Platform For AI:Usage notes on multimedia analysis SDK for Python

The environment relies on Python 3 or later. Run the following command to install multimedia analysis SDK for Python:

wget https://ai-service-data.oss-cn-beijing.aliyuncs.com/python-sdk/ai_service_python_sdk-1.1.4-py3-none-any.whl
pip install ai_service_python_sdk-1.1.4-py3-none-any.whl

Run the following command to initialize the environment:

from ai_service_python_sdk.client.api_client import ApiClient
client = ApiClient('<HOST>', '<YOUR-APPID>', '<YOUR-TOKEN>')

Modify the following parameters based on your business requirements.

You can evaluate the quality of an image. The model service returns a floating-point number from 0 to 100. The following code block provides a sample request:

from ai_service_python_sdk.client.api.ai_service_image_api import AiServiceImageApi

# The URL of the image. 
image_url = 'https://your_image_url.jpg'
ai_service_api = AiServiceImageApi(client)
# The name of the custom model. 
model_name = ''
# The response settings of the model. If the mode does not have response parameters, you can specify an empty dictionary. 
configure = {}
# The model service that you want to call. 
response = ai_service_api.image_qa(image_url, model_name, configure)
# The ID of the request. 
request_id = response.request_id
# The status of the request. 
code = response.code
# The detailed status information about the request. 
message = response.message
# The return value. 
data = response.data
# Display the return value. 
print(response)

The following table describes the parameters in the preceding statement.

The following command output is returned:

{
    "code":"OK",
    "data":{
        "image_height":214,
        "image_width":398,
        "iqa_result":66.88
    },
    "message":"success",
    "request_id":"1d4572a1-2800-4213-9e9c-33f9fa7e****"
}

The following table describes the response parameters.

You can obtain the generated face-related attributes, such as the face shape, hair color, hairstyle, and appearance. The following code block shows a sample request:

from ai_service_python_sdk.client.api.ai_service_image_api import AiServiceImageApi

# The URL of the image. 
image_url = 'https://your_image_url.jpg'
ai_service_api = AiServiceImageApi(client)
# The name of the custom model. 
model_name = ''
# The response settings of the model. If the mode does not have response parameters, you can specify an empty dictionary. 
configure = {}
# The model service to be called. 
response = ai_service_api.face_attr_image(image_url, model_name, configure)
# The ID of the request. 
request_id = response.request_id
# The status of the request. 
code = response.code
# The detailed status information about the request. 
message = response.message
# The return value. 
data = response.data
# Display the return value. 
print(response)

The following table describes the parameters in the preceding statement.

The following result is returned:

{'code': 'OK',
 'data': {'attr': [{'FaceShape': {'Triangular': 0.0013,
                                  'Round': 0.0147,
                                  'Heart': 0.0405,
                                  'Square': 0.0001,
                                  'Oval': 0.9266,
                                  'Diamond': 0.0027,
                                  'Oblong': 0.0141},
                    'FemaleHairStyle': {'BangsType': {'Curtain bangs': 0.5932,
                                                      'Braided bangs': 0.0058,
                                                      'Side-swept bangs': 0.0575,
                                                      'No bangs': 0.3078,
                                                      'See-through bangs': 0.0143,
                                                      'Blunt bangs': 0.0213},
                                        'FemaleCurlyHairType': {'Flow perm': 0.1289,
                                                                'Big wavy curl': 0.2526,
                                                                'Small curls': 0.084,
                                                                'Smooth curls': 0.2027,
                                                                'Air wave perm': 0.1434,
                                                                'Jelly perm': 0.1539,
                                                                'Cone curls': 0.0345},
                                        'FemaleHairType': {'Curly hair': 0.1941,
                                                           'Bun': 0.0112,
                                                           'Straight hair': 0.7947},
                                        FemaleLongShortHair hair ': {' Medium-length': 0.2807,
                                                                'Short hair': 0.0346,
                                                                'Long hair': 0.6846},
                                        'Tied hair': 0.3054,
                                        "Braided hair": 0.3453},
                    'HairColor': {'Others': 0.0001,
                                  'Coffee brown': 0,
                                  'Granny gray': 0,
                                  'Chestnut': 0.0025,
                                  'Brown': 0.0622,
                                  'Gradient': 0.0004,
                                  'Claret': 0.0001,
                                  'Blonde': 0,
                                  'Buff': 0,
                                  'Black': 0.9347},
                    'MaleHairStyle': {'Curtains': 0.9939,
                                      'Buzz cut': 0,
                                      'Bullet': 0.0033,
                                      'Crew cut': 0,
                                      'Induction buzz cut': 0.001,
                                      'Disconnected buzz cut': 0.0008,
                                      'Disconnected bob': 0,
                                      'Slicked back': 0.0001,
                                      'Mohawk': 0.0006},
                    'bbox': [91, 0, 430, 452],
                    'face_score': 3.2431,
                    'index': 0}]},
 'message': 'success',
 'request_id': '9b2f2c0e-d2c0-45f8-b922-058d00edc9ad'}

The following table describes the response parameters.

