verbesserungen e-invoice
This commit is contained in:
parent
0d9c9d8615
commit
f758c4a6ac
39 changed files with 10 additions and 400728 deletions
|
|
@ -1,53 +0,0 @@
|
|||
# ML Models
|
||||
|
||||
Wir verwenden bei Alexander-Global Logistics ein standard Invoice ML Modell. Dieses basiert im Grund auf unserem offizielen spacy modell 'invoice-de-0.1.0'.
|
||||
|
||||
|
||||
|
||||
## Modell Nachtrainieren
|
||||
|
||||
Das Modell bei Alexander Logistics läst sich in der Dev Umggebung bei Bedarf nachtrainieren. Dazu geht man wie folgt vor:
|
||||
|
||||
**1.)** Aktuelles Modell auf Tikal Cloud Server sichern:
|
||||
|
||||
$ ssh imixs@master-1.tikal.imixs.com
|
||||
$ cd tikal-cloud/
|
||||
$ ./apps/alexander-logistics.office-workflow.de/ml_model_backup.sh
|
||||
|
||||
# Falls es zu einem io/error kommt, muss der spacy ml pod neu gestartet werden!
|
||||
|
||||
|
||||
**2.)** Die Tikal-Cloud Pullen
|
||||
|
||||
**3.)** Um auf dem aktuellen Modell weiter zu trainierne, den Inhalt des invoice-de-0.1.0 Folders aus dem Backup directory in die lokale Dev Umgebung kopieren /
|
||||
um ein neues Modell zu genereiren einfach den localen ordner 'invoice-de-0.1.0' umbenennen oder leeren.
|
||||
|
||||
**4.)** Jetzt lokal den Trainingsserver aufrufen
|
||||
|
||||
http://localhost:8081/api/openapi-ui/index.html
|
||||
|
||||
und das training beginnen mit der datei 'training-config-prod.xml'. Man kann das training 3-4 mal durchführen.
|
||||
|
||||
|
||||
**5.)** Nun kann man die Inhalte des invoice-de-0.1.0 Folders zurück auf den Tikal in den modell folder /invoice-de-0.1.0 einspielen
|
||||
|
||||
**6.)** Nun die änderungen nach Git Puschen.
|
||||
|
||||
**7.)** auf dem Tikal Sever nun das aktuellisete Modell wieder einspielen
|
||||
|
||||
$ git pull
|
||||
$ ./apps/alexander-logistics.office-workflow.de/ml_model_deploy.sh invoice-de-0.1.0/
|
||||
|
||||
|
||||
|
||||
|
||||
## 22.05.2021 - invoice-de-0.1.0
|
||||
|
||||
NER=2.1948
|
||||
|
||||
|
||||
## 17.02.2020 - invoice-de-0.1.0
|
||||
|
||||
Modell trainiert anhand der alexander-logistics Produtiv daten
|
||||
|
||||
|
||||
|
|
@ -1,491 +0,0 @@
|
|||
# Test Protokoll Alexander Logistic invoice-de-0.1.0
|
||||
|
||||
|
||||
**Validierung**
|
||||
f4eaceda-f28a-4394-928e-1a05daaf2760
|
||||
a5d1e7fe-d74a-4fa2-9b06-3221865759fa
|
||||
c0290497-f613-4492-81b6-4ae1e1680029
|
||||
d8e3fce4-d11c-46a4-8ba0-369b4c6e902f
|
||||
8b766f35-828a-41f1-be04-00b4b62da4d0
|
||||
|
||||
|
||||
|
||||
**********************************************************************
|
||||
** invoice-de-0.1.0-falsemodell
|
||||
**12.10.2021 15:50** (sort order created)
|
||||
**********************************************************************
|
||||
workflow.query ($workflowgroup:"Rechnungseingang" OR $workflowgroup:"Sachrechnung") AND ($taskid:5900)
|
||||
workflow.pagesize 500
|
||||
ml.training.filepattern .pdf
|
||||
ml.training.iterations 10
|
||||
ml.training.dropoutrate 0,25
|
||||
multiOccurrence false
|
||||
ml.training.quality LOW
|
||||
min_losses 0
|
||||
|
||||
RESULT
|
||||
-----------------------------------------------------------------------
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 53.33% (200)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 31.47% (118)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 15.2% (57)
|
||||
imixs-ml-training_1 | ...... average NER = 17.195895012525614
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 51.73% (194)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 32.8% (123)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 15.47% (58)
|
||||
imixs-ml-training_1 | ...... average NER = 6.50170386961344
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 53.87% (202)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 31.73% (119)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 14.4% (54)
|
||||
imixs-ml-training_1 | ...... average NER = 4.8940276912225
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 52.8% (198)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 32% (120)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 15.2% (57)
|
||||
imixs-ml-training_1 | ...... average NER = 3.9605563888416824
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 54.13% (203)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 29.6% (111)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 16.27% (61)
|
||||
imixs-ml-training_1 | ...... average NER = 3.744507591826106
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 53.07% (199)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 31.2% (117)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 15.73% (59)
|
||||
imixs-ml-training_1 | ...... average NER = 2.8395576715820736
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 53.87% (202)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 32% (120)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 14.13% (53)
|
||||
imixs-ml-training_1 | ...... average NER = 2.6799682681142363
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 53.6% (201)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 31.47% (118)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 14.93% (56)
|
||||
imixs-ml-training_1 | ...... average NER = 2.520244211218683
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 49.33% (185)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 34.93% (131)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 15.73% (59)
|
||||
imixs-ml-training_1 | ...... average NER = 2.1511980661715193
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 53.87% (202)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 31.2% (117)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 14.93% (56)
|
||||
imixs-ml-training_1 | ...... average NER = 2.2739690429824475
|
||||
|
||||
|
||||
|
||||
**13.10.2021 12:00**
|
||||
workflow.query ($workflowgroup:"Rechnungseingang" OR $workflowgroup:"Sachrechnung") AND ($taskid:5900)
|
||||
workflow.pagesize 500
|
||||
ml.training.filepattern .pdf|.PDF
|
||||
ml.training.iterations 10
|
||||
ml.training.dropoutrate 0,25
|
||||
multiOccurrence false
|
||||
ml.training.quality LOW
|
||||
min_losses 0
|
||||
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 61.33% (230)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 38.67% (145)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 3.790466332166552
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 61.07% (229)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 38.93% (146)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 3.160620521438082
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 58.13% (218)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 41.87% (157)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 2.636420357788331
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 58.13% (218)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 41.87% (157)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 2.506552163520219
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 58.93% (221)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 41.07% (154)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 2.3495061575286793
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 59.47% (223)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 40.53% (152)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 1.9351332692220107
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 61.33% (230)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 38.67% (145)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 1.8881396005118698
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 57.87% (217)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 42.13% (158)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 1.9754112840739593
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 59.73% (224)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 40.27% (151)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 1.7839739270522237
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 59.73% (224)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 40.27% (151)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 1.6024293913431429
|
||||
|
||||
|
||||
|
||||
|
||||
**********************************************************************
|
||||
** invoice-de-0.1.0
|
||||
**12.10.2021 15:50** (sort order created)
|
||||
**********************************************************************
|
