A method for matching character strings to a reference character string is disclosed. One or more processors receive a plurality of character strings. The one or more processors match each of the plurality of character strings to a main reference character string and registers a match to positions on the main reference character string that satisfy a pre-set match criteria. The one or more processors match each of the plurality of character strings to an alternate reference character string and registers a match to positions on the alternate reference character string that satisfy the pre-set match criteria. The alternate reference character string is derived from the main character string. The one or more processors identifies a match for each of the plurality of character strings that match to either a position on the main reference character string or the alternate reference character string.

Embodiments of this application disclose a method for retrieving similar videos performed at a computing device. The computing device obtains video information of a video for which similar videos are to be retrieved, the video information including a video tag and a video title, and trains the video information by using a preset text depth representation model, to convert the video information into a word vector. After selecting, from a video library according to a preset knowledge graph, videos matching the video information, to obtain a first candidate video set, the computing device screens, in the video library, videos similar to the video information according to the word vector, to obtain a second candidate video set and then determines a similar video for the video information from the first candidate video set and the second candidate video set.

Disclosed herein are computer-implemented methods; computer-implemented systems; and non-transitory, computer-readable media, for quantifying text similarity. One computer-implemented method includes obtaining a plurality of shortest operation paths including one or more edit pairs for correcting an optical correction recognition (OCR) text string with an edit text string, where each of the one or more edit pairs denotes an operation performable to a character of the OCR text string during correction by the edit text string. A plurality of similarity scores is determined, each corresponding to one of the plurality of shortest operation paths and determined by summing historical similarity scores of the one or more edit pairs of each of the plurality of shortest operation paths. A minimum one of the plurality of similarity scores is selected to quantify text similarity between the OCR text string and the edit text string.

A document processing system is configured to identify, for each accessed electronic document in a first set of multiple electronic documents, a set of identified multi-word phrases determined to be in ordered text information in the accessed electronic document, each multi-word phrase of the set of identified multi-word phrases including adjacent words in the ordered text information; and determine, for each accessed electronic document in the first set of multiple electronic documents, a selected document type from the first set of document types based at least on an analysis of the set of identified multi-word phrases with respect to multi-word-phrase characteristics identified by a first definition and associated with each document type in a first set of document types associated with a first document-set type.

A computer-implemented tool for automated classification and interpretation of documents, such as life science documents supporting clinical trials, is configured to perform a combination of raw text, document construct, and image analyses to enhance classification accuracy by enabling a more comprehensive machine-based understanding of document content. The combination of analyses provides context for classification by leveraging relative spatial relationships among text and image elements, identifying characteristics and formatting of elements, and extracting additional metadata from the documents as compared to conventional automated classification tools.

A computer-implemented tool for automated classification and interpretation of documents, such as life science documents supporting clinical trials, is configured to perform a combination of raw text, document construct, and image analyses to enhance classification accuracy by enabling a more comprehensive machine-based understanding of document content. The combination of analyses provides context for classification by leveraging relative spatial relationships among text and image elements, identifying characteristics and formatting of elements, and extracting additional metadata from the documents as compared to conventional automated classification tools.

Similarity detection methods and systems are provided that utilize a convolutional neural network model to jointly learn string matching and semantic textual similarity as an image recognition solution. For example, in some embodiments described herein, the similarity detection system may receive two strings as input, transform the two strings into two separate vectors, generate a high-resolution image and a low-resolution image, apply one or more convolutional operations to each image, and determine string matching and semantic textual similarity based at least partly on the high-resolution image and the low-resolution image.

A pattern recognition locking system and method is operable to lock and unlock an object through a sequence of knocks, rotations, and ambient vibrations that are measured by an accelerometer as acceleration, and a gyroscope as orientation. The sequence and intensity of vibrations and intensity are processed by a microcontroller that utilizes a pattern recognition algorithm to: recognize the intensity and sequence of acceleration and orientation; identify the most intense motion from the degrees of freedom; and, after identifying a sequence of the most intense motions for respective degree of freedom, the microcontroller transmits a signal to lock mechanism to lock or unlock an object if sequence of degrees of motion match a stored passcode. A sleep module powers off the system when no motion or vibrations detected. A new sequence of ambient vibrations and motion are created through a learning module. A reset switch reprograms the sequence of motions.

A character recognizing apparatus includes an acquiring unit, an identifying unit, and a character recognizing unit. The acquiring unit acquires a string image that is an image of a string generated in accordance with one of multiple string generation schemes. The identifying unit identifies a range specified for a result of character recognition in each of the multiple string generation schemes. The character recognizing unit performs first character recognition on the string image, and if a result of the first character recognition has a feature of a particular string generation scheme of the multiple string generation schemes, the character recognizing unit performs second character recognition on the string image within the range specified for a result of character recognition in the particular string generation scheme.

Disclosed herein are a method and an apparatus for detecting abnormal traffic based on a convolutional autoencoder (CAE). The method of detecting abnormal traffic based on the CAE may include converting a character string of normal traffic into an image, learning the converted image using the CAE, and detecting abnormal traffic by inputting target traffic to the learned CAE.