Abstract: A BLUETOOTH low energy mobile payments system may comprise a BLE beacon that is deployed at a merchant location. The BLE beacon may be associated with a specific merchant terminal. The BLE beacon may be configured to broadcast a unique beacon ID that is detectable by a user device. The user device may be configured to communicate the beacon ID to a payment system. In response to receiving the beacon ID, the user device may initiate a payment between a user and a merchant, via a user device and a merchant terminal.

Abstract: In some aspects, the techniques described herein relate to a method including: generating, by a processor, verification data; encoding, by the processor, the verification data within a base avatar using a steganography algorithm to generate an augmented avatar; and transmitting, by the processor, the augmented avatar to a recipient.

Abstract: An information processing method includes: causing a display to display: an advertisement within a game that is different from another advertisement for the game, and a question related to the advertisement in response to displaying the advertisement; calculating a degree of scrutinization according to an answer to the question received from a player of the game, the degree of scrutinization indicating a degree to which the player has scrutinized the advertisement; providing a content that the player uses in the game based on the display of the advertisement: and prioritizing the player to whom the controller provided the content based on the degree of scrutinization.

Abstract: A server connected to a network performs processing of: receiving first information transmitted from a first information terminal connected to the network and transmitting the first information to a second information terminal connected to the network; receiving second information that is information transmitted from the second information terminal and includes the first information, and generating print data based on the second information; and transmitting the print data to a plurality of printing devices connected to the network.

Abstract: Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.

Abstract: Systems and methods for generating secondary content item that includes a first portion that is a reminder of the original interest and a second portion that is content relevant to the original interest are disclosed. The methods provide primary content for the user's consumption. User interest based on a plurality of factors, such as user's gaze, heartbeat, or facial expression, is determined during the user's consumption of the primary content. One or more objects or frames are identified as primary objects or frames of interest. The methods also scan in real-time, real-life objects that are in the field of view of an augmented reality device. A determination that the real-time object is related to the primary object of interest is made. A determination is also made if any environmental or local adjustments need to be made. A secondary content item with any environmental or local adjustments is generated.

Abstract: Embodiments of the present disclosure provides a real-time crowd measurement and management system including data capturing devices installed in a plurality of zones for continuously capturing crowd data of a plurality of crowds in a plurality of zones. The system also includes an analysis module for identifying crowd characteristics from the crowd data; analyzing the crowd data to determine one or more patterns and changes in mood of the plurality of crowds; and predicting crowd information comprising emergent crowd characteristics, an emergent crowd behaviour of the crowds, and one or more issues based on the analysis in real-time. The system also includes a display module for displaying the predicted crowd information along with at least one of an alert and at least one indicator in real-time.

Abstract: A method, a computer program, an apparatus, a transportation vehicle, and a network entity for predicting a deadlock situation for an automated transportation vehicle. The deadlock situation is an exceptional traffic situation necessitating a change of an operational mode of the transportation vehicle. The method for predicting a deadlock situation for the automated transportation vehicle includes obtaining information related to a historical deadlock situation cause, determining historical context information for the historical deadlock situation cause, determining information indicative for the deadlock situation cause based on the information related to the historical context information, monitoring actual context information for information indicative for the deadlock situation, and predicting the deadlock situation based on the information indicative for the deadlock situation in the actual context information.

Abstract: Systems and methods are described for presenting supplemental information to a user that is related to an advertisement consumed by the user that the user found interesting. It may be determined that a user is interested in receiving supplemental information based on the user starting to use a device within a threshold time period from consuming the advertisement on a different device. The threshold time period may be determined based on historical amounts of time users have taken to access supplemental information after consuming the advertisement (e.g., if users access a webpage associated with the advertisement five minutes after the conclusion of the advertisement, the threshold time period may be five minutes). In response to determining that the user started using the first device within the threshold period of time from the end of the advertisement, supplemental information associated with the advertisement may be presented.

