将字符串列表转换为数值向量，以计算汉明距离

import numpy as np
import gensim.downloader as api

# 加载预训练的词嵌入模型
model = api.load("word2vec-google-news-300")

def string_list_to_vector(string_list):
    vectors = []
    for string in string_list:
        words = string.split()  # 或者使用字符级别的切分，例如 list(string)
        word_vectors = [model[word] for word in words if word in model]
        if len(word_vectors) > 0:
            string_vector = np.mean(word_vectors, axis=0)  # 平均每个单词的向量
            vectors.append(string_vector)
    return vectors

string_list = ["hello world", "natural language processing", "machine learning"]
vectors = string_list_to_vector(string_list)