Abstract: Described herein is a system for using a machine learning model to predict a metric value indicative of quality of user experience. The system can receive an indication that a mobile device was used to access electronic content. The system obtains a set of characteristics of a user of the mobile device and generates a predicted metric value indicative of a quality of user experience interacting with the electronic content by applying a trained machine learning model to the obtained set of characteristics. The machine learning model is trained on cluster data representing clusters of users of the system, and each cluster is associated with a one or more shared characteristics of users in the cluster and an average metric value selected by users in the cluster. The system selects and transmit an interactive element associated with the predicted metric value to the mobile device.

Abstract: Described herein is a system for providing access to a virtual assistant using a hidden element in source code of a document. The system can receive a request from a computing device to access a document, which has source code that includes a first set of characters embedded at its beginning. The first set of characters may only be accessible by an accessibility engine design to render data describing a document for individuals with visual impairments. When the accessibility engine parses the first set of characters, the computing device outputs content indicating that the individual can access the virtual assistant by performing an interaction. When the computing device detects the interaction, the computing device invokes the virtual assistant to guide the individual through the document.

Abstract: The system creates a first group including a first multiplicity of UEs and a second group including a second multiplicity of UEs. The system provides an information campaign to the first group and prevents the second group from being exposed to the information campaign. The system obtains a first parameters across multiple interaction channels associated with a network and a second parameters across the multiple interaction channels associated with the network. The system determines a difference between the first multiplicity of indications associated with the first group and the second multiplicity of indications associated with the second group. Based on the difference, the system predicts bandwidth consumption in multiple interaction channels of the network upon releasing the information campaign to other UEs operating on the network.

Abstract: Introduced here is a computer-implemented virtual assistant used for completing tasks in an omnichannel environment. The virtual assistant is a common entry point for task completion at an electronic device in a network and can be operable based on a model trained on user activity and network activity. The virtual assistant can receive a request to perform a task associated the electronic device. The virtual assistant can facilitate performance of a first action via a first channel of the network in furtherance of completing the task. Upon detecting performance of the first action, the virtual assistant can present instructions to perform a second action via a second channel (different from the first channel) in furtherance of completing the task. The virtual assistant can detect performance of the second action and present an indication of the completion of the task at the electronic device.

Abstract: The disclosed system receives an indication to seek assistance from a second UE, including a unique identifier of the second UE. The system generates a shared digital location configured to present an output of the computer program and a first avatar indicating a cursor location and an input provided by the first UE. The system generates a unique identifier of the shared digital location. The system generates a message including the unique identifier associated with shared digital location and sends the message to the second UE. The system receives a selection of the unique identifier of shared digital location included in the message from the second UE. Upon receiving the selection, the system generates a second avatar representing indicating a cursor location associated with the second UE. The system provides the shared digital location, the first avatar, and the second avatar to the first and second UE.

Abstract: Introduced here is a computer-implemented system for determining current conditions of electronic devices. The system receives an indication from an electronic device that its user is seeking to trade-in the handheld wireless device. The system presents a user interface with a touch screen verification widget for determining operability of a touchscreen of the electronic device. The system receives an identification number and verifies that the electronic device is available for trade-in using the identification number. The system prompts upload of image data depicting the electronic device via a display mechanism. The system inputs the image data to a machine learned model that is trained to determine make, model, and physical condition of electronic devices. The system receives outputs from the machine learned model and determines the current condition of the electronic device based on the outputs, the operability, and the verification.