Abstract: Embodiments of the present disclosure generally relate to a content management system that automatically determines and generates topic clusters from a collection of electronic text documents. For example, the content management system analyzes a collection of electronic text documents to identify key terms and terms related to the key terms. Based on the key terms and related terms, the content management system generates a topic cluster that includes the key term and related terms. The content management system then organizes the electronic text documents based on terms within a given text document matching terms within a given topic cluster. Further, the content management system presents the topic clusters and organized electronic text documents to a user.

Abstract: The present embodiments provide an environment where a user first creates or imports a document comprising of fields to be completed by one or more users. All users who have view-only access or can act on a document are considered to be “in the workflow.” All users in the workflow (except view-only users) can take actions in the document by editing, adding or entering values or signatures in those fields. When the document is complete, a computing device adds an encrypted token visualization element to the document that uniquely identifies and secures the document. Thereafter, a copy of the original document, all attachments, authentication, security and validation information, and all other relevant information about the document and users will be available to view in the chain of custody and audit trail by the authorized users by scanning the token visualization element within the platform (web application or mobile application).

Abstract: A method for providing analysis data of a dynamic website is a method for providing analysis data, the method including the steps of: receiving visitor behavior analysis data of a dynamic webpage; identifying, from the dynamic webpage, an effective area corresponding to an effective element; acquiring, from the analysis data, event counter data corresponding to the effective area; on the basis of the event counter data, generating a heatmap representing analysis results of user behavior on the dynamic webpage; and synchronizing the generated heatmap onto the dynamic webpage, and outputting same.

Abstract: The techniques disclosed herein enable systems to provide intelligent snap assist recommendations using a diverse set of factors and factor weights. To generate recommendations, a system receives a user input placing a first item in a region of a snapped configuration in a display environment. In response, the system assigns a confidence score for a plurality of items including items open in the display environment as well as items that are not open. The system then ranks the items based on confidence score and selects a list of recommended items from the ranked list. The recommended items are then presented in a second region of the snapped configuration for selection. The system is further configured to receive and analyze user selections of snapped items to learn over time and adjust confidence scoring.

Abstract: A collection management system presents, as part of a content discovery session, a first content item from a content discovery collection that includes a plurality of content items that are ordered sequentially for presentation. In response to receiving an advancement input, the collection management system determines whether a number of content items presented as part of the content discovery session meets or exceeds a threshold number of content items, and whether an amount of elapsed time of the content discovery session meets or exceeds a threshold amount of time. The collection management system presents a first alternate content item as part of the content discover session. The first alternate content item is not included in the content discovery collection. After presenting the first alternate content item, the collection management system presents a second content item from the content discover collection that is ordered after the first content item.

Abstract: A system for executing a video summary is provided. One or more video segments for a video based on one or more digital media is generated. A video summary is generated based on a user request.

Abstract: A method including the following steps: receiving user input; resolving a feature of the input using a trainable algorithm, the trainable algorithm being trainable to resolve a feature by application of the algorithm to a dataset including a plurality of labelled dataset entries, the label of each labelled dataset entry describing a feature; wherein the trainable algorithm resolves the features in user input by identifying in the user input a dataset entry labelled with said feature; forming a UI that incorporates the resolved feature; presenting the formed UI; obtaining feedback in relation to the presented UI or a feature thereof; applying the feedback to train the trainable algorithm to resolve features of a UI, wherein feedback for training the trainable algorithm derives from any one or more of, or a combination of: user selection/validation/customisation of features presented to the user and/or user observation.

Abstract: In one aspect, a method includes while a first content-presentation device is performing a content-replacement operation in which the first content-presentation device outputs a replacement advertisement segment in place of an advertisement segment, determining, by a computing system, that the advertisement segment is not an expected modifiable advertisement segment. The method also includes in response to determining that the advertisement segment is not the expected modifiable advertisement segment, determining, by the computing system, that the advertisement segment is ineligible for replacement.

