diff --git a/docs/api/api_python/ops/mindspore.ops.Custom.rst b/docs/api/api_python/ops/mindspore.ops.Custom.rst
index 63cd054e041..c8c794544b4 100644
--- a/docs/api/api_python/ops/mindspore.ops.Custom.rst
+++ b/docs/api/api_python/ops/mindspore.ops.Custom.rst
@@ -5,7 +5,7 @@ mindspore.ops.Custom
 
     `Custom` 算子是MindSpore自定义算子的统一接口。用户可以利用该接口自行定义MindSpore内置算子库尚未包含的算子。
     根据输入函数的不用，你可以创建多个自定义算子，并且把它们用在神经网络中。
-    关于自定义算子的详细说明和介绍，包括参数的正确书写，见编程指南 https://www.mindspore.cn/tutorials/experts/zh-CN/master/operation/op_custom.html 。
+    关于自定义算子的详细说明和介绍，包括参数的正确书写，见 `教程 <https://www.mindspore.cn/tutorials/experts/zh-CN/master/operation/op_custom.html>`_ 。
 
     .. warning::
         这是一个实验性接口，后续可能删除或修改。
diff --git a/docs/api/api_python/ops/mindspore.ops.func_scatter_div.rst b/docs/api/api_python/ops/mindspore.ops.func_scatter_div.rst
index 3bb126cb0de..e635085fc9d 100644
--- a/docs/api/api_python/ops/mindspore.ops.func_scatter_div.rst
+++ b/docs/api/api_python/ops/mindspore.ops.func_scatter_div.rst
@@ -17,7 +17,7 @@ mindspore.ops.scatter_div
         - **indices** (Tensor) - 指定相除操作的索引，数据类型必须为mindspore.int32或者mindspore.int64。
         - **updates** (Tensor) - 指定与 `input_x` 相除的Tensor，数据类型与 `input_x` 相同，shape为 `indices.shape + input_x.shape[1:]` 。
 
-    输出：
+    返回：
         Tensor，更新后的 `input_x` ，shape和类型与 `input_x` 相同。
 
     异常：
diff --git a/docs/api/api_python/ops/mindspore.ops.func_scatter_max.rst b/docs/api/api_python/ops/mindspore.ops.func_scatter_max.rst
index fcfec63bed2..e4987dc920e 100644
--- a/docs/api/api_python/ops/mindspore.ops.func_scatter_max.rst
+++ b/docs/api/api_python/ops/mindspore.ops.func_scatter_max.rst
@@ -18,7 +18,7 @@ mindspore.ops.scatter_max
         - **indices** (Tensor) - 指定最大值操作的索引，数据类型必须为mindspore.int32或者mindspore.int64。
         - **updates** (Tensor) - 指定与 `input_x` 取最大值操作的Tensor，数据类型与 `input_x` 相同，shape为 `indices.shape + input_x.shape[1:]` 。
 
-    输出：
+    返回：
         Tensor，更新后的 `input_x` ，shape和类型与 `input_x` 相同。
 
     异常：
diff --git a/docs/api/api_python/ops/mindspore.ops.func_scatter_min.rst b/docs/api/api_python/ops/mindspore.ops.func_scatter_min.rst
index bb76cb2aa4a..9d547d74ffb 100644
--- a/docs/api/api_python/ops/mindspore.ops.func_scatter_min.rst
+++ b/docs/api/api_python/ops/mindspore.ops.func_scatter_min.rst
@@ -18,7 +18,7 @@ mindspore.ops.scatter_min
         - **indices** (Tensor) - 指定最小值操作的索引，数据类型必须为mindspore.int32或者mindspore.int64。
         - **updates** (Tensor) - 指定与 `input_x` 取最小值操作的Tensor，数据类型与 `input_x` 相同，shape为 `indices.shape + input_x.shape[1:]` 。
 
-    输出：
+    返回：
         Tensor，更新后的 `input_x` ，shape和类型与 `input_x` 相同。
 
     异常：
diff --git a/mindspore/python/mindspore/ops/composite/array_ops.py b/mindspore/python/mindspore/ops/composite/array_ops.py
index a47cdc1e185..35dcb9bee27 100644
--- a/mindspore/python/mindspore/ops/composite/array_ops.py
+++ b/mindspore/python/mindspore/ops/composite/array_ops.py
@@ -65,7 +65,7 @@ def repeat_elements(x, rep, axis=0):
         rep (int): The number of times to repeat, must be positive.
         axis (int): The axis along which to repeat, default 0.
 