Abstract: The exemplary embodiments relate to devices, systems and methods for a streaming service to provide fast video stream startup at a user device. The streaming service may determine that a video stream for on-demand content is to be provided to the user device and is to include multiple subclips corresponding to the on-demand content and a dynamic content insertion opportunity (DCIO). A first set of multimedia data is transmitted to the user device that corresponds to a first subclip of the on-demand content. When a predetermined condition corresponding to the DCIO is satisfied, a second set of multimedia data is transmitted to the user device that includes multimedia data corresponding to at least the multiple subclips.

Abstract: A system and method are provided for executing a notification service.

Abstract: Techniques for enhancing actionable opportunities through machine learning are disclosed. In some embodiments, a system includes an event listener for detecting an opportunity to perform an action using one or more computing resources. When a new opportunity is detected, the system generates a set of search criteria, which is used to search a set of external web resources for current events. The system may then generate, using a machine learning model as a function of one or more features extracted from current events satisfying the search criteria, a score representing a likelihood of success that the action leads to an optimal result. The system may tune the machine learning model based on feedback received that is indicative of how the current events affected the likelihood of success for the action.

Abstract: An immersive content presentation system can capture the motion or position of a performer in a real-world environment. A game engine can be modified to receive the position or motion of the performer and identify predetermined gestures or positions that can be used to trigger actions in a 3-D virtual environment, such as generating a digital effect, transitioning virtual assets through an animation graph, adding new objects, and so forth. The use of the 3-D environment can be rendered and composited views can be generated. Information for constructing the composited views can be streamed to numerous display devices in many different physical locations using a customized communication protocol. Multiple real-world performers can interact with virtual objects through the game engine in a shared mixed-reality experience.

Abstract: Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.

Abstract: Computer-implemented methods, computer systems, and computer readable media for determining, sorting, or determining and sorting a set of items. The method includes receiving, via a user device, parameter values from a user and receiving parameter weights. The method further includes determining a sort score for each vehicle of a set of vehicles based on the received parameter values and parameter weights, and sorting the set of vehicles based on the sort score of each vehicle of the set of vehicles.

Abstract: Systems, methods, and machine-readable media for facilitating the following operations are disclosed. A first content composite that is configured with a containerization object may be transmitted. The containerization object may be configured with one or both of containerization specifications and a container flag to facilitate performance of operations by an endpoint media device with respect to the first content composite. The first content composite may include a set of one or more audio and/or video packets corresponding to audio and/or video content. One or more communications corresponding to one or more indications of one or more detected operations associated with the endpoint media device may be received consequent to the endpoint media device performing the operations. Based at least in part on the one or more communications, a set of observation data mapped to the endpoint media device and the first content composite may be aggregated.

Abstract: Systems and methods are provided for dynamically adjusting notification frequency for a sporting event. During a sporting event, information related to the sporting event is received. A first level of interest of a user in the sporting event is determined. A performance metric of a competitor in the sporting event is determined. A second level of interest of the user in receiving notifications relating to the sporting event is generated as a function of the first level of interest and the performance metric. In response to determining that the second level of interest exceeds a notification frequency threshold, a notification is presented for the user that includes the information related to the sporting event when the information is received during the sporting event.

Abstract: Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.

Abstract: A system for enabling in store routing of a user generated shopping list using existing store cameras and artificial intelligence and machine learning is provided. The system uses a pixelbuffer comparison of items imaged in real time to compared to a database of machine learned images. The system further provides item recognition and detection through machine learning so as to improve a shoppers experiences. The system and method further includes drone assistance means and radio signal item and biological detection so as to improve accuracy. Other features to improve guidance and accuracy include landmark navigation and masking to improve accuracy of item recognition and detection.

Abstract: A system for enabling in store routing of a user generated shopping list using existing store cameras and artificial intelligence and machine learning is provided. The system uses a pixelbuffer comparison of items imaged in real time to compared to a database of machine learned images. The system further provides item recognition and detection through machine learning so as to improve a shoppers experiences. The system and method further includes drone assistance means and radio signal item and biological detection so as to improve accuracy. Other features to improve guidance and accuracy include landmark navigation and masking to improve accuracy of item recognition and detection. The system may be a standalone kiosk.

