Resume Match Ml

🚀 Sentence Similarity Model for Job Matching

This project uses a sentence-transformers model to calculate sentence similarity, which can be applied to job matching scenarios. By comparing source sentences (such as job - seeker self - descriptions) with target sentences (job descriptions), it helps to find the most suitable job opportunities.

🚀 Quick Start

The widget section in the README provides several examples of source sentences and corresponding job description sentences. You can use the pre - trained model sentence - transformers/all - MiniLM - L6 - v2 to calculate the similarity between source sentences and job description sentences, so as to match the most suitable jobs.

✨ Features

• Sentence Similarity Calculation: Based on the sentence - transformers framework, it can accurately calculate the similarity between sentences.
• Multiple Job Matching: Support matching multiple job descriptions for a single source sentence.
• Rich Skills Coverage: Cover a wide range of skills and job requirements, such as data analysis, marketing analysis, programming, etc.

📦 Installation

There is no specific installation steps provided in the original README. If you want to use the sentence - transformers model, you can use the following command to install:

pip install sentence-transformers

💻 Usage Examples

Basic Usage

from sentence_transformers import SentenceTransformer, util

# Load the pre-trained model
model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')

# Source sentence
source_sentence = "committed and motivated professional with exceptional customer service and decision making skills..."
# Job description sentences
sentences = [
    "data analyst  job title: sr data analystlocation: juno beach (onsite)work authorization: usc/gc holder job type: 12+ month contract...",
    # Other job descriptions...
]

# Calculate embeddings
source_embedding = model.encode(source_sentence, convert_to_tensor=True)
sentence_embeddings = model.encode(sentences, convert_to_tensor=True)

# Calculate cosine similarity
cosine_scores = util.pytorch_cos_sim(source_embedding, sentence_embeddings)

# Print similarity scores
for i in range(len(sentences)):
    print(f"Similarity with sentence {i + 1}: {cosine_scores[0][i]}")

Advanced Usage

# Sort job descriptions by similarity score
import torch

# Calculate embeddings and similarity scores as above
#...

# Get the indices sorted by similarity scores in descending order
sorted_indices = torch.argsort(cosine_scores[0], descending=True)

# Print job descriptions in order of similarity
for index in sorted_indices:
    print(f"Similarity: {cosine_scores[0][index]}, Job description: {sentences[index]}")

📚 Documentation

Model Information

Job Matching Examples

The README provides multiple groups of source sentences and corresponding job description sentences, which can be used for job matching. Each group includes a source sentence (usually a self - description of a job - seeker) and multiple job description sentences.

📄 License

No license information is provided in the original README.