Systems and methods for generating intelligent overlays for interactive displays

Abstract

The technology described herein relates to a computer-implemented method for generating smart overlays in an interactive display. The method can include receiving a plurality of real-time event data comprising a plurality of real-time event actions; receiving a plurality of user data comprising a plurality of user actions; capturing one or more real-time user interactions with the interactive display; generating a unique relevance threshold using the plurality of real-time event actions, the plurality of user actions, and the one or more real-time user interactions upon receiving the plurality of real-time event data and the one or more real-time user interactions; generating, in real-time, at least one unique smart overlay having a relevance that exceeds the unique relevance threshold; and updating, in real-time, the interactive display with the at least one unique smart overlay.

Description

Cross-references to related applications

[0001] This application claims priority to U.S. Provisional Application Serial No. 63 / 549,235, filed February 2, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0002] Various embodiments of the present invention generally relate to computer-implemented techniques for generating interactive displays, and more particularly, to systems and methods for generating intelligent overlays for interactive displays. Background Technology

[0003] User interfaces that display content irrelevant to the user can significantly hinder the user experience. Users may struggle to identify essential information in a cluttered layout with too many elements. Irrelevant content can also obscure key actions or information, reducing the usability and effectiveness of the interface. Prioritizing user needs can alleviate one or more of these challenges.

[0004] Unless otherwise stated herein, the techniques and information described in this section are not prior art for the purposes of the claims in this application and are not recognized as prior art or suggestions for prior art. Summary of the Invention

[0005] In some aspects, the technology described herein relates to a computer-implemented method for generating smart overlays in an interactive display. The method may include receiving multiple real-time event data comprising multiple real-time event actions. The method may also include receiving multiple user data comprising multiple user actions. The method may further include capturing one or more real-time user interactions with the interactive display. The method may further include generating a unique relevance threshold using the multiple real-time event actions, the multiple user actions, and the one or more real-time user interactions. The unique relevance threshold can be generated in real-time upon receiving the multiple real-time event data and the one or more real-time user interactions. The method may further include generating in real-time at least one unique smart overlay whose relevance may exceed the unique relevance threshold. The method may further include updating the interactive display having at least one unique smart overlay in real-time.

[0006] In some aspects, the technology described herein relates to a system for generating smart overlays in an interactive display. The system may include a memory storing instructions and a processor operatively connected to the memory and configured to execute the instructions to perform operations. Operations may include receiving multiple real-time event data comprising multiple real-time event actions. Operations may also include receiving multiple user data comprising multiple user actions. Operations may further include capturing one or more real-time user interactions with the interactive display. Operations may further include generating a unique correlation threshold using the multiple real-time event actions, the multiple user actions, and the one or more real-time user interactions. The unique correlation threshold can be generated in real-time upon receiving the multiple real-time event data and the one or more real-time user interactions. Operations may further include generating in real-time at least one unique smart overlay whose correlation may exceed the unique correlation threshold. Operations may further include updating the interactive display having at least one unique smart overlay in real-time.

[0007] In some aspects, the technology described herein relates to a non-transitory computer-readable medium storing instructions that, when executed by one or more processors, perform a method for generating a smart overlay in an interactive display. The method may include receiving multiple real-time event data comprising multiple real-time event actions. The method may also include receiving multiple user data comprising multiple user actions. The method may further include capturing one or more real-time user interactions with the interactive display. The method may further include generating a unique relevance threshold using the multiple real-time event actions, the multiple user actions, and the one or more real-time user interactions. The unique relevance threshold can be generated in real-time upon receiving the multiple real-time event data and the one or more real-time user interactions. The method may further include generating in real-time at least one unique smart overlay whose relevance may exceed the unique relevance threshold. The method may further include updating the interactive display having at least one unique smart overlay in real-time. Attached Figure Description

[0008] To gain a detailed understanding of the above-described features of the invention, a more specific description of the invention, which has been briefly summarized above, can be obtained with reference to the embodiments, some of which are illustrated in the accompanying drawings. However, it is worth noting that the drawings only show typical embodiments of the invention and should therefore not be considered as limiting its scope, as the invention may recognize other equally effective embodiments.

[0009] Figure 1 A block diagram illustrating a computing environment according to an example embodiment is depicted.

[0010] Figure 2 A flowchart is depicted for a method of generating smart overlays in interactive displays.

[0011] Figures 3A to 3LAn embodiment of a smart overlay displayed within an interactive display is described.

[0012] Figure 4 A flowchart for training an artificial intelligence model according to an example embodiment is depicted.

[0013] Figures 5A to 5B A block diagram illustrating a computing device according to an example embodiment is depicted.

[0014] For ease of understanding, the same reference numerals are used where possible to denote common elements in the figures. It is contemplated that elements disclosed in one embodiment may be advantageously used in other embodiments without specific description. Detailed Implementation

[0015] According to the techniques and systems disclosed herein, overlays can be dynamically generated and displayed on video streams (e.g., live video streams, broadcast video streams, etc.). Overlays can include various sports information, such as, but not limited to, player information, match information, team information, and sports information. Such information can be generated based on sports data, such as event data and / or tracking data. Event data and / or tracking data can be generated based on in-field streams or broadcast streams. Event data and / or tracking data can be generated, for example, using one or more machine learning models trained to output such data based on inputs, including in-field streams, broadcast streams, labeled data, etc.

[0016] Overlays can be partially transparent, allowing the video stream to be seen through them. Overlays can be interactive, allowing users (e.g., users of a user device) to select an overlay or a subset thereof (e.g., buttons, icons, etc.). This interaction can allow users to take odds-based actions (e.g., make market predictions, perform fantasy sports moves). Overlays can be dynamically determined based on event data and can provide odds-based options based on that data. Potential market predictions can be automatically generated based on event actions associated with the sports corresponding to the video stream. These predictions can be provided to the user device for display via the overlay using the device's graphical user interface (GUI). For example, an event action associated with a sporting event could be a corner kick for a given team. Based on the identification of this event action via associated event data, market prediction options associated with the corner kick (e.g., whether a goal will be scored) with associated odds can be generated. Market prediction options can be provided via the overlay, allowing users to select a market prediction before taking the corner kick. By selecting this market prediction option, a secondary overlay or a new interface can be provided to the user to confirm the market prediction, provide or display information associated with it, etc.

[0017] The location and / or content of the overlay can be determined based on event data, as discussed herein. The location of the overlay can be dynamic, such that, for example, it can change based on variations in camera angle, viewpoint, player movement, team, team in possession of the ball, match actions (e.g., goals, kicks, penalty kicks, passes, points, blocks, time-based attributes, etc.). Similarly, the content of the overlay can be dynamic, such that, for example, it can change based on variations in camera angle, viewpoint, player movement, team, team in possession of the ball, match actions, player attributes, player statistics, time-based attributes, etc.