||||
workflow.query ($workflowgroup:"Rechnungseingang" OR $workflowgroup:"Sachrechnung") AND ($taskid:5900)
|
||||
workflow.pagesize 500
|
||||
ml.training.filepattern .pdf|.PDF
|
||||
ml.training.iterations 10
|
||||
ml.training.dropoutrate 0,25
|
||||
multiOccurrence true
|
||||
ml.training.quality LOW
|
||||
min_losses 0
|
||||
|
||||
|
||||
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 68.27% (256)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 31.47% (118)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 21.57255353509432
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 67.73% (254)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 32.27% (121)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 8.249835149395697
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 68.53% (257)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 31.2% (117)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 5.892598287488733
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 68.53% (257)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 31.2% (117)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 4.964129124089013
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 68.53% (257)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 31.2% (117)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 3.5603186705177947
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 67.2% (252)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 32.53% (122)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 2.692053828307031
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 68% (255)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 31.73% (119)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 2.3509401762802873
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 65.87% (247)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 34.13% (128)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 2.2695994889458104
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 68.27% (256)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 31.47% (118)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 1.844410364015416
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 70.67% (265)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 29.07% (109)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 1.6153951610034658
|
||||
|
||||
|
||||
page=1 (count=500)
|
||||
--------------------------------
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 69.6% (261)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 30.4% (114)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 7.093659738880595
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 66.4% (249)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 33.6% (126)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 5.201780406598962
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 68.27% (256)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 31.73% (119)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 3.8116329003426204
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 66.67% (250)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 33.33% (125)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 3.3164488404836154
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 66.93% (251)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 33.07% (124)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 2.7822570929398576
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 69.07% (259)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 30.93% (116)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 2.31773083524846
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 68.8% (258)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 31.2% (117)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 2.165804551920185
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 66.4% (249)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 33.6% (126)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 1.9591955652007715
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 66.4% (249)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 33.6% (126)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 1.5473874007025803
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 375
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 65.87% (247)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 34.13% (128)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 1.705957084193204
|
||||
imixs-ml-training_1 | |#]
|
||||
imixs-ml-training_1 |
|
||||
|
||||
page=0 (count=1000)
|
||||
--------------------------------
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 67.47% (506)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 32.53% (244)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 3.2147245242951565
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 68.8% (516)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 31.07% (233)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.13% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 2.2084385109690565
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 67.73% (508)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 32.27% (242)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0% (0)
|
||||
imixs-ml-training_1 | ...... average NER = 2.1797281610496464
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 67.2% (504)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 32.67% (245)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.13% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 1.8908819163368502
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 66% (495)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 33.87% (254)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.13% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 1.7774978150912477
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 67.6% (507)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 32.27% (242)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.13% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 1.669098427922433
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 67.33% (505)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 32.53% (244)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.13% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 1.6048149396167861
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 67.6% (507)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 32.27% (242)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.13% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 1.4026393956412981
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 67.87% (509)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 32% (240)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.13% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 1.1139796046407426
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 65.87% (494)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 34% (255)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.13% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 1.2621875029460226
|
||||
|
||||
|
||||
|
||||
page=1 (count=1000)
|
||||
--------------------------------
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 63.47% (476)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 36.4% (273)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.13% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 3.7501272727903876
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 64% (480)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 35.87% (269)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.13% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 2.7749715296165482
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 65.47% (491)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 34.27% (257)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (2)
|
||||
imixs-ml-training_1 | ...... average NER = 2.191986221088383
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 63.2% (474)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 36.53% (274)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (2)
|
||||
imixs-ml-training_1 | ...... average NER = 1.836000005105162