-    Outputs:
+    Returns:
         One tensor with values repeated along the specified axis. If x has shape
         (s1, s2, ..., sn) and axis is i, the output will have shape (s1, s2, ...,
         si * rep, ..., sn). The output type will be the same as the type of `x`.
@@ -142,7 +142,7 @@ def sequence_mask(lengths, maxlen=None):
         maxlen (int): size of the last dimension of returned tensor. Must be positive and same
             type as elements in `lengths`. Default is None.
 
-    Outputs:
+    Returns:
         One mask tensor of shape `lengths.shape + (maxlen,)` .
 
     Raises:
diff --git a/mindspore/python/mindspore/ops/composite/math_ops.py b/mindspore/python/mindspore/ops/composite/math_ops.py
index 1f588745bad..2e612726744 100644
--- a/mindspore/python/mindspore/ops/composite/math_ops.py
+++ b/mindspore/python/mindspore/ops/composite/math_ops.py
@@ -258,7 +258,7 @@ def tensor_dot(x1, x2, axes):
             automatically picks up last N dims from `a` input shape and first N dims from `b` input shape in order
             as axes for each respectively.
 
-    Outputs:
+    Returns:
         Tensor, the shape of the output tensor is :math:`(N + M)`. Where :math:`N` and :math:`M` are the free axes not
         contracted in both inputs
 
@@ -346,7 +346,7 @@ def dot(x1, x2):
         x2 (Tensor): Second tensor in Dot op with datatype float16 or float32,
             The rank must be greater than or equal to 2.
 
-    Outputs:
+    Returns:
         Tensor, dot product of x1 and x2.
 
     Raises:
@@ -559,7 +559,7 @@ def batch_dot(x1, x2, axes=None):
           `a` input shape and last N dimensions from `b` input shape in order as axes for each respectively.
           Default: None.
 
-    Outputs:
+    Returns:
         Tensor, batch dot product of `x1` and `x2`. For example: The Shape of output
         for input `x1` shapes (batch, d1, axes, d2) and `x2` shapes (batch, d3, axes, d4) is (batch, d1, d2, d3, d4),
         where d1 and d2 means any number.
@@ -779,7 +779,7 @@ def resize_nearest_neighbor(input_x, size, align_corners=False):
         align_corners (bool): Whether the centers of the 4 corner pixels of the input
                               and output tensors are aligned. Default: False.
 
-    Outputs:
+    Returns:
         Tensor, the shape of the output tensor is  :math:`(N, C, NEW\_H, NEW\_W)`.
         The data type is the same as the `input_x`.
 
diff --git a/mindspore/python/mindspore/ops/function/array_func.py b/mindspore/python/mindspore/ops/function/array_func.py
index 27b2877e26c..e17d832a982 100644
--- a/mindspore/python/mindspore/ops/function/array_func.py
+++ b/mindspore/python/mindspore/ops/function/array_func.py
@@ -1237,7 +1237,7 @@ def squeeze(input_x, axis=()):
             all the dimensions of size 1 in the given axis parameter. If specified, it must be int32 or int64.
             Default: (), an empty tuple.
 
-    Outputs:
+    Returns:
         Tensor, the shape of tensor is :math:`(x_1, x_2, ..., x_S)`.
 
     Raises:
@@ -1419,7 +1419,7 @@ def scatter_max(input_x, indices, updates):
         updates (Tensor): The tensor doing the max operation with `input_x`,
             the data type is same as `input_x`, the shape is `indices.shape + x.shape[1:]`.
 
-    Outputs:
+    Returns:
         Tensor, the updated `input_x`, the type and shape same as `input_x`.
 
