Use GetMediaAuditResult to query automated media audit results - ApsaraVideo VOD - Alibaba Cloud - ApsaraVideo VOD

Retrieves the summary of automated review results.

Operation description

Usage notes

This operation is supported only in the Singapore region.

QPS limit

You can call this operation up to 20 times per second per account. If the number of calls per second exceeds the limit, throttling is triggered. This may affect your business. For more information, see QPS limit.

Try it now

Try this API in OpenAPI Explorer, no manual signing needed. Successful calls auto-generate SDK code matching your parameters. Download it with built-in credential security for local usage.

Test

RAM authorization

The table below describes the authorization required to call this API. You can define it in a Resource Access Management (RAM) policy. The table's columns are detailed below:

Action: The actions can be used in the Action element of RAM permission policy statements to grant permissions to perform the operation.
API: The API that you can call to perform the action.
Access level: The predefined level of access granted for each API. Valid values: create, list, get, update, and delete.
Resource type: The type of the resource that supports authorization to perform the action. It indicates if the action supports resource-level permission. The specified resource must be compatible with the action. Otherwise, the policy will be ineffective.
- For APIs with resource-level permissions, required resource types are marked with an asterisk (*). Specify the corresponding Alibaba Cloud Resource Name (ARN) in the Resource element of the policy.
- For APIs without resource-level permissions, it is shown as All Resources. Use an asterisk (*) in the Resource element of the policy.
Condition key: The condition keys defined by the service. The key allows for granular control, applying to either actions alone or actions associated with specific resources. In addition to service-specific condition keys, Alibaba Cloud provides a set of common condition keys applicable across all RAM-supported services.
Dependent action: The dependent actions required to run the action. To complete the action, the RAM user or the RAM role must have the permissions to perform all dependent actions.

Action

Access level

Resource type

Condition key

Dependent action

vod:GetMediaAuditResult

get

*All Resource

*

None

Request parameters

Parameter	Type	Required	Description	Example
MediaId	string	Yes	The ID of the video or image to query.	93ab850b4f6f*****54b6e91d24d81d4