Abstract: Systems, and methods for selecting advertisements based on party size and/or engagement are provided. An Internet-connected media display device may be detected as displaying media. An up-to-date party size in a monitored space may be determined based on frequency response data by a wireless access point located close to the space. An up-to-date engagement level may also be determined with respect to each individual in the space based on frequency response data by the wireless access point. An advertisement database may be filtered for a qualifying advertisement based on the identified party size and engagement levels.

Abstract: A method, apparatus and computer program product are provided for parsing a message received from a requesting computer to identify an indication of a transaction, an entity identifier, and an identifier of a first evaluation system. The entity identifier is evaluated based on historical data and/or eligibility data to determine an alternative evaluation procedure. The alternative evaluation procedure is preformed to obtain response information regarding the transaction, that may differ from response information otherwise obtained via the first evaluation system. A response to the message is constructed that includes the response information and is transmitted to the requesting computer.

Abstract: An online system, such as a social networking system, generates shared models for one or more clusters of categories. A shared model for a cluster is common to the categories assigned to the cluster. In this manner, the shared models are specific to the group of categories (e.g., selected content providers) in each cluster while requiring a reasonable computational complexity for the online system. The categories are clustered based on the performance of a model specific to a category on data for other categories.

Abstract: A digital advertising system includes at least one processor configured to execute a plurality of functional modules including an analytics module to receive and analyze client attributes associated with a website visitor and a requested website to define an analytics event. The analytics module ingests and enriches data within the analytics event and provides it to a machine learning module that generates prediction models for potential bids. A management platform receives the bidding prediction and generates candidate configs. An optimization module receives the candidate configs and applies weights and additional features to select a config and generate an optimized script for the selected config. A deployment module receives the optimized script and delivers the script to the website visitor.

Abstract: Computer systems, methods and program products for automating pseudonymization of personal identifying information (PII) using machine learning, metadata, and crowdsourcing patterns to identify and replace PII. Machine learning models are trained for classifying known column names or key names for processing, using metadata. Column or key names are classified to be unprocessed, anonymized or pseudonymized by a pseudonymizer without revealing PII or scrubbing data into a useless format. A library of crowdsourced patterns are utilized for matching PII to data values within column or key names and PII is mapped to replacement methods. Feedback from user annotations retrains the algorithms to improve classification accuracy and Deep Learning algorithms automate the identification of PII using regular expression generation to concisely articulate how pseudonymizers search for PII patterns within a data set.

Abstract: Systems and methods are described herein for a media guidance application to determine that a user has switched away from a source transmitting a media asset with which the user was engaged and detect, while the user is switched away from the source, that secondary content transmitted by the source during a break of playback of the media asset relates to the media asset. In response to detecting that the secondary content relates to the media asset, the media guidance application may access a database to determine whether the secondary content specifically corresponds to the media asset, and, in response to determining that the secondary content specifically corresponds to the media asset, the media guidance application may generate for display the secondary content to the user.

Abstract: An information processing device generates web page data of a first window including a program causing a terminal device to execute an elapsed time determination process for obtaining first time information at a timing of a transition from the first window to a second window, obtaining second time information at a timing during which a process in the first window is executable in a state after the transition to the second window, calculating an elapsed time from a difference between the first time information and the second time information, and executing a predetermined process according to a comparison between the elapsed time and a threshold time. The information processing device executes a process for transmitting the web page data to the terminal device and causing the terminal device to present the web page data.

Abstract: The present disclosure provides a method and apparatus for determining an extended reading content, a device, and a storage medium, relating to the field of data processing. The method may include: displaying a target page, in response to a viewing request to the target page; giving a reading prompt to an extended reading resource in the target page, based on a corresponding relationship between a requirement recognition result of at least one target reading content in the target page and the extended reading resource; and displaying the extended reading resource, in response to the viewing request matching the reading prompt.

Abstract: A system and method for evaluating a subterranean earth formation as well as a method of steering a drill bit in a subterranean earth formation. The system comprises a logging tool that is operable to measure formation data and locatable in a wellbore intersecting the subterranean earth formation. The system also comprises a processor that is in communication with the logging tool. The processor is operable to calculate multiple distance-to-bed-boundary (DTBB) solutions using the measured formation data, identify DTBB solutions that satisfy a threshold, convert the identified solutions into pixelated solutions by dividing the identified solutions into pixels, generate a formation model based on the pixelated solutions, and evaluate the formation using the generated formation model.

