fix serving link (#994)

* fix serving link, test=document_fix

* fix link

README_ch.md

@@ -84,7 +84,7 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
     - [基于pip安装whl包快速推理](./doc/doc_ch/whl.md)
     - [基于Python脚本预测引擎推理](./doc/doc_ch/inference.md)
     - [基于C++预测引擎推理](./deploy/cpp_infer/readme.md)
-    - [服务化部署](./deploy/hubserving/readme.md)
+    - [服务化部署](./doc/doc_ch/serving_inference.md)
     - [端侧部署](./deploy/lite/readme.md)
     - [模型量化](./deploy/slim/quantization/README.md)
     - [模型裁剪](./deploy/slim/prune/README.md)

doc/doc_ch/quickstart.md

@@ -95,5 +95,5 @@ python3 tools/infer/predict_system.py --image_dir="./doc/imgs/11.jpg" --det_mode
 
 此外，文档教程中也提供了中文OCR模型的其他预测部署方式：
 - [基于C++预测引擎推理](../../deploy/cpp_infer/readme.md)
-- [服务部署](../../deploy/pdserving/readme.md)
+- [服务部署](./serving_inference.md)
 - [端侧部署](../../deploy/lite/readme.md)

doc/doc_en/quickstart_en.md

@@ -98,5 +98,5 @@ For more text detection and recognition tandem reasoning, please refer to the do
 
 In addition, the tutorial also provides other deployment methods for the Chinese OCR model:
 - [Server-side C++ inference](../../deploy/cpp_infer/readme_en.md)
-- [Service deployment](../../deploy/pdserving/readme_en.md)
+- [Service deployment](../../deploy/hubserving/readme_en.md)
 - [End-to-end deployment](../../deploy/lite/readme_en.md)