In some implementations, a device may receive a document associated with a series of recurring events and associated with an account. The device may analyze, using at least one of an optical character recognition technique or a natural language processing technique, the document to identify one or more characteristics associated with the document. The device may match the document with a record included in a ledger associated with the account based on the one or more characteristics associated with the document, enabling the device to identify that the record is associated with a recurring event of the series of recurring events. The device may modify display information associated with the ledger to append at least one characteristic associated with the document to information associated with the record. The device may transmit, to a user device, the display information to cause the display information to be displayed by the user device.

Systems, apparatuses, and methods are described for generating simulated synthetic voice samples for use in training voice recognition models. The simulated synthetic voice samples may be diversified and in large quantities, in order to train the voice recognition models to handle a large variety of possible voice types and commands. These voice samples may be generated based on simulated user profiles indicating different types of speaker characteristics and words. The generated synthetic voice samples mimic realist human inputs and voice traffic, and may be used to test these voice recognition models for their performance in various situations. Based on the testing, these models may be efficiently retrained to improve their performance in a wide variety of conditions.

A computing system and a method of remotely verifying documents use a document verification code present on the documents. A user establishes communication with the computing system from a user computing device and is instructed to enter the document verification code displayed on a document to be verified. Depending on the code format, the user can enter the code on a keyboard or by capturing an image with a camera of the user computing device. The computing system receives and compares the received code to a plurality of verification codes stored in a storage device and transmits a message to the user device indicating that the document is valid when the received code matches one of the verification codes stored in the storage device or that the document is not valid when the received code does not match any of the verification codes stored in the storage device.

A drug inspection apparatus includes an inspection processing portion for collating a photographed image of each drug with drug master data for a dispensed drug group; and determines a normal result when the photographed image is contained in the drug group, as an uncertain result when it is uncertain if the photographed image is a drug in the drug group, and as a result to be confirmed when it is estimated that the photographed image is a drug contained in the drug group, but recommended to be confirmed by a person. The inspection result processor displays the photographed image corresponding to the drug which needs to be confirmed in a first display field that is provided corresponding to each drug which has been identified in the inspection process, on the inspection process screen, and displays the photographed image which has been determined as uncertain, in a second display field.

In some implementations, a device may receive a document associated with a series of recurring events and associated with an account. The device may analyze, using at least one of an optical character recognition technique or a natural language processing technique, the document to identify one or more characteristics associated with the document. The device may match the document with a record included in a ledger associated with the account based on the one or more characteristics associated with the document, enabling the device to identify that the record is associated with a recurring event of the series of recurring events. The device may modify display information associated with the ledger to append at least one characteristic associated with the document to information associated with the record. The device may transmit, to a user device, the display information to cause the display information to be displayed by the user device.

Disclosed is an autonomous driving control apparatus which includes at least one sensor, one or more processors, and memory. The autonomous driving control apparatus obtains, using the at least one sensor and while a driving device is being autonomously controlled, data about a driving route of the driving device, stops a movement of the driving device based on a comparison between the cumulative quantity of the edge pairs identified along the driving route and edge pair data previously stored in the memory, obtains, using the at least one sensor, at least one image, and determines, based on the at least one image, that the driving device has reached a destination.

Embodiments of the present disclosure provide systems and methods for implementing enhanced Optical Character Recognition (OCR) of text overlapping scenes through text graph structuring. Text graph structuring is performed to provide a graph data structure for each data character or letter of multiple letters and a library of graph templates from graph structured data of each of the multiple letters. Text graph structuring is performed to convert visual content of an identified overlapping text image region to an overlapping text topology graph. The overlapping text topology graph is split into multiple subgraphs using the graph template library to match recognizable letters in the overlapping text.

Computer-implemented methods, systems and devices having segmented numeral character recognition. In an embodiment, users may take digital pictures of a seven-segment display on a sensor device. For example, a user at a remote location may use a digital camera to capture a digital image of a seven-segment display on a sensor device. Captured images of a seven-segment display may then be sent or uploaded over a network to a remote health management system. The health care management system includes a reader that processes the received images to determine sensor readings representative of the values output on the seven-segment displays of the remote sensor devices. Machine learning and OCR are used to identify numeric characters in images associated with seven-segment displays. In this way, a remote heath management system can obtain sensor readings from remote locations when users only have access to sensor devices with seven-segment displays.

A method for training machine learning model is provided. The method comprises extracting texts and locations of the texts from a document, generating embeddings for the document, a first set of the embeddings characterizing a first subset of the texts and locations of the first subset of the texts and a second set of the embeddings characterizing a second subset of the texts that are masked and additional locations of the second subset of the texts that are masked, generating additional embeddings characterizing contents of the second subset of the texts, generating relevance values based on a comparison, identifying, for each of the additional locations of the second subset of the texts that are masked, a respective content of the second subset of the texts having a reference value that is higher than a remaining relevance values, and outputting each of the respective content.

An application server may receive an input document including a set of input text fields and an input key phrase querying a value for a key-value pair that corresponds to one or more of the set of input text fields. The application server may extract, using an optical character recognition model, a set of character strings and a set of two-dimensional locations of the set of character strings on a layout of the input document. After extraction, the application server may input the extracted set of character strings and the set of two-dimensional locations into a machine learned model that is trained to compute a probability that a character string corresponds to the value for the key-value pair. The application server may then identify the value for the key-value pair corresponding to the input key phrase and may out the identified value.