Abstract: A transaction tracking service (TTS). The TTS includes a transaction repository configured to store transaction records organized within a transaction groups. The TTS also includes a computer processor operatively connected to the transaction repository. The computer processor is configured to execute instructions to make a first determination that a first transaction record of the plurality of transaction records is unassigned, generate, based on the first determination, an unassigned transaction list (UTL) comprising a first set of transaction data associated with the first transaction record, and transmit the UTL to a client device operatively connected to the TTS.

Abstract: Embodiments presented herein provide systems and methods for creating and modifying a hash chain. A hash chain is created to track resource-privilege transfers between entities. A root node of the hash chain identifies the resource and specifies a digest of a possession token held by a first entity that initially possesses the privilege. A transfer of the privilege to a second entity can be recorded by adding an expansion node to the hash chain. If the second entity successfully reveals a possession token that a hashing function associated with the hash chain maps to the digest, an expansion node is linked to the root node. The expansion node indicates the possession token and a successor digest that is based on a successor possession token.

Abstract: Systems and methods for providing contextual information for computerized document understanding. The systems and methods can be used to assist users in filling out documents by providing contextual information based on anomalies identified in a provided document. The methods and systems may identify the deficiency in the document and automatically generate a query related to the anomaly. The query can be fed as an input to a question-answering (QA) model that can provide an answer as the contextual information.

Abstract: A method includes receiving first metrics describing first behaviors of applications having a fault, and second metrics describing second behaviors of an enterprise system in which the applications are executing. The first and second metrics are ingested. Ingesting includes assigning a first cardinality score to first metrics related to the fault. Ingesting also includes assigning a second, lower cardinality score to second metrics that are unrelated to the fault. Tumbling window processing is performed on the ingested metrics by sorting the first metrics and the second metrics into time slices. Each of the time slices includes a corresponding data structure for storing the data in the different time periods. Tumbling window processing is also performed on the ingested metrics by storing more data in the time slices for the first metrics having the first cardinality score relative to the second metrics having the second cardinality score.

Abstract: Generating a difference between a first and second plurality of lines of text in structured machine-readable format may include determining, by at least one processor, a line of the second plurality of lines that constitutes a best match for a line of the first plurality of lines. The line of the first plurality of lines and its respective best match may be associated with a similarity score. The at least one processor may compare the similarity score to a threshold value. In response to determining that the similarity score is greater than or equal to the threshold value, the at least one processor may compute, the textual difference between the line of the first plurality of lines and its best match. In response to computing the textual difference, the at least one processor may analyze the textual difference to identify a non-meaningful change.

Abstract: A system for matching a consumer of a service with a provider of the service includes a service consumer program host computer communicatively coupled to a consumer/provider matching computer through a first network. The system also includes a service provider host computer communicatively coupled to the consumer/provider matching computer through a second network. The system further includes a consumer computer communicatively coupled to the consumer/provider matching computer through a third network. Moreover, the system includes a provider computer communicatively coupled to the consumer/provider matching computer through a fourth network. The consumer/provider matching computer generates a ranked list of providers by analyzing consumer data.

Abstract: A method for hash chain migration includes detecting a version update of an object that includes a hash chain that stores fields of the object. Sub chains are identified from the hash chain. Migration sub chains are generated from the plurality of sub chains using a plurality of processes. Container blocks are generated from the plurality of migration sub chains. A migration chain is generated from the plurality of container blocks. The object is accessed using the migration chain.

Abstract: Systems and methods that may be used to generate and use a social graph generated by user financial transaction data (i.e., a financial transaction-based social graph). Connections and other data within the financial transaction-based social graph can be used for targeted product offerings, other offerings, and or advertisements via e.g., collaborative filtering and user segmentation and profiling.

Abstract: An intermediate computer hosts a tax return preparation application and generates an interview screen presented to a preparer through a display of the preparer computing device executing a browser. In response, the preparer acquires images of tax documents to begin preparation of an electronic tax return, e.g., by sequentially taking photographs of tax documents using a camera of a mobile communication device, which transmits the images or results of image processing such as Optical Character Recognition (OCR) to the intermediate computer. The intermediate computer, as necessary, performs OCR processing and automatically populates a plurality of electronic tax forms with the first electronic tax data and the second electronic tax data. The electronic tax return may be completed by tax document imaging and manual corrections to OCR results as necessary, in contrast to traditional tax return preparation applications structured according to a pre-determined and programmed sequence of interview screens.

