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 +1,63 @@
{
"source_file": "CRH 23116191.pdf",
"total_replacements": 126,
"regex_replacements": 115,
"ner_replacements": 5,
"sweep_replacements": 6,
"entities_found": [
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "10002083912",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "DUTHEIL",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9889217019081116
},
{
"original": "VAREIL",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9814341068267822
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8010601997375488
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9867895841598511
},
{
"original": "SALABERRY Victoire",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.966895580291748
}
]
}

View File

@@ -0,0 +1,417 @@
{
"source_file": "trackare-BA045058-23116191_BA045058_23116191.pdf",
"total_replacements": 305,
"regex_replacements": 147,
"ner_replacements": 49,
"sweep_replacements": 109,
"entities_found": [
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23116191",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "BIARRITZ",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "90 IMPASSE DE L OSSAU Ville de résidence: ARCANGUES",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "GUILLEMAUD JAOUEN GUILLEMAUD",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9908361434936523
},
{
"original": "MAJCHRZAK Camille",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9877211451530457
},
{
"original": "KWIKPEN SOL MAJCHRZAK Camille",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9015160799026489
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9975671768188477
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9973106384277344
},
{
"original": "Marie ORALE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9948469996452332
},
{
"original": "AJCHRZAK Camille",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9348159432411194
},
{
"original": "Marie ORALE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9948065280914307
},
{
"original": "MAJCHRZAK Camille",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9958699345588684
},
{
"original": "MAJCHRZAK Camille",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9966215491294861
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9979076385498047
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9968183636665344
},
{
"original": "MAJCHRZAK Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9882935285568237
},
{
"original": "T BRAYER Céline",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.8394927978515625
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9917473196983337
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9871574640274048
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9914770722389221
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9866377115249634
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.995118260383606
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9947945475578308
},
{
"original": "MAJCHRZAK Camille",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.926320493221283
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9124571681022644
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9329898953437805
},
{
"original": "Camille GELULE",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9062533378601074
},
{
"original": "CHRZAK Camille",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9349265098571777
},
{
"original": "Marie S",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9647573828697205
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9965357780456543
},
{
"original": "Marie Signé",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9909256100654602
},
{
"original": "BRAYER Céline",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.963607668876648
},
{
"original": "Céline",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.8084023594856262
},
{
"original": "Carine",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.8984113931655884
},
{
"original": "Céline",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.8856143355369568
},
{
"original": "Céline",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9169430732727051
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9972590208053589
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.8585644960403442
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.8386083245277405
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.8920542001724243
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.8211178183555603
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9706887006759644
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9589396715164185
},
{
"original": "Evane BOULARD",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.9497519731521606
},
{
"original": "Ferriman-Gallwey",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.995330810546875
},
{
"original": "Camille Marie",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9862009286880493
},
{
"original": "Fabrice",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.8957215547561646
},
{
"original": "DESRUES",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.8540062308311462
},
{
"original": "Fabrice PREVISCAN",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9775803685188293
},
{
"original": "DESRUES",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.9814857840538025
},
{
"original": "SON EPOUX",
"replacement": "[CONTACT_1]",
"source": "ner",
"score": 0.9440138339996338
},
{
"original": "Soeur picot cklementine",
"replacement": "[PATIENT_2]",
"source": "ner",
"score": 0.9943422079086304
}
]
}