feat: enrich question insights classification

ai_knowledge_base_v2/apps/backend/app/services/question_insight_service.py

@@ -11,6 +11,7 @@ from sqlalchemy import select
 from sqlalchemy.orm import Session
 
 from app.models.chat import ChatMessage, ChatSession
+from app.models.logs import AiRequestLog
 from app.models.user import User
 
 
@@ -116,6 +117,7 @@ class QuestionInsightService:
         messages = _load_user_messages(db, date_from=date_from, date_to=date_to, limit=max_messages)
         cleaned, filtered_count = _clean_messages(messages)
         clusters = _cluster_questions(cleaned)
+        ai_logs = _load_ai_logs(db, date_from=date_from, date_to=date_to, limit=max_messages)
         visible_clusters = [cluster for cluster in clusters if len(cluster.questions) >= min_count]
         visible_clusters.sort(key=lambda item: (len(item.questions), item.questions[-1].created_at), reverse=True)
 
@@ -137,7 +139,7 @@ class QuestionInsightService:
                 "visibleClusterCount": total,
                 "minCount": min_count,
             },
-            "items": [_cluster_dict(index + offset + 1, cluster) for index, cluster in enumerate(page_clusters)],
+            "items": [_cluster_dict(index + offset + 1, cluster, ai_logs) for index, cluster in enumerate(page_clusters)],
             "total": total,
             "page": page,
             "pageSize": page_size,
@@ -168,6 +170,21 @@ def _load_user_messages(
     )
 
 
+def _load_ai_logs(
+    db: Session,
+    *,
+    date_from: datetime | None,
+    date_to: datetime | None,
+    limit: int,
+) -> list[AiRequestLog]:
+    query = select(AiRequestLog)
+    if date_from is not None:
+        query = query.where(AiRequestLog.created_at >= date_from.replace(tzinfo=None))
+    if date_to is not None:
+        query = query.where(AiRequestLog.created_at <= date_to.replace(tzinfo=None))
+    return list(db.scalars(query.order_by(AiRequestLog.created_at.desc(), AiRequestLog.id.desc()).limit(limit)).all())
+
+
 def _clean_messages(messages: Iterable[tuple[ChatMessage, ChatSession | None, User | None]]) -> tuple[list[CleanedQuestion], int]:
     cleaned: list[CleanedQuestion] = []
     filtered_count = 0
@@ -317,19 +334,30 @@ def _looks_more_question_like(candidate: str, current: str) -> bool:
     return any(marker in candidate for marker in markers) and not any(marker in current for marker in markers)
 
