diff --git a/demo/serving/bert_service/README.md b/demo/serving/bert_service/README.md
index 7f318e5c9ac99390a75de8addf80d6d13c911cad..6923fceadb5b568d8848ef9e451cbe5bbcc5f967 100644
--- a/demo/serving/bert_service/README.md
+++ b/demo/serving/bert_service/README.md
@@ -46,7 +46,7 @@ result = bc.get_result(input_text=input_text)
 ```python
 [[0.9993321895599361, 0.9994612336158751, 0.9999646544456481, 0.732795298099517, -0.34387934207916204, ... ]]
 ```
-客户端代码demo文件见[示例](../paddlehub/serving/bert_serving/bert_service.py)。  
+客户端代码demo文件见[示例](./bert_service_client.py)。  
 运行命令如下：  
 ```shell
 $ python bert_service_client.py
diff --git a/tutorial/serving.md b/tutorial/serving.md
index 2a7ad3a375ad00f8156767d23232bf94f68b5e15..c754a1b7a2737458b84326c347a5295520d76afe 100644
--- a/tutorial/serving.md
+++ b/tutorial/serving.md
@@ -193,7 +193,7 @@ if __name__ == "__main__":
 
   该示例展示了利用lac完成中文文本分词服务化部署和在线预测，获取文本的分词结果，并可通过用户自定义词典干预分词结果。
 
-* [目标检测-基于yolov3_darknet53_coco2017](.../demo/serving/serving/object_detection_yolov3_darknet53_coco2017)  
+* [目标检测-基于yolov3_darknet53_coco2017](../demo/serving/module_serving/object_detection_yolov3_darknet53_coco2017)  
 
   该示例展示了利用yolov3_darknet53_coco2017完成目标检测服务化部署和在线预测，获取检测结果和覆盖识别框的图片。