Scholarlink

<p>Resume screening plays an important role in Human Resource Management (HRM) in improving the effectiveness of the hiring process. None of the existing works considered the contextual nuance in resumes for proper screening. Thus, people management in resume screening is proposed by structuring the contextual nuance in the job seeker's resume. Initially, the resume and job description are collected and preprocessed. Then, the contextual nuance is captured using the Exponential Soft Minimum Cosine Spanning Tree (ESM-CST) Machine Learning (ML) technique. Next, the similarity between the job requirement and resume is analyzed. Meanwhile, the preprocessed data is grouped using the Co-occurrent Frequency Latent Dirichlet Dependency Allocation (CFLDDA) technique. Then, the relevant information is embedded using the Nish Bidirectional Encoder Representations from Transformers (Nish-BERT) Artificial Intelligence (AI) model. Then, the features are extracted from hierarchical and clustered output. Finally, the features, embedded output, and similarity score are given to the Gated Attention on Attention Recurrent Unit (GAARU) deep learning classifier to find a suitable resume. Then, the resume and classified details are secured using Advanced Fractional Order Chaotic Encryption Standard (AFOCES) and stored in the Ethereum blockchain. Thus, the resume screening is done with an accuracy of 97.58%, showing better performance in HRM.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Automatic Resume Screening Approach Based on AI and Ethereum Blockchain for Human Resource Management Using Gaaru

  • 期刊论文

  • 发表日期：

    2025年4月2日

查看全文
  • Mohan Reddy Sareddy,
  • Muhammad Farhan

摘要

Resume screening plays an important role in Human Resource Management (HRM) in improving the effectiveness of the hiring process. None of the existing works considered the contextual nuance in resumes for proper screening. Thus, people management in resume screening is proposed by structuring the contextual nuance in the job seeker's resume. Initially, the resume and job description are collected and preprocessed. Then, the contextual nuance is captured using the Exponential Soft Minimum Cosine Spanning Tree (ESM-CST) Machine Learning (ML) technique. Next, the similarity between the job requirement and resume is analyzed. Meanwhile, the preprocessed data is grouped using the Co-occurrent Frequency Latent Dirichlet Dependency Allocation (CFLDDA) technique. Then, the relevant information is embedded using the Nish Bidirectional Encoder Representations from Transformers (Nish-BERT) Artificial Intelligence (AI) model. Then, the features are extracted from hierarchical and clustered output. Finally, the features, embedded output, and similarity score are given to the Gated Attention on Attention Recurrent Unit (GAARU) deep learning classifier to find a suitable resume. Then, the resume and classified details are secured using Advanced Fractional Order Chaotic Encryption Standard (AFOCES) and stored in the Ethereum blockchain. Thus, the resume screening is done with an accuracy of 97.58%, showing better performance in HRM.