Upload statistics_processor.py

fixed the calculation difference about testing and Ops

statistics_processor.py

@@ -4,23 +4,111 @@ from typing import Dict, List, Optional, Any
 class StatisticsProcessor:
     """
     統計分析處理器 - 負責複雜的物件統計分析和數據轉換
-
-    此類別專門處理物件統計信息的深度分析、Places365信息處理，
-    以及基於統計數據生成替換內容的複雜邏輯。
+    增加了決策穩健性機制來處理環境差異
     """
 
-    def __init__(self):
+    def __init__(self, stability_config=None):
         """初始化統計分析處理器"""
         self.logger = logging.getLogger(self.__class__.__name__)
-        self.logger.debug("StatisticsProcessor initialized successfully")
-
-    def generate_statistics_replacements(self, object_statistics: Optional[Dict]) -> Dict[str, str]:
+        
+        # 穩定性配置參數
+        self.stability_config = stability_config or {
+            'confidence_tolerance': 0.05,  # 信心度容差範圍
+            'count_stability_threshold': 0.8,  # 計數穩定性閾值
+            'decision_buffer_zone': 0.1,  # 決策緩衝區
+            'prefer_specific_descriptions': True,  # 優先使用具體描述
+            'multi_furniture_threshold': 2,  # 多家具類型的最小閾值
+        }
+        
+        self.logger.debug("StatisticsProcessor initialized with stability enhancements")
+
+    def _stabilize_object_counts(self, object_statistics):
+        """
+        穩定化物件計數，減少環境差異影響
+        
+        Args:
+            object_statistics: 原始物件統計數據
+            
+        Returns:
+            穩定化後的物件統計數據
+        """
+        if not object_statistics:
+            return object_statistics
+            
+        stabilized_stats = {}
+        
+        for obj_type, stats in object_statistics.items():
+            stabilized_stats[obj_type] = stats.copy()
+            
+            # 穩定化信心度 - 將接近的值標準化到區間中點
+            confidence = stats.get('confidence', 0.0)
+            if confidence > 0:
+                # 將信心度調整到標準化區間
+                tolerance = self.stability_config['confidence_tolerance']
+                stabilized_confidence = round(confidence / tolerance) * tolerance
+                stabilized_stats[obj_type]['confidence'] = max(stabilized_confidence, confidence)
+                
+        return stabilized_stats
+
+    def _should_use_specific_furniture_description(self, furniture_items, furniture_counts, object_statistics):
+        """
+        決定是否使用具體的家具描述（如 "six chairs"）還是通用描述（如 "furniture pieces"）
+        增加了決策穩健性邏輯
+        
+        Args:
+            furniture_items: 檢測到的家具類型列表
+            furniture_counts: 對應的家具數量列表
+            object_statistics: 完整的物件統計數據
+            
+        Returns:
+            tuple: (是否使用具體描述, 主要家具類型, 主要家具數量)
+        """
+        # 如果沒有檢測到家具，返回通用描述
+        if not furniture_items:
+            return False, None, 0
+            
+        # 如果只有一種家具類型，優先使用具體描述
+        if len(furniture_items) == 1:
+            return True, furniture_items[0], furniture_counts[0]
+            
+        # 多種家具類型的決策邏輯
+        total_furniture_count = sum(furniture_counts)
+        main_furniture = furniture_items[0]
+        main_count = furniture_counts[0]
+        
+        # 計算主要家具類型的比例
+        main_furniture_ratio = main_count / total_furniture_count if total_furniture_count > 0 else 0
+        
+        # 決策緩衝區機制
+        buffer_zone = self.stability_config['decision_buffer_zone']
+        dominance_threshold = 0.7 + buffer_zone  # 主導性閾值加上緩衝區
+        
+        # 椅子的特殊處理邏輯
+        if main_furniture == "chair":
+            chair_stats = object_statistics.get("chair", {})
+            chair_confidence = chair_stats.get('confidence', 0.0)
+            
+            # 如果椅子檢測信心度很高且數量占主導地位，使用具體描述
+            confidence_threshold = 0.8 - buffer_zone  # 降低閾值增加穩定性
+            
+            if (chair_confidence >= confidence_threshold and 
+                main_furniture_ratio >= dominance_threshold):
+                return True, main_furniture, main_count
+                
+            # 如果椅子數量適中且是唯一明確的家具類型，也使用具體描述
+            if main_count <= 8 and main_furniture_ratio >= 0.6:
+                return True, main_furniture, main_count
+                
+        # 其他情況使用通用描述
+        return False, main_furniture, main_count
+
+    def generate_statistics_replacements(self, object_statistics):
         """
         基於物體統計信息生成模板替換內容
-
+        
         Args:
             object_statistics: 物體統計信息
-
+            
         Returns:
             Dict[str, str]: 統計信息基礎的替換內容
         """
@@ -30,9 +118,12 @@ class StatisticsProcessor:
             return replacements
 
         try:
+            # 首先穩定化物件統計數據
+            stabilized_stats = self._stabilize_object_counts(object_statistics)
+            
             # 處理植物元素
-            if "potted plant" in object_statistics:
-                count = object_statistics["potted plant"]["count"]
+            if "potted plant" in stabilized_stats:
+                count = stabilized_stats["potted plant"]["count"]
                 if count == 1:
                     replacements["plant_elements"] = "a potted plant"
                 elif count <= 3:
@@ -40,59 +131,12 @@ class StatisticsProcessor:
                 else:
                     replacements["plant_elements"] = f"multiple potted plants ({count} total)"
 
