基于大模型知识库的研究生管理系统设计与实现

import pandas as pd

# 加载学生信息

students_df = pd.read_csv('students.csv')

print(students_df.head())

]]>

from transformers import BertTokenizer, BertModel

import torch

tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')

model = BertModel.from_pretrained('bert-base-uncased')

def get_similarity(text1, text2):

inputs1 = tokenizer(text1, return_tensors='pt', padding=True, truncation=True)

inputs2 = tokenizer(text2, return_tensors='pt', padding=True, truncation=True)

outputs1 = model(**inputs1).last_hidden_state.mean(dim=1)

outputs2 = model(**inputs2).last_hidden_state.mean(dim=1)

cosine_similarity = torch.nn.functional.cosine_similarity(outputs1, outputs2)

return cosine_similarity.item()

# 示例：比较两个研究方向的相似性

similarity_score = get_similarity("Natural Language Processing", "Machine Learning")

print(f"Similarity Score: {similarity_score}")

]]>

from sklearn.feature_extraction.text import TfidfVectorizer

from sklearn.metrics.pairwise import cosine_similarity

courses = [

"Introduction to Data Science",

"Advanced Machine Learning",

"Database Systems",

"Computer Vision"

]

tfidf = TfidfVectorizer().fit_transform(courses)

cosine_similarities = cosine_similarity(tfidf[0], tfidf).flatten()

recommended_courses = [courses[i] for i in cosine_similarities.argsort()[-3:][::-1]]

print("Recommended Courses:", recommended_courses)

]]>