A system and method for tracking user activity across multiple advertising domains, including both off-site and on-site user activity. The present methods employ at least a first creative pixel associated with an ad exposure to obtain a unique ID for the user and capture user activity data associated with this unique ID. The unique ID assigned to the user is the same regardless of which advertising platform serves the ad. The present methods further employ at least a first site pixel associated with content provided by the advertiser to receive the unique ID for a visitor to the website which has previously been exposed to one or more advertisements on off-site websites. The use of a common unique ID for on-site and off-site activity, regardless of platform, enables sophisticated analytics of advertising performance across multiple advertising platforms.

Virtual reality devices bring a new type of advertisement preference input command data. The data comes from a source of having your eyes at least partially viewing the sight of a virtual experience. For this reason, and many more, it is very important that this new generation of devices, as they exist and develop, control the advertisements the virtual reality device owners see and react to in the awe struck environment of something new. In order to do this, they will need many different ways to send commands at different points and complexities of advertisements, especially to enjoy the experience of this new device that would otherwise be lost in advertisements that have no ability to coexist without the participants giving orders of what they want to see.

Apparatuses and methods are provided for storing information related to objects associated with a hand of a user via a wearable camera system. In one implementation, a wearable apparatus for storing the information is provided comprising a wearable image sensor configured to capture a plurality of images from the environment of the user, and at least one processing device programmed to process the images. The processing device may detect the hand of the user, and an object associated with the user's hand. The processing device may proceed to store information related to the object. Consistent with disclosed embodiments, the stored information may be used for various purposes, such as warning the user of dangers, catering advertising to the user, and helping the user find objects when they are lost.

The disclosed subject matter relates to a system and method for selecting/recommending ads based on a contextual bandit approach. The disclosed approach leverages various embedding vectors of item, search, page taxonomy trained based on traffic data via advanced deep learning models, and uses model signals (e.g. historical CTR, item price, rating, quality) from other ad placements. The learning mechanism on top of the current methodology to automatic chooses the best feature sets and adjust model performance over time. The contextual bandit model performs better with respect to CTR than the Thompson Sampling model, and achieves lower regret and faster convergence over time.

A system comprising a computer-readable storage medium storing at least one program, and a computer-implemented method for providing text message alerts. A telephony interface module receives an alert enrollment request from a client device. The alert enrollment request is received through a first type of communication channel. The alert enrollment request includes a protocol specific portion that includes a communication endpoint identifier assigned to the client device. A data database management module links the communication endpoint identifier to an opt-in record. A text message interface module communicates, based on the client device identifier being linked to the opt-in record, an alert to the client device through a second type of communication channel. The alert is addressed to the client device based on the communication endpoint identifier linked to the opt-in record.

Systems and methods are provided to authorize users to anonymously access resources of different web sites. For example, a business listing service may authenticate users and allow the authenticated users to access the resources of the businesses listed via the business listing service, without the users having to create separate accounts with the businesses and without having to reveal the identities of the users to the businesses.

A first data packet can be received from an origination terminal at a remote server operatively coupled to the origination terminal and an end user terminal. The first data packet can have a plurality of offers and image or video data acquired by an image/video sensor. The image or video data can be processed by the remote server using an image processing algorithm to estimate a current idle time associated with the origination terminal. One or more aspects of the plurality of offers can be controlled by the remote server based on the current idle time. A second data packet including the plurality of offers can be transmitted to the end user terminal by the remote server. A selection of a preferred offer of the plurality of offers can be received from the end user terminal at the remote server. The preferred offer can be provided to the origination terminal.

Techniques described herein are directed to e-commerce tags in multimedia content. In an example, multimedia content is received that includes a representation of an item offered for sale by a merchant. A user profile of the viewer is determined. Identifying information including customized item details are generated based on the user profile. The identifying information is sent to a different application (on a same device or different device as the device that is playing the multimedia content), which allows for linkage of a merchant profile and user profile and enables payment for the item.

A system for enhancing advertisement interaction, which may include receiving, from a publisher, media content, and media information; creating, form the media content, at least one media audio fingerprint; storing, on a database, the at least one media audio fingerprint and the media information; receiving, from an electronic device, a device input; creating, from the device input, at least one input audio fingerprint; matching at least one media audio fingerprint with at least one input audio fingerprint; retrieving from the database the media information related to the matched media audio fingerprint; displaying, via a display of the electronic device, the retrieved media information. The electronic device may include a microphone.

A system for placing a real-time interactive advertisement on, inside, or in the general vicinity of a moving vehicle, during a live feed, wherein a user has the capability to pause and then click on the provided HTML hyperlinks with the goal of a user learning more about an advertisement.