sumi / rules.json
NagaYu's picture
Sumi demo: Japanese PII detection running entirely in the browser
ac17e0e verified
Raw History Blame Contribute Delete
6.91 kB
{
"schema": "sumi-rules-v1",
"specs": [
{
"rule_id": "email.basic",
"label": "EMAIL",
"pattern": "(?<![A-Za-z0-9._%+\\-])[A-Za-z0-9._%+\\-]{1,64}@[A-Za-z0-9](?:[A-Za-z0-9\\-]{0,61}[A-Za-z0-9])?(?:\\.[A-Za-z0-9](?:[A-Za-z0-9\\-]{0,61}[A-Za-z0-9])?)+",
"confidence": 0.99,
"require_context": false,
"context": [],
"negative_context": [],
"priority": 90,
"validator": null,
"reject_date_shape": false
},
{
"rule_id": "phone.jp",
"label": "PHONE",
"pattern": "(?<![0-9A-Za-z\\-])(?:\\+81[\\-\\s]?)?0\\d{1,4}[\\-\\(\\)\\s]?\\d{1,4}[\\-\\)\\s]?\\d{3,4}(?![0-9A-Za-z\\-])",
"confidence": 0.8,
"require_context": false,
"context": [
"TEL",
"Tel",
"tel",
"電話",
"でんわ",
"連絡先",
"携帯",
"FAX",
"Fax",
"お電話",
"番号",
"ご連絡",
"直通",
"代表"
],
"negative_context": [
"型番",
"製品コード",
"注文番号",
"整理番号",
"追跡番号",
"ISBN",
"図面番号",
"会議室",
"在庫コード",
"試験区分",
"バージョン",
"郵便物番号",
"測定値",
"商品コード",
"管理番号",
"伝票"
],
"priority": 80,
"validator": "jp_phone",
"reject_date_shape": true
},
{
"rule_id": "postal.jp",
"label": "POSTAL_CODE",
"pattern": "(?<![0-9A-Za-z\\-])\\d{3}-\\d{4}(?![0-9A-Za-z\\-])",
"confidence": 0.55,
"require_context": true,
"context": [
"〒",
"郵便番号",
"住所",
"所在地",
"送付先",
"ご住所"
],
"negative_context": [],
"priority": 70,
"validator": null,
"reject_date_shape": false
},
{
"rule_id": "bank.code_branch_account",
"label": "BANK_ACCOUNT",
"pattern": "(?<![0-9A-Za-z\\-])\\d{4}-\\d{3}-\\d{7}(?![0-9A-Za-z\\-])",
"confidence": 0.95,
"require_context": false,
"context": [
"口座",
"振込",
"支店",
"普通",
"当座",
"引落",
"銀行"
],
"negative_context": [],
"priority": 85,
"validator": null,
"reject_date_shape": false
},
{
"rule_id": "bank.prose",
"label": "BANK_ACCOUNT",
"pattern": "(?:普通|当座|貯蓄)\\s*(?:預金)?\\s*(?<![0-9A-Za-z\\-])\\d{7}(?![0-9A-Za-z\\-])",
"confidence": 0.92,
"require_context": false,
"context": [],
"negative_context": [],
"priority": 84,
"validator": null,
"reject_date_shape": false
},
{
"rule_id": "card.16digit",
"label": "CREDIT_CARD",
"pattern": "(?<![0-9A-Za-z\\-])(?:\\d{4}[\\-\\s]\\d{4}[\\-\\s]\\d{4}[\\-\\s]\\d{4}|\\d{16})(?![0-9A-Za-z\\-])",
"confidence": 0.93,
"require_context": false,
"context": [],
"negative_context": [],
"priority": 88,
"validator": null,
"reject_date_shape": false
},
{
"rule_id": "card.amex",
"label": "CREDIT_CARD",
"pattern": "(?<![0-9A-Za-z\\-])3[47]\\d{2}[\\-\\s]\\d{6}[\\-\\s]\\d{5}(?![0-9A-Za-z\\-])",
"confidence": 0.93,
"require_context": false,
"context": [],
"negative_context": [],
"priority": 88,
"validator": null,
"reject_date_shape": false
},
{
"rule_id": "mynumber.12digit",
"label": "MYNUMBER",
