{% extends "ewoooc_base.html" %} {% block title %}AI 品質診斷台{% endblock %} {% block ewooo_content %} {% set total_feedback = namespace(value=0) %}{% set worst_avg = namespace(value=5) %}{% for caller, info in trends %}{% set total_feedback.value = total_feedback.value + (info.total_feedback or 0) %}{% if info.avg_score < worst_avg.value %}{% set worst_avg.value = info.avg_score %}{% endif %}{% endfor %} {% set episode_total = (episode_distribution.values() | sum) if episode_distribution else 0 %} {% set rag_total = (rag_overall_dist | sum(attribute='count')) if rag_overall_dist else 0 %}
Quality Diagnostics · {{ days }}d Window

AI 品質診斷台

這裡看 AI 的回答到底有沒有變好：caller 反饋、RAG 分數、learning episode 流量、action plan 與 outcome 閉環全部聚合到同一張品質雷達。

Feedback
{{ total_feedback.value }}caller feedback 總量
Worst Avg
{{ "%.2f"|format(worst_avg.value) }}最差 caller 平均分
Episodes
{{ episode_total }}蒸餾池 {{ days }} 日
RAG Scores
{{ rag_total }}已回饋 RAG query
{% if error %}
{{ error }}
{% endif %}
Caller Feedback

呼叫端 × 反饋分佈

{% for caller, info in trends %}{% else %}{% endfor %}
呼叫端平均讚倒讚總數趨勢分布
{{ caller }}{{ "%.2f"|format(info.avg_score) }}/5{{ info.thumbs_up }}{{ info.thumbs_down }}{{ info.total_feedback }}{% if info.trend == 'positive' %}正向{% elif info.trend == 'negative' %}負向{% elif info.trend == 'neutral' %}中性{% else %}無資料{% endif %}
無反饋資料
{% if action_plans_status %}
Action Plans

Action Plans 狀態分布

{% for a in action_plans_status %}{% endfor %}
狀態計畫類型數量
{{ a.status }}{{ a.plan_type }}{{ a.count }}
{% endif %}
{% if rag_root_causes %}
Root Cause

RAG 自動根因建議

{% for rc in rag_root_causes %}
{{ rc.caller }}{{ "%.2f"|format(rc.avg_score) }}/5{{ rc.feedback_n }} 筆
    {% for h in rc.hits %}
  • {{ h.insight_type }}相似度 {{ "%.2f"|format(h.similarity) }}{{ h.content }}{% if h.content|length >= 200 %}…{% endif %}
    • {% endfor %}
{% endfor %}
{% endif %} {% if recommendations %}
Recommendations

智能建議

    {% for rec in recommendations %}
  • {% if rec.action == 'review' %}{% else %}{% endif %}{{ rec.caller }}：{{ rec.reason }}
    • {% endfor %}
{% endif %} {% if action_outcomes_stats %}
Action Outcomes

實際動作成效

{% set total_ao = (action_outcomes_stats | sum(attribute='count')) or 1 %}{% for r in action_outcomes_stats %}
{{ r.verdict }}{{ r.count }}{{ "%.1f"|format(r.count / total_ao * 100) }}%
{% endfor %}
{% endif %}

Operation Ollama-First v5.0 — AI 品質診斷台

{% if rag_overall_dist %}{% endif %} {% endblock %}