Text Moderation

Requirements

Item	Specification
Encoding	UTF-8
Method	POST
Recommended timeout	1s

Request

Request URL

Cluster	Request URL	Supported Products
Shanghai	`http://api-text-sh.fengkongcloud.com/text/v4`	Chinese Text
USA (Virginia)	`http://api-text-fjny.fengkongcloud.com/text/v4`	Chinese Text, International Text
Singapore	`http://api-text-xjp.fengkongcloud.com/text/v4`	Chinese Text, International Text
Beijing	`http://api-text-bj.fengkongcloud.com/text/v4`	Chinese Text

Request Parameters

Parameter	Type	Required	Description
`accessKey`	string	Yes	API authentication key, provided by ISHUMEI.
`appId`	string	Yes	Application identifier. Contact ISHUMEI to activate. Use the value provided by ISHUMEI.
`eventId`	string	Yes	Event identifier. Contact ISHUMEI to activate. Use the value provided by ISHUMEI.
`type`	string	Yes	Risk detection types. See Detection Types.
`agentType`	string	No	Agent detection risk types. Same values as `type` (excluding `PROMPTATTACK` and `PUBLICFIGURE`). Combine with underscores.
`data`	json_object	Yes	Request data content. Max 1 MB. See `data` Object.
`kbType`	string	No	Knowledge base type. Max input: 510 characters (exceeding this prevents knowledge base matching). Contact ISHUMEI sales to enable. See Knowledge Base Types.
`translationTargetLang`	string	No	Translate input text to a target language. Contact ISHUMEI sales to enable. `zh`: Chinese. `en`: English.
`acceptLang`	string	No	Language for returned labels. `zh`: Chinese. `en`: English. Defaults to Chinese if not specified.
`callback`	string	No	Callback HTTP URL. When non-empty, the service sends moderation results to this URL.

Detection Types

Combine multiple types with underscores (e.g., TEXTRISK_FRAUD). Combined types take the union of detection capabilities.

Value	Description
`POLITY`	Political content detection
`VIOLENT`	Violence & terrorism detection
`BAN`	Prohibited content detection
`EROTIC`	Pornographic content detection
`DIRTY`	Abusive language detection
`ADVERT`	Advertising detection
`PRIVACY`	Privacy information detection
`ADLAW`	Advertising law violation detection
`MEANINGLESS`	Meaningless content detection
`TEXTRISK`	Standard risk detection (includes: political, terrorism, prohibited, pornographic, abusive, advertising, privacy, advertising law, meaningless)
`FRAUD`	Online fraud detection
`UNPOACH`	High-value user anti-poaching detection
`TEXTMINOR`	Minor-related content detection
`PROMPTATTACK`	Prompt injection / instruction attack detection
`PUBLICFIGURE`	Public figure recognition

Knowledge Base Types

Contact ISHUMEI sales to enable.

Value	Description
`PKB`	Political knowledge base
`BKB`	Prohibited content knowledge base
`SKB`	Pornographic knowledge base
`AKB`	Abusive language knowledge base

`data` Object

Parameter	Type	Required	Description
`text`	string	Yes	Text to be moderated. Max 10,000 characters per request (error returned if exceeded). If the `nickname` field is also provided, both text and nickname content are validated simultaneously.
`relateText`	string	No	Associated text for moderation. Max 128 characters (truncated if exceeded). When provided, it is reviewed in combination with `text`.
`tokenId`	string	Yes	User account identifier. Recommended to use your user UID (can be encrypted). Used for behavioral risk detection (spam, advertising, etc.). Must be an alphanumeric string with underscores and hyphens, up to 64 characters.
`lang`	string	No	Language of the text. Default: `zh`. For domestic clusters, omit or use `zh`. For international text that cannot be categorized, use `auto` for automatic language detection. See Supported Languages.
`nickname`	string	No	User nickname. Validates nickname content for risks. Max 150 characters (truncated if exceeded).
`ip`	string	No	Public IPv4 or IPv6 address of the user who sent the text.
`deviceId`	string	No	ISHUMEI device fingerprint identifier.
`dataId`	string	No	Custom data identifier.
`extra`	json_object	No	Auxiliary parameters. See `extra` Object.

