Systems and method for dynamic hybrid content sequencing

1. A system for hybrid content provisioning, the system comprising:

a memory comprising a learning-asset database comprising a plurality of learning assets each comprising a link directing to educational content, wherein at least some of the educational content is stored on a remote content platform; and

at least one server configured to execute a user microservice, wherein the at least one server is configured to:

identify a set of learning assets with each of the learning assets comprising a link to educational content and associated metadata;

automatically determine a sequencing of learning assets in the set of learning assets, wherein the sequencing is partially adaptive-based such that the sequencing is partially determined according to one or more machine learning models and partially non-adaptive-based such that the sequencing is partially determined according to one or more rules;

generate a graph-based representation of the set of learning assets based on the determined sequencing, the graph-based representation comprising nodes representing the set of learning assets and edges for linking the set of learning assets based on the sequencing;

receive a request for a local-user microservice that is unique to a specific user;

identify a portion of the graph-based representation relevant to the local-user microservice; and

provide a local copy of the portion of the graph-based representation relevant to the local-user microservice.

2. The system of claim 1 , wherein the at least one server is further configured to retrieve a content model associated with the set of learning assets.

3. The system of claim 2 , wherein the content model is retrieved from the memory.

4. The system of claim 1 , wherein the user microservice comprises a platform-user microservice and the at least one server is configured to execute the platform-user microservice to:

synchronize operation of the platform-user microservice and the local-user microservice;

persist user state data and identify next learning assets for presentation;

interact with the asset sequencer to select next learning assets according to the one or more machine learning models;

retrieve the identified next learning assets; and

evaluate performance of the user.

5. The system of claim 4 , wherein the at least one server is further configured to:

identify the requested local-user microservice from a set of pre-created local-user microservices; and

provide the requested local-user microservice.

6. The system of claim 5 , wherein the at least one server is further configured to synchronize state data by receiving updated state information identifying an updated state for the user.

7. The system of claim 6 , wherein the at least one server is further configured to, subsequent to synchronizing the state data:

receive a content request; and

select a next learning asset for presentation according to the one or more machine learning models.

8. The system of claim 7 , wherein the at least one server is further configured to provide the next learning asset to the local-user microservice.

9. The system of claim 8 , wherein the at least one server is further configured to:

receive a user response to the provided learning asset from the user;

evaluate the user response to the provided learning asset;

update a user model characterizing user mastery; and

update local user state data based on the updated user model.

10. A method of hybrid content provisioning, the method comprising:

identifying a set of learning assets by executing a microservice, each of the learning assets comprising a link to educational content and associated metadata;

automatically determining, by executing the microservice, a sequencing of learning assets in the set of learning assets, wherein the sequencing is partially adaptive-based such that the sequencing is partially determined according to one or more machine learning models and partially non-adaptive-based such that the sequencing is partially determined according to one or more rules;

generating a graph-based representation of the set of learning assets based on the determined sequencing, the graph-based representation comprising nodes representing the set of learning assets and edges for linking the set of learning assets based on the sequencing;

receiving a request for a local-user microservice that is unique to a specific user;

identifying a portion of the graph-based representation relevant to the local-user microservice; and

providing a local copy of the portion of the graph-based representation relevant to the local-user microservice.

11. The method of claim 10 , further comprising retrieving, by executing the microservice, a content model associated with the set of learning assets.

12. The method of claim 10 , further comprising:

identifying the requested local-user microservice from a set of pre-created local-user microservices; and

providing the requested local-user microservice.

13. The method of claim 12 , further comprising synchronizing state data by receiving updated state information identifying an updated state for a user.

14. The method of claim 13 , further comprising executing a platform-user microservice to:

synchronize operation of a platform-user microservice and the local-user microservice;

select learning assets for presentation to the user according to the one or more machine learning models;

present the learning assets to the user; and

evaluate performance of the user by scoring responses submitted by the user to the learning assets.

15. The method of claim 13 , further comprising, subsequent to synchronizing the state data:

receiving a content request; and

selecting, by executing a platform-user microservice, a next learning asset for presentation.

16. The method of claim 15 , further comprising providing the next learning asset to the local-user microservice.

17. The method of claim 16 , further comprising:

receiving a user response to the provided learning asset;

evaluating the user response to the provided learning asset;

updating a user model characterizing user mastery; and

updating local user state data based on the updated user model.

18. A non-transitory computer-readable storage medium having instructions stored thereon that, when executed by at least one processor, cause the at least one processor to implement operations comprising:

identifying a set of learning assets by executing a microservice, each of the learning assets comprising a link to educational content and associated metadata;

automatically determining, by executing the microservice, a sequencing of learning assets in the set of learning assets, wherein the sequencing is partially adaptive-based such that the sequencing is partially determined according to one or more machine learning models and partially non-adaptive-based such that the sequencing is partially determined according to one or more rules;

generating a graph-based representation of the set of learning assets based on the determined sequencing, the graph-based representation comprising nodes representing the set of learning assets and edges for linking the set of learning assets based on the sequencing;

receiving a request for a local-user microservice that is unique to a specific user;

identifying a portion of the graph-based representation relevant to the local-user microservice; and

providing a local copy of the portion of the graph-based representation relevant to the local-user microservice.

19. The computer-readable medium of claim 18 , wherein the one or more machine learning models are trained based on inputs that identify attributes of the user.

20. The computer-readable medium of claim 18 , wherein the one or more machine learning models are trained based on inputs that identify attributes of the educational content.