Intel Corporation

Marvellworld Trade Ltd.

Marvell International Limited

Tensera Networks Ltd.

International Business Machines Corporation

D.s.p.c. Technologies Ltd.

Ramot University Authority for Applied Research and Industrial Development Limited

Dspc Israel, Ltd.

Daniel Yellin

Yona Perets

Shimon Moshavi

Adoram Erell

David Ben Eli

Ezer Melzer

Eilon Regev

Doron Rainish

Roee Peled

Krishna Srikanth Gomadam

Kobby Pick

Ronen Mayrench

Ehud Weinstein

Navot Goren

Nadav Shulman

Amit Wix

Sharon Levy

Yu-Ngok Li

Guy Wolf

Ilan Sutskover

David Ben-Eli

Rony Ashkenazi

Shlomo Shamai

Amir Francos

Itsik Bergel

Yoni Perets

Ofir Shalvi

Avner Dor

Paul Samuel Spencer

Ilan Saul Barak

Eliav Zipper

Lev Smolyar

Shahar Fattal

Eran Gureshnik

Tsofnat Hagin-Metzer

Yakir Ovadia

Girish Dhanakshirur

Eran Segev

Nir Binshtok

Rohen Mayrench

Jorge Buenabad-Chavez

Avi Brillant

Liron Oded Ehrenwald

Jacob Pick

Shlomo Shamai (Shitz)

Arie Stalberg

Shlomo Yakobovich

A method includes, in a user device () that runs an Operating System (OS-), deciding to preload at least a User-Interface (UI) display of a user application (). At least the UI display is preloaded in a simulated-foreground mode in which the UI display is (i) processed in a foreground mode by the user application, but (ii) kept in a background mode by the OS and hidden from a user of the user device.

Preloading of applications and in-application content in user devices

A method includes, in a processor () of a user device (), preloading one or more user applications () in a background mode, in which activities associated with preloaded user applications are hidden from a user of the user device. An activity, which is invoked in the processor and is associated with a given preloaded user application, is detected. An assessment is made by the processor, whether the activity is a preload-initiated activity that is invoked due to preloading of the given user application, or whether the activity is a user-initiated activity that is invoked due to an action by the user. If the activity is assessed to be a preload-initiated activity, the activity is handled using a first handling scheme. If the activity is assessed to be a user-initiated activity, the activity is handled using a second handling scheme, different from the first handling scheme.

Application preloading in the presence of user actions

A user device includes an interface and one or more processors. The interface is configured to communicate over a network. The one or more processors are configured to evaluate a pre-load scheduling condition with respect to a user application installed in the user device, and to schedule pre-loading of the user application depending on the pre-load scheduling condition.

Scheduling of application preloading in user devices

A user device includes a memory and one or more processors. The memory is configured to store one or more user applications installed in the user device. The one or more processors are configured to run an Operating System (OS) of the user device, including maintaining a data structure that tracks activity of the user applications, and to pre-load a user application before the user application is accessed by a user, including preventing the data structure from tracking the pre-loaded user application.

Transparent pre-loading of user applications

A user device includes a memory and one or more processors. The memory is configured to store one or more user applications installed in the user device. The one or more processors are configured to select one or more operations, which are to be performed in normal launching of a user application but not in background pre-loading of the user application, to pre-load the user application before the user application is accessed by a user, including skipping the one or more selected operations, and to complete the one or more skipped operations in response to the user accessing the user application.

Pre-loading of user applications including skipping of selected launch actions

A user device includes a display screen and one or more processors. The display screen is configured to display content to a user. The one or more processors are configured to pre-load a user application by running at least part of a program code of the user application in a background, including enabling the program code of the user application to pre-render a visual display of the user application in the background, and, in response to the user accessing the user application, to transfer the pre-rendered visual display to a foreground, thereby displaying the visual display to the user on the display screen.