Response elements

Element	Type	Description	Example
	object	The response data.
RequestId	string	The request ID.	CB7D7232-1AB2-40FE-B8D5-****
MediaAuditResult	object	The content moderation result.
Suggestion	string	The recommended action based on the moderation result. Valid values: block: Blocked. review: Needs manual review. pass: Passed.	pass
AbnormalModules	string	The content types that contain violations. Multiple values are separated by commas (,). Valid values: video: video. image-cover: thumbnail. text-title: title.	video
Label	string	The category of the moderation result. Multiple values are separated by commas (,). Valid values: porn: pornography. terrorism: terrorist content or politically sensitive content. ad: image or text violations. live: undesirable scenes. logo: image logos. audio: audio anti-spam. normal: normal.	porn
AudioResult	array<object>	The audio moderation results.
	object
Score	string	The score of the audio that matches the label. Value range: `[0, 100]`. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	99.91
Suggestion	string	The recommended action based on the moderation result. Valid values: block: Blocked. review: Needs manual review. pass: Passed.	pass
Label	string	The category of the moderation result: normal: normal. spam: spam. ad: advertisement. politics: politically sensitive content. terrorism: terrorist content. abuse: abusive content. porn: pornographic content. flood: junk content. contraband: prohibited content. meaningless: meaningless content.	normal
Scene	string	The moderation scenario. Fixed value: antispam.	antispam
ImageResult	array<object>	The image moderation results.
	array<object>
Type	string	The image type. Valid values: cover (thumbnail).	cover
Url	string	The URL of the image.	http://www.test.com/****.jpg
Suggestion	string	The recommended action based on the moderation result. Valid values: block: Blocked. review: Needs manual review. pass: Passed.	pass
Label	string	The category of the image moderation result. Multiple values are separated by commas (,). Valid values: porn: pornography. terrorism: terrorist content or politically sensitive content. ad: image or text violations. live: undesirable scenes. logo: image logos. normal: normal.	porn
Result	array<object>	The details of the image moderation result.
	object
Score	string	The score of the image that matches the label. Value range: `[0, 100]`. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100.00000
Suggestion	string	The recommended action based on the moderation result. Valid values: block: Blocked. review: Needs manual review. pass: Passed.	pass
Label	string	The category of the moderation result. When scene is porn, valid values: porn: pornographic. sexy: sexy. normal: normal. When scene is terrorism, valid values: normal: normal. bloody: bloody. explosion: explosion or smoke. outfit: special attire. logo: special logo. weapon: weapon. politics: politically sensitive. violence: fighting. crowd: crowd gathering. parade: parade. carcrash: car crash scene. flag: flag. location: landmark. others: others. When scene is ad, valid values: normal: normal. ad: other advertisement. politics: text contains politically sensitive content. porn: text contains pornographic content. abuse: text contains abusive content. terrorism: text contains terrorist content. contraband: text contains prohibited content. spam: text contains other spam content. npx: small ads. qrcode: contains QR code. programCode: contains mini program code. When scene is live, valid values: normal: normal. meaningless: no content in the image (for example, black screen or white screen). PIP: Picture-in-Picture (PiP). smoking: smoking. drivelive: in-car live streaming. When scene is logo, valid values: normal: normal. TV: contains a regulated logo. trademark: contains a trademark.	porn
Scene	string	The moderation scenario. Valid values: porn: pornography detection. terrorism: terrorist content or politically sensitive content. ad: image or text violations. live: undesirable scenes. logo: image logos.	porn
TextResult	array<object>	The text moderation results.
	object
Type	string	The text categorization. Valid values: title (title).	title
Suggestion	string	The recommended action based on the moderation result. Valid values: block: Blocked. review: Needs manual review. pass: Passed.	pass
Score	string	The score of the text that matches the label. Value range: `[0, 100]`. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100.00000
Label	string	The category of the moderation result. Valid values: spam: spam. ad: advertisement. abuse: abusive content. flood: junk content. contraband: prohibited content. meaningless: meaningless content. normal: normal.	ad
Content	string	The text content that was moderated.	Hotline 123****
Scene	string	The moderation scenario. Fixed value: antispam.	antispam
VideoResult	object	The video moderation result.
Label	string	The category of the moderation result. Valid values: porn: pornography. terrorism: terrorist content or politically sensitive content. ad: image or text violations. live: undesirable scenes. logo: image logos. normal: normal.	porn
Suggestion	string	The recommended action based on the moderation result. Valid values: block: Blocked. review: Needs manual review. pass: Passed.	pass
PornResult	object	The pornography detection result.
Suggestion	string	The recommended action based on the pornography detection result. Valid values: block: Blocked. review: Needs manual review. pass: Passed.	pass
AverageScore	string	The average score of video snapshots that match the label. Value range: `[0, 100]`, with precision up to 10 decimal places. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100
