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 +1,489 @@
{
"source_file": "trackare-07026002-23061319_07026002_23061319.pdf",
"total_replacements": 620,
"regex_replacements": 252,
"ner_replacements": 34,
"sweep_replacements": 334,
"entities_found": [
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07026002",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061319",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "MONTBELIARD",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "GYNECOLOGIE BAYONNE - GYNECOLOGIE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "6 RUE CHANDIRU BAITA Ville de résidence: URRUGNE",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "Mademoiselle MORENO ANITA",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9171513915061951
},
{
"original": "LAGARRIGUE Juliette",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9579103589057922
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9478012919425964
},
{
"original": "DI LULLO Emilie",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9637511372566223
},
{
"original": "DI LULLO Emilie",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9698300361633301
},
{
"original": "DI LULLO Emilie",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9742663502693176
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9841904044151306
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9982695579528809
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9976927638053894
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.982537031173706
},
{
"original": "LAGARRIGUE Juliette",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9831036925315857
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9933406710624695
},
{
"original": "DI LULLO Emilie",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9944068789482117
},
{
"original": "DI LULLO Emilie",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.8899135589599609
},
{
"original": "DI LULLO Emilie",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9363398551940918
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9874768257141113
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9976192116737366
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9969990849494934
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_16]",
"source": "ner",
"score": 0.9910719394683838
},
{
"original": "Juliette",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8326550126075745
},
{
"original": "Sophie",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.8490750789642334
},
{
"original": "Emilie DI SOMMEIL",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9750807285308838
},
{
"original": "LAGARRIGUE",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.976455807685852
},
{
"original": "Sophie BARBE",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9946913719177246
},
{
"original": "Sophie BARBE",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9850058555603027
},
{
"original": "Sophie BARBE",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.8749452233314514
},
{
"original": "Sophie BARBE",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9914361834526062
},
{
"original": "Sophie BARBE",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.998176634311676
},
{
"original": "Sophie BARBE",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9982059001922607
},
{
"original": "Sophie BARBE",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9977426528930664
},
{
"original": "Sophie BARBE",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9949286580085754
},
{
"original": "Sophie BARBE",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.996090829372406
},
{
"original": "ESI Béatrice",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8023673892021179
},
{
"original": "Béatrice BLOC",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9533495903015137
}
]
}