Abstract: Systems as described herein may determine a plurality of content items posted to a mesh network and each content item may be associated with a signature stored in a blockchain. A search engine may query each content item based on the corresponding signature in the blockchain. The search engine may parse each content item to obtain a label and store the label, the signature and content associated with each content item in a database. The search engine may query the blockchain to obtain a frequency that each content item has been queried in a predetermined period of time. The search engine may rank the content items based on the frequencies, and determine a subset of the content items as frequently searched content. Accordingly, the search engine may distribute the frequently searched content to a plurality of cached nodes in the mesh network.

Abstract: Systems and methods are disclosed herein for building contextual transcripts. A computing system may receive a textual transcript of a meeting that contains a variety of statements made by various attendees of the meeting, select the first statement made during the meeting, and determine which meeting attendee made the statement. A machine learning model corresponding to the particular attendee that has been trained using previously received statements by the particular attendee may be used on the utterance to determine the tone of the utterance. That tone may be recorded within the transcript and this process may be repeated for each utterance to build a contextual transcript.

Abstract: A computer-implemented method may include: receiving financial information regarding a user; categorizing transaction information of the user based on the financial information; displaying the categorized transaction information of the user; receiving information regarding at least one financial preference and at least one transaction preference of the user; training a machine learning engine based on the at least one financial preference and at least one transaction preference of the user to determine one or more activities available to the user; calculating, for each of the one or more activities available to the user, an estimated influence on the at least one financial preference; displaying the estimated influence on the at least one financial preference based on a user selected one of the one or more activities available to the user; filtering the one or more activities available to the user with a positive estimated influence to the at least one financial preference; and presenting a recommendation of

Abstract: In some implementations, a device may train the model to generate embeddings for log files associated with an application, and to enable the model to generate embeddings for sensitive information included in a set of training log files. The device may receive a log file associated with the application. The device may generate a compressed log file including a set of embedding vectors associated with records included in the log file, where a record that includes sensitive information is associated with one or more embedding vectors for the sensitive information and one or more embedding vectors for other information included in the record. The device may store the compressed log file including the set of embedding vectors where a size of the compressed file is less than a size of the log file, and the embedding vectors obfuscate the records included in the log file.

Abstract: Aspects described herein may relate to methods, systems, and apparatuses for generating synthetic data based on time series predictions and plural machine learning models. Generating the synthetic data may include receiving one or more data records that include transaction data of a user, categorizing and/or segmenting the one or more data records, determining a first predicted time step based on the categorizing and/or segmenting, and performing an iterative process that determines further predicted time steps. The first predicted time step may be determined using one model of a plurality of machine learning models. The iterative process may determine the further predicted time steps using the plural machine learning models. Based on iterations of the iterative process, potential time series may be determined. The synthetic time series may be determined from the potential time series. The synthetic time series may be used by additional processes, such as additional machine-learning processes.

Abstract: Methods and systems are described herein for modifying scheduled events based on bandwidth availability. To modify the scheduled event, the system determines a plurality of user devices corresponding to an event. The system receives first network conditions for a first user device and generates a feature input based on the first network conditions. The system inputs the feature input into an artificial intelligence model to determine a first available bandwidth metric and aggregates the first available bandwidth metric with respective available bandwidth metrics for other user devices of the plurality of user devices to determine a composite available bandwidth metric. The system can compare the composite available bandwidth metric to a threshold available bandwidth metric and in response to determining that the composite available bandwidth metric equals or exceeds the threshold available bandwidth metric, the system generates for display, on a user device interface, a recommendation for modifying the event.

Abstract: A computer-implemented method includes tracking, by a computing device, user browsing activity of a first page having known elements; mapping, by the computing device, the user browsing activity to the known elements; storing, by the computing device, mapping information that maps the user browsing activity to the known elements; tracking, by the computing device, user browsing activity of a second page having unknown elements; identifying, by the computing device, the unknown elements based on the mapping information and the user browsing activity of the second page; and executing, by the computing device, one or more computer-based instructions based on the determining the unknown elements that were identified.

Abstract: Systems as described herein may implement a tunable pre-trained discriminator in a machine learning model, such as a general adversarial network. A server may generate training data using a generator of the machine learning model. The server may send the training data to a first discriminator (e.g., a pre-trained discriminator) and a second discriminator (e.g., an untrained discriminator). The server may receive a first set and a second set of labels from the first discriminator and the second discriminator, respectively. The server may select a label from either the first or the second set of labels. Accordingly, the server may provide the selected labels and the corresponding data records to further train the generator of the machine learning model.

Abstract: A computer-implemented method may include: receiving, from at least one camera, image data associated with a first user at a public access user computing device; detecting, based on the received image data, by employing a machine learning model trained using a dataset of actions collected from a plurality of previous users, that the first user has moved away from the public access user computing device; automatically encrypting, based upon the detection, a user session associated with the first user, wherein the encrypted user session is configured to be subsequently activated by the first user; and initiating a new generic user session on the public access user computing device for a second user.

Abstract: Disclosed herein are system, method, and computer program product embodiments for determining a probability of a device at risk. The device may be associated with a plurality of security parameters. For a security parameter, the device can be in multiple states. A probability value corresponding to a security parameter can indicate the security parameter being in a state among the multiple states. A probabilistic graphical model may be used to represent dependences of the plurality of security parameters. A device security risk prediction module may determine a probability of the device at risk based on the probabilistic graphical model and the probability assignments to the plurality of nodes of the probabilistic graphical model, and further determine a user action instruction to be provided to a user of the device based on the probability of the device at risk.

