Education: Starter Kit - Student Counsellor

Student Counsellor can help the student across many areas such as: 1. Clarifications on subjects of your choice. 2. Help students to prepare for admissions applications and tests. 3. Provide one-on-one career guidance and skills assessment to assist with career development 4. Offer referrals to outside resources, such as for mental health, substance abuse, or vocational-related activities. In this challenge, we are inviting to build a virtual counsellor application which will help with addressing student queries round the clock. You can also choose any topics of your choice. Please see below a sample solution kit to jumpstart your solution on creating a Virtual Agent application. To use this kit to build your own solution, scroll down to refer sections Kit Deployment Instructions and Instruction to Run. Complexity : Simple

Development Environment

VSCode and Jupyter Notebook are used for development and debugging. Jupyter Notebook is a web based interactive environment often used for experiments, whereas VSCode is used to get a typical experience of IDE for developers. Jupyter Notebook is used for our development.

Exploratory Data Analysis

For extensive analysis and exploration of data, and to deal with arrays, these libraries are used. They are also used for performing scientific computation and data manipulation. For building Virtual Agent, we use pandas to load, view and analyse data from csv file; and we use numpy to find out the indices of maximum values of an array.

Text Mining

Libraries in this group are used for analysis and processing of unstructured natural language. The data, as in its original form aren't used as it has to go through processing pipeline to become suitable for applying machine learning techniques and algorithms. We use py-lingualytics to manage pre-processing of data like removing numerical values, stopwords, punctuations and so on.

Machine Learning

Machine learning libraries and frameworks here are helpful in capturing state-of-the-art embeddings. Embeddings are vectoral representation of text with their semantics. For generating sentence embedding, we use sentence-transformers with pretrained models. We reference bert-cosine-sim to build similarity engine for comparing two sets of input text.

Instruction to Run

Follow below instructions to run the solution. 1. Locate and open the Student Counsellor App.ipynb notebook from the Jupyter Notebook browser window. 2. Execute cells in the notebook by selecting Cell --> Run All from Menu bar For customizing to your Questions and Answers, 1. Open the input file faqs.csv in the faq-virtual-agent-main directory from the kit_installer.bat location 2. Update questions for training under the column Q and update corresponding answer in the column A 3. Execute cells in the notebook by selecting Cell --> Run All from Menu bar 4. Type in the query when you're prompted and hit Enter key Input file: faqs.csv - contains questions and answers to train You can additionally build interfaces to the chatbot and other enhancements for additional score. For any support, you can direct message us at #help-with-kandi-kits

Troubleshooting

1. While running batch file, if you encounter Windows protection alert, select More info --> Run anyway 2. During kit installer, if you encounter Windows security alert, click Allow

Support

If you need help to use this kit, you can email us at kandi.support@openweaver.com or direct message us on Twitter Message @OpenWeaverInc.