[0018] Additionally, user interactions can be captured and processed by a publicly available computing system to determine various aspects of interactive displays and / or smart overlays. These aspects can include how the interactive displays and / or smart overlays are displayed within the user interface (e.g., positioned within the user interface), when they are displayed (e.g., after user interaction and / or combined with real-time sports data, etc.), what content is displayed (e.g., within the interactive display and / or smart overlay), etc. Therefore, interactive displays and / or smart overlays can be updated and / or generated "instantly" by the computing system based on captured user interactions. In one example, if a user is making market predictions via interactive displays and / or smart overlays, additional relevant and / or related content can be presented to the user via the interactive display, smart overlay, or by presenting additional smart overlays determined to be relevant to the user interaction. Therefore, interactive displays and / or smart overlays can be customized for each unique user based on user-specific input.

[0019] Figure 1 This is a block diagram illustrating a computing environment 100 according to an example embodiment. The computing environment 100 may include a tracking system 102 (e.g., located at or in communication with one or more components, the one or more components being located at a site 106), an organization computing system 104, and one or more client devices 108 communicating via a network 105.

[0020] Network 105 can be of any suitable type, including a separate connection via the Internet, such as a cellular or Wi-Fi network. In some embodiments, network 105 can use a direct connection to connect terminals, services, and mobile devices, such as Radio Frequency Identification (RFID), Near Field Communication (NFC), Bluetooth™, Bluetooth Low Energy™ (BLE), Wi-Fi™, ZigBee™, Ambient Backscatter Communication (ABC) protocol, USB, WAN, or LAN. Because the transmitted information may be personal or confidential, security concerns may require encryption or other protection of one or more of these types of connections. However, in some embodiments, the transmitted information may be less personal, and therefore, the network connection may be chosen for convenience rather than security.

[0021] Network 105 may include any type of computer networking arrangement for exchanging data or information. For example, network 105 may be the Internet, a private data network, a virtual private network using a public network, and / or other suitable connections that enable components in computing environment 100 to send and receive information between components of environment 100.

[0022] Tracking system 102 may be located within field 106 and / or may communicate with components located at field 106 (e.g., electronic communication, wireless communication, wired communication, etc.). For example, field 106 may be configured to host a sporting event including one or more actors 112. Tracking system 102 may be configured to capture the movement of one or more actors (e.g., players) on the playing field, as well as the movement of one or more other related actors (e.g., objects) (e.g., a ball, hockey, referees, etc.). In some embodiments, tracking system 102 may be an optical-based system using, for example, multiple fixed cameras, movable cameras, one or more panoramic cameras, etc. For example, a system consisting of six calibrated cameras (e.g., fixed cameras) may be used to project the three-dimensional positions of the players and the ball onto a two-dimensional top view of the playing field. In another example, a combination of fixed and non-fixed cameras may be used to capture the movement of all actors on the playing field, as well as the movement of one or more related objects. Using such a tracking system (e.g., tracking system 102), many different camera views of the playing field can be generated (e.g., high sideline view, free throw line view, convergence view, face-off view, end zone view, etc.).

[0023] In some embodiments, tracking system 102 can be used for a broadcast signal source for a given match. For example, tracking system 102 can be used to generate match file 110 to facilitate a broadcast signal source for a given match. In such embodiments, each frame of the broadcast signal source can be stored in match file 110. The broadcast signal source can be a signal source formatted for broadcasting over one or more channels (e.g., broadcast channels, internet-based channels, etc.). Match file 110 can be converted from a first format (e.g., a format output by one or more cameras or a format different from the format output by one or more cameras) and can be converted to a second format (e.g., for broadcast transmission).

[0024] In some embodiments, the game file 110 may also be enhanced with other event information corresponding to the event data, such as, but not limited to, game event information (pass, shot made, turnover, etc.) and background information (current score, remaining time, etc.). According to embodiments, the event data may be generated manually or may be generated in real time by a computing system (e.g., within approximately 30 seconds of the event occurring), as discussed herein. The computing system may generate the event data by, for example, analyzing tracking data (e.g., from tracking system 102) and / or one or more other data types, such as video signal sources, excitement data, etc. The computing system may utilize machine learning models to determine when a given set of tracking data or a change in tracking data (e.g., a given player movement, object movement, its change, etc.) corresponds to an event (e.g., a score event, a free throw event, a ball possession-based event, a game type event, etc.). Event data may be automatically identified using machine learning, which is trained to receive the game file 110 or a subset thereof as input and output game information and / or background information based on the input. According to the techniques disclosed herein, the machine learning model may be trained using supervised, semi-supervised, or unsupervised learning. Machine learning models can be trained by analyzing training data using one or more machine learning algorithms, as disclosed in this paper. Training data may include match files or simulated match files from historical matches, simulated matches, etc., and may include labeled and / or unlabeled data.

[0025] Tracking system 102 can be configured to communicate with organizational computing system 104 via network 105. For example, tracking system 102 can be configured to provide real-time or near-real-time broadcast streams of matches or events to organizational computing system 104 via network 105. As an example, tracking system 102 can provide one or more match files 110 in a first format (e.g., a format corresponding to a component based on tracking system 102). Alternatively or additionally, tracking system 102 or organizational computing system 104 can convert the broadcast stream (e.g., match file 110) from the first format to a second format. The second format can be based on organizational computing system 104. For example, the second format can be a format associated with data storage device 118, as discussed further herein.

[0026] The organization computing system 104 can be configured to process broadcast streams of matches. The organization computing system 104 may include at least a network client application server 114, a tracking data system 116, a data storage device 118, a live match reporting module 120, a filling module 122, and / or an interface generation module 124. Each of the tracking data system 116, the live match reporting module 120, the filling module 122, and the interface generation module 124 may include one or more software modules. One or more software modules may be a set of code or instructions stored on a medium (e.g., the memory of the organization computing system 104) representing a series of machine instructions (e.g., program code) that implement one or more algorithm steps. Such machine instructions may be the actual computer code that the processor of the organization computing system 104 parses to implement the instructions, or alternatively, may be higher-level instruction encoding that is parsed to obtain the actual computer code. One or more software modules may also include one or more hardware components. One or more aspects of the example algorithm may be executed by the hardware component (e.g., circuitry) itself, rather than as a result of instructions.

[0027] The tracking data system 116 can be configured to receive broadcast data from the tracking system 102 and generate tracking data based on the broadcast data. In some embodiments, the tracking data system 116 may employ artificial intelligence and / or computer vision systems, which are configured to derive player tracking data from broadcast video signal sources.

[0028] To generate tracking data based on broadcast data, the tracking data system 116 may, for example, map pixels corresponding to each player and ball to points, and may transform these points into a semantically meaningful event layer that can be used to describe player attributes. For example, the tracking data system 116 may be configured to capture broadcast video received from the tracking system 102. In some embodiments, the tracking data system 116 may also classify each frame of the broadcast video into trackable and untrackable clips. In some embodiments, the tracking data system 116 may also calibrate moving cameras based on trackable and untrackable clips. In some embodiments, the tracking data system 116 may also use skeletal tracking to detect players within each frame. In some embodiments, the tracking data system 116 may also track and re-identify players over time. For example, the tracking data system 116 may re-identify players who are not in the camera's line of sight during a given frame. In some embodiments, the tracking data system 116 may also detect and track objects across multiple frames. In some embodiments, the tracking data system 116 may also utilize optical character recognition (OCR) technology. For example, the tracking data system 116 may utilize OCR technology to extract score information and remaining time information from the digital scoreboard for each frame.

