Abstract: Local data can be made available in a cloud computing environment. A persistent remote connection may be established between a processor and a server. The server may receive a request for data from an external device through a network. The request for data may be sent through the persistent remote connection from the server to a first executable process of the processor. The processor may obtain the data from an application being executed by the processor separately from the first executable process. The data may be sent through the persistent remote connection from the processor to the server. The server may send the data to the external device through the network in response to the request. The persistent remote connection may be maintained in an open state regardless of a status of the request for data.

Abstract: The disclosure provides an approach for processing frames of a virtualized desktop to improve accessibility for users, such as users with disabilities. The approach involves processing frames by an accessibility engine that is located on a client device of the user. The virtualized desktop runs on a virtual machine that is remote to the client device. The location of the accessibility engine on the client device allows advantages such as the ability to process frames that indicate a non-operational virtual machine.

Abstract: A method includes generating recommendations and user structures by applying a recommender machine learning model to training user information and item information, and generating, from the user structures and by applying a demographic machine learning model, demographic predictions of users represented by the user structures. The method further includes generating a first accuracy measure of the demographic machine learning model based on a first comparison of the demographic predictions with demographics of the users. A recommender loss function is generated based on the first accuracy measure and a second comparison of the recommendations with selections of users, where the recommender loss function uses the first accuracy measure to suppress detectability by the demographic machine learning model. The method further includes updating the recommender machine learning model according to the recommender loss function.

Abstract: Certain aspects of the present disclosure provide techniques for providing an augmented reality user interface, including: receiving, by an image sensor of an electronic device, an image of a physical document; determining a document type associated with the physical document by performing image recognition on the image of the physical document; determining an augmented reality template to display on a display of the electronic device; displaying the augmented reality template on the display of the electronic device, wherein the augmented reality template is aligned in three dimensions with the physical document; determining a distance between the physical document and the electronic device; and enabling one or more interactive user interface elements within the augmented reality template displayed on the display of the electronic device if the determined distance between the physical document and the electronic device is less than a threshold distance.

Abstract: A processor may receive a plurality of text samples generated by a user and identify at least one variable text element in at least one of the plurality of text samples. The processor may tokenize the at least one variable text element, thereby producing a plurality of tokenized text samples including at least one token. The processor may build a longest common substring from the plurality of tokenized text samples and add the longest common substring and the at least one token to a set of selectable user interface options specific to the user. The processor may generate a user interface comprising the set of selectable user interface options. This can include detecting a user interface context and automatically replacing the at least one token with information specific to the user interface context within the set of selectable user interface options.

Abstract: At least one processor may capture a plurality of image snapshots containing information about a monitored system at a plurality of sequential times, each snapshot having the same vertical and horizontal dimensions. The processor may label the plurality of image snapshots as indicative of an event that took place in the monitored system, may receive additional data describing the event, may cluster the labeled plurality of image snapshots and the additional data using at least one machine learning clustering algorithm, and may merge the clustered plurality of image snapshots and the clustered additional data into merged data. The processors may create a model by processing the merged data using at least one neural network, the model being configured to detect future events of a same type as the event in the monitored system. The processor may store the model in a memory in communication with the processor.

Abstract: Systems and methods for forecasting cashflows across one or more accounts of a user disclosed. One example method may include retrieving a data set for each of a plurality of accounts from a database, constructing a graph including a plurality of nodes linked together by a multitude of edges, wherein each node identifies a time series value corresponding to one of the accounts, and each edge indicates a time series value of a corresponding set of transactions occurring between a corresponding pair of accounts, determining a plurality of constraints, determining a specified loss function based on the plurality of constraints, back-propagating a derivative of the specified loss function into a deep neural network (DNN) to determine a set of neural network parameters, forecasting, using the DNN, a time sequence for one or more of the nodes and one or more of the edges, and providing the forecasted time sequences to the user.

Abstract: A processor may receive a request payload from an external device and data describing a plurality of user interface (UI) elements configured to be presented in a UI of the external device. The request payload may include a user identifier. The processor may generate a user feature vector from the user identifier. Using a contextual bandit machine learning (ML) model that takes the user feature vector and the data describing the plurality of UI elements as input, the processor may select at least one of the plurality of UI elements as at least one recommended UI element. The at least one recommended UI element may be presented in the UI of the external device. The processor may receive event data indicating a user interaction with the at least one recommended UI element in the UI of the external device. The ML model may be trained using the event data.

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 computer-implemented system and method for predicting and flagging an anomaly entered in a digital form. A server computing device classifies a plurality of data fields of the digital form to identify a set of non-zero value data fields; and obtains an anomaly detection model comprising a statistical tree structure associated with the data field of the digital form. The server computing device receives datasets including a target value of a data field and values of a set of cohorting data features; traverses a statistical tree structure of the anomaly detection model with the target dataset to form a set of target cohorts to determine a target statistic value for the data field; flags the data field value of the target dataset as an anomaly item; and generates one or more confidence scores for a runtime prediction based on one or more variance changes for the data field.

