feat: 2026-07-12~13 全量更新 - AI对话链路改造+H5 v4/v5+坐席端v5+上下文感知诊断+知识库迭代3
## H5 员工端 v4 (2026-07-13 00:48 已部署)
- 人工按钮三态文案统一为"人工坐席"
- 按钮位置移至发送键和语音按钮上方(垂直堆叠)
- 点按钮直接调 store.shakeAgent()，删除 CallAgentModal 弹窗动画
- 截图快捷键提示改为"截图->粘贴：Alt+Shift+A-Ctrl+V ---> Ctrl+V"
- 移动端隐藏截图提示(CSS 媒体查询)
- AI转人工提示改为"已为您呼叫人工坐席，请稍等!"
- 坐席接入提示改为"坐席正在查看您的信息，请等待处理回复！"
- 删除"摇铃呼叫坐席"入口和文案
- 删除孤儿组件 MessageList.vue + shake 动画 CSS
## H5 员工端 v5 (2026-07-13 02:08 已部署)
- RightPanel v2.1：删除"软件安装"和"资源权限"标签页
- 移除标签栏，智能推荐(DynamicRecommend)直接展示
- 删除 SoftwareDownloads/ApprovalLinks 引用和相关 CSS
## AI 对话链路全栈改造 Phase 1-6 (已部署)
- Phase 1: Dify JSON输出 + 后端blocking解析 + 双WS推送 + 错误降级
- Phase 2: 关键词收窄(~25强意图词) + 两级分类Prompt + 删除前端checkApprovalIntent
- Phase 3: WS扩展(ai_thinking+dynamic_recommend) + ai_structured气泡 + RightPanel v2 + 选项回传
- Phase 4: VisionService接入 + 图片消息融合(5秒窗口) + 降级策略
- Phase 5: 坐席端ai_thinking指示器 + ai_structured/byod_card渲染 + handleNewMessage修复
- Phase 6: diagnosis_stage(6值) + response_time_ms计时 + 慢响应告警(>10s)
## 坐席端 v5 (2026-07-13 01:38 已部署)
- ai_structured/byod_card 只读渲染
- AI思考指示器 UI
- handleNewMessage 透传 msg_type/extra_data 修复
- 布局优化v2.0: QuickReplyBar L1+L2悬浮 + ReplyBox左右分区 + 右栏260/560px切换
- 键盘快捷键v2.3: 纯数字路由 + ESC分层撤销 + Shift+Space用event.code
## 上下文感知智能诊断闭环 (2026-07-12 已部署)
- 三层诊断(API→Script→AI) + 三段排队(VIP→info_locked→not locked)
- 答题插队 + 五场景关闭
- 迁移052(6表+6列) + queue_service + quiz_service + closing_service
- H5前端: QueueWaiting + RightPanel双Tab + InputBar三态 + ResolveConfirmCard
- 坐席前端: pending_close结单流程 + 信息锁定(Dify步骤完成+有效回答率≥70%)
## 知识库迭代3 (2026-07-12 已部署)
- 分诊交互(H5+坐席+Dify独立应用)
- 拓扑预览(ECharts只读)
- 代答排除(4种匹配器: keyword/regex/intent/category)
- 迁移051 + 44文件43测试通过
## 后端变更
- 6个Python文件改造(h5_ai_task.py/h5.py/ai_service.py/closing_service.py等)
- funny_phrase_service.py: shake/connected/keyword 默认文案更新
- session_service.py: 企微消息文案同步
- 新增: queue.py/quiz.py/triage.py/exclusion_rules.py 等API端点
- 新增: diagnostic.py/quiz.py/triage_session.py 等模型
- 新增: closing_service/queue_service/quiz_service/triage_service 等服务
## 文档更新
- CHANGELOG.md: 新增 [未发布] 区全部变更记录
- 项目管理主文档 v2.5: 新增v0.7.3版本 + 已完成看板 + 最近搞定
- 版本记录: 新增v0.7.3条目
- AI对话链路实施计划: Phase 1-6 全部标记✅已实施
- 新增架构图/时序图/类图(mermaid)
## 部署路径修正
- 服务器项目根路径: /opt/wecom-it-desk/
- 所有前端dist均为ro bind mount，只能在宿主机源路径操作
- 服务器nginx /h5/ 是静态文件服务(非proxy_pass)
- elFinder上传二进制不可靠(MD5不匹配)，改用base64分块上传
This commit is contained in:
Simon
@@ -0,0 +1,174 @@
|
||||
# =============================================================================
|
||||
# 企微IT智能服务台 — 每日测验题目自动生成定时任务
|
||||
# =============================================================================
|
||||
# 说明：每天凌晨 3:00 自动执行：
|
||||
# 1. 按星期轮转生成 1 个类别的 5 道知识题（7 天一轮）
|
||||
# 2. 分析近 7 天已解决工单 → 生成 3 道诊断题
|
||||
