AgensGraph Use Case #6. Personalized Education Service
Hi everyone, Hello, we are Bitnine, the dedicated research and development company in graph database.
We are glad to introduce the sixth Use Case of AgensGraph: Personalized Education Service
The reason why most students feel exhausted on what they study is that we have tried to teach them only with the same, standardized curriculum. Company E was one of the companies trying to make an innovation in this old way of teaching and provide unprecedented educational services, and AgensGraph was the key.
There has been the lack of resources and time required to take care of each individual student and not enough preparation to automate the whole educational process. Company E had a large volume of learning data and know-how accumulated over a long period of time but it wasn’t easy to efficiently provide a learning model that takes into account the individual characteristics of each student.
A more serious problem that Company E faced was that they needed to create an unprecedented curriculum for each student to provide personalized education services. Regardless of the overall educational progress status or sequence, all concepts must be organized into an interconnected network structure so that they can be taught freely. The problem was that, with relational databases where data is stored in ‘table’, Company E was not able to secure performance needed to manage the knowledge base in the form of a network.
Bitnine suggested 3 major solutions to Company E.
First, Bitnine built “Knowledge Space” for each subject using AgensGraph, a Bitnine’s graph database. Educational subjects, areas, units, concept units, and items are expressed as “dots” and relationships among dots are represented as “lines” to form a graph; this graph can be considered a network structure where multiple knowledge units are connected to one another.
Next, based on this Knowledge Space, Bitnine implemented an optimized education service for each student. The service first diagnoses the student’s current knowledge level by analyzing variables (e.g. probability that the student makes a mistake while solving problems) that are generated in the learning process. It also uses the learning behavior data (e.g. degree of immersion and comprehensive understanding level) to identify the poorly-achieved areas and recommend the optimized learning path accordingly.
For the personalized education services above, Bitnine created a model that can analyze the data collected throughout the student’s learning process and thereby determine the student’s inclination. This model analyzes student data to figure out his or her problem-solving abilities, reasoning abilities, concentration and sincerity, and then diagnoses student’s inclination.
Now, Company E uses AgensGraph to provide “fully personalized” education services. Company E’s services take into account each student’s academic achievement, behavioral patterns, and personal preferences, and then suggest an effective way to study for each. This way, Company E has provided a true “tailored” education program, which is absolutely different from its competitors’ that simply modify students’ progress by reflecting their test scores.
This is the end of a brief summary of Company E’s Personalized Education Service with AgensGraph.
Please visit Bitnine webpage to reach the details of this case.
If you have any question about AgensGraph, please contact us at firstname.lastname@example.org