Dehao L.

Key Skills

Software

No software listed

Top Subject Matter

Resume Recommendation/AI Resume Analysis

AI-powered Attendance Information Extraction

Top Data Types

Document

Image

Top Task Types

Classification

Freelancer Overview

AI Resume Diagnosis, AI Q&A Data Annotation (Project-based). Brings 1+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal, Proprietary Tooling, and Tesseract.js. Education includes Associate Degree, 襄阳职业技术大学 (2023). AI-training focus includes data types such as Document and Image and labeling workflows including Classification.

Labeling Experience

AI Resume Diagnosis, AI Q&A Data Annotation (Project-based)

DocumentClassification

In the campus recruiting recommendation system project, integrated large models via APIs and local deployments to provide AI resume diagnosis and Q&A assistant functionalities. Utilized text and skill labels from resumes and job descriptions to match candidates with suitable positions, optimizing feature weights to improve matching accuracy by 40%. Applied text classification algorithms (jieba, TF-IDF) as part of an intelligent recommendation and annotation pipeline to analyze and tag resume-job pairs used for AI model fine-tuning. • Implemented data-driven features for matching and recommendation. • Designed and labeled content-based text pairs for algorithmic evaluation. • Used classification and entity recognition to generate training data. • Inferred annotation and AI evaluation outputs for LLM feature optimization.

2023 - Present

OCR Image Data Annotation for Attendance (Project-based)

ImageClassification

In the intelligent attendance management system, integrated Tesseract.js to automatically recognize and extract information from uploaded attendance images, classifying and annotating date, shift, and personnel data. Optimized high-frequency result caching with Redis to minimize manual entry and reduce annotation workload by 60%. Supported multi-device data syncing and ensured accurate labeling even in offline scenarios for batch attendance image imports. • Performed image annotation for AI-driven attendance parsing. • Automated classification of key fields (date, personnel) from images. • Implemented batch image data import with annotation consistency. • Enhanced accuracy and speed for labeled attendance data using AI OCR.

Present

Education

Work History