• 撰寫比對樣式，用 spaCy 的 Matcher 與 PhraseMatcher 擷取術語與片語：

matcher = Matcher(nlp.vocab)
pattern = [{"LOWER": "good"}, {"LOWER": {"IN": ["morning", "evening"]}}]
matcher.add("morning_greeting", [pattern])

matcher = PhraseMatcher(nlp.vocab, attr = "LOWER")
patterns = [nlp.make_doc(term) for term in terms]
matcher.add("InvestmentTerms", patterns)