You can add multiple labels to an image. The model service can return top K labels with the highest probabilities and the probability of each label. The model service can also return high-dimensional features of the image. The following code block shows a sample request:

from ai_service_python_sdk.client.api.ai_service_image_api import AiServiceImageApi

# The URL of the image. 
image_url = 'https://your_image_url.jpg'
ai_service_api = AiServiceImageApi(client)
# The name of the custom model. 
model_name = ''
# The response settings of the model. 
configure = {'tag_top_k': 5, 'output_embedding': False}
# The model service to be called. 
response = ai_service_api.multi_label_image_v2(image_url, model_name, configure)
# The ID of the request. 
request_id = response.request_id
# The status of the request. 
code = response.code
# The detailed status information about the request. 
message = response.message
# The return value. 
data = response.data
# Display the return value. 
print(response)

The following table describes the parameters in the preceding statement.

The following command output is returned:

{'code': 'OK',
 'data': {'image_height': 510,
          'image_width': 516,
          'tag_result': [{'score': 0.505, 'tag': 'Smiling face'},
                         {'score': 0.493, 'tag': 'Lady'},
                         {'score': 0.475, 'tag': 'Beauty'},
                         {'score': 0.438, 'tag': 'Smile'},
                         {'score': 0.432, 'tag': 'Honey tea brown'}]},
 'message': 'success',
 'request_id': 'c9e5aa33-4d8d-49ce-8991-bcbb5f12e43b'}

The following table describes the response parameters.

You can evaluate the quality of a video. The model service returns a floating-point number from 0 to 100. You can use one of the following methods to call the model service:

• Classify a single video. The following code block shows a sample request:

  from ai_service_python_sdk.client.api.ai_service_video_api import AiServiceVideoApi
  
  video_url = 'https://your_video_url.mp4'
  ai_service_api = AiServiceVideoApi(client)
  # The name of the custom model. 
  model_name = ''
  # The title of the video. 
  video_title = ''
  # The response settings of the model. 
  configure = {}
  # The model service to be called. 
  response = ai_service_api.video_qa(video_url, model_name, video_title, configure)
  # The ID of the request. 
  request_id = response.request_id
  # The status of the request. 
  code = response.code
  # The detailed status information about the request. 
  message = response.message
  # The content returned by the model service. 
  data = response.data
  # The ID of the job. 
  job_id = response.data['job_id']
  # Display the return value. 
  print(response)

  The following table describes the parameters in the preceding statement.

  Parameter	Data type	Required	Description
  video_url	STRING	Yes	The URL of the video. We recommend that the size of the video is no larger than 100 MB and the resolution of the video is equal to or higher than 320 × 240.
  video_title	STRING	Yes	The title of the video. Specify an empty string because the model service does not require you to specify a video title.
  model_name	STRING	Yes	By default, an empty string is specified to call a general-purpose model. If the general-purpose model cannot meet your business requirements, contact your account manager to obtain a custom model. You can specify the name of a custom model to call the custom model.
  configure	Dict	Yes	The response settings of the model. Specify an empty dictionary for the model service.

  The following command output is returned:

  {'code': 'OK',
   'data': {'job_id': 10**},
   'message': 'success',
   'request_id': '228235a6-db4f-466a-b20b-a4453f81****'}

  Obtain job_id from the preceding returned response and specify the job ID in the following code to query the result.

  from ai_service_python_sdk.client.api.ai_service_job_api import AiServiceJobApi
  
  ai_service_job_api = AiServiceJobApi(client)
  # Query the result. 
  result = ai_service_job_api.get_async_job(<YOUR-JOB-ID>)
  # Display the return value. 
  print(result)

  Replace <YOUR-JOB-ID> with the value of job_id returned by the model service, which is of the INT type.

