fix(analytics): shrink video efficiency and gate noisy boards by views

This commit is contained in:
kairee committed 2026-11-01 12:25:27 +08:00
1 parent e7034cfb84
commit bc3bef0743
12 files changed
+125 -40

No files matched your search

+59 -7
View File
@@ -699,6 +699,7 @@ class DashboardQueries:
latest = self._latest_date(conn) or self._today()
analytics = self.config_store.get().analytics
duration_sorts = {"efficiency", "interaction_efficiency"}
min_view_for_ranking = max(0, int(analytics.min_view_for_ranking))
within_field = None
if within_days is not None:
if within_days < 1:
@@ -716,7 +717,7 @@ class DashboardQueries:
)
aids = [int(video["aid"]) for video in videos]
snapshots = self._snapshot_map(conn, aids)
_, _, heat, percentiles = self._global_heat(conn)
videos_all, snapshots_all, heat, percentiles = self._global_heat(conn)
previous: dict[int, dict[str, Any]] = {}
if sort in {"growth", "growth_rate", "interaction"}:
@@ -740,16 +741,60 @@ class DashboardQueries:
if sort in duration_sorts:
latest_start, _ = day_bounds(latest)
minimum_seconds = max(0, int(analytics.min_duration_seconds))
min_view = max(0, int(analytics.min_view_for_efficiency))
items = [
item for item in items
if item["metrics"] is not None
and int(item["duration"] or 0) >= minimum_seconds
and int((item["metrics"] or {}).get("view", 0)) >= min_view
and int((item["metrics"] or {}).get("view", 0)) >= min_view_for_ranking
and is_mature(
item["pubdate"], latest_start, analytics.maturity_days
)
]
kappa_hours = max(0, int(analytics.video_shrink_minutes)) / 60.0
total_hours = 0.0
total_views = 0.0
total_interactions = 0.0
for video in videos_all:
hours = content_hours(video.get("duration"))
if hours is None:
continue
metrics = _metric_map(snapshots_all.get(int(video["aid"])))
if metrics is None:
continue
total_hours += hours
total_views += metrics["view"]
total_interactions += (
metrics["like"] + metrics["coin"] + metrics["favorite"]
)
prior_views = total_views / total_hours if total_hours > 0 else 0.0
prior_interactions = (
total_interactions / total_hours if total_hours > 0 else 0.0
)
for item in items:
hours = content_hours(item.get("duration")) or 0.0
metrics = item["metrics"] or {}
denominator = hours + kappa_hours
if hours <= 0 or denominator <= 0:
item["efficiency_score"] = None
item["interaction_efficiency_score"] = None
continue
view = int(metrics.get("view", 0))
interactions = (
int(metrics.get("like", 0))
+ int(metrics.get("coin", 0))
+ int(metrics.get("favorite", 0))
)
item["efficiency_score"] = (
view + kappa_hours * prior_views
) / denominator
item["interaction_efficiency_score"] = (
interactions + kappa_hours * prior_interactions
) / denominator
if sort == "heat":
items = [
item for item in items
if int((item["metrics"] or {}).get("view", 0)) >= min_view_for_ranking
]
if sort == "interaction":
items = [item for item in items if item["interaction_rate"] is not None]
if sort in {"growth", "growth_rate"}:
@@ -773,7 +818,11 @@ class DashboardQueries:
if sort == "interaction":
return item["interaction_rate"] if item["interaction_rate"] is not None else float("-inf")
if sort in {"efficiency", "interaction_efficiency"}:
value = item.get(sort)
field = (
"efficiency_score" if sort == "efficiency"
else "interaction_efficiency_score"
)
value = item.get(field)
return value if value is not None else float("-inf")
if sort in {"growth", "growth_rate"}:
field = "delta" if sort == "growth" else "rate"
@@ -800,13 +849,15 @@ class DashboardQueries:
duration_filter = {
"min_duration_seconds": max(0, int(analytics.min_duration_seconds)),
"maturity_days": max(0, int(analytics.maturity_days)),
"min_view": max(0, int(analytics.min_view_for_efficiency)),
"min_view": min_view_for_ranking,
"shrink_minutes": max(0, int(analytics.video_shrink_minutes)),
}
if not items:
available = False
reason = (
f"仅统计时长 ≥ {duration_filter['min_duration_seconds']} 秒、"
f"发布满 {duration_filter['maturity_days']} 天的视频"
f"发布满 {duration_filter['maturity_days']} 天、"
f"播放 ≥ {duration_filter['min_view']} 的视频"
)
return {
"sort": sort,
@@ -1425,7 +1476,8 @@ class DashboardQueries:
"analytics": {
"min_duration_seconds": cfg.analytics.min_duration_seconds,
"maturity_days": cfg.analytics.maturity_days,
"min_view_for_efficiency": cfg.analytics.min_view_for_efficiency,
"min_view_for_ranking": cfg.analytics.min_view_for_ranking,
"video_shrink_minutes": cfg.analytics.video_shrink_minutes,
"shrink_minutes": cfg.analytics.shrink_minutes,
},
"heat_weights": {