修复 P0:根因判定、退服率口径、影响评估与告警关联量化

- 根因判定改为三级(衍生关系/时间窗/疑似)并带置信度;小区退服告警 ±2 分钟匹配;
  衍生告警按父告警归类;优先选随业务恢复清除的告警;时间窗按历史流水 95% 分位数标定
- 退服率按日历统计周期计算;站点数分母支持站名关键字;重复退服率除以全部站点;
  月均按统计周期自然月数;导出与看板同一口径
- 影响评估新增受影响用户·小时与 500 米邻站覆盖补偿
- 新增告警—退服关联量化(支持度/置信度/提升度)及 /api/association,根因页展示
- 新增 tests/(扰动数据集留出检验、指标口径检验)与 bench.py;旧库启动时自动迁移

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
treeandClaude Opus 5.5 committed 2026-11-18 14:43:34 +08:00
1 parent f8d1ccc526
commit e9616af34d
10 files changed
+869 -119

No files matched your search

+40 -18
View File
@@ -5,7 +5,7 @@
接口分组(与下方代码顺序一致):
页面与认证 / /login /logout /healthz
看板与统计 /api/meta /api/dashboard /api/stats /api/confusion /api/sites/rank
看板与统计 /api/meta /api/dashboard /api/stats /api/confusion /api/association /api/sites/rank
退服流水 /api/outages(查询、新增、修改、删除、批量) /api/analyze
数据导入 /api/import/preview /api/import/confirm /api/template
站点与场景 /api/sites /api/scenes
@@ -154,7 +154,8 @@ def dashboard():
started = time.time()
filters = current_filters()
df = core.frame(filters)
stats = core.site_stats(df)
minutes, months = core.period(filters)
stats = core.site_stats(df, months)
# 月度趋势:次数与时长(小时)
trend = df.groupby('month').agg(n=('id', 'size'), h=('duration_min', 'sum')).reset_index()
@@ -175,11 +176,12 @@ def dashboard():
scene_sites = core.site_count({**filters, 'scene': scene})
if scene_sites == 0:
continue
scene_kpi = core.kpis(df[df['scene'] == scene], scene_sites)
scene_kpi = core.kpis(df[df['scene'] == scene], scene_sites, minutes, months)
bench.append(dict(scene=scene, **scene_kpi))
return jsonify(
kpi=core.kpis(df, core.site_count(filters)),
kpi=core.kpis(df, core.site_count(filters), minutes, months),
period=dict(days=round(minutes / 1440, 1), months=months),
elapsed=round(time.time() - started, 3),
rank=to_records(stats.head(15), ['site_name', 'scene', 'total_min', 'count']),
trend=trend.to_dict('records'),
@@ -209,10 +211,10 @@ def stats():
grouped = df.groupby(dimension).agg(
count=('id', 'size'), total_min=('duration_min', 'sum'), avg_min=('duration_min', 'mean'),
max_min=('duration_min', 'max'), long_count=('is_long', 'sum'), users=('affected_users', 'sum'),
loss_gb=('loss_gb', 'sum'), sites=('site_name', 'nunique'),
user_h=('user_hours', 'sum'), loss_gb=('loss_gb', 'sum'), sites=('site_name', 'nunique'),
).reset_index()
grouped['long_ratio'] = (grouped['long_count'] / grouped['count'] * 100).round(2)
grouped = grouped.round({'total_min': 1, 'avg_min': 1, 'loss_gb': 1})
grouped = grouped.round({'total_min': 1, 'avg_min': 1, 'loss_gb': 1, 'user_h': 1})
sort = request.args.get('sort', 'total_min')
if sort not in grouped.columns:
@@ -231,14 +233,29 @@ def confusion():
df = df[df['cause_category'].isin(core.CAUSES)]
matrix = pd.crosstab(df['cause_category'], df['root_cause'])
matrix = matrix.reindex(index=core.CAUSES, columns=core.CAUSES, fill_value=0)
return jsonify(causes=core.CAUSES, matrix=matrix.values.tolist())
# 按置信度分组的准确率:用来说明“高 / 中 / 低”置信度标签是否可信
by_confidence = []
for level in ['高', '中', '低']:
part = df[df['confidence'] == level]
if len(part):
by_confidence.append(dict(level=level, n=len(part),
acc=round((part['cause_category'] == part['root_cause']).mean() * 100, 2)))
return jsonify(causes=core.CAUSES, matrix=matrix.values.tolist(), by_confidence=by_confidence)
@app.route('/api/association')
@login_required
def association():
"""告警类别 → 退服 的关联强度(支持度、置信度、提升度)与当前使用的时间窗。"""
return jsonify(rows=core.association(current_filters()), windows=core.window_table())
@app.route('/api/sites/rank')
@login_required
def site_rank():
"""超长退服站点(kind=long)/ 高频重复站点(kind=repeat)清单,附处置建议。"""
stats = core.site_stats(core.frame(current_filters()))
filters = current_filters()
stats = core.site_stats(core.frame(filters), core.period(filters)[1])
kind = request.args.get('kind', 'long')