Label	string	The pornography detection result. Valid values: porn: pornographic. sexy: sexy. normal: normal.	porn
MaxScore	string	The highest score of video snapshots that match the label. Value range: `[0, 100]`, with precision up to 10 decimal places. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100
CounterList	array<object>	The number of video snapshots for each moderation result category.
	object
Label	string	The pornography detection result. Valid values: porn: pornographic. sexy: sexy. normal: normal.	porn
Count	integer	The number of video snapshots.	1
TopList	array<object>	The information about the video snapshots with the highest scores for the matched label.
	object
Url	string	The URL of the video snapshot.	http://temp-testbucket.oss-cn-shanghai.aliyuncs.com/aivideocensor/****.jpg
Score	string	The score of the video snapshot that matches the label. Value range: `[0, 100]`, with precision up to 10 decimal places. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100.0000
Timestamp	string	The position of the video snapshot in the video. Unit: milliseconds.	3005
Label	string	The pornography detection result. Valid values: porn: pornographic. sexy: sexy. normal: normal.	porn
AdResult	object	The advertisement moderation result.
Suggestion	string	The recommended action based on the moderation result. Valid values: block: Blocked. review: Needs manual review. pass: Passed.	block
AverageScore	string	The average score of video snapshots that match the label. Value range: `[0, 100]`, with precision up to 10 decimal places. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100
Label	string	The category of the advertisement moderation result. Valid values: normal: normal. ad: other advertisement. politics: text contains politically sensitive content. porn: text contains pornographic content. abuse: text contains abusive content. terrorism: text contains terrorist content. contraband: text contains prohibited content. spam: text contains other spam content. npx: small ads. qrcode: contains QR code. programCode: contains mini program code.	ad
MaxScore	string	The highest score of video snapshots that match the label. Value range: `[0, 100]`, with precision up to 10 decimal places. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100
CounterList	array<object>	The number of video snapshots for each moderation result category.
	object
Label	string	The category of the advertisement moderation result. Valid values: normal: normal. ad: other advertisement. politics: text contains politically sensitive content. porn: text contains pornographic content. abuse: text contains abusive content. terrorism: text contains terrorist content. contraband: text contains prohibited content. spam: text contains other spam content. npx: small ads. qrcode: contains QR code. programCode: contains mini program code.	ad
Count	integer	The number of video snapshots.	12
TopList	array<object>	The information about the video snapshots with the highest scores for the matched label.
	object
Url	string	The URL of the video snapshot.	http://temp-testbucket.oss-cn-shanghai.aliyuncs.com/aivideocensor/****.jpg
Score	string	The score of the video snapshot that matches the label. Value range: `[0, 100]`, with precision up to 10 decimal places. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100
Timestamp	string	The position of the video snapshot in the video. Unit: milliseconds.	10
Label	string	The category of the advertisement moderation result. Valid values: normal: normal. ad: other advertisement. politics: text contains politically sensitive content. porn: text contains pornographic content. abuse: text contains abusive content. terrorism: text contains terrorist content. contraband: text contains prohibited content. spam: text contains other spam content. npx: small ads. qrcode: contains QR code. programCode: contains mini program code.	ad
LogoResult	object	The logo moderation result.
Suggestion	string	The recommended action based on the moderation result. Valid values: block: Blocked. review: Needs manual review. pass: Passed.	block
AverageScore	string	The average score of video snapshots that match the label. Value range: `[0, 100]`, with precision up to 10 decimal places. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100
Label	string	The category of the logo moderation result. Valid values: normal: normal. TV: contains a regulated logo. trademark: contains a trademark.	TV
MaxScore	string	The highest score of video snapshots that match the label. Value range: `[0, 100]`, with precision up to 10 decimal places. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100
CounterList	array<object>	The number of video snapshots for each moderation result category.
	object
Label	string	The category of the logo moderation result. Valid values: normal: normal. TV: contains a regulated logo. trademark: contains a trademark.	TV
Count	integer	The number of video snapshots.	1
TopList	array<object>	The information about the video snapshots with the highest scores for the matched label.
	object
Url	string	The URL of the video snapshot.	http://temp-testbucket.oss-cn-shanghai.aliyuncs.com/aivideocensor/****.jpg
Score	string	The score of the video snapshot that matches the label. Value range: `[0, 100]`, with precision up to 10 decimal places. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100
Timestamp	string	The position of the video snapshot in the video. Unit: milliseconds.	16
Label	string	The category of the logo moderation result. Valid values: normal: normal. TV: contains a regulated logo. trademark: contains a trademark.	TV
LiveResult	object	The undesirable content moderation result.
Suggestion	string	The recommended action based on the moderation result. Valid values: block: Blocked. review: Needs manual review. pass: Passed.	block
