​

Overview

Automate content moderation reduces the cost of your image, video, text, and voice moderation by accurately detecting inappropriate content.

Jarvis Moderator provides services through open application programming interfaces (APIs). You can obtain the inference result by calling APIs. It helps you build an intelligent service system and improves service efficiency.

• A software tool such as curl and Postman

These are good options if you are more comfortable writing code, HTTP requests, and API calls. For details, see Using Postman to Call Jarvis.

​

Internationalization labels

The following content will be subject to review and detection to ensure compliance with relevant laws, regulations, and platform policies:

1. Advertising: Detects malicious advertising and redirection content to prevent users from being led to unsafe or inappropriate sites.
2. Violent Content: Detects violent or terrorist content to prevent the dissemination of harmful information.
3. Political Content: Reviews political content to ensure that it does not involve sensitive or inflammatory political information.
4. Specified Speech: Detects specified speech or voice content to identify and manage audio that meets certain conditions.
5. Specified Lyrics: Detects specified lyrics content to prevent the spread of inappropriate or harmful lyrics.
6. Sexual Content: Reviews content related to sexual behavior or sexual innuendo to protect users from inappropriate information.
7. Moaning Sounds: Detects sounds related to sexual activity, such as moaning, to prevent the spread of such audio.
8. Contraband: Identifies and blocks all illegal or prohibited content.
9. Profane Language: Reviews and filters content containing profanity or vulgar language.
10. Religious Content: Reviews religious content to avoid controversy or offense to specific religious beliefs.
11. Cyberbullying: Detects cyberbullying behavior to prevent such content from harming users.
12. Harmful or Inappropriate Content: Reviews and manages harmful or inappropriate content to maintain a safe and positive environment on the platform.
13. Silent Audio: Detects silent audio content to identify and address potential technical issues or other anomalies.
14. Customized Content: Allows users to define and review specific types of content according to business needs or compliance requirements.

This content will be thoroughly detected by our review system to ensure that all content on the platform meets the relevant standards and regulations.

​

Subscribing to the Service

NOTE: This service is available only to enterprise users now.

To subscribe to Jarvis Moderator, perform the following steps:

1. Register an AKOOL account.
2. Then click the picture icon in the upper right corner of the website, and click the “APl Credentials” function to set the key pair (clientId, clientSecret) used when accessing the API and save it.
3. Use the secret key pair just saved to send the api interface to obtain the access token.

​

Jarvis Moderator

POST https://openapitest.akool.com/api/open/v3/content/analysis/sentiment

Request Headers

Body Attributes

Response Attributes

Example

Body

{
   
    "type":1,   // 1:image 2:video 3: auido 4:text
    "content":"https://drz0f01yeq1cx.cloudfront.net/1714023431475-food.jpg",
    "webhookUrl":"http://localhost:3004/api/v3/webhook",
    "input": "xxx" // The user defines the content to be detected in words	
}

Request

curl --location 'https://openapitest.akool.com/api/open/v3/content/analysis/sentiment' \
--header 'Authorization: Bearer token' \
--header 'Content-Type: application/json' \
--data '{
   
    "type":1,
    "content":"https://drz0f01yeq1cx.cloudfront.net/1714023431475-food.jpg",


}'

Response

{
    "code": 1000,
    "msg": "OK",
    "data": {
        "create_time": 1710757900382,
        "uid": 101690,
        "type": 1,
        "status": 1,   // current status of content： 【1：queueing（The requested operation is being processed），2：processing（The requested operation is being processing），3：completed（The request operation has been processed successfully），4：failed（The request operation processing failed）】
        "webhookUrl": "http://localhost:3007/api/open/v3/test/webhook",
        "result": "",
        "_id": "65f8180c24d9989e93dde3b6",
        "__v": 0
    }
}

​

Get analysis Info Result

GET https://openapitest.akool.com/api/open/v3/content/analysis/infobyid?_id=662df7928ee006bf033b64bf

Request Headers

Query Attributes

Response Attributes

Example

Request

curl --location 'https://openapitest.akool.com/api/open/v3/content/analysis/infobyid?_id=662e20b93baa7aa53169a325' \
--header 'Authorization: Bearer token'

Response

{
    "code": 1000,
    "msg": "OK",
    "data": {
        "_id": "662e20b93baa7aa53169a325",
        "uid": 100002,
        "status": 3,
        "result": "- violence: Presence of a person holding a handgun, which can be associated with violent content.\nResult: Non-Compliant",
        "final_conclusion" :"Non-Compliant"   // Non-Compliant、Compliant、Unknown
    }
}

Response Code Description