Abstract: The disclosed exemplary embodiments include computer-implemented systems, apparatuses, and processes that, among other things, provide a marketplace platform accessed within various application environments, such as a gaming environment associated with a video game. The market platform automatically determines product advertisements that appropriate for presentation within the gaming environment based on an application of trained machine learning and artificial intelligence models to selected elements of input data, and facilitates a purchase of advertised products without a user's exit from the gaming environment by maintaining centralized elements of profile data characterizing the user.

Abstract: Example methods and systems for inserting information into playing content are described. In some example embodiments, the methods and systems may identify a break in content playing via a playback device, select an information segment representative of information received by the playback device to present during the identified break, and insert the information segment into the content playing via the playback device upon an occurrence of the identified break.

Abstract: An online system receives information describing a target group of online system users from a third party system that includes one or more user properties, which may identify an action performed by a an online user within a time interval to include the user in the target group. When an opportunity to present advertisement requests to a user is identified, the online system retrieves actions associated with the user and times associated with the actions. If an action associated with the user matches the action identified by the user properties and occurred within the time interval identified by the user properties, and other characteristics of the user satisfy at least a threshold number of the user properties, the online system includes the user in the target group. Advertisement requests having targeting criteria, including the target group, satisfied by characteristics of the user are evaluated for presentation to the user.

Abstract: System and methods are provided to create representations of geographic areas. Such representations enable users to search for items and services of interest and to quickly locate and utilize such items and services. Representations are created using user preferences thus reducing the amount of information presented to a user, i.e., user preferences control the contents of a representation. Control APIs contained within a representation may be used to control devices represented in a representation or to manufacture them using 3-D printing technologies. Methods to learn user preferences via his movements and other actions and impose a user's preferences upon an environment are shown. Some details of the invention are described by applying the invention to problems in retail marketing and figures depicting an implementation illustrate certain aspects of the invention.

Abstract: Systems and methods that provide electronic bidding on digital advertising placed on non-personal digital devices in public or semi-public settings and enable subsequent consumer actions taken on other media channels and devices to be attributed to such advertising in digital ad buying systems.

Abstract: An example computing device is configured to determine (i) a future start time of an upcoming live media event and (ii) a uniform resource indicator (URI) at which a live media stream of the live media event will be accessible at the future start time. The computing device displays, via the graphical user interface, a notification identifying the upcoming live media event, and the computing device receives, via the graphical user interface, (i) a first selection of the displayed notification and (ii) a second selection of a plurality of playback devices of a media playback system. Based on the first and second selections, the computing device causes, at the start time of the live media event, at least one of the plurality of playback devices to access the live media stream at the URI for synchronous playback by the plurality of playback devices.

Abstract: In one embodiment, a system, is provided to take not just a person's time and location into consideration, but also has knowledge of and takes into account their availability, their preferences, their schedule, their purpose for being at their current location, and/or their next goal or stop. One embodiment is able to take into account a real-time view of supplier inventory and deduce and make available much better-adapted offerings and support for that person's travels and endeavors. In one embodiment, having an understanding of a rate of conversion and its relation to traffic and weather patterns allows service providers to make more accurate predictions about various items, including but not limited to, conversion rates, offer types, offer upgrades, traffic etc. In yet another aspect of the invention, the information collected from many travelers, and also information collected from airlines and weather observers, etc.

Abstract: The exemplary embodiments relate to devices, systems and methods for a streaming service to provide fast video stream startup at a user device. The streaming service may determine that a video stream for on-demand content is to be provided to the user device and is to include multiple subclips corresponding to the on-demand content and a dynamic content insertion opportunity (DCIO). A first set of multimedia data is transmitted to the user device that corresponds to a first subclip of the on-demand content. When a predetermined condition corresponding to the DCIO is satisfied, a second set of multimedia data is transmitted to the user device that includes multimedia data corresponding to at least the multiple subclips.