[0029] These technologies help the tracking data system 116 generate tracking data based on the broadcast signal source (e.g., broadcast video data). For example, the tracking data system 116 can perform these processes to generate tracking data across thousands of ball-handling and / or broadcast frames. In addition to these processes, the organizational computing system 104 can go beyond generating tracking data based on broadcast video data. Instead, to provide descriptive analysis and useful feature representations for the interface generation module 124, the organizational computing system 104 can be configured to map tracking data to a semantic layer (e.g., events).

[0030] The tracking data system 116 can be implemented using a machine learning model. According to the techniques disclosed herein, the machine learning model can be trained using supervised, semi-supervised, or unsupervised learning. The machine learning model can be trained by analyzing training data using one or more machine learning algorithms, as disclosed herein. Training data may include match files or simulated match files from historical matches, simulated matches, historical or simulated feature representations, etc., and may include labeled and / or unlabeled data. Labeled data may include location information, movement information, object information, trends, actor identifiers, actor re-identifiers, etc.

[0031] The live game reporting module 120 can be configured to receive live game reporting data from one or more third-party systems. For example, the live game reporting module 120 can receive live game reporting signals corresponding to broadcast video data. In some embodiments, the live game reporting data can represent manually generated data based on events that occur during the game. Although the goal of computer vision technology is to capture all data directly from the broadcast video stream, in some cases, the referee is the final decision-maker regarding the successful outcome of an event. For example, in basketball, whether a shot is a two-pointer or a three-pointer (or valid, traveling, defensive / offensive foul, etc.) is determined by the referee. Therefore, to capture these data points, the live game reporting module 120 can utilize machine learning outputs and / or manually annotated data that reflects the referee's final decision. Such data can be referred to as a live game reporting signal source.

[0032] To aid in identifying events in the generated tracking data, the tracking data system 116 can merge or align live game reporting data with the newly generated tracking data (which may include game and time fields). The tracking data system 116 can utilize a fuzzy matching algorithm that combines live game reporting data, optical character recognition data (e.g., shot clock, score, remaining time, etc.), and the position of the game / ball (e.g., the original tracking data) to generate aligned tracking data.

[0033] Once aligned, the tracking data system 116 can be configured to perform various operations on the aligned tracking system. For example, the tracking data system 116 can use live game reporting data to refine the positions of players and the ball, as well as the precise frames of end-of-possession events (e.g., shot / rebound positions). In some embodiments, the tracking data system 116 can also be configured to automatically detect events from the tracking data. In some embodiments, the tracking data system 116 can also be configured to enhance events with contextual information.

[0034] For automated event detection, the tracking data system 116 may include a neural network system trained to detect / refine various events in a sequential manner. For example, the tracking data system 116 may include an actor-action attention neural network system to detect / refine one or more of the following: shooting, scoring, points, rebounding, passing, dribbling, free throws, fouls, and / or ball possession. The tracking data system 116 may also include a large number of specialized event detectors trained to identify higher-level events. Exemplary higher-level events may include, but are not limited to: tactics, transitions, pressure, crosses, getting past defenders, back-to-the-basket moves, drives, isolation plays, on-ball screens, offsides, handoffs, off-ball screens, etc. In some embodiments, each of the specialized event detectors may represent a neural network specifically trained to identify a particular event type. More generally, such event detectors can utilize any type of detection method. For example, specialized event detectors may use neural network methods or another machine learning classifier (e.g., random decision forest, SVM, logistic regression, etc.).

[0035] While mapping tracking data to events can capture player representation, the tracking data system 116 can generate contextual information to enhance detected events in order to further construct the best possible player representation. Exemplary contextual information may include defensive matchup information (e.g., who is guarding whom in each frame, defensive formation), as well as other defensive information such as defensive coverage of screens or pressures on the ball.

[0036] In some embodiments, to measure influence, the tracking data system 116 may use a metric called an "influence score." An influence score captures a player's influence on every other player on the opposing team and ranges from 0 to 100. In some embodiments, the value of the influence score may be based on sports principles such as, but not limited to, proximity to a player, distance to a scoring object (e.g., the basket, goal, boundary, etc.), gap closure rate, passing routes, routes to the scoring object, etc.

[0037] The imputation module 122 can be configured to use mean regression to create new player representations to reduce random noise in the features. For example, one of the deep challenges of modeling using only data from a potentially limited number of matches per player (e.g., 20-30 matches) may be the high variance of low-frequency events seen in the tracking data. Therefore, the imputation module 122 can be configured to utilize an imputation method, which could be a weighted average between the observations and the sample mean.

[0038] Therefore, for each player, the tracking data system 116, the live match reporting module 120, and the filling module 122 can work together to generate a raw dataset and a filled dataset for each player.

[0039] Interface generation module 124 can be configured to generate overlays and / or interactive displays using data received by tracking data system 116. In various embodiments, interface generation module 124 can be configured to generate overlays and / or interactive displays based on video signal sources (e.g., broadcast signal sources, in-field signal sources), tracking data, and / or event data. Interactive displays may include at least one graphical representation of one or more of the aspects described herein. In various embodiments, interactive displays are generated in real time when data is received (e.g., by tracking data system 116).

[0040] Data storage device 118 can be configured to store one or more match files 126. Each match file 126 may include video data for a given match. For example, the video data may correspond to multiple video frames captured by tracking system 102, tracking data derived from broadcast video generated by tracking data system 116, live match reporting data, enriched data, and / or padded training data. Match file 126 may be based, for example, on match file 110 as discussed herein. Match file 126 may have a different format than match file 110. For example, a first format of match file 110 or a subset thereof may be transformed into a second format of match file 126. The transformation may be performed automatically based on the type and / or content of the first format and the type and / or content of the second format.

[0041] Client device 108 can communicate with organizational computing system 104 via network 105. Client device 108 can be operated by a user. For example, client device 108 can be a mobile device, tablet, desktop computer, or any computing system with the capabilities described herein. Users can include, but are not limited to, individuals such as, for example, subscribers, clients, potential clients, or customers of an entity associated with organizational computing system 104, such as individuals who have received, will receive, or may receive products, services, or advice from an entity associated with organizational computing system 104.

[0042] Client device 108 may include at least one application 130. Application 130 may represent a web browser that allows access to websites or may be a standalone application. Client device 108 may access application 130 to access one or more functions of organizational computing system 104. Client device 108 may communicate via network 105 to request web pages, for example, from network client application server 114 of organizational computing system 104. For example, client device 108 may be configured to execute application 130 to generate smart triggers. Content displayed to client device 108 may be transferred from network client application server 114 to client device 108 and subsequently processed by application 130 for display via graphical user interface (GUI) of client device 108.

