\n| 0-59<\/td>\n | \u8f83\u5dee<\/td>\n | \u591a\u4e2a\u7ef4\u5ea6\u5b58\u5728\u4e25\u91cd\u95ee\u9898<\/td>\n | \u4e0d\u63a8\u8350\u4f7f\u7528<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n2.3 \u6743\u91cd\u4f18\u5316\u65b9\u6cd5<\/h4>\n\u521d\u59cb\u6743\u91cd\u57fa\u4e8e\u8d77\u540d\u4e13\u5bb6\u7684\u7ecf\u9a8c\u8bbe\u5b9a，\u4f46\u4e13\u5bb6\u7ecf\u9a8c\u4e0d\u4e00\u5b9a\u7b26\u5408\u7528\u6237\u7684\u5b9e\u9645\u504f\u597d\u3002\u6211\u4eec\u91c7\u7528 \u201c\u57fa\u4e8e\u7528\u6237\u53cd\u9988\u7684\u6743\u91cd\u8fed\u4ee3\u4f18\u5316\u201d \u65b9\u6cd5：<\/p>\n \u521d\u59cb\u6743\u91cd（\u4e13\u5bb6\u7ecf\u9a8c）
\n \u2193
\n\u7528\u6237\u8bc4\u5206\u6570\u636e\u91c7\u96c6（\u7528\u6237\u5bf9\u540d\u5b57\u7684\u4e3b\u89c2\u8bc4\u5206）
\n \u2193
\n\u76f8\u5173\u6027\u5206\u6790（\u5404\u5b50\u6307\u6807\u4e0e\u7528\u6237\u6ee1\u610f\u5ea6\u7684\u76f8\u5173\u6027）
\n \u2193
\n\u6743\u91cd\u8c03\u6574（\u63d0\u9ad8\u9ad8\u76f8\u5173\u6027\u6307\u6807\u6743\u91cd，\u964d\u4f4e\u4f4e\u76f8\u5173\u6027\u6307\u6807\u6743\u91cd）
\n \u2193
\nA\/B\u6d4b\u8bd5\u9a8c\u8bc1（\u65b0\u65e7\u6743\u91cd\u7684\u8bc4\u5206\u6ee1\u610f\u5ea6\u5bf9\u6bd4）
\n \u2193
\n\u6743\u91cd\u66f4\u65b0（\u901a\u8fc7\u9a8c\u8bc1\u5219\u66f4\u65b0，\u5426\u5219\u56de\u6eda）
\n \u2193
\n\u6301\u7eed\u8fed\u4ee3（\u6bcf\u5b63\u5ea6\u91cd\u65b0\u91c7\u96c6\u6570\u636e\u5e76\u4f18\u5316）<\/p>\n # algorithms\/weight_optimizer.py
\nimport numpy as np
\nimport pandas as pd
\nfrom typing import Dict, List, Tuple
\nfrom scipy.optimize import minimize
\nfrom sklearn.model_selection import train_test_split
\nfrom sklearn.metrics import mean_squared_error, r2_score<\/p>\n class WeightOptimizer:
\n """\u57fa\u4e8e\u7528\u6237\u53cd\u9988\u7684\u6743\u91cd\u4f18\u5316\u5668"""<\/p>\n def __init__(self, initial_weights: Dict[str, float]):
\n self.weights = initial_weights.copy()
\n self.optimization_history = []<\/p>\n def calculate_score(self, sub_scores: Dict[str, float],
\n weights: Dict[str, float] = None) -> float:
\n """\u6839\u636e\u5b50\u6307\u6807\u8bc4\u5206\u548c\u6743\u91cd\u8ba1\u7b97\u7efc\u5408\u8bc4\u5206"""
\n w = weights or self.weights
\n total_weight = sum(w.values())
\n score = sum(sub_scores.get(k, 0) * w.get(k, 0) for k in w) \/ total_weight
\n return round(score, 1)<\/p>\n def optimize(self, feedback_data: pd.DataFrame) -> Dict:
\n """
\n \u57fa\u4e8e\u7528\u6237\u53cd\u9988\u6570\u636e\u4f18\u5316\u6743\u91cd
\n feedback_data: \u5305\u542b\u5404\u5b50\u6307\u6807\u8bc4\u5206\u548c\u7528\u6237\u4e3b\u89c2\u6ee1\u610f\u5ea6\u7684DataFrame
\n """
\n # \u5206\u79bb\u7279\u5f81\u548c\u76ee\u6807
\n feature_cols = [c for c in feedback_data.columns if c != "user_satisfaction"]
\n X = feedback_data[feature_cols].values
\n y = feedback_data["user_satisfaction"].values<\/p>\n # \u5212\u5206\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6
\n X_train, X_test, y_train, y_test = train_test_split(
\n X, y, test_size=0.2, random_state=42
\n )<\/p>\n # \u521d\u59cb\u6743\u91cd\u5411\u91cf
\n initial_w = np.array([self.weights.get(col, 0.1) for col in feature_cols])<\/p>\n # \u76ee\u6807\u51fd\u6570：\u6700\u5c0f\u5316\u9884\u6d4b\u8bc4\u5206\u4e0e\u7528\u6237\u6ee1\u610f\u5ea6\u7684MSE
\n def objective(w):
\n # \u6743\u91cd\u5f52\u4e00\u5316
\n w_norm = w \/ w.sum()
\n predictions = X_train.dot(w_norm)
\n return mean_squared_error(y_train, predictions)<\/p>\n # \u7ea6\u675f：\u6240\u6709\u6743\u91cd\u4e3a\u6b63，\u4e14\u548c\u4e3a1
\n constraints = {"type": "eq", "fun": lambda w: np.sum(w) – 1}
\n bounds = [(0.01, 0.5) for _ in range(len(feature_cols))]<\/p>\n # \u4f18\u5316
\n result = minimize(
\n objective, initial_w, method="SLSQP",
\n bounds=bounds, constraints=constraints,
\n options={"maxiter": 1000, "disp": False}
\n )<\/p>\n # \u5f52\u4e00\u5316\u6700\u4f18\u6743\u91cd
\n optimal_w = result.x \/ result.x.sum()
\n optimal_weights = {col: round(float(w), 4) for col, w in zip(feature_cols, optimal_w)}<\/p>\n # \u5728\u6d4b\u8bd5\u96c6\u4e0a\u9a8c\u8bc1
\n predictions_test = X_test.dot(optimal_w)
\n mse_new = mean_squared_error(y_test, predictions_test)
\n r2_new = r2_score(y_test, predictions_test)<\/p>\n # \u65e7\u6743\u91cd\u5728\u6d4b\u8bd5\u96c6\u4e0a\u7684\u8868\u73b0
\n old_w = initial_w \/ initial_w.sum()
\n predictions_old = X_test.dot(old_w)
\n mse_old = mean_squared_error(y_test, predictions_old)
\n r2_old = r2_score(y_test, predictions_old)<\/p>\n # \u8bb0\u5f55\u4f18\u5316\u5386\u53f2
\n self.optimization_history.append({
\n "timestamp": pd.Timestamp.now().isoformat(),
\n "sample_size": len(feedback_data),
\n "old_weights": self.weights.copy(),
\n "new_weights": optimal_weights,
\n "old_mse": round(mse_old, 4),
\n "new_mse": round(mse_new, 4),
\n "old_r2": round(r2_old, 4),
\n "new_r2": round(r2_new, 4),
\n "improvement": round((mse_old – mse_new) \/ mse_old * 100, 2),
\n })<\/p>\n return {
\n "optimal_weights": optimal_weights,
\n "old_mse": round(mse_old, 4),
\n "new_mse": round(mse_new, 4),
\n "old_r2": round(r2_old, 4),
\n "new_r2": round(r2_new, 4),
\n "mse_improvement_pct": round((mse_old – mse_new) \/ mse_old * 100, 2),
\n "r2_improvement": round(r2_new – r2_old, 4),
\n }<\/p>\n def apply_weights(self, new_weights: Dict[str, float]):
\n """\u5e94\u7528\u65b0\u6743\u91cd"""
\n self.weights = new_weights.copy()<\/p>\n \u4e09\u3001\u97f3\u97f5\u8bc4\u5206\u7b97\u6cd5\u5b9e\u73b0<\/h3>\n3.1 \u62fc\u97f3\u4e0e\u58f0\u8c03\u5206\u6790<\/h4>\n\u97f3\u97f5\u8bc4\u5206\u7684\u57fa\u7840\u662f\u51c6\u786e\u83b7\u53d6\u6bcf\u4e2a\u5b57\u7684\u62fc\u97f3\u548c\u58f0\u8c03\u3002\u6211\u4eec\u4f7f\u7528 pypinyin \u5e93，\u5e76\u7ed3\u5408\u81ea\u5b9a\u4e49\u62fc\u97f3\u5e93\u5904\u7406\u591a\u97f3\u5b57\u548c\u7279\u6b8a\u5b57：<\/p>\n # algorithms\/phonetic_scorer.py
\nfrom pypinyin import pinyin, Style, lazy_pinyin
\nfrom typing import List, Dict, Tuple
\nimport re<\/p>\n class PhoneticScorer:
\n """\u97f3\u97f5\u8bc4\u5206\u5668"""<\/p>\n # \u58f0\u8c03\u5206\u7c7b：1\u30012\u58f0\u4e3a\u5e73\u58f0，3\u30014\u58f0\u4e3a\u4ec4\u58f0
\n TONE_CATEGORY = {1: "\u5e73", 2: "\u5e73", 3: "\u4ec4", 4: "\u4ec4", 5: "\u8f7b\u58f0"}<\/p>\n # \u97f5\u6bcd\u5206\u7c7b
\n FINAL_CATEGORY = {
\n "\u5f00\u53e3\u547c": ["a", "o", "e", "ai", "ei", "ao", "ou", "an", "en", "ang", "eng", "er"],
\n "\u9f50\u9f7f\u547c": ["i", "ia", "ie", "iao", "iou", "ian", "in", "iang", "ing"],
\n "\u5408\u53e3\u547c": ["u", "ua", "uo", "uai", "uei", "uan", "uen", "uang", "ueng", "ong"],
\n "\u64ae\u53e3\u547c": ["\u00fc", "\u00fce", "\u00fcan", "\u00fcn", "iong"],
\n }<\/p>\n def __init__(self, char_db_path: str = None):
\n self.char_db = {} # \u591a\u97f3\u5b57\u7279\u6b8a\u5904\u7406\u5e93
\n if char_db_path:
\n self._load_char_db(char_db_path)<\/p>\n def get_pinyin(self, char: str, context: str = None) -> Tuple[str, int]:
\n """
\n \u83b7\u53d6\u6c49\u5b57\u7684\u62fc\u97f3\u548c\u58f0\u8c03
\n char: \u6c49\u5b57
\n context: \u4e0a\u4e0b\u6587（\u7528\u4e8e\u591a\u97f3\u5b57\u5224\u65ad）
\n \u8fd4\u56de: (\u62fc\u97f3\u4e0d\u5e26\u58f0\u8c03, \u58f0\u8c031-4)
\n """
\n # \u5148\u67e5\u81ea\u5b9a\u4e49\u591a\u97f3\u5b57\u5e93
\n if char in self.char_db and context:
\n for reading, conditions in self.char_db[char].items():
\n if any(cond in context for cond in conditions):
\n return self._split_pinyin(reading)<\/p>\n # \u4f7f\u7528pypinyin\u83b7\u53d6\u62fc\u97f3
\n result = pinyin(char, style=Style.TONE3, heteronym=False)
\n if result and result[0]:
\n py_with_tone = result[0][0]
\n return self._split_pinyin(py_with_tone)<\/p>\n return "", 0<\/p>\n def _split_pinyin(self, py_with_tone: str) -> Tuple[str, int]:
\n """\u5c06\u5e26\u58f0\u8c03\u6570\u5b57\u7684\u62fc\u97f3\u62c6\u5206\u4e3a\u62fc\u97f3\u548c\u58f0\u8c03"""
\n match = re.match(r"^([a-zA-Z\u00fc]+)(\\\\d?)$", py_with_tone)
\n if match:
\n py = match.group(1)
\n tone = int(match.group(2)) if match.group(2) else 5
\n return py, tone
\n return py_with_tone, 0<\/p>\n def get_name_pinyin(self, name: str) -> List[Dict]:
\n """\u83b7\u53d6\u5b8c\u6574\u540d\u5b57\u7684\u62fc\u97f3\u4fe1\u606f"""
\n results = []
\n for i, char in enumerate(name):
\n context = name[max(0, i-1):i+2] # \u524d\u540e\u5404\u53d6\u4e00\u4e2a\u5b57\u4f5c\u4e3a\u4e0a\u4e0b\u6587
\n py, tone = self.get_pinyin(char, context)
\n results.append({
