Platform for document classification
A device obtains image data associated with a document. Using a first machine learning model, the device determines, for the document, a first classification of one of a plurality of document types and a first confidence score associated with the first classification, and a second classification of one of the plurality of document types and a second confidence score associated with the second classification based on the image data. The device determines a difference between the first confidence score and the second confidence score, compares the difference and a threshold value, and accept the first classification of the document when the difference satisfies the threshold value.
1. A method, comprising:
obtaining, by a processor, data associated with a document;
determining, for the document, by the processor, and using a machine learning model, a classification of one of a plurality of document types and a confidence score associated with the classification based on the data,
wherein the confidence score represents a minimum confidence score that produces a reliable document classification;
comparing, by the processor, the confidence score and a threshold value; and
accepting, by the processor, the classification of the document when the confidence score satisfies the threshold value.
2. The method of claim 1 , further comprising:
determining a different confidence score that fails to satisfy a different threshold value.
3. The method of claim 1 , where the data includes image data of the document.
4. The method of claim 1 , where:
the document contains a plurality of pages,
a first page of the document corresponds to a first document type,
a second page of the document corresponds to a second document type, and
the first document type is different than the second document type.
5. The method of claim 1 , where the plurality of document types include at least one of:
a document containing personal identifying information,
a document containing tax information,
a document containing legal information, or
a document containing banking information.
6. The method of claim 1 , where the threshold value is a higher value when associated with a confidence level for a text classification than a value associated with a confidence level for an image classification.
7. The method of claim 1 , further comprising:
assigning a label corresponding to the classification; and
storing the label for access by a third party device.
8. A device, comprising:
one or more memories; and
one or more processors, coupled to the one or more memories, configured to:
obtain data associated with a document;
determine, for the document, and using a machine learning model, a classification of one of a plurality of document types and a confidence score associated with the classification based on the data,
wherein the confidence score represents a minimum confidence score that produces a reliable document classification;
compare the confidence score and a threshold value; and
provide, to a third party device, the classification of the document when the confidence score satisfies the threshold value.
9. The device of claim 8 , where the one or more processors are further configured to:
determine a different confidence score that fails to satisfy a different threshold value.
10. The device of claim 8 , where the data includes image data of the document.
11. The device of claim 8 , where:
the document contains a plurality of pages,
a first page of the document corresponds to a first document type,
a second page of the document corresponds to a second document type, and
the first document type is different than the second document type.
12. The device of claim 8 , where the threshold value is a higher value when associated with a confidence level for a text classification than a value associated with a confidence level for an image classification.
13. The device of claim 8 , where the one or more processors are further configured to:
assign a label corresponding to the classification; and
store the label for access by the third party device.
14. The device of claim 8 , where the plurality of document types include at least one of:
a document containing personal identifying information,
a document containing tax information,
a document containing legal information, or
a document containing banking information.
15. A non-transitory computer-readable medium storing instructions, the instructions comprising:
one or more instructions that, when executed by one or more processors, cause the one or more processors to:
obtain data associated with a document;
determine, for the document, and using a machine learning model, a classification of a document type and a confidence score associated with the classification based on the data,
wherein the confidence score represents a minimum confidence score that produces a reliable document classification;
compare the confidence score and a threshold value; and
provide, to a third party device, the classification of the document when the confidence score satisfies the threshold value.
16. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions when executed by the one or more processors, further cause the one or more processors to:
determine a different confidence score that fails to satisfy a different threshold value.
17. The non-transitory computer-readable medium of claim 15 , where the data includes image data of the document,
the image data including one or more of:
a Portable Document Format (PDF), or
a Joint Photographic Experts Group (JPEG).
18. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions when executed by the one or more processors, further cause the one or more processors to:
train the machine learning model to use a computer vision technique to:
identify a plurality of features of the document, and
perform a dimensionality reduction to reduce the plurality of features to a particular feature set;
where the classification is determined based on the trained machine learning model.
19. The non-transitory computer-readable medium of claim 15 , where the threshold value is a higher value when associated with a confidence level for a text classification than a value associated with a confidence level for an image classification.
20. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions when executed by the one or more processors, further cause the one or more processors to:
assign a label corresponding to the classification; and
store the label for access by the third party device.