Abstract: In one aspect, an example method includes (i) determining an estimated number of replacement advertisement segment viewings remaining before an end date of a first advertising campaign; (ii) determining a number of impressions remaining for the first advertising campaign in order to reach a guaranteed total; (iii) determining, using the estimated number of replacement advertisement segment viewings and the number of impressions remaining, a first value of serving a first replacement advertising segment corresponding to the first advertising campaign to a content-presentation device; (iv) determining a second value of serving a second replacement advertisement segment corresponding to a second advertising campaign to the content presentation device; (v) selecting the first replacement advertisement segment rather than the second replacement advertisement segment based on the first value being greater than the second value; and (vi) causing the first replacement advertisement segment to be transmitted to the co

Abstract: Various examples are directed to systems and methods for adaptively generating leads. A marketing system may determine that a first lead score for a first lead is greater than a first lead score threshold and determine that a second lead score for a second lead is less than the first lead score threshold. The marketing system may generate a set of filtered leads including the first lead information from the first lead. The marketing system may determine a scrub rate that describes a portion of first execution cycle data having lead scores greater than the first lead score threshold and determine that the scrub rate is greater than an analysis window scrub rate by more than a scrub rate threshold. The marketing system may select a second lead score threshold that is lower than the first lead score threshold.

Abstract: Systems and methods perform predictive analytics using analytical tool(s) on an aggregation of user action history data. A cluster model classifies action(s) previously entered into by a user, including scoring the action(s) previously entered into by the user. A predicted action score predicted to be currently applied to at least one of the action(s) previously entered into by the user is programmatically generated. Predicted user reaction(s) of the user resulting from providing, via a digital platform, the user with recommended user action(s) are programmatically simulated, the simulating identifying a preferred recommended user action capable of being at least partially performed by the user across a network via the digital platform. Program instructions determine that the user is accessing, via a user interface of a user device, the digital platform to perform user action(s), and display, via the user interface, the preferred recommended user action.

Abstract: System, apparatus and method may control charging a battery of one or more mobile energy storage and power consumption devices, such as installed on electric vehicles (EVs), and delivering a targeted advertisement, provided over a communication network, at an EV charging apparatus selected for charging the battery of the mobile energy storage and power consumption device of an EV, or by a software application on a computing device of an EV user which may perform functions of a process for EV charging.

Abstract: A system for guiding interactions with a user device requests a response from a plurality of users, stores the response as response data forming a subset of a personal data set of each of the responding users, and generates a predictive model during training of a machine learning program utilizing at least one neural network with a training data set including the personal data set of each of the plurality of users. The predictive model predicts a probability of a first one of the users associated with the user device interacting with a first product and/or service by correlating a personal data set of the first one of the users to the personal data set of at least a second one of the users and sends a communication relating to the first product and/or service to the user device when the predicted probability meets or exceeds a threshold value.

Abstract: One variation of a method for aggregating advertisement interaction data includes: receiving a ping from a visual element loaded onto a mobile device, the ping containing: a timestamp; and a value representing a proportion of the visual element visible in a viewport at the mobile device; in response to the value exceeding a threshold value, grouping the ping with a group of pings in a ping feed, the group of pings containing a unique identifier associated with the mobile device; in response to the value falling below the threshold value, concluding an advertisement view session containing the group of pings; calculating a time spent value for visibility of advertisement content in the visual element within the advertisement view session based on timestamps of pings in the group of pings; outputting an advertisement view session packet containing the unique identifier and the time spent value to a database.

Abstract: A video generation method and apparatus, and a promotional video generation method and apparatus are disclosed. The video generation method includes: obtaining a plurality of original files, each of the plurality of original files includes at least one subject matter; extracting multiple subject matters and labeling information corresponding to the multiple subject matters from the plurality of original files; establishing a display structure corresponding to the multiple subject matters based on the labeling information; and combining the multiple subject matters using the display structure to generate a target video. The present disclosure solves the technical problems of difficulties in automatic reconstruction and generation of video data from a product detail page in existing technologies.

Abstract: Techniques described herein provide for a live advertising processing engine service to act as an intermediary between client applications and advertising networks. The live advertising processing engine service can provide an interface with which the client can interact, via an application programming interface (API) or directly through the use of a standardized language, thereby allowing client applications to receive advertisement data without the need to be customized to communicate with specific advertising networks. The live advertising processing engine service can further track where, in playback the live content, a client currently is, to indicate to the client—or other application—when advertisement breaks are and/or provide supplemental advertisement information to enable the client to provide a rich user experience.

Abstract: Deep neural network (DNN) models have been widely used for user-relevance content prediction. Presented herein are embodiments of a new user-relevance framework, which may be referred as Gating-Enhanced Multi-task Neural Networks (GemNN) embodiments. Neural network-based multi-task learning model embodiments herein predict user engagement with content in a coarse-to-fine manner, which gradually reduces content candidates and allows parameter sharing from upstream tasks to downstream tasks to improve the training efficiency. Also, in one or more embodiments, a gating mechanism was introduced between embedding layers and multi-layer perceptions to learn feature interactions and control the information flow fed to MLP layers. Tested embodiments demonstrated considerable improvements over prior approaches.