Abstract: Systems and methods for providing notification delivery based on utilization of bloom filters are provided. A collaboration system obtains subscriber information for each user of a collaboration system, whereby the subscriber information corresponds to one or more features of content that are relevant to each user. The collaboration system hashes the subscriber information to generate a bloom filter for each user. The collaboration system receives an article to be published, whereby the article comprises a set of features. The set of features is hashed to obtain a hash set. The hashing of the set of features is performed using same hashing functions as that used to generate the bloom filter. The collaboration system compares the hash set to the bloom filter to identify a match, whereby the match indicates a feature of the article matches the subscriber information. The collaboration system generates a list of recipients based on the match.

Abstract: The disclosed embodiments generally relate to systems, methods, and apparatus for dynamic context-based electronic offer communication. In one aspect, a computer server is disclosed, comprising: a hardware processor configured to execute instructions stored in a memory to: receive location data from a mobile device; determine a context of the mobile device based on the location data; generate a database query using the determined context; send the generated query to an events database; receive a conditional electronic offer from the events database; determine user data requirements based on the conditional electronic offer; send a request based on the user data requirements to a secure server; receive user data from the secure server; generate an electronic offer communication based on the conditional electronic offer when the user data received from the secure server meets the user data requirements; and send the electronic offer communication to the mobile device.

Abstract: A system provides interactive and automated features to aid in planning, management, and execution of events within venues. Venue hardscapes are geolocated, parsed, and stored to be used when configuring events. During event configuration a venue softscape may be automatically generated and applied to the venue hardscape to produce an initial layout. The initial layout may be modified to create and assign booths to exhibitors by multiple coordinators in parallel. Geolocation of hardscaped may be extended into softscapes, such that location data may be maintained for temporary structures such as booths. Conflicts may be avoided by implementing one or more conflict prevention features, including enforcement of universal layouts, booth locking, synchronous session management, automatic identifier assignment to preserve locational correspondence, booth and layout validation, and others.

Abstract: Methods, systems and computer program products are provided for prefetching information and/or (pre)allocating computing resources based on predicting classification labels with temporal data. A trained temporal classification model forecasts events (e.g., too numerous for individual modeling) by predicting classification labels indicating whether events will occur, or a number of occurrences of the events, during each of a plurality of future time intervals. Time-series datasets, indicating whether events occurred, or a number of occurrences of the events, during each of a plurality of past time intervals, are transformed into temporal classification datasets. Classifications may be based, at least in part, on extracted features, such as data seasonality, temporal representation, statistical and/or real-time features. Classification labels are used to determine whether to take one or more actions, such as, for example, prefetching information or (pre)allocating a computing resource.

Abstract: Example methods and systems for inserting information into playing content are described. In some example embodiments, the methods and systems may identify a break in content playing via a playback device, select an information segment representative of information received by the playback device to present during the identified break, and insert the information segment into the content playing via the playback device upon an occurrence of the identified break.

Abstract: An image processing apparatus obtains virtual viewpoint information indicating at least a position of a virtual viewpoint and a view direction from the virtual viewpoint and generates a virtual viewpoint image based on the virtual viewpoint information and a plurality of images captured from a plurality of viewpoints by hiding processing a specific region of the virtual viewpoint image, the specific region being determined based on that the obtained virtual viewpoint information satisfies a condition.

Abstract: A method and system for providing a device with audio data, the method comprising the steps of: receiving from a device a request for audio data, wherein the request is received while the device is rendering a digital work, the digital work including video data. Determining audio data to send to the device in response to the request. Sending the determined audio data to the device together with computer readable instructions, wherein the computer readable instructions cause the device to: while continuing the rendering of the digital work on the device, suspend playback of first audio data currently playing on the device and playing the received audio data on the device. When the received audio data stops playing continuing with the rendering of the digital work on the device and resume playback of the first audio data previously playing on the device.

Abstract: Systems, methods, and machine-readable media for adapting content items to device operations of an endpoint media device are disclosed. A first content composite may be created by one or more processing devices for delivery in a packet stream from a content provider system via one or more networks, where the first content composite may include an adaptable content item corresponding to a set of one or more audio and/or video packets corresponding to audio and/or video content. The first content composite may be transmitted, where, consequent to delivery of the first content composite to a first endpoint media device or a second endpoint media device, the first endpoint media device or the second endpoint media device may perform one operation relating to a second content item of the first content composite, where the adaptable content item may be modified based on the second content item.