Abstract: A device may obtain user information associated with a user and first account information associated with the user. The device may determine, based on the user information, user employment information and may determine, based on the first account information, user compensation information. The device may process, using a first machine learning model, the user employment information and the user compensation information to determine predicted future user compensation information. The device may obtain second account information associated with the user and may determine, based on the second account information, new user compensation information. The device may determine whether the new user compensation information is consistent with the predicted future user compensation information. The device may determine a predicted reason for the new user compensation information not being consistent with the predicted future user compensation information.

Abstract: In an embodiment, a method is performed by a computer system and includes intercepting machine learning (ML) input data before the ML input data flows into a ML model. The method also includes scanning the ML input data against a plurality of ML threat signatures, the scanning yielding at least a first result. The method also includes examining a correlation between values of first and second variables in the ML input data, the examining yielding at least a second result. The method also includes validating at least one of the first and second results via a variability analysis of error instances in the ML input data, the validating yielding at least a third result. The method also includes applying thresholding to the ML input data via the third result, where the applying thresholding results in at least a portion of the ML input data being filtered.

Abstract: A method, system and computer program product are provided. For each keyword that is visible on a display device, scanning the content that is stored on a user device, or is accessed from a network connection to identify and extract keywords. Further provided is cross-referencing the extracted keywords with a corpus of scored keywords. Based on the extracted keywords being found in the corpus of scored keywords, expanding and/or abridging any of the extracted keywords based on a score in the corpus of scored keywords prior to displaying the modified content on the display device. wherein the extracted keywords match a keyword in the corpus.

Abstract: Systems and methods to integrate point of sale processing, online order processing, and supply chain and store management over the Internet. In one aspect, a central server provides point of sale, online order processing, and supply chain and store management functions via browser based interfaces. The system enables users to enter orders from remote locations for order fulfillment at brick and mortar retail locations, where the POS terminals configured based on the browser based interfaces can be changed into a self service mode to allow customers to place orders for themselves at the retail locations.

Abstract: There are disclosed devices, system and methods for predicting a likelihood of whether digital video ads will start on a given user device using a predictive model of the user device. The predictive model simulates a start of play in the user device and determines if the digital video ad started to play.

Abstract: A method for providing analysis data of a dynamic website is a method for providing analysis data, the method including the steps of: receiving visitor behavior analysis data of a dynamic webpage; identifying, from the dynamic webpage, an effective area corresponding to an effective element; acquiring, from the analysis data, event counter data corresponding to the effective area; on the basis of the event counter data, generating a heatmap representing analysis results of user behavior on the dynamic webpage; and synchronizing the generated heatmap onto the dynamic webpage, and outputting same.

Abstract: A system and method for locking a charging port to charge an electric vehicle that includes determining that the electric vehicle is located within a predetermined distance of a charging station and determining when the charging port of an electric vehicle supply equipment of the charging station is attached to the electric vehicle to actively charge the electric vehicle. The system and method also include determining if the charging station accesses a parking citation associated with parking of the electric vehicle if the electric vehicle is not attached to the charging port. The system and method additionally include locking the charging port to the electric vehicle to disallow decoupling of the charging port from the electric vehicle by an unauthorized individual to avoid the parking citation.

Abstract: The present teaching relates to personalized content recommendation. A webpage is contrasted for a user having a plurality of slots each of which is to be allocated with a content item. For each of the plurality of slots, a plurality of content items in a plurality of types of content are accessed. For each of the plurality of types of content, a personalized score is predicted for each content item in the type of content, wherein the personalized score is obtained based on a trained model trained. A recommended content item of the type of content is selected based on personalized scores. An overall recommended content item is selected and allocated to a slot based on criteria associated with the personalized scores of the recommended content items and a business rule. The webpage with the plurality of slots allocated with content items is provided to the user.

