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

2026-11-01 12:25:27 +08:00
1 parent e7034cfb84
commit bc3bef0743
@@ -41,7 +41,8 @@ DEFAULT_HEAT_WEIGHTS: dict[str, float] = {
 DEFAULT_ANALYTICS: dict[str, Any] = {
    "min_duration_seconds": 600,
    "maturity_days": 2,
-    "min_view_for_efficiency": 0,
+    "min_view_for_ranking": 2000,
+    "video_shrink_minutes": 60,
    "shrink_minutes": None,
 }

@@ -173,7 +174,8 @@ class DiscoverConfig:
 class AnalyticsConfig:
    min_duration_seconds: int
    maturity_days: int
-    min_view_for_efficiency: int
+    min_view_for_ranking: int
+    video_shrink_minutes: int
    shrink_minutes: int | None


@@ -463,9 +465,14 @@ def _build_config(data: Mapping[str, Any], path: Path) -> AppConfig:
            "analytics.maturity_days",
            minimum=0,
        ),
-        min_view_for_efficiency=_as_int(
-            analytics_raw.get("min_view_for_efficiency", 0),
-            "analytics.min_view_for_efficiency",
+        min_view_for_ranking=_as_int(
+            analytics_raw.get("min_view_for_ranking", 2000),
+            "analytics.min_view_for_ranking",
+            minimum=0,
+        ),
+        video_shrink_minutes=_as_int(
+            analytics_raw.get("video_shrink_minutes", 60),
+            "analytics.video_shrink_minutes",
            minimum=0,
        ),
        shrink_minutes=(
@@ -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": {
@@ -51,8 +51,8 @@ export async function renderAbout(root) {
        <li><strong>互动</strong>：点赞 + 投币 + 收藏。综合热度也使用全部七项指标，按配置权重加权。</li>
        <li><strong>互动率</strong>：(点赞 + 投币 + 收藏) / 播放；播放不足 100 不计算。</li>
        <li><strong>综合热度</strong>：每项先 <code>log1p</code>，再按中位数与 IQR 做稳健标准化，最后加权求和。分数只用于同一批数据内排序，不能跨日期比较。</li>
-        <li><strong>内容效率</strong>：播放 / 内容小时。内容小时 = 视频总时长（多 P 为各 P 之和）÷ 3600。</li>
-        <li><strong>互动效率</strong>：互动 / 内容小时，互动口径同上。</li>
+        <li><strong>内容效率</strong>：播放 / 内容小时。内容小时 = 视频总时长（多 P 为各 P 之和）÷ 3600。榜单里的单条视频用收缩后的估计：<code>(播放 + κ·μ₀) / (小时 + κ)</code>，κ 默认 ${analytics.video_shrink_minutes} 分钟、μ₀ 为全库播放/小时；详情页保留原始播放/小时。</li>
+        <li><strong>互动效率</strong>：互动 / 内容小时，互动口径与收缩方式同上。</li>
        <li><strong>UP 内容效率</strong>：把该 UP 的全部视频合并后计算，并用 Gamma–Poisson 经验贝叶斯向全库均值收缩，避免单条视频或极小样本冲榜。收缩强度 κ ${analytics.shrink_minutes ? `固定为 ${analytics.shrink_minutes} 分钟` : "取全库 UP 总内容分钟的中位数"}。</li>
        <li><strong>累计触达</strong>：总播放。它是规模指标，不代表吸引力；高产 UP 排在前列是正常结果。</li>
        <li><strong>分 P</strong>：<code>pages</code> 是分 P 数，<code>duration</code> 是该 bvid 各 P 时长之和。B 站不公开单 P 播放，因此没有单 P 榜；分 P 数只用于详情展示，不参与排序。</li>
@@ -66,7 +66,7 @@ export async function renderAbout(root) {
        <li>只统计发布满 <strong>${analytics.maturity_days}</strong> 天的视频；reaction 视频通常在发布前两天完成数据积累，两周内接近平台期，过早比较会系统性低估新视频。</li>
        <li>不引入无界的“年龄惩罚”：超过成熟窗口后不再按天加分或扣分。</li>
        <li><code>duration</code> 为空或 ≤ 0 的视频（通常只在失效视频上出现）不进入任何时长相关榜，也不做插补。</li>
-        <li>当前配置的最小播放门槛为 <strong>${analytics.min_view_for_efficiency}</strong>。</li>
+        <li>播放低于 <strong>${analytics.min_view_for_ranking}</strong> 的视频不进入内容效率、互动效率与综合热度榜；这是为了避免小样本噪声冲榜。</li>
      </ul>
    </section>

