中文本文实现多文本相似度计算的代码

以下是一个简单的中文文本相似度计算的代码实现，使用了jieba分词和余弦相似度计算方法：

import jieba
import numpy as np

def cosine_similarity(vector1, vector2):
    dot_product = np.dot(vector1, vector2)
    norm1 = np.linalg.norm(vector1)
    norm2 = np.linalg.norm(vector2)
    return dot_product / (norm1 * norm2)

def get_word_vector(text):
    words = jieba.lcut(text)
    word_vector = {}
    for word in words:
        if word not in word_vector:
            word_vector[word] = 1
        else:
            word_vector[word] += 1
    return word_vector

def get_text_vector(text, word_vector):
    words = jieba.lcut(text)
    text_vector = []
    for word in word_vector:
        if word in words:
            text_vector.append(words.count(word))
        else:
            text_vector.append(0)
    return np.array(text_vector)

def text_similarity(text1, text2):
    word_vector1 = get_word_vector(text1)
    word_vector2 = get_word_vector(text2)
    word_set = set(word_vector1.keys()) | set(word_vector2.keys())
    text_vector1 = get_text_vector(text1, word_set)
    text_vector2 = get_text_vector(text2, word_set)
    return cosine_similarity(text_vector1, text_vector2)

使用方法：

text1 = "这是一段测试文本1"
text2 = "这是一段测试文本2"
similarity = text_similarity(text1, text2)
print(similarity)

输出结果为两个文本的相似度。