Abstract: This disclosure describes techniques for generating curated In-Real Life (IRL) media data for distribution via third-party multimedia platform(s), and further providing an engagement entity (i.e., producer, merchant, or curator) with a recommendation to solicit an interaction with another engagement entity. Particularly, an IRL-Media Platform Analytics (IRL-MPA) system is described that can create curated IRL-media data by refining a presentation of raw IRL-media data, and further embedding product-service offerings and engagement requests. The IRL-MPA system may configure the curated IRL-media data for playback on one or more third-party platforms, such that a viewing audience member may respond to an engagement request embedded within the curated IRL-media data.

Abstract: Embodiments are disclosed for determining an answer to a query associated with a graphical representation of data. In particular, in one or more embodiments, the disclosed systems and methods comprise obtaining a visual embedding for a graphical representation of data, the visual embedding representing a plurality of graphical elements. The one or more embodiment further include obtaining a query embedding for a query associated with the graphical representation of data, the query embedding representing a plurality of textual elements of the query with at least one textual element substituted with an identifier for at least one graphical element of the set of graphical elements. The one or more embodiment further include generating a chart sequence from the visual embedding and a query sequence from the query embedding, generating an output sequence based on the graph and the query sequences, and determining an answer to the query from the output sequence.

Abstract: Embodiments disclosed herein select a content message to present to a user on a page of an application based on paralinguistic features of audio input received from the user for the application. The audio input is received via a microphone associated with a computing device. A feature extractor extracts paralinguistic features from the audio input. A predictive model determines a label indicating a measure of receptiveness to product placement (e.g., a predicted marketing outcome) based on the paralinguistic features. A content-selection component selects a content message to present to the user based on the label and based on a profile of the user.

Abstract: Embodiments of the present disclosure provide systems, methods, and computer storage media for implementing a nuanced-color search and recommendation system. Employing various techniques described herein, an improved search engine for categorizable items is provided to generate accurate color-based search results and recommendations that are relevant to a nuanced color provided as a search parameter. In various implementations, digital assets that depict categorizeable items can be analyzed to characterize the depicted items with, among other things, a particular shade of a determined dominant color. In this way, categorizeable items can be searched based at least in part on a selected shade of a particular dominant color to generate a primary search result. In further embodiments, other categorizeable items can be generated as recommendations based on characteristics of the primary search result.

Abstract: A server-side technique to detect and mitigate client-side content filtering, such as ad blocking. In operation, the technique operates on a server-side of a client-server communication path to provide real-time detect the existence of a client filter (e.g., an ad blocker plug-in) through transparent request exchanges, and then to mitigate (defeat) that filter through one or operations designed to modify the HTML response body or otherwise obscure URLs. Preferably, the publisher (the CDN customer) defines one or more criteria of the page resources being served by the overlay (CDN) and that need to be protected against the client-side filtering.

Abstract: A system includes at least one hardware processor and a memory storing instructions which, when executed, cause the hardware processor to perform operations including identifying a notification trigger configured by a user of a target computing device, the notification trigger including at least one trigger condition and notification content, the trigger condition references a value from a trigger data source and includes a condition based on the value, the notification content includes content provided by the user, receiving the value from the trigger data source, determining, based on the value, that the at least one trigger condition is satisfied, and presenting the notification content to the user on a target computing device associated with the user, the notification content is presented in a target content venue configured to present third-party advertisements to the user.

Abstract: The usefulness of content (target content), such as advertisements, may be increased by determining additional content and providing such additional content in association with the content. The target content may be text, a Web page, a URL, a search query, etc. The additional content might be related suggested queries (e.g. “Try a search for ______”), news articles (or excerpts or summaries thereof), reviews (or excerpts or summaries thereof), advertisements, user group messages, etc.

Abstract: Systems and methods include receiving, at a server, a content data and a set of timepoints relating to the content data and storing, by the server, the set of timepoints in a database. The method also includes sending, by the server, the content data and the set of timepoints to a portable device, generating, at the portable device, display signals based on the content data and sending display signals, by the portable device, to a display device that represent the content data. The method also includes receiving, by the server, a notification from the portable device over the internet. The notification indicates that the content data has reached a first time associated with a first timepoint of the set of timepoints.

