如何在Python中比较两个字符串(非英语)之间的相似性

import Levenshtein

str1 = "字符串1"
str2 = "字符串2"

distance = Levenshtein.distance(str1, str2)
similarity = 1 - distance / max(len(str1), len(str2))

from sklearn.feature_extraction.text import CountVectorizer
from sklearn.metrics.pairwise import cosine_similarity

str1 = "字符串1"
str2 = "字符串2"

vectorizer = CountVectorizer().fit_transform([str1, str2])
vectors = vectorizer.toarray()

similarity = cosine_similarity([vectors[0]], [vectors[1]])[0][0]

str1 = "字符串1"
str2 = "字符串2"

set1 = set(str1)
set2 = set(str2)

similarity = len(set1 & set2) / len(set1 | set2)