System and method for content provisioning with dual recommendation engines

• US 10,614,368 B2
• Filed: 08/12/2016
• Issued: 04/07/2020
• Est. Priority Date: 08/28/2015
• Status: Active Grant

• Current Assignee: Pearson Education Incorporated (Pearson plc)
• Original Assignee: Pearson Education Incorporated (Pearson plc)
• Inventors: Moriarty, Brian, McFall, Greg
• Primary Examiner(s): Afshar, Kamran
• Assistant Examiner(s): Buss, Benjamin J
• Application Number:
  US15/236,238
• Publication Number:
  US 20170178002A1
• Time in Patent Office: 1,334 Days
• Field of Search: None
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/52 specially adapted for the location of the user terminal
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04L 67/567 Integrating service provisioning from a plurality of service providers

Abstract

Systems and methods for content selection with first and second recommendation engines are disclosed herein. The system can include a memory include a content library database and a model database. The system can include a user device having a first network interface and a first I/O subsystem. The system can include one or more servers that can include a packet selection system and a presentation system. These one or more servers can: receive response data from the user device; provide received response data to a first recommendation engine; alert a second recommendation engine when a selected next node is a placeholder node; retrieve at least one statistical model relevant to selection of next node content; and select next node content based on an output of the at least one statistical model.

Claims

1. A system for content selection with a rules-based recommendation engine and an adaptive recommendation engine, the system comprising:

memory comprising;

a content library database comprising a plurality of nodes arranged in a content network, wherein the nodes in the content network are pairwise connected via a plurality of edges, wherein some of the nodes in the content network are associated with a data packet and a guard condition, and wherein some of the nodes in the content network are associated with a database of placeholder content; and

a model database comprising a plurality of models relating to at least one of;

a user skill level or a data packet difficulty level;

a user device comprising;

a first network interface configured to exchange data via a communication network; and

a first I/O subsystem configured to convert electrical signals to user interpretable outputs via a user interface; and

one or more servers comprising a packet selection system and a presentation system, wherein the one or more servers are configured to;

receive response data from the user device;

provide received response data to a rules-based recommendation engine, wherein the rules-based recommendation engine is configured to select a next node based on a current location in the content network, potential next nodes, past response data, and one or several guard conditions associated with the potential next nodes;

alert an adaptive recommendation engine when a selected next node comprises a placeholder node, wherein the placeholder node is associated with the database of placeholder content the adaptive recommendation engine performing;

retrieving at least one model relevant to selection of next node content; and

selecting next node content based on an output of the at least one model;

generate subsequent output based at least in part on the rules-based recommendation engine when the selected next node is determined to not be a placeholder node, the subsequent output linked directly to the selected next node.

2. The system of claim 1, wherein providing received response data to the rules-based recommendation engine further comprises selecting a next node.

3. The system of claim 2, wherein selecting the next node comprises:

identifying potential next nodes; and

retrieving guard conditions, wherein each guard condition defines one or several prerequisites for entry into one of the potential next nodes.

4. The system of claim 2, wherein identifying potential next nodes comprises:

identifying the user'"'"'s location in the content network, wherein the user'"'"'s location in the content network comprises an origin node;

identifying edges extending from the origin node; and

identifying non-prerequisite nodes connected to the origin node via the identified edges.

5. The system of claim 4, wherein selecting the next node further comprises:

identifying the user associated with the user device; and

retrieving the user history from the memory.

6. The system of claim 5, wherein selecting the next node further comprises application of the user history to the guard conditions of the potential next nodes.

7. The system of claim 6, wherein application of the user history to the guard conditions of the potential next nodes comprises:

(a) selecting one of the potential next nodes;

(b) identifying of a guard condition associated with the selected potential next node;

(c) comparing the guard condition with the user history; and

(d) associating a first value with the selected one of the potential next nodes when the comparison of the guard condition with the user history indicates that the guard condition is met.

8. The system of claim 7, wherein steps (a)-(d) are repeated for each of the potential next nodes.

9. The system of claim 8, wherein selecting next node content based on an output of the at least one model comprises:

identifying the user associated with the user device;

retrieving the user history; and

identifying potential next node content.

10. The system of claim 9, wherein selecting next node content based on an output of the at least one model comprises:

identifying one or several features of at least one of;

the potential next node content or the user history;

extracting the identified one or several features; and

inputting some or all of the one or several features into the retrieved at least one model.

11. The system of claim 10, wherein selecting next node content based on an output of the at least one model comprises generating an output with the retrieved at least one model based on the input some or all of the one or several features.

12. The system of claim 11, wherein the one or more servers are further configured to provide the selected next node content to the user device.

13. The system of claim 12, wherein providing the selected next node content to the user device comprises:

generating a plurality of electrical signals comprising the selected next node content; and

sending the electrical signal to the user device.

14. The system of claim 1, wherein the rules-based recommendation engine is in the presentation system and wherein the adaptive recommendation engine is in the packet selection system.

15. A method for content selection with a rules-based recommendation engine and an adaptive recommendation engine, the method comprising:

receiving response data from a user device at one or more servers comprising a packet selection system and a presentation system;

automatically providing received response data to a rules-based recommendation engine, wherein the rules-based recommendation engine is configured to select a next node based on;

a current location in the content network, potential next nodes, past response data, and one or several guard conditions associated with the potential next nodes;

alerting an adaptive recommendation engine when a selected next node comprises a placeholder node, wherein a placeholder node is associated with a database of placeholder content the adaptive recommendation engine performing;

retrieving at least one model relevant to selection of next node content from a model database comprising a plurality of models relating to at least one of;

a user skill level or a data packet difficulty level; and

selecting next node content based on an output of the at least one model;

generating subsequent output based at least in part on the rules-based recommendation engine when the selected next node is determined to not be a placeholder node, the subsequent output linked directly to the selected next node.

16. The method of claim 15, further comprising providing the selected next node content to the user device.

17. The method of claim 16, wherein providing the selected next node content to the user device comprises:

generating a plurality of electrical signals comprising the selected next node content; and

sending the electrical signal to the user device.

18. The method of claim 17, wherein the rules-based recommendation engine is in the presentation system and wherein the adaptive recommendation engine is in the packet selection system.

19. The method of claim 17, wherein selecting next node content based on an output of the at least one model comprises:

identifying the user associated with the user device;

retrieving the user history; and

identifying potential next node content.

20. The method of claim 19, wherein selecting next node content based on an output of the at least one model comprises:

identifying one or several features of at least one of;

the potential next node content or the user history;

extracting the identified one or several features; and

inputting some or all of the one or several features into the retrieved at least one model.