# 3. 停用被 >80% 活跃员工答过的陈旧题目
|
||||
#
|
||||
# 调度：CronTrigger(hour=3, minute=0)
|
||||
# 降级：Dify 不可用时记录错误，不影响其他步骤
|
||||
# =============================================================================
|
||||
|
||||
import datetime
|
||||
import logging
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# 7 个题目类别（按星期轮转：周一=network, 周二=vpn, ...）
|
||||
QUIZ_CATEGORIES = ["network", "vpn", "email", "system", "printer", "security", "office"]
|
||||
|
||||
# 每日知识题生成数量
|
||||
KNOWLEDGE_QUESTIONS_PER_DAY = 5
|
||||
|
||||
# 诊断题生成数量
|
||||
DIAGNOSTIC_QUESTIONS_PER_BATCH = 3
|
||||
|
||||
# 默认诊断题问题类别（当近期无工单数据时使用）
|
||||
DEFAULT_DIAGNOSTIC_CATEGORIES = ["network_connect", "vpn_auth_fail", "printer_offline"]
|
||||
|
||||
|
||||
async def run_daily_quiz_generation():
|
||||
"""每日测验题目生成任务。
|
||||
|
||||
执行流程：
|
||||
1. 按星期轮转生成 1 个类别的 5 道知识题
|
||||
2. 分析近 7 天已解决工单 → 取 top 1 问题类别生成 3 道诊断题
|
||||
3. 停用被 >80% 活跃员工答过的陈旧题
|
||||
4. 记录汇总日志
|
||||
|
||||
调度：每日 03:00（CronTrigger hour=3, minute=0）
|
||||
"""
|
||||
from app.database import _get_session_factory
|
||||
from app.services.quiz_generation_service import get_quiz_generation_service
|
||||
|
||||
logger.info("===== 开始每日测验题目生成 =====")
|
||||
|
||||
factory = _get_session_factory()
|
||||
service = get_quiz_generation_service()
|
||||
|
||||
total_generated = 0
|
||||
total_errors = 0
|
||||
|
||||
async with factory() as db:
|
||||
try:
|
||||
# ============================================================
|
||||
# 1. 知识题生成（按星期轮转 1 个类别）
|
||||
# ============================================================
|
||||
today = datetime.date.today()
|
||||
weekday = today.weekday() # 0=Monday, 6=Sunday
|
||||
category = QUIZ_CATEGORIES[weekday]
|
||||
|
||||
logger.info(f"今日轮转类别: {category} (weekday={weekday})")
|
||||
|
||||
try:
|
||||
result = await service.generate_knowledge_questions_batch(
|
||||
db=db,
|
||||
category=category,
|
||||
count=KNOWLEDGE_QUESTIONS_PER_DAY,
|
||||
is_active=False, # 定时生成的题目需管理员审批
|
||||
)
|
||||
total_generated += result["success_count"]
|
||||
total_errors += result["failed_count"]
|
||||
logger.info(
|
||||
f"知识题生成 [{category}]: "
|
||||
f"成功 {result['success_count']}, 失败 {result['failed_count']}"
|
||||
)
|
||||
if result["errors"]:
|
||||
logger.warning(f"知识题错误详情: {result['errors'][:3]}")
|
||||
except Exception as e:
|
||||
logger.error(f"知识题生成 [{category}] 异常: {e}")
|
||||
total_errors += KNOWLEDGE_QUESTIONS_PER_DAY
|
||||
|
||||
# ============================================================
|
||||
# 2. 诊断题生成（基于近期工单模式）
|
||||
# ============================================================
|
||||
try:
|
||||
# 获取近期工单摘要
|
||||
ticket_summaries = await service._get_recent_ticket_summaries(
