Personalized search results are provided to a user by sending to the user a direct marketing email having associated therewith one or more opt-out elements. Information related to the user's interaction with the one or more opt-out elements is maintained in a database. When a search request is thereafter submitted to a search engine by the user, the information related to the user's interaction with the one or more opt-out elements is used to inhibit inclusion within the search results of one or more items. In addition or alternatively, when the user accesses a search interface having a plurality of search options selectable to provide a search request to the search engine, the information related to the user's interaction with the one or more opt-out elements is used to inhibit inclusion within the search interface of one or more of the plurality of user selectable search options.

A deep linking system includes a search engine including a processing system and a storage system that stores a plurality of application records and a plurality of cluster records. The processing system includes one or more processors that execute computer-readable instructions causing the processing system to receive a search query containing one or more query terms from a remote device and identify a consideration set of application records from the plurality of application records based on the search query. For each application record, the instructions cause the processing system to determine one or more clusters from a plurality of clusters to which the state of the respective software application belongs based on a function identifier of the application record and determine a result score of the application record based on contents of the application record and one or more cluster records respectively corresponding to the one or more clusters.

Techniques for identifying groups of local features in an image and presenting advertisement information associated with stored images that match one or more features within the group of local features are described. The techniques include providing an image, identifying a region of interest in the image, providing a user-selectable link associated with the region of interest in the image, receiving a request for the region of interest in the image via the user-selectable link, and presenting advertisement information associated with a stored image that matches one or more features within the requested region of interest.

A computer system determines that an item has been selected for purchase by a user on a user device. In response to determining that the item has been selected for purchase, the computer system determines that the purchase of the item was not completed. In response to determining that the purchase of the item was not completed, the computer system analyzes activity associated with the user device, and based on the analyzed activity, predicts whether the user intended to complete the purchase. In response to predicting that the user intended to complete the purchase, the computer system causes a communication corresponding to the item to be presented to the user.

The invention relates to a computer application that allows a consumer to recreate his/her community of favorite business from around town and around the world on a computer platform by selecting, on a virtual map, businesses of interest to the consumer, and thereby allows direct communication over a computer network between the selected businesses and the consumer. The consumer interacts with this virtual world through an engaging graphical interface containing icons that depict each business as a uniquely represented, three-dimensional building. Once the consumer creates and account and selects the business on the map, the business can gain real-time access to the consumer through the application delivering highly relevant marketing material to the consumer who had initiated the interaction. The application also provides for a unique reward system for users of the platform.

An image recognition approach employs both computer generated and manual image reviews to generate image tags characterizing an image. The computer generated and manual image reviews can be performed sequentially or in parallel. The generated image tags may be provided to a requester in real-time, be used to select an advertisement, and/or be used as the basis of an internet search. In some embodiments generated image tags are used as a basis for an upgraded image review. A confidence of a computer generated image review may be used to determine whether or not to perform a manual image review.

A method and system for planning and running video-on-demand (VOD) advertising includes a planner for planning advertising campaigns and an ad selector for running selected advertisements from selected ones of the campaigns. The campaigns are associated with household demographic classifications, video content category categories, household geographic locations, and/or video viewing times. In response to a viewer requesting a video, the selector selects the campaigns corresponding to the demographic classification associated with the viewer, the content category of the requested video, the geographic location associated with the viewer, and/or the viewing time at which the requested video is viewed. The demographic classification is determined by using an identifier of the viewer's set-top-box. The selector may select the campaigns corresponding to the content categories of the requested video. The content categories are determined by using an identifier associated with the requested video.

The disclosure herein relates to systems, methods, and devices for decreasing latency and/or preventing data leakage that may arise from advertisement insertion. In some embodiments, the systems, methods, and devices described herein provide for asynchronous advertisement selection and/or insertion separate from user-requested content retrieval and/or delivery, wherein the advertisement selection can be performed in parallel with and/or at a separate location from the user-requested content retrieval and/or delivery, thereby decreasing latency in rendering user-requested content. Further, in certain embodiments, the systems, methods, and devices described herein can prevent data leakage by preventing and/or circumventing the need to use cookie syncing among different DSPs, SSPs, or the like. Moreover, in some embodiments, the systems, methods, and devices described herein are configured to deliver advertisements as a native content, thereby further decreasing latency and/or preventing data leakage.

Described herein are techniques for streaming digital media content, such as music, video, or television content. In accordance with an embodiment, the system includes support for providing music-styled advertisement or other sponsor-directed content. Metadata describes media content that can be streamed or otherwise provided to a user's media device. A media streaming logic and targeting service analyzes a playing media content, and selects advertisements for delivery in conjunction with that content. For example, the system can determine a genre, tempo, or mood of music being streamed during a session, and select advertisements targeted to a style of music. Information associated with the user, for example their location, can be used to predict their mood, and select appropriate advertisements. Advertisements can also be selected based on an analysis of, for example, a playlist description or a song lyrics.

In some embodiments, a method determines characteristics of a user that is viewing a video and analyzes presentation data describing products within a presentation. A product opportunity is selected based on the characteristics of the user and the presentation data for a product. The method selects first metadata for the presentation data and second metadata for the product associated with the presentation data. Then, the method dynamically inserts the first metadata for the presentation data and second metadata for the product into a portion of the video and sends the portion of the video to the user. The product is displayed in the video using the presentation data at the product opportunity.