IP Library › Granted Patent US 12,353,444
Granted Patent B1
US 12,353,444 · App. 18/887,313 · Granted Jul 8, 2025

Systems and methods for machine learning to assess and increase user engagement from user inputs

Inventors: Neeru Khosla (Portola Valley, CA); Nimish Pachapurkar (Fremont, CA); Miral Shah (San Jose, CA)
Assignee: CK12 Foundation
G06F16/287G06N20/00
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,353,444
App. No.
18/887,313
Granted
Jul 8, 2025
Kind
B1
Abstract

A method including receiving at least one input, detecting at least one parameter associated with a context, generating, by a machine learning model, a first set of data classes enriched with the context, determining if each data class is associated with a data class repository to define a subset of data classes not associated with a data class repository, and generating, by a machine learning model, at least one data class repository for each data class. The method includes generating a display signal to display information associated with at least one data class repository, the display signal associated with a graphical user interface, altering, using a machine learning model, the display signal by altering at least one portion of the graphical user interface associated with the context, and sending the display signal to display the at least one portion of the graphical user interface on the user device.

Claims (51)

1. A method, comprising:

receiving, by a compute device, at least one input from at least one of a user device of a user or at least one database;

detecting, by the compute device, at least one parameter from the at least one input, the at least one parameter associated with a context;

generating, by a first machine learning model and based on the at least one parameter, a first set of data classes, the first set of data classes enriched with the context;

determining, by the compute device, if each data class from the first set of data classes is associated with a data class repository to define a subset of data classes, the subset of data classes including data classes that are not associated with a data class repository;

generating, by a second machine learning model, at least one data class repository for each data class from the subset of data classes;

generating a display signal to display, on the user device, information associated with at least one data class repository associated with the first set of data classes, the display signal associated with a graphical user interface;

altering, using a third machine learning model based on the context, the display signal, wherein altering the display signal includes altering at least one portion of the graphical user interface associated with the context; and

sending the display signal to display the at least one portion of the graphical user interface on the user device.

2. The method of claim 1 , wherein the at least one parameter includes at least one of a goal associated with the user or an interest of the user.

3. The method of claim 1 , wherein the data classes include learning content.

4. The method of claim 1 , further comprising:

determining, using a reinforcement learning model, a set of actions associated with the at least one parameter;

determining, using the reinforcement learning model, at least one recommended action from the set of actions based on a user parameter associated with the user; and

executing the at least one recommended action.

5. The method of claim 1 , wherein the at least one parameter is associated with user engagement.

6. The method of claim 1 , wherein the context is associated with learning behaviors associated with the user.

7. The method of claim 1 , wherein the at least one input includes user interactions with a conversation model.

8. The method of claim 1 , further comprising:

removing, from the first set of data classes, data classes associated with a set of learned data classes of the user.

9. A non-transitory processor-readable medium storing code representing instructions to be executed by one or more processors, the instructions comprising code to cause the one or more processors to:

receive, by a compute device, at least one input from at least one of a user device of a user or at least one database;

detect, by the compute device, at least one parameter from the at least one input;

generate, by a first machine learning model and based on the at least one parameter, a first set of data classes;

determine, by the compute device, if each data class from the first set of data classes is associated with a data class repository to define a subset of data classes, the subset of data classes including data classes that are not associated with a data class repository;

generate, by a second machine learning model, at least one data class repository for each data class from the subset of data classes;

enrich the at least one data class repository with at least one content enrichment, the at least one content enrichment associated with the at least one parameter and a context;

generate a display signal to display, on the user device, information associated with at least one data class repository associated with the first set of data classes, the display signal associated with a graphical user interface;

alter, using a third machine learning model based on the context, the display signal, wherein altering the display signal includes altering at least one portion of the graphical user interface associated with the context; and

send the display signal to display the at least one portion of the graphical user interface on the user device.

10. The non-transitory processor-readable medium of claim 9 , wherein the at least one parameter includes at least one of a goal associated with the user or an interest of the user.

11. The non-transitory processor-readable medium of claim 9 , wherein the first set of data classes includes learning content.

12. The non-transitory processor-readable medium of claim 9 , wherein the at least one parameter is associated with user engagement.

13. The non-transitory processor-readable medium of claim 9 , wherein the at least one input includes user interactions with a conversational model.

