基于知识图谱的电影知识问答系统：训练TF-IDF 向量算法和朴素贝叶斯分类器、在 Neo4j 中查询

{
  "introduction_by_movie": [
    "nm简介",
    "nm剧情简介",
    "nm的内容是什么",
    "nm讲了什么",
    "nm讲了什么故事",
    "nm演了什么",
    "nm的故事梗概是什么",
    "nm的剧情简介是什么",
    "nm的内容简介是什么",
    "nm的剧情介绍是什么",
    "nm的情节是什么",
    "nm的主要情节是什么"
  ],
  "rating_by_movie": [
    "nm的评分是多少",
    "nm得了多少分",
    "nm的评分有多少",
    "nm的评分",
    "nm得分是多少",
    "nm的分数是",
    "nm电影分数是多少",
    "nm电影评分",
    "nm评分",
    "nm的分数是多少",
    "nm这部电影的评分是多少"
  ],
  "release_date_by_movie": [
    "nm上映时间",
    "nm定档时间",
    "nm的上映时间是什么时候",
    "nm的首映时间是什么时候",
    "nm什么时候上映",
    "nm什么时候首映",
    "最早什么时候能看到nm",
    "nm什么时候在影院上线",
    "什么时候可以在影院看到nm",
    "nm什么时候在影院放映",
    "nm什么时候首播"
  ],
  

Forrest Gump nm
Kill Bill: Vol. 1 nm
英雄 nm
Miami Vice nm
Indiana Jones and the Temple of Doom nm
卧虎藏龙 nm
Pirates of the Caribbean: At World's End nm
Kill Bill: Vol. 2 nm
The Matrix Reloaded nm
The Matrix Revolutions nm
Harry Potter and the Chamber of Secrets nm
Harry Potter and the Prisoner of Azkaban nm
Harry Potter and the Goblet of Fire nm
Harry Potter and the Order of the Phoenix nm
The Last Emperor nm
Harry Potter and the Half-Blood Prince nm
花样年华 nm
2046 nm
Lethal Weapon 4 nm
Hannibal Rising nm
TMNT nm
무사 nm
Anna and the King nm
满城尽带黄金甲 nm

jieba
neo4j
python-dotenv
scikit-learn
flask
flask-cors
gunicorn

import os

from neo4j import GraphDatabase


class Database:
    """
    Neo4j 数据库访问层。

    管理数据库连接的生命周期，并提供查询接口。
    """

    def __init__(self):
        uri = os.environ["DATABASE_URI"]
        user = os.environ["DATABASE_USER"]
        password = os.environ["DATABASE_PASSWORD"]

        try:
            self._driver = GraphDatabase.driver(uri, auth=(user, password))
            self._session = self._driver.session()
        except Exception as e:
            raise Exception("数据库连接失败") from e

    def close(self):
        try:
            self._session.close()
            self._driver.close()
        except Exception as e:
            raise Exception("数据库断开失败") from e

    def find_one(self, query: str, **parameters):
        result = self._session.run(query, parameters).single()
        return result.value() if result else None

    def find_many(self, query: str, **parameters):
        return self._session.run(query, parameters).value()


if __name__ == "__main__":
    import dotenv

    dotenv.load_dotenv()

    database = Database()
    genres = database.find_many(
        """
        MATCH (m:Movie)-[BELONGS_TO]->(g:Genre)
        WHERE m.name = $movie_name
        RETURN g.name
        """,
        movie_name="卧虎藏龙",
    )
    database.close()

    print(genres)

import json
import os

import jieba
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB

TRAIN_DATASET_PATH = os.path.join("data", "train.json")

jieba.setLogLevel("ERROR")


def normalize(sentence: str):
    return " ".join(jieba.cut(sentence))


class BaseClassifier:
    """
    底层分类器。

    使用 TF-IDF 向量化文本，然后使用朴素贝叶斯预测标签。
    """

    def __init__(self):
        self._vectorizer = TfidfVectorizer()
        self._classifier = MultinomialNB(alpha=0.01)

    def _train(self, x: list, y: list):
        X = self._vectorizer.fit_transform(x).toarray()
        self._classifier.fit(X, y)

    def _predict(self, x: list):
        X = self._vectorizer.transform(x).toarray()
        return self._classifier.predict(X)


class Classifier(BaseClassifier):
    """
    问题分类器。

    根据问题中出现的关键词，将问题归于某一已知类别下。
    """

    def __init__(self):
        BaseClassifier.__init__(self)
        questions, labels = Classifier._read_train_dataset()
        self._train(questions, labels)

    def classify(self, sentence: str):
        question = normalize(sentence)
        return self._predict([question])[0]

    @staticmethod
    def _read_train_dataset():
        with open(TRAIN_DATASET_PATH, "r", encoding="utf-8") as fr:
            train_dataset: dict[str, list[str]] = json.load(fr)

        questions = []
        labels = []
        for label, sentences in train_dataset.items():
            questions.extend([normalize(sentence) for sentence in sentences])
            labels.extend([label for _ in sentences])

        return questions, labels


if __name__ == "__main__":
    classifier = Classifier()

    while True:
        sentence = input("请输入问题：").strip()
        label = classifier.classify(sentence)
        print(f"问题分类：{label}")

# Neo4j 数据库地址
DATABASE_URI=

# Neo4j 用户名
DATABASE_USER=

# Neo4j 密码
DATABASE_PASSWORD=

cd backend
gunicorn app:app

# 后端服务地址
VITE_API_BASE_URL=

cd frontend
npm build
npm preview