Abstract:
Disclosed is a system and method for calibrating BLE signal strengths to high-accuracy/precise distances. The present disclosure involves auto-calibrating BLE-based tracking systems, such as, for example, those used indoors using acoustic signals. The present disclosure enables BLE-based distance estimation to be accurate to decimeters and centimeters. The disclosed systems and methods utilize signals communicated to and from roaming devices in order to determine the distance(s) between the roaming device and installed BLE units. A signal-strength to distance map can then be constructed for reuse on any device with a Bluetooth component.
Abstract:
Techniques are provided that include generating a single script block for placement at a single location on an HTML document in response to a creation of one or more ad units for the HTML document, the single script block including one or more section codes that correspond to one or more content blocks of the HTML document. A syndication script for obtaining logic and metadata is generated for injecting native advertisements in the HTML document based on the one or more section codes. The syndication script is provided in response to a request generated by the single script block, and one or more native advertisements are provided in response to an ad call generated by the syndication script, the one or more native advertisements for injection in the one or more content blocks of the HTML document based on the logic and metadata. The ad request may contain one or more sections containing the metadata of the XPath identifying nodes within a Document Object Model of the HTML document as native ad placement containers.
Abstract:
One or more methods and/or techniques for providing an advertisement to a user are provided herein. Message communication associated with a user may be evaluated to identify message content (e.g., a forum post soliciting a recommendation for vacuum cleaners). The message content may be evaluated to identify recommendation content (e.g., a vacuum cleaner recommendation). The recommendation content may comprise a recommendation request and/or a recommendation for the recommendation request. An advertisement corresponding to the recommendation content may be identified (e.g., a vacuum cleaner advertisement). The advertisement may be displayed to the user.
Abstract:
Systems and methods for building a search index for query recommendation and ad matching are disclosed. The system accesses a query-URL graph and extracts a subgraph related to an ad campaign. The subgraph is annotated according to desired criteria. The sub graph is reversed and the reversed annotated subgraph is ranked to find nodes of importance. The nodes of importance are then used to build a preference vector which is used to find a stationary distribution of the sub graph. A plurality of random walks of the sub graph is performed to build a corpus of words. The corpus of words are input into a language model to learn associations, from which the top query terms associated with an ad campaign are found and indexed. The index is then inverted for recommending ads for received query terms.
Abstract:
Described herein are example systems and operations for enhancing targeted delivery of online content using action rate lift and/or A/B testing. These examples provide solutions to problems in targeted delivery of online content, such as the problem of not being able to identify audience and/or situational targets mostly or only influenced by the content item or campaign of concern. For example, described herein are solutions that can estimate AR lift associated with a content item, and then distribute the content item or similar content items accordingly. An AR lift model can be used and such a model can use machine learning, A/B testing, and/or statistical analysis.
Abstract:
Systems and methods for are provided for measuring treatment effect of advertisement campaigns. The system includes a processor and a non-transitory storage medium accessible to the processor. The system includes a memory storing a database including historical advertisement data. A computer server is in communication with the memory and the database, the computer server programmed to obtain a tree-based model using the historical advertisement data, where the tree-based model include a plurality of leaf nodes. Within at least one leaf node of the tree-based model, the computer server obtains a number of subjects and estimates a treatment effect for a treatment. The computer server calculates a final treatment effect for the tree-based model using the number of subjects and the treatment effect. The computer server then determines a parameter for future advertising strategy using the final treatment effect.
Abstract:
One or more systems and/or methods for identifying a positional state of a mobile device are provided. An output audio pulse may be generated from a speaker of a mobile device. An input audio pulse, corresponding to the output audio pulse, may be detected utilizing a microphone of the mobile device. The output audio pulse and the input audio pulse may be evaluated to determine a positional feature associated with the mobile device. The positional feature may be evaluated using a classifier to identify a positional state of the mobile device (e.g., the mobile device may be laying on a table, inside a user's jacket pocket, within a vehicle, etc.). In an example, an operating characteristic of the mobile device may be adjusted based on the positional state of the mobile device (e.g., a ringer volume may be increased, a content recommendation may be displayed, etc.).
Abstract:
Among other disclosures, a method may include collecting historical communication data and personal data relating to a portion of a plurality of communications, a sender of one or more of the communications or one or more recipients of the communications. The method may include depositing the collected data into a repository of historical communication data and personal data. The method may include presenting one or more items in the repository, in response to user behavior.