Abstract: Systems and methods for censoring text characters in text-based data are provided. In some embodiments, an artificial intelligence system may be configured to receive text-based data and store the text-based data in a database. The artificial intelligence system may be configured to receive a list of target pattern types identifying sensitive data and receive censorship rules for the target pattern types determining target pattern types requiring censorship. The artificial intelligence system may be configured to assemble a computer-based model related to a received target pattern type in the list of target pattern types. The artificial intelligence system may be configured to use a computer-based model to identify a target data pattern corresponding to the received target pattern type within the text-based data, identify target characters within the target data pattern, and to assign an identification token to the target characters.

Abstract: Exemplary embodiments may use word embeddings to enhance scanning of programming code scripts for sensitive subject matter, such as confidential subject matter. The scanning may be performed by a neural network in some exemplary embodiments. The neural network initially may be trained on a corpus of programming code scripts to identify keywords relating to sensitive subject matter, such as passwords, tokens or credentials. The neural network may not only identify instances of the keywords but also may identify related terms as well. The output of the scan may be a ranked list of terms in the programming code script that may relate to sensitive subject matter.

Abstract: An example method includes receiving historical usage data associated with computing services provided by distributed servers and an inference model. The inference model is configured to receive a request and make an inference based on the request. The method further includes training a machine learning model to determine a correlation between usage of a first computing service of the and usage of the inference model. The correlation indicates that a first spike in usage of the first computing service precedes a second spike in usage of the inference model. The method further includes receiving, in real-time, current usage data associated with the first computing service. The method further includes determining, based on the current usage data and the correlation, that the current usage data is indicative of the first spike in usage of the first computing service that precedes the second spike in usage of the inference model.

Abstract: The exemplary embodiments provide an improved approach to preventing exfiltration through email messages. The exemplary embodiments process outbound email messages to determine whether an outbound email message contains sensitive subject matter based on contextual information. The determination may be made based at least in part on the context reflected in the contextual information. In the exemplary embodiments, the determination of whether an outbound email message contains sensitive subject matter that should not be exfiltrated may be based at least in part on analysis performed by a trained neural network model.

Abstract: A method for object protection identification is provided. The method may: monitor, using a processor, at least one of audio data or history data associated with a user; detect an object replacement triggering event, based on a result of the monitoring; receive user data for a user associated with the at least one of audio data or history data; identify an object corresponding to the object replacement triggering event based on the user data; identify object-related information, the object-related information including at least one of an object protection information or an object replacement information; and transmit the at least one of the object protection information or the object replacement information based on identifying the object-related information.

Abstract: Aspects described herein may relate to methods, systems, and apparatuses for labeling data in connection with synthetic data generation. The data labeling may begin with a manual process where a user provides labels for data. Based on the labels provided by the user, modified data may be generated and may include one or more encodings associated with the labels provided by the user. A machine-learning model may be trained to predict labels based on the modified data samples. Accuracy of the model may be determined based on comparing the predicted labels to further labels provided by the user and/or by allowing the user to indicate whether predicted labels are correct or incorrect. Once the model is determined to be accurate, the predicted labels may be used as a basis for generating synthetic data.

Abstract: In some implementations, a user device may determine that the user device was granted access to a first set of resources by a first authentication process. The user device may receive a request to access a second set of resources. The user device may generate, based on the request, a token that indicates that the user device was granted access to the first set of resources by the first authentication process. The user device may transmit, based on the request, the token to a server device to cause a second authentication process to be performed on the token. The user device may receive, from the server device, access information indicating whether access to the second set of resources is granted or denied based on transmitting the token to the server device.

Abstract: Logic may adjust communications between customers. Logic may cluster customers into a first group associated with a first subset of synonyms and a second group associated with a second subset of the synonyms. Logic may associate a first tag with the first group and with each of the synonyms of the first subset. Logic may associate a second tag with the second group and with each of the synonyms of the second subset. Logic may associate one or more models with pairs of the groups. A first pair may comprise the first group and the second group. The first model associated with the first pair may adjust words in communications between the first group and the second group, based on the synonyms associated with the first pair, by replacement of words in a communication between customers of the first subset and customers of the second subset.

Abstract: In the disclosed transaction processing system, a system and method are described that increase the ease of access and use of different currency networks by consumers using customizable transaction devices. The customizable transaction devices may be re-programmed prior to or during a currency transaction in accordance with the consensus protocol of the currency network associated with the currency transaction. The currency network further includes one or more host devices, each of which include an interface configured to communicate with a transaction device for the purposes of re-programming a Field Programmable Gate Array (FPGA) of the transaction device according to one or more currency network consensus protocols. Optimizing the performance of transaction devices for proof-of-work or other consensus protocol processing decreases the latency associated with validating currency network transactions, thereby increasing the suitability of cryptocurrency for retail transactions.

Abstract: A computer-implemented method includes receiving a plurality of messages in a thread associated with a topic, providing the plurality of messages to a machine learning model configured to classify messages based on groupings, identifying, by the machine learning model, a first grouping associated with a first subset of the plurality of messages in the thread, wherein the first grouping is identified based on the first subset of the plurality of messages deviating from the topic, initiating a new thread comprising the first subset of the plurality of messages, determining a first user group comprising a first plurality of users associated with the first subset of the plurality of messages and granting the first user group access to the first thread.