[0043] Figure 2 A flowchart depicts a method 200 for generating a smart overlay in an interactive display. In step 205, multiple real-time event data are received. The multiple real-time event data may include real-time event actions. These actions may include at least one of scoring a goal, completing a pass, intercepting, conceding a goal, or no action. Real-time sports event data (e.g., player data, match data, team data, performance data, trend data, etc.) can be combined with user data, market forecast data, etc., to provide personalized smart overlays (e.g., via live stream, video source, etc.). Real-time event data may be generated and / or provided based on video sources (e.g., broadcast sources, in-field sources), tracking data, and / or event data. For example, tracking data can be generated (e.g., based on the content source) by converting visual and / or audio elements of a content source into digital depictions of actors (e.g., players) and / or objects (e.g., a ball, hockey, etc.). The movement, trends, actions, and / or predicted versions of the actors and / or objects can be correlated with the event type to determine when a given movement, trend, action, or predicted version corresponds to an event. For example, the numerical representation of an object (e.g., a ball) crossing a boundary (e.g., a goalpost) can lead to the determination of a goal-scoring action.

[0044] In step 210, multiple user data are received. Multiple user data may include multiple user actions. In this example, user data may include data associated with a user profile, historical interactions between the user and the platform or software modules as described herein, the type and / or category of user interactions, historical market predictions of the user, the type and / or category of historical market predictions of the user, user preferences (e.g., user-selected preferences and / or user preferences learned by machine learning and / or artificial intelligence models, such as user preferences for sports teams or players), etc.

[0045] In step 215, one or more real-time user interactions with the interactive display can be captured. In various embodiments, real-time user interactions can be captured by recording or tracking system events such as clicks, cursor movements, text input, haptic input, screen unlocking, voice input, speech-to-text input, etc. Such interactions can also be associated with timestamps and stored (e.g., in data storage device 118, such as...). Figure 1 (as shown), or it can be fed as a data stream (e.g., when user interaction occurs in real time) to an interface generation module (such as interface generation module 124, as shown). Figure 1 (As shown). Therefore, one or more real-time user interactions can inform the interface generation module of real-time updates to the user interface. In the example, such updates to the user interface can include highlighting elements, adding elements, removing elements, repositioning icons or elements, etc. In step 220, a unique relevance threshold can be generated using multiple real-time event actions, multiple user actions, and one or more real-time user interactions. The unique relevance threshold can be generated in real-time as multiple real-time event data and one or more real-time user interactions are received. For example, pricing information (e.g., associated with market forecasts, selections, teams, sports, etc.), sports event data (e.g., associated with sports statistics, insights, ratings, and / or predictive metrics, such as those generated using artificial intelligence) and / or user data (e.g., user profiles, user actions previously taken on market forecasts, user market forecasts, user favorites, price ranges, etc.) can be integrated to provide user-specific, personalized smart overlays. In the example, a machine learning or artificial intelligence model can determine the unique relevance threshold by analyzing rating metrics and correlating user data. For example, metrics such as fundamentality, retrieval, and contextual precision can be used to assign scores based on the alignment of one or more previous smart overlays with user interactions and context. In another example, threshold calibration can improve the independent relevance threshold by setting a "cutoff" value to classify the output as relevant or irrelevant to the user. In yet another example, features highly relevant to user needs and preferences can be identified by machine learning or artificial intelligence models using rank correlation, decision trees, etc.

[0046] In various embodiments, smart overlaps can be customized by an operator (e.g., an entity or automated system providing content via smart overlaps). In examples, smart overlaps can be provided based on events occurring in a real-time match (e.g., in a live video feed or broadcast), such as goals, shots, fouls, offsides, corner kicks, passes, tackles, etc. Smart overlaps generated and displayed in the user interface can include information about individual player statistics, the total number of teams with relevant statistics (e.g., relevant to the user), and augmented metrics determined using artificial intelligence or machine learning models, such as shifts in the game, major scoring opportunities (e.g., before a scoring opportunity that significantly impacts the probability of winning), major scoring opportunity conversion rates, etc. In other examples, insights can be displayed as smart overlaps based on various triggers (e.g., user interactions, changes in independent correlation thresholds, events occurring in a real-time match, etc.). In some embodiments, an operator (e.g., an automated system) can turn triggers on / off; for example, they can turn off triggers associated with a tackle when the operator is not providing market information about it.

[0047] In step 225, at least one unique smart overlap with a correlation exceeding a unique correlation threshold can be generated. The collected and / or generated data that can be used to generate one or more overlaps and / or interactive displays may include user data (e.g., a user's favorite team, the number of market predictions made by the user for the team, market prediction history, etc.), event data (e.g., scores of players or teams that changed the context or potential prospects of a match), background data (e.g., excitement data collected through smart ratings, such as increased interactions within a predetermined time period, etc.), and transaction triggers (e.g., previous successful interactions with similar overlaps, such as market predictions made, etc.).

[0048] According to embodiments of the disclosed subject matter, intelligent overlay may include providing sports event data and / or information generated based on sports event data via a content stream, such as a sports signal source or via sports stories. Such a content stream can be accessed via a user device (e.g., an application with an interface providing sports-related content). The content stream may include content selected based on the integration of pricing information, sports event data, and / or user data. Therefore, the content stream may include content relevant to a given user. The content stream may also be populated with supplementary content (e.g., advertising content) based on user data and / or sports event data.

[0049] In step 230, an interactive display with at least one unique smart overlay can be updated in real time. The interactive display can be displayed on a user's mobile device. In an example, the at least one unique smart overlay can be an interactive interface overlaid on a live video stream on the user's device. In various embodiments, the position of the at least one unique smart trigger within the interactive display can be automatically determined based on one or more of multiple real-time event actions, multiple user actions, one or more real-time user interactions, and camera angles of the live video stream. For example, the smart overlay can be arranged, reordered, updated, etc., relative to the interactive display, relative to one or more other smart overlays, or relative to the live video stream, based on the relevance of the smart overlay, or the camera angles of multiple real-time event actions, multiple user actions, one or more real-time user interactions, and / or the live video stream. Therefore, the at least one unique smart overlay can be generated and / or updated based on one or more of multiple real-time event actions, multiple user actions, one or more real-time user interactions, and / or camera angles of the live video stream. In another aspect, the interactive display can be updated in real time based on multiple real-time event actions, multiple user actions, and / or one or more real-time user interactions.

[0050] In various embodiments, the unique smart overlay can push information to users based on events occurring on the field, on the court, etc. Alternatively, users can decide when they want to collect information, which may affect how the smart overlay updates in real time. In various embodiments, performance metrics can be generated using one or more artificial intelligence and / or machine learning models. Such performance metrics can be updated and displayed in real time via one or more smart overlays. For example, players can be ranked according to real-time performance metrics. Clicking on a player in the smart overlay in an interactive interface or on the device screen allows the user to collect more details about individual statistics contributing to that player's performance metrics. Users can also interact with one or more market predictions associated with the real-time video stream and performance metrics (e.g., via the smart overlay).

