Abstract: The disclosed embodiments describe methods, devices, systems, and computer-readable media for synchronizing streamlining multimedia files among client devices. In the various embodiments, multiple client devices are configured to adjust playback of live multimedia content to synchronize playback in combination with a video conference.

Abstract: One or more computing devices, systems, and/or methods are provided. Shaded bid values may be determined and/or submitted to one or more auction modules for participation in auctions. Auction information including at least one of minimum bid values to win associated with the auctions, sets of features associated with the auctions, the shaded bid values associated with the auctions, unshaded bid values associated with the auctions, etc. may be stored in a database. A machine learning model may be trained using a loss function and/or the auction information to generate a first machine learning model with feature parameters associated with features. A bid request, indicative of a second set of features, may be received. The first machine learning model may be used to determine a shaded bid value for submission based upon one or more first feature parameters, of the feature parameters, associated with the second set of features.

Abstract: Improved systems and methods for enhancing the performance of network based computerized content rendering and hosting and providing of devices, systems and/or platforms by modifying the capabilities and providing non-native functionality to such devices, systems and/or platforms through a novel and improved data processing and networking framework.

Abstract: One or more computing devices, systems, and/or methods for generating dynamic content item recommendations are provided. Content item information, extracted from message data, is aggregated to calculate popularity and attributes of content items. The content items are ranked based upon the popularity and attributes to generate a ranked list of content items. Exploration traffic is served utilizing a set of eligible content items selected from the ranked list of content items. An eligible content item is promoted for participation in auctions for serving non-exploration traffic based upon the eligible content item being served a threshold number of times.

Abstract: Disclosed are embodiments for providing batch performance using a stream processor. In one embodiment, a method is disclosed comprising receiving an event, such as a streaming event, from a client. The method determines that the event comprises a primary event and, if so, writes the primary event to a cache and returning the primary event to the client. The method later receives a second event from the client, the second event associated with the first event, annotates the second event based on the primary event, and returns the annotated second event to the client.

Abstract: Briefly, embodiments of methods and/or systems of generating preference indices for contiguous portions of digital images are disclosed. For one embodiment, as an example, parameters of a neural network may be developed to generate object labels for digital images. The developed parameters may be transferred to a neural network utilized to generate signal sample value levels corresponding to preference indices for contiguous portions of digital images.

Abstract: One or more computing devices, systems, and/or methods for content recommendations using historical future data are provided. A model serving delay time is computed as an average of training delays of events. A historical data time interval is determined based upon the model serving delay time. A model is trained for predicting user content preferences using historic user distribution data and historic content distribution data associated with the historic data time interval. The model is utilized to generate and provide content recommendations to users.

Abstract: Systems and methods are disclosed for utilizing a comment moderation bot for detecting and normalizing neologisms in social media. One method comprises transmitting, by a neologism normalization system, a comment moderation bot for detecting neologisms on an online platform maintained by one or more publisher systems. The comment moderation bot may aggregate data related to user comments and transmit the aggregated data to the neologism normalization system for further processing. The neologism normalization system implements unsupervised machine learning models for detecting neologisms in the aggregated data through tokenization and filtering; and normalizing the neologisms through similarity analysis and lattice decoding.

Abstract: Managing electronic addresses based on communication patterns. A method includes tracking metadata of a plurality of electronic communications of a user. One or more lists of electronic addresses of recipients are generated for the user based on the metadata. Electronic addresses of potential recipients are identified from the one or more lists in response to an input indicative of selection of an electronic address of a recipient. The identified electronic addresses are recommended to the user. An input indicative of one or more electronic addresses selected by the user from the identified electronic addresses is received. Further, an electronic message is sent to the selected electronic addresses.

Abstract: One or more computing devices, systems, and/or methods are provided. A machine learning model may be trained using a plurality of sets of information. One or more pruning operations may be performed in association with the training to generate a machine learning model with sparse vector representations associated with features of the plurality of sets of information. A request for content associated with a client device may be received. A set of features associated with the request for content may be determined. A plurality of positive signal probabilities associated with a plurality of content items may be determined using the machine learning model based upon one or more sparse vector representations, of the machine learning model, associated with the set of features. A content item may be selected from the plurality of content items for presentation via the client device based upon the plurality of positive signal probabilities.

Abstract: One or more computing devices, systems, and/or methods for future event recommendation are provided. For example, messages of a user account of a user are parsed to identify messages corresponding to events attended by the user. Event features are extracted from the messages, where an event feature is descriptive of an aspect of an event. An event database of future events is queried using the event features to identify future events having one or more of the event features. A description of the future events is constructed and provided to the user.

Abstract: Event logs in a video advertisement insertion network are processed to remove duplicate entries. One or more ad servers are continuously generating new event entries and writing them to a database. The entries are randomized such that generated time contiguous entries are distributed over multiple storage locations, thereby facilitating resource scaling and a uniform use of storage and computing resources. The distributed entries are read from the storage locations using sequential reads of chunks of the entries and processed to remove duplicate entries.