  • The following result is returned if the job is running:

    {'code': 'OK',
     'data': {'job': {'Result': '',
                      'app_id': '202209070402410****',
                      'create_time': '2022-09-07T14:03:33.8+08:00',
                      'id': 1012,
                      'message': 'video downloading',
                      'state': 1}},
     'message': 'success',
     'request_id': '5259ec57-e55c-4772-b01e-3deafd74****'}

  • The following result is returned if the job is completed:

    {'code': 'OK',
     'data': {'job': {'Result': '{"avg_fps":30,"duration":14,"height":1920,"single_img":0.74072265625,"video_score":20.57750291278764,"width":1080}',
                      'app_id': '202209290847310****',
                      'create_time': '2022-10-12T10:51:30.015+08:00',
                      'id': 1012,
                      'message': 'success',
                      'state': 2}},
     'message': 'success',
     'request_id': '0b4f658f-cd96-4606-8d81-d2fe0a6d****'}

  The following table describes the response parameters.

  Parameter	Data type	Description
  request_id	STRING	The request ID, which is of the STRING type.
  code	STRING	The request status code, which is of the STRING type.
  message	STRING	The detailed status information about the request, which is of the STRING type. Sample command output: success Invalid Input - video data error - load video failed Invalid Input - json format error - json parse runtime exception For more information, see Error codes.
  data	Dict	The content returned by the model service, which is of the DICT type. For more information about the response parameters, see Data parameters.

  Table 4. Data parameters

  Parameter	Description
  id	The ID of the job (job_id), which is of the INT type.
  app_id	The AppId, which is of the INT type.
  state	The status code of the job, which is of the INT type. Valid values: 0: The job is initializing. 1: The job is running. 2: The job is completed. 3: The job failed.
  message	The execution information of the job, which is of the STRING type. Valid values: success video downloading
  create_time	The time when the job was created, which is of the STRING type.
  Result	The result returned by the model service, which is of the STRING type. For more information, see Result parameters.

  Table 5. Result parameters

  Parameter	Description
  video_score	The quality score of the video, which is of the FLOAT type. Valid values: 0 to 100.
  avg_fps	The average frame rate of the video, which is of the INT type.
  duration	The duration of the video, which is of the INT type. Unit: seconds.
  single_img	The difference between the images in the video, which is of the FLOAT type. Valid values: 0 to 1. A smaller value indicates a smaller difference. This means that the video is generated based on static images.
  height	The height of the video in pixels, which is of the INT type.
  width	The width of the video in pixels, which is of the INT type.

• Evaluate the quality of multiple videos in a batch. The following code block shows a sample request:

  from ai_service_python_sdk.client.api.ai_service_video_api import AiServiceVideoApi
  from ai_service_python_sdk.client.models.batch_video_request_videos import BatchVideoRequestVideos
  
  ai_service_api = AiServiceVideoApi(client)
  
  # Create a batch processing request (video URL + video title). 
  videos = [
      BatchVideoRequestVideos('https://your_video_1_url.mp4', ''),
      BatchVideoRequestVideos('https://your_video_2_url.mp4', '')
      ]
  # The name of the custom model. 
  model_name = ''
  # The response settings of the model. 
  configure = {}
  # The model service to be called. 
  response = ai_service_api.batch_video_qa(videos, model_name, configure)
  # The ID of the request. 
  request_id = response.request_id
  # The status of the request. 
  code = response.code
  # The detailed status information about the request. 
  message = response.message
  # The content returned by the model service. 
  data = response.data
  # The ID of the batch job. 
  batch_id = response.data['batch_id']
  # Display the return value. 
  print(response)

  The following command output is returned:

  {'code': 'OK',
   'data': {'batch_id': 14},
   'message': 'success',
   'request_id': '6d5ef1b5-c01f-4e63-9eec-150ddde9****'}

  Obtain batch_id from the preceding returned response and use the batch ID in the following code to query the result:

  from ai_service_python_sdk.client.api.ai_service_job_api import AiServiceJobApi
  
  ai_service_job_api = AiServiceJobApi(client)
  # Query the result. 
  result = ai_service_job_api.get_batch_job_with_id(<YOUR-BATCH-ID>)
  # Display the return value. 
  print(result)

  Replace <YOUR-BATCH-ID> with the value of batch_id returned by the model service, which is of the INT type.

