Platform-agnostic Bayes net content aggregation system and method

Patent metadata

Field	Value
Publication number	US-10839304-B2
Application number	US-201815878272-A
Country	US
Kind code	B2
Filing date	Jan 23, 2018
Priority date	Jan 25, 2017
Publication date	Nov 17, 2020
Grant date	Nov 17, 2020

Abstract

Systems and methods for automatic generating of a Bayes net content graph are disclosed herein. The system can include a memory including a mapping matrix. The system can include at least one server. The at least one server can generate a user matrix having n columns and p rows. In some aspects, each of the n columns is associated with a student and each of the p rows is associated with a content item. The at least one server can: store the user matrix in the memory; retrieve the mapping matrix from the memory; iteratively identify prerequisite relationships between the skills identified in the user matrix; generate edges between the skills in the user matrix based on the iteratively identified prerequisite relationships; and orient the edges between the skill.

First claim

What is claimed is:

1. A system for automatic generating a content assignment, the system comprising:
a memory comprising:
a prerequisite matrix comprising a matrix representation of a first level prerequisite graph, the first level prerequisite graph comprising a plurality of linked first-level nodes, each of the first-level nodes representing a learning objective, and of a third level prerequisite graph, the third level prerequisite graph comprising a plurality of linked third-level nodes, each of the third-level nodes representing a content item; and

at least one server configured to:
retrieve the third level prerequisite graph from the memory;
automatically generate a plurality of second level prerequisite graphs, each of the plurality of second level prerequisite graphs comprising a plurality of linked second-level nodes, wherein each of the second-level nodes represents a skill, wherein the second level prerequisite graph is generated based on the third-level prerequisite graph, and wherein automatically generating the second prerequisite graph comprises iteratively applying an expectation step and a maximization step until stop criteria are achieved;
identify one of the plurality of second level prerequisite graphs as a final second level prerequisite graph, wherein identifying one of the plurality of second level prerequisite graphs as the final second level prerequisite graph comprises eliminating equivalent second level prerequisite graphs with the at least one server via generation of edges linking the nodes of the plurality of second level prerequisite graphs in prerequisite relationships such that a first node representing a prerequisite skill to a second node is identified in the second level prerequisite graph as a parent node of the second node;
forming an integrated prerequisite graph from: the first level prerequisite graph;

the second level prerequisite graph; and the third level prerequisite graph;
receive a selection of objectives;
identify from the first level prerequisite graph missing objectives;
supplement the received objectives with at least some of the missing objectives;
package the received objective and the supplemented missing objectives into a content assignment; and
deliver content in the content assignment, wherein the delivered content is selected based on a statistical correspondence between skills associated with the objectives and skills associated with content items.

2. The system of claim 1 , wherein the prerequisite graph comprises a directed acyclic graph.

3. The system of claim 2 , wherein the prerequisite graph comprises a plurality of nodes pairwise linked by an edge in a hierarchical relationship.

4. The system of claim 3 , wherein each of the objectives is associated with a node in the first level prerequisite graph.

5. The system of claim 4 , wherein the at least one server is further configured to provide the content assignment to a user device.

6. The system of claim 5 , wherein the at least one server is further configured to select content forming part of the content assignment based on a statistical correspondence between skills associated with the objectives and skills associated with content items.

7. The system of claim 6 , wherein identifying the missing objectives comprises:
identifying selected objectives;
receiving user information; and
determining prerequisite objectives to the selected objectives.

8. The system of claim 7 , wherein identifying the missing objectives further comprises:
determining mastery of the prerequisite objectives to the selected objectives; and
identifying one of the prerequisite objectives to the selected objectives as missing when the one of the prerequisite objectives is unmastered.

9. The system of claim 8 , wherein mastery of a one of the prerequisite objectives is determined based on at least one conditional probability linking the one or the prerequisite objectives to other objectives in the first level prerequisite graph and previously received user responses.

10. The system of claim 9 , wherein the at least one server is further configured to receive a request for providing of the content assignment from a user device, and wherein the delivered content in the content assignment is delivered to the requesting user device.

11. A method of generating and delivering a content assignment, the method comprising:
retrieving a third level prerequisite graph from a memory communicatingly coupled with a processor, the third level prerequisite graph comprising a plurality of linked third-level nodes, each of the third-level nodes representing a content item;
automatically generating, with the processor, a plurality of second level prerequisite graphs, each of the plurality of second level prerequisite graphs comprising a plurality of linked second-level nodes, wherein each of the second-level nodes represents a skill, wherein the second level prerequisite graph is generated based on the third level prerequisite graph, and wherein automatically generating the second prerequisite graph comprises iteratively applying an expectation step and a maximization step until stop criteria are achieved;
identify with the processor one of the plurality of second level prerequisite graphs as a final second level prerequisite graph, wherein identifying one of the plurality of second level prerequisite graphs as the final second level prerequisite graph comprises eliminating equivalent second level prerequisite graphs with the processor via generation of edges linking the nodes of the plurality of second level prerequisite graphs in prerequisite relationships such that a first node representing a prerequisite skill to a second node is identified in the second level prerequisite graph as a parent node of the second node;
forming an integrated prerequisite graph from: a first level prerequisite graph comprising objectives; the second level prerequisite graph; and the third level prerequisite graph;
receiving a selection of objectives;
identifying with the processor missing objectives from a first level prerequisite graph of a prerequisite graph, wherein the prerequisite graph is represented in a prerequisite matrix;
supplementing the received objectives with at least some of the missing objectives;
packaging with the processor the received objective and the supplemented missing objectives into a content assignment; and
delivering content in the content assignment, wherein the delivered content is automatically selected with the processor based on a statistical correspondence between skills associated with the objectives and skills associated with content items.

12. The method of claim 11 , wherein the prerequisite graph comprises a directed acyclic graph.

13. The method of claim 12 , wherein the prerequisite graph comprises a plurality of nodes pairwise linked by an edge in a hierarchical relationship.

14. The method of claim 13 , wherein each of the objectives is associated with a node in the first level prerequisite graph.

15. The method of claim 14 , further comprising providing the content assignment to a user device.

16. The method of claim 15 , further comprising selecting content forming part of the content assignment based on a statistical correspondence between skills associated with the objectives and skills associated with content items.

17. The method of claim 16 , wherein identifying the missing objectives comprises:
identifying selected objectives;
receiving user information; and
determining prerequisite objectives to the selected objectives.

Assignees

• Pearson Education Inc

Inventors

• Corbin James David
• Larusson Johann
• Strong David
• Fredrich Todd
• Stewart Timothy

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G09B7/02 Primary

  of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student · CPC title

• G06F18/2323

  based on graph theory, e.g. minimum spanning trees [MST] or graph cuts · CPC title

• G06F18/29

  Graphical models, e.g. Bayesian networks · CPC title

• G06F16/9024

  Graphs; Linked lists (G06F16/9027 takes precedence) · CPC title