Disclosed are techniques for building a dynamic dictionary and using the dictionary to remove phrases or words appearing in and out of context in a document. The techniques include, for example, receiving electronic health record (EHR) data, determining, using natural language processing (NLP), an instance of a personal health information (PHI) phrase in the EHR data based on a NLP system confidence metric being above a threshold, determining another instance of the PHI phrase in the EHR data that does not have the same context as the first context, removing the instances of the PHI phrase from the EHR data to produce cleaned EHR data, and taking an action based on the cleaned EHR data. The confidence metric can indicate likelihood that the PHI phrase is a PHI phrase and the metric can be based at least in part on a first context of the PHI phrase.

An auto-rotation module having a single-layer neural network on a user device can convert a document image to a monochrome image having black and white pixels and segment the monochrome image into bounding boxes, each bounding box defining a connected segment of black pixels in the monochrome image. The auto-rotation module can determine textual snippets from the bounding boxes and prepare them into input images for the single-layer neural network. The single-layer neural network is trained to process each input image, recognize a correct orientation, and output a set of results for each input image. Each result indicates a probability associated with a particular orientation. The auto-rotation module can examine the results, determine what degree of rotation is needed to achieve a correct orientation of the document image, and automatically rotate the document image by the degree of rotation needed to achieve the correct orientation of the document image.

A character recognition method includes inputting an input image of a document, with the input image including a plurality of characters; selecting the plurality of characters through an object detection module to form at least one character region; separating the plurality of characters in the at least one character region to form a plurality of character boxes; performing calculation to determine a format of a character in each of the plurality of character boxes; recognizing the characters in the at least one character region through an object recognition module to determine a symbol content of the character in each of the plurality of character boxes; and converting the plurality of characters according to the format and symbol content of the character in each of the plurality of character boxes, and outputting corresponding editable characters.

In some aspects, a method includes performing optical character recognition (OCR) based on data corresponding to a document to generate text data, detecting one or more bounded regions from the data based on a predetermined boundary rule set, and matching one or more portions of the text data to the one or more bounded regions to generate matched text data. Each bounded region of the one or more bounded regions encloses a corresponding block of text. The method also includes extracting features from the matched text data to generate a plurality of feature vectors and providing the plurality of feature vectors to a trained machine-learning classifier to generate one or more labels associated with the one or more bounded regions. The method further includes outputting metadata indicating a hierarchical layout associated with the document based on the one or more labels and the matched text data.

Disclosed is an effective domain name defense solution in which a domain name string may be provided to or obtained by a computer embodying a visual domain analyzer. The domain name string may be rendered or otherwise converted to an image. An optical character recognition function may be applied to the image to read out a text string which can then be compared with a protected domain name to determine whether the text string generated by the optical character recognition function from the image converted from the domain name string is similar to or matches the protected domain name. This visual domain analysis can be dynamically applied in an online process or proactively applied in an offline process to hundreds of millions of domain names.

Enhanced techniques and circuitry are presented herein for providing responses to questions from among digital documentation sources spanning various documentation formats, versions, and types. One example includes a method comprising receiving an indication of a question directed to subject having a documentation corpus, determining a set of passages of the documentation corpus related to the question, ranking the set of passages according to relevance to the question, forming semantic clusters comprising sentences extracted from ranked ones of the set of passages according to sentence similarity, and providing a response to the question based at least on a selected semantic cluster.

Briefly, embodiments of a system, method, and article for receiving a document from a remote device and identifying items in the document. Various operations may be performed based on one or more dependencies of the identified items. For example, additional items may be identified in the document. One or more of the identified items may be parsed. A correspondence between the identified items and a second set of items may be determined. The identified items may be validated based on a set of rules. One or more of the identified items may be transmitted to the remote device in response to the performance of the various operations.

Users of a database management engine may generate fillable digital documents by mapping interface elements onto form documents. When a user maps interface elements onto a form document, the user may accidentally overlap two or more interface elements. To rectify this, the database management engine may modify the position of one of interface elements based on a set of positioning rules. In addition, the database management engine may identify and suggest mappings to users based on similar documents that have been previously mapped. The database management engine identifies similar documents using information about the document, the user, and the mapping itself. The mapping associated with the most similar document may be provided to the user as a suggested mapping. The database management engine converts the form document and finalized mapping into a fillable digital document. The fillable digital document is sent to recipients, who complete the fillable digital document.

Methods and devices for generating a training sample, training a model and recognizing a character are provided. The method for generating a training sample comprises: acquiring an image of characters, and determining respective characters contained in the image; and using a projection method to determine weights of the respective characters contained in the image, tagging the image with labels according to the weights of the respective characters contained in the image, and forming a training sample. The method for training a model comprises: using the training sample to train a character recognition model. The method for recognizing a character comprises: using the character recognition model to perform character recognition. The above methods and devices realize accurate recognition of characters, such as double-half characters, contained in an image of a wheel-type meter, and can provide a highly accurate biased recognition result.

Systems and methods are disclosed for selectively reading text. A system may comprise an image capture device, an audio capture device, and a processor. The processor may be configured to receive images captured by the image capture device and audio signals captured by the audio capture device. The processor may analyze the image to identify text represented in the image; identify, based on the image, a structural element of the text; identify a request to read a first portion of the text associated with the structural element, the request being identified by at least one of analyzing the audio signals to detect a spoken request or detecting a gesture in the plurality of images; and present the first portion of text to the user of the wearable device.