\n "char": char,
\n "pinyin": py,
\n "tone": tone,
\n "tone_category": self.TONE_CATEGORY.get(tone, "\u672a\u77e5"),
\n "initial": self._get_initial(py),
\n "final": self._get_final(py),
\n "final_category": self._get_final_category(py),
\n })
\n return results<\/p>\n def _get_initial(self, pinyin: str) -> str:
\n """\u83b7\u53d6\u58f0\u6bcd"""
\n initials = ["zh", "ch", "sh", "b", "p", "m", "f", "d", "t", "n", "l",
\n "g", "k", "h", "j", "q", "x", "r", "z", "c", "s", "y", "w"]
\n for init in initials:
\n if pinyin.startswith(init):
\n return init
\n return "" # \u96f6\u58f0\u6bcd<\/p>\n def _get_final(self, pinyin: str) -> str:
\n """\u83b7\u53d6\u97f5\u6bcd"""
\n initial = self._get_initial(pinyin)
\n return pinyin[len(initial):] if initial else pinyin<\/p>\n def _get_final_category(self, pinyin: str) -> str:
\n """\u83b7\u53d6\u97f5\u6bcd\u5206\u7c7b（\u56db\u547c）"""
\n final = self._get_final(pinyin)
\n for category, finals in self.FINAL_CATEGORY.items():
\n if final in finals:
\n return category
\n return "\u672a\u77e5"<\/p>\n 3.2 \u97f3\u97f5\u548c\u8c10\u5ea6\u8ba1\u7b97<\/h4>\n\u97f3\u97f5\u548c\u8c10\u5ea6\u4ece\u58f0\u8c03\u642d\u914d\u3001\u97f5\u6bcd\u548c\u8c10\u3001\u58f0\u6bcd\u642d\u914d\u4e09\u4e2a\u5b50\u7ef4\u5ea6\u8bc4\u4f30：<\/p>\n def score_phonetic(self, name: str) -> Dict:
\n """\u8ba1\u7b97\u97f3\u97f5\u7efc\u5408\u8bc4\u5206"""
\n pinyin_info = self.get_name_pinyin(name)<\/p>\n # 1. \u58f0\u8c03\u642d\u914d\u8bc4\u5206
\n tone_score = self._score_tone_pattern(pinyin_info)<\/p>\n # 2. \u97f5\u6bcd\u548c\u8c10\u8bc4\u5206
\n final_score = self._score_final_harmony(pinyin_info)<\/p>\n # 3. \u58f0\u6bcd\u642d\u914d\u8bc4\u5206
\n initial_score = self._score_initial_pattern(pinyin_info)<\/p>\n # 4. \u8c10\u97f3\u6b67\u4e49\u68c0\u6d4b（\u6263\u5206\u5236）
\n homophone_penalty = self._check_homophone(name, pinyin_info)<\/p>\n # \u97f3\u97f5\u7efc\u5408\u8bc4\u5206（\u58f0\u8c0340% + \u97f5\u6bcd30% + \u58f0\u6bcd30%，\u518d\u51cf\u8c10\u97f3\u60e9\u7f5a）
\n total = tone_score * 0.4 + final_score * 0.3 + initial_score * 0.3
\n total = max(0, total – homophone_penalty)<\/p>\n return {
\n "total_score": round(total, 1),
\n "tone_score": tone_score,
\n "final_score": final_score,
\n "initial_score": initial_score,
\n "homophone_penalty": homophone_penalty,
\n "pinyin_info": pinyin_info,
\n "details": {
\n "tone_pattern": "".join(p["tone_category"] for p in pinyin_info),
\n "final_repeat": self._check_final_repeat(pinyin_info),
\n "initial_repeat": self._check_initial_repeat(pinyin_info),
\n }
\n }<\/p>\n def _score_tone_pattern(self, pinyin_info: List[Dict]) -> float:
\n """\u58f0\u8c03\u642d\u914d\u8bc4\u5206：\u5e73\u4ec4\u4ea4\u66ff\u4e3a\u4f73，\u8fde\u7eed\u540c\u58f0\u8c03\u4e3a\u5dee"""
\n if len(pinyin_info) < 2:
\n return 85.0 # \u5355\u5b57\u540d\u9ed8\u8ba4\u8f83\u9ad8\u5206<\/p>\n tones = [p["tone_category"] for p in pinyin_info]<\/p>\n # \u7406\u60f3\u6a21\u5f0f：\u5e73\u4ec4\u5e73\u3001\u4ec4\u5e73\u4ec4\u3001\u5e73\u4ec4\u4ec4\u3001\u4ec4\u5e73\u5e73（\u6709\u53d8\u5316）
\n # \u5dee\u6a21\u5f0f：\u5e73\u5e73\u5e73\u3001\u4ec4\u4ec4\u4ec4（\u5355\u8c03）<\/p>\n # \u8ba1\u7b97\u58f0\u8c03\u53d8\u5316\u6b21\u6570
\n changes = sum(1 for i in range(1, len(tones)) if tones[i] != tones[i-1])
\n max_changes = len(tones) – 1
\n change_ratio = changes \/ max_changes if max_changes > 0 else 0<\/p>\n # \u57fa\u7840\u5206：\u53d8\u5316\u8d8a\u591a\u5206\u8d8a\u9ad8
\n base_score = 60 + change_ratio * 40<\/p>\n # \u60e9\u7f5a：\u5168\u5e73\u6216\u5168\u4ec4
\n if len(set(tones)) == 1:
\n base_score -= 20<\/p>\n # \u5956\u52b1：\u7406\u60f3\u7684\u5e73\u4ec4\u4ea4\u66ff\u6a21\u5f0f
\n ideal_patterns = [["\u5e73", "\u4ec4", "\u5e73"], ["\u4ec4", "\u5e73", "\u4ec4"],
\n ["\u5e73", "\u4ec4"], ["\u4ec4", "\u5e73"]]
\n if tones in ideal_patterns:
\n base_score += 10<\/p>\n return round(min(100, max(0, base_score)), 1)<\/p>\n def _score_final_harmony(self, pinyin_info: List[Dict]) -> float:
\n """\u97f5\u6bcd\u548c\u8c10\u8bc4\u5206：\u907f\u514d\u97f5\u6bcd\u91cd\u590d，\u56db\u547c\u642d\u914d\u591a\u6837\u4e3a\u4f73"""
\n if len(pinyin_info) < 2:
\n return 85.0<\/p>\n finals = [p["final"] for p in pinyin_info]
\n final_categories = [p["final_category"] for p in pinyin_info]<\/p>\n score = 85.0<\/p>\n # \u60e9\u7f5a：\u5b8c\u5168\u76f8\u540c\u7684\u97f5\u6bcd（\u5982"\u4f9d\u4f9d"y\u012b y\u012b）
\n if len(set(finals)) == 1:
\n score -= 30<\/p>\n # \u60e9\u7f5a：\u97f5\u6bcd\u8fc7\u4e8e\u76f8\u4f3c（\u5982"an"\u548c"ian"）
\n for i in range(len(finals)):
\n for j in range(i+1, len(finals)):
\n if self._finals_similar(finals[i], finals[j]):
\n score -= 10<\/p>\n # \u5956\u52b1：\u56db\u547c\u642d\u914d\u591a\u6837
\n category_diversity = len(set(final_categories)) \/ len(final_categories)
\n score += category_diversity * 15<\/p>\n return round(min(100, max(0, score)), 1)<\/p>\n def _finals_similar(self, f1: str, f2: str) -> bool:
\n """\u5224\u65ad\u4e24\u4e2a\u97f5\u6bcd\u662f\u5426\u8fc7\u4e8e\u76f8\u4f3c"""
\n # \u97f5\u5c3e\u76f8\u540c\u4e14\u4e3b\u5143\u97f3\u76f8\u8fd1
\n if f1[-1] == f2[-1] and len(f1) > 1 and len(f2) > 1:
\n # \u68c0\u67e5\u4e3b\u5143\u97f3\u662f\u5426\u76f8\u540c
\n vowels = set("aeiou\u00fc")
\n main_vowel1 = next((c for c in f1 if c in vowels), "")
\n main_vowel2 = next((c for c in f2 if c in vowels), "")
\n if main_vowel1 == main_vowel2:
\n return True
\n return False<\/p>\n def _score_initial_pattern(self, pinyin_info: List[Dict]) -> float:
\n """\u58f0\u6bcd\u642d\u914d\u8bc4\u5206：\u907f\u514d\u58f0\u6bcd\u91cd\u590d，\u7279\u522b\u662f\u7ed5\u53e3\u7684\u7ec4\u5408"""
\n if len(pinyin_info) < 2:
\n return 85.0<\/p>\n initials = [p["initial"] for p in pinyin_info]
\n score = 85.0<\/p>\n # \u60e9\u7f5a：\u5b8c\u5168\u76f8\u540c\u7684\u58f0\u6bcd（\u5982"\u4e3d\u4e3d"l\u00ec l\u00ec）
\n if len(set(initials)) == 1 and initials[0]:
\n score -= 25<\/p>\n # \u60e9\u7f5a：\u7ed5\u53e3\u7ec4\u5408（\u5982zh\/ch\/sh\u4e0ez\/c\/s\u6df7\u7528，n\/l\u6df7\u7528）
\n confusing_pairs = [
\n ({"zh", "z"}, {"ch", "c"}, {"sh", "s"}),
\n ({"n", "l"},),
\n ({"f", "h"},),
\n ]
\n for pair_group in confusing_pairs:
\n pair_set = set()
\n for s in pair_group:
\n pair_set.update(s)
\n if len(set(initials) & pair_set) >= 2:
\n score -= 15<\/p>\n # \u5956\u52b1：\u58f0\u6bcd\u53d1\u97f3\u90e8\u4f4d\u591a\u6837
\n places = [self._initial_place(init) for init in initials if init]
\n if len(set(places)) == len(places):
\n score += 10<\/p>\n return round(min(100, max(0, score)), 1)<\/p>\n def _initial_place(self, initial: str) -> str:
\n """\u83b7\u53d6\u58f0\u6bcd\u53d1\u97f3\u90e8\u4f4d"""
\n places = {
\n "\u53cc\u5507\u97f3": ["b", "p", "m"],
\n "\u5507\u9f7f\u97f3": ["f"],
\n "\u820c\u5c16\u524d\u97f3": ["z", "c", "s"],
\n "\u820c\u5c16\u4e2d\u97f3": ["d", "t", "n", "l"],
\n "\u820c\u5c16\u540e\u97f3": ["zh", "ch", "sh", "r"],
\n "\u820c\u9762\u97f3": ["j", "q", "x"],
\n "\u820c\u6839\u97f3": ["g", "k", "h"],
\n "\u96f6\u58f0\u6bcd": ["y", "w", ""],
\n }
\n for place, initials in places.items():
\n if initial in initials:
\n return place
\n return "\u672a\u77e5"<\/p>\n 3.3 \u8c10\u97f3\u4e0e\u6b67\u4e49\u68c0\u6d4b<\/h4>\n\u8c10\u97f3\u68c0\u6d4b\u662f\u97f3\u97f5\u8bc4\u5206\u4e2d\u6700\u6709\u4ef7\u503c\u4f46\u4e5f\u6700\u590d\u6742\u7684\u90e8\u5206，\u9700\u8981\u68c0\u6d4b\u540d\u5b57\u662f\u5426\u6709\u4e0d\u826f\u8c10\u97f3：<\/p>\n def _check_homophone(self, name: str, pinyin_info: List[Dict]) -> float:
\n """
\n \u68c0\u6d4b\u8c10\u97f3\u6b67\u4e49，\u8fd4\u56de\u60e9\u7f5a\u5206\u6570（0-40\u5206）
\n \u60e9\u7f5a\u8d8a\u591a，\u8bf4\u660e\u8c10\u97f3\u95ee\u9898\u8d8a\u4e25\u91cd
\n """
\n penalty = 0.0<\/p>\n # 1. \u6574\u4f53\u8c10\u97f3\u68c0\u6d4b（\u540d\u5b57\u6574\u4f53\u8bfb\u97f3\u662f\u5426\u4e0e\u4e0d\u826f\u8bcd\u6c47\u76f8\u540c\u6216\u76f8\u8fd1）
\n full_pinyin = " ".join(p["pinyin"] for p in pinyin_info)
\n for bad_word, bad_pinyin in self.BAD_HOMOPHONES.items():
\n if self._pinyin_similar(full_pinyin, bad_pinyin):
\n penalty += 20
\n break<\/p>\n # 2. \u8fde\u7eed\u5b57\u8c10\u97f3\u68c0\u6d4b（\u76f8\u90bb\u4e24\u5b57\u662f\u5426\u7ec4\u6210\u4e0d\u826f\u8bcd\u6c47）
\n for i in range(len(pinyin_info) – 1):
\n two_pinyin = f"{pinyin_info[i]['pinyin']} {pinyin_info[i+1]['pinyin']}"