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 64.8% (486)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 34.93% (262)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (2)
|
||||
imixs-ml-training_1 | ...... average NER = 1.629252182245437
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 64.27% (482)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 35.47% (266)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (2)
|
||||
imixs-ml-training_1 | ...... average NER = 1.5023185259959349
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 63.6% (477)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 36.13% (271)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (2)
|
||||
imixs-ml-training_1 | ...... average NER = 1.1618358977500587
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 64.93% (487)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 34.93% (262)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.13% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 1.1362052688492958
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 64.4% (483)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 35.33% (265)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (2)
|
||||
imixs-ml-training_1 | ...... average NER = 1.0497074333838767
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 65.33% (490)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 34.4% (258)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (2)
|
||||
imixs-ml-training_1 | ...... average NER = 0.8865013575787167
|
||||
|
||||
page=1 (count=1000)
|
||||
--------------------------------
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 63.33% (475)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 36.4% (273)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (2)
|
||||
imixs-ml-training_1 | ...... average NER = 1.6325150460009787
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 61.73% (463)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 38% (285)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (2)
|
||||
imixs-ml-training_1 | ...... average NER = 1.5385085364524884
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 63.6% (477)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 36.13% (271)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (2)
|
||||
imixs-ml-training_1 | ...... average NER = 1.343965340697668
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 64.13% (481)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 35.73% (268)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.13% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 1.1842750119930687
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 63.73% (478)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 36% (270)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (2)
|
||||
imixs-ml-training_1 | ...... average NER = 1.112559219903824
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 62.8% (471)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 36.93% (277)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (2)
|
||||
imixs-ml-training_1 | ...... average NER = 0.9444137586901881
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 64% (480)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 35.73% (268)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (2)
|
||||
imixs-ml-training_1 | ...... average NER = 0.9175624525798468
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 63.47% (476)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 36.27% (272)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (2)
|
||||
imixs-ml-training_1 | ...... average NER = 0.8877949306723629
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 62.53% (469)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 37.2% (279)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.27% (2)
|
||||
imixs-ml-training_1 | ...... average NER = 0.7669201996298972
|
||||
imixs-ml-training_1 |
|
||||
imixs-ml-training_1 | ......documents trained in total = 750
|
||||
imixs-ml-training_1 | ...... quality level GOOD = 62.8% (471)
|
||||
imixs-ml-training_1 | ...... quality level LOW = 37.07% (278)
|
||||
imixs-ml-training_1 | ...... quality level BAD = 0.13% (1)
|
||||
imixs-ml-training_1 | ...... average NER = 0.7161310708827515
|
||||
|
|
@ -1,128 +0,0 @@
|
|||
[paths]
|
||||
train = null
|
||||
dev = null
|
||||
vectors = null
|
||||
init_tok2vec = null
|
||||
|
||||
[system]
|
||||
seed = 0
|
||||
gpu_allocator = null
|
||||
|
||||
[nlp]
|
||||
lang = "de"
|
||||
pipeline = ["ner"]
|
||||
disabled = []
|
||||
before_creation = null
|
||||
after_creation = null
|
||||
after_pipeline_creation = null
|
||||
batch_size = 1000
|
||||
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
||||
|
||||
[components]
|
||||
|
||||
[components.ner]
|
||||
factory = "ner"
|
||||
incorrect_spans_key = null
|
||||
moves = null
|
||||
scorer = {"@scorers":"spacy.ner_scorer.v1"}
|
||||
update_with_oracle_cut_size = 100
|
||||
|
||||
[components.ner.model]
|
||||
@architectures = "spacy.TransitionBasedParser.v2"
|
||||
state_type = "ner"
|
||||
extra_state_tokens = false
|
||||
hidden_width = 64
|
||||
maxout_pieces = 2
|
||||
use_upper = true
|
||||
nO = null
|
||||
|
||||
[components.ner.model.tok2vec]
|
||||
@architectures = "spacy.HashEmbedCNN.v2"
|
||||
pretrained_vectors = null
|
||||
width = 96
|
||||
depth = 4
|
||||
embed_size = 2000
|
||||
window_size = 1
|
||||
maxout_pieces = 3
|
||||
subword_features = true
|
||||
|
||||
[corpora]
|
||||
|
||||
[corpora.dev]
|
||||
@readers = "spacy.Corpus.v1"
|
||||
path = ${paths.dev}
|
||||
gold_preproc = false
|
||||
max_length = 0
|
||||
limit = 0
|
||||
augmenter = null
|
||||
|
||||
[corpora.train]
|
||||
@readers = "spacy.Corpus.v1"
|
||||
path = ${paths.train}
|
||||
gold_preproc = false
|
||||
max_length = 0
|
||||
limit = 0
|
||||
augmenter = null
|
||||
|
||||
[training]
|
||||
seed = ${system.seed}
|
||||
gpu_allocator = ${system.gpu_allocator}
|
||||
dropout = 0.1
|
||||
accumulate_gradient = 1
|
||||
patience = 1600
|
||||
max_epochs = 0
|
||||
max_steps = 20000
|
||||
eval_frequency = 200
|
||||
frozen_components = []
|
||||
annotating_components = []
|
||||
dev_corpus = "corpora.dev"
|
||||
train_corpus = "corpora.train"
|
||||
before_to_disk = null
|
||||
|
||||
[training.batcher]
|
||||
@batchers = "spacy.batch_by_words.v1"
|
||||
discard_oversize = false
|
||||
tolerance = 0.2
|
||||
get_length = null
|
||||
|
||||
[training.batcher.size]
|
||||
@schedules = "compounding.v1"
|
||||
start = 100
|
||||
stop = 1000
|
||||
compound = 1.001
|
||||
t = 0.0
|
||||
|
||||
[training.logger]
|
||||
@loggers = "spacy.ConsoleLogger.v1"
|
||||
progress_bar = false
|
||||
|
||||
[training.optimizer]
|
||||
@optimizers = "Adam.v1"
|
||||
beta1 = 0.9
|
||||
beta2 = 0.999
|
||||
L2_is_weight_decay = true
|
||||
L2 = 0.01
|
||||
grad_clip = 1.0
|
||||
use_averages = false
|
||||
eps = 0.00000001
|
||||
learn_rate = 0.001
|
||||
|
||||
[training.score_weights]
|
||||
ents_f = 1.0
|
||||
ents_p = 0.0
|
||||
ents_r = 0.0
|
||||
ents_per_type = null
|
||||
|
||||
[pretraining]
|
||||
|
||||
[initialize]
|
||||
vectors = ${paths.vectors}
|
||||
init_tok2vec = ${paths.init_tok2vec}
|
||||
vocab_data = null
|
||||
lookups = null
|
||||
before_init = null
|
||||
after_init = null
|
||||
|
||||
[initialize.components]
|
||||
|
||||
[initialize.tokenizer]
|
||||
|
|
@ -1,38 +0,0 @@
|
|||
{
|
||||
"lang":"de",
|
||||
"name":"pipeline",
|
||||
"version":"0.0.0",
|
||||
"spacy_version":">=3.4.1,<3.5.0",
|
||||
"description":"",
|
||||
"author":"",
|
||||
"email":"",
|
||||
"url":"",
|
||||
"license":"",
|
||||
"spacy_git_version":"Unknown",
|
||||
"vectors":{
|
||||
"width":0,
|
||||
"vectors":0,
|
||||
"keys":0,
|
||||
"name":null,
|
||||
"mode":"default"
|
||||
},
|
||||
"labels":{
|
||||
"ner":[
|
||||
"cdtr.bic",
|
||||
"cdtr.iban",
|
||||
"cdtr.name",
|
||||
"invoice.date",
|
||||
"invoice.number",
|
||||
"invoice.total"
|
||||
]
|
||||
},
|
||||
"pipeline":[
|
||||
"ner"
|
||||
],
|
||||
"components":[
|
||||
"ner"
|
||||
],
|
||||
"disabled":[
|
||||
|
||||
]
|
||||
}
|
||||
|
|
@ -1,13 +0,0 @@
|
|||
{
|
||||
"moves":null,
|
||||
"update_with_oracle_cut_size":100,
|
||||
"multitasks":[
|
||||
|
||||
],
|
||||
"min_action_freq":1,
|
||||
"learn_tokens":false,
|
||||
"beam_width":1,
|
||||
"beam_density":0.0,
|
||||
"beam_update_prob":0.0,
|
||||
"incorrect_spans_key":null
|
||||
}
|
||||
Binary file not shown.
