Abstract: Disclosed herein identifies audiences of mobile devices that behave a like a seed group of devices. That is, the behave alike group are those devices that move in similar patterns and visit the similar locations with a similar frequency as the devices of the seed group. Similarity is based on correlative similarity in having visited matching categories of location styles identified via mapping data (e.g., devices that visit national parks at a similar frequency). Correlative similarity is performed using a machine learning model trained via a follow the regularized leader proximal.

Abstract: Methods of providing building performance data include receiving building performance data from multiple different building performance data sources each comprising one of multiple different system programming languages and configured to provide building performance data at different time intervals, aggregating the received building performance data from the different building performance data sources into a single data stream, generating graphical data that represents data in the single data stream and providing the data in the single data stream and/or the graphical data to be displayed data to a user.

Abstract: Data transformation offloading in an artificial intelligence infrastructure that includes one or more storage systems and one or more graphical processing unit (‘GPU’) servers, including: storing, within the storage system, a dataset; identifying, in dependence upon one or more machine learning models to be executed on the GPU servers, one or more transformations to apply to the dataset; and generating, by the storage system in dependence upon the one or more transformations, a transformed dataset.

Abstract: A first email message is received from a first user communication endpoint. In one embodiment, the first email message is addressed to a general email messaging address for a corporation. In response to receiving the first email message from the first user communication endpoint, a second email message is sent to the first user communication endpoint. The second email message is used to identify a way to select an individual user of the plurality users. For example, the second email message may have a menu with a list of users. A third email message is received from the first user communication endpoint. The third email message identifies the individual user of the plurality of users. A fourth email message is sent that allows the first user communication endpoint and a user communication endpoint of the selected individual user to establish an email messaging session.

Abstract: A data collection device includes a memory and a processor coupled to the memory and the processor configured to acquire, for a plurality of data transmission requests, first predicted values of a delay from transmission of the respective data transmission requests to a start of reception of data and second predicted values of a throughput regarding the reception of the data, classify the plurality of data transmission requests into groups based on first dispersion of the first predicted values and second dispersion of the second predicted values, and determine transmission timings of the respective data transmission requests in a unit of the group.

Abstract: One or more files are determined. Each file of the one or more files has a score threshold for access. One or more users are determined. Each user of the one or more users has a score for each file of the one or more files. An access request from a user of the one or more users is received. The request is for the user to access a file of the one or more files. The score for the file for the user is compared to the score threshold for access for the file.

Abstract: System and method for identifying nodes with packet loss in a wireless communication network. The method comprises a central probe server—establishing a TWAMP session with a plurality of nodes. The central probe server probes the plurality of nodes for packet loss for a time duration ?T and categorizes each of the plurality of nodes as one of violator node and non-violator node. A sectionalisation module retrieves a topology of the at least one violator node. The central probe server probes at least one neighboring node of the at least one violator node for packet loss for the time duration ?T. The sectionalisation module identifies the at least one violator node as one of a silo node and a daisy chain node based on the probe of the at least one neighboring node.

Abstract: Various systems, mediums, and methods herein describe aspects of data exchange schemas accessible with client devices over communication networks in data infrastructures. A data exchange system may build one or more data exchange schemas for a user. The system may also determine a location of a client device of the user associated with one or more entities. Based on the location of the client device, the system may identify a data exchange schema of the user for transferring data to the one or more entities. The system may determine an access for the one or more entities to a portion of data from the data exchange schema of the user. The system may also transmit a notification to the client device that indicates the access of the one or more entities to the portion of data from the data exchange schema.

Abstract: A computer-implemented method for enriching data may include: receiving, via a server, a data packet from a source of a plurality of sources; determining, via the server, at least one machine learning model of a plurality of machine learning models that applies to the data packet based on at least one of the source or attributes of the data packet; in response to determining the at least one machine learning model, sending, via the server, the data packet to the at least one machine learning model; analyzing the data packet with the at least one machine learning model; receiving, via the server, the result from the at least one machine learning model; adding, via the server, the result to the data packet to create an enriched data packet; and sending, via the server, the enriched data packet to a notification service.

Abstract: A spoken communication system includes a plurality of domestic devices and a server. Each of the devices is responsive to spoken communication to communicate that spoken communication to other devices, and to receive spoken communications received by other communication devices. The server is in digital communication with domestic devices to communicate that spoken communication among the registered devices.

