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 +1,45 @@
{
"source_file": "CONSULTATION ANESTHESISTE 23092887.pdf",
"total_replacements": 27,
"regex_replacements": 21,
"ner_replacements": 2,
"sweep_replacements": 4,
"entities_found": [
{
"original": "23642846",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23642846",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "42 BIS CHEMIN DE SALAMON N° Tél : [TEL_1]",
"replacement": "[ADRESSE_2]",
"source": "regex",
"category": "adresse"
},
{
"original": "42 BIS CHEMIN DE SALAMON N° Tél : [TEL_1]",
"replacement": "[ADRESSE_2]",
"source": "regex",
"category": "adresse"
},
{
"original": "Holter",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8225114345550537
},
{
"original": "hartman",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9154958724975586
}
]
}

View File

@@ -0,0 +1,39 @@
{
"source_file": "CRO 23092887.pdf",
"total_replacements": 11,
"regex_replacements": 5,
"ner_replacements": 5,
"sweep_replacements": 1,
"entities_found": [
{
"original": "GOBERT, PHILIPPE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8063299059867859
},
{
"original": "Hartmann",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9881500005722046
},
{
"original": "ANDRIANAVALOMIONONA",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9902159571647644
},
{
"original": "PHILIPPE",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.9659547805786133
},
{
"original": "GOBERT",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.9793516397476196
}
]
}

View File

@@ -0,0 +1,645 @@
{
"source_file": "trackare-22032570-23092887_22032570_23092887.pdf",
"total_replacements": 758,
"regex_replacements": 232,
"ner_replacements": 62,
"sweep_replacements": 464,
"entities_found": [
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22032570",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23092887",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "ANGERS",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "CHIRURGIE VISCERALE - CHIRURGIE VISCERALE\nDossier Patient\nDétails des patients",
"replacement": "[MEDECIN_1]",
"source": "regex",
"category": "patient"
},
{
"original": "42 BIS CHEMIN DE SALAMON Ville de résidence: CASTAGNEDE",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "Hartmann",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8939698934555054
},
{
"original": "Ttes Marie Helene",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9702754020690918
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990850687026978
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990769624710083
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990642666816711
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990990161895752
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990906715393066
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9989051818847656
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.998906672000885
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9976974725723267
},
{
"original": "Marie Helene",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9712438583374023
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9989097118377686
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990799427032471
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990642666816711
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9991166591644287
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990373849868774
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990144968032837
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9989861249923706
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9989013075828552
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9986083507537842
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9971882104873657
},
{
"original": "LEGRAS Claire",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9890294075012207
},
{
"original": "LEGRAS Claire",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9794985055923462
},
{
"original": "LEGRAS Claire",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9954758286476135
},
{
"original": "LEGRAS Claire",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9961704611778259
},
{
"original": "LEGRAS Claire",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.985964834690094
},
{
"original": "DUHALDE",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.8641757369041443
},
{
"original": "Ttes Marie Helene",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8527515530586243
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9337936639785767
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9989829063415527
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9988899230957031
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9991037249565125
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990701079368591
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9988431930541992
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9989482164382935
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9987776279449463
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9991111755371094
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9991048574447632
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990742206573486
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990618228912354
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990651607513428
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990009069442749
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990801811218262
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990798234939575
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9990796446800232
},
{
"original": "Marie Helene DUHALDE",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9985597133636475
},
{
"original": "LEGRAS Claire",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9961652755737305
},
{
"original": "LEGRAS Claire",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9953472018241882
},
{
"original": "LEGRAS Claire",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9026361107826233
},
{
"original": "LEGRAS Claire",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9932544231414795
},
{
"original": "LEGRAS Claire",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8886913061141968
},
{
"original": "Goudarz",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9282044768333435
},
{
"original": "TAGHVA",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9826955795288086
},
{
"original": "Goudarz",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9198237061500549
},
{
"original": "Goudarz",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9242982864379883
},
{
"original": "ARW Goudarz",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9336225390434265
},
{
"original": "Pierre KUHN- B",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8100298643112183
},
{
"original": "Goudarz TAGHVA",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9900467991828918
},
{
"original": "Hartmann",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9886800050735474
},
{
"original": "Goudarz TAGHVA",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.982764720916748
},
{
"original": "Hartmann",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9743219614028931
},
{
"original": "Hartmann",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9654439091682434
}
]
}