Abstract: A processor may obtain historic clickstream data indicating a plurality of interactions with a user interface (UI) by a plurality of users. The processor may select at least one user for real-time monitoring by processing, using a machine learning (ML) model, the historic clickstream data and at least one user feature and predicting, from the processing, that the at least one user will utilize a UI resource. The processor may monitor ongoing clickstream data of the selected at least one user and configure the UI resource according to the ongoing clickstream data.

Abstract: A method includes executing an encoder machine learning model on multiple token values contained in a document to create an encoder hidden state vector. A decoder machine learning model executing on the encoder hidden state vector generates raw text comprising an entity value and an entity label for each of multiple entities. The method further includes generating a structural representation of the entities directly from the raw text and outputting the structural representation of the entities of the document.

Abstract: The invention relates to a method for allowing users to categorize transactions at moment-of-sale using mobile payments. The method includes detecting a transaction performed on a mobile device. The method further includes prompting, a user of the mobile device to provide a categorization of the transaction as a business transaction or a personal transaction, where the transaction is categorized by the user contemporaneously with the transaction being detected by the FMA interface. The method further includes receiving the transaction and the categorization of the transaction from the user. The method further includes sending the FMA time stamp of the transaction with the categorization as the business transaction, Finally, the method includes matching the FMA time stamp of the business transaction to a financial institution time stamp of a pending transaction.

Abstract: A method and system distinguish between anomalous members of a majority group and members of a target group. The system and method utilize a neural network architecture that attends to each level of a classification hierarchy. The system and method chain a semi-supervised autoencoder with a supervised classifier neural network. The autoencoder is trained in a semi-supervised manner with a machine learning process to identify user profile data that are typical of a majority class. The classifier neural network is trained in a supervised manner with a machine learning process to distinguish between user profile data that are anomalous members of the majority class and user profile data that are members of the target class.

Abstract: This disclosure relates to restricting access in a social network. The social network stores profile information for each of a plurality of users of the social network in a database. The social network receives, from a first user of the social network, a request to invite a second user to establish a connection with the first user. The social network transmits, to the first user, one or more questions pertaining to the profile information of the second user. The social network receives, from the first user, one or more answers responsive to the one or more questions. The social network determines whether each of the answers is correct based on the stored profile information of the second user. The social network transmits, to the second user, an invitation to establish the connection with the first user when at least a number of the answers are correct.

Abstract: Systems and methods are disclosed. An example method may be performed by one or more processors of a system and include retrieving case data indicating, for each respective case of a number of cases, one or more documents retrieved to assist a system user associated with the respective case, generating, from the case data, a case matrix including a plurality of rows each corresponding to a respective case of the number of cases and a plurality of columns each corresponding to the documents retrieved to assist the system user associated with the respective case, and identifying groups of similar cases among the plurality of cases based on a clustering process performed on at least a portion of the case matrix.

Abstract: A processor may receive an image and identify a plurality of characters in the image using a machine learning (ML) model. The processor may generate at least one word-level bounding box indicating one or more words including at least a subset of the plurality of characters and/or may generate at least one field-level bounding box indicating at least one field including at least a subset of the one or more words. The processor may overlay the at least one word-level bounding box and the at least one field-level bounding box on the image to form a masked image including a plurality of optically-recognized characters and one or more predicted fields for at least a subset of the plurality of optically-recognized characters.

Abstract: Aspects of the present disclosure provide techniques for image-based document search. Embodiments include receiving an image of a document and providing the image of the document as input to a machine learning model, where the machine learning model generates separate embeddings of a plurality of patches of the image of the document and the machine learning model generates an embedding of the image of the document based on the separate embeddings of the plurality of patches. Embodiments include determining a compact embedding of the image of the document based on applying a dimensionality reduction technique to the embedding of the image of the document generated by the machine learning model. Embodiments include performing a search for relevant documents based on the compact embedding of the image of the document. Embodiments include performing one or more actions based on one or more relevant documents identified through the search.

Abstract: Systems and methods for personalizing messages in a conversational chatbot are disclosed. An example method may include receiving clickstream event data corresponding to click events by users of an application, generating featurized clickstream data based at least in part on the received clickstream event data, determining one or more predicted intentions for a first user based at least in part on the featurized clickstream data, and generating one or more personalized messages for the first user based at least in part on the one or more predicted user intentions.

Abstract: A method for classifying organizations involves obtaining, for an unknown organization, transactional data representing a multitude of transactions. The transactional data comprises a descriptive text for each of the multitude of transactions. The method further involves processing the descriptive text for each of the multitude of transactions to obtain one vector representing the unknown organization, categorizing the unknown organization using a classifier applied to the vector, and identifying a software service for the unknown organization, according to the categorization.