     Raises:
@@ -1511,7 +1511,7 @@ def scatter_min(input_x, indices, updates):
         updates (Tensor): The tensor doing the min operation with `input_x`,
             the data type is same as `input_x`, the shape is `indices.shape + input_x.shape[1:]`.
 
-    Outputs:
+    Returns:
         Tensor, the updated `input_x`, has the same shape and type as `input_x`.
 
     Raises:
@@ -1566,7 +1566,7 @@ def scatter_div(input_x, indices, updates):
         updates (Tensor): The tensor doing the divide operation with `input_x`,
           the data type is same as `input_x`, the shape is `indices.shape + input_x.shape[1:]`.
 
-    Outputs:
+    Returns:
         Tensor, the updated `input_x`, has the same shape and type as `input_x`.
 
     Raises:
@@ -3487,7 +3487,7 @@ def index_fill(x, dim, index, value):
             a Tensor, it must be a 0-dimensional Tensor and has the same dtype as `x`. Otherwise,
             the `value` will be cast to a 0-dimensional Tensor with the same data type as `x`.
 
-    Outputs:
+    Returns:
         Tensor, has the same dtype and shape as input Tensor.
 
     Raises:
diff --git a/mindspore/python/mindspore/ops/function/math_func.py b/mindspore/python/mindspore/ops/function/math_func.py
index f3e04cea9c2..c0b6639373a 100644
--- a/mindspore/python/mindspore/ops/function/math_func.py
+++ b/mindspore/python/mindspore/ops/function/math_func.py
@@ -2123,7 +2123,7 @@ def linspace(start, stop, num):
         num (int): Number of ticks in the interval, inclusive of start and stop.
             Must be positive int number.
 
-    Outputs:
+    Returns:
         Tensor, has the same dtype as `start`, and the shape of :math:`(num)`
 
     Raises:
@@ -2380,7 +2380,7 @@ def ldexp(x, other):
         x (Tensor): The input tensor.
         other (Tensor): A tensor of exponents, typically integers.
 
-    Outputs:
+    Returns:
         out (Tensor, optional) : the output tensor.
 
     Raises:
@@ -2600,12 +2600,15 @@ def ge(x, y):
     r"""
     Computes the boolean value of :math:`x >= y` element-wise.
 
-    Inputs of `x` and `y` comply with the implicit type conversion rules to make the data types consistent.
-    The inputs must be two tensors or one tensor and one scalar.
-    When the inputs are two tensors,
-    dtypes of them cannot be bool at the same time, and the shapes of them could be broadcast.
-    When the inputs are one tensor and one scalar,
-    the scalar could only be a constant.
+    Note:
+        - Inputs of `x` and `y` comply with the implicit type conversion rules to make the data types consistent.
+        - The inputs must be two tensors or one tensor and one scalar.
+        - When the inputs are two tensors, dtypes of them cannot be bool at the same time,
+          and the shapes of them can be broadcast.
+        - When the inputs are one tensor and one scalar, the scalar could only be a constant.
+        - Broadcasting is supported.
+        - If the input Tensor can be broadcast, the low dimension will be extended to the corresponding high dimension
+          in another input by copying the value of the dimension.
 
     .. math::
 
@@ -2691,10 +2694,12 @@ def ne(x, y):
     r"""
     Computes the non-equivalence of two tensors element-wise.
 
-    Inputs of `x` and `y` comply with the implicit type conversion rules to make the data types consistent.
-    The inputs must be two tensors or one tensor and one scalar.
-    When the inputs are two tensors, the shapes of them could be broadcast.
-    When the inputs are one tensor and one scalar, the scalar could only be a constant.
+    Note:
+        - Inputs of `x` and `y` comply with the implicit type conversion rules to make the data types consistent.
+        - The inputs must be two tensors or one tensor and one scalar.
+        - When the inputs are two tensors, the shapes of them could be broadcast.
+        - When the inputs are one tensor and one scalar, the scalar could only be a constant.
+        - Broadcasting is supported.
 