|
|
@ -1 +0,0 @@
|
|||
‚¥movesÚÄ{"0":{},"1":{"invoice.total":-1,"invoice.number":-2,"cdtr.name":-3,"invoice.date":-4,"cdtr.iban":-5,"cdtr.bic":-6},"2":{"invoice.total":-1,"invoice.number":-2,"cdtr.name":-3,"invoice.date":-4,"cdtr.iban":-5,"cdtr.bic":-6},"3":{"invoice.total":-1,"invoice.number":-2,"cdtr.name":-3,"invoice.date":-4,"cdtr.iban":-5,"cdtr.bic":-6},"4":{"":1,"invoice.total":-1,"invoice.number":-2,"cdtr.name":-3,"invoice.date":-4,"cdtr.iban":-5,"cdtr.bic":-6},"5":{"":1}}£cfg<66>§neg_keyÀ
|
||||
File diff suppressed because one or more lines are too long
|
|
@ -1 +0,0 @@
|
|||
<EFBFBD>
|
||||
|
|
@ -1 +0,0 @@
|
|||
<EFBFBD>
|
||||
File diff suppressed because it is too large
Load diff
Binary file not shown.
|
|
@ -1,3 +0,0 @@
|
|||
{
|
||||
"mode":"default"
|
||||
}
|
||||
|
|
@ -1,127 +0,0 @@
|
|||
[paths]
|
||||
train = null
|
||||
dev = null
|
||||
vectors = null
|
||||
init_tok2vec = null
|
||||
|
||||
[system]
|
||||
seed = 0
|
||||
gpu_allocator = null
|
||||
|
||||
[nlp]
|
||||
lang = "de"
|
||||
pipeline = ["ner"]
|
||||
disabled = []
|
||||
before_creation = null
|
||||
after_creation = null
|
||||
after_pipeline_creation = null
|
||||
batch_size = 1000
|
||||
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
||||
|
||||
[components]
|
||||
|
||||
[components.ner]
|
||||
factory = "ner"
|
||||
incorrect_spans_key = null
|
||||
moves = null
|
||||
update_with_oracle_cut_size = 100
|
||||
|
||||
[components.ner.model]
|
||||
@architectures = "spacy.TransitionBasedParser.v2"
|
||||
state_type = "ner"
|
||||
extra_state_tokens = false
|
||||
hidden_width = 64
|
||||
maxout_pieces = 2
|
||||
use_upper = true
|
||||
nO = null
|
||||
|
||||
[components.ner.model.tok2vec]
|
||||
@architectures = "spacy.HashEmbedCNN.v2"
|
||||
pretrained_vectors = null
|
||||
width = 96
|
||||
depth = 4
|
||||
embed_size = 2000
|
||||
window_size = 1
|
||||
maxout_pieces = 3
|
||||
subword_features = true
|
||||
|
||||
[corpora]
|
||||
|
||||
[corpora.dev]
|
||||
@readers = "spacy.Corpus.v1"
|
||||
path = ${paths.dev}
|
||||
gold_preproc = false
|
||||
max_length = 0
|
||||
limit = 0
|
||||
augmenter = null
|
||||
|
||||
[corpora.train]
|
||||
@readers = "spacy.Corpus.v1"
|
||||
path = ${paths.train}
|
||||
gold_preproc = false
|
||||
max_length = 0
|
||||
limit = 0
|
||||
augmenter = null
|
||||
|
||||
[training]
|
||||
seed = ${system.seed}
|
||||
gpu_allocator = ${system.gpu_allocator}
|
||||
dropout = 0.1
|
||||
accumulate_gradient = 1
|
||||
patience = 1600
|
||||
max_epochs = 0
|
||||
max_steps = 20000
|
||||
eval_frequency = 200
|
||||
frozen_components = []
|
||||
annotating_components = []
|
||||
dev_corpus = "corpora.dev"
|
||||
train_corpus = "corpora.train"
|
||||
before_to_disk = null
|
||||
|
||||
[training.batcher]
|
||||
@batchers = "spacy.batch_by_words.v1"
|
||||
