feat: update Python processors and add utility scripts

- Update ASR, face, OCR, pose processors
- Add release pre-flight check script
- Add synonym generation, chunk processing scripts
- Add face recognition, stamp search utilities

scripts/simple_face_stats.py

@@ -0,0 +1,113 @@
+#!/usr/bin/env python3
+"""
+簡單人臉統計
+"""
+
+import psycopg2
+from datetime import datetime
+
+
+def get_simple_stats():
+    """獲取簡單統計"""
+    conn = psycopg2.connect(
+        host="localhost",
+        port=5432,
+        database="momentry",
+        user="accusys",
+        password="accusys",
+    )
+
+    cursor = conn.cursor()
+
+    # 總體統計
+    cursor.execute("""
+        SELECT 
+          COUNT(*) as total_faces,
+          SUM(CASE WHEN attributes->>'gender' = 'male' THEN 1 ELSE 0 END) as male_count,
+          SUM(CASE WHEN attributes->>'gender' = 'female' THEN 1 ELSE 0 END) as female_count,
+          ROUND(AVG(CASE WHEN attributes->>'age' ~ '^[0-9]+$' THEN (attributes->>'age')::numeric ELSE NULL END)::numeric, 1) as avg_age,
+          MIN(CASE WHEN attributes->>'age' ~ '^[0-9]+$' THEN (attributes->>'age')::numeric ELSE NULL END) as min_age,
+          MAX(CASE WHEN attributes->>'age' ~ '^[0-9]+$' THEN (attributes->>'age')::numeric ELSE NULL END) as max_age
+        FROM face_detections
+    """)
+
+    total_stats = cursor.fetchone()
+
+    # 按視頻統計
+    cursor.execute("""
+        SELECT 
+          video_uuid,
+          COUNT(*) as total_faces
+        FROM face_detections 
+        GROUP BY video_uuid 
+        ORDER BY total_faces DESC
+    """)
+
+    video_stats = cursor.fetchall()
+
+    cursor.close()
+    conn.close()
+
+    return total_stats, video_stats
+
+
+def main():
+    print("=" * 60)
+    print("人臉識別統計報告")
+    print("=" * 60)
+    print(f"生成時間: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
+    print()
+
+    try:
+        total_stats, video_stats = get_simple_stats()
+
+        total_faces, male_count, female_count, avg_age, min_age, max_age = total_stats
+
+        print("📊 總體統計")
+        print("-" * 40)
+        print(f"總人臉數: {total_faces}")
+        print(f"男性: {male_count} ({male_count / total_faces * 100:.1f}%)")
+        print(f"女性: {female_count} ({female_count / total_faces * 100:.1f}%)")
+        print(f"平均年齡: {avg_age} 歲")
+        print(f"年齡範圍: {min_age} - {max_age} 歲")
+        print()
+
+        print("🎬 視頻統計")
+        print("-" * 40)
+
+        video_names = {
+            "384b0ff44aaaa1f1": "Old_Time_Movie_Show_-_Charade_1963.HD.mov",
+            "9760d0820f0cf9a7": "ExaSAN PCIe series - Director Ou Yu-Zhi Shares His Experience.mp4",
+        }
+
+        for video_uuid, face_count in video_stats:
+            video_name = video_names.get(video_uuid, video_uuid)
+            print(f"{video_name}:")
+            print(f"  UUID: {video_uuid}")
+            print(f"  檢測到人臉: {face_count}")
+            print()
+
+        print("=" * 60)
+        print()
+
+        # 直接回答問題
+        print("📝 問題回答:")
+        print("-" * 40)
+        print(f"Q: 這兩個影片內有幾個人?")
+        print(f"A: 總共檢測到 {total_faces} 個人臉")
+        print()
+        print(f"Q: 幾男幾女?")
+        print(f"A: 男性 {male_count} 人 ({male_count / total_faces * 100:.1f}%)")
+        print(f"   女性 {female_count} 人 ({female_count / total_faces * 100:.1f}%)")
+        print()
+        print(f"Q: 平均年齡?")
+        print(f"A: 平均 {avg_age} 歲 (範圍: {min_age}-{max_age}歲)")
+        print()
+        print("=" * 60)
+
+    except Exception as e:
+        print(f"❌ 獲取統計數據時出錯: {e}")
+
+
+if __name__ == "__main__":
+    main()