[0051] Figures 3A to 3LExamples of smart overlays displayed within an interactive display are described. As discussed herein, overlays (e.g., smart overlays) can be provided on video streams. For example, a smart overlay can provide sports statistics and / or other sports-related information on a video stream of a corresponding sporting event. In such an example, sports data (e.g., event data) can be overlaid onto a video stream (e.g., live video). The sports data can be related to players, matches, team-based statistics, etc. In various embodiments, the overlay graphical representation of the data can be interactive. A portion of the displayed data can be selected (e.g., clicked), which may result in the generation of a new overlay display and / or redirection to a new video, webpage, etc. In other examples, interacting with a smart overlay display can allow a computing system to collect data or information from a user, allowing the user to make market predictions, etc. The interactions presented in the smart overlay display can present relevant information in real time. For example, opportunities to make market predictions related to a match broadcast live via a video stream can be presented. In one example, a user can be prompted to make a market prediction about the outcome of an upcoming corner kick during a broadcast via a smart overlay display. In another example, a smart overlay display can be used in the context of fantasy sports prediction.

[0052] In various embodiments, the location of the smart overlay display can be determined based on detected event data. In this way, the smart overlay display can not obstruct the user's view of the game. The computing system can use various methods to utilize the analysis of event data and / or visual data to determine how to display the smart overlay display based on the real-time game. According to embodiments, the computing system can analyze the video signal source in real time to determine critical and non-critical information regions. A machine learning model can classify all or a subset of the video signal source (e.g., each frame) into critical or non-critical regions. Such classification can be output by a machine learning model trained to perform such classification based on historical or simulated video or content signal source data, marked critical regions, marked non-critical regions, etc. The overlay module or other components can identify the optimal non-critical regions for displaying the smart overlay so that critical regions are not obscured by the overlay. For example, the overlay module can score each non-critical region using a machine learning model (e.g., the same machine learning model that classifies critical and non-critical regions or a separate machine learning model). The score can be based on factors such as the size of the display area associated with each non-critical region, the salience of the non-critical region, and the proximity of the non-critical region to the corresponding information of the smart overlay to be displayed. Smart overlays can take on various formats based on the game, user preferences, and the data or interactions to be displayed. Additionally, users can choose to hide the smart overlay (e.g., for a period of time).

[0053] In various embodiments, intelligent overlays can be dynamically generated, allowing content to be sorted or otherwise displayed based on live event data associated with sporting events. The content to be displayed, the location of the content, and / or the position of the overlay can be output by a machine learning model, as discussed herein. For example, the machine learning model can receive one or more of the following as input: sporting event data, video streams associated with the sporting event data, player information, team information, etc. The machine learning model can be trained using historical or simulated event data, overlay information, etc. The machine learning model can be based on input / output location information, content, market forecast information, fantasy sports information, etc.

[0054] like Figure 3A As shown, a smart overlay 304 can be displayed on video stream 302. The smart overlay may, for example, include interactive market prediction options, allowing users to interact with overlay 304 to select these options. As discussed herein, the smart overlay 304 can be dynamically generated. A secondary interface 306 can also be dynamically generated during the generation of the smart overlay 304. The secondary interface 306 can be populated to provide supplementary information to the smart overlay 304. For example, as... Figure 3A As shown, the smart overlay 304 can provide market forecasts related to the predicted number of corner kicks associated with a sporting event displayed via video stream 302. The secondary interface 306 can be populated to include sporting event data related to the market forecast options of the smart overlay 304. In various embodiments, the interactive display with the smart overlay can be displayed on a mobile device, such as... Figure 3B As shown in image 308, interactive displays and smart overlays can be displayed on any type of user device, such as mobile devices, desktop or laptop computing devices, televisions, smartwatches, tablets, etc.

[0055] As described herein, the positioning of smart overlays and / or interactive displays on the display of a computing device can be relative to other elements, and therefore the positioning of the smart overlay or elements within the smart overlay can be determined in real time based on other factors, such as a live video signal source. Figure 3C As shown in image 310, the interactive display or smart overlay is positioned at the bottom center of the screen so that the smart overlay does not obstruct the viewing of the broadcast (e.g., a football match). Figure 3D As shown in image 312, the interactive display or smart overlay is positioned at the bottom right of the screen (e.g., as in a tennis match broadcast). Figure 3E As shown in Figure 314, interactive displays or smart overlays can be positioned alternatively at the top center of the screen during tennis broadcasts, depending on the positioning of one or more display elements in the broadcast.

[0056] As described herein, interactive displays may include one or more smart overlays. Figure 3F As shown in image 316, the intelligent overlay depicting "team statistics" can be displayed as an overlay of the live video signal source. According to... Figure 3F In the example shown, users can switch between "Team Statistics" and "Player Statistics," where the interactive display updates to show "Team Statistics" based on the user's action of selecting "Team Statistics" via a toggle element. Figure 3G As shown in image 318, after a user interacts with the smart overlay, the interactive display can be updated using a smart overlay that displays additional content or information (e.g., full screen). Figure 3H As shown in image 320, the intelligent overlay depicting "player statistics" can be displayed as an overlay of the live video signal source based on user interaction with the toggling element. Furthermore, as... Figure 3I As shown in image 322, after the user interacts with the smart overlay (e.g., as...), Figure 3H As shown), interactive displays can be updated using smart overlays (e.g., full screen) that display additional content or information.

[0057] In various embodiments, the interactively displayed toggle elements may include market forecast elements, such as... Figure 3J Image 324 is shown. Interacting with elements in the market forecast smart overlay can update the interactive display to show the current odds, such as... Figure 3K Image 326 is shown. Furthermore, as... Figure 3L As shown in Figure 328, user interaction with one or more elements of the smart overlay can be used to update the interactive display with options for market prediction of a given value.

[0058] In various embodiments, one or more of the following can be provided as input to one or more artificial intelligence models: a unique relevance threshold, multiple real-time event actions, multiple user actions, and one or more real-time user interactions.

[0059] In various embodiments, generative AI models can be trained to learn user interests by analyzing one or more patterns of user interactions with a user interface or smart overlay (e.g., mouse clicks, text input, voice input, haptic input, or visual data input). The generative AI model can leverage machine learning techniques, such as deep learning, to process user behavior and contextual information. In one example, by tracking mouse clicks on specific content or elements in a user interface or smart overlay, the AI ​​model can infer user preferences based on the frequency or type of the interaction (e.g., mouse clicks). In other examples, analyzing text input, such as search queries or chat messages, can enable the generative AI model to identify recurring themes, sentiments, or keywords that reflect user interests.

[0060] In other embodiments, voice and visual input can further enhance the learning process of generative AI models. In one example, a voice recognition system or component (e.g., as a hardware component and / or software module running on a user device, and a dedicated application) can transcribe spoken words into text and extract emotional tone and / or intent. In another example, computer vision algorithms can analyze uploaded images or videos (e.g., video streams or live streams) and identify objects, topics, players, elements, or styles of interest. In all such examples, the generative AI model can use reinforcement learning or feedback loops to refine (e.g., retrain) its understanding, thereby continuously updating predictions based on new user interactions. This personalized approach can allow generative AI models to customize responses, recommendations, or content generation (e.g., generating one or more smart overlays) to more closely align with individual user preferences.