`extra` Object

Parameter	Type	Required	Description
`receiveTokenId`	string	No	Message receiver's `tokenId` for private chat scenarios. Alphanumeric with underscores and hyphens, up to 64 characters. Required when `eventId` is `message`.
`topic`	string	No	Topic ID, book review section ID, or forum post ID. When `eventId` is `article`, this field is strongly recommended to enable context recognition. Without it, context cannot be associated.
`atId`	string	No	`tokenId` of the @mentioned user in group chat scenarios. Alphanumeric with underscores and hyphens, up to 64 characters. Required when `eventId` is `groupChat`.
`room`	string	No	Live room / game room ID. When `eventId` is `groupChat`, this field is strongly recommended to enable context recognition. Without it, context cannot be associated.
`sex`	int	No	User gender. `0`: male. `1`: female. `2`: unknown.
`passThrough`	json	No	Pass-through field. Content is returned as-is with the response.

Supported Languages

Value	Language
`zh`	Chinese (default)
`en`	English
`ar`	Arabic
`hi`	Hindi
`es`	Spanish
`fr`	French
`ru`	Russian
`pt`	Portuguese
`id`	Indonesian
`de`	German
`ja`	Japanese
`tr`	Turkish
`vi`	Vietnamese
`it`	Italian
`th`	Thai
`tl`	Filipino
`ko`	Korean
`ms`	Malay
`auto`	Automatic language detection

Response

Response Parameters

ℹ️
Parameters other than code, message, and requestId are only guaranteed to be returned when code is 1100.

Parameter	Type	Required	Description
`code`	int	Yes	Response code. See Response Codes.
`message`	string	Yes	Response message corresponding to the `code`.
`requestId`	string	Yes	Unique request identifier. Strongly recommended to save for troubleshooting and optimization.
`riskLevel`	string	Yes	Disposition recommendation. `PASS`: normal (allow), `REVIEW`: suspicious (manual review), `REJECT`: violation (block).
`riskLabel1`	string	Yes	Level 1 risk label. Returns `normal` when `riskLevel` is `PASS`.
`riskLabel2`	string	Yes	Level 2 risk label. Empty when `riskLevel` is `PASS`.
`riskLabel3`	string	Yes	Level 3 risk label. Empty when `riskLevel` is `PASS`.
`riskDescription`	string	Yes	Risk description. Returns "Normal" when `riskLevel` is `PASS`.
`riskDetail`	json_object	Yes	Risk detail information. See `riskDetail` Object.
`tokenLabels`	json_object	Yes	Account risk profile label information.
`tokenLabels.UGC_account_risk`	json_object	No	UGC content risk.
`tokenLabels.UGC_account_risk.sexy_risk_tokenid`	float	No	Pornographic account risk score (0–1).
`auxInfo`	json_object	Yes	Auxiliary information. See `auxInfo` Object.
`allLabels`	json_array	Yes	All matched risk labels and details. See `allLabels` Array.
`businessLabels`	json_array	Yes	All matched business labels and details. See `businessLabels` Array.
`tokenProfileLabels`	json_array	No	Account attribute labels.
`tokenRiskLabels`	json_array	No	Account risk labels.
`langResult`	json_object	No	Language information. See `langResult` Object.
`kbDetail`	json_object	No	Knowledge base detail. See `kbDetail` Object.
`finalResult`	int	Yes	Whether this is the final result. `1`: final result (can be used directly for downstream processing). `0`: intermediate result (machine moderation; human review will follow).
`resultType`	int	Yes	Current result stage. `0`: machine moderation. `1`: human moderation.
`disposal`	json_object	No	Custom disposition and mapping result. Returned only when a custom label system is configured. See `disposal` Object.

Response Codes

Code	Message
`1100`	Success
`1901`	QPS limit exceeded
`1902`	Invalid parameters
`1903`	Service failure
`1905`	Character count exceeded
`9101`	Unauthorized operation

`riskDetail` Object

Parameter	Type	Required	Description
`matchedLists`	json_array	No	Matched custom list information.
`matchedLists[].name`	string	No	Name of the matched list.
`matchedLists[].words`	json_array	No	Matched sensitive word details.
`matchedLists[].words[].word`	string	No	The matched sensitive word.
`matchedLists[].words[].position`	int_array	No	Position of the sensitive word.
`riskSegments`	json_array	No	High-risk content segments. Present when political, terrorism, prohibited, or advertising law content is detected.
`riskSegments[].segment`	string	No	High-risk content segment text.
`riskSegments[].position`	int_array	No	Position of the high-risk segment.

