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 +1,165 @@
{
"source_file": "CRH 23056364.pdf",
"total_replacements": 82,
"regex_replacements": 79,
"ner_replacements": 0,
"sweep_replacements": 3,
"entities_found": [
{
"original": "10110601324",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101096005",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100163277",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101639580",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004606595",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102268702",
"replacement": "[RPPS_8]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102272209",
"replacement": "[RPPS_9]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101856135",
"replacement": "[RPPS_10]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002815024",
"replacement": "[RPPS_11]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100817005",
"replacement": "[RPPS_12]",
"source": "regex",
"category": "rpps"
},
{
"original": "10110601324",
"replacement": "[RPPS_1]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101096005",
"replacement": "[RPPS_2]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100163277",
"replacement": "[RPPS_3]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101639580",
"replacement": "[RPPS_4]",
"source": "regex",
"category": "rpps"
},
{
"original": "10004606595",
"replacement": "[RPPS_5]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101480506",
"replacement": "[RPPS_6]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100858090",
"replacement": "[RPPS_7]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102268702",
"replacement": "[RPPS_8]",
"source": "regex",
"category": "rpps"
},
{
"original": "10102272209",
"replacement": "[RPPS_9]",
"source": "regex",
"category": "rpps"
},
{
"original": "10002815024",
"replacement": "[RPPS_11]",
"source": "regex",
"category": "rpps"
},
{
"original": "10100817005",
"replacement": "[RPPS_12]",
"source": "regex",
"category": "rpps"
},
{
"original": "10101856135",
"replacement": "[RPPS_10]",
"source": "regex",
"category": "code_barre"
},
{
"original": "secr.medint@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
},
{
"original": "secr.medint@ch-cotebasque.fr",
"replacement": "[EMAIL_1]",
"source": "regex",
"category": "email"
}
]
}

View File

@@ -0,0 +1,363 @@
{
"source_file": "trackare-22012288-23056463_22012288_23056463.pdf",
"total_replacements": 332,
"regex_replacements": 137,
"ner_replacements": 27,
"sweep_replacements": 168,
"entities_found": [
{
"original": "22012288",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22012288",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22012288",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22012288",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22012288",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22012288",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22012288",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22012288",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22012288",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22012288",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22012288",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22012288",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22012288",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22012288",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23056463",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056463",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056463",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056463",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056463",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056463",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056463",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056463",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056463",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056463",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056463",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056463",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056463",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056463",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "krasnoarmeyck",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "MED INTERNE RHUMATOLOGIE - RHUMATOLOGIE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "ROUTE D ABENS Ville de résidence: TARDETS SORHOLUS",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "BURTIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9690310955047607
},
{
"original": "Laure CURUTCHET",
"replacement": "[MEDECIN_8]",
"source": "ner",
"score": 0.9980459809303284
},
{
"original": "DESINFECTION MAYA Bernadette",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9713426828384399
},
{
"original": "PAQUAY DE PLATER Camille",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9125579595565796
},
{
"original": "PAQUAY DE PLATER Camille",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9620047211647034
},
{
"original": "Thomas",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.88099205493927
},
{
"original": "IZALGI",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8640586137771606
},
{
"original": "Thomas",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9281516075134277
},
{
"original": "IZALGI",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9184188842773438
},
{
"original": "MAYA Bernadette",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9372833371162415
},
{
"original": "PAQUAY DE PLATER Camille Signé — NAPROSYNE",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9847782850265503
},
{
"original": "NAPROSYNE",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9344480633735657
},
{
"original": "PAQUAY DE PLATER Camille Signé",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9925532937049866
},
{
"original": "LANSOPRAZOLE",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.925342857837677
},
{
"original": "Thomas",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.877484142780304
},
{
"original": "IZALGI",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8698870539665222
},
{
"original": "IZALGI",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8472633957862854
},
{
"original": "Camille PAQUAY",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9980012774467468
},
{
"original": "Camille PAQUAY",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9959917068481445
},
{
"original": "Camille PAQUAY",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9963905811309814
},
{
"original": "Camille PAQUAY",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9627436399459839
},
{
"original": "Camille PAQUAY",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9530572295188904
},
{
"original": "Camille PAQUAY",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9949723482131958
},
{
"original": "NAPROSYNE",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.8297728300094604
},
{
"original": "ERIE LANSOPRAZOLE",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9303933382034302
},
{
"original": "Camille PAQUAY",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9675116539001465
},
{
"original": "Whipple",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8883078098297119
}
]
}