Abstract: The NFT Based Secure Authentication and Notification Apparatuses, Processes and Systems (“NBSA”) transforms authenticating NFT generation input, NFT authentication input, document publishing input, NFT document access input datastructure/inputs via NBSA components into authenticating NFT generation output, NFT authentication output, document publishing output, NFT document access output outputs. An authenticating NFT generation request datastructure structured to specify a set of source asset identifiers and an owner blockchain address is obtained. For each respective source asset identifier, source asset data associated with the respective source asset identifier is obtained, a hash of the source asset data is generated, and a source asset object associated with the respective source asset identifier is stored in an adjunct repository. A master hash is generated from the generated hashes. An NFT metadata datastructure structured to specify the master hash and a link to each source asset object is generated.

Abstract: Computerized systems and methods are provided for identifying connection between at least one application in a set of client applications within a multi-tenant network and a service application hosted on a server. Audit logs are generated that track activities for respective ones of the client applications over a predetermined duration. Information from a first audit message of each client application is extracted that includes an audit identification and a connecting IP address associated with the corresponding client application. Information from a second audit message of each client application is extracted that includes an audit identification and a process identification of the corresponding client application. The extracted information is used to identify one or more client applications as being connected to and consuming the service application.

Abstract: Systems and methods are described for predicting tasks that users perform on websites. More specifically, a machine learning model is trained using page session data (that includes page flows which are a sequence of pages visited by a user) for each user that is associated with the website. In addition, the machine learning model is fine-tuned using previous page flows associated with the user, user attribute data that is associated with the user, and user tasks, which are tasks that have been previously completed by the user. When a user visits the website, the machine learning model determines a predicted task after the user visits a predetermined number of webpages. A recommended content is generated based on the predicted task and displayed before the user.

Abstract: A computerized method is provided for automated profiling and comparison of electronic data including in different environments and formats. Data column comparison and/or mapping can be efficiently accomplished without input of human experts through a three-step process including column name direct matching, a fuzzy string matching algorithm (token sort ratio) on unmatched columns, and finally a column data comparison for remaining unmatched columns.

Abstract: Methods and apparatuses are described for intelligent text classification with limited or no training data. A server computing device receives one or more of structured text or unstructured text corresponding to compliance text data from a database. The server computing device executes a trained few-shot natural language inference (NLI) classification model on one or more sentences in the received compliance text data to identify whether the one or more sentences comprise a compliance violation. The server computing device transmits the results of the model execution to a remote computing device.

Abstract: Methods and apparatuses for synchronizing data recovery files in cloud-based database management platforms include a server that allocates physical storage media for database management platforms hosted in a cloud computing environment and attaches a source database management platform in a first region of the environment to the allocated storage media. The server attaches a target database management platform in a second region of the environment to the allocated storage media. The server establishes a periodic replication job between the source database management platform and the target database management platform, including validating change files associated with differential data changes in a primary database instance and transmitting the validated change files to the target database management platform for replication in a secondary database instance.

Abstract: A method for identifying the presence of a logo in an image includes providing a neural network having an image encoder, a text encoder, and a score calculator. The method includes receiving the image and a textual description associated with the logo. The method further includes providing the image to the image encoder and the textual description to the text encode. The method includes executing the image encoder and the text encoder, wherein the image encoder generates one or more image embeddings from the image and the text encoder generates one or more text embeddings from the textual description. The method further includes executing the score calculator, wherein the score calculator generates a score from the one or more image embeddings and the one or more text embeddings. The method also includes determining the presence of the logo in the image based on the score.

Abstract: Methods and apparatuses are described for digital content classification and recommendation using constraint-based predictive machine learning. A server trains a machine learning (ML) recommendation model to generate digital content layouts each comprising digital content item slots arranged according to one or more digital content selection constraints. The server receives user profile information for a first user. The server executes the trained ML recommendation model to generate a plurality of digital content item displays, each including a selected digital content item placed in each slot. The server determines, for each digital content item display, an interaction prediction score for each digital content item in the display. The server selects a digital content item display based upon the interaction predictions scores. The server transmits the selected digital content item display to a client device.

Abstract: The Distributed Benefits Coverage Validation Apparatuses, Processes and Systems (“DBCV”) transforms provider info, add provider transaction request, employee subscriber ID card data datastructure/inputs via DBCV components into add provider transaction response, benefit coverage validation notification outputs. A benefit coverage validation request datastructure structured to specify subscriber ID card data associated with a beneficiary is obtained. A blockchain address of a smart contract associated with the beneficiary is determined via the subscriber ID card data. Encrypted benefit coverage data associated with the beneficiary is obtained by sending a blockchain transaction to the blockchain address of the smart contract. An encryption key corresponding to the encrypted benefit coverage data is obtained from a key management server. The encrypted benefit coverage data associated with the beneficiary is decrypted with the encryption key.

Abstract: A computerized method is provided for user authentication using hand gestures. Multiple points on a user's hand can be tracked using cameras or various sensors and the motion of those points in space and relative to each other can used to create gesture-based passwords. Such user authentication techniques have advantages in augmented and virtual reality applications where traditional text-based passwords may be difficult. Gesture-based user authentication can be augmented with physical characteristics of the specific user's fingers and hands including size, shape, and distinguishing marks to enhance security.

Abstract: Techniques are provided for monitoring the integrity of a table in a dataset. The table may include one or more columns and one or more rows, in which data elements in the table are associated with a specific row and a specific column. A coverage rule set may be generated based on metadata of the table, which describes attributes of the table and the columns associated with the table. The coverage rule set includes table rules and column rules. A table fault value is generated for each table rule in the coverage rule set and a column fault value is generated for each column rule in the coverage rule set. An error is detected when a table fault value or a column fault value exceeds at least one of a corresponding table rule threshold or a corresponding column rule threshold. A notification is transmitted for error detected.