Abstract: There is disclosed a method and system for selecting one or more targeted messages to be included within a web resource. The method comprises: receiving a first request for a targeted message, the request including a target context parameter and a target floor price; executing an MLA configured to generate a first confidence parameter vis-a-vis a first server and a second confidence parameter vis-a-vis a second server; transmitting a second request to a selected one of the first server and the second server based on the first confidence parameter and the second confidence parameter; receiving the targeted message from the selected on of the first server and the second server; transmitting the targeted message to the a web server for inclusion within the web resource.

Abstract: Candidate brands are identified for an ad clip of a query video advertisement using two different techniques. Optical character recognition (OCR) is performed on a thumbnail of a plurality of different video ads in a curated database that includes brand-identifying metadata. In one technique, text vectorization is performed for each brand using all of the text that is extracted from each of the thumbnails for each brand, thereby providing a numerical brand embedding for each brand, a similar text vectorization is performed on the query video ad, and then a comparison is made between the embeddings to identify highest-ranking candidate brands based on brand-level identification. In another technique, a transformer-based model generates numerical embeddings for each ad clip in the curated database, and a comparison is made to these clip-based numerical embeddings to identify highest-ranking candidate brands based on clip-level identification.

Abstract: Performance of a computer running a plan recognition application is improved by obtaining, with a user interface implemented on the computer, a specification of a plan recognition problem, including a plurality of candidate observations; formulating at least one planning problem, with the computer, based on the specification; solving the at least one planning problem, with the computer, to determine at least one plan. The at least one plan is post-processed, with the computer, to determine at least one of the candidate observations which should be selected to solve the plan recognition problem; and the plan recognition problem is solved, with the computer, using the at least one of the candidate observations which should be selected to solve the plan recognition problem. Less CPU time is typically required for the solution as compared to techniques without guidance for selecting the observations.

Abstract: The disclosed technology provides solutions for automatically generating customizable advertisements based on user preferred musical selection. In some aspects, a process of the disclosed technology can include steps for receiving a first video segment and a second video segment, receiving an audio file wherein the audio file comprises a musical selection corresponding with preferences of at least one user, and automatically editing the first video segment, based on the musical selection to produce a first edited segment. In some aspects, the process further includes operations for automatically editing the second video segment to produce a second edited segment, and automatically combining the first edited segment with the second edited segment and the musical selection. Systems and machine-readable media are also provided.

Abstract: Techniques described herein provide for a live advertising processing engine service to act as an intermediary between client applications and advertising networks. The live advertising processing engine service can provide an interface with which the client can interact, via an application programming interface (API) or directly through the use of a standardized language, thereby allowing client applications to receive advertisement data without the need to be customized to communicate with specific advertising networks. The live advertising processing engine service can further track where, in playback the live content, a client currently is, to indicate to the client—or other application—when advertisement breaks are and/or provide supplemental advertisement information to enable the client to provide a rich user experience.

Abstract: A method includes receiving project information indicating a location of a worksite. The method also includes providing a first travel path to an electronic device associated with a mobile machine, wherein providing the first travel path to the electronic device causes at least part of the first travel path to be displayed via a display. The method further includes receiving location information indicating an initial location of the machine and one or more additional locations of the machine. Additionally, the method includes determining that the machine reached the worksite, and identifying, based at least in part on the location information, a second travel path extending from the initial location to the worksite. The method further includes determining whether the second travel path matches the first travel path, and storing at least one of the travel paths in a memory associated with a controller.

Abstract: A non-transitory computer readable storage medium having an arrangement program according to the present application thereon causes a computer to execute an acquiring process and an arranging process. The acquiring process acquires browsing mode information that indicates a mode of browsing content. The arranging process arranges, in a mode based on the browsing mode information acquired at the acquiring process, at least one element that is used to judge whether the content has actually been browsed by a user in a content area in which the content is provided.

Abstract: Universal tags are placed on various web pages of a website. Unlike prior art action tags that indicate that an action has occurred, the universal tag sends a broader range of data capturing a user's experience on the website (e.g., whether an item was placed in a shopping cart, etc.) to a server. The server obtains an identity of the user from its own cookie on the user's device and stores the information received with the universal tag in connection with the user's account. A graphical user interface is used to define the information to be sent upon activation of the universal tag.

Abstract: The present invention is a method and system for evaluating relative effectiveness of content in a digital signage network, using a series of measurements to compare and evaluate different contents. The measurements are performed on a plurality of input images of the people captured by a plurality of means for capturing images in the vicinity of at least a digital signage. The present invention is a content rating system based on how the audience responds to the digital content in the intended context of digital media network in-store or in other public viewing areas. The present invention allows the measurement of the response to the content for different segments, further allowing for better planning of the content and optimizing the advertising dollars.

Abstract: Systems and methods are provided for determining the efficacy of digital assets provided to an audience. One embodiment is a system that includes a brand management server. The brand management server includes a memory that stores assets comprising digital media. The brand management server also includes a controller. The controller distributes the assets for consumption by members of an audience at remote devices. The controller also selects one of the assets, determines a look-back period, acquires metrics indicating at least two different types of consumption of the asset by the audience during the look-back period, and calculates an asset score for the asset that indicates a popularity of the asset and is based on the metrics indicating the at least two different types of consumption.

Abstract: A method and system to facilitate an online promotion in a network-based marketplace. A user-provided election to participate in the online promotion is recorded on a client machine associated with a user. Responsive to a trigger event, a determination of the user-provided election as recorded on the client machine associated with the user is made. The determination causes a presentation of the online promotion if so elected.