Saputra, Muhammad Daffa (2025) Menterjemahkan Kontrak Asuransi Kesehatan Ke Dalam Ekstensi Medis Di Business Central Menggunakan AI. Other thesis, Institut Teknologi Sepuluh Nopember.
![]() |
Text
05211942000003-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (2MB) |
Abstract
Tesis ini menyajikan pengembangan dan evaluasi solusi berbantuan AI untuk mengekstraksi data terstruktur dari kontrak asuransi kesehatan. Proyek ini dilaksanakan selama magang kelulusan di GAC Business Solutions B.V. oleh Muhammad Daffa Saputra, mahasiswa gelar ganda di bidang TIK & Sistem Informasi Bisnis di Fontys University of Applied Sciences. Di GAC, konsultan yang bekerja dengan klien di sektor medis seringkali menangani kontrak yang panjang dan rumit. Penerjemahan dokumen-dokumen ini ke dalam konfigurasi sistem untuk Business Central merupakan proses manual yang memakan waktu dan menyisakan ruang untuk inkonsistensi dan perbedaan interpretasi. Tujuan proyek ini adalah untuk mengeksplorasi bagaimana AI dapat mendukung proses ini melalui ekstraksi data berbasis prompt. Sebuah solusi dirancang untuk mengekstraksi komponen-komponen kontrak utama, seperti klasifikasi produk, jenis AIP, dan indikator harga. Solusi ini disempurnakan melalui uji kegunaan, wawancara ahli, dan umpan balik dari konsultan.
Bukti konsep akhir menunjukkan bahwa perangkat AI dapat mengekstraksi data secara andal dari kontrak yang kompleks dan menghasilkan keluaran Excel terstruktur untuk mendukung keputusan konfigurasi. Meskipun belum terintegrasi langsung ke Business Central, solusi ini terbukti efektif dalam mengurangi pekerjaan manual dan meningkatkan konsistensi. Para konsultan mengonfirmasi nilai praktisnya dan menyatakan minat untuk mengadopsinya dalam alur kerja mereka.
Proyek ini menunjukkan potensi alat bantu AI dalam mempercepat, memperjelas, dan meningkatkan skalabilitas pemrosesan data kontrak. =====================================================================================================================
This thesis presents the development and evaluation of an AI-assisted solution for extracting structured data from healthcare insurance contracts. The project was carried out during a graduation internship at GAC Business Solutions B.V. by Muhammad Daffa Saputra, a double degree student in ICT & Business Information Systems at Fontys University of Applied Sciences. At GAC, consultants working with clients in the medical sector often deal with lengthy and complex contracts. Translating these documents into system configurations for Business Central is a manual, time-consuming process that leaves room for inconsistency and interpretation differences. The aim of this project was to explore how AI could support this process through prompt-based data extraction. A solution was designed to extract key contract components, such as product classification, AIP types, and pricing indicators. The solution was refined through usability testing, expert interviews, and feedback from consultants. The final proof of concept showed that the AI tool could reliably extract data from complex contracts and produce a structured Excel output to support configuration decisions. While it doesn’t yet integrate directly into Business Central, the solution proved effective in reducing manual work and improving consistency. Consultants confirmed its practical value and expressed interest in adopting it within their workflow.
This project demonstrates the potential of AI prompting tools in making contract data processing faster, clearer, and more scalable.
Item Type: | Thesis (Other) |
---|---|
Uncontrolled Keywords: | Prompt Engineering, AI for Contract Extraction, Microsoft 365 Copilot, Healthcare Insurance Contract, Business Central, |
Subjects: | T Technology > T Technology (General) > T58.6 Management information systems |
Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information System > 57201-(S1) Undergraduate Thesis |
Depositing User: | Muhammad Daffa Saputra |
Date Deposited: | 13 Aug 2025 02:26 |
Last Modified: | 13 Aug 2025 02:26 |
URI: | http://repository.its.ac.id/id/eprint/128035 |
Actions (login required)
![]() |
View Item |