discard_oversize = false
|
||||
tolerance = 0.2
|
||||
get_length = null
|
||||
|
||||
[training.batcher.size]
|
||||
@schedules = "compounding.v1"
|
||||
start = 100
|
||||
stop = 1000
|
||||
compound = 1.001
|
||||
t = 0.0
|
||||
|
||||
[training.logger]
|
||||
@loggers = "spacy.ConsoleLogger.v1"
|
||||
progress_bar = false
|
||||
|
||||
[training.optimizer]
|
||||
@optimizers = "Adam.v1"
|
||||
beta1 = 0.9
|
||||
beta2 = 0.999
|
||||
L2_is_weight_decay = true
|
||||
L2 = 0.01
|
||||
grad_clip = 1.0
|
||||
use_averages = false
|
||||
eps = 0.00000001
|
||||
learn_rate = 0.001
|
||||
|
||||
[training.score_weights]
|
||||
ents_f = 1.0
|
||||
ents_p = 0.0
|
||||
ents_r = 0.0
|
||||
ents_per_type = null
|
||||
|
||||
[pretraining]
|
||||
|
||||
[initialize]
|
||||
vectors = ${paths.vectors}
|
||||
init_tok2vec = ${paths.init_tok2vec}
|
||||
vocab_data = null
|
||||
lookups = null
|
||||
before_init = null
|
||||
after_init = null
|
||||
|
||||
[initialize.components]
|
||||
|
||||
[initialize.tokenizer]
|
||||
|
|
@ -1,40 +0,0 @@
|
|||
{
|
||||
"lang":"de",
|
||||
"name":"pipeline",
|
||||
"version":"0.0.0",
|
||||
"spacy_version":">=3.1.1,<3.2.0",
|
||||
"description":"",
|
||||
"author":"",
|
||||
"email":"",
|
||||
"url":"",
|
||||
"license":"",
|
||||
"spacy_git_version":"ffaead8fe",
|
||||
"vectors":{
|
||||
"width":0,
|
||||
"vectors":0,
|
||||
"keys":0,
|
||||
"name":null
|
||||
},
|
||||
"labels":{
|
||||
"ner":[
|
||||
"cdtr.bic",
|
||||
"cdtr.iban",
|
||||
"cdtr.name",
|
||||
"invoice.date",
|
||||
"invoice.number",
|
||||
"invoice.total"
|
||||
]
|
||||
},
|
||||
"pipeline":[
|
||||
"ner"
|
||||
],
|
||||
"components":[
|
||||
"ner"
|
||||
],
|
||||
"disabled":[
|
||||
|
||||
],
|
||||
"_sourced_vectors_hashes":{
|
||||
|
||||
}
|
||||
}
|
||||
|
|
@ -1,13 +0,0 @@
|
|||
{
|
||||
"moves":null,
|
||||
"update_with_oracle_cut_size":100,
|
||||
"multitasks":[
|
||||
|
||||
],
|
||||
"min_action_freq":1,
|
||||
"learn_tokens":false,
|
||||
"beam_width":1,
|
||||
"beam_density":0.0,
|
||||
"beam_update_prob":0.0,
|
||||
"incorrect_spans_key":null
|
||||
}
|
||||
Binary file not shown.
|
|
@ -1 +0,0 @@
|
|||
‚¥movesÚÄ{"0":{},"1":{"cdtr.name":-1,"cdtr.iban":-2,"cdtr.bic":-3,"invoice.total":-4,"invoice.date":-5,"invoice.number":-6},"2":{"cdtr.name":-1,"cdtr.iban":-2,"cdtr.bic":-3,"invoice.total":-4,"invoice.date":-5,"invoice.number":-6},"3":{"cdtr.name":-1,"cdtr.iban":-2,"cdtr.bic":-3,"invoice.total":-4,"invoice.date":-5,"invoice.number":-6},"4":{"":1,"cdtr.name":-1,"cdtr.iban":-2,"cdtr.bic":-3,"invoice.total":-4,"invoice.date":-5,"invoice.number":-6},"5":{"":1}}£cfg<66>§neg_keyÀ
|
||||
File diff suppressed because one or more lines are too long
|
|
@ -1 +0,0 @@
|
|||
<EFBFBD>
|
||||
|
|
@ -1 +0,0 @@
|
|||
<EFBFBD>
|
||||
File diff suppressed because it is too large
Load diff
Binary file not shown.