     .. math::
 
@@ -2757,7 +2762,7 @@ def approximate_equal(x, y, tolerance=1e-5):
         y (Tensor): A tensor of the same type and shape as `x`.
         tolerance (float): The maximum deviation that two elements can be considered equal. Default: 1e-05.
 
-    Outputs:
+    Returns:
         Tensor, the shape is the same as the shape of `x`, and the data type is bool.
 
     Raises:
@@ -2964,13 +2969,15 @@ def maximum(x, y):
     """
     Computes the maximum of input tensors element-wise.
 
-    Inputs of `x` and `y` comply with the implicit type conversion rules to make the data types consistent.
-    The inputs must be two tensors or one tensor and one scalar.
-    When the inputs are two tensors,
-    dtypes of them cannot be bool at the same time, and the shapes of them could be broadcast.
-    When the inputs are one tensor and one scalar,
-    the scalar could only be a constant.
-    If one of the elements being compared is a NaN, then that element is returned.
+    Note:
+        - Inputs of `x` and `y` comply with the implicit type conversion rules to make the data types consistent.
+        - The inputs must be two tensors or one tensor and one scalar.
+        - When the inputs are two tensors,
+          dtypes of them cannot be bool at the same time, and the shapes of them could be broadcast.
+        - When the inputs are one tensor and one scalar,
+          the scalar could only be a constant.
+        - Broadcasting is supported.
+        - If one of the elements being compared is a NaN, then that element is returned.
 
     .. math::
         output_i = max(x_i, y_i)
@@ -3416,7 +3423,7 @@ def mv(mat, vec):
         mat (Tensor): Input matrix of the tensor. The shape of the tensor is :math:`(N, M)`.
         vec (Tensor): Input vector of the tensor. The shape of the tensor is :math:`(M,)`.
 
-    Outputs:
+    Returns:
         Tensor, the shape of the output tensor is :math:`(N,)`.
 
     Raises:
@@ -3478,7 +3485,7 @@ def addmv(x, mat, vec, beta=1, alpha=1):
         alpha (scalar[int, float, bool], optional): Multiplier for `mat` @ `vec` (α). The `alpha` must
             be int or float or bool, Default: 1.
 
-    Outputs:
+    Returns:
         Tensor, the shape of the output tensor is :math:`(N,)`, has the same dtype as `x`.
 
     Raises:
@@ -3838,7 +3845,7 @@ def deg2rad(x):
         x (Tensor[Number]): The input tensor. It must be a positive-definite matrix.
             With float16, float32 or float64 data type.
 
-    Outputs:
+    Returns:
         Tensor, has the same dtype as the `x`.
 
     Raises:
@@ -3876,7 +3883,7 @@ def rad2deg(x):
     Args:
         x (Tensor): The input tensor.
 
-    Outputs:
+    Returns:
         Tensor, has the same shape and dtype as the `x`.
 
     Raises:
@@ -4127,7 +4134,7 @@ def logsumexp(x, axis, keep_dims=False):
             If False, don't keep these dimensions.
             Default : False.
 
-    Outputs:
+    Returns:
         Tensor, has the same dtype as the `x`.
 
         - If axis is (), and keep_dims is False,
@@ -5020,7 +5027,7 @@ def log2(x):
     Args:
         x (Tensor): Input Tensor of any dimension. The value must be greater than 0.
 
-    Outputs:
+    Returns:
         Tensor, has the same shape and dtype as the `x`.
 
     Raises:
@@ -5195,7 +5202,7 @@ def log10(x):
     Args:
         x (Tensor): Input Tensor of any dimension. The value must be greater than 0.
 
-    Outputs:
+    Returns:
         Tensor, has the same shape and dtype as the `x`.
 
     Raises:
@@ -5474,9 +5481,9 @@ def remainder(x, y):
         y (Union[Tensor, numbers.Number, bool]): When the first input is a tensor, The second input
             could be a number, a bool or a tensor whose data type is number.
 
-    Outputs:
+    Returns:
         Tensor, the shape is the same as the one after broadcasting,
-            and the data type is the one with higher precision or higher digits among the two inputs.
+        and the data type is the one with higher precision or higher digits among the two inputs.
 
