the alimentary instruction set into a plurality of tokens;

storing the plurality of tokens as one or more chains;

assigning an alimentary label to one or more of the plurality of tokens using a Hidden Markov Model; and

generating an alimentary instruction set descriptor by converting one or more alimentary labels into narrative language by retrieving one or more elements of narrative language from a table associating alimentary labels with elements of narrative language;

generating, by the at least a server, at least a self-fulfillment instruction set, the self-fulfillment instruction set comprising a data structure identifying a plurality of self-fulfilling actions a user can take to self-fulfill a suggested nourishment requirement, as a function of at least a self-fulfillment action, wherein generating the at least a self-fulfillment instruction set comprises:

receiving training data including a plurality of data entries, each data entry of the plurality of data entries including at least an alimentary instruction and at least a correlated self-fulfillment action datum;

training a machine-learning model as a function of the training data; and

generating the at least a self-fulfillment instruction set as a function of the alimentary instruction set and the machine-learning model;

generating a query as a function of at least an instruction of the self-fulfillment instruction set;

querying a web index as a function of the query by classifying, using an index classifier, the user to a physiologically linked web index, and querying the physiologically linked web index, wherein the index classifier is iteratively trained with elements of physiological data sets correlated to user cohort labels, wherein the server is configured to continuously generate, using a feature learning algorithm implementing a clustering analysis, cohort labels when a threshold number of physiological data sets fails to converge within a threshold distance of existing clusters;

receiving a search result corresponding to the query; and

modifying the at least an instruction as a function of the search result;

receiving, by the at least a server, at least an entry containing an alimentary self-fulfillment action;

generating, by the at least a server a modified self-fulfillment instruction set as a function of the alimentary self-fulfillment action.

10 . The method of claim 9 , wherein receiving the alimentary instruction set further comprises:

receiving at least a dietary request; and

generating the alimentary instruction set as a function of the at least a dietary request.

11 . The method of claim 9 , wherein generating the modified self-fulfillment instruction set further comprises:

generating a modified alimentary instruction set as a function of the alimentary self-fulfillment action; and

generating the at least a self-fulfillment instruction set as a function of the modified alimentary instruction set.

12 . The method of claim 11 , wherein generating the at least a self-fulfillment instruction set as a function of the modified alimentary instruction set further comprises generating the at least a self-fulfillment instruction set as a function of the modified alimentary instruction set and the machine-learning model.

13 . The method of claim 9 , wherein generating the modified self-fulfillment instruction set further comprises generating the modified self-fulfillment instruction set as a function of the alimentary self-fulfillment action and the machine-learning model.

14 . The method of claim 9 , wherein the server is further configured to generate the self-fulfillment instruction set by:

generating a loss function of user specific variables; and

minimizing the loss function.

15 . The method of claim 14 , wherein a user specific variable further comprises an ingredient standard request.

16 . The method of claim 14 , wherein a user specific variable further comprises an ingredient requirement request.

17 . The system of claim 1 , wherein generating the cohort labels using the feature learning algorithm comprises:

dividing physiological data from a given user into a plurality of sub-combinations to create a plurality of physiological data sets using a cluster analysis; and

evaluating which physiological data sets tend to co-occur with which other physiological data sets as a function of a degree of similarity index value,

wherein the cluster analysis is configured to configured to:

generate an initial set of user cohort labels from an initial set of user physiological data; and

iteratively identify new clusters to generate new user cohort labels.

18 . The method of claim 9 , wherein generating the cohort labels using the feature learning algorithm comprises:

dividing physiological data from a given user into a plurality of sub-combinations to create a plurality of physiological data sets using a cluster analysis; and

evaluating which physiological data sets tend to co-occur with which other physiological data sets as a function of a degree of similarity index value, wherein the cluster analysis is configured to configured to:

generate an initial set of user cohort labels from an initial set of user physiological data; and

iteratively identify new clusters to generate new user cohort labels.

Assignments (1)

Continuity (2)

References Cited (42)