diff --git a/models/invoice-de-0.1.0/ner/model b/models/invoice-de-0.1.0/ner/model index 8ce9017..62a1139 100644 Binary files a/models/invoice-de-0.1.0/ner/model and b/models/invoice-de-0.1.0/ner/model differ diff --git a/models/invoice-de-0.1.0/vocab/strings.json b/models/invoice-de-0.1.0/vocab/strings.json index 60099c5..27bf81d 100644 --- a/models/invoice-de-0.1.0/vocab/strings.json +++ b/models/invoice-de-0.1.0/vocab/strings.json @@ -20449,6 +20449,7 @@ "01928", "0193457", "0194", + "0194018084888", "01942", "019421", "0194586", @@ -22134,6 +22135,7 @@ "04714844149", "04718", "04719", + "047198395", "0472178", "047293", "0472930", @@ -24516,6 +24518,7 @@ "0961", "0962070", "09629", + "0963", "0963306", "0963308", "0963349", @@ -31790,6 +31793,7 @@ "11456,84", "11457,85", "1146", + "114616939", "114683", "114697500", "1147", @@ -48644,6 +48648,7 @@ "20.658,000", "20.670,18", "20.692", + "20.700,00", "20.700,001", "20.710", "20.720", @@ -61801,6 +61806,7 @@ "23.08.2021", "23.082", "23.083,000", + "23.09.2021", "23.092,000", "23.094,00", "23.096", @@ -71295,6 +71301,7 @@ "30.085,21", "30.09", "30.09.2020", + "30.09.21", "30.12.1899", "30.12.2018", "30.12.2020", @@ -76942,6 +76949,7 @@ "38600", "38603", "38604", + "3861", "38620", "38629", "38632", @@ -79209,8 +79217,10 @@ "40", "40'-", "40'-DC", + "40'-Flat", "40'-HC", "40'-dc", + "40'-flat", "40'-hc", "40'1IC", "40'1ic", @@ -79227,6 +79237,7 @@ "40'GP", "40'H-H", "40'HC", + "40'HCFLMAEU", "40'HG", "40'HIGH", "40'HQ", @@ -79248,6 +79259,7 @@ "40'gp", "40'h-h", "40'hc", + "40'hcflmaeu", "40'hg", "40'high", "40'hq", @@ -99515,6 +99527,8 @@ "73699", "737", "737,80", + "737,80EUR", + "737,80eur", "7370", "7371483", "7372", @@ -111330,6 +111344,7 @@ "ABGENOMMEN", "ABGO", "ABH", + "ABHOLUNG", "ABI", "ABICIDEIFIGHH", "ABIDJAN", @@ -115433,6 +115448,7 @@ "Abpeten", "Abr", "Abrachung", + "Abrahamsen", "Abratd", "Abrechnen", "Abrechnung", @@ -116047,6 +116063,7 @@ "Addiass", "Addibonal", "Addibonals", + "Addicks", "Addie", "Addiess", "Addifioha", @@ -117919,6 +117936,7 @@ "Amerder", "America", "American", + "Amerikaring", "Amerlca", "Amerling", "Amernes", @@ -118560,6 +118578,7 @@ "Aniolye", "Anions", "Anis", + "Anisa", "Anisehit", "Anisterdam", "Aniston", @@ -121922,6 +121941,7 @@ "Aveo", "Aver", "Avera", + "Averberg", "Averiue", "Avery", "Aves", @@ -143085,6 +143105,7 @@ "DEEX2766589", "DEEX2768626", "DEF", + "DEF1", "DEF2101250109C", "DEF2105050247", "DEF2105070176", @@ -151405,6 +151426,7 @@ "EF", "EF-", "EF-PRO", + "EF1", "EF114", "EF9315E948B94A61A713168575D1E032@Giuseppe", "EFA", @@ -153755,6 +153777,7 @@ "EX-PRO-2107-Surplus", "EX-PRO-2107-XXX", "EX-PRO-2108", + "EX-PRO-2109", "EX-PRO-2706-", "EX-PRO-MOCUR", "EX-RAL", @@ -180729,6 +180752,7 @@ "H\u00a5Ve", "H\u00c4N", "H\u00c4TTE", + "H\u00d6R", "H\u00dcTTENSTR", "H\u00e4BErISEHA", "H\u00e4P", @@ -189044,6 +189068,7 @@ "KOLI", "KOLJA", "KOLLI", + "KOLLIWINDKRAFT", "KOLLS", "KOLN", "KOLNANLIEFERN", @@ -192100,6 +192125,7 @@ "Kreuzlingen", "Kreuzschlitzschraube", "Kreuztal", + "Kreye", "Kreysztota", "Krichel", "Kriebethal", @@ -193359,6 +193385,7 @@ "LAGEREI-", "LAGERGELD", "LAGERGELDFREI", + "LAGERN", "LAGERUNG", "LAGHENDORF", "LAGI", @@ -211904,6 +211931,7 @@ "Nachweispflicht", "Nachwels", "Nachziehen", + "Nachzulesen", "Nach\u00e9pigende", "Nacifalgande", "Nackbagende", @@ -220803,6 +220831,7 @@ "PLUEMAT", "PLUFF", "PLUG", + "PLUM", "PLUMDE29XXX", "PLUS", "PLY", @@ -269522,6 +269551,7 @@ "W\u00e4hrun", "W\u00e4hrung", "W\u00e4hrungsbetrag", + "W\u00e4hrungsbetragPreisMengePer", "W\u00e4hrungskennzeichen", "W\u00e4hrungskurs", "W\u00e4hrungsschl\u00fcssel", @@ -276560,6 +276590,7 @@ "XxxxxXxxxxXxxx", "XxxxxXxxxxXxxxx", "XxxxxXxxxxXxxxxXx", + "XxxxxXxxxxXxxxxXxx", "XxxxxXxxxxXxxxxXxxxx", "XxxxxXxxxxXxxxx_Xxxxx", "XxxxxXxxxx_Xxxxx_dddd.xxxx", @@ -279500,6 +279531,7 @@ "ZUBARA", "ZUBARAI|VSL", "ZUBARA|VSL", + "ZUBEH\u00d6R", "ZUBTAN-", "ZUC-HMBG-BERLIN", "ZUC-HMBG-BIELSKO", @@ -279732,6 +279764,7 @@ "Zahlungsbedingungefechnung", "Zahlungsbedingungefkechnung", "Zahlungsbedingungen", + "Zahlungsbedingungen:19", "Zahlungsbedingungetechnung", "Zahlungsbeg\u00fcnstigter", "Zahlungsbeleg", @@ -284251,6 +284284,7 @@ "abr", "abrachung", "abraerd", + "abrahamsen", "abrasive", "abratd", "abrechnen", @@ -285417,6 +285451,7 @@ "addiass", "addibonal", "addibonals", + "addicks", "addie", "addieks", "addiess", @@ -289367,6 +289402,7 @@ "americas(85031", "americas@", "amerikanischen", + "amerikaring", "amerlca", "amerling", "amern", @@ -290582,6 +290618,7 @@ "anipenga", "aniraie", "anis", + "anisa", "anisehit", "anislaw", "anispaudas", @@ -297202,6 +297239,8 @@ "avera", "average", "averal", + "averberg", + "averberg@addicks.de", "avercengehomen", "avercenkomsten", "averecagetomen", @@ -310687,8 +310726,10 @@ "cbm", "cbm21.180Total", "cbm21.180total", + "cbmGewicht", "cbmInhaltVerpackungAnzahlZeichen", "cbma", + "cbmgewicht", "cbmgtdy", "cbmi", "cbmichf", @@ -322716,6 +322757,7 @@ "dd&d|", "dd'-", "dd'-XX", + "dd'-Xxxx", "dd'X", "dd'X-X", "dd'XX", @@ -326868,6 +326910,7 @@ "deex2766589", "deex2768626", "def", + "def1", "def2101250109c", "def2105050247", "def2105070176", @@ -345717,6 +345760,7 @@ "ex-pro-2107-surplus", "ex-pro-2107-xxx", "ex-pro-2108", + "ex-pro-2109", "ex-pro-2706-", "ex-pro-mocur", "ex-ral", @@ -370302,6 +370346,7 @@ "hb-va40", "hb-va45", "hb-vo", + "hb1", "hb101", "hb12", "hb14", @@ -387036,6 +387081,7 @@ "kg:243000,00", "kg:599580,00", "kgJ", + "kgVerpackungAnzahlZeichen", "kg\\", "kgaa", "kgal-norker", @@ -387062,6 +387108,7 @@ "kgs]104", "kgs|", "kgt", + "kgverpackunganzahlzeichen", "kg|", "kg\u00e9", "kh", @@ -388388,6 +388435,7 @@ "kollianzahl", "kollin", "kollislag", + "kolliwindkraft", "kollort", "kolls", "koln", @@ -389441,6 +389489,7 @@ "kreuzlingen", "kreuzschlitzschraube", "kreuztal", + "kreye", "kreysztota", "krf\u00fchher", "krg", @@ -409064,6 +409113,7 @@ "nachweispflicht", "nachwels", "nachziehen", + "nachzulesen", "nach\u00e9pigende", "nacifalgande", "nacional", @@ -430565,6 +430615,7 @@ "pluff", "pluf\u00a2", "plug", + "plum", "plumde29xxx", "plump", "plune", @@ -493436,6 +493487,7 @@ "www.abnamro.nl/intera", "www.abnamro.nvintera", "www.aclcargo.com", + "www.addicks.de", "www.ahg-online.de", "www.ahg-online.de/audi-gotha", "www.ahg-online.de/audi-suhl", @@ -494482,6 +494534,7 @@ "w\u00e4hrund", "w\u00e4hrung", "w\u00e4hrungsbetrag", + "w\u00e4hrungsbetragpreismengeper", "w\u00e4hrungskennzeichen", "w\u00e4hrungskurs", "w\u00e4hrungsschl\u00fcssel", @@ -496592,6 +496645,7 @@ "xxXxxxxXx+XddX", "xxXxxxxXxXXx", "xxXxxxxXxxxx", + "xxXxxxxXxxxxXxxxx", "xxXxxxxdXxXdxxxdxXX", "xxXxxxxdddd", "xxXxx\u20acx-XxxxxXxXxxX'XxxxxXx.xxd.", @@ -497947,6 +498001,7 @@ "xxxxXXX", "xxxxXXX@xx.xxx.xxx", "xxxxXXXX", + "xxxxXXXX-XXXX", "xxxxXXXXx", "xxxxXXXXxXXxXxXdXXXxXXxxdxdXxxdXxxd", "xxxxXXXXxxxx", @@ -501166,7 +501221,9 @@ "zahlan", "zahlan\u0131o", "zahlbar", + "zahlbarMWST-FREI", "zahlbarl", + "zahlbarmwst-frei", "zahlbelege", "zahlbetrag", "zahlbnapppdyn", @@ -501211,6 +501268,7 @@ "zahlungsbedingungefkechnung", "zahlungsbedingungefrechnung", "zahlungsbedingungen", + "zahlungsbedingungen:19", "zahlungsbedingungerechnung", "zahlungsbedingungetechnung", "zahlungsbeg\u00fcnstigter", @@ -502283,6 +502341,7 @@ "zentr.e-a-management@polizei.sachsen-anhalt.de", "zentralamerika", "zentrale", + "zentrale@addicks.de", "zentralen", "zentralfax", "zentralkl\u00e4ranlage", diff --git a/workflow/posteingang-de-1.0.8.bpmn b/workflow/posteingang-de-1.0.8.bpmn new file mode 100644 index 0000000..d33470b --- /dev/null +++ b/workflow/posteingang-de-1.0.8.bpmn @@ -0,0 +1,829 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + For the OCR Adapter the following minimal options should be set: + + * X-Tika-PDFocrStrategy=OCR_AND_TEXT_EXTRACTION + * X-Tika-OCRLanguage=eng+deu + +These options allow OCR and text extraction suporting English and German language. + +Additional Tika Options can be set but are NOT needed in most cases: + + * X-Tika-PDFOcrImageType=RGB (setting the RGB color mode) + * X-Tika-PDFOcrDPI=400 (setting DPI) + +Setting the OcrDPI is only recommended if the DPI is know! + +Possible ImageTypes are: + + * ARGB Alpha, Red, Green, Blue + * BINARY Black or white. + * GRAY Shades of gray + * RGB Red, Green, Blue + + + + + + + Task_4 + ExclusiveGateway_2 + Task_1 + ExclusiveGateway_1 + StartEvent_1 + EndEvent_1 + IntermediateCatchEvent_2 + Task_2 + IntermediateCatchEvent_3 + IntermediateCatchEvent_4 + IntermediateCatchEvent_5 + BoundaryEvent_1 + IntermediateCatchEvent_6 + IntermediateCatchEvent_1 + Task_3 + + + + + + + + + + + + + + + + + + + + + true + + + + + + + + $workflowgroup - $workflowstatus]]> + SequenceFlow_13 + SequenceFlow_3 + + + SequenceFlow_3 + SequenceFlow_1 + + + + + + + + + + + _subject]]> + + + + + + + + + _amount (Brutto € _amount_brutto) +_description]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + home +Empfang]]> + + + + + + + + + + + + false + + + + SequenceFlow_1 + SequenceFlow_4 + + + + + SequenceFlow_13 + + + + + + + + + + + + + + + + + + + + true + + + + + + + + Rechnungseingangskontrolle +