AverageScore	string	The average score of video snapshots that match the label. Value range: `[0, 100]`, with precision up to 10 decimal places. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100
Label	string	The category of the moderation result. Valid values: normal: normal. meaningless: no content in the image (for example, black screen or white screen). PIP: Picture-in-Picture (PiP). smoking: smoking. drivelive: in-car live streaming.	smoking
MaxScore	string	The highest score of video snapshots that match the label. Value range: `[0, 100]`, with precision up to 10 decimal places. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100
CounterList	array<object>	The categories of the undesirable content moderation results and the number of video snapshots for each category.
	object
Label	string	The category of the moderation result. Valid values: normal: normal. meaningless: no content in the image (for example, black screen or white screen). PIP: Picture-in-Picture (PiP). smoking: smoking. drivelive: in-car live streaming.	smoking
Count	integer	The number of video snapshots.	2
TopList	array<object>	The information about the video snapshots with the highest scores for the matched label.
	object
Url	string	The URL of the video snapshot.	http://temp-testbucket.oss-cn-shanghai.aliyuncs.com/aivideocensor/****.jpg
Score	string	The score of the video snapshot that matches the label. Value range: `[0, 100]`, with precision up to 10 decimal places. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100
Timestamp	string	The position of the video snapshot in the video. Unit: milliseconds.	10
Label	string	The category of the moderation result. Valid values: normal: normal. meaningless: no content in the image (for example, black screen or white screen). PIP: Picture-in-Picture (PiP). smoking: smoking. drivelive: in-car live streaming.	smoking
TerrorismResult	object	The terrorism and political content review result.
Suggestion	string	The review suggestion for terrorism and political content. Valid values: block: Violation. review: Suspected violation. pass: Passed.	pass
AverageScore	string	The average score of video snapshots that match the label. Value range: `[0, 100]`, with precision up to 10 decimal places. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100
Label	string	The review result label for terrorism and political content. Valid values: normal: Normal. bloody: Bloody content. explosion: Explosion or smoke. outfit: Special outfit. logo: Special logo. weapon: Weapon. politics: Political content. violence: Fighting. crowd: Crowd gathering. parade: Parade. carcrash: Car crash scene. flag: Flag. location: Landmark. others: Others.	normal
MaxScore	string	The highest score of video snapshots that match the label. Value range: `[0, 100]`, with precision up to 10 decimal places. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100
CounterList	array<object>	The categories of terrorism and political content review results and the number of video snapshots in each category.
	object
Label	string	The review result label for terrorism and political content. Valid values: normal: Normal. bloody: Bloody content. explosion: Explosion or smoke. outfit: Special outfit. logo: Special logo. weapon: Weapon. politics: Political content. violence: Fighting. crowd: Crowd gathering. parade: Parade. carcrash: Car crash scene. flag: Flag. location: Landmark. others: Others.	outfit
Count	integer	The number of video snapshots that contain terrorism and political content.	1
TopList	array<object>	The information about the video snapshots with the highest scores for the matched label.
	object
Url	string	The URL of the video snapshot.	http://temp-testbucket.oss-cn-shanghai.aliyuncs.com/aivideocensor/****.jpg
Score	string	The score of the video snapshot that matches the label. Value range: `[0, 100]`, with precision up to 10 decimal places. The score represents the probability of the corresponding label classification. A higher value indicates higher accuracy.	100.000
Timestamp	string	The position of the video snapshot in the video. Unit: milliseconds.	3005
Label	string	The review result label for terrorism and political content. Valid values: normal: Normal. bloody: Bloody content. explosion: Explosion or smoke. outfit: Special outfit. logo: Special logo. weapon: Weapon. politics: Political content. violence: Fighting. crowd: Crowd gathering. parade: Parade. carcrash: Car crash scene. flag: Flag. location: Landmark. others: Others.	normal
GreenEnhancedResult	object	The review result of the GreenEnhanced route.
Suggestion	string	The frame review conclusion mapped from frameResult.riskLevel: high→block, medium/low→review, none→pass.
Label	string	The union of matched Green native labels, comma-separated (such as pornographic_adultContent_tii). The value is normal if no labels are matched.
MaxScore	string	The highest confidence score of matched frames. This field is not returned if no frames are matched.
AverageScore	string	The average confidence score of matched frames. This field is not returned if no frames are matched.
CounterList	array<object>	The aggregated count of violation labels: Label (Green label) / Count (number of matched frames for the label).
	object
Label	string	The review result category.
Count	integer	The number of video snapshots for the corresponding label.
TopList	array<object>	The matched frame details, sorted by confidence score in descending order.
	object
Label	string	The review result category.
Score	string	The confidence score of the video snapshot that matches the label.
Timestamp	string	The position of the video snapshot in the video.
Url	string	The URL of the video snapshot.