Abstract: Methods and systems are disclosed herein for using machine learning to send notifications. A computer system may receive a message and may determine a sentiment level and/or an urgency level associated with the message. The computer system may use the sentiment level and/or urgency level to predict when the user will respond to the message. The computer system may compare the predicted response time with one or more thresholds to determine a time to send a notification for the message to the user device.

Abstract: Systems and methods for synthetic data generation. A system includes at least one processor and a storage medium storing instructions that, when executed by the one or more processors, cause the at least one processor to perform operations including receiving a continuous data stream from an outside source, processing the continuous data stream in real-time, and using machine learning techniques to generating synthetic data to populate the dataset. The operations also include creating a plurality of bins, wherein the plurality of bins occupy a data range between the determined minimum and maximum values without overlapping; and determining a number of samples within each of the created bin, based on a bin edges, wherein the bin edges are bounds within the data range.

Abstract: In some implementations, a system may obtain document lineage training data associated with a plurality of historical documents and corresponding lineage data of independent historical documents of the plurality of historical documents. The system may train, based on the document lineage training data, a lineage analysis model to determine a lineage of edited sections of a source document. The system may receive a plurality of document files that correspond to a plurality of versions of a document. The system may determine, using a similarity analysis model, that a first section from a first version of the plurality of versions corresponds to a second section from a second version of the plurality of versions. The system may determine, using the lineage analysis model, a lineage of a corresponding section of the document that is associated with the first section and the second section.

Abstract: Systems and methods for classifying data are disclosed. For example, a system may include at least one memory storing instructions and at least one processor configured to execute the instructions to perform operations. The operations may include receiving training data comprising a class. The operations may include training a data classification model using the training data to generate a trained data classification model. The operations may include receiving additional data comprising labeled samples of an additional class not contained in the training data. The operations may include creating a synthetic data generator. The operations may include training the synthetic data generator to generate synthetic data corresponding to the additional class. The operations may include generating a synthetic classified dataset comprising the additional class. The operations may include retraining the trained data classification model using the synthetic classified dataset.

Abstract: Systems and methods disclosed herein provide fraud mitigation via dynamic transaction card wireless communication. A mobile device may cause a dynamic transaction card to periodically scan its environment to detect wireless enabled devices proximately located near the dynamic transaction card. Based on identifying the wireless enabled devices frequently located near the dynamic transaction card, a set of approved devices may be determined. During a transaction, a dynamic transaction card may scan its environment for other wireless enabled devices proximately located near the dynamic transaction card. If wireless enabled devices detected by the dynamic transaction card are all, or a subset, of the devices that are frequently located near the card, then the transaction may be authorized. However, if the wireless enabled devices detected by the dynamic transaction card are not all, or a subset, of the devices that are frequently located near the card, then the transaction may be unauthorized.

Abstract: Apparatuses, systems and methods are described herein for separately collecting and storing form contents. Different information may be collected from a user on a form. Based on determining that portions of the form request a first type of information, an extended reality (XR) environment may be provided to the user. The user may provide the first type information via an input method in the XR environment. The user may provide a second type of information using a different input method outside of the XR environment. The first type of information may be processed and stored in a different database as compared to the second type of information. The database storing the first type of information may have a higher security standard than the database storing second type of information.

Abstract: A device detects a communication involving a user associated with an account and a service representative, and sends, to a user device associated with the account, an authentication notification that causes the user device to display an authentication field for the user. The device sends, to a service representative device associated with the service representative, a message that indicates that the service representative is to request, via the communication, the user to enter personal information associated with the user into the authentication field, where the user device is configured to generate a first authentication code based on a user input received from the user device in the authentication field. The device generates a second authentication code based on personal information associated with the account from a data structure, receives the first authentication code, and performs an action based on the first authentication code and the second authentication code.

Abstract: Randomizations of a web page may be generated in advance and provided to a client. The client may store the randomizations in its cache. Multiple randomizations for the same web page may be provided to the client and stored in the client's cache. When a request for a web page is made, it is determined if the client has any cached randomizations. Randomizations for the probable next web page to be requested by the client may be provided to the client for storage in the cache. For example, the probability that a link will be clicked or a website visited may be determined. Those web pages and websites with higher probabilities may be determined. Randomizations for those web pages are then provided to the client for use.

Abstract: Aspects described herein may relate to systems and methods for automatically adjusting user device settings when a user attends an event or otherwise brings a user device into a context in which an automatic adjustment of settings is appropriate. By providing for automatic adjusting of user device settings, the systems and methods may achieve greater compliance with rules and other policies of airlines, performance venues, schools, and/or other entities associated with events and/or contexts in which user device settings should be adjusted. Aspects described herein may allow for automatic adjustment of user device settings without compromising a user's privacy, security, or control of a user device.

Abstract: In some embodiments, gaze-tracking-based image downscaling for multi-party video communication may be provided. In some embodiments, a set of gaze locations may be received from a set of receiving devices during concurrent video communication sessions between the receiving devices and a sending device. Different collections of positions may be determined based on the gaze locations, and, for each such collection, a spatial indicator (e.g., a bounded region) may be determined. A first downscaled encoding of the source image (from the sending device) may be generated based on the first spatial indicator, and a second downscaled encoding of the source image may be generated based on the second spatial indicator, etc. The downscaled encodings may then be sent to the respective receiving devices during the concurrent video communication sessions.