"pattern": "(?<![0-9A-Za-z\\-])(?:\\d{4}[\\-\\s]\\d{4}[\\-\\s]\\d{4}|\\d{12})(?![0-9A-Za-z\\-])",
"confidence": 0.7,
"require_context": true,
"context": [
"マイナンバー",
"個人番号",
"通知カード",
"本人確認",
"マイナ"
],
"negative_context": [
"追跡番号",
"郵便物番号",
"注文番号",
"型番",
"整理番号",
"伝票",
"管理番号",
"在庫",
"図面番号",
"試験区分",
"製品コード",
"商品コード",
"会議室",
"ISBN"
],
"priority": 86,
"validator": null,
"reject_date_shape": false
},
{
"rule_id": "member.prefixed",
"label": "MEMBER_ID",
"pattern": "(?<![A-Za-z0-9])[A-Z]{2,6}[\\-]?\\d{4,12}(?:[\\-]\\d{2,6})?(?![A-Za-z0-9])",
"confidence": 0.6,
"require_context": true,
"context": [
"会員番号",
"顧客番号",
"契約番号",
"受付番号",
"お客様番号",
"整理番号",
"会員ID",
"顧客ID",
"社員番号",
"登録番号",
"カード番号"
],
"negative_context": [],
"priority": 60,
"validator": null,
"reject_date_shape": false
},
{
"rule_id": "member.numeric_ctx",
"label": "MEMBER_ID",
"pattern": "(?<![0-9A-Za-z\\-])\\d{6,12}(?:-\\d{2,6})?(?![0-9A-Za-z\\-])",
"confidence": 0.55,
"require_context": true,
"context": [
"会員番号",
"顧客番号",
"契約番号",
"お客様番号",
"社員番号",
"会員ID"
],
"negative_context": [],
"priority": 55,
"validator": null,
"reject_date_shape": false
}
],
"phone_plan": {
"area2": [
"03",
"06"
],
"area3": [
"011",
"015",
"017",
"018",
"019",
"022",
"023",
"024",
"025",
"026",
"027",
"028",
"029",
"042",
"043",
"044",
"045",
"046",
"047",
"048",
"049",
"052",
"053",
"054",
"055",
"058",
"059",
"072",
"073",
"075",
"076",
"077",
"078",
"079",
"082",
"083",
"084",
"086",
"087",
"088",
"089",
"092",
"093",
"095",
"096",
"097",
"098",
"099"
],
"mobile": [
"070",
"080",
"090"
],
"ip": [
"050"
],
"tollfree4": [
"0120",
"0570",
"0800"
]
},
"types": {
"NAME": {
"ja": "氏名",
"en": "Name",
"rule_deterministic": false,
"model_driven": true
},
"ADDRESS": {
"ja": "住所",
"en": "Address",
"rule_deterministic": false,
"model_driven": true
},
"PHONE": {
"ja": "電話番号",
"en": "Phone",
"rule_deterministic": true,
"model_driven": false
},
"EMAIL": {
"ja": "メールアドレス",
"en": "Email",
"rule_deterministic": true,
"model_driven": false
},
"DOB": {
"ja": "生年月日",
"en": "Birth date",
"rule_deterministic": false,
"model_driven": true
},
"BANK_ACCOUNT": {
"ja": "金融口座",
"en": "Bank account",
"rule_deterministic": true,
"model_driven": false
},
"CREDIT_CARD": {
"ja": "カード番号",
"en": "Card number",
"rule_deterministic": true,
"model_driven": false
},
"MYNUMBER": {
"ja": "マイナンバー様式",
"en": "My Number",
"rule_deterministic": true,
"model_driven": false
},
"MEMBER_ID": {
"ja": "会員番号",
"en": "Member ID",
"rule_deterministic": true,
"model_driven": false
},
"POSTAL_CODE": {
"ja": "郵便番号",
"en": "Postal code",
"rule_deterministic": true,
"model_driven": false
}
},
"rule_deterministic": [
"MYNUMBER",
"CREDIT_CARD",
"PHONE",
"EMAIL",
"BANK_ACCOUNT",
"MEMBER_ID",
"POSTAL_CODE"
],
"context_window": 12
}