FIELD: information technology.
SUBSTANCE: in the method for determining the type of digital document, the processed digital document is received. Using the electronic device processor, many classifiers are started on the basis of the machine learning algorithm (MLA). In this case, each classifier from the set of MLA classifiers is trained to determine a specific type of document. The set of MLA classifiers is arranged in a hierarchical order of execution of the set of MLA classifiers. They determine in the hierarchical order of execution whether the document type relates to one of the types of documents confidently determined by each of the MLA classifiers.
EFFECT: reducing the required computing resources to determine the type of digital documents.
57 cl, 8 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD AND DEVICE FOR DETERMINING DOCUMENT SUITABILITY FOR OPTICAL CHARACTER RECOGNITION (OCR) ON SERVER | 2016 |
|
RU2640296C1 |
METHOD AND DEVICE FOR DETERMINING DOCUMENT SUITABILITY FOR OPTICAL CHARACTER RECOGNITION (OCR) | 2016 |
|
RU2634195C1 |
TRAINING CLASSIFIERS USED TO EXTRACT INFORMATION FROM NATURAL LANGUAGE TEXTS | 2018 |
|
RU2691855C1 |
CLASSIFIER TRAINING USED FOR EXTRACTING INFORMATION FROM TEXTS IN NATURAL LANGUAGE | 2018 |
|
RU2681356C1 |
USING VERIFIED BY USER DATA FOR TRAINING MODELS OF CONFIDENCE | 2016 |
|
RU2646380C1 |
TRAINING METHOD OF RATING MODULE USING THE TRAINING SELECTION WITH THE INTERFERENCE LABELS | 2016 |
|
RU2632143C1 |
VERIFICATION OF INFORMATION OBJECT ATTRIBUTES | 2016 |
|
RU2640718C1 |
CHARACTER RECOGNITION USING A HIERARCHICAL CLASSIFICATION | 2018 |
|
RU2693916C1 |
SYSTEM AND METHOD OF FORMING TRAINING SET FOR MACHINE LEARNING ALGORITHM | 2017 |
|
RU2711125C2 |
METHOD AND SYSTEM FOR CLASSIFYING AN ELECTRONIC DEVICE USER | 2021 |
|
RU2795152C2 |
Authors
Dates
2017-11-09—Published
2016-06-22—Filed