Granted Patent B2

US 12,361,348 · App. 17/448,740 · Granted Jul 15, 2025

Inventors: Christopher D. Kasabach (Brooklyn, NY); Andrew Michael Tikofsky (Oakland, CA)

Assignee: The trustee of the Thomas J. Watson Foundation

G06Q10/063112G06F16/2455

Abstract

Claims (42)

1. A computer-implemented method for identifying or developing a potential of a user, the method comprising:

training, by one or more processors, a machine learning model using a first set of labeled free-living activity data to create a mapping between multidimensional vectors of the first set of free-living activity data and one or more values for personal, professional, and cultural components;

receiving, by the one or more processors, a second set of free-living activity data of the user captured with one or more electronic devices;

sequencing, by the one or more processors, the second set of free-living activity data into a first set of multidimensional vectors, wherein a multidimensional vector comprises values for personal, professional, and cultural components of the second set of free-living activity data;

mapping, using the trained machine learning model, the first set of multidimensional vectors into a multidimensional space of components;

identifying, based on the mapping, a goal for the user, wherein the identifying comprises:

determining a distribution of the first set of multidimensional vectors in the multidimensional space of components,

searching for a gap in the distribution, and

assigning values for the personal, professional, and cultural components for the goal based on a location of the gap in the multidimensional space of components;

synthesizing, by the one or more processors, an experience for the user, wherein synthesizing the experience comprises generating multidimensional vectors with values for personal, professional, and cultural components for a set of experiences and selecting the experience based on a similarity score between the values of the components of the experience and the values of the components of the goal; and

delivering a suggestion of the experience to the user;

receiving a selection, from the second user, of an experience from the set of experiences; and

retraining, by the one or more processors, the machine learning model based, at least in part, on the received selection.

2. The method of claim 1 , wherein the experience is at least one of an activity, a career path, an educational milestone, or a travel destination.

3. The method of claim 1 , further comprising:

sequencing the experience into a second multidimensional vector;

mapping the second multidimensional vector into the multidimensional space of criteria; and

identifying at least one relationship between the mapping of the first multidimensional vector and the mapping of the second multidimensional vector.

4. The method of claim 3 , wherein the at least one relationship comprises a distance measure.

5. The method of claim 3 , wherein the at least one relationship comprises a relative location of the mappings in the multidimensional space.

6. The method of claim 3 , wherein the goal comprises at least one goal relationship between the mapping of the first multidimensional vector and the mapping of the second multidimensional vector.

7. The method of claim 1 , further comprising:

receiving user feedback in response to the suggestion of the experience; and

updating the goal based on the user feedback.

8. The method of claim 1 , further comprising:

identifying activities in the second set of free-living activity data; and

synthesizing the experience based on the activities.

9. The method of claim 1 , wherein the second set of free-living activity data is collected from a wearable device.

10. The method of claim 9 , wherein data collected from the wearable device comprises physiological data of the user.

11. The method of claim 1 , wherein sequencing the second set of free-living activity data into the first multidimensional vector comprises comparing fee-living data against a library of labeled free-living data.

12. The method of claim 1 , further comprising:

synthesizing a second experience for the user;

delivering a suggestion of the second experience to the user;

receiving an indication of a selection between the suggestion of the experience and the suggestion of the second experience; and

updating the goal for the user based on the received indication.

13. The method of claim 1 , wherein the second set of free-living activity data comprises a sequence of free-living activities, and wherein synthesizing the experience for the user comprises synthesizing based on the sequence.

14. The method of claim 1 , wherein the second set of free-living activity data comprises at least one of: user location, duration of activities, choices between activities, temporal relationship between activities, type of activity, number of other participants in the activity, or level or participation in the activity.

15. The method of claim 1 , further comprising:

querying at least one database for activity information associated with the second set of free-living activity data; and

sequencing the second set of free-living activity data into the first multidimensional vector based on the activity information.

16. The method of claim 15 , wherein the activity information includes data about a locations associated with the second set of free-living activity data.

17. The method of claim 16 , wherein the activity information includes data from social media associated with the second set of free-living activity data.

Assignments (1)

Continuity (2)

References Cited (21)