Dynamic education planning methods and systems

1 . A computer-implemented method for generating a plurality of education plans for a plurality of fellows, comprising:

receiving, via one or more processors, a set of fellow skill graphs,

each including a respective plurality of nodes, wherein each node represents a respective skill corresponding to a respective skill rating, and wherein a first node from the respective plurality of nodes is related to a second node from the respective plurality of nodes, and

each corresponding to a respective one of the plurality of fellows, wherein updating each of the set of fellow skill graphs comprises:

generating a first update to a corresponding skill rating of the first node based on updated performance information associated with the first node; and

generating a second update to a corresponding skill rating of the second node by propagating the first update based on one or more of:

one or more decay relevance value representing skill decay between the first node and the second node; or

one or more amplifying relevance value representing skill amplification between the first node and the second node;

receiving, via the one or more processors, a plurality of electronic calendar objects,

each corresponding to a respective one of the plurality of fellows, and

each including at least one free block of time;

processing, via the one or more processors, the set of fellow skill graphs and the plurality of electronic calendar objects using a trained machine learning model to predict a set of sessions corresponding to the plurality of fellows,

wherein the trained machine learning model is trained using successive evaluation of historical training samples to predict the set of sessions, the successive evaluation including creating weights of the trained machine learning model and adjusting the weights, and

and wherein processing the set of fellow skill graphs and the plurality of electronic calendar objects includes, for each fellow, determining that a corresponding session has a duration less than or equal to the at least one free block of time included in a corresponding electronic calendar object;

and

causing, via the one or more processors, the set of sessions to be displayed on a roadmap graphical user interface, wherein each of the set of sessions includes a respective session topic, a respective session type, a respective session date, a respective session start time and a respective session duration.

2 . The computer-implemented method of claim 1 ,

wherein processing, via the one or more processors, the set of fellow skill graphs and the plurality of electronic calendar objects using the trained machine learning model to predict the set of sessions corresponding to the plurality of fellows includes predicting the set of sessions based on one or more features included within the set of fellow skill graphs.

3 . The computer-implemented method of claim 2 ,

wherein at least one session in the set of sessions includes at least one of a session name, a session duration, a session mentor, or an indication of one or more fellow-mentees.

4 . The computer-implemented method of claim 1 ,

wherein processing, via the one or more processors, the set of fellow skill graphs and the plurality of electronic calendar objects using the trained machine learning model to predict the set of sessions corresponding to the plurality of fellows includes matching one or more fellows of the plurality of fellows to one or more sessions of the set of sessions based on one or both of (i) a respective skill level of the one or more fellows of the plurality of fellows, and (ii) a respective skill level of the one or more sessions of the set of sessions.

5 . The computer-implemented method of claim 4 ,

wherein matching the one or more fellows of the plurality of fellows to the one or more sessions of the set of sessions is based on mentor feedback or fellow feedback.

6 . The computer-implemented method of claim 1 ,

wherein the trained machine learning model is an unsupervised machine learning model trained to cluster the set of fellow skill graphs according to skill ratings, and further comprising:

processing the set of fellow skill graphs using the unsupervised machine learning model to predict the set of sessions.

7 . The computer-implemented method of claim 1 ,

wherein the trained machine learning model is a supervised machine learning model trained using historical skill ratings data, and further comprising:

processing the set of fellow skill graphs using the trained machine learning model to generate the set of sessions.

8 . A computing system for generating a plurality of education plans for a plurality of fellows, comprising:

one or more processors; and

one or more memories having stored thereon executable instructions that, when executed by the one or more processors, cause the computing system to:

receive, via the one or more processors, a set of fellow skill graphs,

each including a respective plurality of nodes, wherein each node represents a respective skill corresponding to a respective skill rating, and wherein a first node from the respective plurality of nodes is related to a second node from the respective plurality of nodes, and

each corresponding to a respective one of the plurality of fellows, wherein updating each of the set of fellow skill graphs comprises:

generating a first update to a corresponding skill rating of the first node based on updated performance information associated with the first node; and

generating a second update to a corresponding skill rating of the second node by propagating the first update based on one or more of:

one or more decay relevance value representing skill decay between the first node and the second node; or

one or more amplifying relevance value representing skill amplification between the first node and the second node;

receive, via the one or more processors, a plurality of electronic calendar objects,

each corresponding to a respective one of the plurality of fellows, and

each including at least one free block of time;

process, via the one or more processors, the set of fellow skill graphs and the plurality of electronic calendar objects using a trained machine learning model to predict a set of sessions corresponding to the plurality of fellows,

wherein the trained machine learning model is trained using successive evaluation of historical training samples to predict the set of sessions, the successive evaluation including creating weights of the trained machine learning model and adjusting the weights, and

and wherein processing the set of fellow skill graphs and the plurality of electronic calendar objects includes, for each fellow, determining that a corresponding session has a duration less than or equal to the at least one free block of time included in a corresponding electronic calendar object;

and

cause, via the one or more processors, the set of sessions to be displayed on a roadmap graphical user interface, wherein each of the set of sessions includes a respective session topic, a respective session type, a respective session date, a respective session start time and a respective session duration.

