This disclosure relates to recommendations made to users based on learned behavior patterns. User behavior data is collected and grouped according labels. The grouped user behavior data is labeled and used to train a machine learning model based on features and tasks associated with the classification. User behavior is then predicted by applying the trained machine learning model to the collected user behavior data, and a task is recommended to the user.

Technologies are described for generating, acquiring, transferring, and manipulating sets of interaction representations, where an interaction representation represents user interaction with content on a computer device, typically using a software application. The set can be represented as an interaction representation. To facilitate set creation, including adding items to a set, a request can be sent to an application to provide an interaction representation, such as an interaction representation of a current state of user-content interaction associated with the software application. Sets can be associated with different types, where the set type can determine whether, and what types, of interaction representations can be added to a set. Sets can be associated with expiration events, where the interaction representation for the set, and in some cases the component interaction representations, can be deleted upon the occurrence of the expiration event. In some cases, a set can be designated not to expire.

An example developer tools system provided by a messaging system includes a software development kit (SKD) engagement monitor that permits capturing app open events in third party resources (e.g., third party apps) that use the developer tools system. The SKD engagement monitor is configured to operate in a manner that preserves privacy of the third party developers and avoids conveying to the messaging system backend environment personally identifiable information (PII) about the third party resource usage.

Systems, methods, computer-readable media, and apparatuses for identifying and executing one or more interactive condition evaluation tests to generate an output are provided. In some examples, user information may be received by a system and one or more interactive condition evaluation tests may be identified. An instruction may be transmitted to a computing device of a user and executed on the computing device to enable functionality of one or more sensors that may be used in the identified tests. A user interface may be generated including instructions for executing the identified tests. Upon initiating a test, data may be collected from one or more sensors in the computing device. The data collected may be transmitted to the system and may be processed using one or more machine learning datasets to generate an output.

Aspects of the present disclosure involve a system and method for performing operations comprising providing to a client device, a messaging application comprising multiple features; accessing a configuration rule that associates a device property rule with a feature; determining at a first point in time, that a property of the client device matches the device property rule associated with the configuration rule; in response to determining that the property of the client device matches the device property rule associated with the configuration rule, enabling the feature on the client device at the first point in time; receiving an updated property of the client device at a second point in time; and in response to determining that the updated property of the client device fails to match the device property rule associated with the configuration rule at the second point in time, disabling the feature on the client device.

Systems for web page or web application instrumentation. Embodiments commence upon identification of a computer-readable user interface description comprising at least some markup language conforming to a respective document object model that is codified in a computer-readable language. An injector process modifies the user interface description by inserting markup text and code into the user interface description, where the inserted code includes instrumentation code to invoke dynamic generation of instrumentation locator IDs using the hierarchical elements found in the document object model. The modified computer-readable interface description is transmitted to a user device. Log messages are emitted upon user actions taken while using the user device. The log messages comprise the instrumentation locator IDs that are formed using hierarchical elements found in the document object model.

A variety of systems and methods can include evaluation of human user effort data. Various embodiments apply techniques to identify anomalous effort data for the purpose of detecting the efforts of a single person, as well as to segment and isolate multiple persons from a single collection of data. Additional embodiments describe the methods for using real-time anomaly detection systems that provide indicators for scoring effort data in synthesized risk analysis. Other embodiments include approaches to distinguish anomalous effort data when the abnormalities are known to be produced by a single entity, as might be applied to medical research and enhance sentiment analysis, as well as detecting the presence of a single person's effort data among multiple collections, as might be applied to fraud analysis and insider threat investigations. Embodiments include techniques for analyzing the effects of adding and removing detected anomalies from a given collection on subsequent analysis.

An analytics server receives from client computing devices end-user events. Each client computing device is operated by an end-user to access an application at a web server based on the end-user events resulting in calls being passed through a proxy to the web server. The analytics server receives from the proxy the calls being made to the web server, and receives return responses from the web server being passed through the proxy. The return responses correspond to activities being performed within the application. The end-user events are correlated with the corresponding calls and return responses from the proxy. Respective correlated end-user events, calls and return responses are translated into respective event vectors. The respective event vectors are processed to determine similarities among the client computing devices. The similar activities are associated with a quality indicator to identify anomalies within the application for corrective action to be taken.

An information processor includes an operation history obtaining unit configured to obtain operation histories created user operations at a terminal device; a function identifying unit configured to, based on the obtained operation histories, identify a function performed by the user operations as an operation target function; an operation extracting unit configured to, based on information about the operation target function identified by the function identifying unit, extract predetermined operation histories from the obtained operation histories; an index calculating unit configured to calculate an index which indicates a level of efficiency of the operations for the operation histories extracted by the operation extracting unit; an operation selecting unit configured to, based on the index, select the operation histories having a predetermined efficiency; and an output controller configured to output a guide information based on the operation histories selected by the operation selecting unit.

Embodiments of the present disclosure provide a content creation method and a device. The method comprises: displaying a creation guide panel in response to a triggering operation on a content publishing control, wherein the creation guide panel comprises at least two creation guide themes, and creation attributes corresponding to the creation guide themes are different; and in response to a triggering operation on a target creation guide theme, displaying multiple pieces of creation guide content information corresponding to the target creation guide theme, so that a user performs content creation according to the creation guide content information, wherein the target creation guide theme is any one of the at least two creation guide themes. According to the embodiments of the present disclosure, the user can use the creation guide content information for content creation, and the user can determine creatable content and also can provide a content consumer with content needed by the content consumer, thereby improving content creation efficiency and experience.