Abstract: Systems, methods, and apparatus are provided for deep learning architecture for adverse media screening. A dynamic data stream may be generated from news reports acquired from a variety of media channels in a variety of formats. Reports may be separated by format. A graphing module for each type of media may use geometric clustering algorithms to group reports into a coherence graph. Fact-checking sources may be incorporated into the graph. A graph neural network may determine coherence between news claims and fact-checking sources, between news claims and supporting report details, between similar reports, and/or between video and audio within the report itself. The network may output a legitimacy score for a report. A credible report may be flagged and retrieved in the course of a customer screening. Materiality may be determined for a credible report and may trigger a customer account closure protocol.

Abstract: Transactions between entities may be validated using LoRaWAN communications to more quickly process those transactions. In the example of check depositing, a first entity associated with a check payee may transmit a check clearance request to a second entity associated with a check payor using LoRaWAN communications. The LoRaWAN signaling and communications may be performed between devices within LoRaWAN range. For example, a check depositing device may receive a check deposit where the payor is associated with a different financial institution or entity. Accordingly, the check depositing device may communicate with another device associated with the payor institution or entity using LoRaWAN signals to confirm check clearance.

Abstract: Transactions may be performed using a mobile device such as a user-wearable device using LoRaWAN protocol to minimize power consumption while maximizing communication range. Transaction information may be stored in the user-wearable device and transmitted to a transaction processing device using LoRaWAN communications. Transaction information may include user-specific information, payment information, merchant information, product information, user preference information and the like. In some instances, the only communication interface (or wireless communication interface) provided in the mobile device is a LoRaWAN communication interface.

Abstract: Communication, authentication, and/or validation may be required in various types of device interactions. For example, for some types of device functions, user or device authentication may be required to confirm that the function can and should be performed. Authentication information may be communicated and authentication and/or validation may be performed using LoRaWAN signaling. LoRaWAN signaling provides low power and long-range communication capabilities to efficiently and effectively perform authentication processes. In some arrangements, LoRaWAN signals may be generated by both a first device (e.g., a user device) and a second device (e.g., a function-performing device) and subsequently compared to determine whether they correspond. This correspondence may provide the requisite authentication or validation of the first device and/or an associated user.

Abstract: Device information may be obtained using LoRaWAN communications. A device information request may be generated and transmitted by a user device and include request parameters such as a device type for which information is desired, a type of information requested, a geographic range for the request, and the like and/or combinations thereof. Device information requests may also be propagated or repeated by intermediary devices to achieve the desired request range. Accordingly, a recipient device of the original request may propagate or repeat, using LoRaWAN, a request signal if it determines that the request range has not been met. If the request range has been met, the recipient device might not repeat the request.

Abstract: A system communicates a request to a plurality of network nodes to provide user information associated with a document. The system receives a plurality of log files that comprises data communications among the network nodes and responses to the request. The system determines a first number of network nodes that are associated with a first anomaly from the plurality of log files. The system determines a second number of network nodes that are associated with a second anomaly from the plurality of log files. The system determines the number of malicious network nodes by combining the first number and the second number of network nodes. If the system determines that the number of malicious network nodes exceeds a threshold percentage, it assigns one or more network nodes to store the user information until the number of malicious network nodes is less than the threshold percentage.

Abstract: A system accesses a scan of a document that shows first user information. The system extracts the first user information from the scan of the document. The system identifies an entity associated with the document, where an identifier associated with the entity is shown on the scan of the document. The system communicates a request to provide second user information to a computing device associated with the entity. The system receives a response comprising the second user information and compares each component in the first user information with a counterpart component in the second user information. The determines whether the document is valid based on the comparison between the first user information and the second user information.

Abstract: Aspects of the disclosure relate to processing asset transfers. A computing platform may receive an asset transfer request and extract information from it. The computing platform may modify a distributed ledger to include a new block corresponding to the asset transfer request. The computing platform may identify a consensus method by identifying, for each of a plurality of consensus methods, a subset of blocks from the distributed ledger that, when used to execute the corresponding consensus method, result in a lowest energy consumption value in comparison to remaining subsets of blocks. The computing platform may execute each consensus method using the corresponding identified subset of blocks, which may result in establishing consensus to process the asset transfer request. Based on establishing the consensus, the computing platform may direct an event processing platform to process the asset transfer request, which may cause the event processing platform to process the request accordingly.

Abstract: A system receives a speech of a user that indicates a request. The system extracts a plurality of voice features from the speech. The system converts the speech into a plurality of binary digits. The system determines a first voice feature constant value associated with a first voice feature, where the first voice feature constant value is an average of the first voice feature. The system determines a second voice feature constant value associated with the second voice feature, where the second voice feature constant value is an average of the second voice feature. The system encrypts the plurality of binary digits using the first and second voice feature constant values, where the encrypted plurality of binary digits corresponds to a voice-based hash value. The system generates a new block in a blockchain network using the voice-based hash value.

Abstract: A system for resolving exceptions in requests determines that a request comprises an exception. The exception impeded processing the request to be granted or denied. The system determines a type of exception that indicates whether the exception is incomplete information, incorrect information, or previously-unknown information. The system generates a block in a blockchain network. Based on the stored details in the block, the type of exception is identified. Accordingly, the block is segregated for exception processing based on its exception type. The system stores the exception in the block. The system compares the request with user information previously provided by the user. The system determines a similarity score between the request and the user information. The system compares the similarity score with a threshold percentage. In response to determining that the similarity score exceeds the threshold percentage, the system determines that the exception can be resolved and resolves the exception.