9 . The computing system of claim 8 , the one or more memories having stored thereon executable instructions that, when executed by the one or more processors, cause the computing system to:

predict the set of sessions based on one or more features included within the set of fellow skill graphs.

10 . The computing system of claim 9 ,

wherein at least one session in the set of sessions includes at least one of a session name, a session duration, a session mentor, or an indication of one or more fellow-mentees.

11 . The computing system of claim 8 , the one or more memories having stored thereon executable instructions that, when executed by the one or more processors, cause the computing system to:

match one or more fellows of the plurality of fellows to one or more sessions of the set of sessions based on one or both of (i) a respective skill level of the one or more fellows of the plurality of fellows, and (ii) a respective skill level of the one or more sessions of the set of sessions.

12 . The computing system of claim 11 , wherein matching the one or more fellows of the plurality of fellows to the one or more sessions of the set of sessions is based on mentor feedback or fellow feedback.

13 . The computing system of claim 8 ,

wherein the trained machine learning model is an unsupervised machine learning model trained to cluster the set of fellow skill graphs according to skill ratings, and the one or more memories having stored thereon executable instructions that, when executed by the one or more processors, cause the computing system to:

process the set of fellow skill graphs using the unsupervised machine learning model to predict the set of sessions.

14 . The computing system of claim 8 ,

wherein the trained machine learning model is a supervised machine learning model trained using historical skill ratings data, and the one or more memories having stored thereon executable instructions that, when executed by the one or more processors, cause the computing system to:

process the set of fellow skill graphs using the trained machine learning model to generate the set of sessions.

15 . A non-transitory computer-readable medium having stored thereon executable instructions that, when executed, cause a computer to:

receive, via one or more processors, a set of fellow skill graphs,

each including a respective plurality of nodes, wherein each node represents a respective skill corresponding to a respective skill rating, and wherein a first node from the respective plurality of nodes is related to a second node from the respective plurality of nodes, and

each corresponding to a respective one of a plurality of fellows, wherein updating each of the set of fellow skill graphs comprises:

generating a first update to a corresponding skill rating of the first node based on updated performance information associated with the first node; and

generating a second update to a corresponding skill rating of the second node by propagating the first update based on one or more of:

one or more decay relevance value representing skill decay between the first node and the second node; or

one or more amplifying relevance value representing skill amplification between the first node and the second node;

receive, via the one or more processors, a plurality of electronic calendar objects,

each corresponding to a respective one of the plurality of fellows, and

each including at least one free block of time;

process, via the one or more processors, the set of fellow skill graphs and the plurality of electronic calendar objects using a trained machine learning model to predict a set of sessions corresponding to the plurality of fellows,

wherein the trained machine learning model is trained using successive evaluation of historical training samples to predict the set of sessions, the successive evaluation including creating weights of the trained machine learning model and adjusting the weights, and

and wherein processing the set of fellow skill graphs and the plurality of electronic calendar objects includes, for each fellow, determining that a corresponding session has a duration less than or equal to the at least one free block of time included in a corresponding electronic calendar object;

and

cause, via the one or more processors, the set of sessions to be displayed on a roadmap graphical user interface, wherein each of the set of sessions includes a respective session topic, a respective session type, a respective session date, a respective session start time and a respective session duration.

16 . The non-transitory computer-readable medium of claim 15 , having stored thereon executable instructions that, when executed, cause a computer to:

predict the set of sessions based on one or more features included within the set of fellow skill graphs.

17 . The non-transitory computer-readable medium of claim 16 ,

wherein at least one session in the set of sessions includes at least one of a session name, a session duration, a session mentor, or an indication of one or more fellow-mentees.

18 . The non-transitory computer-readable medium of claim 15 , having stored thereon executable instructions that, when executed, cause a computer to:

match one or more fellows of the plurality of fellows to one or more sessions of the set of sessions based on one or both of (i) a respective skill level of the one or more fellows of the plurality of fellows, and (ii) a respective skill level of the one or more sessions of the set of sessions.

19 . The non-transitory computer-readable medium of claim 18 , wherein matching the one or more fellows of the plurality of fellows to the one or more sessions of the set of sessions is based on mentor feedback or fellow feedback.

20 . The non-transitory computer-readable medium of claim 15 ,

wherein the trained machine learning model is an unsupervised machine learning model trained to cluster the set of fellow skill graphs according to skill ratings, and having stored thereon executable instructions that, when executed, cause a computer to:

process the set of fellow skill graphs using the unsupervised machine learning model to predict the set of sessions.