Abstract: A computing system generates a plurality of training data sets for generating the NLP model. The computing system trains a teacher network to extract and classify tokens from a document. The training includes a pre-training stage where the teacher network is trained to classify generic data in the plurality of training data sets and a fine-tuning stage where the teacher network is trained to classify targeted data in the plurality of training data sets. The computing system trains a student network to extract and classify tokens from a document by distilling knowledge learned by the teacher network during the fine-tuning stage from the teacher network to the student network. The computing system outputs the NLP model based on the training. The computing system causes the NLP model to be deployed in a remote computing environment.

Abstract: This disclosure provides systems, methods and apparatuses for machine learning. In some implementations, a pre-processing system may identify one or more special features in an input dataset and may generate one or more pruned datasets, respectively, based on the identified special features. The pre-processing system maps each of the pruned datasets to one or more predictions and selectively removes the values associated with one or more special features from the input dataset based on the mapping. In some other implementations, a pre-processing system may map each of the feature sets in an input dataset to multiple predictions in accordance with multiple machine learning algorithms. The pre-processing system evaluates a performance of each of the mappings and selects one of the machine learning algorithms to be used to train the machine learning model based on the performance of each mapping.

Abstract: A method including receiving an electronic record including a scan of a physical document. A coordinate system, unique to the electronic record, is established for the scan. A first boundary, defined according to the coordinate system, is generated automatically around a first set of recognized characters in the scan. A second boundary, defined according to the coordinate system, is generated automatically around a second set of recognized characters in the scan. The first set of recognized characters are physically separated in the scan by at least a predetermined distance with respect to the coordinate system. A comparison value is generated automatically by comparing a first location of the first boundary to a second location of the second boundary, relative to the coordinate system. The first set of recognized characters is associated, in storage, with the second set of recognized characters, responsive to the comparison value satisfying a rule.

Abstract: A method may include extracting, from a document, a first key-value pair including a key and a first value and corresponding to a first confidence score, extracting a second key-value pair including the key and a second value corresponding to a second confidence score, classifying a first match probability for the first key-value pair and a second match probability for the second key-value pair, generating a first calibrated confidence score for the first confidence score and a second calibrated confidence score for the second confidence score by transforming, using precision lookup tables constructed from training records, the first match probability to the first calibrated confidence score and the second match probability to second calibrated confidence score, selecting, using the first and second calibrated confidence scores, one of the first key-value pair and the second key-value pair, and presenting, in a graphical user interface (GUI), the selected key-value pair.

Abstract: Techniques are disclosed for managing encrypted data stored in one or more blocks of a first data structure. One embodiment presented herein includes a computer-implemented method, which includes retrieving the encrypted data from the one or more blocks. The method further includes placing the encrypted data in a container object. The method further includes applying an encryption technique to the container object to generate an encrypted container object and a key. The method further includes generating a second data structure. A first block of the second data structure may include either the encrypted container object or information related to the encrypted container object.

Abstract: Certain aspects of the present disclosure provide techniques for establishing a web session between a computing device and a web-based integrated development environment to create and/or update files (e.g., content files and/or resource files). In the web session, content file(s) can be evaluated in real-time with one or more resource files. Further, in the web session, a set of validation rules of a resource file can be updated by the computing device. To stablish the web session, a first communication connection is established between the computing device and the web-based integrated development environment. With the first communication established, a second communication connection is established for real-time, bi-directional communication between the computing device and a language server instance of the web-based integrated development environment.

Abstract: Certain aspects of the present disclosure provide techniques for operation of a feature management platform. A feature management platform is an end-to-end platform developed to manage the full lifecycle of data features. For example, to create a stateful feature, the feature management platform can receive a processing artifact from a computing device. The processing artifact defines the stateful feature, including the data source to retrieve event data from, when to retrieve the event data, the type of transform to apply, etc. Based on the processing artifact, the feature management system generates a processing job (e.g., the API defines a pipeline), which when initiated generates a vector that encapsulates the stateful feature. The vector is transmitted to the computing device that locally hosts a model, which generates a prediction that is transmitted to the feature management platform. Subsequently, the predication and stateful feature can be transmitted to other computing devices.

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 flexible, multi-constraint risk segmentation.

Abstract: Aspects of the present disclosure provide techniques for dynamic location tracking. Embodiments include receiving a plurality of location records associated with a site, wherein each respective location record of the plurality of location records comprises respective location coordinates of a respective device associated with the respective location record. Embodiments include determining respective distances from a center point of the site to the respective location coordinates in each respective location record of the plurality of location records. Embodiments include determining a radius of a region definition for the site based on the respective distances. Embodiments include receiving a device location from a device associated with a user. Embodiments include performing, based on the device location and the region definition, one or more location-based operations.