chore: mise à jour output pipeline (anonymized + structured)

Résultats de re-traitement pipeline v2 sur 261 dossiers.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
dom
2026-03-07 23:14:42 +01:00
parent c73515ac89
commit 13fe9fa666
734 changed files with 157158 additions and 304963 deletions

View File

@@ -0,0 +1,45 @@
{
"source_file": "CONSULTATION ANESTHESISTE 23100745.pdf",
"total_replacements": 28,
"regex_replacements": 25,
"ner_replacements": 0,
"sweep_replacements": 3,
"entities_found": [
{
"original": "23651408",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23651408",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23651408",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "N° Tél :",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "N° Tél :",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "N° Tél :",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
}
]
}

View File

@@ -0,0 +1,519 @@
{
"source_file": "trackare-00272363-23100745_00272363_23100745.pdf",
"total_replacements": 538,
"regex_replacements": 240,
"ner_replacements": 39,
"sweep_replacements": 259,
"entities_found": [
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "00272363",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23100745",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "BAYONNE",
"replacement": "[ADRESSE_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "CHIRURGIE UROLOGIE - CHIRURGIE UROLOGIE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "Marie",
"replacement": "[CONTACT_1]",
"source": "regex",
"category": "contact"
},
{
"original": "DUMAS- MARIE-",
"replacement": "[CONTACT_2]",
"source": "regex",
"category": "contact"
},
{
"original": "14 AVENUE FOCH RESIDENCE EUROPE Ville de résidence: BAYONNE",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "Thromb Haemost",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9980424642562866
},
{
"original": "Thromb Haemost",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9986377954483032
},
{
"original": "Becker",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9980295896530151
},
{
"original": "Becker",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9937994480133057
},
{
"original": "Jan Steffel",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9989145994186401
},
{
"original": "Jan Steffel",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9988529086112976
},
{
"original": "Signé — DOULEUR",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8303936123847961
},
{
"original": "MERGEL Sandrine",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.9751890301704407
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9936699271202087
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9956961274147034
},
{
"original": "LAGARRIGUE Juliette",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.97247314453125
},
{
"original": "LAGARRIGUE",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.8378173112869263
},
{
"original": "LAGARRIGUE Juliette",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.978748083114624
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.896230936050415
},
{
"original": "MERGEL Sandrine",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.9844685196876526
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9562546610832214
},
{
"original": "Juliette TRANSDERM",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.993836522102356
},
{
"original": "DUROGESIC",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9719291925430298
},
{
"original": "Juliette TRANSDERM",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9923495054244995
},
{
"original": "DUROGESIC",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.95270174741745
},
{
"original": "LAGARRIGUE Juliette Signé",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.8959382772445679
},
{
"original": "Myriam TOILETTE",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9627387523651123
},
{
"original": "Sandrine SOMMEIL",
"replacement": "[SOIGNANT_10]",
"source": "ner",
"score": 0.977534294128418
},
{
"original": "Myriam S",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.8281614780426025
},
{
"original": "Myriam",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.8114824891090393
},
{
"original": "Myriam",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.807702362537384
},
{
"original": "LAGARRIGUE",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9944831132888794
},
{
"original": "H DISP TRANSDERM DR",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.8065325021743774
},
{
"original": "DUROGESIC",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9934436678886414
},
{
"original": "Signé DUROGESIC",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.8997652530670166
},
{
"original": "YL",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8898364305496216
},
{
"original": "Y.Lammertyn",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9862663149833679
},
{
"original": "Yann Lammertyn",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9977647662162781
},
{
"original": "Y.Lammertyn",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9853658676147461
},
{
"original": "Dufour",
"replacement": "[PERSONNE_7]",
"source": "ner",
"score": 0.8929396271705627
},
{
"original": "Agnes SAINT-",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.8012412190437317
},
{
"original": "Agnes SAINT-",
"replacement": "[PERSONNE_8]",
"source": "ner",
"score": 0.8995113372802734
},
{
"original": "dumas marie helene",
"replacement": "[CONTACT_1]",
"source": "ner",
"score": 0.9211328625679016
},
{
"original": "GOMEZ HELENE",
"replacement": "[CONTACT_3]",
"source": "ner",
"score": 0.9715149402618408
}
]
}