Methods and systems disclosed herein may quantify the content and nature of a first stream of text to detect when the typical composition of the first stream of text changes. Quantifying the content and nature of the first stream of text may begin by generating a baseline representation of the content of the first stream of text as represented by a first matrix. Once generated, the first matrix may be used as a control against subsequently received sequences of text. In this regard, a second matrix may be generated from a second sequence of text and compared to the first matrix to determine the differences between the first sequence of text and the second sequence of text. Once a difference is determined, the difference may be compared to a threshold value and, when the difference exceeds the threshold value, an administrator may be notified and corrective action taken.

Disclosed are techniques for enhancing two-dimensional (2D) image capture of subjects (e.g., a physical structure, such as a residential building) to maximize the feature correspondences available for three-dimensional (3D) model reconstruction. More specifically, disclosed is a computer-vision network configured to provide viewfinder interfaces and analyses to guide the improved capture of an intended subject for specified purposes. Additionally, the computer-vision network can be configured to generate a metric representing a quality of feature correspondences between images of a complete set of images used for reconstructing a 3D model of a physical structure. The computer-vision network can also be configured to generate feedback at or before image capture time to guide improvements to the quality of feature correspondences between a pair of images.

A method and apparatus for adaptively displaying a handwriting input on an electronic device are provided. The method includes receiving a handwriting input from an electronic device, detecting handwriting features in the handwriting input and comparing the handwriting features with stored handwriting feature data, determining, according to a result of the comparing, whether a subject of the handwriting input is an existing user or a new user, and displaying, according to the determination, a subsequent handwriting input by the subject of the handwriting input to match a target handwriting input style.

Methods and systems disclosed herein may quantify the content and nature of a first stream of text to detect when the typical composition of the first stream of text changes. Quantifying the content and nature of the first stream of text may begin by generating a baseline representation of the content of the first stream of text as represented by a first matrix. Once generated, the first matrix may be used as a control against subsequently received sequences of text. In this regard, a second matrix may be generated from a second sequence of text and compared to the first matrix to determine the differences between the first sequence of text and the second sequence of text. Once a difference is determined, the difference may be compared to a threshold value and, when the difference exceeds the threshold value, an administrator may be notified and corrective action taken.

Symbol prediction can be implemented using a multi-task system trained for different tasks. The tasks may include a single symbol prediction, symbol category prediction, and symbol subcategory prediction. Categories of symbols can be generated by clustering sets of training data using a clustering scheme.

Representative embodiments disclose mechanisms to create a text stream from raw OCR outputs. The raw OCR output comprises a plurality of bounding boxes, each bounding box defining a region containing text which has been recognized by the OCR system. A weight matrix is calculated that comprises a weight for each pair of bounding boxes. The weight representing the probability that a pair of bounding boxes belongs to the same cluster. The bounding boxes are then clustered along the weights. The resulting clusters are first ordered using an ordering criteria. The bounding boxes within each cluster are then ordered according to a second ordering criteria. The ordered clusters and bounding boxes are then arranged into a text stream.

Symbol prediction can be implemented using a multi-task system trained for different tasks. The tasks may include a single symbol prediction, symbol category prediction, and symbol subcategory prediction. Categories of symbols can be generated by clustering sets of training data using a clustering scheme.

The present disclosure relates to a system and method to extract information from unstructured image documents. The extraction technique is content-driven and not dependent on the layout of a particular image document type. The disclosed method breaks down an image document into smaller images using the text cluster detection algorithm. The smaller images are converted into text samples using optical character recognition (OCR). Each of the text samples is fed to a trained machine learning model. The model classifies each text sample into one of a plurality of pre-determined field types. The desired value extraction problem may be converted into a question-answering problem using a pre-trained model. A fixed question is formed on the basis of the classified field type. The output of the question-answering model may be passed through a rule-based post-processing step to obtain the final answer.

Methods, apparatus, systems, and articles of manufacture are disclosed that determine related content. An example apparatus includes processor circuitry to generate a segment-level graph by sampling segment-level edges among segment nodes representing text segments, the segment-level graph including segment node embeddings representing features of the segment nodes; cluster the text segments to form entities by applying a first GAN based model to the segment-level graph to update the segment node embeddings; generate a multi-level graph by (a) generating an entity-level graph including hypernodes representing the entities and sampled entity edges connecting ones of the hypernodes, and (b) connecting the segment nodes to respective ones of the hypernodes using relation edges; generate hypernode embeddings by propagating the updated segment node embeddings using a relation graph; and cluster the entities by product by applying a second GAN based model to the multi-level graph, the multi-level graph to generate updated hypernode embeddings.

Representative embodiments disclose mechanisms to create a text stream from raw OCR outputs. The raw OCR output comprises a plurality of bounding boxes, each bounding box defining a region containing text which has been recognized by the OCR system. A weight matrix is calculated that comprises a weight for each pair of bounding boxes. The weight representing the probability that a pair of bounding boxes belongs to the same cluster. The bounding boxes are then clustered along the weights. The resulting clusters are first ordered using an ordering criteria. The bounding boxes within each cluster are then ordered according to a second ordering criteria. The ordered clusters and bounding boxes are then arranged into a text stream.