`auxInfo` Object

Parameter	Type	Required	Description
`filteredText`	string	No	Text with risky segments replaced by asterisks (`*`).
`passThrough`	json_object	No	Pass-through field. Same value as `data.extra.passThrough` in the request.
`contactResult`	json_array	No	Contact information detection results, including WeChat, QQ, and phone numbers.
`contactResult[].contactType`	int	No	Contact type. `0`: phone number. `1`: QQ number. `2`: WeChat ID. `3`: other.
`contactResult[].contactString`	string	No	Detected contact information string.
`contextText`	string	No	Returned when context recognition is enabled.
`unauthorizedType`	string	No	Moderation types that are not enabled. Contact ISHUMEI to enable.

`allLabels` Array

Each element in the array:

Parameter	Type	Required	Description
`riskLabel1`	string	Yes	Level 1 risk label.
`riskLabel2`	string	Yes	Level 2 risk label.
`riskLabel3`	string	Yes	Level 3 risk label.
`riskDescription`	string	Yes	Risk description.
`riskLevel`	string	Yes	Risk level: `REVIEW` or `REJECT`.
`probability`	float	Yes	Confidence score (0–1). Higher values indicate greater confidence.
`riskDetail`	json_object	Yes	Risk detail with same structure as `riskDetail` Object.

`businessLabels` Array

Each element in the array:

Parameter	Type	Required	Description
`businessLabel1`	string	Yes	Level 1 business label.
`businessLabel2`	string	Yes	Level 2 business label.
`businessLabel3`	string	Yes	Level 3 business label.
`businessDescription`	string	Yes	Business label description.
`probability`	float	Yes	Confidence score (0–1).
`businessDetail`	json_object	Yes	Business detail information.

Token Labels

Both tokenProfileLabels and tokenRiskLabels share the same structure:

Parameter	Type	Required	Description
`label1`	string	No	Level 1 label.
`label2`	string	No	Level 2 label.
`label3`	string	No	Level 3 label.
`description`	string	No	Label description.
`timestamp`	int	No	Label timestamp. 13-digit Unix timestamp in milliseconds.

`langResult` Object

Parameter	Type	Required	Description
`detectedLang`	string	No	Language detection result. Returned when `lang` is set to `auto` on an international text product. Value is a standard language code (e.g., `zh`, `en`, `ar`).
`translatedText`	string	No	Translation result. Returned when `translationTargetLang` is provided in the request.

`kbDetail` Object

Parameter	Type	Required	Description
`qlabel`	string	Yes	Question label. `UNKNOWN`: no match. `CANNOT_ASK`: question is not allowed. `EXACTNESS`: answer must be accurate (including stance). `POSITIVE`: answer must contain positive guidance. `PENDING`: temporary answer for streaming queries.
`answer`	string	Yes	Suggested answer. Provided when `qlabel` is `EXACTNESS` or `POSITIVE`.
`isEnd`	bool	Yes	Whether the full answer has been returned.
`hasAnswer`	int	Yes	Whether an answer is available. `0`: no suggested answer. `1`: suggested answer available. `2`: streaming query needed. Default: `0`.

`disposal` Object

Returned only when a custom label system is configured with ISHUMEI. ISHUMEI can return results aligned with your company's custom label system and identifiers.

Parameter	Type	Required	Description
`riskLevel`	string	Yes	Mapped disposition recommendation. If rule labels do not map, the default recommendation is returned.
`riskLabel1`	string	Yes	Mapped level 1 risk label. Returns `normal` when unmapped and `riskLevel` is `PASS`.
`riskLabel2`	string	Yes	Mapped level 2 risk label. Empty when unmapped and `riskLevel` is `PASS`.
`riskLabel3`	string	Yes	Mapped level 3 risk label. Empty when unmapped and `riskLevel` is `PASS`.
`riskDescription`	string	Yes	Mapped risk description. Returns "Normal" when `riskLevel` is `PASS`.
`riskDetail`	json_object	Yes	Mapped risk detail. Same structure as `riskDetail` Object.

