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": "SCAN 23119469.pdf",
"total_replacements": 24,
"regex_replacements": 17,
"ner_replacements": 2,
"sweep_replacements": 5,
"entities_found": [
{
"original": "238066452800261",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "64528",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "AGUERRE Carole",
"replacement": "[MEDECIN_1]",
"source": "regex",
"category": "patient"
},
{
"original": "IRIBARNE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "LABY",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "ALICE",
"replacement": "[PATIENT_3]",
"source": "regex",
"category": "patient"
},
{
"original": "ALICE",
"replacement": "[PATIENT_3]",
"source": "regex",
"category": "patient"
},
{
"original": "ALICE LABY",
"replacement": "[PATIENT_2]",
"source": "ner",
"score": 0.8545963168144226
},
{
"original": "IRIBARNE ALICE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.886472761631012
}
]
}

View File

@@ -0,0 +1,549 @@
{
"source_file": "trackare--23119469__23119469.pdf",
"total_replacements": 576,
"regex_replacements": 141,
"ner_replacements": 70,
"sweep_replacements": 365,
"entities_found": [
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119469",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "SUHESCUN",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "MEDECINE PNEUMOLOGIE - PNEUMOLOGIE PHTISIOLOGIE HC\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_3]",
"source": "regex",
"category": "patient"
},
{
"original": "CHEMIN SALIKARTE ST JEAN PIED DE PORT Ville de résidence: ST JEAN PIED DE PORT",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "Sylvie AMESTOY",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9850256443023682
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9966958165168762
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.996241569519043
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9986715316772461
},
{
"original": "Sylvie AMESTOY",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.998165488243103
},
{
"original": "Sylvie AMESTOY",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9973591566085815
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9979572296142578
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9989134669303894
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9988982081413269
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9985060691833496
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9971041679382324
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9975624084472656
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9988703727722168
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9988747835159302
},
{
"original": "Anna",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9718072414398193
},
{
"original": "Anna Signé",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8201130032539368
},
{
"original": "Anna",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9590686559677124
},
{
"original": "Anna Signé",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8450631499290466
},
{
"original": "T ANDRE Alexia",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.8840673565864563
},
{
"original": "T ANDRE Alexia",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.96281498670578
},
{
"original": "SA",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9015544652938843
},
{
"original": "MALECK MAMODE Anna",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9080145955085754
},
{
"original": "Anna Ttes",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8237188458442688
},
{
"original": "Anna Ttes",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8343600630760193
},
{
"original": "Anna Ttes",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8014604449272156
},
{
"original": "Sylvie AMESTOY",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9798834323883057
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9735360145568848
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.998913586139679
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9986557960510254
},
{
"original": "Sylvie AMESTOY",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9980207085609436
},
{
"original": "Sylvie AMESTOY",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9981078505516052
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9980226755142212
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9975212812423706
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9989134669303894
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9988982081413269
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9985083341598511
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9983563423156738
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9975624084472656
},
{
"original": "Marie Pierre LORDA",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.997594952583313
},
{
"original": "Anna",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.920114278793335
},
{
"original": "Anna",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9620068073272705
},
{
"original": "Anna Signé",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.994823157787323
},
{
"original": "Anna Signé",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9930379986763
},
{
"original": "Anna S",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9411695003509521
},
{
"original": "SACHET ANDRE Alexia",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.8800231218338013
},
{
"original": "SACHET ANDRE Alexia",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.8998651504516602
},
{
"original": "Anna Arrêté",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.984634280204773
},
{
"original": "Anna Signé",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9347332119941711
},
{
"original": "Marie Pierre",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9470648169517517
},
{
"original": "Marie Pierre",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9331717491149902
},
{
"original": "Alexia ANDRE",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.9988191723823547
},
{
"original": "Alexia ANDRE",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.998827338218689
},
{
"original": "Anna MALECK MAMODE",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9884294271469116
},
{
"original": "Anna MALECK MAMODE",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9903286695480347
},
{
"original": "Anna MALECK",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9630588293075562
},
{
"original": "Anna MALECK",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.998670220375061
},
{
"original": "Alexia ANDRE",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.9990370869636536
},
{
"original": "Alexia ANDRE",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.9989717602729797
},
{
"original": "Alexia ANDRE",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.9990056753158569
},
{
"original": "Alexia ANDRE",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.9990013837814331
},
{
"original": "Alexia ANDRE",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.9989369511604309
},
{
"original": "Alexia ANDRE",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.9989919662475586
},
{
"original": "Anna MALECK",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9984159469604492
},
{
"original": "Anna MALECK",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9982485771179199
},
{
"original": "Anna MALECK",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9982541799545288
},
{
"original": "Anna MALECK",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9983265995979309
},
{
"original": "Alexia ANDRE",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.9970353841781616
},
{
"original": "Anna MALECK",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9965507984161377
},
{
"original": "Alexia ANDRE",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.9869233965873718
},
{
"original": "Alexia ANDRE",
"replacement": "[SOIGNANT_1]",
"source": "ner",
"score": 0.9800338745117188
}
]
}