  The following result is returned:

  {'code': 'OK',
   'data': {'jobs': [{'Result': '{"avg_fps":30,"duration":14.633333333333333,"height":1280,"single_img":0.486328125,"video_score":55.3773279862801,"width":720}',
                      'app_id': '202209290847310****',
                      'batch_id': 14,
                      'create_time': '2022-10-26T19:44:47.501+08:00',
                      'id': 44**,
                      'message': 'success',
                      'object': 'https://your_video_1_url.mp4',
                      'state': 2},
                     {'Result': '{"avg_fps":30,"duration":18.2,"height":568,"single_img":0.5791015625,"video_score":67.21071975649835,"width":320}',
                      'app_id': '202209290847310****',
                      'batch_id': 14,
                      'create_time': '2022-10-26T19:44:47.501+08:00',
                      'id': 4484,
                      'message': 'success',
                      'object': 'https://your_video_2_url.mp4',
                      'state': 2}]},
   'message': 'success',
   'request_id': 'e99697ff-7d42-4c0a-a0a0-c6a0c0ba****'}

  The data['jobs'] parameter returned by the batch job is an array. The following table describes the parameters in the array.

  Parameter	Description
  id	The ID of the data entry in the batch job, which is of the INT type.
  batch_id	The ID of the batch job, which is of the INT type.
  app_id	The AppId, which is of the INT type.
  state	The status code of the job, which is of the INT type. Valid values: 0: The job is initializing. 1: The job is running. 2: The job is completed. 3: The job failed.
  message	The execution information of the job, which is of the STRING type. Valid values: success video downloading
  create_time	The time when the job was created, which is of the STRING type.
  object	The URL of the video, which is of the STRING type.
  Result	The result returned by the model service, which is of the STRING type. Note The Result parameters are the same as the Result parameters returned by the model service that is used to evaluate the quality of a single video.

You can classify short videos by adding labels to the videos. The mode service can return the class of the videos, the top K labels with the highest probabilities, and the probability of each label. The model service can also return the high-dimensional features of the videos. You can use one of the following methods to classify videos:

• Classify a single video. The following code block shows a sample request:

  from ai_service_python_sdk.client.api.ai_service_video_api import AiServiceVideoApi
  
  video_url = 'https://your_video_url.mp4'
  ai_service_api = AiServiceVideoApi(client)
  # The name of the custom model. 
  model_name = ''
  # The title of the video. 
  video_title = 'your_video_title'
  # The response settings of the model. 
  configure = {
      'output_classification': True,
      'classification_top_k': 1,
      'output_tag': True,
      'tag_top_k': 5,
      'output_embedding': True
      }
  # The model service to be called. 
  response = ai_service_api.classify_label_video(video_url, video_title, model_name, configure)
  # The ID of the request. 
  request_id = response.request_id
  # The status of the request. 
  code = response.code
  # The detailed status information about the request. 
  message = response.message
  # The content returned by the model service. 
  data = response.data
  # The ID of the job. 
  job_id = response.data['job_id']
  # Display the return value. 
  print(response)

  The following table describes the parameters in the preceding statement.

  Parameter	Data type	Required	Description
  video_url	STRING	Yes	The URL of the video. We recommend that the size of the video is no larger than 100 MB and the resolution of the video is equal to or higher than 320 × 240.
  video_title	STRING	Yes	The title of the video. If the video does not have a title, specify an empty string.
  model_name	STRING	Yes	By default, an empty string is specified to indicate a general-purpose model. If the general-purpose model cannot meet your requirements, you can contact the technical support of PAI to obtain a custom model. You can specify the name of a custom model to call the custom model.
  configure	Dict	Yes	The response settings of the model. The default value is None. For more information, see Configure parameters. Note If configure is set to None, the parameters in the configure list use the default settings.

  Table 6. Configure parameters

  Parameter	Data type	Required	Description
  output_classification	BOOL	No	Specify whether to return the video classification result. Valid values: True (default) False
  classification_top_k	INT	No	The top K classes of the video. Valid values of K: 1 to 10. Default value: 1.
  output_tag	BOOL	No	Specify whether to return the labels of the video. Valid values: True (default) False
  tag_top_k	INT	No	The top K labels of the video. Valid values of K: 1 to 10. Default value: 5.
  output_embedding	BOOL	No	Specify whether to return the 64-dimensional video embedding. Valid values: True (default) False

  The following command output is returned:

  {'code': 'OK',
   'data': {'job_id': 5},
   'message': 'success',
   'request_id': '4f6caecb-e3d6-4997-89fe-26ac7536****'}

  Obtain job_id from the preceding returned response and specify the job ID in the following code to query the result.

  from ai_service_python_sdk.client.api.ai_service_job_api import AiServiceJobApi
  
  ai_service_job_api = AiServiceJobApi(client)
  # Query the result. 
  result = ai_service_job_api.get_async_job(<YOUR-JOB-ID>)
  # Display the return value. 
  print(result)

  Replace <YOUR-JOB-ID> with the value of job_id returned by the model service, which is of the INT type.