Risk Label Reference

Chinese Text Labels (lang=zh or auto-detected as Chinese)

Level 1 Label	Identifier	Type	Required `type` Value
Political	`politics`	Regulatory	`TEXTRISK`
Violence & Terrorism	`violence`	Regulatory	`TEXTRISK`
Pornographic	`porn`	Regulatory	`TEXTRISK`
Prohibited	`ban`	Regulatory	`TEXTRISK`
Abusive	`abuse`	Regulatory	`TEXTRISK`
Advertising Law	`ad_law`	Regulatory	`TEXTRISK`
Advertising	`ad`	Regulatory	`TEXTRISK`
Blocklist	`blacklist`	Regulatory	`TEXTRISK`
Meaningless	`meaningless`	Regulatory	`TEXTRISK`
Privacy	`privacy`	Regulatory	`TEXTRISK`
Online Fraud	`fraud`	Regulatory	`FRAUD`
Minor	`minor`	Regulatory	`TEXTMINOR`

Non-Chinese Text Labels

Level 1 Label	Identifier	Type	Required `type` Value
Political	`Politics`	Regulatory	`TEXTRISK`
Violence & Terrorism	`Violence`	Regulatory	`TEXTRISK`
Pornographic	`Erotic`	Regulatory	`TEXTRISK`
Prohibited	`Prohibit`	Regulatory	`TEXTRISK`
Abusive	`Abuse`	Regulatory	`TEXTRISK`
Advertising	`Ads`	Regulatory	`TEXTRISK`
Blocklist	`Blacklist`	Regulatory	`TEXTRISK`

Examples

Request Example

{
  "accessKey": "YOUR_ACCESS_KEY",
  "appId": "default",
  "eventId": "text",
  "type": "TEXTRISK",
  "data": {
    "text": "Add me on QQ: qq12345",
    "tokenId": "4567898765jhgfdsa",
    "ip": "118.89.214.89",
    "deviceId": "device_fingerprint_id",
    "nickname": "user_nickname",
    "extra": {
      "topic": "12345",
      "atId": "username1",
      "room": "ceshi123",
      "receiveTokenId": "username2"
    }
  }
}

Response Example

{
  "allLabels": [
    {
      "probability": 1,
      "riskDescription": "Politics: Political: Political",
      "riskDetail": {},
      "riskLabel1": "politics",
      "riskLabel2": "shezheng",
      "riskLabel3": "shezheng",
      "riskLevel": "REVIEW"
    },
    {
      "probability": 0.95559550232975,
      "riskDescription": "Advertising: Add friend: Add friend",
      "riskDetail": {
        "matchedLists": [
          {
            "name": "Community Sensitive Word List",
            "words": [
              {
                "position": [6, 7],
                "word": "qq"
              }
            ]
          }
        ]
      },
      "riskLabel1": "ad",
      "riskLabel2": "jiahaoyou",
      "riskLabel3": "jiahaoyou",
      "riskLevel": "REJECT"
    },
    {
      "probability": 1,
      "riskDescription": "Advertising: Contact information: Contact information",
      "riskDetail": {},
      "riskLabel1": "ad",
      "riskLabel2": "lianxifangshi",
      "riskLabel3": "lianxifangshi",
      "riskLevel": "REJECT"
    }
  ],
  "auxInfo": {
    "contactResult": [
      {
        "contactString": "qq12345",
        "contactType": 2
      }
    ],
    "filteredText": "Add me on QQ: **12345"
  },
  "businessLabels": [],
  "code": 1100,
  "message": "Success",
  "finalResult": 1,
  "resultType": 0,
  "requestId": "bb917ec5fa11fd02d226fb384968feb1",
  "riskDescription": "Advertising: Contact information: Contact information",
  "riskDetail": {},
  "riskLabel1": "ad",
  "riskLabel2": "lianxifangshi",
  "riskLabel3": "lianxifangshi",
  "riskLevel": "REJECT"
}

Requirements

Request

Request URL

Request Parameters

Detection Types

Knowledge Base Types

data Object

extra Object

Supported Languages

Response

Response Parameters

Response Codes

riskDetail Object

auxInfo Object

allLabels Array

businessLabels Array

Token Labels

langResult Object

kbDetail Object

disposal Object

Risk Label Reference

Chinese Text Labels (lang=zh or auto-detected as Chinese)

Non-Chinese Text Labels

Examples

Request Example

Response Example

`data` Object

`extra` Object

`riskDetail` Object

`auxInfo` Object

`allLabels` Array

`businessLabels` Array

`langResult` Object

`kbDetail` Object

`disposal` Object