\n for bad_word, bad_pinyin in self.BAD_HOMOPHONES.items():
\n if self._pinyin_similar(two_pinyin, bad_pinyin):
\n penalty += 15
\n break<\/p>\n # 3. \u5355\u5b57\u8c10\u97f3\u68c0\u6d4b（\u5355\u5b57\u662f\u5426\u4e0e\u4e0d\u826f\u5b57\u540c\u97f3）
\n for p in pinyin_info:
\n if p["pinyin"] in self.BAD_SINGLE_CHARS:
\n penalty += 10
\n break<\/p>\n return min(40, penalty)<\/p>\n def _pinyin_similar(self, py1: str, py2: str) -> bool:
\n """\u5224\u65ad\u4e24\u4e2a\u62fc\u97f3\u4e32\u662f\u5426\u76f8\u4f3c（\u5141\u8bb8\u58f0\u8c03\u4e0d\u540c\u3001\u97f5\u6bcd\u76f8\u8fd1）"""
\n parts1 = py1.split()
\n parts2 = py2.split()<\/p>\n if len(parts1) != len(parts2):
\n return False<\/p>\n match_count = 0
\n for p1, p2 in zip(parts1, parts2):
\n # \u5b8c\u5168\u76f8\u540c
\n if p1 == p2:
\n match_count += 1
\n # \u58f0\u6bcd\u76f8\u540c\u3001\u97f5\u6bcd\u76f8\u8fd1
\n elif (self._get_initial(p1) == self._get_initial(p2) and
\n self._finals_similar(self._get_final(p1), self._get_final(p2))):
\n match_count += 0.7<\/p>\n return match_count \/ len(parts1) >= 0.8<\/p>\n # \u4e0d\u826f\u8c10\u97f3\u8bcd\u5e93（\u793a\u4f8b，\u5b9e\u9645\u5e94\u7528\u4e2d\u9700\u8981\u66f4\u5b8c\u6574\u7684\u8bcd\u5e93）
\n BAD_HOMOPHONES = {
\n "\u7b28\u86cb": "ben dan",
\n "\u767d\u75f4": "bai chi",
\n "\u8d31\u4eba": "jian ren",
\n "\u738b\u516b\u86cb": "wang ba dan",
\n "\u795e\u7ecf\u75c5": "shen jing bing",
\n "\u6d41\u6c13": "liu mang",
\n "\u65e0\u803b": "wu chi",
\n "\u5e9f\u7269": "fei wu",
\n }<\/p>\n BAD_SINGLE_CHARS = {
\n "si": "\u6b7b",
\n "sha": "\u6740",
\n "gui": "\u9b3c",
\n "chou": "\u4e11",
\n "e": "\u6076",
\n }<\/p>\n \u8be5\u97f3\u97f5\u8bc4\u5206\u7b97\u6cd5\u5df2\u5e94\u7528\u4e8e\u5728\u7ebf\u8d77\u540d\u5de5\u5177\u7684\u540d\u5b57\u8bc4\u5206\u529f\u80fd，\u7528\u6237\u8f93\u5165\u540d\u5b57\u540e\u53ef\u5b9e\u65f6\u67e5\u770b\u97f3\u97f5\u8bc4\u5206\u3001\u62fc\u97f3\u4fe1\u606f\u548c\u8c10\u97f3\u68c0\u6d4b\u7ed3\u679c，\u5e2e\u52a9\u5bb6\u957f\u907f\u514d\u8d77\u51fa\u6709\u4e0d\u826f\u8c10\u97f3\u7684\u540d\u5b57\u3002<\/p>\n \u56db\u3001\u5b57\u5f62\u8bc4\u5206\u7b97\u6cd5\u5b9e\u73b0<\/h3>\n4.1 \u7b14\u753b\u6570\u4e0e\u7ed3\u6784\u5206\u6790<\/h4>\n\u5b57\u5f62\u8bc4\u5206\u7684\u57fa\u7840\u662f\u51c6\u786e\u83b7\u53d6\u6bcf\u4e2a\u5b57\u7684\u7b14\u753b\u6570\u548c\u5b57\u5f62\u7ed3\u6784：<\/p>\n # algorithms\/graphic_scorer.py
\nfrom typing import List, Dict
\nimport pandas as pd<\/p>\n class GraphicScorer:
\n """\u5b57\u5f62\u8bc4\u5206\u5668"""<\/p>\n # \u5b57\u5f62\u7ed3\u6784\u5206\u7c7b
\n STRUCTURE_TYPES = {
\n "\u72ec\u4f53\u7ed3\u6784": ["\u4e00", "\u4e59", "\u4eba", "\u5165", "\u516b", "\u513f", "\u5315", "\u51e0", "\u5201", "\u4e86"],
\n "\u5de6\u53f3\u7ed3\u6784": ["\u4ed6", "\u4f60", "\u4eec", "\u597d", "\u7684", "\u548c", "\u5979", "\u5b83", "\u628a", "\u88ab"],
\n "\u4e0a\u4e0b\u7ed3\u6784": ["\u5b57", "\u5bb6", "\u82b1", "\u8349", "\u82d7", "\u82f1", "\u6770", "\u5404", "\u540d", "\u591a"],
\n "\u5de6\u4e2d\u53f3\u7ed3\u6784": ["\u6811", "\u6e56", "\u6e3a", "\u68da", "\u6e24", "\u6ec1", "\u6f4b", "\u6f8e", "\u6f6d", "\u6fb3"],
\n "\u4e0a\u4e2d\u4e0b\u7ed3\u6784": ["\u610f", "\u83ab", "\u9ec4", "\u846c", "\u7980", "\u5180", "\u7bdd", "\u7be1", "\u56a3", "\u5151"],
\n "\u5168\u5305\u56f4\u7ed3\u6784": ["\u56fd", "\u56de", "\u56e0", "\u56ed", "\u56f4", "\u56fe", "\u5706", "\u5708", "\u56fa", "\u5703"],
\n "\u534a\u5305\u56f4\u7ed3\u6784": ["\u8fd9", "\u8fc7", "\u5efa", "\u5ef6", "\u5f0f", "\u6b66", "\u6216", "\u8f7d", "\u621a", "\u5a01"],
\n "\u54c1\u5b57\u7ed3\u6784": ["\u54c1", "\u6676", "\u68ee", "\u6dfc", "\u7131", "\u579a", "\u946b", "\u78ca", "\u4f17", "\u77d7"],
\n "\u7a7f\u63d2\u7ed3\u6784": ["\u5deb", "\u4e58", "\u723d", "\u4e56", "\u5782", "\u91cd", "\u79b9", "\u79ba", "\u79bb", "\u80e4"],
\n }<\/p>\n def __init__(self, char_db_path: str):
\n # \u52a0\u8f7d\u6c49\u5b57\u6570\u636e\u5e93：\u5305\u542b\u7b14\u753b\u6570\u3001\u7ed3\u6784\u3001\u5e38\u7528\u5ea6\u7b49
\n self.char_db = pd.read_csv(char_db_path).set_index("char")<\/p>\n def get_char_info(self, char: str) -> Dict:
\n """\u83b7\u53d6\u6c49\u5b57\u7684\u5b57\u5f62\u4fe1\u606f"""
\n if char in self.char_db.index:
\n row = self.char_db.loc[char]
\n return {
\n "char": char,
\n "strokes": int(row["kangxi_strokes"]),
\n "structure": row.get("structure", self._infer_structure(char)),
\n "common_level": int(row.get("common_level", 3)), # 1\u5e38\u7528 2\u6b21\u5e38\u7528 3\u751f\u50fb
\n "radical": row.get("radical", ""),
\n "radical_strokes": int(row.get("radical_strokes", 0)),
\n }
\n return {
\n "char": char,
\n "strokes": 0,
\n "structure": "\u672a\u77e5",
\n "common_level": 4, # \u672a\u6536\u5f55\u89c6\u4e3a\u6781\u751f\u50fb
\n "radical": "",
\n "radical_strokes": 0,
\n }<\/p>\n def _infer_structure(self, char: str) -> str:
\n """\u6839\u636e\u504f\u65c1\u63a8\u65ad\u5b57\u5f62\u7ed3\u6784（\u7b80\u5316\u7248）"""
\n # \u5b9e\u9645\u5e94\u7528\u4e2d\u5e94\u4f7f\u7528\u5b8c\u6574\u7684\u5b57\u5f62\u7ed3\u6784\u6570\u636e\u5e93
\n for structure, chars in self.STRUCTURE_TYPES.items():
\n if char in chars:
\n return structure
\n return "\u672a\u77e5"<\/p>\n 4.2 \u5b57\u5f62\u7f8e\u89c2\u5ea6\u8ba1\u7b97<\/h4>\n\u5b57\u5f62\u7f8e\u89c2\u5ea6\u4ece\u7b14\u753b\u5747\u8861\u3001\u7ed3\u6784\u642d\u914d\u3001\u89c6\u89c9\u534f\u8c03\u4e09\u4e2a\u5b50\u7ef4\u5ea6\u8bc4\u4f30：<\/p>\n def score_graphic(self, name: str) -> Dict:
\n """\u8ba1\u7b97\u5b57\u5f62\u7efc\u5408\u8bc4\u5206"""
\n char_info = [self.get_char_info(c) for c in name]<\/p>\n # 1. \u7b14\u753b\u5747\u8861\u8bc4\u5206
\n stroke_score = self._score_stroke_balance(char_info)<\/p>\n # 2. \u7ed3\u6784\u642d\u914d\u8bc4\u5206
\n structure_score = self._score_structure_diversity(char_info)<\/p>\n # 3. \u751f\u50fb\u7a0b\u5ea6\u8bc4\u5206
\n rarity_score = self._score_rarity(char_info)<\/p>\n # 4. \u8fa8\u8bc6\u5ea6\u8bc4\u5206
\n recognition_score = self._score_recognition(char_info)<\/p>\n # \u5b57\u5f62\u7efc\u5408\u8bc4\u5206
\n total = (stroke_score * 0.30 + structure_score * 0.25 +
\n rarity_score * 0.25 + recognition_score * 0.20)<\/p>\n return {
\n "total_score": round(total, 1),
\n "stroke_score": stroke_score,
\n "structure_score": structure_score,
\n "rarity_score": rarity_score,
\n "recognition_score": recognition_score,
\n "char_info": char_info,
\n "details": {
\n "total_strokes": sum(c["strokes"] for c in char_info),
\n "avg_strokes": round(sum(c["strokes"] for c in char_info) \/ len(char_info), 1),
\n "structures": [c["structure"] for c in char_info],
\n "has_rare_char": any(c["common_level"] >= 3 for c in char_info),
\n }
\n }<\/p>\n def _score_stroke_balance(self, char_info: List[Dict]) -> float:
\n """\u7b14\u753b\u5747\u8861\u8bc4\u5206：\u5404\u5b57\u7b14\u753b\u6570\u4e0d\u5b9c\u76f8\u5dee\u8fc7\u5927，\u603b\u7b14\u753b\u9002\u4e2d"""
\n strokes = [c["strokes"] for c in char_info if c["strokes"] > 0]<\/p>\n if not strokes:
\n return 50.0<\/p>\n score = 80.0<\/p>\n # 1. \u7b14\u753b\u5dee\u5f02\u60e9\u7f5a（\u76f8\u90bb\u5b57\u7b14\u753b\u5dee\u8fc7\u5927）
\n for i in range(len(strokes) – 1):
\n diff = abs(strokes[i] – strokes[i+1])
\n if diff > 10:
\n score -= 15
\n elif diff > 7:
\n score -= 10
\n elif diff > 5:
\n score -= 5<\/p>\n # 2. \u603b\u7b14\u753b\u6570\u8bc4\u4f30（\u9002\u4e2d\u4e3a\u4f73，\u8fc7\u591a\u8fc7\u5c11\u90fd\u6263\u5206）
\n total = sum(strokes)
\n if 10 <= total <= 30:
\n score += 10 # \u7406\u60f3\u8303\u56f4
\n elif total < 8:
\n score -= 10 # \u8fc7\u4e8e\u7b80\u5355
\n elif total > 40:
\n score -= 20 # \u8fc7\u4e8e\u7e41\u7410<\/p>\n # 3. \u5355\u5b57\u7b14\u753b\u6781\u7aef\u503c\u60e9\u7f5a
\n for s in strokes:
\n if s > 25:
\n score -= 10 # \u5355\u5b57\u7b14\u753b\u8fc7\u591a
\n elif s < 3:
\n score -= 5 # \u5355\u5b57\u7b14\u753b\u8fc7\u5c11<\/p>\n return round(min(100, max(0, score)), 1)<\/p>\n def _score_structure_diversity(self, char_info: List[Dict]) -> float:
\n """\u7ed3\u6784\u642d\u914d\u8bc4\u5206：\u5b57\u5f62\u7ed3\u6784\u591a\u6837\u4e3a\u4f73，\u907f\u514d\u91cd\u590d\u7ed3\u6784"""
\n structures = [c["structure"] for c in char_info if c["structure"] != "\u672a\u77e5"]<\/p>\n if not structures:
\n return 60.0<\/p>\n score = 75.0<\/p>\n # \u7ed3\u6784\u591a\u6837\u6027\u5956\u52b1
\n diversity = len(set(structures)) \/ len(structures)
