Design of an AI-Powered Visual Search, Customer Assistance, and Scene Generation System for Artisan E-Commerce Platforms.

Fuente: Zenodo
Salvato in:
Dettagli Bibliografici
Autori principali: Barhoum, Tarek, Salloum, Ahmed
Natura: Recurso digital
Pubblicazione: Zenodo 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866901592644517888
author Barhoum, Tarek
Salloum, Ahmed
author_facet Barhoum, Tarek
Salloum, Ahmed
contents <p class="p"><em><span class="16">This project presents the design of an AI-powered system for an e-commerce platform specializing in traditional Syrian handcrafted wooden boxes and decorative pieces inlaid with mother-of-pearl. The platform addresses key limitations in artisan e-commerce by integrating four core AI features: a visual similarity search engine that allows customers to upload images and find matching products using vision-language models and feature embeddings, a conversational AI chatbot built on RAG architecture to assist customers and recommend products, an AI scene generation tool that enables store managers to create professional marketing imagery for their products using diffusion models, and a custom order preview system that generates AI-powered visualizations of personalized orders before submission. The system is built on a Laravel backend with a React frontend, leveraging cloud-based LLM APIs and vector databases. This work aims to bridge the gap between traditional artisan craftsmanship and modern AI-driven shopping experiences, offering capabilities that existing platforms like Etsy, Amazon, and Google Lens do not combine in a single specialized solution.<br>This work was conducted at Arab International University (AIU), Syria. The official website of the university is: </span></em><a href="https://www.aiu.edu.sy"><em><u><span class="15">https://www.aiu.edu.sy</span></u></em></a></p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19561017
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Design of an AI-Powered Visual Search, Customer Assistance, and Scene Generation System for Artisan E-Commerce Platforms.
Barhoum, Tarek
Salloum, Ahmed
Visual Similarity Search
Content-Based Image Retrieval (CBIR)
Retrieval-Augmented Generation (RAG)
Conversational AI Chatbot
AI Scene Generation
Diffusion Models
Artisan E-Commerce
Product Recommendation System
Vision-Language Models
Syria
Arab International University
Academic Research
Artificial Intelligence
Engineering
Data Analysis
<p class="p"><em><span class="16">This project presents the design of an AI-powered system for an e-commerce platform specializing in traditional Syrian handcrafted wooden boxes and decorative pieces inlaid with mother-of-pearl. The platform addresses key limitations in artisan e-commerce by integrating four core AI features: a visual similarity search engine that allows customers to upload images and find matching products using vision-language models and feature embeddings, a conversational AI chatbot built on RAG architecture to assist customers and recommend products, an AI scene generation tool that enables store managers to create professional marketing imagery for their products using diffusion models, and a custom order preview system that generates AI-powered visualizations of personalized orders before submission. The system is built on a Laravel backend with a React frontend, leveraging cloud-based LLM APIs and vector databases. This work aims to bridge the gap between traditional artisan craftsmanship and modern AI-driven shopping experiences, offering capabilities that existing platforms like Etsy, Amazon, and Google Lens do not combine in a single specialized solution.<br>This work was conducted at Arab International University (AIU), Syria. The official website of the university is: </span></em><a href="https://www.aiu.edu.sy"><em><u><span class="15">https://www.aiu.edu.sy</span></u></em></a></p>
title Design of an AI-Powered Visual Search, Customer Assistance, and Scene Generation System for Artisan E-Commerce Platforms.
topic Visual Similarity Search
Content-Based Image Retrieval (CBIR)
Retrieval-Augmented Generation (RAG)
Conversational AI Chatbot
AI Scene Generation
Diffusion Models
Artisan E-Commerce
Product Recommendation System
Vision-Language Models
Syria
Arab International University
Academic Research
Artificial Intelligence
Engineering
Data Analysis
url https://doi.org/10.5281/zenodo.19561017