chatgpt生成的计算文本相似度算法

GloVe

import numpy as np
import gensim.downloader as api
from sklearn.metrics.pairwise import cosine_similarity

# 岗位描述和个人简历中提取的关键词列表
job_description_keywords = ['Java', 'Python', 'SQL', 'AWS']
resume_keywords = ['Python', 'R', 'SQL', 'Data Analysis']

# 加载GloVe词向量模型
model = api.load("glove-wiki-gigaword-300")

# 将关键词转换为词向量，并将它们组合成句子向量
job_description_vector = np.mean([model[keyword] for keyword in job_description_keywords if keyword in model], axis=0)

resume_vector = np.mean([model[keyword] for keyword in resume_keywords if keyword in model], axis=0)

# 计算余弦相似度
similarity = cosine_similarity([job_description_vector], [resume_vector])[0][0]

print('The similarity between job description and resume is:', similarity)

One-hot

import numpy as np
from sklearn.metrics.pairwise import cosine_similarity

# 岗位描述和个人简历中提取的关键词列表
job_description_keywords = ['Java', 'Python', 'SQL', 'AWS']
resume_keywords = ['Python', 'R', 'SQL', 'Data Analysis']

# 将关键词列表转换为独热编码向量
all_keywords = list(set(job_description_keywords + resume_keywords))
job_description_vector = [1 if keyword in job_description_keywords else 0 for keyword in all_keywords]
resume_vector = [1 if keyword in resume_keywords else 0 for keyword in all_keywords]

# 计算余弦相似度
similarity = cosine_similarity([job_description_vector], [resume_vector])[0][0]

print('The similarity between job description and resume is:', similarity)

Word2Vec

import numpy as np
import gensim.downloader as api
from sklearn.metrics.pairwise import cosine_similarity

# 岗位描述和个人简历中提取的关键词列表
job_description_keywords = ['Java', 'Python', 'SQL', 'AWS']
resume_keywords = ['Python', 'R', 'SQL', 'Data Analysis']

# 加载Word2Vec词向量模型
model = api.load("word2vec-google-news-300")

# 将关键词转换为词向量，并将它们组合成句子向量
job_description_vector = np.mean([model.wv[keyword] for keyword in job_description_keywords if keyword in model.wv], axis=0)
resume_vector = np.mean([model.wv[keyword] for keyword in resume_keywords if keyword in model.wv], axis=0)

# 计算余弦相似度
similarity = cosine_similarity([job_description_vector], [resume_vector])[0][0]

print('The similarity between job description and resume is:', similarity)