\n score += diversity * 25<\/p>\n # \u60e9\u7f5a：\u5168\u76f8\u540c\u7ed3\u6784（\u5982"\u6797\u68ee"\u90fd\u662f\u5de6\u53f3\u7ed3\u6784）
\n if len(set(structures)) == 1:
\n score -= 20<\/p>\n # \u60e9\u7f5a：\u590d\u6742\u7ed3\u6784\u7ec4\u5408（\u5982\u5168\u5305\u56f4+\u54c1\u5b57\u7ed3\u6784，\u89c6\u89c9\u4e0a\u8fc7\u4e8e\u590d\u6742）
\n complex_structures = {"\u5168\u5305\u56f4\u7ed3\u6784", "\u54c1\u5b57\u7ed3\u6784", "\u5de6\u4e2d\u53f3\u7ed3\u6784", "\u4e0a\u4e2d\u4e0b\u7ed3\u6784"}
\n if len(set(structures) & complex_structures) >= 2:
\n score -= 10<\/p>\n return round(min(100, max(0, score)), 1)<\/p>\n def _score_rarity(self, char_info: List[Dict]) -> float:
\n """\u751f\u50fb\u7a0b\u5ea6\u8bc4\u5206：\u5e38\u7528\u5b57\u4e3a\u4f73，\u751f\u50fb\u5b57\u6263\u5206"""
\n levels = [c["common_level"] for c in char_info]
\n score = 100.0<\/p>\n for level in levels:
\n if level == 1:
\n pass # \u5e38\u7528\u5b57，\u4e0d\u6263\u5206
\n elif level == 2:
\n score -= 5 # \u6b21\u5e38\u7528\u5b57，\u5c11\u91cf\u6263\u5206
\n elif level == 3:
\n score -= 20 # \u751f\u50fb\u5b57，\u8f83\u591a\u6263\u5206
\n elif level == 4:
\n score -= 40 # \u6781\u751f\u50fb\/\u672a\u6536\u5f55，\u5927\u91cf\u6263\u5206<\/p>\n # \u5e73\u5747\u6263\u5206
\n score = score \/ len(levels) if levels else 50<\/p>\n return round(min(100, max(0, score)), 1)<\/p>\n def _score_recognition(self, char_info: List[Dict]) -> float:
\n """\u8fa8\u8bc6\u5ea6\u8bc4\u5206：\u540d\u5b57\u662f\u5426\u5bb9\u6613\u88ab\u6b63\u786e\u8bfb\u5199"""
\n score = 85.0<\/p>\n for c in char_info:
\n # \u591a\u97f3\u5b57\u964d\u4f4e\u8fa8\u8bc6\u5ea6
\n if c.get("is_polyphone", False):
\n score -= 10
\n # \u7b14\u753b\u8fc7\u591a\u964d\u4f4e\u8fa8\u8bc6\u5ea6
\n if c["strokes"] > 20:
\n score -= 10
\n # \u4e0e\u5e38\u7528\u5b57\u5b57\u5f62\u76f8\u8fd1（\u5bb9\u6613\u5199\u9519）
\n if c.get("easily_confused", False):
\n score -= 15<\/p>\n # \u540d\u5b57\u6574\u4f53\u8fa8\u8bc6\u5ea6：\u662f\u5426\u5bb9\u6613\u4e0e\u5176\u4ed6\u540d\u5b57\u6df7\u6dc6
\n name_str = "".join(c["char"] for c in char_info)
\n if self._is_easily_confused_name(name_str):
\n score -= 10<\/p>\n return round(min(100, max(0, score)), 1)<\/p>\n def _is_easily_confused_name(self, name: str) -> bool:
\n """\u5224\u65ad\u540d\u5b57\u662f\u5426\u5bb9\u6613\u4e0e\u5176\u4ed6\u540d\u5b57\u6df7\u6dc6（\u7b80\u5316\u7248）"""
\n # \u5b9e\u9645\u5e94\u7528\u4e2d\u5e94\u4e0e\u5e38\u89c1\u540d\u5b57\u5e93\u8fdb\u884c\u76f8\u4f3c\u5ea6\u6bd4\u5bf9
\n confusing_patterns = ["\u5b50\u8f69", "\u6893\u6db5", "\u6d69\u7136", "\u6b23\u6021", "\u5b87\u8f69"]
\n return any(pattern in name for pattern in confusing_patterns)<\/p>\n \u4e94\u3001\u5b57\u4e49\u8bc4\u5206\u7b97\u6cd5\u5b9e\u73b0<\/h3>\n5.1 \u5b57\u4e49\u8912\u8d2c\u4e0e\u5bd3\u610f\u5206\u6790<\/h4>\n\u5b57\u4e49\u8bc4\u5206\u7684\u6838\u5fc3\u662f\u8bc4\u4f30\u6bcf\u4e2a\u5b57\u7684\u5bd3\u610f\u662f\u5426\u79ef\u6781\u6b63\u9762，\u4ee5\u53ca\u540d\u5b57\u6574\u4f53\u7684\u5bd3\u610f\u662f\u5426\u8fde\u8d2f\u7f8e\u597d：<\/p>\n # algorithms\/semantic_scorer.py
\nfrom typing import List, Dict, Optional
\nimport pandas as pd
\nimport jieba
\nfrom collections import defaultdict<\/p>\n class SemanticScorer:
\n """\u5b57\u4e49\u8bc4\u5206\u5668"""<\/p>\n def __init__(self, char_db_path: str, idiom_db_path: str = None,
\n poem_db_path: str = None):
\n # \u6c49\u5b57\u5b57\u4e49\u5e93：\u5305\u542b\u91ca\u4e49\u3001\u8912\u8d2c\u3001\u4e94\u884c\u3001\u6027\u522b\u503e\u5411\u7b49
\n self.char_db = pd.read_csv(char_db_path).set_index("char")
\n # \u6210\u8bed\u5e93（\u7528\u4e8e\u540d\u5b57\u5bd3\u610f\u6269\u5c55）
\n self.idiom_db = self._load_idiom_db(idiom_db_path) if idiom_db_path else {}
\n # \u8bd7\u8bcd\u5178\u6545\u5e93（\u7528\u4e8e\u6587\u5316\u51fa\u5904\u68c0\u6d4b）
\n self.poem_db = self._load_poem_db(poem_db_path) if poem_db_path else {}<\/p>\n def get_char_semantic(self, char: str) -> Dict:
\n """\u83b7\u53d6\u6c49\u5b57\u7684\u8bed\u4e49\u4fe1\u606f"""
\n if char in self.char_db.index:
\n row = self.char_db.loc[char]
\n return {
\n "char": char,
\n "meaning": row.get("meaning", ""),
\n "sentiment": row.get("sentiment", "\u4e2d\u6027"), # \u8912\u4e49\/\u4e2d\u6027\/\u8d2c\u4e49
\n "sentiment_score": float(row.get("sentiment_score", 0.5)), # 0-1
\n "gender_tendency": row.get("gender_tendency", "\u4e2d\u6027"), # \u7537\/\u5973\/\u4e2d\u6027
\n "cultural_level": int(row.get("cultural_level", 1)), # 1\u666e\u901a 2\u6709\u51fa\u5904 3\u7ecf\u5178
\n "tags": eval(row.get("tags", "[]")) if isinstance(row.get("tags"), str) else [],
\n }
\n return {
\n "char": char,
\n "meaning": "",
\n "sentiment": "\u672a\u77e5",
\n "sentiment_score": 0.3,
\n "gender_tendency": "\u4e2d\u6027",
\n "cultural_level": 0,
\n "tags": [],
\n }<\/p>\n def score_semantic(self, name: str, gender: str = "\u901a\u7528") -> Dict:
\n """\u8ba1\u7b97\u5b57\u4e49\u7efc\u5408\u8bc4\u5206"""
\n char_semantic = [self.get_char_semantic(c) for c in name]<\/p>\n # 1. \u5bd3\u610f\u8912\u8d2c\u8bc4\u5206
\n sentiment_score = self._score_sentiment(char_semantic)<\/p>\n # 2. \u6587\u5316\u5185\u6db5\u8bc4\u5206
\n cultural_score = self._score_cultural(name, char_semantic)<\/p>\n # 3. \u6027\u522b\u9002\u914d\u8bc4\u5206
\n gender_score = self._score_gender_fit(char_semantic, gender)<\/p>\n # 4. \u65f6\u4ee3\u611f\u8bc4\u5206
\n era_score = self._score_era_appropriateness(name, char_semantic)<\/p>\n # \u5b57\u4e49\u7efc\u5408\u8bc4\u5206
\n total = (sentiment_score * 0.35 + cultural_score * 0.30 +
\n gender_score * 0.20 + era_score * 0.15)<\/p>\n return {
\n "total_score": round(total, 1),
\n "sentiment_score": sentiment_score,
\n "cultural_score": cultural_score,
\n "gender_score": gender_score,
\n "era_score": era_score,
\n "char_semantic": char_semantic,
\n "details": {
\n "overall_sentiment": self._overall_sentiment(char_semantic),
\n "cultural_sources": self._find_cultural_sources(name),
\n "gender_match": self._gender_match_level(char_semantic, gender),
\n }
\n }<\/p>\n def _score_sentiment(self, char_semantic: List[Dict]) -> float:
\n """\u5bd3\u610f\u8912\u8d2c\u8bc4\u5206：\u6240\u6709\u5b57\u90fd\u5e94\u4e3a\u8912\u4e49\u6216\u4e2d\u6027，\u4e0d\u80fd\u6709\u8d2c\u4e49"""
\n scores = [c["sentiment_score"] for c in char_semantic]<\/p>\n if not scores:
\n return 50.0<\/p>\n # \u57fa\u7840\u5206：\u5e73\u5747\u60c5\u611f\u5206
\n avg_score = sum(scores) \/ len(scores)
\n base = 50 + avg_score * 50<\/p>\n # \u60e9\u7f5a：\u6709\u8d2c\u4e49\u5b57
\n for c in char_semantic:
\n if c["sentiment"] == "\u8d2c\u4e49":
\n base -= 40
\n elif c["sentiment"] == "\u672a\u77e5":
\n base -= 10<\/p>\n # \u5956\u52b1：\u6240\u6709\u5b57\u90fd\u662f\u8912\u4e49
\n if all(c["sentiment"] == "\u8912\u4e49" for c in char_semantic):
\n base += 10<\/p>\n return round(min(100, max(0, base)), 1)<\/p>\n def _score_cultural(self, name: str, char_semantic: List[Dict]) -> float:
\n """\u6587\u5316\u5185\u6db5\u8bc4\u5206：\u662f\u5426\u6709\u8bd7\u8bcd\u5178\u6545\u3001\u6210\u8bed\u51fa\u5904"""
\n score = 60.0<\/p>\n # \u5355\u5b57\u6587\u5316\u7b49\u7ea7
\n avg_cultural = sum(c["cultural_level"] for c in char_semantic) \/ len(char_semantic)
\n score += avg_cultural * 10<\/p>\n # \u540d\u5b57\u6574\u4f53\u662f\u5426\u6709\u6210\u8bed\u51fa\u5904
\n idiom_source = self._find_idiom_source(name)
\n if idiom_source:
\n score += 20<\/p>\n # \u540d\u5b57\u6574\u4f53\u662f\u5426\u6709\u8bd7\u8bcd\u51fa\u5904
\n poem_source = self._find_poem_source(name)
\n if poem_source:
\n score += 15<\/p>\n # \u540d\u5b57\u662f\u5426\u6709\u7ecf\u5178\u7ec4\u5408（\u5982"\u535a\u6587"\u6765\u81ea"\u535a\u5b66\u4e8e\u6587"）
\n classic_combo = self._find_classic_combination(name)
\n if classic_combo:
\n score += 10<\/p>\n return round(min(100, max(0, score)), 1)<\/p>\n def _score_gender_fit(self, char_semantic: List[Dict], gender: str) -> float:
\n """\u6027\u522b\u9002\u914d\u8bc4\u5206：\u540d\u5b57\u6c14\u8d28\u4e0e\u6027\u522b\u662f\u5426\u5339\u914d"""
\n if gender == "\u901a\u7528":
\n return 80.0 # \u4e0d\u6307\u5b9a\u6027\u522b\u65f6\u7ed9\u4e2d\u7b49\u504f\u4e0a\u5206<\/p>\n score = 70.0
\n target = "\u7537" if gender == "\u7537" else "\u5973"<\/p>\n for c in char_semantic:
\n tendency = c["gender_tendency"]
\n if tendency == target:
\n score += 10
