可以将人名从文本中删除，或者将人名视为单词处理并保留在文本中。 代码实现如下：

删除人名

import spacy

nlp = spacy.load("en_core_web_sm") doc = nlp("John Smith is a software engineer") names = [ent.text for ent in doc.ents if ent.label_ == "PERSON"] print(names) # Output: ['John Smith']

将人名视为单词处理

from bertopic import BERTopic from nltk.tokenize import word_tokenize

topic_model = BERTopic(language="english") text = "John Smith is a software engineer" tokens = word_tokenize(text) cleaned_tokens = [token for token in tokens if token not in names] cleaned_text = " ".join(cleaned_tokens) topic_model.fit_transform([cleaned_text])