  • The following result is returned if the job is running:

    {'code': 'OK',
     'data': {'job': {'Result': '',
                      'app_id': '202209070402410****',
                      'create_time': '2022-09-07T14:03:33.8+08:00',
                      'id': 5,
                      'message': 'video downloading',
                      'state': 1}},
     'message': 'success',
     'request_id': '5259ec57-e55c-4772-b01e-3deafd74****'}
    

  • The following result is returned if the job is completed:

    {'code': 'OK',
     'data': {'job': {'Result':
        '{"classification_result":[
            {"class":"three rural issues","score":0.997}
            ],
        "duration":14.633333333333333,
        "embedding_result":"-0.162,0.483,0.881,0.686,0.319,-1.569,0.266,0.227,-1.352,1.157,-0.784,-1.016,-0.987,-1.214,-0.493,-1.182,0.85,1.473,-1.27,-3.391,3.394,-0.471,-0.434,0.256,2.146,0.787,0.348,1.67,0.229,-0.878,0.299,0.392,-2.161,-0.756,-3.438,-0.158,0.713,-5.812,-1.248,0.253,-1.111,-0.165,2.644,-2.368,-1.636,-0.533,0.468,1.2,-1.431,-1.151,-1.276,-1.954,1.167,-0.938,-0.111,-2.636,-1.248,4.662,1.892,5.485,-1.137,1.589,-1.935,1.018",
        "tag_result":[
            {"score":0.728,"tag":"potted plants"},
            {"score":0.576,"tag":"plants"},
            {"score":0.539,"tag":"planting techniques"},
            {"score":0.466,"tag":"agricultural technology"},
            {"score":0.458,"tag":"planting"}
            ],
        "video_height":1280,
        "video_width":720}\n',
      'app_id': '202209070402410****',
      'create_time': '2022-09-07T14:03:33.8+08:00',
      'id': 5,
      'message': 'success',
      'state': 2}},
     'message': 'success',
     'request_id': '9283066a-f414-40fd-8fd3-0f77c1ef****'}

  The following table describes the response parameters.

  Parameter	Description
  request_id	The request ID, which is of the STRING type.
  code	The request status code, which is of the STRING type.
  message	The detailed status information about the request, which is of the STRING type. Sample command output: success Invalid Input - video data error - load video failed Invalid Input - json format error - json parse runtime exception For more information, see Error codes.
  data	The content returned by the model service, which is of the DICT type. For more information, see Data ['job'] parameters.

  Table 7. Data ['job'] parameters

  Parameter	Description
  id	The ID of the job (job_id), which is of the INT type.
  app_id	The AppId, which is of the INT type.
  state	The status code of the job, which is of the INT type. Valid values: 0: The job is initializing. 1: The job is running. 2: The job is completed. 3: The job failed.
  message	The execution information of the job, which is of the STRING type. Valid values: success video downloading
  create_time	The time when the job was created, which is of the STRING type.
  Result	The result returned by the model service, which is of the STRING type. For more information, see Result parameters.

  Table 8. Result parameters

  Parameter	Description
  classification_result	The classification result, which is of the LIST type. The classes are sorted in descending order by score (probability). The length of the list varies based on classification_top_k. This parameter is returned only when output_classification is set to True.
  tag_result	The labels of the video, which are sorted in descending order by score (probability). The length of the list varies based on tag_top_k. This parameter is returned only when output_tag is set to True.
  score	The probability of the label, which is of the FLOAT type. The value is accurate to three decimal places.
  class	The alias of the class, which is of the STRING type.
  tag	The name of the label, which is of the STRING type.
  embedding_result	The 64-dimensional features of the video, which are of the STRING type. The features are separated by commas (,). This parameter is returned only when output_embedding is set to True.
  video_height	The height of the video in pixels, which is of the INT type.
  video_width	The width of the video in pixels, which is of the INT type.
  duration	The duration of the video, which is of the FLOAT type.

