Classification and visualization of user interactions with an interactive computing platform

Patent metadata

Field	Value
Publication number	US-11513822-B1
Application number	US-202117455063-A
Country	US
Kind code	B1
Filing date	Nov 16, 2021
Priority date	Nov 16, 2021
Publication date	Nov 29, 2022
Grant date	Nov 29, 2022

Abstract

Classification and visualization of user interactions with an interactive computing platform is provided by applying machine learning (ML) model(s) to user transcripts, the ML model(s) trained to classify interactions with an interactive computing platform, the user transcripts including user interactions between users and the interactive computing platform in progression of the users through tasks based on the user interactions, where the applying classifies the user interactions and identifies features of the user interactions, and building and providing a graphical user interface (GUI) of graphical elements for display on a display device, the graphical elements presenting visualizations of the user interactions and the identified features thereof relative to the tasks and progression of the users therethrough, the GUI including, for each of the tasks, a respective task element that reflects identified features of a set of user interactions of user(s) in progressing through that task.

First claim

What is claimed is:

1. A computer-implemented method comprising:
applying at least one machine learning (ML) model to user transcripts, the at least one ML model trained to classify interactions with an interactive computing platform, the user transcripts comprising user interactions between users and the interactive computing platform in progression of the users through tasks based on the user interactions, wherein the applying classifies the user interactions and identifies features of the user interactions; and
building and providing a graphical user interface (GUI) of graphical elements for display on a display device, the graphical elements presenting visualizations of the user interactions and the identified features thereof relative to the tasks and progression of the users therethrough, the GUI comprising, for each of the tasks, a respective task element that reflects identified features of a set of user interactions of one or more users in progressing through that task.

2. The method of claim 1 , wherein the building and providing the GUI comprises building the task element for a task as a polygon having vertices corresponding to subtasks of the task and edges between the vertices, wherein the applying the at least one ML model comprises identifying a plurality of features of user interactions, of the set of user interactions, of at least one user in progressing the at least one user from one subtask of the task to a sequentially-next subtask of the task, and wherein building the task element comprises building an edge between a first vertex corresponding to the one subtask and a second vertex corresponding to the sequentially-next subtask of the task, the edge including at least one graphical element corresponding to each feature of the plurality of features of the user interactions of the at least one user.

3. The method of claim 2 , wherein the identified plurality of features comprises classified interaction types of the user interactions of the at least one user, and wherein the building the edge further comprises providing, as part of the edge, a respective at least one graphical element corresponding to each classified interaction type of the classified interaction types.

4. The method of claim 3 , wherein the identified plurality of features further comprises identified positive user interactions and negative user interactions of the user interactions of the at least one user, and wherein the building the edge further comprises:
providing a first one or more graphical elements representing the positive user interactions on a first side of an edge line between the first vertex and the second vertex;
providing a second one or more graphical elements representing the negative user interactions on a second side of the edge line between the first vertex and the second vertex.

5. The method of claim 2 , wherein the building and providing the GUI further comprises building and providing with the task element an interval indicator specific to the task, the interval indicator presenting a visualization of interval information of the at least one user in progressing through the task, the interval information comprising discrete intervals of one or more measured properties of the progression by the at least one user through the task, the one or more measured properties being at least one selected from the group consisting of: turns, sessions, and time taken by the at least one user in progressing through the task.

6. The method of claim 1 , wherein the building and providing the GUI comprises building, between a first task element corresponding to a first task of the tasks and a second task element corresponding to a second task of the tasks, an edge and one or more graphical elements representing user experience with the second task after progressing from the first task.

7. The method of claim 1 , wherein the interactive computing platform comprises an interactive learning platform providing a chat agent with which the users interact to provide the user interactions included in the user transcripts, and wherein the tasks represent learning objectives for the users.

8. The method of claim 1 , further comprising building and training the at least one ML model using labeled user transcripts with labels of the features of user interactions included in the labeled user transcripts.

9. The method of claim 1 , wherein the method further comprises applying the at least one ML model to additional user interactions, in real-time as the additional user interactions are provided, to classify the additional user interactions and identify features of the additional user interactions, and wherein the building and providing updates the GUI in real-time as the additional user interactions are provided and the at least one ML model is applied to classify the additional user interactions and identify the features of the additional user interactions, the updating the GUI updating the visualizations to reflect the additional user interactions and identified features thereof relative to the tasks and progression of the users therethrough.

10. The method of claim 1 , further comprising, based on interaction by a GUI user with an interactive graphical element of the GUI to select at least one selected from the group consisting of (i) one or more feature types of the identified features and (ii) a task element corresponding to a task of the tasks, updating the GUI to change the graphical elements presenting visualizations of the user interactions and the identified features thereof.

11. The method of claim 1 , wherein a plurality of possible task traversal paths exist through which the users can progress through the tasks, wherein the method further comprises receiving a selection, by a GUI user, of a selected task traversal path of the plurality of possible task traversal paths, wherein the visualizations presented by the graphical elements in the GUI reflect user interactions, and the identified features thereof, that include the user interactions of a first set of users who progressed through the tasks along the selected task traversal path and exclude the user interactions of a second set of users who progressed through the tasks along any other task traversal path different than the selected task traversal path, wherein the respective task element for each of the tasks reflects identified features of user interactions that include the user interactions of the first set of users in progressing through that task and excludes the user interactions of the second set of users in progressing through that task.

12. A computer system comprising:
a memory; and
a processor in communication with the memory, wherein the computer system is configured to perform a method comprising:
applying at least one machine learning (ML) model to user transcripts, the at least one ML model trained to classify interactions with an interactive computing platform, the user transcripts comprising user interactions between users and the interactive computing platform in progression of the users through tasks based on the user interactions, wherein the applying classifies the user interactions and identifies features of the user interactions; and
building and providing a graphical user interface (GUI) of graphical elements for display on a display device, the graphical elements presenting visualizations of the user interactions and the identified features thereof relative to the tasks and progression of the users therethrough, the GUI comprising, for each of the tasks, a respective task element that reflects identified features of a set of user interactions of one or more users in progressing through that task.

13

Assignees

• IBM

Inventors

• Kwatra Shikhar
• MARVANIYA Smitkumar Narotambhai
• Miles Caleb
• Decrop Clement

Classifications

• G06F16/248

  Presentation of query results · CPC title

• G06F3/0481

  based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance · CPC title

• G06F3/04847 Primary

  Interaction techniques to control parameter settings, e.g. interaction with sliders or dials · CPC title

• G06T11/26

  Drawing of charts or graphs · CPC title

• G06F9/451 Primary

  Execution arrangements for user interfaces · CPC title