Abstract: A method includes executing a Optical Character Recognition (OCR) preprocessor on training images to obtain OCR preprocessor output, executing an OCR engine on the OCR preprocessor output to obtain OCR engine output, and executing an approximator on the OCR preprocessor output to obtain approximator output. The method further includes iteratively adjusting the approximator to simulate the OCR engine using the OCR engine output and the approximator output, and generating OCR preprocessor losses using the approximator output and target labels. The method further includes iteratively adjusting the OCR preprocessor using the OCR preprocessor losses to obtain a customized OCR preprocessor.

Abstract: A federation link is used to facilitate bi-directional identity federation between software applications. The federation link is created to include user and account identity information for software applications having respective authentication providers. The federation link is created by one of the software applications and shared, for example, with the authentication provider of the other software application. The federation link can be utilized by both software applications to facilitate automated user authentication when navigating in either direction between the software applications.

Abstract: A computing system identifies an incoming voice call from a user device to an agent device associated with the computing system. The computing system generates a transcription of the incoming voice call using one or more natural language processing techniques. The computing system extracts a problem description from the transcription. The problem description indicates a topic for the incoming voice call. A first machine learning model estimates a situation vector from the problem description. A second machine learning model identifies a pre-existing situation vector that closely matches the estimated situation vector. The computing system retrieves a situation description that corresponds to the identified pre-existing situation vector.

Abstract: Systems and methods for scoring potential actions are disclosed. An example method may be performed by one or more processors of a system and include training a machine learning model based at least in part on a sequential database and retention data, identifying an action subsequence executed by a user, generating, for each of a plurality of potential actions, using the machine learning model, a first value indicating a probability that the user will execute the potential action immediately after executing the action subsequence, a second value indicating a probability that the user will continue to use the system if the user executes the potential action immediately after executing the action subsequence, and a confidence score indicating a likelihood that recommending the potential action to the user will result in the user continuing to use the system, the confidence score generated based on the first value and the second value.

Abstract: Aspects of the present disclosure provide techniques for FAQ retrieval. Embodiments include receiving, via a user interface of a computing application, a query related to a subject. Embodiments include generating a first multi-dimensional representation of the query. Embodiments include obtaining a plurality of question and answer pairs related to the subject and, for a given question and answer pair comprising a given question and a given answer, generating a second multi-dimensional representation of the given question and a third multi-dimensional representation of the given answer. Embodiments include providing input to a model based on the first multi-dimensional representation, the second multi-dimensional representation, and the third multi-dimensional representation and determining a match score for the query and the given question and answer pair based on an output of the model.

Abstract: Systems and methods of optimizing cash flow are disclosed. A system obtains bill information regarding a plurality of bills and invoice information regarding a plurality of invoices, and the system pairs one or more bills to one or more invoices. Pairing the one or more bills includes, for each bill, generating one or more potential pairs of the bill to an invoice. For each potential pair, the system calculates a matching score associated with the potential pair based on the bill information of the bill and the invoice information of the invoice, identifies a subset of potential pairs of the one or more potential pairs associated with a threshold matching score, and selects a pair of a paired invoice to the bill from the subset of potential pairs. The system generates instructions to automatically pay the one or more bills, with payment scheduled based on the pairings.

Abstract: A processor may receive an image and determine a number of foreground pixels in the image. The processor may obtain a result of optical character recognition (OCR) processing performed on the image. The processor may identify at least one bounding box surrounding at least one portion of text in the result and overlay the at least one bounding box on the image to form a masked image. The processor may determine a number of foreground pixels in the masked image and a decrease in the number of foreground pixels in the masked image relative to the number of foreground pixels in the image. Based on the decrease, the processor may modify an aspect of the OCR processing for subsequent image processing.

Abstract: A method including receiving, at an embedded browser embedded in an application, a request to access data designated by a uniform resource locator (URL) specified by the request. The method also includes intercepting, by a method interceptor, an application programming interface (API) call to access the data designated by the URL. Intercepting is performed prior to execution of the API call. The API call is performable by an API of the embedded browser. The method also includes comparing, by the method interceptor, a domain specified by the URL to an list of allowed domains. The method also includes blocking, by the method interceptor and responsive to the domain failing to be a member of the list of allowed domains, the API call. Blocking is performed by the method interceptor preventing the API call from passing to the API.

Abstract: A unified graph query system provides an abstraction layer that increases the interoperability of different graph technologies by exposing graphs stored in graph databases using a unified query language. The abstraction layer generates graph models for each of the available graph databases and extracts a graph component and other source data used to identify the source of the data requested by a query. The unified graph query system executes the query across the multiple graphs included in different graph databases by using the graph models to locate the graph component in each of the multiple graphs and extract the feature data associated with the graph component. The feature data is used to generate features that are used by a machine learning service to train machine learning models and is also used to make predictions in real time.