Personalized learning system and method for the automated generation of structured learning assets based on user data
Learning systems and methods of the present disclosure include generating a text document based on a digital file, tokenizing the text document, generating a semantic model based on the tokenized text document using an unsupervised machine learning algorithm, assigning a plurality of passage scores to a corresponding plurality of passages of the tokenized text document, selecting one or more candidate knowledge items from the tokenized text document based on the plurality of passage scores, filtering the one or more candidate knowledge items based on user data, generating one or more structured learning assets based on the one or more filtered candidate knowledge items, generating an interaction based at least on the one or more structured learning assets, and transmitting the interaction to a user device. Each passage score is assigned based on a relationship between a corresponding passage and the semantic model.
1. A learning system comprising:
a non-transitory memory; and
one or more hardware processors configured to read instructions from the non-transitory memory to cause the system to perform operations comprising:
generating a semantic model based on a source material using a machine learning algorithm;
assigning a plurality of concept scores to a corresponding plurality of concepts included in the source material, wherein each of the plurality of concept scores is assigned based on a relationship between a respective one of the plurality of concepts and the semantic model;
selecting one or more candidate knowledge items from the source material based on the plurality of concept scores;
generating an interaction based at least on the one or more candidate knowledge items; and
transmitting the interaction to a user device.
2. The learning system of claim 1 , wherein the operations further comprise:
filtering the one or more candidate knowledge items based on user data to provide one or more filtered candidate knowledge items; and
generating the interaction based at least on the one or more filtered candidate knowledge items.
3. The learning system of claim 2 , wherein
the filtering of the one or more candidate knowledge items based on the user data includes identifying one or more learning objectives of a user of the user device; and
the one or more learning objectives of the user correspond to a query provided by the user of the user device.
4. The learning system of claim 2 , wherein
the filtering of the one or more candidate knowledge items based on the user data includes identifying one or more learning objectives of a user of the user device; and
the one or more learning objectives are generated automatically based on existing knowledge of the user.
5. The learning system of claim 4 , wherein
the one or more learning objectives are automatically generated by comparing the existing knowledge of the user of the one or more candidate knowledge items with a predetermined threshold;
when the existing knowledge of the user of the one or more candidate knowledge items is greater than the predetermined threshold it is determined that re-learning of the one or more candidate knowledge items is not necessary.
6. The learning system of claim 2 , wherein
the filtering of the one or more candidate knowledge items based on the user data includes identifying one or more learning objectives of a user of the user device; and
the one or more candidate knowledge items are filtered by determining a relevance score for each of the one or more candidate knowledge items and determining whether the relevance score meets a threshold.
7. The learning system of claim 2 , wherein the operations further comprise:
generating user data that includes one or more metrics that indicate a level of retention or understanding of the one or more candidate knowledge items by a user of the user device; and
determining the one or more metrics based on the user's responses to one or more previous interactions.
8. The learning system of claim 7 , wherein the one or more metrics are further determined based on historical user responses associated with other knowledge items or interactions.
9. The learning system of claim 1 , wherein the source material includes at least one of a text, a video, an image, or audio content.
10. The learning system of claim 1 , wherein the interaction includes a voice interaction.
11. The learning system of claim 1 , wherein the one or more candidate knowledge items are selected adaptively to reduce redundancies among the one or more candidate knowledge items.
12. The learning system of claim 1 , wherein
each of the plurality of concept scores indicates a level of relevance between a respective concept included in the source material and one or more learning objectives of a user of the user device; and
the plurality of concepts included in the source material are ranked based on the plurality of concept scores.
13. The learning system of claim 1 , wherein the relationship is defined by a centrality metric that indicates how central a corresponding concept is to one or more topics in the semantic model.
14. The learning system of claim 1 , wherein
the interaction transmitted to the user device is an interaction of a course;
the course is completed by a user of the user device in order to obtain a professional certification.
15. The learning system of claim 1 , wherein the operations further comprise:
sending, to the user device, analytics data that indicate a performance result based on a respective response to the interaction by a user of the user device.
16. The learning system of claim 15 , wherein the operations further comprise:
sending the analytics data to a device of an individual other than the user of the user device to inform the individual whether or not the user understands at least one of the one or more candidate knowledge items based on which the interaction was generated.
17. A method comprising:
generating a semantic model based on a source material using a machine learning algorithm;
assigning a plurality of concept scores to a corresponding plurality of concepts included in the source material, wherein each of the plurality of concept scores is assigned based on a relationship between a respective one of the plurality of concepts and the semantic model;
selecting one or more candidate knowledge items from the source material based on the plurality of concept scores;
generating an interaction based at least on the one or more candidate knowledge items; and
transmitting the interaction to a user device.
18. The method of claim 17 , further comprising:
filtering the one or more candidate knowledge items based on user data to provide one or more filtered candidate knowledge items; and
generating the interaction based at least on the one or more filtered candidate knowledge items.
19. A non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a machine to perform operations comprising:
generating a semantic model based on a source material using a machine learning algorithm;
assigning a plurality of concept scores to a corresponding plurality of concepts included in the source material, wherein each of the plurality of concept scores is assigned based on a relationship between a respective one of the plurality of concepts and the semantic model;
selecting one or more candidate knowledge items from the source material based on the plurality of concept scores;
generating an interaction based at least on the one or more candidate knowledge items; and
transmitting the interaction to a user device.
20. The non-transitory machine-readable medium of claim 19 , wherein generating the interaction includes:
filtering the one or more candidate knowledge items based on user data to provide one or more filtered candidate knowledge items; and
generating the interaction based at least on the one or more filtered candidate knowledge items.