Abstract: A processor may receive clear text data. The processor may represent at least a portion of the clear text data as at least one array encoding a description of at least one feature of the clear text data. The processor may process the at least one array using a clustering algorithm to determine whether the at least one array is grouped with a benign cluster or a sensitive cluster of a model. In response to determining that the at least one array is grouped with the sensitive cluster, the processor may generate an alert indicating that the clear text data includes sensitive information.

Abstract: Systems and methods for synchronizing cloud resources are disclosed. An example method may include receiving a first request to synchronize first target cloud resources to a first specified state defined in a configuration repository, generating one or more first configuration commands corresponding to the first request, the one or more first configuration commands associated with a first cloud provider and a first cloud configuration framework, and executing the one or more first configuration commands to set a state of the first target cloud resources to the first specified state.

Abstract: The present disclosure provides techniques for recommending vendors using machine learning models. One example method includes generating a dependency graph based on one or more microservices, computing, for each microservice of the one or more microservices, a complexity score using the dependency graph, identifying a subset of the one or more microservices, wherein each microservice in the subset of the one or more microservices has a complexity score meeting a threshold value, and applying a transactional lock on each microservice in the subset of the one or more microservices.

Abstract: Matching validation includes obtaining a candidate match between a target entity and a candidate application user and filtering multiple transaction records of multiple application users to obtain a subset of the transaction records each involving a transaction with the target entity. The application users exclude the candidate application user. Matching validation further includes determining, for each transaction record in the subset, whether a matching transaction record exists in multiple candidate users transaction records of the candidate application user, and validating the candidate match when at least a threshold amount of transaction records in the subset has the matching transaction record in the candidate users transaction records.

Abstract: A method for detecting data drift between a first database and a second database involves obtaining (from the first database) and based on a change data capture (CDC) event generated in response to a change detected in the first database, a first record identified by the CDC event, obtaining (from the second database) a second record corresponding to the first record, transforming a data structure of the first record from the first database to the data structure of the second database generating a transformed record, and based on determining that a difference between the first record and a second record exists, reporting a presence of data drift.

Abstract: Systems and methods for matching entities to target objects using an ensemble model are disclosed. The ensemble model includes a general trained machine learning (ML) model (which is trained using the entirety of a training dataset) and a subarea trained ML model (which is trained using a subset of the training dataset corresponding to a specific, defined subarea) that provides potential matches to a meta-model of the ensemble model to generate a final match. The ensemble model may also include a general trained natural language processing (NLP) model and a subarea trained NLP model that provides potential matches to the meta-model. The meta-model of a quad-ensemble ML model combines the four potential matches (such as probabilities and similarities of matching specific pairs of targets objects and entities) to generate a final match (such as a final probability used to identify the final match).

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: A computing system receives, from a client device, an image of a content item uploaded by a user of the client devices. The computing system divides the image into one or more overlapping patches. The computing system identifies, via a first machine learning model, one or more distortions present in the image based on the image and the one or more overlapping patches. The computing system determines that the image meets a threshold level of quality. Responsive to the determining, the computing system corrects, via a second machine learning model, the one or more distortions present in the image based on the image and the one or more overlapping patches. Each patch of the one or more overlapping patches are corrected. The computing system reconstructs the image of the content item based on the one or more corrected overlapping patches.

Abstract: A system and method for extracting data from a piece of content using spatial information about the piece of content. The system and method may use a conditional random fields process or a bidirectional long short term memory and conditional random fields process to extract structured data using the spatial information.

Abstract: A method including preprocessing natural language text by cleaning and vectorizing the natural language text. A first machine learning model (MLM) extracts negative reviews. A first input to the first MLM is the natural language text and a first output of the first MLM is first probabilities that the negative reviews have negative sentiments. The method also includes categorizing the negative reviews by executing a second MLM. A second input to the second MLM is the negative reviews. A second output of the second MLM is second probabilities that the negative reviews are assigned to categories. The method also includes identifying, using a name recognition controller and based on categorizing, a name of a software application in the negative reviews and sorting the negative reviews into a subset of negative reviews relating to the name. The software application is adjusted based on the subset of negative reviews.

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.