if kind == 'long':
stats = stats[stats['long']]
@@ -254,8 +271,8 @@ def site_rank():
# ================================================================ 退服流水管理
OUTAGE_LIST_COLUMNS = ['id', 'record_id', 'ne_id', 'cell_id', 'site_name', 'scene', 'site_type', 'region', 'vendor',
'start_time', 'end_time', 'duration_min', 'reported_min', 'dur_diff', 'cause_category',
'cause_detail', 'cause_code', 'ticket_id', 'root_cause', 'evidence', 'level', 'status',
'handler', 'remark', 'affected_users', 'loss_gb', 'advice']
'cause_detail', 'cause_code', 'ticket_id', 'root_cause', 'evidence', 'confidence', 'level',
'status', 'handler', 'remark', 'affected_users', 'user_hours', 'loss_gb', 'advice']
# 新增 / 管理员修改时写入的字段,顺序与 outage_values() 返回值一致
OUTAGE_EDIT_FIELDS = ['record_id', 'ne_id', 'cell_id', 'start_time', 'end_time', 'duration_min', 'cause_category',
@@ -380,12 +397,12 @@ def outage_batch():
@app.route('/api/analyze', methods=['POST'])
@admin_required
def reanalyze():
"""对全部退服流水重新做根因分析(修改阈值或导入告警后使用)。"""
"""先按历史流水重新标定时间窗,再对全部退服流水重新做根因分析(导入告警或流水后使用)。"""
started = time.time()
count = core.analyze_all()
accuracy = core.kpis(core.frame())['acc']
log(session['user'], '全量根因分析', f'{count} 条')
return jsonify(n=count, elapsed=round(time.time() - started, 3), acc=accuracy)
return jsonify(n=count, elapsed=round(time.time() - started, 3), acc=accuracy, windows=core.window_table())
# ================================================================ 数据导入
@@ -523,6 +540,7 @@ EXPORT_COLUMN_NAMES = {
'duration_min': '系统计算时长(分)', 'reported_min': '上报时长(分)', 'cause_category': '上报原因大类',
'cause_detail': '原因细项', 'cause_code': '原因码', 'ticket_id': '工单号', 'root_cause': '系统判定根因',
'evidence': '关联告警', 'level': '断站分级', 'status': '闭环状态', 'advice': '处置建议', 'record_id': '流水号',
'confidence': '判定置信度', 'user_h': '受影响用户·小时', 'user_hours': '受影响用户·小时',
}
@@ -546,20 +564,23 @@ def excel_response(sheets, filename):
@login_required
def export(kind):
"""三类报表:stats 退服统计表、long 超长退服站点清单、advice 根因处置建议清单。"""
df = core.frame(current_filters())
stats = core.site_stats(df)
filters = current_filters()
df = core.frame(filters)
minutes, months = core.period(filters)
stats = core.site_stats(df, months)
stamp = datetime.now().strftime('%Y%m%d%H%M')
if kind == 'stats':
k = core.kpis(df)
k = core.kpis(df, core.site_count(filters), minutes, months) # 与看板同一口径
kpi_rows = [
['退服次数', k['count']], ['累计退服时长(小时)', k['total_h']], ['平均退服时长(分钟)', k['avg_min']],
['退服率(%)', k['outage_rate']], ['网络可用率(%)', k['availability']], ['超长退服占比(%)', k['long_ratio']],
['重复退服率(%)', k['repeat_rate']], ['受影响用户数', k['users']], ['业务损失(GB)', k['loss_gb']],
['重复退服率(%)', k['repeat_rate']], ['受影响用户数', k['users']], ['受影响用户·小时', k['user_h']],
['业务损失(GB)', k['loss_gb']], ['统计站点数', k['sites']], ['统计周期(天)', round(minutes / 1440, 1)],
['根因判定准确率(%)', k['acc']], ['闭环率(%)', k['closed']], ['上报时长差错(条)', k['dur_fix']],
]
site_columns = ['ne_id', 'site_name', 'region', 'scene', 'site_type', 'count', 'total_min', 'avg_min',
'max_min', 'long_count', 'users', 'top_cause']
'max_min', 'long_count', 'users', 'user_h', 'top_cause']
sheets = {
'考核指标': pd.DataFrame(kpi_rows, columns=['指标', '数值']),
'站点退服统计': stats[site_columns].rename(columns=EXPORT_COLUMN_NAMES),
@@ -589,7 +610,8 @@ def export(kind):
for cause, level in zip(long_outages['root_cause'], long_outages['level'])]
long_outages = long_outages.sort_values('duration_min', ascending=False)
columns = ['record_id', 'ne_id', 'site_name', 'scene', 'start_time', 'end_time', 'duration_min',
'cause_category', 'cause_code', 'root_cause', 'evidence', 'level', 'status', 'ticket_id', 'advice']
'cause_category', 'cause_code', 'root_cause', 'evidence', 'confidence', 'level', 'status',
'ticket_id', 'advice']
sheets = {'根因处置建议': long_outages[columns].rename(columns=EXPORT_COLUMN_NAMES)}
title = '根因处置建议清单'