Abstract: External events are correlated with patterns of characteristics in virtual assets. Upon detection of a pattern in a different asset that matches a pattern corresponding to an event, that detection is treated as a trigger event, with resulting responsive action(s) and other process operations. Security threats are managed in a similar manner, with first security threats being added to a collection of security threats. When a virtual asset detects a change in operating characteristics, a request is provided for the collection of current security threats, and the collection of security threats is provided responsive to the request.

Abstract: A processor may receive a social media post related to a monitored system. The processor may automatically process at least one element of the social media post by applying at least one natural language processing algorithm. The processor may determine a meaning of the social media post based on an output of the at least one natural language processing algorithm. The processor may automatically route the social media post to at least one recipient based on the meaning.

Abstract: A computer-implemented system and method for generating heterogeneous graph feature embeddings for feature learning and prediction. An application server may receive and process a plurality of feature datasets to generate a graph data structure comprising a plurality of interconnected transaction pairs. The application server processes the graph data structure to determine a first-order transaction pair corresponding to a maximum transaction frequency based on a user identifier; executes a jumping probability algorithm to process the graph data structure to determine a second-order transaction pair jumping from a first-order transaction pair; and generates a transaction sequence associated with the user identifier.

Abstract: A method is disclosed. The method includes obtaining an access request associated with a user for a software application; obtaining a plurality of verification attributes associated with the user; generating a fraud score for the access request by feeding a supervised machine learning (ML) classifier with a feature vector for the user that is based on the plurality of verification attributes; selecting a first unsupervised ML anomaly detector of a plurality of unsupervised ML anomaly detectors based on the fraud score; generating an anomaly score for the access request by feeding the first unsupervised ML anomaly detector with an augmented feature vector for the user that is based on the plurality of verification attributes and the fraud score; and processing the access request based on the anomaly score.

Abstract: A method and system learn functions to be associated with data fields of forms to be incorporated into an electronic document preparation system. The functions are essentially sets of operations required to calculate the data field. The method and system receive form data related to a data field that expects data values resulting from performing specific operations. The method and system utilize machine learning and training set data to generate, test, and evaluate candidate functions to determine acceptable functions.

Abstract: A method including receiving, at a mobile device, a request to provision a first geofence. The first geofence has a first predicted duration that expires before a second predicted geofence is provisioned by the mobile device. Provisioning the first geofence and the second predicted geofence together consume a first amount of power. The method also includes determining a predictive geofence radius based on a predicted speed of the mobile device. The method also includes provisioning a first predictive geofence having the predictive geofence radius and further having a second predicted duration that is different than the first predicted duration and that expires before a second predictive geofence is provisioned by the mobile device. Provisioning the first predictive geofence and the second predictive geofence together consume a second amount of power, the second amount of power less than the first amount of power.

Abstract: Certain aspects of the present disclosure provide techniques for predicting a transaction time based on user position data. In certain aspects, a method for predicting a transaction time based on user position data includes obtaining a transaction record and one or more user positions associated with a user. The method also includes obtaining one or more business records associated with each respective user position. The method further includes calculating one or more similarity scores, where each similarity score is based on a similarity between a respective business record and the transaction record. The method also includes associating the transaction record with a business record based on a maximum similarity score of the one or more similarity scores. The method further includes determining a predicted transaction time for the transaction record based on at least a timestamp of a user position associated with the business record associated with the transaction record.

Abstract: Systems and methods that approximate and use branching operations on data encrypted by fully homomorphic encryption (FHE). The systems and methods may use polynomial approximation to convert “if” statements into “soft if” statements that may be applied to the FHE encrypted data in a manner that preserves the security of the systems and methods.

Abstract: A method for automatically updating a plurality of brokers in a cluster of a distributed streaming platform within a container orchestration tool, the method including querying each of a plurality of brokers to obtain metadata from a distributed streaming platform; using the obtained metadata to identify a broker within the plurality of brokers that acts as a controlling broker; computing an order in which the plurality of brokers will be updated based on the obtained metadata, wherein the order specifies that the controlling broker will be updated last; and performing, via an update manager executed by at least one processor, a rolling update of each of the plurality of brokers according to the computed order.

Abstract: A method for mitigating cold starts in recommendations includes receiving a request that identifies a requested page and identifying a content vector of the requested page. The content vector is generated based on providing text of the requested page to a neural network text encoder. The method further includes selecting, based on the content vector, a link to a cold start page that does not satisfy a threshold level of interaction data. The selected link is ranked above a second link to a warm page that does satisfy the threshold level of the interaction data. The method further includes presenting the requested page with the selected link.