diff --git a/mindspore/lite/README.md b/mindspore/lite/README.md
index c756a7db07..fde5c6bcb9 100644
--- a/mindspore/lite/README.md
+++ b/mindspore/lite/README.md
@@ -1 +1,6 @@
-NNACL(neural network accelerated computing library) is a high performance library of neural network inference computing kernels for ARM.
+ＭｉｎｄＳｐｏｒｅ的设计目标
+１　端云一体化：ＩＲ统一，云侧训练模型可以在端侧重训；云侧混合精度训练与端侧混合精度推理协同提升推理性能；
+２　高性能与轻量化：高性能内核计算库ｎｎａｃｌ，支持ｓｌｉｄｅ　ｗｉｎｄｏｗ、ｉｍ２ｃｏｌ＋ｇｅｍｍ、ｗｉｎｏｇｒａｄｅ等多种卷积算法，深度汇编指令优化；在线运行模块不依赖第三方库，保持框架的轻量化；
+３　快捷部署：支持ＴｅｎｓｏｒＦｌｏｗ　Ｌｉｔｅ、Ｃａｆｆｅ、ＯＮＮＸ等多种格式的模型转换；提供量化、图片数据处理等功能，便利用户部署；
+４　全场景覆盖：　Ｌｉｔｅ　＆　Ｍｉｃｒｏ覆盖手机、ＩｏＴ等各种智能设备
+　
\ No newline at end of file
diff --git a/mindspore/lite/nnacl/README.md b/mindspore/lite/nnacl/README.md
new file mode 100644
index 0000000000..c756a7db07
--- /dev/null
+++ b/mindspore/lite/nnacl/README.md
@@ -0,0 +1 @@
+NNACL(neural network accelerated computing library) is a high performance library of neural network inference computing kernels for ARM.