Technical Job Recommendation System Using APIs and Web Crawling

Towards a knowledge-based decision support system to foster the return to work of wheelchair users

Accidents at work may force workers to face abrupt changes in their daily life: one of the most impactful accident cases consists of the worker remaining in a wheelchair. Return To Work (RTW) of wheelchair users in their working age is still challenging, encompassing the expertise of clinical and rehabilitation personnel and social workers to match the workers' residual capabilities with job requirements. This work describes a novel and prototypical knowledge-based Decision Support System (DSS) that matches workers' residual capabilities with job requirements, thus helping vocational therapists and clinical personnel in the RTW decision-making process for WUs. The DSS leverages expert knowledge in the form of ontologies to represent the International Classification of Functioning, Disability, and Health (ICF) and the Occupational Information Network (O*NET). These taxonomies enable both workers' health conditions and job requirements formalization, which are processed to assess the suitability of a job depending on a worker's condition. Consequently, the DSS suggests a list of jobs a wheelchair user can still perform, exploiting his/her residual abilities at their best. The manuscript describes the theoretical approach and technological foundations of such DSS, illustrating its development, its output metric, and application. The developed solution was tested with real wheelchair users' health conditions provided by the Italian National Institute for Insurance against Accidents at Work. The feasibility of an approach based on objective data was thus demonstrated, providing a novel point of view in the critical process of decision-making during RTW.

Design and Implementation of a Recommendation System for Buying Fresh Foods Online Based on Web Crawling

As shopping patterns have gradually shifted from offline to online mode, and with recent lockdowns during the coronavirus disease 2019 (COVID-19) pandemic restricting foreign trade and accelerating the growth of the domestic economy, digital transformation has become a major strategy for many retailers to support and expand their businesses. With the pandemic becoming a turning point, the business of major e-commerce companies in Taiwan in the retail of dry goods has grown significantly, and it has driven the online sales of fresh products as well. In this era of fierce competition, it is especially important to find a way that enables consumers to quickly find ideal fresh products on multiple platforms, shortens the time for price comparison, and improves the efficiency of online shopping. This study uses the Python programming language to write a web crawler program that captures product information from fresh food e-commerce platforms, including product introduction, price, origin, and sales volume, and then defines the relevant status of the product, such as product popularity. Accordingly, through Chinese text segmentation and term-frequency calculation, it aims to classify the product names and introductions into frequently occurring words and use them as product-related labels. Finally, the program combines the product information processing results and product-related labels to construct an online fresh food recommendation system. The results of the proposed system show that it reduces the time and energy spent comparing prices. It can also guide consumers to browse products that may be of interest using relevant tags and increase consumption efficiency by helping them find the ideal item when shopping.