diff --git a/backend/ai_services/services.py b/backend/ai_services/services.py
index 8c95f1a..8a6f702 100644
--- a/backend/ai_services/services.py
+++ b/backend/ai_services/services.py
@@ -183,8 +183,24 @@ class AliyunTingwuService:
         # 3. 解析结果
         task_result = data_obj.get('Result', {})
         
+        # 兼容处理：如果 Result 为空，或者不存在，尝试直接使用 data_obj 作为结果源
+        # 某些情况下，Summarization/AutoChapters 可能直接位于 Data 层级
+        if not task_result:
+            task_result = data_obj
+
+        # 辅助函数：从源字典或其 Result 子字典中获取字段
+        def get_data_field(source, key):
+            # 1. 尝试直接从 task_result 获取 (如果 task_result 就是 Data 本身，这里也会生效)
+            if isinstance(source, dict) and key in source:
+                return source[key]
+            # 2. 如果 source 是 Data，尝试从 source['Result'] 获取
+            if isinstance(source, dict) and 'Result' in source and isinstance(source['Result'], dict):
+                if key in source['Result']:
+                    return source['Result'][key]
+            return None
+        
         # --- A. 处理逐字稿 (Transcription) ---
-        transcription_data = task_result.get('Transcription', {})
+        transcription_data = get_data_field(task_result, 'Transcription') or get_data_field(data_obj, 'Transcription') or {}
         
         # 处理 URL 下载
         if isinstance(transcription_data, str) and transcription_data.startswith('http'):
@@ -233,7 +249,7 @@ class AliyunTingwuService:
             task.transcription = "\n".join(full_text_lines)
         
         # --- B. 处理 AI 总结 (Summarization) ---
-        summarization = task_result.get('Summarization', {})
+        summarization = get_data_field(task_result, 'Summarization') or get_data_field(data_obj, 'Summarization') or {}
         
         # 处理 URL 下载
         if isinstance(summarization, str) and summarization.startswith('http'):
@@ -270,12 +286,14 @@ class AliyunTingwuService:
             summary_text.append(summarization['Text'])
         elif 'Headline' in summarization:
              summary_text.append(summarization['Headline'])
+        elif 'ParagraphSummary' in summarization:
+             summary_text.append(summarization['ParagraphSummary'])
              
         if summary_text:
             task.summary = "\n".join(summary_text)
 
         # --- C. 处理章节 (AutoChapters) ---
-        auto_chapters = task_result.get('AutoChapters', [])
+        auto_chapters = get_data_field(task_result, 'AutoChapters') or get_data_field(data_obj, 'AutoChapters') or []
         
         # 处理 URL 下载
         if isinstance(auto_chapters, str) and auto_chapters.startswith('http'):