Granted Patent B1

US 12,505,165 · App. 19/240,255 · Granted Dec 23, 2025

Inventor: Maren E. Boothby (Laconia, NH)

Assignee: Boothby Therapy Services, LLC

G06F16/9035G06F16/906G06F16/909

Abstract

Claims (60)

1 . An apparatus for triadic user matching based on profile data, the apparatus comprising:

at least a processor; and

a memory communicatively connected to the at least a processor, wherein the memory contains instructions that, when executed by the at least a processor, configure the at least a processor to:

receive a plurality of sets of profile data comprising a set of first user profile data associated with at least one first user, a set of second user profile data associated with at least one second user, and a set of third user profile data associated with at least one third user, wherein:

each of the plurality of sets of profile data comprises a temporal availability element and the set of first user profile data comprises a first user descriptor;

classify the set of first user profile data into one or more first user classification groups based on the first user descriptor;

determine a triadic match comprising the at least one second user and the at least one third user associated with the at least one first user as a function of the temporal availability element of each of the plurality of sets of profile data and the one or more first user classification groups using a triadic machine-learning model that has been trained on historical triadic match data;

append the triadic match to a database as at least a portion of historical record data; and

modify a graphical user interface as a function of the triadic match.

2 . The apparatus of claim 1 , wherein classifying the set of first user profile data comprises classifying the set of first user profile data to the one or more first user classification groups as a function of a deficiency type, severity, or interaction requirements of the first user descriptor.

3 . The apparatus of claim 1 , wherein classifying the set of first user profile data comprises using a classification group classifier that has been trained on classification group training data comprising exemplary first user profile data correlated to exemplary first user classification groups.

4 . The apparatus of claim 1 , wherein determining the triadic match comprises:

generating an absence score of the at least one second user based on the historical record data; and

determining the triadic match as a function of the absence score.

5 . The apparatus of claim 1 , wherein determining the triadic match comprises:

determining a triadic session time as a function of the temporal availability element of each of the plurality of sets of profile data;

receiving a global positioning system (GPS) signal from a device associated with the at least one second user at the triadic session time; and

determining a check-in status of the at least one second user by comparing GPS coordinates of the GPS signal with a location of the at least one first user.

6 . The apparatus of claim 5 , wherein determining the triadic match comprises:

logging an event as a record failure in the historical record data when the check-in status indicates that a location of the at least one second user does not correspond to the location of the at least one first user at the triadic session time.

7 . The apparatus of claim 1 , wherein determining the triadic match comprises:

parsing external data comprising weather data;

determining an availability disruption as a function of the external data and the set of second user profile data; and

determining the triadic match as a function of the availability disruption.

8 . The apparatus of claim 1 , wherein determining the triadic match comprises

selecting a weight distribution over a plurality of decision parameters of the triadic machine-learning model as a function of the one or more first user classification groups; and

determining a compatibility score for each potential triadic match by applying the selected weight distribution to the plurality of decision parameters.

9 . The apparatus of claim 8 , wherein selecting the weight distribution comprises selecting the weight distribution over at least a physical proximity between the at least one first and second users as a function of a deficiency type of the one or more first user classification groups.

10 . The apparatus of claim 1 , wherein appending the triadic match comprises:

receiving a user interaction from the graphical user interface, wherein the user interaction comprises a candidate session rejection; and

appending the triadic match as a function of the user interaction.

11 . A method for triadic user matching based on profile data, the method comprising:

receiving, using at least a processor, a plurality of sets of profile data comprising a set of first user profile data associated with at least one first user, a set of second user profile data associated with at least one second user, and a set of third user profile data associated with at least one third user, wherein:

each of the plurality of sets of profile data comprises a temporal availability element and the set of first user profile data comprises a first user descriptor;

classifying, the at least a processor, the set of first user profile data into one or more first user classification groups based on the first user descriptor;

determining, the at least a processor, a triadic match comprising the at least one second user and the at least one third user associated with the at least one first user as a function of the temporal availability element of each of the plurality of sets of profile data and the one or more first user classification groups using a triadic machine-learning model that has been trained on historical triadic match data;

appending, the at least a processor, the triadic match to a database as at least a portion of historical record data; and

modifying, the at least a processor, a graphical user interface as a function of the triadic match.

12 . The method of claim 11 , wherein classifying the set of first user profile data comprises classifying the set of first user profile data to the one or more first user classification groups as a function of a deficiency type, severity, or interaction requirements of the first user descriptor.

13 . The method of claim 11 , wherein classifying the set of first user profile data comprises using a classification group classifier that has been trained on classification group training data comprising exemplary first user profile data correlated to exemplary first user classification groups.

14 . The method of claim 11 , wherein determining the triadic match comprises:

generating an absence score of the at least one second user based on the historical record data; and

determining the triadic match as a function of the absence score.

15 . The method of claim 11 , wherein determining the triadic match comprises:

determining a triadic session time as a function of the temporal availability element of each of the plurality of sets of profile data;

receiving a global positioning system (GPS) signal from a device associated with the at least one second user at the triadic session time; and

determining a check-in status of the at least one second user by comparing GPS coordinates of the GPS signal with a location of the at least one first user.

16 . The method of claim 15 , wherein determining the triadic match comprises:

logging an event as a record failure in the historical record data when the check-in status indicates that a location of the at least one second user does not correspond to the location of the at least one first user at the triadic session time.

17 . The method of claim 11 , wherein determining the triadic match comprises:

parsing external data comprising weather data;

determining an availability disruption as a function of the external data and the set of second user profile data; and

determining the triadic match as a function of the availability disruption.

18 . The method of claim 11 , wherein determining the triadic match comprises

selecting a weight distribution over a plurality of decision parameters of the triadic machine-learning model as a function of the one or more first user classification groups; and

determining a compatibility score for each potential triadic match by applying the selected weight distribution to the plurality of decision parameters.

19 . The method of claim 18 , wherein selecting the weight distribution comprises selecting the weight distribution over at least a physical proximity between the at least one first and second users as a function of a deficiency type of the one or more first user classification groups.

20 . The method of claim 11 , wherein appending the triadic match comprises:

receiving a user interaction from the graphical user interface, wherein the user interaction comprises a candidate session rejection; and

appending the triadic match as a function of the user interaction.

Assignments (2)

References Cited (9)