diff --git a/docs/source_en/help_seeking_path.md b/docs/source_en/help_seeking_path.md
new file mode 100644
index 0000000000000000000000000000000000000000..e57c6c84ac11fdae95976ae625f386400e1f122c
--- /dev/null
+++ b/docs/source_en/help_seeking_path.md
@@ -0,0 +1,34 @@
+# Seeking Help and Support
+
+This document describes how to seek help and support when you encounter problems in using MindSpore.
+
+<a href="https://gitee.com/mindspore/docs/blob/master/docs/source_en/help_seeking_path.md" target="_blank"><img src="./_static/logo_source.png"></a>
+
+The following flowchart shows the overall help-seeking process which starts from users encountering a problem in using MindSpore and ends with they finding a proper solution. Help-seeking methods are introduced based on the flowchart.
+
+![solution](./images/problem_solving_process.png)
+
+- Website search
+
+  - Go to the [official search page](https://www.mindspore.cn/search/en).
+  - When encountering a problem, search on the official website first, which is simple and efficient.
+  - Enter a keyword in the search box and click the search icon. The related content is displayed.
+  - Resolve the problem based on the search result.
+
+
+- User group consultation
+
+  - QQ user group number: 871543426.
+  - If you cannot solve the problem using the website search method and want a quick consultation, consult users in the QQ user group.
+  - After joining the group, discuss with other users. Technical experts in the group can also provide answers.
+  - Resolve the problem by asking experts or communicating with other users.
+
+
+- Forum Help-Seeking
+
+  - If you want a detailed solution, start a help post on the [MindSpore forum](https://bbs.huaweicloud.com/forum/forum-1076-1.html).
+  - To improve the speed and quality of problem solving, refer to [post suggestions](https://bbs.huaweicloud.com/forum/thread-69695-1-1.html) before posting.
+  - After the post is sent, a forum moderator collects the question and contacts technical experts to answer the question. The question will be resolved within three working days.
+  - Resolve the problem by referring to solutions provided by technical experts.
+  
+  If the expert test result shows that the MindSpore function needs to be improved, you are advised to submit an issue in the [MindSpore repository](https://gitee.com/mindspore). Issues will be resolved in later versions.
\ No newline at end of file
diff --git a/docs/source_en/images/problem_solving_process.png b/docs/source_en/images/problem_solving_process.png
new file mode 100644
index 0000000000000000000000000000000000000000..b2fc7a9668b07af46632977cb5478e68f98e0f51
Binary files /dev/null and b/docs/source_en/images/problem_solving_process.png differ
diff --git a/tutorials/notebook/README.md b/tutorials/notebook/README.md
index 7c7bf55d6b69e203b9a2d511560270c607f1fd32..4c4a4d2d1d11d1704e48f96a9701c6b6021d3d10 100644
--- a/tutorials/notebook/README.md
+++ b/tutorials/notebook/README.md
@@ -51,6 +51,7 @@
 | 教&nbsp;&nbsp;程&nbsp;&nbsp;名&nbsp;&nbsp;称                    | 文&nbsp;&nbsp;件&nbsp;&nbsp;名&nbsp;&nbsp;称       | 教&nbsp;&nbsp;程&nbsp;&nbsp;类&nbsp;&nbsp;别               |  内&nbsp;&nbsp;容&nbsp;&nbsp;描&nbsp;&nbsp;述
 | :-----------               | :-----------   | :-------              |:------   
 | 手写数字分类识别入门体验教程           |   [quick_start.ipynb](https://gitee.com/mindspore/docs/blob/master/tutorials/notebook/quick_start.ipynb)     |  快速入门                                       | - CPU平台下从数据集到模型验证的全过程解读 <br/> - 体验教程中各功能模块的使用说明 <br/> - 数据集图形化展示 <br/> - 了解LeNet5具体结构和参数作用 <br/> - 学习使用自定义回调函数 <br/> - loss值与训练步数的变化图 <br/> - 模型精度与训练步数的变化图 <br/> -  使用模型应用到手写图片的预测与分类上
+| 线性拟合         | [linear_regression.ipynb](https://gitee.com/mindspore/docs/blob/master/tutorials/notebook/linear_regression.ipynb)       | 快速入门           | - 了解线性拟合的算法原理<br/> - 了解在MindSpore中如何实现线性拟合的算法原理 <br/> - 学习使用MindSpore实现AI训练中的正向传播和方向传播<br/> - 可视化线性函数拟合数据的全过程。
 | 加载数据集        | [loading_dataset.ipynb](https://gitee.com/mindspore/docs/blob/master/tutorials/notebook/loading_dataset.ipynb)           | 使用指南               | - 学习MindSpore中加载数据集的方法 <br/> - 展示加载常用数据集的方法<br/> - 展示加载MindRecord格式数据集的方法<br/> - 展示加载自定义格式数据集的方法 
 | 将数据集转换为MindSpore数据格式        | [convert_dataset_to_mindspore_data_format.ipynb](https://gitee.com/mindspore/docs/blob/master/tutorials/notebook/convert_dataset_to_mindspore_data_format/convert_dataset_to_mindspore_data_format.ipynb)           | 使用指南               | - 展示将MNIST数据集转换为MindSpore数据格式 <br/> - 展示将CSV数据集转换为MindSpore数据格式 <br/> - 展示将CIFAR-10数据集转换为MindSpore数据格式 <br/> - 展示将CIFAR-100数据集转换为MindSpore数据格式 <br/> - 展示将ImageNet数据集转换为MindSpore数据格式 <br/> - 展示用户自定义生成MindSpore数据格式
 | 数据处理与数据增强      |  [data_loading_enhancement.ipynb](https://gitee.com/mindspore/docs/blob/master/tutorials/notebook/data_loading_enhance/data_loading_enhancement.ipynb)            | 使用指南             | - 学习MindSpore中数据处理和增强的方法 <br/> - 展示数据处理、增强方法的实际操作 <br/> - 对比展示数据处理前和处理后的效果<br/> - 表述在数据处理、增强后的意义
diff --git a/tutorials/source_zh_cn/quick_start/linear_regression.md b/tutorials/source_zh_cn/quick_start/linear_regression.md
index 148a3a01937afdd33b3f71a896257dc2985b8b96..4d8a29049d05b7bc054854e9d824b63e76aa98a0 100644
--- a/tutorials/source_zh_cn/quick_start/linear_regression.md
+++ b/tutorials/source_zh_cn/quick_start/linear_regression.md
@@ -40,6 +40,8 @@
 4. 定义线性拟合过程的可视化函数
 5. 执行训练
 
