Predictive recommendation engine

• US 9,667,321 B2
• Filed: 10/30/2015
• Issued: 05/30/2017
• Est. Priority Date: 10/31/2014
• Status: Active Grant

• Current Assignee: Pearson Education Incorporated (Pearson plc)
• Original Assignee: Pearson Education Incorporated (Pearson plc)
• Inventors: Rho, Yun Jin, Anderson, Jacob M., Kukartsev, Gennadiy A.
• Primary Examiner(s): Wong, Linda
• Application Number:
  US14/928,152
• Publication Number:
  US 20160127010A1
• Time in Patent Office: 578 Days
• Field of Search: 375219, 375220, 375221, 375222, 375224, 375240, 37524026-24027, 375284, 375285, 375278, 375295, 375316, 375324, 375340, 375346, 375347, 375354, 375356, 375211, 375213, 375147, 375148, 375358, 434322, 434350, 434362, 434323, 705 10, 705 7, 705769, 705E17014, 705 11, 705 52
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 50/20 Education
• CPC Class Codes: G09B 5/065 Combinations of audio and video presentations, e.g. videotapes, videodiscs, television systems
• CPC Class Codes: G09B 7/00 Electrically-operated teaching apparatus or devices working with questions and answers mechanically operated G09B3/00; computing arrangements G06F
• CPC Class Codes: G09B 7/02 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 Class Codes: G09B 7/07 providing for individual presentation of questions to a plurality of student stations
• CPC Class Codes: H04B 3/544 Setting up communications; Call and signalling arrangements
• CPC Class Codes: H04L 41/069 using logs of notifications; Post-processing of notifications
• CPC Class Codes: H04L 63/0272 Virtual private networks
• CPC Class Codes: Y04S 10/50 Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

Systems and methods for alerting a user device when an objective is mastered according to a piecewise Gaussian distribution updated according to a Bayesian method are disclosed herein. The system can include a user device having a network interface to exchange data with a server via a communication network, and an I/O subsystem to convert electrical signals to user interpretable outputs user interface. The system can include a server that can: receive a response from the user device; identify a user associated with the response; receive user attribute data; identify a next objective; provide a data packet from the aggregation of data packets to the user via the user device; receive a response from the user device; update the user attribute data according to a Bayesian method; and generate and provide an alert to the user device.

Claims

1. A system for alerting a user device when an objective is mastered according to a piecewise Gaussian distribution updated according to a Bayesian method, the system comprising:

a the user device comprising;

a network interface configured to exchange data with a server via a communication network; and

an I/O subsystem configured to convert electrical signals to user interpretable outputs; and

a server configured to;

receive a first response from the user device, the first response comprising an encoded data-carrying electrical signal;

from the encoded data-carrying electrical signal;

identify a user, wherein the user is associated with the first response;

receive user attribute data, wherein the user attribute data comprises a piecewise Gaussian distribution model of a user skill level and a user error value, and wherein the user attribute data, the user skill level, and the user error value are associated with the identified user;

identify a next objective, wherein the next objective is an aggregation of questions;

provide a first question from the aggregation of questions to the identified user via the user device;

receive a second response from the user device in response to the first question;

in response to receiving the second response from the user device;

update the user attribute data according to a Bayesian method, wherein the update to the user attribute data updates the piecewise Gaussian distribution model; and

in response to the update of the user attribute data, generate and provide an alert to the user device indicating to the identified user that the next objective is mastered, wherein the alert comprises a code to direct the user device to provide an indicator of the received alert via the I/O subsystem.

2. The system of claim 1, wherein the server is further configured to receive first question attribute data.

3. The system of claim 2, wherein the first question attribute data comprises a Gaussian distribution model of first question difficulty level.

4. The system of claim 3, wherein the server is configured to:

determine the user skill level by determining a mode of the piecewise Gaussian distribution; and

determine the first question difficulty level by determining the mode of the piecewise Gaussian distribution.

5. The system of claim 4, wherein the server is further configured to evaluate data of the second response.

6. The system of claim 5, wherein the user attribute data is updated according to the Bayesian method and according to the evaluation of the data of the second response.

7. The system of claim 6, wherein the update of the user attribute data positively shifts the mode of the piecewise Gaussian distribution when a desired second response is received.

8. The system of claim 6, wherein the update of the user attribute data negatively shifts the mode of the piecewise Gaussian distribution when an undesired second response is received.

9. The system of claim 6, wherein providing the first question comprises selecting a first question for the providing of the first question.

10. The system of claim 9, wherein selecting the first question comprises:

identifying a plurality of potential questions for providing to the identified user;

calculating a probability for each of these identified potential questions, wherein the probability is calculated based on the difficulty of the first question and the user skill level; and

identifying one of the plurality of potential questions for selection when the probability is within a desired range.

11. The system of claim 10, wherein the indicator of the received alert comprises one of:

an aural indicator;

a tactile indicator;

or a visual indicator.

12. A method for alerting a user device when an objective is mastered according to a piecewise Gaussian distribution updated according to a Bayesian method, the method comprising:

receiving a first response from a user device comprising a network interface configured to exchange data with a server via a communication network and an I/O subsystem configured to convert electrical signals to user interpretable outputs, the response comprising an encoded data-carrying electrical signal;

identifying a user associated with the first response;

receiving user attribute data, wherein the user attribute data comprises a piecewise Gaussian distribution model of a user skill level and a user error value based on the identified user;

identifying a next objective, wherein the next objective is an aggregation of questions;

providing a first question from the aggregation of questions to the identified user via the user device;

receiving a second response from the user device;

updating the user attribute data according to a Bayesian method, wherein the update to the user attribute data updates the piecewise Gaussian distribution model; and

in response to the updating of the user attribute data, generating and providing an alert to the user device indicating mastery of the next objective, wherein the alert comprises a code to direct the user device to provide an indicator of the received alert via the I/O subsystem.

13. The method of claim 12, further comprising receiving first question attribute data, wherein the first question attribute data comprises a Gaussian distribution model of data packet difficulty level.

14. The method of claim 13, further comprising:

determining the user skill level by determining a mode of the piecewise Gaussian distribution; and

determining the first question difficulty level by determining the mode of the piecewise Gaussian distribution.

15. The method of claim 14, further comprising evaluating data of the second response, and wherein the user attribute data is updated according to the Bayesian method and according to the evaluation of the data of the second response.

16. The method of claim 15, wherein the update of the user attribute data positively shifts the mode of the piecewise Gaussian distribution when a desired response is received.

17. The method of claim 15, wherein the update of the user attribute data negatively shifts the mode of the piecewise Gaussian distribution when an undesired response is received.

18. The method of claim 15, wherein providing the first question comprises selecting a first question for providing the first question.

19. The method of claim 18, wherein selecting the first question comprises:

identifying a plurality of potential questions for providing to the identified user;

calculating a probability for each of these identified potential questions, wherein the probability is calculated based on the difficulty of the first question and the user skill level; and

identifying one of the plurality of potential questions for selection

when the probability is within a desired range.

20. The method of claim 19, wherein the indicator of the received alert comprises one of:

an aural indicator;

a tactile indicator; and

or a visual indicator.