\n elif tendency == "\u4e2d\u6027":
\n score += 5
\n elif tendency != "\u4e2d\u6027" and tendency != target:
\n score -= 15<\/p>\n # \u5e73\u5747\u5316
\n score = score \/ len(char_semantic) * len(char_semantic) \/ len(char_semantic)<\/p>\n return round(min(100, max(0, score)), 1)<\/p>\n def _score_era_appropriateness(self, name: str, char_semantic: List[Dict]) -> float:
\n """\u65f6\u4ee3\u611f\u8bc4\u5206：\u662f\u5426\u7b26\u5408\u5f53\u4ee3\u5ba1\u7f8e，\u907f\u514d\u8fc7\u65f6\u611f"""
\n score = 75.0<\/p>\n # \u68c0\u6d4b\u8fc7\u65f6\u7528\u5b57（\u5982\u5efa\u56fd\u3001\u63f4\u671d\u3001\u6587\u9769\u7b49\u65f6\u4ee3\u7279\u5f81\u660e\u663e\u7684\u5b57）
\n outdated_chars = ["\u56fd", "\u519b", "\u5175", "\u6218", "\u7ea2", "\u536b", "\u4e1c", "\u5f6a", "\u8d85", "\u6ce2"]
\n outdated_count = sum(1 for c in char_semantic if c["char"] in outdated_chars)
\n score -= outdated_count * 15<\/p>\n # \u68c0\u6d4b\u8fc7\u4e8e\u6d41\u884c\u7684\u5b57（\u5bb9\u6613\u91cd\u540d，\u5982\u6893\u3001\u6db5\u3001\u8f69\u3001\u5b87\u7b49）
\n trendy_chars = ["\u6893", "\u6db5", "\u8f69", "\u5b87", "\u8fb0", "\u777f", "\u6d69", "\u6b23", "\u6021", "\u598d"]
\n trendy_count = sum(1 for c in char_semantic if c["char"] in trendy_chars)
\n if trendy_count >= 2:
\n score -= 10 # \u4e24\u4e2a\u4ee5\u4e0a\u6d41\u884c\u5b57，\u5bb9\u6613\u649e\u540d<\/p>\n # \u68c0\u6d4b\u6709\u73b0\u4ee3\u611f\u7684\u5b57（\u65b0\u9896\u4f46\u4e0d\u751f\u50fb）
\n modern_chars = ["\u77e5", "\u884c", "\u8a00", "\u601d", "\u9f50", "\u4fee", "\u8fdc", "\u7136", "\u4e5f", "\u516e"]
\n modern_count = sum(1 for c in char_semantic if c["char"] in modern_chars)
\n score += modern_count * 5<\/p>\n return round(min(100, max(0, score)), 1)<\/p>\n def _find_idiom_source(self, name: str) -> Optional[str]:
\n """\u67e5\u627e\u540d\u5b57\u7684\u6210\u8bed\u51fa\u5904"""
\n # \u7b80\u5316\u7248：\u5b9e\u9645\u5e94\u7528\u4e2d\u5e94\u4f7f\u7528\u5b8c\u6574\u6210\u8bed\u5e93\u8fdb\u884c\u6a21\u7cca\u5339\u914d
\n for idiom, meaning in self.idiom_db.items():
\n # \u68c0\u67e5\u540d\u5b57\u662f\u5426\u662f\u6210\u8bed\u7684\u8fde\u7eed\u5b50\u4e32\u6216\u7ec4\u5408
\n if name in idiom or all(c in idiom for c in name):
\n return f"{idiom}：{meaning}"
\n return None<\/p>\n def _find_poem_source(self, name: str) -> Optional[str]:
\n """\u67e5\u627e\u540d\u5b57\u7684\u8bd7\u8bcd\u51fa\u5904"""
\n for poem, source in self.poem_db.items():
\n if name in poem:
\n return f"\u51fa\u81ea{source}：{poem}"
\n return None<\/p>\n def _find_classic_combination(self, name: str) -> Optional[str]:
\n """\u67e5\u627e\u7ecf\u5178\u540d\u5b57\u7ec4\u5408"""
\n classic_combos = {
\n "\u535a\u6587": "\u51fa\u81ea\u300a\u8bba\u8bed\u300b'\u535a\u5b66\u4e8e\u6587，\u7ea6\u4e4b\u4ee5\u793c'",
\n "\u601d\u9f50": "\u51fa\u81ea\u300a\u8bba\u8bed\u300b'\u89c1\u8d24\u601d\u9f50\u7109'",
\n "\u81f4\u8fdc": "\u51fa\u81ea\u8bf8\u845b\u4eae\u300a\u8beb\u5b50\u4e66\u300b'\u975e\u6de1\u6cca\u65e0\u4ee5\u660e\u5fd7，\u975e\u5b81\u9759\u65e0\u4ee5\u81f4\u8fdc'",
\n "\u4fee\u8fdc": "\u51fa\u81ea\u5c48\u539f\u300a\u79bb\u9a9a\u300b'\u8def\u6f2b\u6f2b\u5176\u4fee\u8fdc\u516e，\u543e\u5c06\u4e0a\u4e0b\u800c\u6c42\u7d22'",
\n }
\n return classic_combos.get(name)<\/p>\n def _overall_sentiment(self, char_semantic: List[Dict]) -> str:
\n """\u5224\u65ad\u540d\u5b57\u6574\u4f53\u60c5\u611f\u503e\u5411"""
\n avg = sum(c["sentiment_score"] for c in char_semantic) \/ len(char_semantic)
\n if avg >= 0.8: return "\u975e\u5e38\u79ef\u6781"
\n elif avg >= 0.6: return "\u79ef\u6781"
\n elif avg >= 0.4: return "\u4e2d\u6027"
\n elif avg >= 0.2: return "\u504f\u6d88\u6781"
\n else: return "\u6d88\u6781"<\/p>\n def _gender_match_level(self, char_semantic: List[Dict], gender: str) -> str:
\n """\u5224\u65ad\u6027\u522b\u5339\u914d\u7a0b\u5ea6"""
\n if gender == "\u901a\u7528":
\n return "\u672a\u6307\u5b9a"
\n target = "\u7537" if gender == "\u7537" else "\u5973"
\n match_count = sum(1 for c in char_semantic if c["gender_tendency"] == target)
\n ratio = match_count \/ len(char_semantic)
\n if ratio >= 0.8: return "\u9ad8\u5ea6\u5339\u914d"
\n elif ratio >= 0.5: return "\u57fa\u672c\u5339\u914d"
\n elif ratio >= 0.3: return "\u90e8\u5206\u5339\u914d"
\n else: return "\u4e0d\u5339\u914d"<\/p>\n def _load_idiom_db(self, path: str) -> Dict:
\n """\u52a0\u8f7d\u6210\u8bed\u5e93"""
\n df = pd.read_csv(path)
\n return dict(zip(df["idiom"], df["meaning"]))<\/p>\n def _load_poem_db(self, path: str) -> Dict:
\n """\u52a0\u8f7d\u8bd7\u8bcd\u5e93"""
\n df = pd.read_csv(path)
\n return dict(zip(df["verse"], df["source"]))<\/p>\n \u8bfb\u8005\u53ef\u524d\u5f80\u5728\u7ebf\u8d77\u540d\u5de5\u5177\u67e5\u770b\u5b8c\u6574\u7684\u5b57\u4e49\u8bc4\u5206\u529f\u80fd，\u5de5\u5177\u652f\u6301\u8f93\u5165\u540d\u5b57\u540e\u67e5\u770b\u6bcf\u4e2a\u5b57\u7684\u91ca\u4e49\u3001\u8912\u8d2c\u503e\u5411\u3001\u6027\u522b\u9002\u914d\u5ea6\u548c\u6587\u5316\u51fa\u5904，\u5e2e\u52a9\u5bb6\u957f\u5168\u9762\u4e86\u89e3\u540d\u5b57\u7684\u5bd3\u610f\u5185\u6db5\u3002<\/p>\n \u516d\u3001\u7efc\u5408\u8bc4\u5206\u4e0e\u6743\u91cd\u4f18\u5316<\/h3>\n6.1 \u52a0\u6743\u7efc\u5408\u8bc4\u5206\u7b97\u6cd5<\/h4>\n\u5c06\u97f3\u97f5\u3001\u5b57\u5f62\u3001\u5b57\u4e49\u4e09\u4e2a\u7ef4\u5ea6\u7684\u8bc4\u5206\u52a0\u6743\u6c42\u548c，\u5f97\u5230\u6700\u7ec8\u7efc\u5408\u8bc4\u5206：<\/p>\n # algorithms\/name_scorer.py
\nfrom typing import Dict, Optional
\nfrom .phonetic_scorer import PhoneticScorer
\nfrom .graphic_scorer import GraphicScorer
\nfrom .semantic_scorer import SemanticScorer<\/p>\n class NameScorer:
\n """\u540d\u5b57\u7efc\u5408\u8bc4\u5206\u5668"""<\/p>\n # \u9ed8\u8ba4\u6743\u91cd（\u97f335% + \u5f6230% + \u4e4935%）
\n DEFAULT_WEIGHTS = {
\n "phonetic": 0.35,
\n "graphic": 0.30,
\n "semantic": 0.35,
\n }<\/p>\n def __init__(self, char_db_path: str, weights: Dict = None,
\n idiom_db_path: str = None, poem_db_path: str = None):
\n self.phonetic_scorer = PhoneticScorer(char_db_path)
\n self.graphic_scorer = GraphicScorer(char_db_path)
\n self.semantic_scorer = SemanticScorer(char_db_path, idiom_db_path, poem_db_path)
\n self.weights = weights or self.DEFAULT_WEIGHTS.copy()<\/p>\n def score(self, name: str, surname: str = "", gender: str = "\u901a\u7528") -> Dict:
\n """
\n \u8ba1\u7b97\u540d\u5b57\u7efc\u5408\u8bc4\u5206
\n name: \u540d\u5b57（\u4e0d\u542b\u59d3\u6c0f）
\n surname: \u59d3\u6c0f（\u7528\u4e8e\u97f3\u97f5\u5206\u6790\u65f6\u8003\u8651\u5168\u540d）
\n gender: \u6027\u522b（\u7537\/\u5973\/\u901a\u7528）
\n """
\n full_name = surname + name<\/p>\n # 1. \u97f3\u97f5\u8bc4\u5206（\u4f7f\u7528\u5168\u540d，\u56e0\u4e3a\u59d3\u6c0f\u4e5f\u5f71\u54cd\u8bfb\u97f3）
\n phonetic_result = self.phonetic_scorer.score_phonetic(full_name)<\/p>\n # 2. \u5b57\u5f62\u8bc4\u5206（\u4f7f\u7528\u5168\u540d，\u56e0\u4e3a\u59d3\u6c0f\u4e5f\u5f71\u54cd\u89c6\u89c9\u5e73\u8861）
\n graphic_result = self.graphic_scorer.score_graphic(full_name)<\/p>\n # 3. \u5b57\u4e49\u8bc4\u5206（\u53ea\u770b\u540d\u5b57\u90e8\u5206，\u59d3\u6c0f\u901a\u5e38\u4e0d\u53c2\u4e0e\u5bd3\u610f）
\n semantic_result = self.semantic_scorer.score_semantic(name, gender)<\/p>\n # 4. \u52a0\u6743\u7efc\u5408\u8bc4\u5206
\n total = (
\n phonetic_result["total_score"] * self.weights["phonetic"] +
\n graphic_result["total_score"] * self.weights["graphic"] +
\n semantic_result["total_score"] * self.weights["semantic"]
\n )<\/p>\n # 5. \u7b49\u7ea7\u8bc4\u5b9a
\n level = self._get_level(total)<\/p>\n # 6. \u751f\u6210\u4f18\u5316\u5efa\u8bae
\n suggestions = self._generate_suggestions(
\n phonetic_result, graphic_result, semantic_result
\n )<\/p>\n return {
\n "name": full_name,
\n "surname": surname,
\n "given_name": name,
\n "gender": gender,
\n "total_score": round(total, 1),
\n "level": level,
\n "phonetic": phonetic_result,
\n "graphic": graphic_result,
\n "semantic": semantic_result,
\n "weights": self.weights,
\n "suggestions": suggestions,
\n "radar_data": {
\n "\u97f3\u97f5": phonetic_result["total_score"],
\n "\u5b57\u5f62": graphic_result["total_score"],
\n "\u5b57\u4e49": semantic_result["total_score"],
\n },
\n }<\/p>\n def _get_level(self, score: float) -> str:
\n """\u6839\u636e\u8bc4\u5206\u83b7\u53d6\u7b49\u7ea7"""
\n if score >= 90: return "\u4f18\u79c0"
\n elif score >= 80: return "\u826f\u597d"