+本次样例源代码请参考：<https://gitee.com/mindspore/docs/blob/master/tutorials/tutorial_code/linear_regression.py>。
+
 ## 环境准备
 
 系统：Ubuntu18.04
@@ -103,6 +105,7 @@ plt.title("Eval_data")
 plt.show()
 ```
 
+输出结果：
 
 ![png](./images/linear_regression_eval_datasets.png)
 
@@ -126,6 +129,8 @@ net = nn.Dense(1,1,TruncatedNormal(0.02),TruncatedNormal(0.02))
 print("weight:", net.weight.default_input[0][0], "bias:", net.bias.default_input[0])
 ```
 
+输出结果：
+
     weight: -0.00034249047 bias: -0.019308656
     
 
@@ -143,6 +148,7 @@ plt.title("Eval data and net")
 plt.show()
 ```
 
+输出结果：
 
 ![png](./images/model_net_and_eval_datasets.png)
 
@@ -351,7 +357,7 @@ def plot_model_and_datasets(weight, bias, data_x, data_y):
 5. 图形展示模型函数和数据集。
 6. 清除本轮迭代的输出`display.clear_output`，起到动态可视化效果。
 
-迭代完成后，输出网络模型的权重值$w和b$。
+迭代完成后，输出网络模型的权重值$w$和$b$。
 
 
 ```python
@@ -375,6 +381,9 @@ plot_model_and_datasets(net.weight.default_input, net.bias.default_input, data_x
 print("weight:", net.weight.default_input[0][0], "bias:", net.bias.default_input[0])
 ```
 
+输出结果：
+
+
     loss_value: 0.42879593
     
 
diff --git a/tutorials/tutorial_code/linear_regression.py b/tutorials/tutorial_code/linear_regression.py
new file mode 100644
index 0000000000000000000000000000000000000000..952607a19d43e1ed0e739d8f606681ab65881d60
--- /dev/null
+++ b/tutorials/tutorial_code/linear_regression.py
@@ -0,0 +1,74 @@
+import numpy as np
+import mindspore as ms
+from mindspore.ops import composite as C
+from mindspore.ops import operations as P
+from mindspore import Tensor
+from mindspore import context
+from mindspore.common.initializer import TruncatedNormal
+from mindspore import nn
+ 
+context.set_context(mode=context.PYNATIVE_MODE, device_target="GPU")
+
+# Generating training data sets
+def get_data(num, w=2.0, b=3.0):
+    np_x = np.ones([num, 1])
+    np_y = np.ones([num, 1])
+    for i in range(num):
+        x  = np.random.uniform(-10.0, 10.0)
+        np_x[i] = x
+        noise = np.random.normal(0, 1)
+        y  = x * w + b + noise
+        np_y[i]=y
+    return Tensor(np_x,ms.float32), Tensor(np_y,ms.float32)
+
+# Define the form of loss function: 1/2 * (y - y')^2
+class MyLoss(nn.loss.loss._Loss):
+    def __init__(self, reduction='mean'):
+        super().__init__(reduction)
+        self.square = P.Square()
+    def construct(self, data, label):
+        x = self.square(data - label) * 0.5
+        return self.get_loss(x)
+
+# Gradient function
+class GradWrap(nn.Cell):
+    """ GradWrap definition """
+    def __init__(self, network):
+        super().__init__(auto_prefix=False)
+        self.network = network
+        self.weights = ms.ParameterTuple(filter(lambda x: x.requires_grad,
+            network.get_parameters()))
+
+    def construct(self, data, label):
+        weights = self.weights
+        return C.GradOperation('get_by_list', get_by_list=True) \
+            (self.network, weights)(data, label)
+
+# Initializing model functions
+net = nn.Dense(1, 1, TruncatedNormal(0.02), TruncatedNormal(0.02))
+
+# Loss function
+criterion = MyLoss()
+loss_opeartion = nn.WithLossCell(net, criterion)
+train_network = GradWrap(loss_opeartion) 
+train_network.set_train()
+
+# Defining optimization
+optim = nn.RMSProp(params=net.trainable_params(), learning_rate=0.02)
+
+# Executive Training
+step_size = 200
+batch_size = 16
+for i in range(step_size):
+    data_x, data_y = get_data(batch_size)
+    grads = train_network(data_x, data_y) 
+    optim(grads)   
+
+    # Print loss value per 10 step
+    if i%10 == 0:
+        output = net(data_x)
+        loss_output = criterion(output, data_y)
+        print(loss_output.asnumpy())
+
+# Print final weight parameters
+print("weight:", net.weight.default_input[0][0], "bias:", net.bias.default_input[0])
\ No newline at end of file