強化商品線配對與組合 veto

services/marketplace_product_matcher.py

@@ -448,6 +448,9 @@ def _has_bundle_offer(identity: ProductIdentity) -> bool:
         or "優惠套組" in text
         or "禮盒組" in text
         or "加大組" in text
+        or "加量組" in text
+        or "分享組" in text
+        or "明星組" in text
         or "套組" in text
     )
 
@@ -461,6 +464,17 @@ def _has_multi_component(identity: ProductIdentity) -> bool:
     )
 
 
+def _has_refill_pack(identity: ProductIdentity) -> bool:
+    text = identity.normalized_name
+    return bool(
+        "補充瓶" in text
+        or "補充包" in text
+        or "替換蕊" in text
+        or "替換芯" in text
+        or "refill" in text
+    )
+
+
 def _spec_mention_count(identity: ProductIdentity) -> int:
     return len(re.findall(r"\d+(?:\.\d+)?\s*(?:ml|毫升|l|g|公克|kg)", identity.normalized_name, re.I))
 
@@ -488,6 +502,23 @@ def _chinese_bigram_score(left: ProductIdentity, right: ProductIdentity) -> floa
     return 2 * len(left_signature & right_signature) / (len(left_signature) + len(right_signature))
 
 
+def _has_strong_product_line_signal(
+    left: ProductIdentity,
+    right: ProductIdentity,
+    token_score: float,
+    chinese_name_score: float,
+) -> bool:
+    shared_core = left.core_tokens & right.core_tokens
+    shared_latin_or_model = {
+        token for token in shared_core
+        if re.fullmatch(r"[a-z][a-z0-9-]{3,}", token)
+        or re.fullmatch(r"[a-z]{2,}-?\d+[a-z0-9-]*", token)
+    }
+    if shared_latin_or_model and token_score >= 0.50:
+        return True
+    return token_score >= 0.56 and chinese_name_score >= 0.45
+
+
 def score_marketplace_match(
     momo_name: str,
     competitor_name: str,
@@ -525,6 +556,8 @@ def score_marketplace_match(
         reasons.append("bundle_offer_conflict")
     if _has_multi_component(left) != _has_multi_component(right):
         reasons.append("multi_component_conflict")
+    if _has_refill_pack(left) != _has_refill_pack(right):
+        reasons.append("refill_pack_conflict")
     left_spec_mentions = _spec_mention_count(left)
     right_spec_mentions = _spec_mention_count(right)
     if left_spec_mentions and right_spec_mentions and left_spec_mentions != right_spec_mentions:
@@ -537,6 +570,8 @@ def score_marketplace_match(
         hard_veto = True
     if _has_multi_component(left) != _has_multi_component(right):
         hard_veto = True
+    if _has_refill_pack(left) != _has_refill_pack(right):
+        hard_veto = True
     if left_spec_mentions and right_spec_mentions and left_spec_mentions != right_spec_mentions:
         hard_veto = True
     if chinese_name_score < 0.16 and token_score < 0.72:
@@ -568,6 +603,16 @@ def score_marketplace_match(
 
     if token_score >= 0.72 and spec_score >= 0.82 and not brand_conflict:
         score += 0.08
+    if (
+        brand_score >= 0.95
+        and not hard_veto
+        and price_penalty == 0
+        and type_score >= 0.55
+        and spec_score >= 0.55
+        and _has_strong_product_line_signal(left, right, token_score, chinese_name_score)
+    ):
+        score += 0.07
+        reasons.append("strong_product_line_match")
     if hard_veto:
         score = min(score, 0.32)
     score = max(0.0, min(1.0, score))