Patents

The present invention provides apparatuses, systems, and methods directed to AI systems that are able to classify and verify documents that are present in files that are uploaded to the system. In one aspect of the inventive subject matter, a method of using an artificial intelligence (AI) system to classify documents comprises the steps of: receiving, at a platform server running the AI system, a file comprising a document; conducting optical character recognition (OCR) on the document to extract text content of the document; identifying a document candidate based on the text content, where the document candidate has an expected document shape; detecting a shape of the document in the file; and classifying the document at least in part by determining whether the shape of the document matches the expected document shape; upon determining that the shape of the document matches the expected shape, verifying that the document candidate is correctly classified.

The present invention is directed to apparatuses, systems, and methods that use artificial intelligence to facilitate document segmentation. Document segmentation can be useful to isolate multiple documents that are included in, e.g., a single image so that each document can be processed individually. In one aspect of the inventive subject matter, a method of document segmentation using artificial intelligence (AI) includes the steps of: receiving, by an AI system, a file comprising an image of a first document and a second document; converting, by the AI system, the file into a tensor; applying a deep learning model to the tensor to create a mask image from the tensor, where the deep learning model has been trained using a training set of images having ground truth masks and where each image in the training set comprises at least two documents; converting the mask image to a grayscale image; applying thresholding to the grayscale image to create a black and white image; applying image processing to the black and white image to identify a first white space and a second white space along with a first contour surrounding the first white space and a second contour surrounding the second white space; where the first contour comprises a first list of vectors that form a first closed shape around the first white space, and wherein the second contour comprises a second list of vectors that form a second closed shape around the second white space; where the first white space has a first area the second white space has a second area; where the black and white image has a total area; comparing the first area to the total area to get a first ratio and comparing the second area to the total area to get a second ratio; comparing the first ratio and the second ratio to a threshold value; upon determining the first ratio exceeds the threshold value, recording the first contour; upon determining the second ratio exceeds the threshold value, recording the second contour; identifying a first minimum bounding rectangle that surrounds the first contour and cropping the image according to the first minimum bounding rectangle to create a first processable image; and identifying a second minimum bounding rectangle that surrounds the second contour and cropping the image according to the second minimum bounding rectangle to create a second processable image.

The present invention provides apparatus, systems, and methods directed to artificial intelligence systems that are capable of determining whether a driver’s license or ID card from one of the states of the United States is Real ID compliant or an Enhanced ID. In one aspect of the inventive subject matter, a method of using artificial intelligence to identify visual indicators on identification cards and driver’s licenses includes the steps of: receiving, by an artificial intelligence system via upload, a digital file, where the digital file comprises a document that is either an identification card or driver’s license from one of the states of the United States; transforming the digital file into a tensor; applying a deep learning model to the tensor, where the deep learning model has been trained to identify visual indicator candidate locations, each visual indicator candidate location having a visual indicator type and a confidence value; where the visual indicator type is a Real ID visual indicator or an Enhanced ID visual indicator; identifying, by applying the deep learning model, a set of visual indicator candidate locations on the document; applying non-maximum suppression to filter the set of visual indicator candidate locations, resulting in a final visual indicator location having a final confidence value and a final visual indicator type; and confirming the final visual indicator type associated with the final visual indicator location by determining that the final confidence value exceeds a confidence value threshold.

The present invention provides apparatuses, systems, and methods directed to AI systems that are able to classify and verify documents that are present in files that are uploaded to the system. In one aspect of the inventive subject matter, a method of using an artificial intelligence (AI) system to classify documents comprises the steps of: receiving, at a platform server running the AI system, a file comprising a document; conducting optical character recognition (OCR) on the document to extract text content of the document; identifying a document candidate based on the text content, where the document candidate has an expected document shape; detecting a shape of the document in the file; and classifying the document at least in part by determining whether the shape of the document matches the expected document shape; upon determining that the shape of the document matches the expected shape, verifying that the document candidate is correctly classified.

The present invention provides apparatuses, systems, and methods directed to document data extraction to facilitate searching. In one aspect of the inventive subject matter, a method of extracting searchable content from an uploaded document is contemplated, the method comprises the steps of: extracting document content from the uploaded document, the document content comprising field labels having associated field content; indexing the document content according to a taxonomy (e.g., user-defined or built-in) to create key-value pairs, where the taxonomy comprises a set of known keys that field labels can be mapped to, and where each key-value pair comprises a field label matched to a key and field content matched to a value; conducting OCR on the uploaded document to extract text content; transforming, using a large language model (LLM), the text content to create LLM generated key-value pairs; and storing the key-value pairs and the LLM generated key-value pairs to a database.