[0061] In such embodiments, users can interact with a live video stream or smart overlay using voice input. In a specific example, a user (e.g., on a user's device) might be watching a live broadcast of a football match and might say, "I like the jersey worn by player number 04." A generative artificial intelligence model utilizing a voice recognition system can analyze the video stream and identify the clothing mentioned by the user. Using computer vision techniques, such as object detection and image segmentation, the AI ​​model can isolate the mentioned clothing and generate content recommendations or deliver advertisements to be displayed within the smart overlay. Such content recommendations or advertisements could include links inviting the user to interact with the purchase of the same or similar jerseys, links to additional information about the jersey or player, etc. For example, identifying an object (e.g., clothing) can trigger a web search for the corresponding item for sale. The search may generate one or more links pointing to that object. If multiple links are identified, the machine learning model can generate a score for each link, and the link with the highest score can be presented to the user via the smart overlay. The score can be based on historical or simulated data (e.g., user purchase data, user merchant preferences, merchant credibility, etc.), pricing information, shipping time and / or location, etc.

[0062] In another embodiment, the generative AI model may receive (e.g., as input) tracking data and / or event data as discussed herein. The generative AI model may be trained to identify associations or patterns within the tracking data, event data, and live video data to generate one or more smart overlays in a user interface associated with a user device connected to a product or service (e.g., a merchant). Based on the identified associations or patterns, ad slots (e.g., ads presented within a live video stream, ads presented in a smart overlay offered to consumer users) may be auctioned to users associated with the product or service. In such an example, the value and / or type of ad slot may be dynamically updated based on associations and patterns (e.g., based on a live “match” and its elements) identified by the generative AI model in the tracking data, event data, and live video data. Ads may be identified based on the auction, and these ads may be presented via the identified ad slots. In other embodiments, the generative AI model may identify ad slots and smart overlays that select ads from a library for display, where the selected ads have the highest score determined by the model. The score may be determined based on the relevance between the ad and a sporting event identified based on the tracking data and / or event data.

[0063] According to embodiments of the disclosed subject matter, generative AI models can leverage historical user data, such as the types of content a user engages with, past market predictions made or conducted by the user, the frequency and duration of interactions, or specific characteristics of interactions, to identify unique trends and preferences for the user. In an example, if a user frequently interacts with certain types of market predictions (e.g., similar risk levels, association with the same team or player, similar value, etc.), the generative AI model can recommend, predict, or inform the user to generate unique smart triggers aligned with the market predictions of interest. Using machine learning techniques, such as collaborative filtering, sequence modeling (e.g., recurrent neural networks), or reinforcement learning, the generative AI model can predict the content that the user might engage with next, or content that might be useful, and can subsequently present such content to the user within a smart overlay. As more data is collected (e.g., when the user interacts in real time), the generative AI model can be retrained on that data, allowing the model to become increasingly accurate. In an example, automated market prediction suggestions (e.g., with an invitation to interact) can be presented to the user via one or more smart overlays. In another example, based on the output derived from the generative AI model, the system can automatically make one or more market predictions after receiving the user's consent.

[0064] As discussed herein, one or more artificial intelligence or machine learning models can be trained to understand sports language (e.g., natural language models, etc.). Therefore, the machine learning models disclosed herein are sports machine learning models. Such sports machine learning models can be trained using sports-related data (e.g., tracking data, event data, etc., as discussed herein). Sports machine learning models trained on sports-related data for understanding sports terminology can be trained on sports-related data to adjust one or more weights, layers, nodes, biases, and / or synapses. Sports machine learning models can include components (e.g., weights, layers, nodes, biases, and / or synapses) that collectively establish one or more of the following associations: player and team or league; team and player or league; score and team; scoring event and player; sporting event and player or team; winning and player or team; losing and player or team, etc. Sports machine learning models can establish associations between sports information and statistics within the context of an event. Sports machine learning models can be trained to adjust one or more weights, layers, nodes, biases, and / or synapses to establish associations of certain sports statistics given the context of an event. For example, a team's winning metrics can be automatically correlated with the opposing team's losing metrics. As another example, static scores can be considered a positive attribution for scoring teams and a negative attribution for losing teams. As yet another example, a given score can be ranked against one or more other scores based on its relative position compared to those scores.

[0065] Sports machine learning models can be trained on tracking data and / or event data, as discussed in this paper. Such data can include player and / or object location information, movement information, trends, and changes. For example, a sports machine learning model can be trained by modifying one or more weights, layers, nodes, biases, and / or synapses to establish associations about the playing field and / or about a given location of one or more actors. As another example, a sports machine learning model can be trained by modifying one or more weights, layers, nodes, biases, and / or synapses to establish associations about the playing field and / or about a given movement or trend of one or more actors. As yet another example, a sports machine learning model can be trained by modifying one or more weights, layers, nodes, biases, and / or synapses to establish associations between a sporting event and corresponding time boundaries, teams, players, coaches, referees, and environmental data associated with the location of the corresponding sporting event.

[0066] Sports machine learning models can be trained by modifying one or more weights, layers, nodes, biases, and / or synapses to establish associations of position, movement, and / or trend information in relation to sports objectives. Sports objectives can be score-related objectives (e.g., points, goals, shots, number of shots, score value, etc.), player outcomes (e.g., passes, objects such as ball movement, player positions, etc.), player positions, etc. Sports machine learning models can be trained in relation to sports objectives, match results, player positions, etc., associated with a given sport (e.g., football, American football, basketball, baseball, tennis, golf, rugby, hockey, team sports, individual sports, etc.). For example, a football-based sports machine learning model can be trained to establish associations or other connections about player positions on a football field. A football-based sports machine learning model can also be trained to establish or otherwise establish associations about multiple players and football-specific sports objectives.

[0067] Depending on various factors, the type of one or more machine learning models for a given sport can be determined based on the attributes of the specific sport to which one or more machine learning models are applicable (e.g., generative learning, linear regression, logistic regression, random forest, gradient boosting machine (GBM), deep learning, graph neural network (GNN), and / or deep neural network). Attributes may include, for example, the type of sport (individual or team sport), sport boundaries (e.g., time factors, number of players, object factors, periods of ball possession (e.g., overlapping or independent), type of playing field (e.g., restricted, unrestricted, virtual, real, etc.), player positions, etc.

[0068] Depending on the context, a sports machine learning model can receive input data including data related to a specific sport and can generate a matrix representation based on the features of a given sport. The sports machine learning model can be trained to determine the latent features of a given sport. For example, the matrix may include fields and / or subfields related to player information, team information, object information, sport boundary information, sport surface information, etc. Attributes associated with each field and / or subfield can be populated within the matrix based on received or extracted data. The sports machine learning model can perform operations based on the generated matrix. Features can be updated based on input data or updated training data, which is based on, for example, sports data associated with features of a previously untrained model related to a given sport. Therefore, the sports machine learning model can be iteratively trained based on sports data or simulated data.