Abstract: Aspects of the disclosure relate to cognitive identification of credit reporting disputes and dispute resolution using quantum computing. A computing platform may retrieve historical data and current credit report data and identify, using a DNA computing engine, potential reporting inaccuracies. The computing platform may send a recommendation to a computing device of a user to initiate a dispute. Based on receiving input from the user accepting the recommendation, the computing platform may initiate the dispute as a block in a distributed ledger. The computing platform may determine a probability that actual reporting inaccuracies exist. The computing platform may identify parameters for adjustment. In addition, each parameter may indicate a type of change to be made. The computing platform may update an account of the user based on the determined probability and the identified parameters. The computing platform may send a notification to the user indicating a resolution of the dispute.

Abstract: Aspects of the disclosure relate to cognitive identification of credit reporting disputes and dispute resolution using quantum computing. A computing platform may retrieve, using a quantum computing device, dispute data from a block chain of dispute requests. The computing platform may convert the dispute data into quantum bits. The computing platform may perform quantum searching of the retrieved dispute data over a plurality of different databases and identify potential dispute transactions. The computing platform may determine probability scores for the potential dispute transactions, each probability score being based on a likelihood that a change associated with the potential dispute transactions is to be made. The computing platform may determine respective parameters associated with the potential dispute transactions, wherein each parameter indicates a type of change to be made.

Abstract: Systems, computer program products, and methods are described herein for an electronic resource transfer platform utilizing a multi-path recommendation engine in blockchain. The present invention may be configured to receive a request from a user to transfer resources, generate a first block comprising the user request, and record the first block on a distributed ledger. The present invention may also be configured to receive resource transfer quotes from an entity or entities. The present invention may also be configured to utilize a recursive auto-recommendation engine to provide recommended resource transfer quotes to the user. Further, the present invention may be configured to generate a smart contract, establish a consensus, and settle the resource transfer after receiving a selection of a resource transfer quote from the user. The present invention may be further configured to generate a second block comprising resource transfer data and store the second block on the distributed ledger.

Abstract: A system includes a production computing environment including a plurality of components, a centralized data repository that receives and stores data feeds relating to one or more components as a data log and at least one processor configured to obtain the data log of each component, generate a current state vector for the component based on the data log, compare the current state vector to a normal state vector of the component, determine that the current state vector deviates from the normal state vector, and in response, predict an anomaly associated with the component using an iterative machine learning method. The at least one processor may be configured to correct the predicted anomaly by taking at least one pre-configured action corresponding to the predicted anomaly.

Abstract: A system includes a production computing environment including a plurality of components, a centralized data repository that receives and stores data feeds relating to one or more components as a data log, a plurality of cloud infrastructures and at least one processor configured to receive the data feed relating to the components, predict an anomaly associated with a component based on the data feed relating to the component, identify a system configuration needed to run a current workload associated with the component, search each cloud infrastructure for a cloud instance that can support the identified system configuration, identify a cloud instance based on the search, initiate the identified cloud instance and switch the workload from an original system to the initiated cloud instance.

Abstract: A system splits the text into at least a first and a second portions. The system extracts a first context information from the first portion, and a second context information from a second portion in response to feeding the plurality of portions to a first plurality of neuron logic gates. The system compares the first context information with the second context information. If it is determined that the first context information is different from the second context information, the system dynamically activates at least one of a second plurality of neuron logic gates. The system determines an additional information from at least one of the first portion and second portions. The system updates at least one of the first context information and the second context information to include the additional information. The system generates a first output that comprises the updated first context information and the updated second context information.

Abstract: A system for validating a response based on context information receives a first message that indicates that a data object is removed from a memory resource via a third party device without authorization by a user. The system communicates a second response that indicates whether a third party confirms the removal of the data object without the authorization by the user to the third party device. The system receives a response from the third party device. The system extracts context information from the response. The system determines whether the response is valid based on the context information, where it is determined to be valid if the response is actionable. In response to determining that the response is actionable, the system recommends one or more actions to be performed with respect to the memory resource.

Abstract: Aspects of the disclosure relate to processing asset transfers. A computing platform may receive an asset transfer request and extract information from it. The computing platform may modify a distributed ledger to include a new block corresponding to the asset transfer request. The computing platform may identify a consensus method by identifying, for each of a plurality of consensus methods, a subset of blocks from the distributed ledger that, when used to execute the corresponding consensus method, result in a lowest energy consumption value in comparison to remaining subsets of blocks. The computing platform may execute each consensus method using the corresponding identified subset of blocks, which may result in establishing consensus to process the asset transfer request. Based on establishing the consensus, the computing platform may direct an event processing platform to process the asset transfer request, which may cause the event processing platform to process the request accordingly.

Abstract: Aspects of the disclosure relate to a cloud-based parallel processing and cognitive learning computing platform. A computing platform may receive query data comprising a plurality of requested metrics. The computing platform may select a secondary node to process the query request from a plurality of secondary nodes of the computing platform. The computing platform may send the query request to the secondary node. The computing platform may send a request to generate a metric mapping table for a first requested metric to a cognitive learning module of the computing platform. The cognitive learning module may generate the metric mapping table for the first requested metric using neuron clusters that comprise a plurality of unique programmable quadratic function neurons. The computing platform may calculate a value for the first requested metric based on the metric mapping table.

Abstract: Arrangements for using a cognitive convergence engine for resource optimization are provided. Requests for service, such as a loan, an account, or the like, may be received via different communication channels. The requests for service may be aggregated based on type of request and transferred to a cloud environment for evaluation. A request may be evaluated to determine whether it is eligible for bot processing. If so, the request may be transferred to a bot server for processing. If not, the request may be evaluated to identify a best fit resource for processing. Identifying the best fit resource may include scores computed by a plurality of computational instances or virtual machines configured to process the computations. A number of computational instances may be determined based on a volume of requests. The computational instances may then be deployed to determine a best fit resource for the first request.