wooo/ewoooc
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

優化 PChome 近門檻商品比對回收
All checks were successful
CD Pipeline / deploy (push) Successful in 1m4s
Details

Browse Source
This commit is contained in:
OoO
2026-05-25 15:20:36 +08:00
parent a00f34ce87
commit dab782cc6d
7 changed files with 399 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

61
services/competitor_price_feeder.py
View File

@@ -1371,6 +1371,13 @@ class CompetitorPriceFeeder:
"replace_same_identity_better_score="
f"{existing_score:.3f}->{match_score:.3f}",
)
if existing_score >= match_score:
return (
False,
f"existing_match_conflict;stronger_existing;existing_id={existing_id};"
f"incoming_id={incoming_id};existing_score={existing_score:.3f};"
f"incoming_score={match_score:.3f}",
)
if match_score >= REPLACE_DIFFERENT_PRODUCT_SCORE:
return True, f"replace_high_confidence_score={match_score:.3f}"
return (
@@ -1937,6 +1944,35 @@ class CompetitorPriceFeeder:
attempts_written += 1
continue
attempt_status = _classify_low_score_attempt(score, diagnostics)
if (
attempt_status == "recoverable_low_score"
and _has_variant_selection_gap(momo_name, [(best_product, score, diagnostics)], score)
):
attempt_status = "true_low_confidence"
attempt_terms = search_terms + [term for term in recovery_terms if term not in search_terms]
self._record_match_attempt(
sku,
momo_name,
momo_product_id=momo_product_id,
momo_price=momo_price,
search_terms=attempt_terms,
candidate_count=max(1, recovery_candidate_count),
attempt_status=attempt_status,
best_product=best_product,
best_score=score,
diagnostics=diagnostics,
error_message=(
"missing_known_product_id_fresh_search_low_confidence; "
f"PChome product_id not returned: {competitor_product_id}; "
f"{_format_match_diagnostics(diagnostics)}"
),
source=source,
)
skipped_low += 1
attempts_written += 1
continue
self._record_match_attempt(
sku,
momo_name,
@@ -1991,17 +2027,20 @@ class CompetitorPriceFeeder:
if score < MIN_MATCH_SCORE:
recovery_terms: list[str] = []
recovery_candidate_count = 0
if not getattr(diagnostics, "hard_veto", False):
recovered, recovery_terms, recovery_candidate_count = _recover_low_score_with_fresh_search(
crawler,
momo_name,
momo_price=momo_price,
existing_product_id=competitor_product_id,
)
if recovered:
recovered_product, recovered_score, recovered_diagnostics = recovered
if recovered_score > score:
best_product, score, diagnostics = recovered_product, recovered_score, recovered_diagnostics
recovered, recovery_terms, recovery_candidate_count = _recover_low_score_with_fresh_search(
crawler,
momo_name,
momo_price=momo_price,
existing_product_id=competitor_product_id,
)
if recovered:
recovered_product, recovered_score, recovered_diagnostics = recovered
if (
recovered_score > score
or getattr(diagnostics, "hard_veto", False)
and not getattr(recovered_diagnostics, "hard_veto", False)
):
best_product, score, diagnostics = recovered_product, recovered_score, recovered_diagnostics
if score >= MIN_MATCH_SCORE:
extras = ["refresh_known_identity"]

38
services/marketplace_product_matcher.py
View File

@@ -365,6 +365,9 @@ SEARCH_IDENTITY_ANCHORS = (
"天然植物香氛精油",
"爆水擦澡濕巾",
"嬰兒潤膚乳",
"可撕式水性兒童指甲油",
"aroma lava 解憂放鬆緩緩燈",
"經典款香氛蠟燭暖燈",
"我愛超磁妝定妝噴霧",
"全天候超完美定妝噴霧",
"怪獸級持色唇膏",
@@ -475,6 +478,7 @@ FOCUSED_IDENTITY_REVIEW_ONLY_REASONS = {
"kate_monster_lipstick_catalog",
"opi_gel_polish_series_catalog",
"romand_juicy_lip_tint_2_catalog",
"recipe_box_peelable_child_polish_catalog",
"solone_longlasting_eyeliner",
"shu_auto_hard_formula_refill_catalog",
"summer_eve_full_skin_wash_2pack",
@@ -497,6 +501,8 @@ FOCUSED_IDENTITY_TOTAL_PRICE_REASONS = {
"selection1990_half_dome_wax_lamp_white",
"selection1990_bendable_wax_lamp_white",
"canmake_tear_bag_palette",
"gdesign_aroma_lava_lamp_2",
"hooome_classic_white_wax_lamp_bulbs_giftbox",
}
SEARCH_BROAD_ANCHORS = {
@@ -3512,6 +3518,38 @@ def _has_focused_low_score_exact_identity_line(left: ProductIdentity, right: Pro
and "淚袋眼影盤" in right_text
):
return "canmake_tear_bag_palette"
if (
{"recipe", "box"} <= brand_tokens
and "可撕式水性兒童指甲油" in left_text
and "可撕式水性兒童指甲油" in right_text
):
return "recipe_box_peelable_child_polish_catalog"
if (
"gdesign" in (left.brand_tokens & right.brand_tokens)
and "aroma" in left_text
and "aroma" in right_text
and "lava" in left_text
and "lava" in right_text
and "解憂放鬆緩緩燈2.0" in left_text
and "解憂放鬆緩緩燈2.0" in right_text
and "熔岩燈" in left_text
and "熔岩燈" in right_text
and "精油擴香" in left_text
and "精油擴香" in right_text
):
return "gdesign_aroma_lava_lamp_2"
if (
"hooome" in (left.brand_tokens & right.brand_tokens)
and "白色" in left_text
and "白色" in right_text
and "香氛蠟燭暖燈" in left_text
and "香氛蠟燭暖燈" in right_text
and "兩顆燈泡" in left_text
and "兩顆燈泡" in right_text
and "禮盒" in left_text
and "禮盒" in right_text
):
return "hooome_classic_white_wax_lamp_bulbs_giftbox"
return ""