[0069] As used herein, a “machine learning model” or “artificial intelligence model” typically comprises instructions, data, and / or a model configured to receive input and apply one or more of weights, biases, classifications, or analyses to the input to generate an output. For example, the output may include a classification of the input, an input-based analysis, a design, process, prediction, or recommendation associated with the input, or any other suitable type of output. Machine learning models are typically trained using training data, such as empirical data and / or samples of input data, which are fed into the model to establish, adjust, or modify one or more aspects of the model, such as weights, biases, criteria used to form classifications or clusters, etc. The various aspects of a machine learning model may operate on the input linearly and in parallel via a network (e.g., a neural network) or via any suitable configuration.

[0070] The execution of a machine learning model can include deploying one or more machine learning techniques, such as generative learning, linear regression, logistic regression, random forests, gradient boosting machines (GBM), deep learning, graph neural networks (GNNs), and / or deep neural networks. Supervised and / or unsupervised training can be employed. For example, supervised learning can include providing training data and labels corresponding to the training data, such as ground truth. Unsupervised methods may include clustering, classification, etc. K-means clustering or K-nearest neighbors can also be used, and these can be supervised or unsupervised. A combination of K-nearest neighbors and unsupervised clustering techniques can also be used. Any suitable type of training can be used, such as stochastic, gradient boosting, random seeding, cyclic, round-robin, or batch-based training.

[0071] While several examples in this document relate to certain types of machine learning, it should be understood that the techniques according to the invention are adaptable to any suitable type of machine learning. It should also be understood that the examples above are merely illustrative. The techniques and methods of the invention may be suitable for any suitable activity.

[0072] Figure 4 A flowchart illustrating a method for training a machine learning model based on one aspect of the disclosed topic is provided. Figure 4 As shown in flowchart 400, training data 412 may include one or more of stage inputs 414 and known results 418 associated with the machine learning model to be trained. Stage inputs 414 may originate from any applicable source, including the components or sets shown in the figures provided herein. Known results 418 may be included for machine learning models generated based on supervised or semi-supervised training. Supervised machine learning models may be trained without using known results 418. Known results 418 may include known or expected outputs for future inputs that are similar to or in the same category as stage inputs 414 that do not have corresponding known outputs.

[0073] Training data 412 and training algorithm 420 can be provided to training component 430, which can apply training data 412 to training algorithm 420 to generate a trained machine learning model 450. According to one embodiment, a comparison result 416 can be provided to training component 430, which compares the previous output of the corresponding machine learning model to apply the previous result to retrain the machine learning model. Training component 430 can use comparison result 416 to update the corresponding machine learning model. Training algorithm 420 can utilize machine learning networks and / or models, including but not limited to, deep learning networks such as deep neural networks (DNN), convolutional neural networks (CNN), fully convolutional networks (FCN), and recurrent neural networks (RCN), probabilistic models (such as Bayesian networks and graphical models), and / or discriminative models (such as decision forests and maximum margin methods). The output of flowchart 400 can be the trained machine learning model 450.

[0074] In a further aspect and according to embodiments disclosed herein, a transformer neural network can receive inputs (e.g., tensor layers), where each input corresponds to a given player, team, or match. The transformer neural network can output predictions for one or more given players or teams based on such inputs. More specifically, the transformer neural network can output such generated predictions for a given player or team based on inputs associated with that player or team and further based on the influence of one or more other players or teams. Thus, as discussed herein, predictions provided by a transformer neural network can take into account the influence of multiple players and / or teams when outputting predictions for a given player and / or team.

[0075] The systems described herein may include machine learning systems configured to generate one or more predictions. In some examples, the system may incorporate transformer neural networks, graph neural networks, recurrent neural networks, convolutional neural networks, and / or feedforward neural networks. The system may implement a series of neural network instances (e.g., feedforward network (FFN) models) connected via a transformer neural network (e.g., a graph neural network (GNN) model). Although transformer neural networks are generally discussed herein, it should be understood that any applicable GNN or other neural network that can be graphically interpreted can be used to perform the techniques discussed herein with reference to transformer neural networks.

[0076] Transformer-based neural networks can include a set of linear embedding layers; a transformer encoder; and a set of fully connected layers. The linear embedding layers map the component tensors of the received input to tensors with a common feature dimension. The transformer encoder performs attention along the time and agent dimensions. The set of fully connected layers embeds the output from the final transformer layer of the transformer encoder to a tensor with the requested feature dimension for each target metric.

[0077] Transformer-based neural networks can be configured to receive input features through this set of linear embedding layers. The input features can be received at different resolutions and time series. The input features can be related to player features, team features, and / or match features. The input features can be fed as tuples of input tensors into the linear embedding layers. For example, a tuple of three tensors can be provided, where the first tensor corresponds to all players in the match, the second tensor corresponds to the two teams in the match, and the third tensor corresponds to the match state.

[0078] Examining this set of linear embedding layers, each layer can contain linear blocks for each input tensor of a tuple, and each block maps the input tensor to a tensor with a common feature dimension D. The output of the linear embedding layer can be a tuple of tensors with a common feature dimension, which can be concatenated along the time and action subject dimensions to form a single tensor.

[0079] A transformer encoder can be configured to receive a single tensor derived from a linear embedding layer. The transformer encoder can be configured to learn embeddings configured to generate predictions for multiple actions per actor (e.g., each player and / or team). The transformer encoder can include a series of axial transformer encoder layers, each layer alternately applying attention along the temporal and actor dimensions. The transformer encoder can include layers that alternate between applying attention temporally to a sequence of action events and applying attention spatially across the group of players and teams at each event time step. The transformer encoder can include axial encoder layers configured to receive tensors derived from linear layers and apply attention along the temporal dimension and subsequently along the actor dimension.

[0080] The attention mechanism implemented by the transformer encoder layer can be graphically interpreted on a dense graph, where each element is a node, and the attention mask is the inverse of the adjacency matrix of the edges between nodes (therefore, the absence of an attention mask implies a fully connected graph). In the case of axial attention used here, with the attention mask in the time (row) dimension, the nodes in the graph can be arranged in a grid, and each node can be connected to all nodes in the same column, as well as to all previous nodes in the same row. In this case, attention may be message passing, where each node can receive the state of the nodes depicted in its vicinity and then update its own state based on these messages. This attention scheme might mean that when making a prediction for a particular player, the model might consider (i.e., pay attention to): nodes containing the player's previous states along the time series; and state nodes of other players, teams, and the current match state in the current time step. Nodes may not need to be homogeneous except for having the same feature dimensions, and therefore the node representing the player can receive messages from nodes representing their team or from nodes representing the player's strength. Thus, the model can learn the interactions between actors and ensure consistent predictions for each actor along the time series. The output of the transformer encoder layer can be a tensor (e.g., an output embedding).