• Classify multiple videos in a batch. The following code shows a sample request:

  from ai_service_python_sdk.client.api.ai_service_video_api import AiServiceVideoApi
  from ai_service_python_sdk.client.models.batch_video_request_videos import BatchVideoRequestVideos
  
  ai_service_api = AiServiceVideoApi(client)
  
  # The response settings of the model. 
  configure = {
      'output_classification': True,
      'classification_top_k': 1,
      'output_tag': True,
      'tag_top_k': 5,
      'output_embedding': True
      }
  # Create a batch processing request (video URL + video title). 
  videos = [
      BatchVideoRequestVideos('https://your_video_1_url.mp4', 'your_video_title_1'),
      BatchVideoRequestVideos('https://your_video_2_url.mp4', 'your_video_title_2')
      ]
  # The name of the custom model. 
  model_name = ''
  # The model service to be called. 
  response = ai_service_api.batch_classify_label_video(videos, model_name, configure)
  # The ID of the request. 
  request_id = response.request_id
  # The status of the request. 
  code = response.code
  # The detailed status information about the request. 
  message = response.message
  # The content returned by the model service. 
  data = response.data
  # batch id
  batch_id = response.data['batch_id']
  # Display the return value. 
  print(response)

  The following command output is returned:

  {'code': 'OK',
   'data': {'batch_id': 1},
   'message': 'success',
   'request_id': 'c59eb912-9df4-4afe-8129-23f7b6dc****'}

  Obtain batch_id from the preceding returned response and use the batch ID in the following code to query the result:

  from ai_service_python_sdk.client.api.ai_service_job_api import AiServiceJobApi
  
  ai_service_job_api = AiServiceJobApi(client)
  # Query the result. 
  result = ai_service_job_api.get_batch_job_with_id(<YOUR-BATCH-ID>)
  # Display the return value. 
  print(result)

  Replace <YOUR-BATCH-ID> with the value of batch_id returned by the model service, which is of the INT type.

  The following result is returned:

  {'code': 'OK',
   'data': {'jobs': [{'Result': '{"classification_result":[{"class":"daily life","score":0.998}],"duration":14.633333333333333,"embedding_result":"0.998,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.002","tag_result":[{"score":0.917,"tag":"potted plants"},{"score":0.777,"tag":"plants"},{"score":0.693,"tag":"gardening"},{"score":0.58,"tag":"happy trees"},{"score":0.509,"tag":"titles"}],"video_height":1280,"video_width":720}',
                      'app_id': '202209290847310****',
                      'batch_id': 13,
                      'create_time': '2022-10-26T18:13:20.928+08:00',
                      'id': 4090,
                      'message': 'success',
                      'object': 'https://your_video_1_url.mp4',
                      'state': 2},
                     {'Result': '{"classification_result":[{"class":"sports","score":0.998}],"duration":18.2,"embedding_result":"0.0,0.0,0.0,0.998,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.001,0.0,0.0,0.0,0.0,0.001,0.0,0.0,0.0,0.0","tag_result":[{"score":0.981,"tag":"National Games"},{"score":0.901,"tag":"table tennis"},{"score":0.798,"tag":"sports"},{"score":0.583,"tag":"title"},{"score":0.498,"tag":"table tennis games"}],"video_height":568,"video_width":320}',
                      'app_id': '202209290847310****',
                      'batch_id': 13,
                      'create_time': '2022-10-26T18:13:20.928+08:00',
                      'id': 4091,
                      'message': 'success',
                      'object': 'https://your_video_2_url.mp4',
                      'state': 2}]},
   'message': 'success',
   'request_id': '73e4b48e-42b8-4347-9cb4-7a49c1f8****'}

  The data['jobs'] parameter returned by the batch job is an array. The following table describes the parameters in the array.

  Parameter	Description
  id	The ID of the data entry in the batch job, which is of the INT type.
  batch_id	The ID of the batch job, which is of the INT type.
  app_id	The AppId, which is of the INT type.
  state	The status code of the job, which is of the INT type. Valid values: 0: The job is initializing. 1: The job is running. 2: The job is completed. 3: The job failed.
  message	The execution information of the job, which is of the STRING type. Valid values: success video downloading
  create_time	The time when the job was created, which is of the STRING type.
  object	The URL of the video, which is of the STRING type.
  Result	The result returned by the model service, which is of the STRING type. Note The Result parameters are the same as the Result parameters returned by the model service that is used to evaluate the quality of a single video.

Request errors