14. A method, comprising:

receiving, by a compute device, at least one input from at least one of a user device of a user or at least one database;

detecting, by the compute device, at least one parameter from the at least one input, the at least one parameter associated with a context;

classifying, by a classifier based on historical user data, current user information associated with the user to produce classified user information;

determining, based on the classified user information, at least one desired parameter from the at least one parameter;

generating, by a first machine learning model and based on the at least one desired parameter, a first set of data classes, the first set of data classes enriched with the context;

generating, by a second machine learning model, at least one data class repository for each data class from a subset of data classes from the first set of data classes, the subset of data classes associated with a plurality of data class repositories;

generating a display signal to display, on the user device, information associated with at least one data class repository associated with the first set of data classes, the display signal associated with a graphical user interface;

altering, using a third machine learning model based on the context, the display signal, wherein altering the display signal includes altering at least one portion of the graphical user interface associated with the context; and

sending the display signal to display the at least one portion of the graphical user interface on the user device.

15. The method of claim 14 , further comprising:

determining, by the compute device, if each data class from the first set of data classes is associated with a data class repository from the plurality of data class repositories to define the subset of data classes, the subset of data classes including data classes that are not associated with a data class repository.

16. The method of claim 14 , wherein the at least one parameter includes at least one of a goal associated with the user or an interest of the user.