Abstract: In one embodiment, the instant disclosure provides a portable computing device that includes at least: a processor; a non-transient computer media; computer instructions, and where, when the processor executes the computer instructions, the portable computing device is programmed to: transmit an electronic request to establish a user session related to an event, where the electronic request includes a user-specific event-specific identifier that is uniquely related to a user and the event; display, during the user session, an user-specific app-like graphical user interface including: a first interface area displaying a text-based content related to the user-specific event-specific identifier and the event, a second interface area displaying a live virtual event content related to the user-specific event-specific identifier and the event, a graphical user interface element that has been programmed to automatically execute a user-specific action related to the event when a user activates the graphical user inte

Abstract: The present teaching relates to method, system, and medium for determining audience clusters to be assigned to an advertisement exposure opportunity. A plurality of advertisement exposure opportunities are obtained, wherein each of the plurality of advertisement exposure opportunities is to be used for placing an advertisement. For each of the plurality of advertisement exposure opportunities, a plurality of audience clusters are generated based on at least one criterion associated with the advertisement exposure opportunity. The plurality of audience clusters are ranked based on at least one ranking criterion, and ordered audience clusters are generated based on the ranking. The ordered audience clusters associated with the plurality of advertisement exposure opportunities in response to an event are updated, wherein the ordered audience clusters for each of the plurality of advertisement exposure opportunities are generated prior to receiving a request for placing the advertisement.

Abstract: A system configured controls access to data associated with a venue-centric event. The system may include one or more hardware processors configured by machine-readable instructions. The processor(s) may be configured to receive from a first remote server a set of first data items associated with a first authenticated event application and store the set of first data on the local appliance. Second data items are received from a second remote server, at least some of the second data items are different from the first data items and thereby form a set of third data items. A request for at least one of the second data items is received from the first authenticated event application and validated. The request may be received after the predetermined start time and before the predetermined end time. The requested at least one second data item is communicated to the first authenticated event application.

Abstract: A computer system that is adapted for: (A) displaying a geographical map on a display screen; (B) displaying a plurality of icons on the geographical map, each of which generally represents the current location of at least one individual; (C) allowing a user to select a group of the icons; and (D) after the user selects the group of icons, providing messaging functionality for allowing the user to send a common message to the respective portable computing devices of at least substantially all of the individuals who correspond to the selected group of icons. In particular embodiments, the system allows the user to send the message by executing a single activity, such as selecting a single button. The system may also be configured to approximate the current location of an individual based on the individual's current travel itinerary.

Abstract: Systems, methods, and machine-readable media for adaptive content splicing with respect to content corresponding to a televised event are disclosed. First content may be received and may be determined to correspond to an event that is televised. One or more indicators of one or more state changes with respect to the event may be detected. A content composite may be created. An adaptable content item received from a first system may be processed. A content object re may be processed. The adaptable content item may be modified based at least in part on the content object to form the content composite. The creating the content composite may be a function of rules mapped to a current geolocation. Second content corresponding to the programming content may be received. The second content may be output for display in conjunction with the content composite.

Abstract: System, computer-readable medium, and methods are provided to determine interest areas of an event held at a venue location. A communication interface of a server device may receive a search request for an event, where the search request includes event data indicating a venue location of the event. An interest processing component of the server device determines an excitement interest in the event based on at least one of the event data and interest data of a user account. An area processing component of the server device determines one or more excitement areas at the venue location based at least on the excitement interest in the event. A ticket processing component of the server device determines one or more available event tickets for the event at the venue location based at least on the one or more excitement areas at the venue location.