|
|
@ -1,128 +0,0 @@
|
|||
[paths]
|
||||
train = null
|
||||
dev = null
|
||||
vectors = null
|
||||
init_tok2vec = null
|
||||
|
||||
[system]
|
||||
seed = 0
|
||||
gpu_allocator = null
|
||||
|
||||
[nlp]
|
||||
lang = "de"
|
||||
pipeline = ["ner"]
|
||||
disabled = []
|
||||
before_creation = null
|
||||
after_creation = null
|
||||
after_pipeline_creation = null
|
||||
batch_size = 1000
|
||||
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
||||
|
||||
[components]
|
||||
|
||||
[components.ner]
|
||||
factory = "ner"
|
||||
incorrect_spans_key = null
|
||||
moves = null
|
||||
scorer = {"@scorers":"spacy.ner_scorer.v1"}
|
||||
update_with_oracle_cut_size = 100
|
||||
|
||||
[components.ner.model]
|
||||
@architectures = "spacy.TransitionBasedParser.v2"
|
||||
state_type = "ner"
|
||||
extra_state_tokens = false
|
||||
hidden_width = 64
|
||||
maxout_pieces = 2
|
||||
use_upper = true
|
||||
nO = null
|
||||
|
||||
[components.ner.model.tok2vec]
|
||||
@architectures = "spacy.HashEmbedCNN.v2"
|
||||
pretrained_vectors = null
|
||||
width = 96
|
||||
depth = 4
|
||||
embed_size = 2000
|
||||
window_size = 1
|
||||
maxout_pieces = 3
|
||||
subword_features = true
|
||||
|
||||
[corpora]
|
||||
|
||||
[corpora.dev]
|
||||
@readers = "spacy.Corpus.v1"
|
||||
path = ${paths.dev}
|
||||
gold_preproc = false
|
||||
max_length = 0
|
||||
limit = 0
|
||||
augmenter = null
|
||||
|
||||
[corpora.train]
|
||||
@readers = "spacy.Corpus.v1"
|
||||
path = ${paths.train}
|
||||
gold_preproc = false
|
||||
max_length = 0
|
||||
limit = 0
|
||||
augmenter = null
|
||||
|
||||
[training]
|
||||
seed = ${system.seed}
|
||||
gpu_allocator = ${system.gpu_allocator}
|
||||
dropout = 0.1
|
||||
accumulate_gradient = 1
|
||||
patience = 1600
|
||||
max_epochs = 0
|
||||
max_steps = 20000
|
||||
eval_frequency = 200
|
||||
frozen_components = []
|
||||
annotating_components = []
|
||||
dev_corpus = "corpora.dev"
|
||||
train_corpus = "corpora.train"
|
||||
before_to_disk = null
|
||||
|
||||
[training.batcher]
|
||||
@batchers = "spacy.batch_by_words.v1"
|
||||
discard_oversize = false
|
||||
tolerance = 0.2
|
||||
get_length = null
|
||||
|
||||
[training.batcher.size]
|
||||
@schedules = "compounding.v1"
|
||||
start = 100
|
||||
stop = 1000
|
||||
compound = 1.001
|
||||
t = 0.0
|
||||
|
||||
[training.logger]
|
||||
@loggers = "spacy.ConsoleLogger.v1"
|
||||
progress_bar = false
|
||||
|
||||
[training.optimizer]
|
||||
@optimizers = "Adam.v1"
|
||||
beta1 = 0.9
|
||||
beta2 = 0.999
|
||||
L2_is_weight_decay = true
|
||||
L2 = 0.01
|
||||
grad_clip = 1.0
|
||||
use_averages = false
|
||||
eps = 0.00000001
|
||||
learn_rate = 0.001
|
||||
|
||||
[training.score_weights]
|
||||
ents_f = 1.0
|
||||
ents_p = 0.0
|
||||
ents_r = 0.0
|
||||
ents_per_type = null
|
||||
|
||||
[pretraining]
|
||||
|
||||
[initialize]
|
||||
vectors = ${paths.vectors}
|
||||
init_tok2vec = ${paths.init_tok2vec}
|
||||
vocab_data = null
|
||||
lookups = null
|
||||
before_init = null
|
||||
after_init = null
|
||||
|
||||
[initialize.components]
|
||||
|
||||
[initialize.tokenizer]
|
||||
|
|
@ -1,38 +0,0 @@
|
|||
{
|
||||
"lang":"de",
|
||||
"name":"pipeline",
|
||||
"version":"0.0.0",
|
||||
"spacy_version":">=3.4.1,<3.5.0",
|
||||
"description":"",
|
||||
"author":"",
|
||||
"email":"",
|
||||
"url":"",
|
||||
"license":"",
|
||||
"spacy_git_version":"Unknown",
|
||||
"vectors":{
|
||||
"width":0,
|
||||
"vectors":0,
|
||||
"keys":0,
|
||||
"name":null,
|
||||
"mode":"default"
|
||||
},
|
||||
"labels":{
|
||||
"ner":[
|
||||
"cdtr.bic",
|
||||
"cdtr.iban",
|
||||
"cdtr.name",
|
||||
"invoice.date",
|
||||
"invoice.number",
|
||||
"invoice.total"
|
||||
]
|
||||
},
|
||||
"pipeline":[
|
||||
"ner"
|
||||
],
|
||||
"components":[
|
||||
"ner"
|
||||
],
|
||||
"disabled":[
|
||||
|
||||
]
|
||||
}
|
||||
|
|
@ -1,13 +0,0 @@
|
|||
{
|
||||
"moves":null,
|
||||
"update_with_oracle_cut_size":100,
|
||||
"multitasks":[
|
||||
|
||||
],
|
||||
"min_action_freq":1,
|
||||
"learn_tokens":false,
|
||||
"beam_width":1,
|
||||
"beam_density":0.0,
|
||||
"beam_update_prob":0.0,
|
||||
"incorrect_spans_key":null
|
||||
}
|
||||
Binary file not shown.
|
|
@ -1 +0,0 @@
|
|||
‚¥movesÚÄ{"0":{},"1":{"invoice.total":-1,"invoice.number":-2,"invoice.date":-3,"cdtr.name":-4,"cdtr.iban":-5,"cdtr.bic":-6},"2":{"invoice.total":-1,"invoice.number":-2,"invoice.date":-3,"cdtr.name":-4,"cdtr.iban":-5,"cdtr.bic":-6},"3":{"invoice.total":-1,"invoice.number":-2,"invoice.date":-3,"cdtr.name":-4,"cdtr.iban":-5,"cdtr.bic":-6},"4":{"":1,"invoice.total":-1,"invoice.number":-2,"invoice.date":-3,"cdtr.name":-4,"cdtr.iban":-5,"cdtr.bic":-6},"5":{"":1}}£cfg<66>§neg_keyÀ
|
||||
File diff suppressed because one or more lines are too long
|
|
@ -1 +0,0 @@
|
|||
<EFBFBD>
|
||||
|
|
@ -1 +0,0 @@
|
|||
<EFBFBD>
|
||||
File diff suppressed because it is too large
Load diff
Binary file not shown.
