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 +1,93 @@
{
"source_file": "CRH 23096278.pdf",
"total_replacements": 245,
"regex_replacements": 234,
"ner_replacements": 6,
"sweep_replacements": 5,
"entities_found": [
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "10100673481",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "10100673481",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9728294610977173
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.899665355682373
},
{
"original": "PARISET Vincent",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.8273124098777771
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9728294610977173
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.899665355682373
},
{
"original": "PARISET Vincent",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9123775362968445
}
]
}

View File

@@ -0,0 +1,357 @@
{
"source_file": "trackare-BA162505-23096278_BA162505_23096278.pdf",
"total_replacements": 288,
"regex_replacements": 161,
"ner_replacements": 39,
"sweep_replacements": 88,
"entities_found": [
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096278",
"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": "3 SQUARE ARRIBE LABOURD Ville de résidence: BAYONNE",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "T BRAYER Céline",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.9160110354423523
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9694432020187378
},
{
"original": "BRAYER Céline",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.983363687992096
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9925718903541565
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9980807304382324
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9971442222595215
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9971673488616943
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9960460662841797
},
{
"original": "Marie Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9977964758872986
},
{
"original": "Marie Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9970100522041321
},
{
"original": "Marie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9533615112304688
},
{
"original": "Marie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8900837898254395
},
{
"original": "Marie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8472509384155273
},
{
"original": "Marie Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9938732981681824
},
{
"original": "Céline Signé",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.995021402835846
},
{
"original": "T BRAYER Céline",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.8437494039535522
},
{
"original": "T BRAYER Céline",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.9160110354423523
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9694432020187378
},
{
"original": "BRAYER Céline",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.9830801486968994
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9925985932350159
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9980807304382324
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9971442222595215
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9971673488616943
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9960460662841797
},
{
"original": "Marie Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9968230128288269
},
{
"original": "Marie Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9944890141487122
},
{
"original": "Marie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9509435892105103
},
{
"original": "Marie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8602900505065918
},
{
"original": "Marie Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9938732981681824
},
{
"original": "Céline Signé",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.995021402835846
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.986012876033783
},
{
"original": "MAJCHRZAK",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9706268906593323
},
{
"original": "Camille Marie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9422469139099121
},
{
"original": "Camille Marie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9562848806381226
},
{
"original": "Camille Marie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9854369163513184
},
{
"original": "Benjamine Briaud",
"replacement": "[PATIENT_2]",
"source": "ner",
"score": 0.9960151314735413
},
{
"original": "Camille Marie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9256747961044312
},
{
"original": "PARISET MELANIE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9820629358291626
},
{
"original": "SQUARE ARRIBE LABOURT",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9328292012214661
}
]
}