|
||||
db, days=7, limit=20
|
||||
)
|
||||
|
||||
# 提取 top 1 问题类别
|
||||
problem_category = _extract_top_problem_category(ticket_summaries)
|
||||
|
||||
logger.info(f"诊断题问题类别: {problem_category}")
|
||||
|
||||
result = await service.generate_diagnostic_questions_batch(
|
||||
db=db,
|
||||
problem_category=problem_category,
|
||||
count=DIAGNOSTIC_QUESTIONS_PER_BATCH,
|
||||
ticket_summaries=[t["summary"] for t in ticket_summaries if t["summary"]],
|
||||
is_active=False,
|
||||
)
|
||||
total_generated += result["success_count"]
|
||||
total_errors += result["failed_count"]
|
||||
logger.info(
|
||||
f"诊断题生成 [{problem_category}]: "
|
||||
f"成功 {result['success_count']}, 失败 {result['failed_count']}"
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(f"诊断题生成异常: {e}")
|
||||
total_errors += DIAGNOSTIC_QUESTIONS_PER_BATCH
|
||||
|
||||
# ============================================================
|
||||
# 3. 停用陈旧题目
|
||||
# ============================================================
|
||||
try:
|
||||
stale_result = await service.deactivate_stale_questions(
|
||||
db=db, threshold=0.8
|
||||
)
|
||||
if stale_result["deactivated_count"] > 0:
|
||||
logger.info(
|
||||
f"陈旧题目停用: {stale_result['deactivated_count']} 道 "
|
||||
f"(活跃员工 {stale_result['total_active_employees']} 人)"
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(f"陈旧题目停用异常: {e}")
|
||||
|
||||
# 统一提交
|
||||
await db.commit()
|
||||
|
||||
except Exception as e:
|
||||
await db.rollback()
|
||||
logger.error(f"每日题目生成任务异常: {e}", exc_info=True)
|
||||
|
||||
logger.info(
|
||||
f"===== 每日题目生成完成: 新增 {total_generated} 道, "
|
||||
f"失败 {total_errors} 道 ====="
|
||||
)
|
||||
|
||||
|
||||
def _extract_top_problem_category(
|
||||
ticket_summaries: list,
|
||||
) -> str:
|
||||
"""从工单摘要中提取最高频的问题类别。
|
||||
|
||||
基于 category_hint 字段统计频率。
|
||||
降级：如果无数据，返回默认类别。
|
||||
|
||||
Args:
|
||||
ticket_summaries: _get_recent_ticket_summaries() 返回的列表
|
||||
|
||||
Returns:
|
||||
str: 问题类别标识（如 "vpn_disconnect"）
|
||||
"""
|
||||
if not ticket_summaries:
|
||||
# 无工单数据时返回默认
|
||||
return DEFAULT_DIAGNOSTIC_CATEGORIES[0]
|
||||
|
||||
# 统计 category_hint 频率
|
||||
hint_counts: dict[str, int] = {}
|
||||
for ticket in ticket_summaries:
|
||||
hint = ticket.get("category_hint", "")
|
||||
if hint:
|
||||
hint_counts[hint] = hint_counts.get(hint, 0) + 1
|
||||
|
||||
if not hint_counts:
|
||||
return DEFAULT_DIAGNOSTIC_CATEGORIES[0]
|
||||
|
||||
# 取最高频的类别
|
||||
top_category = max(hint_counts, key=hint_counts.get)
|
||||
|
||||
# 拼接为 problem_category 格式（如 "vpn_disconnect"）
|
||||
return f"{top_category}_issue"
|
||||
Reference in New Issue
Block a user