|
|
@ -1,3 +0,0 @@
|
|||
{
|
||||
"mode":"default"
|
||||
}
|
||||
|
|
@ -1,44 +0,0 @@
|
|||
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
||||
<document xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
|
||||
xmlns:xs="http://www.w3.org/2001/XMLSchema">
|
||||
|
||||
<!-- Workflow Instance -->
|
||||
<item name="workflow.endpoint"><value xsi:type="xs:string">https://alexander-logistics.office-workflow.de/api/</value></item>
|
||||
<item name="workflow.userid"><value xsi:type="xs:string">admin</value></item>
|
||||
<item name="workflow.password"><value xsi:type="xs:string">imixs4.null</value></item>
|
||||
|
||||
<!-- -->
|
||||
<item name="workflow.query"><value xsi:type="xs:string">($workflowgroup:"Rechnungseingang" OR $workflowgroup:"Sachrechnung") AND ($taskid:5900)</value></item>
|
||||
|
||||
<item name="workflow.pagesize"><value xsi:type="xs:int">100</value></item>
|
||||
<item name="workflow.pageindex"><value xsi:type="xs:int">30</value></item>
|
||||
<item name="workflow.entities">
|
||||
<value xsi:type="xs:string">cdtr.name</value>
|
||||
<value xsi:type="xs:string">cdtr.iban</value>
|
||||
<value xsi:type="xs:string">cdtr.bic</value>
|
||||
<value xsi:type="xs:string">invoice.total</value>
|
||||
<value xsi:type="xs:string">invoice.date</value>
|
||||
<value xsi:type="xs:string">invoice.number</value>
|
||||
</item>
|
||||
<item name="workflow.locale">
|
||||
<value xsi:type="xs:string">en_GB</value>
|
||||
<value xsi:type="xs:string">en_US</value>
|
||||
<value xsi:type="xs:string">de_DE</value>
|
||||
</item>
|
||||
|
||||
<!-- Tika OCR Server -->
|
||||
<item name="tika.ocrmode"><value xsi:type="xs:string">OCR_ONLY</value></item>
|
||||
<item name="tika.options">
|
||||
<value xsi:type="xs:string">X-Tika-OCRLanguage=eng+deu</value>
|
||||
<value xsi:type="xs:string">X-Tika-PDFocrStrategy=OCR_ONLY</value>
|
||||
</item>
|
||||
|
||||
<!-- ML spaCy Server -->
|
||||
<item name="ml.validation.endpoint"><value xsi:type="xs:string">http://imixs-ml-spacy:8000/</value></item>
|
||||
<item name="ml.validation.model"><value xsi:type="xs:string">invoice-de-0.1.0</value></item>
|
||||
<item name="ml.validation.filepattern"><value xsi:type="xs:string">.pdf|.PDF</value></item>
|
||||
|
||||
</document>
|
||||
|
||||
|
||||
|
||||
|
|
@ -1,53 +0,0 @@
|
|||
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
||||
<document xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
|
||||
xmlns:xs="http://www.w3.org/2001/XMLSchema">
|
||||
|
||||
<!-- Workflow Instance -->
|
||||
<item name="workflow.endpoint"><value xsi:type="xs:string">https://alexander-logistics.office-workflow.de/api/</value></item>
|
||||
<item name="workflow.userid"><value xsi:type="xs:string">admin</value></item>
|
||||
<item name="workflow.password"><value xsi:type="xs:string">imixs4.null</value></item>
|
||||
|
||||
<item name="workflow.entities">
|
||||
<value xsi:type="xs:string">cdtr.name</value>
|
||||
<value xsi:type="xs:string">cdtr.iban</value>
|
||||
<value xsi:type="xs:string">cdtr.bic</value>
|
||||
<value xsi:type="xs:string">invoice.total</value>
|
||||
<value xsi:type="xs:string">invoice.date</value>
|
||||
<value xsi:type="xs:string">invoice.number</value>
|
||||
</item>
|
||||
<item name="workflow.locale">
|
||||
<value xsi:type="xs:string">en_GB</value>
|
||||
<value xsi:type="xs:string">en_US</value>
|
||||
<value xsi:type="xs:string">de_DE</value>
|
||||
</item>
|
||||
|
||||
<!-- Tika OCR Server -->
|
||||
<item name="tika.ocrmode"><value xsi:type="xs:string">OCR_ONLY</value></item>
|
||||
<item name="tika.options">
|
||||
<value xsi:type="xs:string">X-Tika-OCRLanguage=eng+deu</value>
|
||||
<value xsi:type="xs:string">X-Tika-PDFocrStrategy=OCR_ONLY</value>
|
||||
</item>
|
||||
|
||||
<!-- ML spaCy Server -->
|
||||
<item name="ml.training.endpoint"><value xsi:type="xs:string">http://imixs-ml-spacy:8000/</value></item>
|
||||
<item name="ml.training.model"><value xsi:type="xs:string">invoice-de-0.2.0</value></item>
|
||||
<item name="ml.training.filepattern"><value xsi:type="xs:string">.pdf|.PDF</value></item>
|
||||
<!-- LOW | GOOD -->
|
||||
<item name="ml.training.quality"><value xsi:type="xs:string">LOW</value></item>
|
||||
|
||||
|
||||
<!-- Define the training set and taining mode -->
|
||||
<item name="workflow.query"><value xsi:type="xs:string">($workflowgroup:"Rechnungseingang" OR $workflowgroup:"Sachrechnung") AND ($taskid:5900)</value></item>
|
||||
<item name="workflow.pagesize"><value xsi:type="xs:int">1000</value></item>
|
||||
<item name="workflow.pageindex"><value xsi:type="xs:int">0</value></item>
|
||||
<item name="ml.training.iterations"><value xsi:type="xs:string">5</value></item>
|
||||
<item name="ml.training.dropoutrate"><value xsi:type="xs:string">0.0</value></item>
|
||||
<item name="ml.options">
|
||||
<value xsi:type="xs:string">min_losses=0.0&retrain_rate=100</value>