Examples

Success response

JSON format

{
  "RequestId": "CB7D7232-1AB2-40FE-B8D5-****",
  "MediaAuditResult": {
    "Suggestion": "pass",
    "AbnormalModules": "video",
    "Label": "porn",
    "AudioResult": [
      {
        "Score": "99.91",
        "Suggestion": "pass",
        "Label": "normal",
        "Scene": "antispam"
      }
    ],
    "ImageResult": [
      {
        "Type": "cover",
        "Url": "http://www.test.com/****.jpg",
        "Suggestion": "pass",
        "Label": "porn",
        "Result": [
          {
            "Score": "100.00000",
            "Suggestion": "pass",
            "Label": "porn",
            "Scene": "porn"
          }
        ]
      }
    ],
    "TextResult": [
      {
        "Type": "title",
        "Suggestion": "pass",
        "Score": "100.00000",
        "Label": "ad",
        "Content": "Hotline 123****",
        "Scene": "antispam"
      }
    ],
    "VideoResult": {
      "Label": "porn",
      "Suggestion": "pass",
      "PornResult": {
        "Suggestion": "pass",
        "AverageScore": "100",
        "Label": "porn",
        "MaxScore": "100",
        "CounterList": [
          {
            "Label": "porn",
            "Count": 1
          }
        ],
        "TopList": [
          {
            "Url": "http://temp-testbucket.oss-cn-shanghai.aliyuncs.com/aivideocensor/****.jpg",
            "Score": "100.0000",
            "Timestamp": "3005",
            "Label": "porn"
          }
        ]
      },
      "AdResult": {
        "Suggestion": "block",
        "AverageScore": "100",
        "Label": "ad",
        "MaxScore": "100",
        "CounterList": [
          {
            "Label": "ad",
            "Count": 12
          }
        ],
        "TopList": [
          {
            "Url": "http://temp-testbucket.oss-cn-shanghai.aliyuncs.com/aivideocensor/****.jpg",
            "Score": "100",
            "Timestamp": "10",
            "Label": "ad"
          }
        ]
      },
      "LogoResult": {
        "Suggestion": "block",
        "AverageScore": "100",
        "Label": "TV",
        "MaxScore": "100",
        "CounterList": [
          {
            "Label": "TV",
            "Count": 1
          }
        ],
        "TopList": [
          {
            "Url": "http://temp-testbucket.oss-cn-shanghai.aliyuncs.com/aivideocensor/****.jpg",
            "Score": "100",
            "Timestamp": "16",
            "Label": "TV"
          }
        ]
      },
      "LiveResult": {
        "Suggestion": "block",
        "AverageScore": "100",
        "Label": "smoking",
        "MaxScore": "100",
        "CounterList": [
          {
            "Label": "smoking",
            "Count": 2
          }
        ],
        "TopList": [
          {
            "Url": "http://temp-testbucket.oss-cn-shanghai.aliyuncs.com/aivideocensor/****.jpg",
            "Score": "100",
            "Timestamp": "10",
            "Label": "smoking"
          }
        ]
      },
      "TerrorismResult": {
        "Suggestion": "pass",
        "AverageScore": "100",
        "Label": "normal",
        "MaxScore": "100",
        "CounterList": [
          {
            "Label": "outfit",
            "Count": 1
          }
        ],
        "TopList": [
          {
            "Url": "http://temp-testbucket.oss-cn-shanghai.aliyuncs.com/aivideocensor/****.jpg",
            "Score": "100.000",
            "Timestamp": "3005",
            "Label": "normal"
          }
        ]
      },
      "GreenEnhancedResult": {
        "Suggestion": "",
        "Label": "",
        "MaxScore": "",
        "AverageScore": "",
        "CounterList": [
          {
            "Label": "",
            "Count": 0
          }
        ],
        "TopList": [
          {
            "Label": "",
            "Score": "",
            "Timestamp": "",
            "Url": ""
          }
        ]
      }
    }
  }
}

Error codes

See Error Codes for a complete list.

Release notes

See Release Notes for a complete list.