17. The method of claim 14 , wherein the first set of data classes includes learning content.

18. The method of claim 14 , wherein the at least one parameter is associated with user engagement.

19. The method of claim 14 , wherein the context is associated with learning behaviors associated with the user.

20. The method of claim 14 , wherein the at least one input includes user interactions with a conversational model.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 7, 2024
From: KHOSLA, NEERU; PACHAPURKAR, NIMISH; SHAH, MIRAL
To: CK12 FOUNDATION
Reel/Frame 068816/0078 →
Continuity (1)
Provisional Application 63583482 · Sep 18, 2023
References Cited (37)
US 11898865B1 · Bhavsar · 2024 [cited by examiner]
US 11966702B1 · Wilkinson et al. · 2024 [cited by applicant]
US 20070136273A1 · Rehberg et al. · 2007 [cited by applicant]
US 20180218268A1 · Kozloski et al. · 2018 [cited by applicant]
US 20190197415A1 · Bulut et al. · 2019 [cited by applicant]
US 20190294694A1 · Dash et al. · 2019 [cited by applicant]
US 20210264520A1 · Cummings · 2021 [cited by applicant]
US 20230185820A1 · Benoit · 2023 [cited by applicant]
US 20230244934A1 · Lazaridou et al. · 2023 [cited by applicant]
Abu-Salih et al. “A systematic literature review of knowledge graph construction and application in education.” Heliyon. Feb. 1, 2024, 10(3): e25383, 23 pages. [cited by applicant]
Akhtar et al. “Detecting fake news and disinformation using artificial intelligence and machine learning to avoid supply chain disruptions.” Annals of Operations Research. Aug. 2023;327(2):633-57. [cited by applicant]
Alhothali et al. “Predicting Student Outcomes in Online Courses Using Machine Learning Techniques: A review.” Sustainability. May 19, 2022;14(10):6199, 23 pages. [cited by applicant]
Alruwais et al. “Evaluating Student Knowledge Assessment Using Machine Learning Techniques.” Sustainability. 2023; 15(7):6229, 25 pages. [cited by applicant]
Author Unknown. “College Tools. Leveraging AI for Effective University Exam Preparation: A Report.” [online blog]. Retrieved from the Internet on Aug. 15, 2024. URL: https://www.collegetools.io/blog/leveraging-ai-for-ef… [cited by applicant]
Ayouni et al. “A new ML-based approach to enhance student engagement in online environment.” Plos one. Nov. 10, 2021;16(11):e0258788, 16 pages. [cited by applicant]
Benedetto, Luca “Tackling Misinformation with Machine Learning.” SWForum.eu [online forum]. Retrieved from the Internet on Aug. 15, 2024. URL: https://swforum.eu/online-sw-forum/software-technology/6/tackling-misinforma… [cited by applicant]
Chance et al. “Using AI to Help Students Prepare for the SAT Creating college entrance exam prep materials can take a lot of time, but artificial intelligence tools make the process easier.” Edutopia.org. Nov. 9, 2023. … [cited by applicant]
Choi et al. “Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing.” L@S '20: Proceedings of the Seventh ACM Conference on Learning @ Scale, Aug. 12-14, 2020, Virtual Event, USA, arXiv:2002.0703… [cited by applicant]
Christopher, James “How to Raise Your Test Scores with Help of AI Simulations.” [online blog]. Retrieved from the Internet on Aug. 15, 2024. URL: https://jameschris.medium.com/how-to-raise-your-test-scores-with-help-of-… [cited by applicant]
Cooper, Colin “How AI and Machine Learning Are Revolutionising Customer Engagement.” [online blog] Jun. 27, 2023. Retrieved from the Internet. URL: https://medium.com/@colin-cooper/how-ai-and-machine-learning-are-revolu… [cited by applicant]
Co-pending U.S. Appl. No. 18/740,464, inventors Khosla; Neeru et al., filed Jun. 11, 2024. [cited by applicant]
Co-pending U.S. Appl. No. 18/827,005, inventors Khosla; Vinod et al., filed Sep. 6, 2024. [cited by applicant]
Ettorre et al. “A Knowledge Graph Enhanced Learner Model to Predict Outcomes to Questions in the Medical Field.” HAL Open Science, EKAW 2020—22nd International Conference on Knowledge Engineering and Knowledge Managemen… [cited by applicant]
Gimpel et al. “Unlocking the power of generative AI models and systems such as GPT-4 and ChatGPT for higher education: A guide for students and lecturers.” Hohenheim Discussion Papers in Business, Economics and Social S… [cited by applicant]
Kannan et al. “Graph Neural Networks for Predicting Student Performance: A Deep Learning Approach for Academic Success Forecasting.” International Journal of Intelligent Systems and Applications in Engineering (IJISAE).… [cited by applicant]
Kong et al. “Validating a Computational Thinking Concepts Test for Primary Education Using Item Response Theory: An Analysis of Students' Responses.” Computers & Education. Oct. 1, 2022;187:104562, 18 pages. [cited by applicant]
Kumar et al. “Identification and Addressal of Knowledge Gaps in Students.” In 2022 3rd International Conference for Emerging Technology (INCET) May 27, 2022, 6 pages. [cited by applicant]
Liu et al. “Improving Knowledge Tracing via Pre-training Question Embeddings,” arXiv:2012.05031v1, URL: https://arxiv.org/pdf/2012.05031, Dec. 9, 2020, 7 pages. [cited by applicant]
Matthews, Ed. “How Can AI Tools Improve Student Assessment Outcomes?” Open Assessment Technologies, TAO. 2023. [online]. Retrieved from the Internet. URL: https://www.taotesting.com/blog/how-can-ai-tools-improve-student… [cited by applicant]
Persaud, “Bloom's Taxonomy: The Ultimate Guide [Free Download], Gain a deep understanding of Bloom's taxonomy and how it can be effectively applied in the learning process to benefit both educators and learners.” Top Ha… [cited by applicant]
Ruiz, Armand “AI for Personalized Learning System for Students.” [online blog]. Jun. 3, 2023. Retrieved from the Internet. URL: https://www.nocode.ai/personalized-learning-system-for-students/, 10 pages. [cited by applicant]
Ruiz-Rojas et al. “Empowering Education with Generative Artificial Intelligence Tools: Approach with an Instructional Design Matrix.” Sustainability. Jul. 25, 2023;15(15):11524, 20 pages. [cited by applicant]
Schmucker et al. “Assessing the Performance of Online Students—New Data, New Approaches, Improved Accuracy.” arXiv preprint arXiv: 2109.01753. Sep. 4, 2021, 44 pages. [cited by applicant]
Sekeroglu et al. “Systematic Literature Review on Machine Learning and Student Performance Prediction: Critical Gaps and Possible Remedies.” Applied Sciences. Nov. 18, 2021;11(22):10907, 23 pages. [cited by applicant]
Toti et al. “Detection of Student Engagement in e-Learning Systems Based on Semantic Analysis and Machine Learning.” In Advances on P2P, Parallel, Grid, Cloud and Internet Computing: Proceedings of the 15th Internationa… [cited by applicant]
Wang, M. “Characteristics of Item Response Time for Standardized Achievement Assessments.” [Doctoral dissertation] University of Iowa, 2017, 244 pages. [cited by applicant]
Wu et al. “SGKT: Session graph-based knowledge tracing for student performance prediction.” Expert Systems with Applications. Nov. 15, 2022; 206:117681, 12 pages. [cited by applicant]
Cited By (1)
US 12,524,708