Der Workflow 'Rechnungseingang' beschreibt beispielhaft einen Ablauf zur Prüfung von Eingangsrechnungen.

+ +

    +
  • Nach Erhalt einer Rechnung (z.B. Post, E-Mail, Fax,...) wird diese in das Workflowsystem übertragen und der Prozess Rechnungseingang gestartet.
  • + +
  • Die Rechnung wird wahlweise eingescannt und über den Abschnitt 'Dokumente' an den Vorgang hinzugefügt.
  • + +
  • In diesem Beispiel wird die Rechnung einem zuvor ausgewählten Mitarbeiter zur Prüfung vorgelegt.
  • + +
  • Nach positiver Prüfung werden die Rechnungsdaten (Zahlungsziel, Bankverbindung) vom Controlling im System erfasst und auf das Zahlungsziel gewartet.
  • + +
  • Nach Erreichen des Zahlungsziels wird der Vorgang automatisch dem Controlling erneut zur abschließenden Bearbeitung vorgelegt.
  • + +
+

Der Workflow

+ +

Eingangsrechnungen können über eine E-Mailschnittstelle oder das Filesystem automatisch eingelesen werden. Eine Eingangsrechnung wird in diesem Beispiel vom zugewiesenen Mitarbeiter sowie den Prozessverantworltichen (Controlling) bearbeitet.

]]>
+ SequenceFlow_4 + SequenceFlow_5 + SequenceFlow_9 + SequenceFlow_8 +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +X-Tika-OCRLanguage=eng+deu +X-Tika-PDFocrStrategy=OCR_ONLY +(PDF|pdf)$ + +]]> + + + + + + + + + + + + false + + + + SequenceFlow_9 + SequenceFlow_2 + SequenceFlow_6 + + + DataOutput_1 + + + DataOutput_1 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + invoice-de-0.1.0 +min_losses=0.01 + + invoice.total + currency + + + invoice.number + text + + + invoice.date + date + + + cdtr.name + text + + + cdtr.iban + text + + + cdtr.bic + text + +]]> + + + + + + + + + + + + false + + + + SequenceFlow_6 + SequenceFlow_7 + + + DataOutput_2 + + + DataOutput_2 + + + + + + + + + + + rechnungseingang-de-1.2 + 5000 + 990 + ]]> + + + + + + SequenceFlow_7 + SequenceFlow_10 + + + + + + + + + + + + + + + + + + + + + + + + true + + + + + + + + + + + + + + $workflowgroup - $workflowstatus]]> + SequenceFlow_11 + SequenceFlow_12 + + + SequenceFlow_10 + SequenceFlow_11 + + + + + SequenceFlow_12 + SequenceFlow_15 + + + + + SequenceFlow_2 + + + + + + + + + + + + + + + + + + + + + + + + + + SequenceFlow_5 + + + + + + + + + + + + + + + + + + + + + + true + + + + + + + + + + + + + + $workflowgroup - $workflowstatus]]> + SequenceFlow_14 + SequenceFlow_15 + + + + + + + + + SequenceFlow_8 + SequenceFlow_14 + + + + + + max_accuracy = 0.01 + + + + scann pdf files only (PDF|pdf)$ + +X-Tika-PDFocrStrategy=OCR_ONLY + + +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
\ No newline at end of file