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 +1,621 @@
{
"source_file": "trackare-03000918-23061103_03000918_23061103.pdf",
"total_replacements": 468,
"regex_replacements": 193,
"ner_replacements": 55,
"sweep_replacements": 220,
"entities_found": [
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "03000918",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23061103",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "99999",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "BORDEAUX",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "CHIRURGIE ORTHOPEDIQUE\nDossier Patient\nDétails des patients",
"replacement": "[MEDECIN_2]",
"source": "regex",
"category": "patient"
},
{
"original": "LAWRENCE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "LAWRENCE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "PHILIPPE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "PHILIPPE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "QU CHATORTEGUY Ville de résidence: URCUIT",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "DEROURE DEROURE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9939146637916565
},
{
"original": "Charlène Glyc",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9949393272399902
},
{
"original": "Charlène Glyc",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9967038035392761
},
{
"original": "Charlène Glyc",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9955446124076843
},
{
"original": "Charlène Glyc",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.969345211982727
},
{
"original": "Maialen LANDART",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.9984381794929504
},
{
"original": "Maialen LANDART",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.9990600943565369
},
{
"original": "Maialen LANDART",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.9988568425178528
},
{
"original": "Maialen LANDART",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.999000072479248
},
{
"original": "Maialen LANDART",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.9989607930183411
},
{
"original": "Maialen LANDART",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.9986424446105957
},
{
"original": "CHOHOBI Ana",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.9602993726730347
},
{
"original": "KETOPRO",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8003379106521606
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.980710506439209
},
{
"original": "BI Ana",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8458276987075806
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9844821691513062
},
{
"original": "CHOHOBI Ana",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.8269215822219849
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9943426251411438
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9840306043624878
},
{
"original": "Charlène Glyc",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.8509711027145386
},
{
"original": "Charlène",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.8153020143508911
},
{
"original": "Charlène Glyc",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9931241869926453
},
{
"original": "Maialen LANDART",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.9990251660346985
},
{
"original": "Maialen LANDART",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.9987161159515381
},
{
"original": "Maialen LANDART",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.9987130761146545
},
{
"original": "Maialen LANDART",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.9989032745361328
},
{
"original": "Maialen LANDART",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.9985435605049133
},
{
"original": "Maialen LANDART",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.9983388781547546
},
{
"original": "CHOHOBI Ana",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.9512155652046204
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9890669584274292
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9799405932426453
},
{
"original": "Ana",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.8929616808891296
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9694490432739258
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9698845744132996
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.99278324842453
},
{
"original": "HOBI Ana",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.8000333309173584
},
{
"original": "ACTISKENAN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9924312829971313
},
{
"original": "ANDRIAMIANDRASOA",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.996580958366394
},
{
"original": "Justin Signé",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.8962323665618896
},
{
"original": "ANDRIAMIANDRASOA",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9971392154693604
},
{
"original": "Justin",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9804994463920593
},
{
"original": "Vanessa SOMMEIL",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.8691412210464478
},
{
"original": "Ana A",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.8407105207443237
},
{
"original": "Signé Charlène",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.8169605731964111
},
{
"original": "Ana CHOHOBI",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.9949864149093628
},
{
"original": "Ana CHOHOBI Justin",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.9821653366088867
},
{
"original": "Ana CHOHOBI",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.996239960193634
},
{
"original": "Ana CHOHOBI",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.9981368184089661
},
{
"original": "Ana CHOHOBI",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.9981690645217896
},
{
"original": "Ana CHOHOBI",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.9902242422103882
},
{
"original": "Ana CHOHOBI",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.9967929720878601
},
{
"original": "Ana CHOHOBI",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.9956587553024292
},
{
"original": "BERMUDEZ",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.8850740790367126
},
{
"original": "Ana CHOHOBI",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.9578329920768738
},
{
"original": "J. ANDRIAMIANDRASOA",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9919416308403015
}
]
}