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 23060661.pdf",
"total_replacements": 34,
"regex_replacements": 33,
"ner_replacements": 0,
"sweep_replacements": 1,
"entities_found": [
{
"original": "23605230",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23605230",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23605230",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "137 HAMEAU DE GARLATZETXE ALAIA N° Tél : [TEL_1]",
"replacement": "[ADRESSE_2]",
"source": "regex",
"category": "adresse"
},
{
"original": "137 HAMEAU DE GARLATZETXE ALAIA N° Tél : [TEL_1]",
"replacement": "[ADRESSE_2]",
"source": "regex",
"category": "adresse"
},
{
"original": "137 HAMEAU DE GARLATZETXE ALAIA N° Tél : [TEL_1]",
"replacement": "[ADRESSE_2]",
"source": "regex",
"category": "adresse"
}
]
}

View File

@@ -0,0 +1,399 @@
{
"source_file": "trackare-20023294-23060661_20023294_23060661.pdf",
"total_replacements": 559,
"regex_replacements": 212,
"ner_replacements": 27,
"sweep_replacements": 320,
"entities_found": [
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "20023294",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23060661",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "HENDAYE",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "CHIRURGIE UROLOGIE - CHIRURGIE UROLOGIE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "137 HAMEAU DE GARLATZETXE ALAIA Ville de résidence: BIRIATOU",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "BURTIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9624838829040527
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9596015214920044
},
{
"original": "MG MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9880596399307251
},
{
"original": "SPASFON C",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.82975172996521
},
{
"original": "MG MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9880989193916321
},
{
"original": "SPASFON C",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8369625210762024
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9652863144874573
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9845430254936218
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9779694080352783
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9803921580314636
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9938207268714905
},
{
"original": "MOULIN Thomas S",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9760910272598267
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9479340314865112
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9811330437660217
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8176030516624451
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.96531081199646
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9867898225784302
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9793215990066528
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9868799448013306
},
{
"original": "MONOPROST",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9935153126716614
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.936667799949646
},
{
"original": "MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9423412084579468
},
{
"original": "SOL MOULIN Thomas",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.974672794342041
},
{
"original": "MOULIN Thomas S",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8823014497756958
},
{
"original": "Céline Réalisé",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.8605408668518066
},
{
"original": "YL",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9465919137001038
},
{
"original": "Gastesi Mayie",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9566909074783325
}
]
}