Abstract: The invention relates to executing an action for a cryptographic storage application by comparing a movement dataset, which may contain positional and inertial datasets, with a user profile dataset. The system may receive a first cryptographic storage application address, retrieve a first movement dataset corresponding to a first time period, retrieve a user profile dataset, compare the first movement dataset with the user profile dataset, and execute an action for the first cryptographic storage application.

Abstract: A method includes storing, by one or more processors of one or more computing devices, a plurality of datasets in a non-transitory computer memory associated with the one or more computing devices. A plurality of index representations is generated where each one of the plurality of index representations includes a compressed representation of a respective one of the plurality of datasets. The plurality of index representations is stored in the non-transitory computer memory. A sample dataset is received by the one or more processors. A sample dataset representation is generated that includes a compressed representation of the sample dataset. A determination that at least one of the plurality of datasets is most similar to the sample dataset based on the sample dataset representation and the plurality of index representations is performed.

Abstract: The disclosed methods may receive a first request for access to a first system memory from a new user and a first justification, the first request includes first role information and first current access information of the new user, determine whether the first request is within a request cluster based on first role history information and current access history information. When the first request is within the request cluster, generate a matrix from the first role information and the first current access information, and determine using a first neural network, whether to grant the first request based on the matrix. When the first request is granted by the first neural network, determine, using a second neural network, whether the first justification is similar to first justification history information. When the first justification is similar to the first justification history information, grant the new user access to the first system memory.

Abstract: The present disclosure provides systems for encoding transforms based on intent to be useable by developers. The system receives input datasets, generates output datasets, and identifies characteristics of the input or output datasets. Using these characteristics, the system can encode transforms associated with the datasets based on intent. The system stores and/or associates the intent-encoded transforms in data profiles, so that the system enables the transforms to be searched, recommended, and/or combined.

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: An enterprise platform may retrieve, from a collaboration data store, information about a selected enterprise team. The enterprise platform may then transmit, from a set of integration tools to a workflow tool of a remote cloud-based environment, a data payload including a notification request associated with a channel. The enterprise platform may also transmit, from a runtime environment to a business communication platform of the cloud-based environment, a request to post a notification to the channel and arrange for a member of the selected enterprise team to receive an adaptive information card, pushed by the business communication platform via the channel, containing information associated with at least one of the integration tools. The member who receives the adaptive information card may also, via selection of a graphical icon on the card, respond to the business communication platform via bi-directional communication.

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: 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: 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: System and devices for live captioning events is disclosed. The system may receive event calendar data and a first plurality of caption files and preselect a first caption file based on the event calendar data. The system may then access an audiovisual recorder of a user device, and receive a first feedback from the recorder. The system may then determine whether the first caption file matches the first feedback. When there is a match, the system may determine a first synchronization between the caption file and the feedback. When there is no match, the system may determine if there is a match with a second caption file of the first plurality of caption files and determine a second synchronization. When the second caption file does not match, the system may receive at least a third caption file over a mobile network and determine a third synchronization for display.

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: 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: 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.