\n elif score >= 70: return "\u4e2d\u7b49"
\n elif score >= 60: return "\u53ca\u683c"
\n else: return "\u8f83\u5dee"<\/p>\n def _generate_suggestions(self, phonetic: Dict, graphic: Dict,
\n semantic: Dict) -> list:
\n """\u6839\u636e\u5404\u7ef4\u5ea6\u8bc4\u5206\u751f\u6210\u4f18\u5316\u5efa\u8bae"""
\n suggestions = []<\/p>\n # \u97f3\u97f5\u5efa\u8bae
\n if phonetic["total_score"] < 70:
\n if phonetic["homophone_penalty"] > 0:
\n suggestions.append("\u5b58\u5728\u4e0d\u826f\u8c10\u97f3，\u5efa\u8bae\u66f4\u6362\u8bfb\u97f3\u76f8\u8fd1\u4f46\u65e0\u6b67\u4e49\u7684\u5b57")
\n if phonetic["tone_score"] < 60:
\n suggestions.append("\u58f0\u8c03\u642d\u914d\u5355\u8c03，\u5efa\u8bae\u9009\u62e9\u5e73\u4ec4\u4ea4\u66ff\u7684\u5b57")
\n if phonetic["final_score"] < 60:
\n suggestions.append("\u97f5\u6bcd\u91cd\u590d\u6216\u62d7\u53e3，\u5efa\u8bae\u9009\u62e9\u97f5\u6bcd\u4e0d\u540c\u7684\u5b57")<\/p>\n # \u5b57\u5f62\u5efa\u8bae
\n if graphic["total_score"] < 70:
\n if graphic["stroke_score"] < 60:
\n suggestions.append("\u7b14\u753b\u4e0d\u5747\u8861\u6216\u8fc7\u4e8e\u7e41\u7410，\u5efa\u8bae\u9009\u62e9\u7b14\u753b\u9002\u4e2d\u7684\u5b57")
\n if graphic["rarity_score"] < 60:
\n suggestions.append("\u5305\u542b\u751f\u50fb\u5b57，\u5efa\u8bae\u66f4\u6362\u4e3a\u5e38\u7528\u5b57\u4ee5\u63d0\u9ad8\u8fa8\u8bc6\u5ea6")
\n if graphic["structure_score"] < 60:
\n suggestions.append("\u5b57\u5f62\u7ed3\u6784\u5355\u4e00，\u5efa\u8bae\u9009\u62e9\u4e0d\u540c\u7ed3\u6784\u7684\u5b57\u642d\u914d")<\/p>\n # \u5b57\u4e49\u5efa\u8bae
\n if semantic["total_score"] < 70:
\n if semantic["sentiment_score"] < 60:
\n suggestions.append("\u5b57\u4e49\u4e0d\u591f\u79ef\u6781，\u5efa\u8bae\u9009\u62e9\u5bd3\u610f\u66f4\u6b63\u9762\u7684\u5b57")
\n if semantic["cultural_score"] < 60:
\n suggestions.append("\u6587\u5316\u5185\u6db5\u4e0d\u8db3，\u53ef\u8003\u8651\u9009\u62e9\u6709\u8bd7\u8bcd\u5178\u6545\u7684\u5b57")
\n if semantic["gender_score"] < 60:
\n suggestions.append("\u6027\u522b\u9002\u914d\u5ea6\u4e0d\u9ad8，\u5efa\u8bae\u9009\u62e9\u66f4\u7b26\u5408\u6027\u522b\u6c14\u8d28\u7684\u5b57")<\/p>\n if not suggestions:
\n suggestions.append("\u5404\u7ef4\u5ea6\u8868\u73b0\u5747\u8861，\u662f\u4e00\u4e2a\u4e0d\u9519\u7684\u540d\u5b57")<\/p>\n return suggestions<\/p>\n 6.2 \u6743\u91cd\u4f18\u5316\u6548\u679c\u9a8c\u8bc1<\/h4>\n\u6211\u4eec\u91c7\u96c6\u4e86 5000 \u6761\u7528\u6237\u5bf9\u540d\u5b57\u7684\u4e3b\u89c2\u8bc4\u5206\u6570\u636e，\u7528\u4e8e\u9a8c\u8bc1\u6743\u91cd\u4f18\u5316\u7684\u6548\u679c：<\/p>\n \u8868\u683c<\/p>\n \n\u6307\u6807\u4f18\u5316\u524d（\u4e13\u5bb6\u6743\u91cd）\u4f18\u5316\u540e（\u6570\u636e\u9a71\u52a8\u6743\u91cd）\u63d0\u5347\u5e45\u5ea6<\/tr>\n \n\n| \u4e0e\u7528\u6237\u6ee1\u610f\u5ea6\u7684\u76f8\u5173\u7cfb\u6570<\/td>\n | 0.62<\/td>\n | 0.78<\/td>\n | +25.8%<\/td>\n<\/tr>\n | \n| \u6d4b\u8bd5\u96c6 MSE<\/td>\n | 85.32<\/td>\n | 52.18<\/td>\n | -38.8%<\/td>\n<\/tr>\n | \n| \u6d4b\u8bd5\u96c6 R\u00b2<\/td>\n | 0.45<\/td>\n | 0.68<\/td>\n | +51.1%<\/td>\n<\/tr>\n | \n| Top10 \u9ad8\u5206\u540d\u5b57\u7528\u6237\u91c7\u7eb3\u7387<\/td>\n | 32%<\/td>\n | 47%<\/td>\n | +46.9%<\/td>\n<\/tr>\n | \n| \u4f4e\u5206\u540d\u5b57\u7528\u6237\u6295\u8bc9\u7387<\/td>\n | 18%<\/td>\n | 9%<\/td>\n | -50.0%<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n \u4f18\u5316\u540e\u7684\u6743\u91cd\u5206\u914d\u53d8\u5316：<\/p>\n \u8868\u683c<\/p>\n \n\u7ef4\u5ea6\u5b50\u6307\u6807\u4f18\u5316\u524d\u6743\u91cd\u4f18\u5316\u540e\u6743\u91cd\u53d8\u5316<\/tr>\n \n\n| \u97f3\u97f5<\/td>\n | \u58f0\u8c03\u642d\u914d<\/td>\n | 12%<\/td>\n | 15%<\/td>\n | +3%<\/td>\n<\/tr>\n | \n| <\/td>\n | \u97f5\u6bcd\u548c\u8c10<\/td>\n | 10%<\/td>\n | 8%<\/td>\n | -2%<\/td>\n<\/tr>\n | \n| <\/td>\n | \u58f0\u6bcd\u642d\u914d<\/td>\n | 5%<\/td>\n | 4%<\/td>\n | -1%<\/td>\n<\/tr>\n | \n| <\/td>\n | \u8c10\u97f3\u6b67\u4e49<\/td>\n | 8%<\/td>\n | 13%<\/td>\n | +5%<\/td>\n<\/tr>\n | \n| \u5b57\u5f62<\/td>\n | \u7b14\u753b\u5747\u8861<\/td>\n | 10%<\/td>\n | 8%<\/td>\n | -2%<\/td>\n<\/tr>\n | \n| <\/td>\n | \u7ed3\u6784\u642d\u914d<\/td>\n | 8%<\/td>\n | 6%<\/td>\n | -2%<\/td>\n<\/tr>\n | \n| <\/td>\n | \u751f\u50fb\u7a0b\u5ea6<\/td>\n | 7%<\/td>\n | 11%<\/td>\n | +4%<\/td>\n<\/tr>\n | \n| <\/td>\n | \u8fa8\u8bc6\u5ea6<\/td>\n | 5%<\/td>\n | 5%<\/td>\n | 0%<\/td>\n<\/tr>\n | \n| \u5b57\u4e49<\/td>\n | \u5bd3\u610f\u8912\u8d2c<\/td>\n | 12%<\/td>\n | 10%<\/td>\n | -2%<\/td>\n<\/tr>\n | \n| <\/td>\n | \u6587\u5316\u5185\u6db5<\/td>\n | 10%<\/td>\n | 7%<\/td>\n | -3%<\/td>\n<\/tr>\n | \n| <\/td>\n | \u6027\u522b\u9002\u914d<\/td>\n | 7%<\/td>\n | 8%<\/td>\n | +1%<\/td>\n<\/tr>\n | \n| <\/td>\n | \u65f6\u4ee3\u611f<\/td>\n | 6%<\/td>\n | 5%<\/td>\n | -1%<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n \u5173\u952e\u53d1\u73b0：<\/p>\n \n- \u8c10\u97f3\u6b67\u4e49\u7684\u6743\u91cd\u4ece 8% \u63d0\u5347\u5230 13%，\u8bf4\u660e\u7528\u6237\u5bf9\u4e0d\u826f\u8c10\u97f3\u975e\u5e38\u654f\u611f<\/li>\n
- \u58f0\u8c03\u642d\u914d\u7684\u6743\u91cd\u4ece 12% \u63d0\u5347\u5230 15%，\u8bf4\u660e\u8bfb\u97f3\u662f\u5426\u987a\u53e3\u662f\u7528\u6237\u6700\u770b\u91cd\u7684\u56e0\u7d20<\/li>\n
- \u751f\u50fb\u7a0b\u5ea6\u7684\u6743\u91cd\u4ece 7% \u63d0\u5347\u5230 11%，\u8bf4\u660e\u7528\u6237\u4e0d\u5e0c\u671b\u540d\u5b57\u4e2d\u6709\u96be\u8ba4\u7684\u5b57<\/li>\n
- \u6587\u5316\u5185\u6db5\u7684\u6743\u91cd\u4ece 10% \u964d\u5230 7%，\u8bf4\u660e\u867d\u7136\u6709\u6587\u5316\u51fa\u5904\u662f\u52a0\u5206\u9879，\u4f46\u7528\u6237\u5e76\u4e0d\u50cf\u4e13\u5bb6\u8ba4\u4e3a\u7684\u90a3\u6837\u770b\u91cd<\/li>\n<\/ul>\n
\u4e0a\u8ff0\u7efc\u5408\u8bc4\u5206\u7b97\u6cd5\u548c\u6743\u91cd\u4f18\u5316\u6548\u679c\u53ef\u5728\u5728\u7ebf\u8d77\u540d\u5de5\u5177\u4e2d\u4f53\u9a8c，\u5de5\u5177\u63d0\u4f9b\u4e86\u8be6\u7ec6\u7684\u8bc4\u5206\u62a5\u544a\u3001\u96f7\u8fbe\u56fe\u548c\u4f18\u5316\u5efa\u8bae，\u5e2e\u52a9\u5bb6\u957f\u5168\u9762\u8bc4\u4f30\u540d\u5b57\u8d28\u91cf\u3002<\/p>\n 6.3 \u8bc4\u5206\u7ed3\u679c\u5bf9\u6bd4\u5b9e\u9a8c<\/h4>\n\u6211\u4eec\u9009\u53d6\u4e86 100 \u4e2a\u540d\u5b57，\u5206\u522b\u7528\u4f20\u7edf\u4e94\u683c\u8bc4\u5206\u6cd5\u548c\u6211\u4eec\u7684\u97f3\u5f62\u4e49\u7efc\u5408\u8bc4\u5206\u6cd5\u8fdb\u884c\u8bc4\u4f30，\u5e76\u4e0e\u7528\u6237\u4e3b\u89c2\u6ee1\u610f\u5ea6\u8fdb\u884c\u5bf9\u6bd4：<\/p>\n \u8868\u683c<\/p>\n \n\u8bc4\u4f30\u65b9\u6cd5\u4e0e\u7528\u6237\u6ee1\u610f\u5ea6\u76f8\u5173\u7cfb\u6570\u9ad8\u5206\u540d\u5b57\u91c7\u7eb3\u7387\u4f4e\u5206\u540d\u5b57\u8bef\u5224\u7387<\/tr>\n \n\n| \u4f20\u7edf\u4e94\u683c\u8bc4\u5206<\/td>\n | 0.38<\/td>\n | 25%<\/td>\n | 32%<\/td>\n<\/tr>\n | \n| \u516b\u5b57\u4e94\u884c\u8bc4\u5206<\/td>\n | 0.41<\/td>\n | 28%<\/td>\n | 28%<\/td>\n<\/tr>\n | \n| \u97f3\u5f62\u4e49\u7efc\u5408\u8bc4\u5206（\u4f18\u5316\u524d）<\/td>\n | 0.62<\/td>\n | 32%<\/td>\n | 15%<\/td>\n<\/tr>\n | \n| \u97f3\u5f62\u4e49\u7efc\u5408\u8bc4\u5206（\u4f18\u5316\u540e）<\/td>\n | 0.78<\/td>\n | 47%<\/td>\n | 8%<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n \u5b9e\u9a8c\u7ed3\u679c\u8868\u660e，\u97f3\u5f62\u4e49\u7efc\u5408\u8bc4\u5206\u6cd5\u663e\u8457\u4f18\u4e8e\u4f20\u7edf\u7684\u5355\u4e00\u7ef4\u5ea6\u8bc4\u5206\u65b9\u6cd5，\u800c\u57fa\u4e8e\u7528\u6237\u53cd\u9988\u7684\u6743\u91cd\u4f18\u5316\u8fdb\u4e00\u6b65\u63d0\u5347\u4e86\u8bc4\u5206\u7684\u51c6\u786e\u6027\u548c\u5b9e\u7528\u6027\u3002<\/p>\n \u4e03\u3001\u8e29\u8fc7\u7684\u5751\u4e0e\u6ce8\u610f\u4e8b\u9879<\/h3>\n\u5728\u5b9e\u73b0\u8fd9\u5957\u97f3\u5f62\u4e49\u7efc\u5408\u8bc4\u5206\u7b97\u6cd5\u7684\u8fc7\u7a0b\u4e2d，\u9047\u5230\u4e86\u4e0d\u5c11\u5b9e\u9645\u95ee\u9898，\u4ee5\u4e0b\u662f\u6700\u6709\u4ef7\u503c\u7684 5 \u6761\u7ecf\u9a8c：<\/p>\n 1. \u591a\u97f3\u5b57\u5904\u7406\u662f\u97f3\u97f5\u8bc4\u5206\u6700\u5927\u7684\u96be\u70b9，\u4e0a\u4e0b\u6587\u5224\u65ad\u51c6\u786e\u7387\u6709\u9650<\/p>\n \u6700\u521d\u6211\u4eec\u76f4\u63a5\u7528 pypinyin \u5e93\u83b7\u53d6\u62fc\u97f3，\u4f46\u591a\u97f3\u5b57\u7684\u5904\u7406\u51c6\u786e\u7387\u53ea\u6709\u7ea6 70%\u3002\u4f8b\u5982 \u201c\u884c\u201d \u5b57，\u5728 \u201c\u77e5\u884c\u201d \u4e2d\u8bfb x\u00edng，\u5728 \u201c\u9053\u884c\u201d \u4e2d\u8bfb h\u00e9ng；\u201c\u91cd\u201d \u5b57，\u5728 \u201c\u91cd\u8fdc\u201d \u4e2d\u8bfb zh\u00f2ng，\u5728 \u201c\u91cd\u590d\u201d \u4e2d\u8bfb