Abstract: Described is a system for cloud-based scheduling of data operations to an object storage. The system may include a server that acts as an intermediary between a client device and an object storage that stores client data. Requests by the client device to manage data on the object storage may be routed through the server. In response, the server may execute corresponding data operations directly on the object storage. The server may manage bandwidth limits for operation requests to an object storage by maintaining a specialized operation pool. The operation pool may be configured to manage operation-specific queues, and these operation-specific queues may include sub-operations (or threads) that are executed on the object storage. Sub-operations of various types of operations may be initiated for concurrent execution on the object storage based on scheduling information derived from the operation pool.

Abstract: Various embodiments of the present disclosure relate to a computer-implemented method of receiving an invalidation command that includes a first asset identifier, and a set of extension value fields, identifying a first file that is stored in a first cache device and is associated with an identifier matching the first asset identifier, comparing attributes of the first file to the set of extension value fields, and upon determining that, for each extension value field, at least one attribute of the first file matches at least one value of the extension value field, causing the first file in the first cache device to be preserved, or upon determining that, for at least one extension value, at least one attribute of the first file does not match at least one value of the extension value field, causing the first file to be invalidated.

Abstract: Methods, systems, and computer-readable storage media for receiving IoT data from an IoT device of an IoT network, the IoT data including identification data and sensor data, determining that a digital twin of the IoT device is stored in a cloud platform based on at least a portion of the identification data, the digital twin including a digital representation of the IoT device that is provided as an instance of a model of the IoT device, and enriching the digital twin with the sensor data.

Abstract: A method includes receiving a message, enqueueing the message, dequeueing the message by a fraud detection service, analyzing the message using a trained machine learning model, analyzing an isolated domain name, storing the message, and causing a mitigation action. A computing system includes a transceiver, a processor, a memory storing instructions that when executed by the processor cause the system to receive a message, enqueue the message, dequeue the message, analyze the message using a machine learning model, analyze an isolated domain name, store the message, and cause a mitigation action. A non-transitory computer readable medium contains instructions that when executed, cause a computer to receive a message, enqueue the message, dequeue the message by a fraud detection service, analyze the message using a machine learning model, analyze an isolated domain name, store the message, and cause a mitigation action.

Abstract: A social network activity mode that is implemented using social network activity rules is identified. The social network activity rules allow only social network posts of relevance to a particular activity of a user to be presented to the user. The social network activity mode is applied to a group of social network posts. Based upon applying the social network activity mode to the group of social network posts, social network posts that comply with the social network activity rules of the social network activity mode are provided to the user and social network posts that do not comply with the social network activity rules of the social network activity mode are blocked.

Abstract: Systems, methods, and computer program products are provided for connecting users and speakers via audio conversations on a mobile application. For example, a method comprises: providing speaker information associated with a speaker, wherein the speaker accesses a mobile application on a first mobile device of the speaker; determining a user accesses a mobile application on a second mobile device of the user; initiating an audio conversation between the speaker and the user; broadcasting, using the one or more computing device processors, on the mobile application, to a listener, a first audio conversation involving the speaker and the user, wherein the listener accesses the mobile application on a third mobile device of the listener.

Abstract: Provided are computer-implemented methods and systems for optimization of publication of an application to a web browser. An example method for optimization of publication of an application to a web browser may include capturing, by a server-side agent, a video frame of a virtual screen associated with the application. The method may further include comparing, by the server-side agent, the video frame to a previous video frame of the virtual screen to detect a change in the video frame. The method may continue with generating, by the server-side agent, an image of the change based on the detection. The method may further include sending, by the server-side agent, the image of the change to a client device. The virtual screen may be re-rendered on the client device based on the image of the change and the previous video frame.

Abstract: In one embodiment, a device in a network receives an access policy and a class behavioral model for a node in the network that are associated with a class asserted by the node. The device applies the access policy and class behavioral model to traffic associated with the node. The device identifies a deviation in a behavior of the node from the class behavioral model, based on the application of the class behavioral model to the traffic associated with the node. The device causes performance of a mitigation action in the network based on the identified deviation in the behavior of the node from the class behavioral model.

Abstract: An application usage estimation device includes: a rule DB serving as a rule holding unit configured to hold an application usage estimation rule for estimating, based on location information, whether a specific application is used; and an application usage estimation unit configured to acquire the location information from a user terminal and to estimate, based on the application usage estimation rule held in the rule DB, whether the specific application is used in the user terminal.

Abstract: A data transaction processing system receives electronic data transaction request messages from client computers over a data communication network and groups a subset of the electronic data transaction request messages at varying intervals. The intervals may be dynamically determined and may be based on the volume and rate of the incoming electronic data transaction request messages. The data transaction processing system may preprocess the group of electronic data transaction request messages before forwarding the electronic data transaction request messages to a transaction processor, which processes the subset of electronic data transaction request messages in a non-chronological order.