Abstract: Allocating bids for providing content within a segmented campaign is controlled to ensure that an event rate associated with the provided content meets or exceeds a threshold rate. A campaign-level event rate, associated with the provided content, is estimated and provided as a feedback signal. This feedback signal is employed to dynamically update bid allocations for each of the segments, which in turn varies the number or rate of provided impressions and events. Such feedback enables the control of the campaign-level rate and ensures that the campaign-level rate meets or exceeds the rate threshold. To control these rates, the number of total impressions, as well as the number of associated events, is temporally sampled across the campaign segments. Based on the number of impressions and events, the campaign-level event rate is estimated and employed as the feedback signal. Updating the bid allocations may be based on the Beta Distribution.

Abstract: The present teaching relates to system, method, and programming for indexing user records. A plurality of user records are obtained, wherein each user record is associated with a user identifier and one or more data-segments. For each data-segment, one or more user identifiers associated with the data-segment are determined, a relative distance of each user identifier with respect to a previous user identifier associated with the data-segment is computed, and a variable number of bits to be used to store the relative distance of each user identifier in a bit stream are determined based on a criterion associated with the relative distance. Offset values are generated for the one or more data-segments, wherein an offset value of a data-segment indicates an index of the bit stream where information of a first user identifier associated with the data-segment is stored.

Abstract: The present teaching relates to a method and a system for advertising. The method obtains information about a conversion associated with an advertisement and generates with respect to the conversion, an operational smart attribution evaluation package (SAEP). The SAEP includes a conversion parameter and a reward. The method transmits the SAEP to a platform to be posted, and thereafter receives from the SAEP, an indication of an entity which is estimated to be associated with the conversion and to which the reward is to be allocated. The entity is determined by the SAEP based on the conversion parameter and information from a plurality of entities that displayed the advertisement.

Abstract: The present teaching relates to method, system, medium, and implementations for identifying k nearest neighbors. One or more KNN lists corresponding to one or more source data points are received. Each KNN list includes K neighbors of a source data point and each of the K neighbors is a data point represented by an index. Neighbor pairs and reverse neighbor pairs are generated based on the one or more KNN lists. The neighbor pairs and reverse neighbor pairs having the same source data point are grouped to generate a grouped pairs of neighbors for the source data point. A local join operation is performed based on grouped pairs of neighbors for each source data point to generate a combined neighborhood for the source data point, which is then sent to a KNN server, where combined neighborhoods generated by multiple local join executors are integrated to update a plurality of global KNN lists.

Abstract: A method is provided, including: storing comments generated in response to a content item served over a network; analyzing the comments to determine features associated with each of the comments; using a scoring model to score each comment based on the comment's corresponding features; receiving a request to serve a subset of the comments; responsive to the request, selecting a ranking of the comments that is one permutation from possible rankings of the comments, wherein selecting the ranking is in accordance with a probability distribution of the possible rankings that is based on the scores of the comments; serving comments identified by the selected ranking over the network to a client device; determining a dwell time on the served comments; applying the dwell time to update the scoring model.

Abstract: Disclosed are systems and methods for improving interactions with and between computers in content providing, searching and/or hosting systems supported by or configured with devices, servers and/or platforms. The disclosed systems and methods provide a novel framework for performing automatic detection of surfaces in video frames resulting in the creation of a seamless in-video ad experience for viewing users. The disclosed framework operates by leveraging available surfaces in videos to show advertisements in compliance with publisher protection, compliance and policy in a fully automatic, end-to-end solution. The disclosed framework evidences a streamlined, automatic and computationally efficient process(es) that modifies digital content at the surface level within the frames of the content in compliance with the digital rights of the owners of the content being merged via the disclosed augmentation.

Abstract: Technologies for selectively streaming video based on mapping buffer data to download rates. The technologies can include sampling download rates of a video player prior to or during downloading of a first video segment to the video player. The technologies can include determining a range of download rates of the video player based at least on the sampled download rates. The technologies can include determining an amount of accumulated video data in a buffer of the video player immediately prior to or during the downloading of the first video segment. Also, the technologies can include mapping the determined amount of accumulated video data to a download rate within the determined range of download rates using a mapping function, and determining a second video segment quality for a second video segment based at least on the mapped download rate.

Abstract: One or more computing devices, systems, and/or methods are provided. Activity of a plurality of devices may be analyzed to identify network traffic. A network profile associated with the plurality of devices may be generated based upon the network traffic. The network profile may be indicative of one or more sets of transmission metrics associated with a first device of the plurality of devices. The network profile may be indicative of one or more sets of reception metrics associated with the first device. Content may be generated based upon the network profile. The content may be transmitted to a device based upon the network profile.