Abstract: Various aspects of the disclosure relate to fraud detection for real-time electronic transactions occurring in a plurality of payments systems. At onboarding of a regional or local payments computing system into a distributed privacy preservice payments fraud detection system, a client computing system trains a centralized model of a specific fraud detection architecture on its local dataset. Changes (e.g., gradient matrices) to the model are identified and communicated and communicates its gradients (matrices) to a centralized server. Upon receipt of gradients from one or more client computing systems, the centralized server aggregates the client gradients (periodically, continually, and the like) and sends the updated model to each client computing systems for use in the next federated round.

Abstract: Real-time transmission of IoT telemetry data to a third-party and use of such data by the third-party for purposes of determining IoT device-related recommendations specific to the IoT device user. Machine learning models receive the IoT telemetry data, as a least a part of the inputs, to determine recommendations that are tied to the IoT device and specific to the IoT device user. Non Fungible Tokens (NFTs) are minted by the IoT device manufacturer/distributor and hold a link to an IoT device identifier and an IoT device user identifier and include a smart contract formed between the third-party and the IoT device user that defines the criteria for the telemetry data that is to be acquired by the third-party. Use of the NFT allows for IoT gateways/data listeners to determine which IoT telemetry data is to be transmitted to the third-party and allows for the transmission to occur without identifying the IoT user in the transmissions.

Abstract: A multi-level, ensemble network monitoring system for detection of suspicious network activity from one or more a plurality of user computing devices on an external network communicatively connected via a network server to a private communication network is disclosed. In malware detection, the ensemble network monitoring system comprises artificial intelligence (AI) with bidirectional long short-term memory (BDLSTM) recurrent neural networks (RNNs) and natural language processing (NLP) to predict possible security threats and then initiate remedial measures accordingly. Enabling a proactive approach to detection and prevention of potential malicious activity, the BDLSTM RNN may perform real-time monitoring and proactively forecast network security violations to block network communications associated with high-risk user computing devices from accessing a private communication network.

Abstract: A system for implementing intelligent interactions in a metaverse comprises a metaverse server in communication with an entity server. A metaverse server receives an interaction request for an interaction session from a first user avatar to obtain a digital item in a virtual environment. The metaverse server determines an item value of the digital item is greater than the first asset value, determines a supplement asset required for the first user to obtain the digital item, and sends an asset request with the supplement asset to an entity avatar. The entity server determines that the supplement asset in a first asset pool in a database. The entity server generates digital contracts to receive the supplement asset and send the supplement asset to the metaverse server. The metaverse server completes the interaction session with the first asset and the supplement asset to obtain the digital item for the first user avatar.

Abstract: A system for creating multiple asset pools comprises a metaverse server in communication with an entity server. A metaverse server receives a request for an interaction session from a first user avatar to obtain a digital item in a virtual environment. The metaverse server determines a supplement asset required to obtain the digital item. The metaverse server sends an asset request to an entity avatar associated with the entity server to obtain the supplement asset. The metaverse server receives and approves a request from a second user avatar with a second asset to enroll in an asset pool associated with an entity. The metaverse server receives the supplement asset corresponding to the second asset from the entity avatar associated with the entity server and completes the interaction session with a combination of a first asset of the first user avatar and the supplement asset to obtain the digital item.

Abstract: A multi-level, ensemble network monitoring system for detection of suspicious network activity from one or more a plurality of user computing devices on an external network communicatively connected via a network server to a private communication network is disclosed. In malware detection, the ensemble network monitoring system comprises artificial intelligence (AI) with bidirectional long short-term memory (BDLSTM) recurrent neural networks (RNNs) and natural language processing (NLP) to predict possible security threats and then initiate remedial measures accordingly. Enabling a proactive approach to detection and prevention of potential malicious activity, the BDLSTM RNN may perform real-time monitoring and proactively forecast network security violations to block network communications associated with high-risk user computing devices from accessing a private communication network.

Abstract: Arrangements for providing secure document distribution are provided. In some aspects, a request to distribute a file may be received. The request may include identification of the file being distributed, as well as identification of a recipient. The identified file may be encrypted and stored in a distributed hash table. In some examples, a file reference key associated with the encrypted file may be generated and stored in a distributed ledger. A secure QR code based on the file reference key may be generated and transmitted to a recipient computing device. In some arrangements, an indication of a scan of the secure QR code may be received. Responsive to receiving the indication of the scan, the file reference key may be retrieved and a decrypted file of the encrypted file may be generated and provided to the recipient for viewing and/or downloading.

Abstract: Aspects of the disclosure relate to geocoding geocode datasets in KYC blockchain data blocks for spatial analytical risk modeling. In some embodiments, a computing platform may receive a client request to initiate a transaction with an enterprise organization. Using financial documentation and identification documentation associated with the client request, the computing platform may generate geocode coordinates and may identify a series of geographic risk factors. The computing platform may translate the geocode coordinates and the geographic risk factors into analytical overlays. The computing platform may stack the analytical overlays to generate an interactive spatial risk analysis model. The enterprise organization may use the interactive spatial analytical risk model to analyze the client request, and to determine whether to approve or deny the client request.