Abstract: A computer-implemented method for adaptively discretizing a position of a textual object in a document includes receiving, by a computer system, an image of the document and determining, by the computer system, an absolute position of the textual object in the image of the document. The method further includes normalizing, by the computer system, the absolute position to determine a relative position of the textual object. The method also includes calculating, by the computer system, a bin size such that at least one axis of the image is divided into a plurality of separate bins, wherein a distance between each bin along the at least one axis and its adjacent bin equals the bin size. The method includes discretizing, by the computer system, the relative position based on the bin size to determine a discretized position of the textual object; and providing, by the computer system, the discretized position and a textual content of the textual object as an input to a machine learning model.

Abstract: The Thematic Protocol and Circle Datastructure Apparatuses, Processes and Systems (“TPCD”) transforms TOP-RC search request, TOP-RC selection request inputs via TPCD components into TOP-RC search response, TOP-RC selection response, pool distribution notification request outputs. A thematic circle join request datastructure that includes a user object identifier, a portfolio object identifier associated with the user object identifier, and a thematic circle template identifier is obtained. A thematic circle object instantiated based on a thematic circle template corresponding to the thematic circle template identifier is determined. The user object identifier is added to participants datastructure. A portfolio object corresponding to the portfolio object identifier is marked as locked. A set of creation criteria associated with the thematic circle object is evaluated. The thematic circle object is activated based on a determination that the set of creation criteria has been met.

Abstract: A computerized method is provided for digitally signing a digital document related to a transaction request from a customer. The method includes receiving, by a computing device, data related to the transaction request from the customer via a web-based interface. Receipt of the transaction data initiates a request session. The method also includes recording during the request session a voice signature sample from the customer via the web-based user interface and verifying the customer for the transaction request by comparing the voice signature sample with a stored voice print of the customer. Further, a consolidated record for the transaction request is generated that includes the transaction data and the transaction result. The digital document is populated with the transaction data if the customer is verified, where the digital document is treated as being digitally signed by the customer.

Abstract: Methods and apparatuses are described for predicting user attributes using uncertainty estimate modeling. A server trains a plurality of machine learning (ML) models to predict a distribution of values for a plurality of user attributes. The server determines an uncertainty measure of the ML models for each user attribute based upon the predicted distribution of values. The server receives a request for prediction of user attributes from a client device and generates for each user attribute a first predicted distribution using one or more of the trained models. The server classifies, for each user attribute, an accuracy of the first predicted distribution based upon the uncertainty measure and provides the first predicted distribution and the accuracy for each user attribute to the client device for presentation. The server updates the first predicted value for the user attributes based upon input received from the client computing device.

Abstract: Methods and apparatuses are described for a dual screen extended reality (XR) headset device, including a first display screen viewable by a wearer of the headset device and a second display screen on an external surface of the headset device and viewable by other persons in proximity to the wearer. The headset device generates a virtual environment for display to the wearer via the first display screen. The headset device captures data associated with execution of the software application, data associated with the virtual environment being displayed to the wearer, and data associated with the wearer. The headset device displays a user interface based upon at least a portion of the captured data on the second display screen, and detects input associated with the user interface displayed on the second display screen. The headset device updates the virtual environment and access to software features based upon the detected input.

Abstract: Methods and apparatuses for optimizing performance of conversational interface applications using example forgetting include a server that retrieves training data comprising utterances each mapped to one or more known intents. The server determines a forgetting count for each utterance and selects utterances from the training data that have a forgetting count above a predetermined threshold. The server identifies whether the predicted intent associated with each utterance is accurate. The server generates updated training data comprising the selected utterances and corresponding predicted intents, and trains conversational interface applications using the updated training data. The server validates performance of the trained conversational interface applications and saves the updated training data.

Abstract: A computer implemented method is provided for assisting an agent in providing feedback to a customer during a chat session. The method includes receiving live feedback from the agent to the customer in response to an inquiry from the customer. The method also includes determining if at least one automated response is needed by comparing and matching the live feedback with at least one predefined trigger pattern. The method further includes identifying one or more trigger phrases in the live feedback if automated response is needed and determining from a conversation history database at least one automated response based on the one or more trigger phrases. The method additionally includes appending the at least one automated response to the live feedback for presentation to the customer during the chat session.

Abstract: The Blockchain Augmented Crypto Asset Valuation Apparatuses, Processes and Systems (“NBSA”) transforms authenticating NFT generation input, NFT authentication input, document publishing input, NFT document access input, transfer transaction input, clawback transaction input, valuation access request datastructure/inputs via NBSA components into authenticating NFT generation output, NFT authentication output, document publishing output, NFT document access output, transfer transaction output, clawback transaction output, valuation access response outputs. A crypto asset valuation request datastructure is obtained. A relevant crypto asset valuation transaction for a crypto asset is determined. Historical crypto asset valuation data is retrieved from a blockchain. A default valuation, a higher band valuation and a lower band valuation of the crypto asset are computed by AI crypto asset valuation engines. A valuation of the crypto asset computed by a best performing AI crypto asset valuation engine is selected.

Abstract: Techniques are provided for predicting data for precaching and/or recaching at a computer cache of a computer environment. Based on a detected login event of a user, a precache API request can be generated for a type of API data request most often utilized by the user over a predetermined time period. An API gateway may use the precache API request to obtain a corresponding precache API response from a microservice. The precache API response may be stored together at an API gateway cache. Subsequently, when information from an API call substantially matches a cache key corresponding to the precache API response, the precache API response can be provided to the user instead of obtaining the response from the microservice. Additionally, the precache API request may include a recache value that can be used to iteratively obtain up-to-date precache API responses from the microservice.