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 +1,75 @@
{
"source_file": "CONSULTATION ANESTH 23085314.pdf",
"total_replacements": 25,
"regex_replacements": 15,
"ner_replacements": 5,
"sweep_replacements": 5,
"entities_found": [
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "N° Tél :",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "N° Tél :",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "N° Tél :",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "BERENGUER Arantxa",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9962565898895264
},
{
"original": "Cormack",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8425434231758118
},
{
"original": "BERENGUER Arantxa",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9930645823478699
},
{
"original": "Cormack",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8973753452301025
},
{
"original": "BERENGUER Arantxa",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9980117082595825
}
]
}

View File

@@ -0,0 +1,963 @@
{
"source_file": "trackare-11009950-23085314_11009950_23085314.pdf",
"total_replacements": 713,
"regex_replacements": 245,
"ner_replacements": 97,
"sweep_replacements": 371,
"entities_found": [
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11009950",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23085314",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "284106442201271",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "284106442201271",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "64422",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "OLORON STE MARIE",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "BERENGUER",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "BERENGUER",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "BERENGUER",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "ARANTXA",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "ARANTXA",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "ARANTXA",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "24",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9876900315284729
},
{
"original": "JAOUEN GUILLEMAUD",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9968672394752502
},
{
"original": "NOEL Eva",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9802482724189758
},
{
"original": "NOEL Eva Glyc",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.975318193435669
},
{
"original": "NOEL Eva Glyc",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9802388548851013
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9929487705230713
},
{
"original": "LARRIEU-- NARZABAL Julie S",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9517667293548584
},
{
"original": "RRIEU-- NARZABAL Julie S",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9034642577171326
},
{
"original": "-- NARZABAL Julie S",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8716609477996826
},
{
"original": "Anne Marie ETCHELECU",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9988856911659241
},
{
"original": "Anne Marie ETCHELECU",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9988398551940918
},
{
"original": "Anne Marie Signé",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9859564900398254
},
{
"original": "Anne Marie ETCHELECU",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9989431500434875
},
{
"original": "Anne Marie ETCHELECU",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9989845156669617
},
{
"original": "Anne Marie ETCHELECU S",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9740927815437317
},
{
"original": "Anne Marie ETCHELECU",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9988486766815186
},
{
"original": "Anne Marie ETCHELECU S",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9714905023574829
},
{
"original": "Anne Marie ETCHELECU",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9990334510803223
},
{
"original": "Nathalie JAUREGUIBERRY",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9988632798194885
},
{
"original": "Nathalie JAUREGUIBERRY",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9988389015197754
},
{
"original": "Nathalie JAUREGUIBERRY",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9979246854782104
},
{
"original": "DE SOUSA PEREIRA Sandy",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9776270985603333
},
{
"original": "DE SOUSA PEREIRA Sandy Signé",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9862431883811951
},
{
"original": "DE SOUSA PEREIRA Sandy Signé",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9842889904975891
},
{
"original": "Pascale TRANSDER",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8544905185699463
},
{
"original": "NOEL Eva",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.900775671005249
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8014915585517883
},
{
"original": "ALPRAZOLAM ARW",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9022403955459595
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9957764744758606
},
{
"original": "ALPRAZOLAM ARW",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9946235418319702
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9927288889884949
},
{
"original": "ALPRAZOLAM ARW",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9861032366752625
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9826039671897888
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.962019145488739
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9681426882743835
},
{
"original": "NOEL Eva",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9306764602661133
},
{
"original": "NARZABAL Julie POC",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9717569351196289
},
{
"original": "NARZABAL Julie POC",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9501419067382812
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9802452325820923
},
{
"original": "Eva Glyc",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9287899732589722
},
{
"original": "NOEL Eva",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.8241932392120361
},
{
"original": "LARRIEU-- NARZABAL Julie S",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9582419991493225
},
{
"original": "LARRIEU-- NARZABAL Julie S",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9181577563285828
},
{
"original": "LARRIEU-- NARZABAL Julie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.969001829624176
},
{
"original": "Anne Marie ETCHELECU",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9978410601615906
},
{
"original": "Anne Marie ETCHELECU",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.997837483882904
},
{
"original": "Anne Marie Signé",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.993918776512146
},
{
"original": "Anne Marie",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9958086013793945
},
{
"original": "Anne Marie ETCHELECU",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9988101124763489
},
{
"original": "Anne Marie ETCHELECU",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9988646507263184
},
{
"original": "Anne Marie ETCHELECU S",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9740927815437317
},
{
"original": "Anne Marie ETCHELECU",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9988486766815186
},
{
"original": "Anne Marie ETCHELECU",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9986200928688049
},
{
"original": "Nathalie JAUREGUIBERRY",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9988853931427002
},
{
"original": "Nathalie JAUREGUIBERRY",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.998891294002533
},
{
"original": "Nathalie JAUREGUIBERRY",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9988731145858765
},
{
"original": "DE SOUSA PEREIRA Sandy Signé",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9842424988746643
},
{
"original": "DE SOUSA PEREIRA Sandy Signé",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9565775394439697
},
{
"original": "DE SOUSA PEREIRA Sandy",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9814987182617188
},
{
"original": "Pascale TRANSDER",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.854384183883667
},
{
"original": "NOEL Eva",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9774565100669861
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9889230728149414
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9347265362739563
},
{
"original": "LARROUY Pascale",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9904125332832336
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9461460709571838
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8819496035575867
},
{
"original": "Eva",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.8080384135246277
},
{
"original": "NOEL Eva",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9232694506645203
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9413320422172546
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9783012270927429
},
{
"original": "LARRIEU--",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.8172709345817566
},
{
"original": "NARZABAL Julie",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9069545865058899
},
{
"original": "LARROUY Pascale Signé",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.90139240026474
},
{
"original": "Marion Signé",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9967038631439209
},
{
"original": "Marion SOINS IDE",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.8947656750679016
},
{
"original": "Marion SOINS",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.951505184173584
},
{
"original": "Marion Signé",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9707066416740417
},
{
"original": "Marion Signé",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9652156233787537
},
{
"original": "Marion Signé",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9656715989112854
},
{
"original": "Anne Marie",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.8837798833847046
},
{
"original": "Sandy DE TOILETTE PRE-",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9485659599304199
},
{
"original": "Sandy DE BRACELET",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9948227405548096
},
{
"original": "Marion SOINS",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9188761711120605
},
{
"original": "DOULEUR",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9575517773628235
},
{
"original": "Anne Marie DOULEUR",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9879066348075867
},
{
"original": "Nathalie SOMMEIL",
"replacement": "[SOIGNANT_15]",
"source": "ner",
"score": 0.9953840374946594
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9983739852905273
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.997646689414978
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9979262948036194
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9982788562774658
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9973669648170471
},
{
"original": "Goudarz TAGHVA PASSAND",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9859689474105835
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9975273013114929
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9981498122215271
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.998231828212738
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_12]",
"source": "ner",
"score": 0.9984220862388611
},
{
"original": "Mère Patou Bernadette",
"replacement": "[CONTACT_2]",
"source": "ner",
"score": 0.9699068069458008
}
]
}