@@ -83,10 +83,10 @@ function controls({ scope, sort, within, growthDays, q, folder, minVideos, folde

 function videoPrimary(item, sort) {
  if (sort === "efficiency") {
-    return { primary: "efficiency", label: "播放/小时", text: formatCount(item.efficiency) };
+    return { primary: "efficiency_score", label: "播放/小时·收缩", text: formatCount(item.efficiency_score) };
  }
  if (sort === "interaction_efficiency") {
-    return { primary: "interaction_efficiency", label: "互动/小时", text: formatCount(item.interaction_efficiency) };
+    return { primary: "interaction_efficiency_score", label: "互动/小时·收缩", text: formatCount(item.interaction_efficiency_score) };
  }
  if (sort === "interaction") {
    return { primary: "view", label: "互动率", text: formatPercent(item.interaction_rate) };
@@ -143,8 +143,11 @@ function listHtml(data, scope, sort, startRank) {
 function durationNote(data) {
  const filter = data.duration_filter;
  if (!filter) return "";
+  const shrink = filter.shrink_minutes
+    ? `并按 ${filter.shrink_minutes} 分钟的先验暴露量向全库均值收缩`
+    : "";
  return `<div class="section-note">内容效率与互动效率仅统计时长 ≥ ${filter.min_duration_seconds} 秒、
-    发布满 ${filter.maturity_days} 天的视频；时长缺失的视频不参与排序。</div>`;
+    发布满 ${filter.maturity_days} 天、播放 ≥ ${filter.min_view} 的视频${shrink}；时长缺失的视频不参与排序。</div>`;
 }

 function bindControls(root, scope) {
@@ -77,8 +77,8 @@ export async function renderVideo(root, { params, query }) {
      <div><span>综合热度</span><strong>${formatScore(detail.heat)}</strong></div>
      <div><span>全库百分位</span><strong>${detail.heat_percentile === null || detail.heat_percentile === undefined ? "—" : `前 ${Math.max(0, 100 - detail.heat_percentile).toFixed(0)}%`}</strong></div>
      <div><span>播放日增</span><strong>${detail.growth?.available ? formatDelta(detail.growth.delta) : "—"}</strong></div>
-      <div><span>内容效率</span><strong>${detail.efficiency == null ? "—" : `${formatCount(detail.efficiency)}/小时`}</strong></div>
-      <div><span>互动效率</span><strong>${detail.interaction_efficiency == null ? "—" : `${formatCount(detail.interaction_efficiency)}/小时`}</strong></div>
+      <div><span>内容效率（原始）</span><strong>${detail.efficiency == null ? "—" : `${formatCount(detail.efficiency)}/小时`}</strong></div>
+      <div><span>互动效率（原始）</span><strong>${detail.interaction_efficiency == null ? "—" : `${formatCount(detail.interaction_efficiency)}/小时`}</strong></div>
      <div><span>UP 粉丝（入库时）</span><strong>${formatCount(detail.up_follower)}</strong></div>
      <div><span>快照数</span><strong>${samples}</strong></div>
      <div><span>最近快照</span><strong>${escapeHtml(detail.snapshot_date || "—")}</strong></div>