ch\u00f3ng\u3002pypinyin \u7684\u9ed8\u8ba4\u8bfb\u97f3\u7ecf\u5e38\u51fa\u9519，\u5bfc\u81f4\u58f0\u8c03\u642d\u914d\u548c\u8c10\u97f3\u68c0\u6d4b\u90fd\u4e0d\u51c6\u786e\u3002\u540e\u6765\u6211\u4eec\u5efa\u7acb\u4e86\u8d77\u540d\u573a\u666f\u4e13\u7528\u7684\u591a\u97f3\u5b57\u5e93，\u6536\u5f55\u4e86 500 \u591a\u4e2a\u5e38\u89c1\u591a\u97f3\u5b57\u5728\u4e0d\u540c\u8bcd\u8bed\u7ec4\u5408\u4e2d\u7684\u6b63\u786e\u8bfb\u97f3，\u5e76\u901a\u8fc7\u4e0a\u4e0b\u6587\u5339\u914d\u6765\u5224\u65ad，\u51c6\u786e\u7387\u63d0\u5347\u5230 92%\u3002\u4f46\u4ecd\u6709\u4e00\u4e9b\u7279\u6b8a\u7ec4\u5408\u65e0\u6cd5\u51c6\u786e\u5224\u65ad，\u5efa\u8bae\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\u5bf9\u591a\u97f3\u5b57\u7ed9\u51fa\u591a\u79cd\u8bfb\u97f3\u9009\u9879，\u8ba9\u7528\u6237\u786e\u8ba4\u3002<\/p>\n 2. \u8c10\u97f3\u68c0\u6d4b\u4e0d\u80fd\u53ea\u770b\u5b8c\u5168\u540c\u97f3，\u8fd1\u97f3\u8bcd\u7684\u6740\u4f24\u529b\u66f4\u5927<\/p>\n \u6700\u521d\u6211\u4eec\u7684\u8c10\u97f3\u68c0\u6d4b\u53ea\u5339\u914d\u5b8c\u5168\u76f8\u540c\u7684\u62fc\u97f3，\u7ed3\u679c\u53d1\u73b0\u5f88\u591a\u6709\u95ee\u9898\u7684\u540d\u5b57\u6ca1\u6709\u88ab\u68c0\u6d4b\u51fa\u6765\u3002\u4f8b\u5982 \u201c\u675c\u5b50\u817e\u201d（\u809a\u5b50\u75bc）\u3001\u201c\u8303\u5efa\u201d（\u72af\u8d31）\u3001\u201c\u6731\u9038\u7fa4\u201d（\u732a\u4e00\u7fa4），\u8fd9\u4e9b\u540d\u5b57\u7684\u62fc\u97f3\u4e0e\u4e0d\u826f\u8bcd\u6c47\u5e76\u4e0d\u5b8c\u5168\u76f8\u540c，\u4f46\u8bfb\u97f3\u975e\u5e38\u63a5\u8fd1，\u542c\u8d77\u6765\u5c31\u4f1a\u4ea7\u751f\u6b67\u4e49\u3002\u540e\u6765\u6211\u4eec\u5f15\u5165\u4e86\u62fc\u97f3\u76f8\u4f3c\u5ea6\u7b97\u6cd5，\u5141\u8bb8\u58f0\u6bcd\u76f8\u540c\u3001\u97f5\u6bcd\u76f8\u8fd1\u7684\u60c5\u51b5\u88ab\u68c0\u6d4b\u5230，\u5e76\u5efa\u7acb\u4e86\u5305\u542b 2000+ \u4e0d\u826f\u8bcd\u6c47\u7684\u8c10\u97f3\u8bcd\u5e93，\u68c0\u6d4b\u8986\u76d6\u7387\u4ece 35% \u63d0\u5347\u5230 85%\u3002\u5efa\u8bae\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\u6301\u7eed\u7ef4\u62a4\u548c\u66f4\u65b0\u8c10\u97f3\u8bcd\u5e93，\u56e0\u4e3a\u7f51\u7edc\u7528\u8bed\u548c\u65b0\u7684\u4e0d\u826f\u7ec4\u5408\u5c42\u51fa\u4e0d\u7a77\u3002<\/p>\n 3. \u5b57\u5f62\u7f8e\u89c2\u5ea6\u975e\u5e38\u4e3b\u89c2，\u7b14\u753b\u5747\u8861\u53ea\u662f\u5176\u4e2d\u4e00\u4e2a\u7ef4\u5ea6<\/p>\n \u6700\u521d\u6211\u4eec\u8ba4\u4e3a\u5b57\u5f62\u8bc4\u5206\u4e3b\u8981\u770b\u7b14\u753b\u6570\u662f\u5426\u5747\u8861，\u4f46\u5b9e\u9645\u6d4b\u8bd5\u53d1\u73b0，\u7b14\u753b\u5747\u8861\u7684\u540d\u5b57\u4e0d\u4e00\u5b9a\u770b\u8d77\u6765\u7f8e\u89c2\u3002\u4f8b\u5982 \u201c\u4e00\u4e8c\u4e00\u201d \u7b14\u753b\u5f88\u5747\u8861，\u4f46\u770b\u8d77\u6765\u8fc7\u4e8e\u7b80\u5355；\u201c\u9e92\u9e9f\u201d \u7b14\u753b\u90fd\u5f88\u591a，\u4f46\u89c6\u89c9\u4e0a\u5f88\u534f\u8c03\u3002\u540e\u6765\u6211\u4eec\u5f15\u5165\u4e86\u5b57\u5f62\u7ed3\u6784\u3001\u504f\u65c1\u90e8\u9996\u3001\u89c6\u89c9\u91cd\u5fc3\u7b49\u591a\u4e2a\u7ef4\u5ea6，\u5e76\u901a\u8fc7\u7528\u6237\u5ba1\u7f8e\u6570\u636e\u8bad\u7ec3\u4e86\u5b57\u5f62\u7f8e\u89c2\u5ea6\u6a21\u578b，\u8bc4\u5206\u4e0e\u7528\u6237\u5ba1\u7f8e\u4e00\u81f4\u6027\u4ece 0.45 \u63d0\u5347\u5230 0.71\u3002\u5efa\u8bae\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\u4e0d\u8981\u8fc7\u5ea6\u4f9d\u8d56\u89c4\u5219，\u8981\u7ed3\u5408\u7528\u6237\u5ba1\u7f8e\u6570\u636e\u8fdb\u884c\u6a21\u578b\u8bad\u7ec3\u3002<\/p>\n 4. \u5b57\u4e49\u8912\u8d2c\u4e0d\u80fd\u53ea\u770b\u5355\u5b57，\u540d\u5b57\u7ec4\u5408\u540e\u7684\u6574\u4f53\u5bd3\u610f\u66f4\u91cd\u8981<\/p>\n \u6700\u521d\u6211\u4eec\u7684\u5b57\u4e49\u8bc4\u5206\u53ea\u662f\u7b80\u5355\u5730\u628a\u6bcf\u4e2a\u5b57\u7684\u8912\u8d2c\u5206\u6570\u52a0\u6743\u5e73\u5747，\u4f46\u5b9e\u9645\u53d1\u73b0\u5f88\u591a\u5355\u5b57\u90fd\u662f\u8912\u4e49\u7684\u540d\u5b57，\u7ec4\u5408\u8d77\u6765\u5bd3\u610f\u5e76\u4e0d\u597d\u3002\u4f8b\u5982 \u201c\u51b0\u96ea\u201d \u5355\u770b\u90fd\u662f\u8912\u4e49，\u4f46\u7ec4\u5408\u8d77\u6765\u6709 \u201c\u51b7\u82e5\u51b0\u971c\u201d \u7684\u6697\u793a；\u201c\u5bcc\u8d35\u201d \u5355\u770b\u90fd\u662f\u8912\u4e49，\u4f46\u7ec4\u5408\u8d77\u6765\u663e\u5f97\u8fc7\u4e8e\u76f4\u767d\u4fd7\u6c14\u3002\u540e\u6765\u6211\u4eec\u5f15\u5165\u4e86\u540d\u5b57\u6574\u4f53\u5bd3\u610f\u5206\u6790，\u901a\u8fc7\u6210\u8bed\u5339\u914d\u3001\u8bd7\u8bcd\u51fa\u5904\u3001\u8bed\u4e49\u8fde\u8d2f\u6027\u7b49\u7ef4\u5ea6\u8bc4\u4f30\u540d\u5b57\u7684\u6574\u4f53\u5bd3\u610f，\u8bc4\u5206\u51c6\u786e\u6027\u663e\u8457\u63d0\u5347\u3002\u5efa\u8bae\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\u5efa\u7acb\u540d\u5b57\u7ec4\u5408\u8bed\u4e49\u5206\u6790\u6a21\u578b，\u800c\u4e0d\u662f\u53ea\u770b\u5355\u5b57\u8bc4\u5206\u3002<\/p>\n 5. \u6743\u91cd\u4f18\u5316\u4e0d\u80fd\u53ea\u770b\u6570\u636e，\u4e13\u5bb6\u7ecf\u9a8c\u548c\u4e1a\u52a1\u7ea6\u675f\u540c\u6837\u91cd\u8981<\/p>\n \u6700\u521d\u6211\u4eec\u5b8c\u5168\u57fa\u4e8e\u7528\u6237\u53cd\u9988\u6570\u636e\u4f18\u5316\u6743\u91cd，\u7ed3\u679c\u53d1\u73b0\u4e00\u4e9b\u4e0d\u5408\u7406\u7684\u6743\u91cd\u5206\u914d：\u4f8b\u5982 \u201c\u65f6\u4ee3\u611f\u201d \u7684\u6743\u91cd\u88ab\u964d\u5230\u63a5\u8fd1 0，\u56e0\u4e3a\u7528\u6237\u8bc4\u5206\u65f6\u4e0d\u592a\u8003\u8651\u8fd9\u4e2a\u56e0\u7d20，\u4f46\u4ece\u4ea7\u54c1\u89d2\u5ea6\u770b，\u907f\u514d\u8fc7\u65f6\u540d\u5b57\u662f\u91cd\u8981\u7684\u4ef7\u503c\u4e3b\u5f20；\u201c\u6587\u5316\u5185\u6db5\u201d \u7684\u6743\u91cd\u4e5f\u88ab\u964d\u5f97\u5f88\u4f4e，\u4f46\u8fd9\u662f\u6211\u4eec\u4ea7\u54c1\u5dee\u5f02\u5316\u7684\u6838\u5fc3\u5356\u70b9\u3002\u540e\u6765\u6211\u4eec\u91c7\u7528 \u201c\u6570\u636e\u9a71\u52a8 + \u4e13\u5bb6\u7ea6\u675f\u201d \u7684\u6df7\u5408\u4f18\u5316\u65b9\u6cd5，\u5728\u4f18\u5316\u65f6\u8bbe\u7f6e\u6743\u91cd\u7684\u4e0a\u4e0b\u9650，\u5e76\u4fdd\u7559\u4e1a\u52a1\u6838\u5fc3\u6307\u6807\u7684\u6700\u4f4e\u6743\u91cd，\u6700\u7ec8\u5f97\u5230\u4e86\u65e2\u7b26\u5408\u7528\u6237\u504f\u597d\u53c8\u6ee1\u8db3\u4e1a\u52a1\u76ee\u6807\u7684\u6743\u91cd\u5206\u914d\u3002\u5efa\u8bae\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\u4e0d\u8981\u76f2\u76ee\u8ffd\u6c42\u6570\u636e\u62df\u5408，\u8981\u7ed3\u5408\u4e1a\u52a1\u76ee\u6807\u548c\u4e13\u5bb6\u7ecf\u9a8c\u8bbe\u7f6e\u5408\u7406\u7684\u7ea6\u675f\u3002<\/p>\n \u516b\u3001\u603b\u7ed3<\/h3>\n\u672c\u6587\u5b8c\u6574\u8bb0\u5f55\u4e86\u7528 Python \u5b9e\u73b0\u540d\u5b57\u97f3\u5f62\u4e49\u7efc\u5408\u8bc4\u5206\u7b97\u6cd5\u7684\u5168\u6d41\u7a0b，\u6838\u5fc3\u8981\u70b9\u5982\u4e0b：<\/p>\n - \u4e09\u7ef4\u5ea6\u5341\u4e8c\u6307\u6807\u4f53\u7cfb：\u97f3\u97f5（\u58f0\u8c03\u642d\u914d\u3001\u97f5\u6bcd\u548c\u8c10\u3001\u58f0\u6bcd\u642d\u914d\u3001\u8c10\u97f3\u6b67\u4e49）\u3001\u5b57\u5f62（\u7b14\u753b\u5747\u8861\u3001\u7ed3\u6784\u642d\u914d\u3001\u751f\u50fb\u7a0b\u5ea6\u3001\u8fa8\u8bc6\u5ea6）\u3001\u5b57\u4e49（\u5bd3\u610f\u8912\u8d2c\u3001\u6587\u5316\u5185\u6db5\u3001\u6027\u522b\u9002\u914d\u3001\u65f6\u4ee3\u611f），\u5168\u9762\u8986\u76d6\u540d\u5b57\u8d28\u91cf\u7684\u5404\u4e2a\u65b9\u9762\u3002<\/li>\n
- \u97f3\u97f5\u8bc4\u5206\u6838\u5fc3\u662f\u591a\u97f3\u5b57\u5904\u7406\u548c\u8c10\u97f3\u68c0\u6d4b：\u5efa\u7acb\u8d77\u540d\u573a\u666f\u4e13\u7528\u591a\u97f3\u5b57\u5e93，\u5f15\u5165\u62fc\u97f3\u76f8\u4f3c\u5ea6\u7b97\u6cd5\u548c\u5b8c\u6574\u7684\u4e0d\u826f\u8c10\u97f3\u8bcd\u5e93，\u662f\u97f3\u97f5\u8bc4\u5206\u51c6\u786e\u6027\u7684\u5173\u952e\u3002<\/li>\n
- \u5b57\u5f62\u8bc4\u5206\u9700\u8981\u8d85\u8d8a\u7b80\u5355\u7684\u7b14\u753b\u6570：\u7ed3\u5408\u5b57\u5f62\u7ed3\u6784\u3001\u504f\u65c1\u90e8\u9996\u3001\u89c6\u89c9\u91cd\u5fc3\u7b49\u591a\u7ef4\u5ea6，\u5e76\u901a\u8fc7\u7528\u6237\u5ba1\u7f8e\u6570\u636e\u8bad\u7ec3\u6a21\u578b，\u624d\u80fd\u51c6\u786e\u8bc4\u4f30\u5b57\u5f62\u7f8e\u89c2\u5ea6\u3002<\/li>\n
- \u5b57\u4e49\u8bc4\u5206\u8981\u5173\u6ce8\u6574\u4f53\u5bd3\u610f\u800c\u975e\u5355\u5b57：\u540d\u5b57\u7ec4\u5408\u540e\u7684\u8bed\u4e49\u8fde\u8d2f\u6027\u3001\u6210\u8bed\u51fa\u5904\u3001\u8bd7\u8bcd\u5178\u6545\u6bd4\u5355\u5b57\u8912\u8d2c\u66f4\u80fd\u53cd\u6620\u540d\u5b57\u7684\u5185\u6db5\u3002<\/li>\n
