Data-enabled success and progression system

• US 10,482,391 B1
• Filed: 04/20/2016
• Issued: 11/19/2019
• Est. Priority Date: 08/28/2015
• Status: Active Grant

• Current Assignee: Pearson Education Incorporated (Pearson plc)
• Original Assignee: Pearson Education Incorporated (Pearson plc)
• Inventors: Lynch, Jay K.
• Primary Examiner(s): Lu, Kuen S
• Application Number:
  US15/134,246
• Time in Patent Office: 1,308 Days
• Field of Search: 706 12
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06Q 10/00 Administration; Management

Abstract

Systems and method for remote intervention are disclosed herein. The system can include a memory including: a user profile database; and a model database. The system can include a user device and a supervisor device, each of which including: a network interface; and an I/O subsystem. The system can include a content management server that can: receive data identifying a user of the user device; retrieve user data for the user from the user profile database; retrieve a risk model from the model database; generate a risk value based on the risk model; generate an action recommendation identifying an action for completion; and generate and send an alert to the supervisor device, which alert includes the action recommendation and includes computer code to trigger activation of the I/O subsystem of the supervisor device to provide the action recommendation.

Claims

1. A system for remote intervention comprising:

memory comprising;

a user profile database comprising information identifying one or several attributes of a user; and

a model database comprising a risk model and categorization data identifying a plurality of alert categories;

a user device comprising;

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

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

a supervisor device comprising;

a second network interface configured to exchange data via the communication network; and

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

a content management server, wherein the content management server is configured to;

receive data identifying a user of the user device;

retrieve user data for the user from the user profile database;

retrieve a risk model from the model database;

input the user data into the risk model to generate a risk value, wherein the risk value is indicative of the likelihood of the user failing to achieve a predetermined outcome;

identify a user categorization according to a classification algorithm;

determine a response attribute for the user, wherein the response attribute identifies the degree of a positive or negative user response to an intervention;

generate an action recommendation identifying an action for completion, wherein the action recommendation is generated based on the response attribute;

generate and send an alert to the supervisor device, wherein the alert comprises the action recommendation, and wherein the alert comprises computer code to trigger activation of the I/O subsystem of the supervisor device to provide the action recommendation; and

select, based on the response attribute, from a plurality of potential dashboard updates stored in a dashboard database, a dashboard update, wherein the dashboard update;

positively affects the risk value, and decreases the risk value of the user failing to achieve the predetermined outcome;

includes, on a second dashboard, a new dashboard data, dashboard architecture, and dashboard content that was not displayed on a first dashboard, the new dashboard data, dashboard architecture, and dashboard content including the alert; and

includes an identification field, a performance field, a participation field, and a notification field displayed in a different position on the second dashboard than on an original position on the first dashboard, wherein the new dashboard data, dashboard architecture, and dashboard content includes a risk field including a graphical depiction of the risk value indicative of the likelihood of the user failing to achieve the predetermined outcome.

2. The system of claim 1, wherein identifying the user categorization according to the classification algorithm comprises:

selecting some of the one or several attributes of the user identified in the user data;

determining correspondence of the selected some of the one or several attributes to attributes of each of a plurality of categorizations; and

generating an inclusion value for one categorization of the plurality of categorizations, wherein the inclusion value is indicative of a likelihood of the user belonging to that one categorization.

3. The system of claim 2, wherein identifying the user categorization according to the classification algorithm further comprises:

identifying the user categorization as that of the one categorization when the inclusion value is larger than a threshold value.

4. The system of claim 2, wherein the plurality of categorizations comprise:

a first category associated with decreased risk in response to an action; and

a second category associated with increased risk in response to an action.

5. The system of claim 1, wherein identifying the user categorization according to the classification algorithm comprises:

selecting some of the one or several attributes of the user identified in the user data;

determining correspondence of the selected some of the one or several attributes to attributes to each of a plurality of categorizations;

generating inclusion values for each of the plurality of categorizations, wherein each inclusion value is indicative of a likelihood of the user belonging to a categorization of the plurality of categorizations associated with the inclusion value; and

identifying the user categorization as that of the categorization associated with the categorization value indicative of the greatest likelihood of the user belonging to the categorization associated with the inclusion value.