Abstract: In an approach, a processor detects at least one training message delivered by a user on a social media application, the training message being accessible by an operator. A processor records training feedback performed by the operator on the social media application regarding to the at least one training message. A processor trains an analysis engine module using (i) the at least one training message as input and (ii) the training feedback as output. A processor generates a predicted feedback for a subsequent message based on the trained analysis engine module.

Abstract: Systems and methods for prefetching content items for display by applications executed on computing devices are provided. The method can include transmitting a first request for content to display within an environment of the application, the first request for content including a first parameter to be used to determine a first content item for display; storing in an associated memory element, the first parameter; transmitting a follow-on request for content including the first parameter of the first request for content; receiving a follow-on content item responsive to the follow-on request for content; storing the follow-on content item in a local cache structure specific to the application; transmitting a second request for content; retrieving, in response to the second request, the follow-on content item from the local cache structure; and displaying, in response to the second request, the follow-on content item within the environment of the application on the computing device.

Abstract: System for present content. The system includes means for receiving a set of timepoints relating to a content data and means for generating display signals based on the content data. The system also includes means for sending display signals to a display device that represent the content data and means for notifying a server over the Internet, that a timepoint among the set of timepoints has been reached in the content data. The system also includes means for receiving, from the server, via the Internet, an identification of one or more particular additional content and in response to receiving the identification of the one or more particular additional content from the server, means for interrupting presentation of the content data; and presenting the one or more particular additional content. The system further includes means for resuming, presentation of the content data after presenting the one or more particular additional content.

Abstract: Systems and methods are disclosed for associating a plurality of Internet-enabled devices with a common user profile for targeting Internet content or advertising. One method includes: receiving, from a plurality of Internet-enabled devices, a plurality of requests for electronic content or advertising; extracting, from each of the plurality of requests, a source IP address and a unique identifier associated with the respective Internet-enabled device; for each source IP address for which requests were received over a predetermined time period from a number of Internet-enabled devices below a threshold number of devices, identifying each possible pair of devices from which requests were received; and for each possible pair of devices, calculating a probability that the pair of devices are owned or operated by a common user.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to rectify false set top box tuning data. Disclosed examples methods include identifying in return path data a first group of set top boxes classified as likely to exhibit machine events in tuning data of the return path data more frequently than a second group of set top boxes represented in the return path data. Additionally, in some examples, the method includes determining whether the first group of set top boxes includes a machine event based on a pattern of the tuning data in the return path data for respective ones of the first group of set top boxes and improving an accuracy of return path data by rectifying the machine event.

Abstract: Technologies for template generation using directed acyclic word graphs (DAWGs). The technologies can include receiving a first plurality of titles from a first plurality of title feeds, and sorting the first plurality of titles into a plurality of category sets. And, for each category set of the plurality of category sets, the technologies can include transforming the respective titles belonging to the category set into a trie data structure by separating words in the respective titles into nodes of the trie data structure. For each category set, the technologies can also include transforming the trie data structure into a directed acyclic word graph (DAWG) data structure. Also, for each category set, the technologies can also include generating one or more unique templates based on the DAWG data structure.

Abstract: A digital advertising system includes at least one processor configured to execute a plurality of functional modules including an analytics module to receive and analyze client attributes associated with a website visitor and a requested website to define an analytics event. The analytics module ingests and enriches data within the analytics event and provides it to a machine learning module that generates prediction models for potential bids. A management platform receives the bidding prediction and generates candidate configs. An optimization module receives the candidate configs and applies weights and additional features to select a config and generate an optimized script for the selected config. A deployment module receives the optimized script and delivers the script to the website visitor.

Abstract: Systems and methods for providing a disposal recommendation for an owned vehicle are provided. The method includes generating a profile for the owned vehicle, the profile including age, mileage, and location of the owned vehicle, receiving monitoring data of the owned vehicle, and receiving sales data for non-owned vehicles corresponding to the profile. The method may further include generating predicted depreciation data of the owned vehicle, based on the sales data and the monitoring data, and providing a recommended disposal time for the owned vehicle, based on the predicted depreciation data.

