Abstract: Devices at different geolocations are configured to determine and share information regarding execution of an application under various conditions. Data determined by a user device includes private information, such as screen capture data, location data, or information about the user. The user device processes the data locally, such as by determining performance metrics or other characteristics of execution of the application, and sends this information to a server. The data sent to the server excludes the private information. The server determines additional data associated with execution of the application by devices other than the user device, which may include screen capture data or location data associated with those other devices. The additional data is used in conjunction with the data received from the user device to generate interfaces indicative of performance metrics of the application.

Abstract: A first device executing an application determines data indicative of conditions associated with the first device during use of the application. Based on correspondence between this data and threshold data that indicates conditions in which frames representing a display output of the first device should be stored, the first device is caused to send data indicative of these frames to a second device. The second device generates user interface data based in part on the received frames and may send the user interface data to other devices. To reduce the amount of data sent and the computational resources used, the first device may store only changed frames of display output, and may send data to the second device at times when a communication interface of the first device is active for other purposes.

Abstract: A machine learning system is trained to determine scores indicative of a quality of video data based on the characteristics of the video data, without requiring information regarding the correct appearance or other aspects of the video content. To train the machine learning system, users input scores for videos having predetermined quality scores, videos that have been previously seen by the users, and videos that have not been previously seen by the users. The differences between a user's score and a predetermined score or a score previously input by the user are used to determine a consistency metric. The scores and consistency metrics determined for a group of users, and the video characteristics of the videos presented to the users, are used to train the machine learning system to determine scores indicative of the quality of a video based on the characteristics of the video.