There is described a neural network system implemented by one or more computers for determining graph similarity. The neural network system comprises one or more neural networks configured to process an input graph to generate a node state representation vector for each node of the input graph and an edge representation vector for each edge of the input graph; and process the node state representation vectors and the edge representation vectors to generate a vector representation of the input graph. The neural network system further comprises one or more processors configured to: receive a first graph; receive a second graph; generate a vector representation of the first graph; generate a vector representation of the second graph; determine a similarity score for the first graph and the second graph based upon the vector representations of the first graph and the second graph.

Systems and methods for generating embeddings for nodes of a corpus graph are presented. More particularly, operations for generation of an aggregated embedding vector for a target node is efficiently divided among operations on a central processing unit and operations on a graphic processing unit. With regard to a target node within a corpus graph, processing by one or more central processing units (CPUs) is conducted to identify the target node's relevant neighborhood (of nodes) within the corpus graph. This information is prepared and passed to one or more graphic processing units (GPUs) that determines the aggregated embedding vector for the target node according to data of the relevant neighborhood of the target node.

A method of detecting a pattern in common in two text files, each comprising an ordered sequence of words, is disclosed. The method includes generating groups of words having the same syntactic function, comprising at least one word from each text file such that each word in a group is synonymous with another word in the same group, associating each word in a text file belonging to a group of words with a tag representative of the group, generating, for each text file, at least one dense set of words satisfying a condition of internal proximity in the text file, determining at least one pattern in common in the two text files, a pattern in common including one or more sets of words sharing the same tag and comprising at least one word from a dense set of words in each text file.

Systems and methods for displaying medical studies. A system includes an electronic processor configured to receive a reference medical study, of a patient, having a reference modality identifier and a reference procedure type in metadata of the reference medical study; access additional medical studies of the patient, each additional medical study having a modality identifier, a procedure type, and a study time in metadata of additional medical studies; apply a set of rules to additional medical studies to determine a relevancy level for each additional medical studies from a set of relevancy levels; generate and display a GUI having a patient-centric timeline including a node for each additional medical study, the node positioned along a first dimension of the timeline based on the study time of the additional medical study and positioned along a second dimension of the timeline based on the relevancy level of the additional medical study.

The present invention relates to a character information recognition method based on image processing. The method comprises: collecting images to obtain a target character image; then sequentially comparing the target character image with character template images in a character template library to find a maximum of a coincidence area of the character in the target character image with the character templates in the character template images; and when the coincidence area meets a preset condition, determining the target character to be recognized as the character in the corresponding character template image. The character templates are designed to include not only a coincidence-permitted region but also a coincidence-restricted region. The coincidence-restricted region is set, so that the direct comparing and matching of the character templates can be more accurately carried out, thereby improving the recognition speed.

Systems and methods for personal data classification, linkage and purpose of processing prediction are provided. The system for personal data classification includes an entity extraction module for extracting personal data from one or more data repositories in a computer network or cloud infrastructure, a linkage module coupled to the entity extraction module, a linkage module coupled to the entity extraction module and a processing prediction module. The entity extraction module performs entity recognition from the structured, semi-structured and unstructured records in the one or more data repositories. The linkage module uses graph-based methodology to link the personal data to one or more individuals. And the purpose prediction module includes a feature extraction module a purpose of processing prediction module, wherein the feature extraction module extracts both context features and record's features from records in the one or more data repositories, and the purpose of processing prediction module predicts a unique or multiple purpose of processing of the personal data.

The description relates the feature matching. Our approach establishes pointwise correspondences between challenging image pairs. It takes off-the-shelf local features as input and uses an attentional graph neural network to solve an assignment optimization problem. The deep middle-end matcher acts as a middle-end and handles partial point visibility and occlusion elegantly, producing a partial assignment matrix.

A string of Latin-alphabet based language texts is received and formed a multi-layer 2-D symbol in a computing system. The received string contains at least one word with each word containing at least one letter of the Latin-alphabet based language. 2-D symbol comprises a matrix of NN pixels of data representing a super-character. The matrix is divided into MM sub-matrices. Each sub-matrix represents one ideogram formed from the at least one letter contained in a corresponding word in the received string. Ideogram has a square format with a dimension EL letters by EL letters (i.e., row and column). EL is determined from the total number of letters (LL) contained in the corresponding word. EL, LL, N and M are positive integers. Super-character represents a meaning formed from a specific combination of at least one ideogram. Meaning of the super-character is learned with image classification of the 2-D symbol.

One or more image parameters of an image may be analyzed using a hierarchical set of models. Executing individual models in the set of models may generate outputs from analysis of different image parameters of the image. Inputs of one or more of the models may be conditioned on a set of outputs derived from one or more preceding model in the hierarchy.

A text correction method and apparatus can take advantage of a greatly reduced number of error-ground truth pairs to train a deep learning model. To generate these error-ground truth pairs, different characters in a ground truth word are replaced with a symbol, not appearing in any ground truth words, to generate error words which are paired with that ground truth word to provide error-ground truth word pairs. This process may be repeated for all ground truth words for which training is to be performed. In embodiments, pairs of characters in a ground truth word may be replaced with a symbol to generate the error words which are paired with that ground truth word to provide error-ground truth word pairs. Again, this process may be repeated for all ground truth words for which training is to be performed.