     Raises:
         TypeError: If neither `x` nor `y` is one of the following: Tensor, number, bool.
diff --git a/mindspore/python/mindspore/ops/function/nn_func.py b/mindspore/python/mindspore/ops/function/nn_func.py
index aae77e4abc4..70a433b71a6 100644
--- a/mindspore/python/mindspore/ops/function/nn_func.py
+++ b/mindspore/python/mindspore/ops/function/nn_func.py
@@ -843,7 +843,7 @@ def softsign(x):
         x (Tensor): Tensor of shape :math:`(N, *)`, where :math:`*` means, any number of
             additional dimensions, with float16 or float32 data type.
 
-    Outputs:
+    Returns:
         Tensor, with the same type and shape as the `x`.
 
     Raises:
@@ -921,7 +921,7 @@ def soft_shrink(x, lambd=0.5):
         x (Tensor): The input of soft shrink with data type of float16 or float32.
         lambd(float): The :math:`\lambda` must be no less than zero. Default: 0.5.
 
-    Outputs:
+    Returns:
         Tensor, has the same shape and data type as `x`.
 
     Raises:
@@ -1236,9 +1236,9 @@ def mirror_pad(input_x, paddings, mode):
     Pads the input tensor according to the paddings and mode.
 
     Args:
-        **input_x** (Tensor) - Tensor of shape :math:`(N, *)`, where :math:`*` means, any number of
+        input_x (Tensor): Tensor of shape :math:`(N, *)`, where :math:`*` means, any number of
           additional dimensions.
-        **paddings** (Tensor) - Paddings requires constant tensor. The value of `paddings` is a
+        paddings (Tensor): Paddings requires constant tensor. The value of `paddings` is a
           matrix(list), and its shape is (N, 2). N is the rank of input data. All elements of paddings
           are int type. For the input in the `D` th dimension, paddings[D, 0] indicates how many sizes
           to be extended ahead of the input tensor in the `D` th dimension, and paddings[D, 1]
@@ -1248,8 +1248,7 @@ def mirror_pad(input_x, paddings, mode):
         mode (str): Specifies the padding mode. The optional values are "REFLECT" and "SYMMETRIC".
             Default: "REFLECT".
 
-
-    Outputs:
+    Returns:
         Tensor, the tensor after padding.
 
         - If `mode` is "REFLECT", it uses a way of symmetrical copying through the axis of symmetry to fill in.
@@ -1366,7 +1365,6 @@ def cross_entropy(inputs, target, weight=None, ignore_index=-100, reduction='mea
         ``Ascend`` ``GPU`` ``CPU``
 
     Examples:
-
         >>> # Case 1: Indices labels
         >>> inputs = mindspore.Tensor(np.random.randn(3, 5), mindspore.float32)
         >>> target = mindspore.Tensor(np.array([1, 0, 4]), mindspore.int32)
@@ -1447,7 +1445,7 @@ def nll_loss(inputs, target, weight=None, ignore_index=-100, reduction='mean', l
         label_smoothing (float): Label smoothing values, a regularization tool used to prevent the model
             from overfitting when calculating Loss. The value range is [0.0, 1.0]. Default value: 0.0.
 
-    Outputs:
+    Returns:
         Tensor, the computed loss value.
 
     Supported Platforms:
@@ -1638,7 +1636,7 @@ def log_softmax(logits, axis=-1):
           additional dimensions, with float16 or float32 data type.
         axis (int): The axis to perform the Log softmax operation. Default: -1.
 
-    Outputs:
+    Returns:
         Tensor, with the same type and shape as the logits.
 
     Raises:
@@ -1845,7 +1843,7 @@ def grid_sample(input_x, grid, interpolation_mode='bilinear', padding_mode='zero
             to the corner points of the input’s corner pixels, making the sampling more resolution agnostic. Default:
             `False`.
 
-    Outputs:
+    Returns:
         Tensor, dtype is the same as `input_x` and whose shape is :math:`(N, C, H_{out}, W_{out})` (4-D) and
         :math:`(N, C, D_{out}, H_{out}, W_{out})` (5-D).