Abstract: A method for a frame certainty metric for automatic content recognition. The method includes determining a frame match between media device frames of a media device stream relative to broadcast frames of a broadcast media stream and determining whether to shift the frame match by determining the following: a first frame certainty metric based on a first media device fingerprint and a target broadcast fingerprint; a second frame certainty metric based on a second media device fingerprint sequentially adjacent the first media device fingerprint and the target broadcast fingerprint; a third frame certainty metric based on a third media device fingerprint sequentially adjacent the first media device fingerprint and the target broadcast fingerprint; and a greatest frame certainty metric. The method further includes identifying the media device fingerprint corresponding to the greatest frame certainty metric as a target media device fingerprint matching the target broadcast fingerprint.

Abstract: Example methods and systems for inserting information into playing content are described. In some example embodiments, the methods and systems may identify at a playback device, content by comparing a fingerprint of the real-time content to reference fingerprints, each of the reference fingerprints corresponding to different media, identify, at the playback device, a break in the real-time content playing via the playback device based on the identification of the real-time content, select an information segment to present during the break based on information captured by a location determination component, and insert the information segment into the real-time content playing via the playback device upon an occurrence of the break.

Abstract: Methods and systems are described for providing advertising services to devices with a customized adaptive user experience. In one embodiment, a system includes a user interface (UI) configurator to provide a custom scripting framework to create and edit customizable ad formats for display on a device. The ad system receives an ad request from the device with the ad request including different types of information including publisher settings of a selected software application on the device, an application id to identify the selected software application, placement information for timing placement of at least one ad or interstitial ad to be displayed on the device. The ad system processes the ad request to determine an ad format and timing placement of the at least one ad or interstitial ad based on the information contained in the ad request.

Abstract: A system and method for selecting inventory pricing for an event at a venue is disclosed. The method comprising determining a rate at which a first inventory of seats have sold for an event at a venue. The method further comprising calculating a demand for a secondary inventory of seats as a function of the rate at which the first inventory of seats sold, the seats of the first and second inventories being comparable in quality, provides a user interface to one or more client devices that displays the data. The method further comprising calculating a demand for a second inventory of seats as a function of the rate at which the first inventory of seats sold, the seats of the first and second inventories being comparable in quality.

Abstract: The present disclosure discusses systems and methods to mitigate traffic spikes in retrieving secondary content items for display in concurrently streamed content streams. The system can pre-fetch secondary content items for the upcoming secondary content slots. To retrieve an appropriate content item, the system can predict the length of the secondary content slot. The system can use the predicted length of the secondary content slot to distribute the traffic spike over a larger span of time to mitigate the spike.

Abstract: A system includes a smart table for a wagering game and which is configured to use radio-frequency identification (RFID)-enabled chips and RFID sensors. The smart table includes a processor configured to open a wagering window for a game round of the wagering game at the smart table, receive a secondary wager from a secondary player computing device for the game round, the secondary wager is placed on an outcome of a primary player during the game round, validate the secondary wager relative to a state of the wagering window, automatically detect the outcome of the primary player during the game round based on input received from the at least one RFID sensor, and resolve the secondary wager for a secondary player based on the detected outcome of the primary player.

Abstract: A system and method for displaying seat inventory at a venue and facilitating planning of ticket prices for events at the venue is presented. Methods to predict total revenue for an event are described. Also presented are systems and methods for determining at what price and when to release so-called ‘flex’ price tickets during an on-sale using the sales velocity and sales/inquiry ratios. Determining demand of seats from secondary markets is also described with methods to use the demand for either repricing the seats in the primary market or presenting ‘best value’ seats to a prospective purchaser.

Abstract: A method of providing cross-media event linking may include: receiving, at a first input of an event coreferencing system, a stream of social media postings, and at a second input, a stream of news articles; generating, by the event coreferencing system, a first set of event representations representing events referenced by the social media postings, and a second set of event representations representing events referenced by the news articles; determining, by the event coreferencing system, that at least one of the social media postings references a same event referenced by at least one of the news articles, the determining including determining at least one similarity using data of at least one of the first set of event representations corresponding to the at least one of the social media postings and data of at least one of the second set of event representations corresponding to the at least one of the news articles; and transmitting, by an output of the event resolution system to the user system, an alert