 
-def _cluster_dict(rank: int, cluster: QuestionCluster) -> dict:
+def _cluster_dict(rank: int, cluster: QuestionCluster, ai_logs: list[AiRequestLog]) -> dict:
     questions = sorted(cluster.questions, key=lambda item: item.created_at, reverse=True)
     users = {item.user_id for item in questions}
     sessions = {item.session_id for item in questions}
     variants = Counter(item.text for item in questions).most_common(6)
     terms = _top_terms(questions)
+    category, category_label = _classify_cluster(cluster)
+    related_logs = _related_ai_logs(cluster, ai_logs)
+    no_hit_count = sum(1 for item in related_logs if not item.knowledge_hit)
+    failed_count = sum(1 for item in related_logs if item.status != "SUCCESS")
     return {
         "rank": rank,
         "title": cluster.title,
         "normalized": cluster.normalized,
+        "category": category,
+        "categoryLabel": category_label,
         "count": len(questions),
         "userCount": len(users),
         "sessionCount": len(sessions),
+        "aiRequestCount": len(related_logs),
+        "noHitCount": no_hit_count,
+        "failedCount": failed_count,
+        "needsKnowledgeFollowUp": _needs_knowledge_follow_up(category, no_hit_count, failed_count),
+        "suggestedAction": _suggested_action(category, no_hit_count, failed_count),
         "firstSeenAt": min(item.created_at for item in questions),
         "lastSeenAt": max(item.created_at for item in questions),
         "topTerms": terms,
@@ -357,3 +385,65 @@ def _top_terms(questions: list[CleanedQuestion]) -> list[str]:
             if len(token) >= 2 and not token.isdigit():
                 counter[token] += 1
     return [term for term, _count in counter.most_common(8)]
+
+
+def _classify_cluster(cluster: QuestionCluster) -> tuple[str, str]:
+    text = f"{cluster.title}{cluster.normalized}"
+    rules = (
+        ("fixed_info", "固定信息", ("上课安排", "回放", "会议链接", "课程助理", "时间", "链接", "权益", "联系方式", "安排")),
+        ("homework", "功课操作", ("功课", "练习", "作业", "怎么做", "步骤", "操作")),
+        ("course_knowledge", "课程知识", ("是什么", "区别", "意思", "概念", "课程", "知识")),
+        ("emotion", "情绪梳理", ("情绪", "身体", "感受", "害怕", "愤怒", "委屈", "抗拒", "焦虑", "释放")),
+        ("service", "服务权益", ("费用", "退款", "续费", "权益", "名额", "有效期", "购买")),
+    )
+    for key, label, keywords in rules:
+        if any(keyword in text for keyword in keywords):
+            return key, label
+    return "other", "其他问题"
+
+
+def _related_ai_logs(cluster: QuestionCluster, ai_logs: list[AiRequestLog]) -> list[AiRequestLog]:
+    session_ids = {item.session_id for item in cluster.questions}
+    matched: list[AiRequestLog] = []
+    for log in ai_logs:
+        if log.session_id not in session_ids:
+            continue
+        prompt = _normalize_question(_prompt_question_text(log.prompt or ""))
+        if not prompt:
+            continue
+        score = max(SequenceMatcher(None, cluster.normalized, prompt).ratio(), _containment(cluster.normalized, prompt))
+        if score >= 0.42 or cluster.normalized in prompt:
+            matched.append(log)
+    return matched
+
+
+def _prompt_question_text(prompt: str) -> str:
+    lines = [line.strip() for line in prompt.splitlines() if line.strip()]
+    for line in lines[:12]:
+        if line.startswith("用户问题") or line.startswith("问题") or line.startswith("用户提问"):
+            return line
+    return "\n".join(lines[:4])
+
+
+def _needs_knowledge_follow_up(category: str, no_hit_count: int, failed_count: int) -> bool:
+    if failed_count > 0:
+        return True
+    if no_hit_count <= 0:
+        return False
+    return category in {"fixed_info", "homework", "course_knowledge", "service"}
+
+
+def _suggested_action(category: str, no_hit_count: int, failed_count: int) -> str:
+    if failed_count > 0:
+        return "优先查看 AI 请求失败原因，确认模型或工具链是否异常。"
+    if no_hit_count > 0 and category == "fixed_info":
+        return "建议优先补充或更新固定信息类知识库，并确认该库处于开放状态。"
+    if no_hit_count > 0 and category in {"homework", "course_knowledge"}:
+        return "建议检查课程知识库切片和召回结果，必要时补充课程章节或关键词。"
+    if no_hit_count > 0:
+        return "建议抽样查看原始对话，判断是否需要补知识库或优化无命中回答。"
+    if category == "emotion":
+        return "建议抽样检查回答是否回到当下、身体感受和觉察方向，避免建议过深过多。"
+    if category == "service":
+        return "建议确认服务权益和运营说明是否已有固定信息沉淀。"
+    return "建议抽样查看相似问法，判断是否需要沉淀成知识库补充项。"

ai_knowledge_base_v2/apps/backend/tests/test_admin_pagination.py

@@ -126,6 +126,7 @@ def test_question_insights_clean_and_cluster_similar_user_questions():
                 ChatMessage(id=5, session_id=1, user_id=1, role="user", content="1、回放在哪里看？\n2、上课链接在哪", created_at=now + timedelta(minutes=3)),
             ]
         )
+        db.add(AiRequestLog(session_id=1, user_id=1, status="SUCCESS", prompt="用户问题：心光有哪些作业？", knowledge_hit=0))
         db.commit()
 
         response = question_insights(
@@ -147,3 +148,6 @@ def test_question_insights_clean_and_cluster_similar_user_questions():
         assert data["items"][0]["count"] == 2
         assert "心光" in data["items"][0]["title"]
         assert data["items"][0]["userCount"] == 2
+        assert data["items"][0]["category"] == "homework"
+        assert data["items"][0]["noHitCount"] == 1
+        assert data["items"][0]["needsKnowledgeFollowUp"] is True