- \u6743\u91cd\u4f18\u5316\u91c7\u7528\u6570\u636e\u9a71\u52a8 + \u4e13\u5bb6\u7ea6\u675f\u7684\u6df7\u5408\u65b9\u6cd5：\u57fa\u4e8e\u7528\u6237\u53cd\u9988\u6570\u636e\u4f18\u5316\u6743\u91cd，\u540c\u65f6\u8bbe\u7f6e\u4e1a\u52a1\u6838\u5fc3\u6307\u6807\u7684\u6700\u4f4e\u6743\u91cd\u7ea6\u675f，\u5f97\u5230\u65e2\u7b26\u5408\u7528\u6237\u504f\u597d\u53c8\u6ee1\u8db3\u4e1a\u52a1\u76ee\u6807\u7684\u6743\u91cd\u5206\u914d\u3002<\/li>\n
- \u7efc\u5408\u8bc4\u5206\u663e\u8457\u4f18\u4e8e\u4f20\u7edf\u5355\u4e00\u7ef4\u5ea6\u8bc4\u5206：\u4e0e\u7528\u6237\u6ee1\u610f\u5ea6\u7684\u76f8\u5173\u7cfb\u6570\u4ece\u4f20\u7edf\u4e94\u683c\u8bc4\u5206\u7684 0.38 \u63d0\u5347\u5230 0.78，\u9ad8\u5206\u540d\u5b57\u7528\u6237\u91c7\u7eb3\u7387\u63d0\u5347 47%，\u4f4e\u5206\u540d\u5b57\u8bef\u5224\u7387\u964d\u5230 8%\u3002<\/li>\n
\u8be5\u7b97\u6cd5\u5df2\u5728 529 \u5b9d\u5b9d\u8d77\u540d\u7f51\u4e0a\u7ebf\u8fd0\u884c\u534a\u5e74，\u7d2f\u8ba1\u4e3a\u8d85\u8fc7 50 \u4e07\u7528\u6237\u63d0\u4f9b\u540d\u5b57\u8bc4\u5206\u670d\u52a1，\u7528\u6237\u6ee1\u610f\u5ea6\u8fbe\u5230 89%\u3002\u540e\u7eed\u8ba1\u5212\u5f15\u5165\u5927\u8bed\u8a00\u6a21\u578b\u8fdb\u884c\u66f4\u6df1\u5c42\u6b21\u7684\u8bed\u4e49\u5206\u6790\u548c\u540d\u5b57\u521b\u610f\u751f\u6210，\u5e76\u6784\u5efa\u57fa\u4e8e\u77e5\u8bc6\u56fe\u8c31\u7684\u540d\u5b57\u6587\u5316\u5185\u6db5\u8bc4\u4f30\u7cfb\u7edf，\u8fdb\u4e00\u6b65\u63d0\u5347\u8bc4\u5206\u7684\u51c6\u786e\u6027\u548c\u5b9e\u7528\u6027\u3002<\/p>\n \u5982\u679c\u672c\u6587\u5bf9\u4f60\u6709\u5e2e\u52a9，\u6b22\u8fce\u70b9\u8d5e\u6536\u85cf，\u6709\u95ee\u9898\u6216\u60f3\u6cd5\u6b22\u8fce\u5728\u8bc4\u8bba\u533a\u4ea4\u6d41\u3002<\/p>\n","protected":false},"excerpt":{"rendered":" \u4e00\u3001\u524d\u8a00
\n\u8d77\u540d\u662f\u4e00\u95e8\u7efc\u5408\u827a\u672f，\u4e00\u4e2a\u597d\u540d\u5b57\u9700\u8981\u540c\u65f6\u6ee1\u8db3\u591a\u4e2a\u7ef4\u5ea6\u7684\u8981\u6c42：\u8bfb\u8d77\u6765\u8981\u6717\u6717\u4e0a\u53e3（\u97f3\u97f5），\u5199\u51fa\u6765\u8981\u7f8e\u89c2\u534f\u8c03（\u5b57\u5f62），\u60f3\u8d77\u6765\u8981\u6709\u7f8e\u597d\u5bd3\u610f（\u5b57\u4e49）\u3002\u7136\u800c，\u5e02\u9762\u4e0a\u5927\u591a\u6570\u8d77\u540d\u5de5\u5177\u5bf9\u540d\u5b57\u7684\u8bc4\u4f30\u90fd\u505c\u7559\u5728\u5355\u4e00\u7ef4\u5ea6 \u2014\u2014 \u8981\u4e48\u53ea\u7b97\u4e94\u683c\u4e09\u624d\u7684\u6570\u7406\u5409\u51f6，\u8981\u4e48\u53ea\u67e5\u751f\u8fb0\u516b\u5b57\u7684\u4e94\u884c\u8865\u7f3a，\u5f88\u5c11\u6709\u5de5\u5177\u80fd\u4ece\u97f3\u3001\u5f62\u3001\u4e49\u4e09\u4e2a\u7ef4<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[81,190,427],"topic":[],"class_list":["post-99080","post","type-post","status-publish","format-standard","hentry","category-server","tag-python","tag-190","tag-427"],"yoast_head":"\n \u7528 Python \u5b9e\u73b0\u540d\u5b57\u97f3\u5f62\u4e49\u7efc\u5408\u8bc4\u5206\u7b97\u6cd5\uff1a\u97f3\u97f5\u3001\u5b57\u5f62\u3001\u5b57\u4e49\u591a\u7ef4\u5ea6\u8bc4\u4f30\u4e0e\u6743\u91cd\u4f18\u5316\u5168\u6d41\u7a0b - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wsisp.com\/helps\/99080.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u7528 Python \u5b9e\u73b0\u540d\u5b57\u97f3\u5f62\u4e49\u7efc\u5408\u8bc4\u5206\u7b97\u6cd5\uff1a\u97f3\u97f5\u3001\u5b57\u5f62\u3001\u5b57\u4e49\u591a\u7ef4\u5ea6\u8bc4\u4f30\u4e0e\u6743\u91cd\u4f18\u5316\u5168\u6d41\u7a0b - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u4e00\u3001\u524d\u8a00 \u8d77\u540d\u662f\u4e00\u95e8\u7efc\u5408\u827a\u672f，\u4e00\u4e2a\u597d\u540d\u5b57\u9700\u8981\u540c\u65f6\u6ee1\u8db3\u591a\u4e2a\u7ef4\u5ea6\u7684\u8981\u6c42：\u8bfb\u8d77\u6765\u8981\u6717\u6717\u4e0a\u53e3（\u97f3\u97f5），\u5199\u51fa\u6765\u8981\u7f8e\u89c2\u534f\u8c03（\u5b57\u5f62），\u60f3\u8d77\u6765\u8981\u6709\u7f8e\u597d\u5bd3\u610f（\u5b57\u4e49）\u3002\u7136\u800c，\u5e02\u9762\u4e0a\u5927\u591a\u6570\u8d77\u540d\u5de5\u5177\u5bf9\u540d\u5b57\u7684\u8bc4\u4f30\u90fd\u505c\u7559\u5728\u5355\u4e00\u7ef4\u5ea6 \u2014\u2014 \u8981\u4e48\u53ea\u7b97\u4e94\u683c\u4e09\u624d\u7684\u6570\u7406\u5409\u51f6，\u8981\u4e48\u53ea\u67e5\u751f\u8fb0\u516b\u5b57\u7684\u4e94\u884c\u8865\u7f3a，\u5f88\u5c11\u6709\u5de5\u5177\u80fd\u4ece\u97f3\u3001\u5f62\u3001\u4e49\u4e09\u4e2a\u7ef4\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/99080.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2026-09-01T14:56:51+00:00\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"19 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/99080.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/99080.html\",\"name\":\"\u7528 Python \u5b9e\u73b0\u540d\u5b57\u97f3\u5f62\u4e49\u7efc\u5408\u8bc4\u5206\u7b97\u6cd5\uff1a\u97f3\u97f5\u3001\u5b57\u5f62\u3001\u5b57\u4e49\u591a\u7ef4\u5ea6\u8bc4\u4f30\u4e0e\u6743\u91cd\u4f18\u5316\u5168\u6d41\u7a0b - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2026-09-01T14:56:51+00:00\",\"dateModified\":\"2026-09-01T14:56:51+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/99080.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/99080.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/99080.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u7528 Python \u5b9e\u73b0\u540d\u5b57\u97f3\u5f62\u4e49\u7efc\u5408\u8bc4\u5206\u7b97\u6cd5\uff1a\u97f3\u97f5\u3001\u5b57\u5f62\u3001\u5b57\u4e49\u591a\u7ef4\u5ea6\u8bc4\u4f30\u4e0e\u6743\u91cd\u4f18\u5316\u5168\u6d41\u7a0b\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u7528 Python \u5b9e\u73b0\u540d\u5b57\u97f3\u5f62\u4e49\u7efc\u5408\u8bc4\u5206\u7b97\u6cd5\uff1a\u97f3\u97f5\u3001\u5b57\u5f62\u3001\u5b57\u4e49\u591a\u7ef4\u5ea6\u8bc4\u4f30\u4e0e\u6743\u91cd\u4f18\u5316\u5168\u6d41\u7a0b - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wsisp.com\/helps\/99080.html","og_locale":"zh_CN","og_type":"article","og_title":"\u7528 Python \u5b9e\u73b0\u540d\u5b57\u97f3\u5f62\u4e49\u7efc\u5408\u8bc4\u5206\u7b97\u6cd5\uff1a\u97f3\u97f5\u3001\u5b57\u5f62\u3001\u5b57\u4e49\u591a\u7ef4\u5ea6\u8bc4\u4f30\u4e0e\u6743\u91cd\u4f18\u5316\u5168\u6d41\u7a0b - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u4e00\u3001\u524d\u8a00 \u8d77\u540d\u662f\u4e00\u95e8\u7efc\u5408\u827a\u672f，\u4e00\u4e2a\u597d\u540d\u5b57\u9700\u8981\u540c\u65f6\u6ee1\u8db3\u591a\u4e2a\u7ef4\u5ea6\u7684\u8981\u6c42：\u8bfb\u8d77\u6765\u8981\u6717\u6717\u4e0a\u53e3（\u97f3\u97f5），\u5199\u51fa\u6765\u8981\u7f8e\u89c2\u534f\u8c03（\u5b57\u5f62），\u60f3\u8d77\u6765\u8981\u6709\u7f8e\u597d\u5bd3\u610f（\u5b57\u4e49）\u3002\u7136\u800c，\u5e02\u9762\u4e0a\u5927\u591a\u6570\u8d77\u540d\u5de5\u5177\u5bf9\u540d\u5b57\u7684\u8bc4\u4f30\u90fd\u505c\u7559\u5728\u5355\u4e00\u7ef4\u5ea6 \u2014\u2014 \u8981\u4e48\u53ea\u7b97\u4e94\u683c\u4e09\u624d\u7684\u6570\u7406\u5409\u51f6，\u8981\u4e48\u53ea\u67e5\u751f\u8fb0\u516b\u5b57\u7684\u4e94\u884c\u8865\u7f3a，\u5f88\u5c11\u6709\u5de5\u5177\u80fd\u4ece\u97f3\u3001\u5f62\u3001\u4e49\u4e09\u4e2a\u7ef4","og_url":"https:\/\/www.wsisp.com\/helps\/99080.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2026-09-01T14:56:51+00:00","author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"19 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/99080.html","url":"https:\/\/www.wsisp.com\/helps\/99080.html","name":"\u7528 Python \u5b9e\u73b0\u540d\u5b57\u97f3\u5f62\u4e49\u7efc\u5408\u8bc4\u5206\u7b97\u6cd5\uff1a\u97f3\u97f5\u3001\u5b57\u5f62\u3001\u5b57\u4e49\u591a\u7ef4\u5ea6\u8bc4\u4f30\u4e0e\u6743\u91cd\u4f18\u5316\u5168\u6d41\u7a0b - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2026-09-01T14:56:51+00:00","dateModified":"2026-09-01T14:56:51+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/99080.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/99080.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/99080.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"\u7528 Python \u5b9e\u73b0\u540d\u5b57\u97f3\u5f62\u4e49\u7efc\u5408\u8bc4\u5206\u7b97\u6cd5\uff1a\u97f3\u97f5\u3001\u5b57\u5f62\u3001\u5b57\u4e49\u591a\u7ef4\u5ea6\u8bc4\u4f30\u4e0e\u6743\u91cd\u4f18\u5316\u5168\u6d41\u7a0b"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/99080","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=99080"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/99080\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=99080"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=99080"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=99080"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=99080"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}} | | | |