Na INFOTEH konferenciji predstavljen je rad E. Trubljan, E. Taruha, S. Cakića, T. Popovića i L. Filipovića “Transforming Matrix Problem Solving with Intelligent Tutoring Systems” u izdanju IEEE Xplore. Istraživači iz UDG-a uz podršku HPC NCC Montenegro razvili su inovativni inteligentni sistem podučavanja koji koristi vještačku inteligenciju (AI) i računarstvo visokih performansi (HPC) kako bi se promijenio način na koji studenti uče matrične operacije. Ovo rješenje zasnovano na chatbot-u kombinuje optičko prepoznavanje znakova (EasyOCR) sa naprednim modelom obrade prirodnog jezika (Qwen2-Math-7B-Instruct) za tumačenje unosa teksta i slike, omogućavajući mu da izvodi matrične operacije kao što su transpozicija, sabiranje i množenje uz pružanje jasnih, korak po korak objašnjenja. Podržan univerzitetskom HPC infrastrukturom, sistem osigurava brzu obradu i povratne informacije u realnom vremenu, postižući do 99% tačnosti u prepoznavanju matrice iz visokokvalitetnih slika. Dizajniran imajući na umu obrazovanje, ovaj tutor sa AI-om poboljšava interaktivnost, razumijevanje i ishode učenja za učenike koji se bave složenim konceptima linearne algebre i postavlja teren za buduća poboljšanja kao što je prepoznavanje ručno pisanog unosa i podrška za naprednije operacije.
ABSTRACT – This paper presents the integration of optical character recognition (OCR) and advanced natural language processing (NLP) models for automated handling of matrices derived from images and textual inputs, all combined within an implemented chatbot. The motivation for choosing this topic arises from the practical experiences of the authors gained while working with groups of students who encounter the concept of matrices as part of their academic responsibilities. Through the analysis of their results and classroom interactions, it was observed that many students struggle with this area. This paper presents an innovative approach to enhancing matrix problem-solving by leveraging intelligent tutoring systems supported by High-Performance Computing, aiming to improve learning efficiency and student outcomes. By combining the EasyOCR framework and the Qwen2-Math-7B-Instruct model, operations such as transposition, addition, and multiplication of matrices are enabled. The system supports the input of one or two matrices, allowing the selection of operations through textual or image-based queries. The OCR component extracts numerical data from images, while the NLP model interprets user requests and executes operations accurately. The interface allows the addition of a second matrix image only when necessary, enhancing the system’s intuitiveness and efficiency. The results of the recognition accuracy of the OCR model of image input matrices of different dimensions show a high level of accuracy of 95%, while for 2×2 matrices they reach an accuracy of 99%. This work contributes to the development of AI-powered tools for mathematical operations and holds potential applications in education.
