An electronic communications method, includes receiving, by a computing device, first electronic information associated with generated a graphical feature in a graphical user interface. The electronic communications method further includes generating, by the computing device, the graphical feature. The electronic communications method further includes sending, by the computing device, the graphical feature to another computing device. The electronic communications method further receiving, by the computing device, second electronic information to classify the graphical feature as public information. The electronic communications method further includes sending, by the computing device, the graphical feature to a third computing device based on the classification of the graphical feature as public information.

An electronic communications method, includes receiving, by a computing device, first electronic information associated with generated a graphical feature in a graphical user interface. The electronic communications method further includes generating, by the computing device, the graphical feature. The electronic communications method further includes sending, by the computing device, the graphical feature to another computing device. The electronic communications method further receiving, by the computing device, second electronic information to classify the graphical feature as public information. The electronic communications method further includes sending, by the computing device, the graphical feature to a third computing device based on the classification of the graphical feature as public information.

Disclosed herein are system, method, and computer program product embodiments for providing recommendations for splitting bills. The approaches disclosed include the ability to obtain information about a bill to be split (such as a photo of the bill), and then use several machine learning models to determine the ‘who,’ ‘what,’ and ‘where’ of the underlying transaction. In particular, machine learning models described herein are used to perform facial recognition of a ‘selfie’ taken when a transaction was made against social media accounts to determine participants of the transaction. The machine learning models may also identify expected pricing from data about a merchant associated with the transaction, and expected amounts for each participant based on the expected pricing.

Disclosed herein are system, method, and computer program product embodiments for providing recommendations for splitting bills. The approaches disclosed include the ability to obtain information about a bill to be split (such as a photo of the bill), and then use several machine learning models to determine the ‘who,’ ‘what,’ and ‘where’ of the underlying transaction. In particular, machine learning models described herein are used to perform facial recognition of a ‘selfie’ taken when a transaction was made against social media accounts to determine participants of the transaction. The machine learning models may also identify expected pricing from data about a merchant associated with the transaction, and expected amounts for each participant based on the expected pricing.

Systems and methods for performing spatial line grouping on digital ink stokes. The system includes an electronic processor configured to access a set of hypothetical lines in an electronic document and determine a set of hypothetical line pairings. The electronic processor is also configured to determine, via a gradient boosting tree model, a merge confidence score for each hypothetical line pairing and compare a first merge confidence score with a merge threshold. The first merge confidence score is associated with a first hypothetical line and a first neighboring hypothetical line. The electronic processor is also configured to, in response to the first merge confidence score satisfying the merge threshold, merge the first hypothetical line and the first neighboring hypothetical line to form a first line grouping. The electronic processor is also configured to perform a digital ink stroke analysis on the electronic document based on the first line grouping.

Methods and systems are presented for detecting a boundary of a document within a digital image. Upon receiving an image, the image is converted into a binary image. One or more kernel-based transformations are performed on the binary image using a horizontal kernel and a vertical kernel. A plurality of edges are identified based on the one or more kernel-based transformations. The plurality of edges includes a plurality of horizontal edges and a plurality of vertical edges. Multiple quadrilaterals are constructed using different combinations of horizontal edges and vertical edges from the plurality of edges. A particular quadrilateral is selected from the multiple quadrilaterals based on how well the edges fit the perimeters of the quadrilaterals. The selected quadrilateral is used to define a boundary of the document within the digital image.

Disclosed embodiments include systems and methods for improving the accuracy of online banking systems. In various embodiments, the system includes a user device capturing receipt information from one or more e-commerce application and a server device for associating captured receipt information with transaction data. The system may include a browser extension for facilitating automatic capture of receipt information and a matching module for associating receipt information with transaction data. In various embodiments, transactions displayed in transaction statements within an online banking application are augmented with item level data including product name, price, and vendor for each product included in a transaction.

Disclosed embodiments include systems and methods for improving the accuracy of online banking systems. In various embodiments, the system includes a user device capturing receipt information from one or more e-commerce application and a server device for associating captured receipt information with transaction data. The system may include a browser extension for facilitating automatic capture of receipt information and a matching module for associating receipt information with transaction data. In various embodiments, transactions displayed in transaction statements within an online banking application are augmented with item level data including product name, price, and vendor for each product included in a transaction.

A method and system are provided for removing noise from document images using a neural network-based machine learning model. A dataset of original document images is used as an input source of images. Random noise is added to the original document images to generate noisy images, which are provided to a neural network-based denoising system that generates denoised images. Denoised images and original document images are evaluated by a neural network-based discriminator system, which generates a predictive output relating to authenticity of evaluated denoised images. Feedback is provided backpropagation updates to train both the denoising and discriminator systems. Training sequences are iteratively performed to provide the backpropagation updates, such that the denoising system is trained to generate denoised images that can pass as original document images while the discriminator system is trained to improve the accuracy in predicting the authenticity of the images presented.

A method and system are provided for removing noise from document images using a neural network-based machine learning model. A dataset of original document images is used as an input source of images. Random noise is added to the original document images to generate noisy images, which are provided to a neural network-based denoising system that generates denoised images. Denoised images and original document images are evaluated by a neural network-based discriminator system, which generates a predictive output relating to authenticity of evaluated denoised images. Feedback is provided backpropagation updates to train both the denoising and discriminator systems. Training sequences are iteratively performed to provide the backpropagation updates, such that the denoising system is trained to generate denoised images that can pass as original document images while the discriminator system is trained to improve the accuracy in predicting the authenticity of the images presented.