Machine learning based classification and annotation of paragraph of resume document images based on visual properties of the resume document images, and methods and apparatus for the same

A non-transitory processor-readable medium storing code representing instructions to be executed by a processor of a first compute device, the code comprising code to cause the processor to:

• receive, from a second compute device remote from the first compute device, a statistical model trained, at the second compute device, based on (1) a plurality of resume document images having a standardized format and (2) a plurality of annotated resume document images;
• generate a resume document image, not included within the plurality of resume document images, having the standardized format, based on a resume document having a plurality of paragraphs;
• execute the statistical model to generate an annotated resume document image from the resume document image without performing optical character recognition (OCR) on text that has been extracted from the resume document image between generating the resume document image and executing the statistical model, the annotated resume document image (1) indicating a bounding box and a paragraph type, for a paragraph from the plurality of paragraphs of the annotated resume document image, and (2) not included in the plurality of annotated resume document images;
• associate the paragraph type to a block of text from a resume document associated with the annotated resume document image after executing the statistical model, the block of text corresponding to the paragraph of the annotated resume document image;
• and
• match the block of text from the resume document to a job posting from a set of job postings.

A method, comprising:

• annotating, for each resume document images from a plurality of resume document images, a plurality of paragraphs of that resume document image with a plurality of bounding boxes to generate a plurality of annotated resume document images, each bounding box from the plurality of bounding boxes indicating a paragraph type from a plurality of paragraph types;
• generating a resume document image having a standardized format and not included within the plurality of annotated resume document images, based on a resume document not included within the plurality of resume documents;
• executing a statistical model trained based on the plurality of annotated resume document images, to generate an annotated resume document image based on the resume document image not included within the plurality of annotated resume document images, the annotated resume document image indicating a bounding box and a paragraph type, for each paragraph of the resume document image;
• identifying, for a paragraph of the annotated resume document image and after executing the statistical model, a block of text corresponding to the paragraph of the annotated resume document image, in the resume document not included within the plurality of resume documents;
• and
• updating a job posting associated with the resume document based on at least one of the block of text or the paragraph type.