-            # 處理座位(椅子)相關
-            if "chair" in object_statistics:
-                count = object_statistics["chair"]["count"]
-
-                # 使用統一的數字轉換邏輯
-                number_words = {
-                    1: "one", 2: "two", 3: "three", 4: "four",
-                    5: "five", 6: "six", 7: "seven", 8: "eight",
-                    9: "nine", 10: "ten", 11: "eleven", 12: "twelve"
-                }
-
-                if count == 1:
-                    replacements["seating"] = "a chair"
-                    replacements["furniture"] = "a chair"
-                elif count in number_words:
-                    word_count = number_words[count]
-                    replacements["seating"] = f"{word_count} chairs"
-                    replacements["furniture"] = f"{word_count} chairs"
-                elif count <= 20:
-                    replacements["seating"] = f"several chairs"
-                    replacements["furniture"] = f"several chairs"
-                else:
-                    replacements["seating"] = f"numerous chairs ({count} total)"
-                    replacements["furniture"] = f"numerous chairs"
-
-            # 處理混合家具情況（當存在多種家具類型時）
-            furniture_items = []
-            furniture_counts = []
-
-            # 收集所有家具類型的統計
-            for furniture_type in ["chair", "dining table", "couch", "bed"]:
-                if furniture_type in object_statistics:
-                    count = object_statistics[furniture_type]["count"]
-                    if count > 0:
-                        furniture_items.append(furniture_type)
-                        furniture_counts.append(count)
-
-            # 如果只有椅子,那就用上面的方式
-            # 如果有多種家具類型，生成組合描述
-            if len(furniture_items) > 1 and "furniture" not in replacements:
-                main_furniture = furniture_items[0]  # 數量最多的家具類型
-                main_count = furniture_counts[0]
-
-                if main_furniture == "chair":
-                    number_words = ["", "one", "two", "three", "four", "five", "six"]
-                    if main_count <= 6:
-                        replacements["furniture"] = f"{number_words[main_count]} chairs and other furniture"
-                    else:
-                        replacements["furniture"] = "multiple chairs and other furniture"
-
+            # 椅子和家具的穩健處理邏輯
+            self._process_furniture_with_stability(stabilized_stats, replacements)
+            
             # 處理人員
-            if "person" in object_statistics:
-                count = object_statistics["person"]["count"]
+            if "person" in stabilized_stats:
+                count = stabilized_stats["person"]["count"]
                 if count == 1:
                     replacements["people_and_vehicles"] = "a person"
                     replacements["pedestrian_flow"] = "an individual walking"
@@ -103,9 +147,9 @@ class StatisticsProcessor:
                     replacements["people_and_vehicles"] = f"many people ({count} individuals)"
                     replacements["pedestrian_flow"] = f"a crowd of {count} people"
 
-            # 處理桌子設置
-            if "dining table" in object_statistics:
-                count = object_statistics["dining table"]["count"]
+            # 處理桌子設置（保持原有邏輯）
+            if "dining table" in stabilized_stats:
+                count = stabilized_stats["dining table"]["count"]
                 if count == 1:
                     replacements["table_setup"] = "a dining table"
                     replacements["table_description"] = "a dining surface"
@@ -113,54 +157,133 @@ class StatisticsProcessor:
                     replacements["table_setup"] = f"{count} dining tables"
                     replacements["table_description"] = f"{count} dining surfaces"
 
-            self.logger.debug(f"Generated {len(replacements)} statistics-based replacements")
+            self.logger.debug(f"Generated {len(replacements)} stability-enhanced replacements")
 
         except Exception as e:
             self.logger.warning(f"Error generating statistics replacements: {str(e)}")
 