6. The system of claim 1, wherein the action recommendation identifies an intervention.

7. The system of claim 6, wherein the risk model comprises a machine learning model.

8. The system of claim 7, wherein the machine learning model comprises a decision tree learning model.

9. The system of claim 1, wherein the content management server is further configured to:

generate a priority value indicative of relative priority of the action associated with the action recommendation; and

wherein the alert comprises the priority value.

10. A method for remote intervention comprising:

receiving at a content management server data identifying a user of a user device, wherein the user device comprises;

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

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

retrieving user data for the user comprising information identifying one or several attributes of the user from a user profile database;

retrieving a risk model from a model database;

automatically inputting the user data into the risk model with the content management server to generate a risk value, wherein the risk value is indicative of the likelihood of the user failing to achieve a predetermined outcome;

identifying with the content management server a user categorization according to a classification algorithm;

determining a response attribute for the user with the content management server, wherein the response attribute identifies the degree of a positive or negative user response to an intervention;

generating an action recommendation with the content management server, wherein the action recommendation identifies an action for completion, and wherein the action recommendation is generated based on the response attribute; and

generating and sending an alert to a supervisor device from the content management server, wherein the alert comprises the action recommendation, and wherein the alert comprises computer code to trigger activation of an I/O subsystem of the supervisor device to provide the action recommendation to a supervisor-user

selecting, based on the response attribute, from a plurality of potential dashboard updates stored in a dashboard database, a dashboard update, wherein the dashboard update;

positively affects the risk value, and decreases the risk value of the user failing to achieve the predetermined outcome;

includes, on a second dashboard, a new dashboard data, dashboard architecture, and dashboard content that was not displayed on a first dashboard, the new dashboard data, dashboard architecture, and dashboard content including the alert; and

includes an identification field, a performance field, a participation field, and a notification field displayed in a different position on the second dashboard than on an original position on the first dashboard, wherein the new dashboard data, dashboard architecture, and dashboard content includes a risk field including a graphical depiction of the risk value indicative of the likelihood of the user failing to achieve the predetermined outcome.

11. The method of claim 10, wherein identifying the user categorization according to the classification algorithm comprises:

selecting some of the one or several attributes of the user identified in the user data;

determining correspondence of the selected some of the one or several attributes to attributes of each of a plurality of categorizations; and

generating an inclusion value for one categorization of the plurality of categorizations, wherein the inclusion value is indicative of a likelihood of the user belonging to that one categorization.

12. The method of claim 11, wherein identifying the user categorization according to the classification algorithm further comprises:

identifying the user categorization as that of the one categorization when the inclusion value is larger than a threshold value.

13. The method of claim 11, wherein the plurality of categorizations comprise:

a first category associated with decreased risk in response to an action; and

a second category associated with increased risk in response to an action.

14. The method of claim 10, wherein identifying the user categorization according to the classification algorithm comprises:

selecting some of the one or several attributes of the user identified in the user data;

determining correspondence of the selected some of the one or several attributes to attributes to each of a plurality of categorizations;

generating inclusion values for each of the plurality of categorizations, wherein each inclusion value is indicative of a likelihood of the user belonging to a categorization of the plurality of categorizations associated with the inclusion value; and

identifying the user categorization as that of the categorization associated with the categorization value indicative of the greatest likelihood of the user belonging to the categorization associated with the inclusion value.

15. The method of claim 10, wherein the action recommendation identifies an intervention.

16. The method of claim 15, wherein the risk model comprises a machine learning model.

17. The method of claim 16, wherein the machine learning model comprises a decision tree learning model.

18. The method of claim 10 further comprising:

generating a priority value indicative of relative priority of the action associated with the action recommendation; and

wherein the alert comprises the priority value.