diff --git a/doc/design/kernel_hint_design.md b/doc/design/kernel_hint_design.md
index 75f0e4ea72779f9bf51048738a9af00a5e5600a5..da4856bb6a0ebdf289708469bd41a88031b8f34a 100644
--- a/doc/design/kernel_hint_design.md
+++ b/doc/design/kernel_hint_design.md
@@ -1,7 +1,7 @@
 ## Problem
-In PaddlePaddle's [Design](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/design/switch_kernel.md), one Operator may have multiple kernels. Users may have some personal preference to choose a certain type of kernel for an operator, such as `force_cpu` to use a CPU kernel, `use_cudnn` to choose a CUDNN kernel, we need to provide a way for a user to do this.
+In PaddlePaddle's [Design](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/design/switch_kernel.md), one Operator may have multiple kernels. Users may have some personal preference to choose a certain type of kernel for an operator, such as `force_cpu` to choose a CPU kernel, `use_cudnn` to choose a CUDNN kernel, we need to provide a way for users to do this.
 
-In the current design,  we use KernelType to describe one kernel.
+In the current design, we use KernelType to describe one kernel.
 
 ```cpp
 struct KernelType {
@@ -10,33 +10,33 @@ struct KernelType {
   LayoutType layout_;
 };
 ```
- `place_` `data_type_` and `layout_` can come from the input tensor of the operator, `GetActualKernelType(inputs)` use inputs to infer the proper kernel key that fit the incoming data, user can not config it.
+ `place_` `data_type_` and `layout_` can be got from the input tensors of the operator, `GetActualKernelType(inputs)` use inputs to infer the proper kernel key that fit the incoming data, but users can not directly configure it.
 
-The design also provides a virtual method `GetExpectedKernelType` that user can overload and choose the KernelType they want to use.
+The [design](https://github.com/PaddlePaddle/Paddle/blob/develop/doc/design/switch_kernel.md) also provides a virtual method `GetExpectedKernelType` that user can overload and use to choose the KernelType they want to use.
 
-so, we should send the information user defined in proto to `GetExpectedKernelType` for choosing a kernel.
+So we should send the information user defined in proto to `GetExpectedKernelType` for choosing a kernel.
 
 The problem is, how should we define and send the information for `GetExpectedKernelType` to use?
 
 ## Solution
 
-### potential choice
-1, Do nothing, let the user add the information they want to operator‘s attribute and get them inside `GetExpectedKernelType`, this can work right. But there is a little problem that users may define many kinds of hints for the same purpose, such as `force_cpu`, `use_cpu`, `CPU` for CPU kernel, and `use_cudnn`, `force_cudnn`, `cudnn_kernel` for use of CUDNN kernel.
+### Potential choice
+1. Do nothing, let the user add the information they want to operator‘s attribute and get them inside `GetExpectedKernelType`, this can work properly. But there is a little problem that users may define many kinds of hints for the same purpose, such as `force_cpu`, `use_cpu`, `cpu_kernel` to choose CPU kernel, and `use_cudnn`, `force_cudnn`, `cudnn_kernel` to choose CUDNN kernel.
 
-2, Pre-define all the needed option and use a single attr key such as `kernel_hint` for the user, this is not so flexible if the user wants to define some more kind of hint.
+2. Pre-define all the needed option and use a single attr key such as `kernel_hint` for the user, this is not so flexible if the user wants to define some more kind of hint.
 
-### final choice
-To provide enough flexibility while avoiding confusion definition, we can predefine some options, such as `force_cpu`, `use_cudnn`, `use_mkldnn` for a user to choose.
+### Final choice
+To provide enough flexibility while avoiding confusion definition, we can define some global constants for these attribute names, such as `force_cpu`, `use_cudnn`, `use_mkldnn` for a user to choose.
+
+In C++
 
 ```cpp
-const std::string kNonHint = "";
 const std::string kForceCPU = "force_cpu";
 const std::string kUseCUDNN = "use_cudnn";
 const std::string kUseMKLDNN = "use_mkldnn";
 
-KernelType GetExpectedKernelTyp() {
-    // "kernel_hint" is a user defined attribute name
-	if (Attr<std::string>("kernel_hint") == kForceCPU) {
+KernelType GetExpectedKernelType() {
+	if (Attr<bool>(kForceCPU)) {
 		return KernelType(CPUPlace, ...)
 	} else {
 		...
@@ -47,10 +47,11 @@ KernelType GetExpectedKernelTyp() {
 In Python code
 
 ```python
-def xx_layer(..., kernel_hint=None):
-	layer_helper = ...
-	layer_helper .append_op(
+FORCE_CPU = core.kForceCPU()
+
+def xx_layer(..., force_cpu=false):
+	layer_helper = LayerHelper(...)
+	layer_helper.append_op(
 		type="xx",
-		# "kernel_hint" should be the same with the attr name in CPP
-		attr={"kernel_hint": kernel_hint or ""})
+		attr={FORCE_CPU: force_cpu})
 ```