Abstract: Systems and methods for formatting data are disclosed. For example, a system may include at least one memory storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving data comprising a plurality of sequences of data values and training a recurrent neural network model to output conditional probabilities of subsequent data values based on preceding data values in the data value sequences. The operations may include generating conditional probabilities using the trained recurrent neural network model and the received data. The operations may include determining a data format of a subset of the data value sequences, based on the generated conditional probabilities, and reformatting at least one of the data value sequences according to the determined data format.

Abstract: Systems and methods mediate permissions for applications on user devices using predictive models. Data communications are monitored on a user device for permission requests and responses. A predictive model is trained with these permission requests and responses until a threshold is met. Then, a default permission response is provided on behalf of the user device in response to a permission request.

Abstract: Systems and methods for generating synthetic data are disclosed. A system may include one or more memory devices storing instructions and one or more processors configured to execute the instructions. The instructions may instruct the system to categorize consumer data based on a set of characteristics. The instructions may also instruct the system to receive a first request to generate a first synthetic dataset. The first request may specify a first requirement for at least one of the characteristics. The instructions may further instruct the system to retrieve, from the consumer data, a first subset of the consumer data satisfying the first requirement. The instructions may also instruct the system to provide the first subset of consumer data as input to a data model to generate the first synthetic dataset, and to provide the first synthetic dataset as training data to a machine-learning system.

Abstract: A method for training a neural network model includes generating a training dataset with a plurality of data types and word samples belonging to each data type. A plurality of character strings stored in a plurality of data fields in a first data file are received where the plurality of character strings includes at least one word belonging to at least one data type in the plurality of data types. The at least one word from each of the plurality of character strings in each of the data fields are split and matched to the at least one data type using the neural network model. An ad hoc second data file with a plurality of data vectors is constructed based on a user selection of data field labels where each data vector includes words matched to a data type with a respective data field label.

Abstract: Systems and methods for searching datasets and classifying datasets are disclosed. For example, a system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving a test dataset from a client device and generating a test data model output using a data model, based on the test dataset. The operations may include processing test data model output by implementing an encoding method, a factorizing method, and/or a vectorizing method. The operations may include retrieving a reference data model output from a dataset index, based on a reference dataset. The operations may include generating a similarity metric based on the reference data model output and the test data model output. The operations may include classifying the test dataset based on the similarity metric and transmitting, to the client device, information comprising the classification.

Abstract: In some implementations, a server may receive, from a user device, one or more credentials associated with a user. Accordingly, the server may transmit, to the user device, instructions for generating a user interface including a plurality of visual components based on authenticating the user with the one or more credentials. The server may detect, during a first interval, a lack of interaction with the user interface. Accordingly, the server may remove one of the plurality of visual components from the user interface based on the lack of interaction. Additionally, the server may detect, during a second interval, one or more interactions with the user interface and may update a similarity score associated with the user based on properties associated with the one or more interactions. Accordingly, the server may restore the visual component to the user interface based on the updated similarity score satisfying a similarity threshold.

Abstract: In certain embodiments, document-based resolution of user inquiries may be facilitated. A predicted intent of the user is determined based on chat activity information associated with the user. A response to a user inquiry may be provided to the user via a chat interface based on the predicted intent. User response may be obtained for the response, which may indicate a failure in providing a resolution to the user (e.g., regarding a user inquiry). Upon detecting a failure in providing the resolution, a document associated with the user and matching the predicted intent may be obtained and presented to via the chat interface. The document may have content related to the predicted intent. The document may be presented as a response to the user response to seek a confirmation from the user regarding its relevance to the user inquiry.

Abstract: Systems, methods, and computer program products to transmit, by a web browser to a web server, a hypertext transfer protocol request for a web page at a first uniform resource identifier (URI). The web browser may receive, from the web server via, the web page and metadata of a plurality of candidate advertisements, the plurality of candidate advertisements determined based on a master machine learning (ML) model. A client ML model executing in the web browser may process the received metadata, the client ML model trained based on prior interactions between one or more users of the web browser and a plurality of previously displayed advertisements. The client ML model may determine based on the processing, a first candidate advertisement of the plurality of candidate advertisements to display in the web browser with the received web page.

Abstract: System, apparatus, and methods are described for monitoring communication sessions and determining to merge two or more of the communication sessions sharing a common ground into a common communication session. A common communication channel may be determined for the common communication session. The two or more communication sessions may be merged to generate the common communication session using the common communication channel.

Abstract: Techniques to apply machine learning to schedule events of interest for a device user. As described herein, a typical device user is inundated with information suggesting activities and other things to do. Using these techniques, the information is categorized according to the activity and those activities that are most likely to be engaged in by the device user are recommended to the device user (via their device) as events of interest. If the device user selects an event of interest, the device is updated to reflect that selection. For instance, a calendar application may be updated to include an event description at the event's date and time. Other embodiments are described and claimed.