This thesis presents the activities carried out during the curricular internship at Wavelop SRL, focused on the analysis, design, and development of a web application in the insurance sector. The application is intended for insurance agents and allows for the upload and automatic interpretation of a client’s vineyard registry, with the goal of efficiently extracting all the information necessary to generate insurance quotes. The development process began with a research phase aimed at identifying the most effective solution for document analysis, considering both traditional OCR techniques and AI-based approaches. The chosen solution was then implemented, with particular attention paid to the structured storage of the extracted data and the development of a user interface designed to facilitate the agent’s interaction with the system.
Questo elaborato descrive le attività svolte durante il progetto di tirocinio curriculare svolto presso l’azienda Wavelop SRL, incentrato sull’analisi, progettazione e sviluppo di una web application in ambito assicurativo. L’applicativo è destinato agli agenti assicurativi e consente il caricamento e l’interpretazione automatica dello schedario viticolo di un cliente, con l’obiettivo di estrarre in modo efficiente tutte le informazioni necessarie alla formulazione di preventivi. Lo sviluppo ha previsto una fase iniziale di ricerca, volta a individuare la soluzione più efficace per l’analisi del documento, considerando sia tecniche OCR tradizionali che approcci basati sull’Intelligenza Artificiale. Successivamente, è stata implementata la soluzione individuata, ponendo particolare attenzione al salvataggio strutturato dei dati estratti e allo sviluppo di un’interfaccia utente in grado di agevolare l’interazione dell’agente con il sistema.
Estrazione automata di dati assicurativi: confronto tra tecniche di OCR tradizionali e basate sull’Intelligenza Artificiale
VALLOTTO, CATERINA
2024/2025
Abstract
This thesis presents the activities carried out during the curricular internship at Wavelop SRL, focused on the analysis, design, and development of a web application in the insurance sector. The application is intended for insurance agents and allows for the upload and automatic interpretation of a client’s vineyard registry, with the goal of efficiently extracting all the information necessary to generate insurance quotes. The development process began with a research phase aimed at identifying the most effective solution for document analysis, considering both traditional OCR techniques and AI-based approaches. The chosen solution was then implemented, with particular attention paid to the structured storage of the extracted data and the development of a user interface designed to facilitate the agent’s interaction with the system.| File | Dimensione | Formato | |
|---|---|---|---|
|
Vallotto_Caterina.pdf
accesso aperto
Dimensione
2.55 MB
Formato
Adobe PDF
|
2.55 MB | Adobe PDF | Visualizza/Apri |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/90013