Background pre-rendering of user applications

Distributing machine learning models to electronic devices is provided. A number of machine learning models are built and stored on a server, wherein each model is customized to different device and user requirements. A request for a machine learning model is received from an electronic device, wherein the request includes a device profile comprising device attributes and user characteristics. The server determines which machine learning model from among the number of models is best suited for the device profile according to a set of model policies. The machine learning model best suited for the device profile is selected and downloaded to the device.

Continuously improve recognition or prediction accuracy using a machine learning model to train and manage an edge application

A user device () includes a display (), audio circuitry () and a processor (). The processor is configured to run an application that includes visual content and audio content, by: (i) before a user of the user device invokes the application, running the application in a background mode in which the visual content is not visible on the display, and inhibiting the audio content from being played by the audio circuitry, and (ii) after the user invokes the application, switching to run the application in a foreground mode in which the visual content is visible on the display, and permitting the audio content to be played by the audio circuitry.

Background pre-loading and refreshing of applications with audio inhibition

An apparatus for content delivery () includes a network interface () and one or more processors (). The network interface is configured for communicating over a communication network (). The one or more processors are configured to receive from a user of a user device () a request to access a User-Interface (UI) unit that includes one or more content items, to initially display, in response to the request, the UI unit to the user with versions of the content items that are available for immediate display in the user device, regardless of whether the initially displayed versions are up-to-date or not, and, for at least a content item whose initially displayed version is not up-to-date, to obtain an up-to-date version of the content item, and merge the up-to-date version of the content item transparently to the user into the UI unit being displayed, to replace the initially displayed version.

Silent updating of content in user devices

A method for content delivery includes selecting one or more time intervals. During each time interval among the selected time intervals, given content is prefetched from a content source to a communication terminal using a guaranteed prefetching mode, by continuously tracking the given content on the content source, so as to detect changes to the given content as they occur during the selected time interval, and maintaining the communication terminal continuously synchronized with the content source with respect to the given content, throughout the selected time interval, notwithstanding the changes that occur during the selected time interval, by continuously prefetching at least part of the given content from the content source to the communication terminal. Outside of the one or more selected time intervals, the given content is prefetched using a best-effort prefetching mode, by tracking the given content less frequently than the guaranteed prefetching mode.

Efficient content delivery over wireless networks using guaranteed prefetching

A system () includes one or more interfaces and multiple processors. The one or more interfaces are configured to communicate over a communication network (). At least a first processor from among the processors is included in a user device () and at least a second processor from among the processors is included in a server () external to the user device. The processors are configured to track content items that are provided by one or more content sources () and to deliver the content items to one or more applications () installed in the user device.

Optimized content-delivery network (CDN) for the wireless last mile

Apparatus and methods are described, including a method for use with a first content delivery network (CDN) and a second CDN that are used by a content source. A processor is used to identify that a device is requesting an exchange of content with the content source, identify a property of the requested exchange of content, and based on the property, select one of the first CDN and the second CDN. Subsequently, content is exchanged between the device and the selected CDN. Other embodiments are also described.

Selecting a content delivery network

A method includes caching content items in a cache memory of a communication terminal connected to a communication network. A content item, which is cached in the cache memory, is presented to a user of the communication terminal. An extent of freshness of the cached content item presented to the user is assessed. Presentation of the cached content item is conditionally modified depending on the assessed extent of freshness.

Freshness-aware presentation of content in communication terminals

An apparatus for content delivery includes a network interface and one or more processors. The network interface is configured for communicating over a communication network. The processors are configured to identify rendering characteristics of a plurality of content items that are to be displayed together as a User-Interface (UI) unit on a user device, to assign the content items to (i) a first subset including one or more content items that are to be prefetched, and (ii) a second subset including one or more content items that are not to be prefetched, to prefetch the content items of the first subset irrespective of any request from a user of the user device to access the UI unit, to fetch the content items of the second subset in response to a request from the user to access the UI unit, and to present the UI unit.

Content prefetching to user devices based on rendering characteristics

Growing community of inventors

Raanana, Israel

Daniel Yellin