|
||||
</item>
|
||||
|
||||
|
||||
</document>
|
||||
|
||||
|
||||
|
||||
|
|
@ -1,48 +0,0 @@
|
|||
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
||||
<document xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
|
||||
xmlns:xs="http://www.w3.org/2001/XMLSchema">
|
||||
|
||||
<!-- Workflow Instance -->
|
||||
<item name="workflow.endpoint"><value xsi:type="xs:string">https://alexander-logistics.office-workflow.de/api/</value></item>
|
||||
<item name="workflow.userid"><value xsi:type="xs:string">admin</value></item>
|
||||
<item name="workflow.password"><value xsi:type="xs:string">imixs4.null</value></item>
|
||||
|
||||
<item name="workflow.entities">
|
||||
<value xsi:type="xs:string">cdtr.name</value>
|
||||
<value xsi:type="xs:string">cdtr.iban</value>
|
||||
<value xsi:type="xs:string">cdtr.bic</value>
|
||||
<value xsi:type="xs:string">invoice.total</value>
|
||||
<value xsi:type="xs:string">invoice.date</value>
|
||||
<value xsi:type="xs:string">invoice.number</value>
|
||||
</item>
|
||||
<item name="workflow.locale">
|
||||
<value xsi:type="xs:string">en_GB</value>
|
||||
<value xsi:type="xs:string">en_US</value>
|
||||
<value xsi:type="xs:string">de_DE</value>
|
||||
</item>
|
||||
|
||||
<!-- Tika OCR Server -->
|
||||
<item name="tika.ocrmode"><value xsi:type="xs:string">OCR_ONLY</value></item>
|
||||
<item name="tika.options">
|
||||
<value xsi:type="xs:string">X-Tika-OCRLanguage=eng+deu</value>
|
||||
<value xsi:type="xs:string">X-Tika-PDFocrStrategy=OCR_ONLY</value>
|
||||
</item>
|
||||
|
||||
<!-- ML spaCy Server -->
|
||||
<item name="ml.training.endpoint"><value xsi:type="xs:string">http://imixs-ml-spacy:8000/</value></item>
|
||||
<item name="ml.training.model"><value xsi:type="xs:string">invoice-de-0.2.0</value></item>
|
||||
<item name="ml.training.filepattern"><value xsi:type="xs:string">.pdf|.PDF</value></item>
|
||||
<!-- LOW | GOOD -->
|
||||
<item name="ml.training.quality"><value xsi:type="xs:string">LOW</value></item>
|
||||
|
||||
|
||||
<!-- Define the training set and taining mode -->
|
||||
<item name="workflow.query"><value xsi:type="xs:string">($workflowgroup:"Rechnungseingang" OR $workflowgroup:"Sachrechnung") AND ($taskid:5900)</value></item>
|
||||
<item name="workflow.pagesize"><value xsi:type="xs:int">100</value></item>
|
||||
<item name="workflow.pageindex"><value xsi:type="xs:int">40</value></item>
|
||||
|
||||
|
||||
</document>
|
||||
|
||||
|
||||
|
||||
|
|
@ -7,6 +7,7 @@ import java.io.IOException;
|
|||
import java.io.InputStream;
|
||||
import java.text.NumberFormat;
|
||||
import java.text.SimpleDateFormat;
|
||||
import java.util.Date;
|
||||
import java.util.HashMap;
|
||||
import java.util.List;
|
||||
import java.util.Locale;
|
||||
|
|
@ -22,6 +23,7 @@ import org.apache.pdfbox.pdmodel.common.filespecification.PDComplexFileSpecifica
|
|||
import org.apache.pdfbox.pdmodel.common.filespecification.PDEmbeddedFile;
|
||||
import org.imixs.einvoice.EInvoiceFormatException;
|
||||
import org.imixs.einvoice.EInvoiceModel;
|
||||
import org.imixs.einvoice.EInvoiceModelCII;
|
||||
import org.imixs.einvoice.EInvoiceModelFactory;
|
||||
import org.imixs.einvoice.TradeLineItem;
|
||||
import org.imixs.einvoice.TradeParty;
|
||||
|
|
@ -243,6 +245,12 @@ public class EInvoiceAdapter implements SignalAdapter {
|
|||
// date
|
||||
model.setIssueDateTime(workitem.getItemValueLocalDate("invoice.date"));
|
||||
model.setDueDateTime(workitem.getItemValueLocalDate("invoice.duedate"));
|
||||
// BT-20: Payment terms description, derived from the due date
|
||||
Date dueDate = workitem.getItemValueDate("invoice.duedate");
|
||||
if (dueDate != null) {
|
||||
String formattedDueDate = dateFormatter.format(dueDate);
|
||||
((EInvoiceModelCII) model).setPaymentTermsDescription("Payment due by " + formattedDueDate);
|
||||
}
|
||||
|
||||
// Update Addresses
|
||||
TradeParty billingAddress = buildAddress(workitem.getItemValueString("partner.id"), "buyer");
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@
|
|||
xmlns:xs="http://www.w3.org/2001/XMLSchema">
|
||||
<rsm:ExchangedDocumentContext>
|
||||
<ram:GuidelineSpecifiedDocumentContextParameter>
|
||||
<ram:ID>urn:cen.eu:en16931:2017</ram:ID>
|
||||
<ram:ID>urn:cen.eu:en16931:2017#compliant#urn:xoev-de:kosit:standard:xrechnung_3.0.2</ram:ID>
|
||||
</ram:GuidelineSpecifiedDocumentContextParameter>
|
||||
</rsm:ExchangedDocumentContext>
|
||||
<rsm:ExchangedDocument>
|
||||
|
|
@ -161,7 +161,7 @@
|
|||
<ram:RateApplicablePercent>23.0</ram:RateApplicablePercent>
|
||||
</ram:ApplicableTradeTax>
|
||||
<ram:SpecifiedTradePaymentTerms>
|
||||
<ram:Description/>
|
||||
<ram:Description>Payment due by 10.03.2025</ram:Description>
|
||||
<ram:DueDateDateTime>
|
||||
<udt:DateTimeString format="102">20250310</udt:DateTimeString>
|
||||
</ram:DueDateDateTime>
|
||||
|
|
|
|||
Loading…
Reference in a new issue