Example implementations relate to predicted usage based on monitored usage. For example, a system comprising a monitor engine can monitor usage of a plurality of applications used by a user during a first time period, during a heartbeat event, and predict usage of the plurality of applications, using a predictor engine, by the user during a second time period based on the analyzed monitored usage of the plurality of applications during the first time period. Additionally, the predictor engine can generate content during the second time period based on the predicated usage of the plurality of applications during the first time period.

Techniques for identifying certain types of network activity are disclosed, including parsing of a Uniform Resource Locator (URL) to identify a plurality of key-value pairs in a query string of the URL. The plurality of key-value pairs may include one or more potential anonymous identifiers. In an example embodiment, a machine learning algorithm is trained on the URL to determine whether the one or more potential anonymous identifiers are actual anonymous identifiers (i.e., advertising identifiers) that provide advertisers a method to identify a user device without using, for example, a permanent device identifier. In this embodiment, a ranking threshold is used to verify the URL. A verified URL associate the one or more potential anonymous identifiers with the user device as actual anonymous identifiers. Such techniques may be used to identify and eliminate malicious and/or undesirable network traffic.

A method, a computer program product, and a system for enacting ameliorative resource action during an e-conference. Exemplary embodiments of the present inventive concept may include a method for enacting ameliorative resource action during an e-conference. The method may include collecting data from a user's computer device during the e-conference. Features may be extracted from the collected e-conference data. A user's participation within the e-conference and a resource consumption thereof may be forecasted by applying a user activity model to the extracted features. The ameliorative resource action may be enacted based upon the forecasted user's participation and the resource consumption thereof.

A non-transitory storage medium stores a program causing a computer to implement a process. The computer is a user terminal connected via a network to a first server that distributes contents and a second server that transmits a push notification. The process includes: generating key information that defines validity of distribution reception of the contents to a first server in response to an access to a web page of a site where the first server distributes the contents; storing the generated key information in a storage unit; receiving a push notification from a second server; detecting an operation for linking to an advertisement page from the push notification; and updating the key information on the basis of the detection of the operation.

Systems and methods are provided for timing message notifications to be provided to mobile device users based on their geographic locations with respect to geographic areas associated with a threshold level of content consumption. The timing of message notifications may be controlled in order to optimize the chances of delivering targeted content to a mobile device user based on the current geographic location of the user's device relative to a threshold level of content consumption area. As mobile device users may be more likely to launch a client application in a place where other users are currently consuming content, a general message notification sent to the user's device located in a geographic area associated with a threshold level of content consumption, may increase the likelihood that the user will launch the client application and thereby, allow targeted content to be delivered to the user's mobile device.

Techniques are described for triggering conditional automated social posts. According to an embodiment, a set of one or more conditions is received through a user interface by a system executing on one or more computing devices. The system monitors one or more social media channels for target content that has been posted on at least one social media channel of the one or more social media channels. In response to detecting, by the system executing on one or more computing devices, that the target content has been posted on at least one social media channel of the one or more social media channels, the system determines whether the set of one or more conditions are satisfied. In response to determining that the set of one or more conditions are satisfied, the system triggers an action responsive to the target content.

The embodiments of the invention relate to a mining method and device based on a blockchain, and a computer readable storage medium. The method comprises: acquiring behavior data of at least one user within a cycle; determining a value corresponding to each user in the at least one user within the cycle according to the behavior data of the at least one user and a value of a rated quantity within the cycle; and recording an identifier, the behavior data and the value of the at least one user within the cycle in the blockchain, so as to realize more reasonable and more resource-efficient mining.

A method for dynamically allocating server resources includes receiving a request from a client system, wherein the request comprises a request for a first set of streaming data, providing from the server to the client system a first portion of streaming data from the first set of streaming data, wherein the first portion is associated with a first quality of service level, receiving user activity data from the client system for the first portion of the streaming data, determining a second quality of service level for a second portion of the streaming data from the first set of streaming data, providing from the server to the client system the second portion of streaming data from the first set of streaming data, wherein the second portion provided with the second quality of service level, and wherein the first quality of service level is different from the second quality of service level.

Artificial intelligence (AI) based multi-application (app) systems and methods are described for predicting user-specific events and/or characteristics and generating user-specific recommendations based on app usage. A training data set comprising a plurality of previous predictive outputs of multiple existing AI apps is aggregated and is used to train an ensemble AI model operable to predict events and/or characteristics of respective users. App data usage of a user is analyzed by the ensemble AI model to determine a predicted event and/or characteristic of the user, and a user-specific electronic recommendation is generated therefrom that is designed to address the predicted event and/or characteristic. The user-specific electronic recommendation may be rendered on a display screen of a user computing device.

Generating user-specific polygraphs for network activity, including: gathering information describing network activity associated with a user and generating, based on the information, a user-specific polygraph that includes one or more destinations associated with the network activity.