Abstract: A method at a client device includes displaying media library information corresponding to a set of media items. The media items include one or more local media items, the one or more local media items including media items stored at the client device, and one or more remote media items, the one or more remote media items including media items stored at a remote system and not at the client device. The method also includes displaying, concurrently with displaying the media library information, affordances identifying the remote media items; detecting user interaction with an affordance identifying a respective remote media item; and in response to detecting the user interaction, initiating a process for downloading a copy of the respective remote media item to the client device for storage at the client device.

Abstract: Methods and systems for performing targeted advertising are described. Relative concentration of consumer types in the audience of particular media content is determined by measuring the coincidence of key values identifying certain consumer types, and other key values identifying audiences of particular media content, in a database.

Abstract: A method for augmenting message streams may comprise receiving a request for augmentation of a message, the request including a parameter associated with the message. The method may further include determining a rule associated with the message. The method may further include applying the determined rule to the message parameters to select an augmentation component. The method may further include transmitting an augmented message to the requestor, the augmented message including the augmentation component.

Abstract: The present teaching relates to obtaining a model for identifying content matching a query. Training data are received which include queries, advertisements, and hyperlinks. A plurality of subwords are identified from each of the queries and a plurality of input vectors for the plurality of subwords of each of the queries are obtained and an input vector for each of the queries is derived based on a plurality of input vectors of a plurality of subwords of the query. A query/ads model is optimized with respect to an objective function via training an input vector for each of the plurality of subwords associated with each of the queries, an input vector for each of the advertisements and links, and a matrix.

Abstract: The present disclosure discloses a method and apparatus for processing information. A specific embodiment of the method comprises: acquiring a target behavior information set; selecting, from at least two unique identity identifiers corresponding to at least two groups of identity identifiers, a unique identity identifier as a target unique identity identifier, based on at least one kind of specified user attribute information; and associating, for each target unique identity identifier of the selected target unique identity identifier, behavior information associated with identity identifiers corresponding to the target unique identity identifier with the target unique identity identifier, to obtain behavior information associated with the target unique identity identifier. According to the embodiment of the present disclosure, various kinds of behavior information of a user are associated with the target unique identity identifier, to facilitate utilization and analysis for the behavior information.

Abstract: An electronic device and method for replacing and outputting an advertisement are provided. The electronic device includes: a memory storing at least one program; a communication unit configured to receive context data to be used to determine a state of a user, from at least one external device; and a processor configured to replace and output an advertisement by executing the at least one program, wherein the at least one program includes instructions to: acquire user state information indicating the state of the user from the received context data, based on a learning model using one or more neural networks; and perform control to replace a previously determined first advertisement with a second advertisement determined based on the user state information and to output the second advertisement.

Abstract: Methods and apparatus for determining a unique audience exposed to media while reducing memory resources of a computing device are disclosed herein. An example apparatus includes means for logging a plurality of impressions based on impression requests from a plurality of client devices, the plurality of impressions corresponding to media accessed at the client devices; means for obtaining counts, the obtaining means to: obtain a count of demographic impressions logged by a database proprietor; and obtain a count of registered users of the database proprietor exposed to the media; and means for determining a unique audience size by: multiplying a count of the plurality of impressions by a square of the count of the registered users to generate a product; dividing the product by the count of the demographic impressions to generate a quotient; and determining the unique audience size based on a square root of the quotient.

Abstract: Improved identification of a computer configured with an operating system (OS), a web browser and one or more applications is disclosed. An identifying code for advertisers (IFA) may be obtained via the operating system (OS) of the computer. A first application configuring the computer may include instructions to initiate an ad call comprising a request including the IFA to cause the first application to render an advertisement received by the computing device from a first web resource in response to the ad call. The web browser may execute the script to configure the web browser with a durable id (DID). The web browser may also communicate the DID to associate the IFA with the computing device.

Abstract: An information processing apparatus, an information processing system, and an information processing method. The information processing apparatus detects a user, acquires schedule information of the user based on the detected user, and suggests one or more shared sites to use according to the schedule information.