Abstract: Embodiments of the invention are directed to systems, computer program products, and methods for assigning geospatial data to tokenized resources via a bridge protocol. The present invention is structured to electronically receive, over a distributed network, a request for a token for a resource. Thereafter, a token generator is initiated and the token is generated, wherein the token comprises resource information and the token is published on a marketplace. Resource information is transmitted to or from the token via a bridge, the resource information comprising geo-spatial data from a geo-spatial analyzer. Thereafter, a consensus is obtained, and the token is recorded on a distributed network.

Abstract: A system is provided for a distributed server network with embedded image decoder as a chain code program runtime event. In particular, the system may comprise a distributed computing network comprising one or more decentralized nodes, each of which may store a separate copy of a distributed data register. The system may further comprise one or more specialized nodes which receive, assess, and analyze user input data, where the one or more specialized nodes may include a client identity node comprising an embedded image decoder which may be configured to analyze image portions of the user input data. Once the image data has been analyzed, the client identity node may convert the image data into a text format for storage within the distributed register.

Abstract: A multi-level, ensemble network monitoring system for detection of suspicious network activity from one or more a plurality of user computing devices on an external network communicatively connected via a network server to a private communication network is disclosed. In malware detection, the ensemble network monitoring system comprises artificial intelligence (AI) with bidirectional long short-term memory (BDLSTM) recurrent neural networks (RNNs) and natural language processing (NLP) to predict possible security threats and then initiate remedial measures accordingly. Enabling a proactive approach to detection and prevention of potential malicious activity, the BDLSTM RNN may perform real-time monitoring and proactively forecast network security violations to block network communications associated with high-risk user computing devices from accessing a private communication network.

Abstract: A multi-level, ensemble network monitoring system for detection of suspicious network activity from one or more a plurality of user computing devices on an external network communicatively connected via a network server to a private communication network is disclosed. In malware detection, the ensemble network monitoring system comprises artificial intelligence (AI) with bidirectional long short-term memory (BDLSTM) recurrent neural networks (RNNs) and natural language processing (NLP) to predict possible security threats and then initiate remedial measures accordingly. Enabling a proactive approach to detection and prevention of potential malicious activity, the BDLSTM RNN may perform real-time monitoring and proactively forecast network security violations to block network communications associated with high-risk user computing devices from accessing a private communication network.

Abstract: Aspects of the disclosure relate to geocoding geocode datasets in KYC blockchain data blocks for spatial analytical risk modeling. In some embodiments, a computing platform may receive a client request to initiate a transaction with an enterprise organization. Using financial documentation and identification documentation associated with the client request, the computing platform may generate geocode coordinates and may identify a series of geographic risk factors. The computing platform may translate the geocode coordinates and the geographic risk factors into analytical overlays. The computing platform may stack the analytical overlays to generate an interactive spatial risk analysis model. The enterprise organization may use the interactive spatial analytical risk model to analyze the client request, and to determine whether to approve or deny the client request.

Abstract: A system is provided for a distributed server network with embedded image decoder as a chain code program runtime event. In particular, the system may comprise a distributed computing network comprising one or more decentralized nodes, each of which may store a separate copy of a distributed data register. The system may further comprise one or more specialized nodes which receive, assess, and analyze user input data, where the one or more specialized nodes may include a client identity node comprising an embedded image decoder which may be configured to analyze image portions of the user input data. Once the image data has been analyzed, the client identity node may convert the image data into a text format for storage within the distributed register.

Abstract: A system for artificial intelligence-based electronic data analysis in a distributed server network is provided. In particular, the system may comprise a distributed computing network comprising one or more decentralized nodes, each of which may store a separate copy of a distributed data register. The system may further comprise one or more specialized nodes which receive, assess, and analyze user input data, as well as use natural language processing (“NLP”) to provide outputs to the user, which may be written to the distributed data register. In this way, the system provides a secure and transparent way of performing data analysis and storing data regarding the decisioning processes of the system.

Abstract: A system provides for data consensus validation in an electronic distributed server network using a screening node. In particular, a distributed database may be hosted on nodes operated by one or more third party entities. The screening node may retrieve reference data, which may be submitted by one or more reference data providers, from the distributed database to generate executable scripts from the screening algorithms within the reference data. The scripts may in turn be validated by the nodes of the distributed database and subsequently embedded into the distributed database for execution by one or more computing systems within the network environment.

Abstract: A system provides for data consensus validation in an electronic distributed server network using a screening node. In particular, a distributed database may be hosted on nodes operated by one or more third party entities. The screening node may retrieve reference data, which may be submitted by one or more reference data providers, from the distributed database to generate executable scripts from the screening algorithms within the reference data. The scripts may in turn be validated by the nodes of the distributed database and subsequently embedded into the distributed database for execution by one or more computing systems within the network environment.