To enable porn detection during live streaming, you need to enable screencapturing either in the CSS console or via APIs. This document describes how to implement porn detection via APIs.

Enabling Porn Detection

As the porn detection feature is based on screencapturing, you have to enable screencapturing first before you can enable porn detection. The steps are as follows:

1. Create a screencapturing template with porn detection enabled

Call CreateLiveSnapshotTemplate, setting PornFlag to 1 to create a screencapturing template with porn detection enabled.

2. Create a screencapturing rule

Call CreateLiveSnapshotRule to create a screencapturing rule, binding the ID of the screencapturing template created in step 1 with the target AppId, DomainName, AppName, and StreamName.

3. Start live streaming

After you create a screencapturing rule with porn detection enabled, the porn detection feature will be automatically enabled for new streams. If you want to enable porn detection for an ongoing stream, you need to stop and restart the stream.

Getting Porn Detection Result

After porn detection is enabled, you can configure a registered domain name in the porn detection callback template to receive callbacks of porn detection results.

Note：

By default, only questionable results will be called back.

1. Create a porn detection callback template

Call CreateLiveCallbackTemplate, setting PornCensorshipNotifyUrl to your domain name to create a porn detection callback template.

2. Create a porn detection callback rule

Call CreateLiveCallbackRule to create a porn detection callback rule, binding the ID of the porn detection callback template created in step 1 to the target AppId, DomainName, and AppName.

3. Get the porn detection result

The CSS backend sends the porn detection result to your registered domain name through an HTTP POST request where the result is stored in the HTTP body in JSON format. You can determine whether the live streaming is pornographic by checking the type field.

Note：

We recommend you use the type of an image to determine whether it is pornographic. As the detection system cannot achieve 100% accuracy, there may be false positives or false negatives, and human confirmation is recommended.

The complete protocol is as follows:

LabelResult

Hit result of the category model

LabelDetailItem

Sub-label hit details of the category model

ObjectResult

Object detection result

ObjectDetail

Object detection details. When the detection scenario is object, advertising logo, or QR code, it returns the label name, label value, label score, and location information of the detection frame.

Location

Coordinates and other information of the detection frame

OcrResult

OCR result

OcrTextDetail

OCR details

LibResult

Blocklist/Allowlist result

LibDetail

Custom list or blocklist/allowlist details

Sample callback message

{
        "ocrMsg": "",
        "type": [1],
        "socre": 99,
        "screenshotTime": 1610640000,
        "level": 0,
        "img": "http://1.1.1.1/download/porn/test.jpg",
        "abductionRisk": [],
        "faceDetails": [],
        "sendTime": 1615859827,
        "suggestion": "Block",
        "label": "Porn",
        "subLabel": "PornHigh",
        "labelResults": [{
                "HitFlag": 0,
                "Scene": "Illegal",
                "Suggestion": "Pass",
                "Label": "Normal",
                "SubLabel": "",
                "Score": 0,
                "Details": []
        }, {
                "HitFlag": 1,
                "Scene": "Porn",
                "Suggestion": "Block",
                "Label": "Porn",
                "SubLabel": "PornHigh",
                "Score": 99,
                "Details": [{
                        "Id": 0,
                        "Name": "PornHigh",
                        "Score": 99
                }, {
                        "Id": 1,
                        "Name": "WomenChest",
                        "Score": 99
                }]
        }, {
                "HitFlag": 0,
                "Scene": "Sexy",
                "Suggestion": "Pass",
                "Label": "Normal",
                "SubLabel": "",
                "Score": 0,
                "Details": []
        }, {
                "HitFlag": 0,
                "Scene": "Terror",
                "Suggestion": "Pass",
                "Label": "Normal",
                "SubLabel": "",
                "Score": 0,
                "Details": []
        }],
        "objectResults": [{
                "HitFlag": 0,
                "Scene": "QrCode",
                "Suggestion": "Pass",
                "Label": "Normal",
                "SubLabel": "",
                "Score": 0,
                "Names": [],
                "Details": []
        }, {
                "HitFlag": 0,
                "Scene": "MapRecognition",
                "Suggestion": "Pass",
                "Label": "Normal",
                "SubLabel": "",
                "Score": 0,
                "Names": [],
                "Details": []
        }, {
                "HitFlag": 0,
                "Scene": "PolityFace",
                "Suggestion": "Pass",
                "Label": "Normal",
                "SubLabel": "",
                "Score": 0,
                "Names": [],
                "Details": []
        }],
        "ocrResults": [{
                "HitFlag": 0,
                "Scene": "OCR",
                "Suggestion": "Pass",
                "Label": "Normal",
                "SubLabel": "",
                "Score": 0,
                "Text": "",
                "Details": []
        }],
        "streamId": "teststream",
        "channelId": "teststream",
        "stream_param": "txSecret=40f38f69f574fd51126c421a3d96c374&txTime=5DEBEC80",
        "app": "5000.myqcloud.com",
        "appname": "live",
        "appid": 10000,
        "event_type": 317,
        "sign": "ac920c3e66**********78cf1b5de2c63",
        "t": 1615860427
}

Disabling Porn Detection

You can disable porn detection by deleting the screencapturing rule or modifying the screencapturing template. Both the deletion and modification are effective only for new live streams. If you want to disable porn detection for an ongoing live stream, you have to stop and restart the stream.

1. Delete the screencapturing rule

Call DeleteLiveSnapshotRule, passing in the DomainName, AppName, and StreamName bind to the screencapturing template ID to delete the screencapturing rule.

2. Modify the screencapturing template

Call ModifyLiveSnapshotTemplate, setting PornFlag to `0.