         return replacements
 
-    def generate_places365_replacements(self, places365_info: Optional[Dict]) -> Dict[str, str]:
+    def _process_furniture_with_stability(self, object_statistics, replacements):
         """
-        基於Places365信息生成模板替換內容
-
+        使用穩健性邏輯處理家具描述, 解決測試與部署時的浮點數計算結果差異
+        
+        
         Args:
-            places365_info: Places365場景分類信息
+            object_statistics: 穩定化後的物件統計數據
+            replacements: 要更新的替換字典
+        """
+        # 數字轉換字典
+        number_words = {
+            1: "one", 2: "two", 3: "three", 4: "four",
+            5: "five", 6: "six", 7: "seven", 8: "eight",
+            9: "nine", 10: "ten", 11: "eleven", 12: "twelve"
+        }
+        
+        # 收集所有家具類型的統計
+        furniture_items = []
+        furniture_counts = []
+        
+        furniture_types = ["chair", "dining table", "couch", "bed"]
+        for furniture_type in furniture_types:
+            if furniture_type in object_statistics:
+                count = object_statistics[furniture_type]["count"]
+                if count > 0:
+                    furniture_items.append(furniture_type)
+                    furniture_counts.append(count)
+
+        # 使用穩健性決策邏輯
+        use_specific, main_furniture, main_count = self._should_use_specific_furniture_description(
+            furniture_items, furniture_counts, object_statistics
+        )
+        
+        # 椅子的特殊處理
+        if "chair" in object_statistics:
+            chair_count = object_statistics["chair"]["count"]
+            
+            if use_specific and main_furniture == "chair":
+                # 使用具體的椅子描述
+                if chair_count == 1:
+                    replacements["seating"] = "a chair"
+                    replacements["furniture"] = "a chair"
+                elif chair_count in number_words:
+                    word_count = number_words[chair_count]
+                    replacements["seating"] = f"{word_count} chairs"
+                    replacements["furniture"] = f"{word_count} chairs"
+                elif chair_count <= 20:
+                    replacements["seating"] = "several chairs"
+                    replacements["furniture"] = "several chairs"
+                else:
+                    replacements["seating"] = f"numerous chairs ({chair_count} total)"
+                    replacements["furniture"] = "numerous chairs"
+                    
+                self.logger.debug(f"Using specific chair description: {replacements.get('furniture', 'N/A')}")
+                
+            else:
+                # 使用通用家具描述
+                total_furniture = sum(furniture_counts)
+                if total_furniture == 1:
+                    replacements["furniture"] = "a furniture piece"
+                elif total_furniture in number_words:
+                    word_count = number_words[total_furniture]
+                    replacements["furniture"] = f"{word_count} furniture pieces"
+                else:
+                    replacements["furniture"] = f"several furniture pieces"
+                    
+                # 但椅子的 seating 描述保持具體
+                if chair_count in number_words:
+                    word_count = number_words[chair_count]
+                    replacements["seating"] = f"{word_count} chairs"
+                else:
+                    replacements["seating"] = "several chairs"
+                    
+                self.logger.debug(f"Using generic furniture description: {replacements.get('furniture', 'N/A')}")
+
+        # 處理混合家具情況的額外邏輯
+        if len(furniture_items) > 1 and "furniture" not in replacements:
+            # 當有多種家具但沒有主導類型時的後備邏輯
+            total_count = sum(furniture_counts)
+            if total_count in number_words:
+                word_count = number_words[total_count]
+                replacements["furniture"] = f"{word_count} furniture pieces"
+            else:
+                replacements["furniture"] = "multiple furniture pieces"
 
-        Returns:
-            Dict[str, str]: Places365基礎的替換內容
+    def generate_places365_replacements(self, places365_info):
+        """
+        基於Places365信息生成模板替換內容
         """
         replacements = {}
 
         if not places365_info or places365_info.get('confidence', 0) <= 0.35:
             replacements["places365_context"] = ""
-            replacements["places365_atmosphere"] = ""
             return replacements
 
         try:
-            scene_label = places365_info.get('scene_label', '').replace('_', ' ')
-            attributes = places365_info.get('attributes', [])
-
-            # 生成場景上下文
-            if scene_label:
-                replacements["places365_context"] = f"characteristic of a {scene_label}"
-            else:
-                replacements["places365_context"] = ""
-
-            # 生成氛圍描述
-            if 'natural_lighting' in attributes:
-                replacements["places365_atmosphere"] = "with natural illumination"
-            elif 'artificial_lighting' in attributes:
-                replacements["places365_atmosphere"] = "under artificial lighting"
-            else:
-                replacements["places365_atmosphere"] = ""
-
-            self.logger.debug("Generated Places365-based replacements")
+            scene_class = places365_info.get('scene_class', '').lower()
+            confidence = places365_info.get('confidence', 0.0)
+
+            # 基於場景類別添加上下文信息
+            if 'kitchen' in scene_class:
+                replacements["places365_context"] = "kitchen environment"
+                replacements["area_description"] = "culinary space"
+            elif 'bedroom' in scene_class:
+                replacements["places365_context"] = "sleeping area"
+                replacements["area_description"] = "rest space"
+            elif 'living' in scene_class or 'room' in scene_class:
+                replacements["places365_context"] = "living area"
+                replacements["area_description"] = "comfortable space"
+            elif 'office' in scene_class:
+                replacements["places365_context"] = "work environment"
+                replacements["area_description"] = "professional workspace"
+            elif 'street' in scene_class or 'road' in scene_class:
+                replacements["places365_context"] = "urban street"
+                replacements["area_description"] = "city thoroughfare"
+
+            self.logger.debug(f"Generated Places365 context: {replacements.get('places365_context', 'none')}")
 
         except Exception as e:
             self.logger.warning(f"Error generating Places365 replacements: {str(e)}")
-            replacements["places365_context"] = ""
-            replacements["places365_atmosphere"] = ""
 
         return replacements