[0081] The final layer of a transformer-based neural network can be a fully connected layer. These layers can embed the output of the final transformer layer of the transformer encoder and map it to the feature dimension of each target metric. The final layer can output a target tuple containing tensors of each of a set of modeling actions for each player and / or team. For example, the modeling actions could be empirical distribution estimates of sports statistics, such as shots, goals, passes, etc.

[0082] Training a transformer-based neural network may involve selecting an appropriate loss function based on the distributional assumptions of each output target. For example, the loss function might be the negative log-likelihood of a Poisson distribution, the binary cross-entropy of a Bernoulli distribution, etc. During training, the loss can be calculated based on the true values ​​of each target in the training set, and the loss values ​​can be summed. The optimizer can then be used to update the model's weights based on the total loss. The learning rate may have been adjusted according to a schedule with cosine annealing (no warm restart).

[0083] The machine learning models disclosed herein can be trained by adjusting one or more weights, layers, and / or biases during the training phase. During the training phase, historical or simulated data can be provided as input to the model. The model can adjust one or more of its weights, layers, and / or biases based on such historical or simulated information. The adjusted weights, layers, and / or biases can be configured based on the training to a production version of the machine learning model (e.g., a trained model). Once trained, the machine learning model can output its output according to the subject matter disclosed herein. According to one implementation, one or more machine learning models disclosed herein can be continuously updated based on the use or implementation of the machine learning model's output.

[0084] Figure 5A An architecture of a computing system 500 according to an example embodiment is shown. System 500 may represent at least a portion of an organizational computing system 104. One or more components of system 500 may communicate electrically with each other using bus 505. System 500 may include a processing unit (CPU or processor) 510 and a system bus 505 that couples various system components, including system memory 515, such as read-only memory (ROM) 520 and random access memory (RAM) 525, to processor 510. System 500 may include a cache of high-speed memory directly connected to, close to, or integrated as part of processor 510. System 500 may copy data from memory 515 and / or storage device 530 to cache 512 for fast access by processor 510. In this way, cache 512 can provide performance improvements by avoiding latency for processor 510 while waiting for data. These and other modules may control or be configured to control processor 510 to perform various actions. Other system memories 515 may also be available. Memory 515 may include various different types of memory with different performance characteristics. Processor 510 may include any general-purpose processor and hardware or software modules, such as Service 1 532, Service 2 534 and Service 3 536 stored in storage device 530, configured to control processor 510; and dedicated processors, where software instructions are incorporated into the actual processor design. Processor 510 may essentially be a completely independent computing system, containing multiple cores or processors, buses, memory controllers, caches, etc. Multi-core processors may be symmetric or asymmetric.

[0085] To enable users to interact with computing system 500, input device 545 can represent any number of input mechanisms, such as a microphone for voice, a touchscreen for gesture or graphical input, a keyboard, a mouse, motion input, voice input, etc. Output device 535 (e.g., a display) can also be one or more of a variety of output mechanisms known to those skilled in the art. In some cases, a multimodal system can enable users to provide multiple types of input to communicate with computing system 500. Communication interface 540 typically governs and manages user input and system output. There are no limitations on operation on any particular hardware arrangement, and therefore the basic features herein can be easily replaced with improved hardware or firmware arrangements during development.

[0086] Storage device 530 may be a non-volatile memory and may be a hard disk or other type of computer-readable medium that can store computer-accessible data, such as a magnetic tape cassette, flash memory card, solid-state storage device, digital multifunction optical disc, ink cartridge, random access memory (RAM) 525, read-only memory (ROM) 520 and mixtures thereof.

[0087] Storage device 530 may include services 532, 534, and 536 for controlling processor 510. Other hardware or software modules are contemplated. Storage device 530 may be connected to system bus 505. In one aspect, a hardware module performing a specific function may include software components stored in a computer-readable medium connected to necessary hardware components, such as processor 510, bus 505, output device 535, etc., to perform that function.

[0088] Figure 5BA computer system 550 is shown having a chipset architecture that can represent at least a portion of an organizational computing system 104. The computer system 550 can be an example of computer hardware, software, and firmware that can be used to implement the disclosed techniques. System 550 may include a processor 555, which represents any number of physically and / or logically distinct resources capable of executing software, firmware, and hardware configured to perform the identified computations. The processor 555 can communicate with a chipset 560, which can control inputs to the processor 555 and outputs from the processor 555. In this example, the chipset 560 outputs information to an output 565, such as a display, and can read and write information to a storage device 570, which may include, for example, magnetic media and solid-state media. The chipset 560 can also read data from and write data to RAM 575. A bridge 580 for interfacing with various user interface components 585 may be provided for interfacing with the chipset 560. Such a user interface component 585 may include a keyboard, microphone, touch detection and processing circuitry, pointing device, such as a mouse, etc. Typically, input to system 550 can come from any of a variety of machine-generated and / or human-generated sources.

[0089] Chipset 560 can also interface with one or more communication interfaces 590 that may have different physical interfaces. Such communication interfaces may include interfaces for wired and wireless local area networks (LANs), broadband wireless networks, and personal area networks (PANs). Some applications of the methods for generating, displaying, and using the GUI disclosed herein may include receiving ordered datasets via physical interfaces or analyzing data stored in storage device 570 or RAM 575 via processor 555, generated by the machine itself. Furthermore, the machine may receive input from the user via user interface component 585 and perform appropriate functions, such as navigating functions by parsing this input using processor 555.

[0090] It is understood that the example systems 500 and 550 may have more than one processor 510 or be part of a group or cluster of computing devices networked together to provide greater processing power.

[0091] While the foregoing describes embodiments herein, other and additional embodiments can be devised without departing from the basic scope of the invention. For example, aspects of the invention can be implemented in hardware or software or a combination of hardware and software. One embodiment described herein can be implemented as a program product for use with a computer system. The program product defines the functionality of the embodiment (including the methods described herein) and can be contained on various computer-readable storage media. Illustrative computer-readable storage media include, but are not limited to: (i) non-writable storage media (e.g., read-only memory (ROM) devices within a computer, such as those that may be CD-ROM drives, flash memory, ROM chips, or any type of solid-state non-volatile memory) on which information is permanently stored; and (ii) writable storage media on which changeable information is stored (e.g., a floppy disk in a floppy disk drive or hard disk drive or any type of solid-state random access memory). Such computer-readable storage media are embodiments of the invention when they carry computer-readable instructions directing the functionality of the disclosed embodiments.

[0092] Those skilled in the art will understand that the foregoing examples are exemplary and not restrictive. It will be apparent to those skilled in the art, upon reading the specification and studying the accompanying drawings, that all permutations, enhancements, equivalents, and modifications are included within the true spirit and scope of the invention. Therefore, the appended claims are intended to cover all such modifications, permutations, and equivalents that fall within the true spirit and scope of these teachings.

Claims

1. A computer-implemented method for generating intelligent overlays in an interactive display, the method comprising: Multiple real-time event data, including multiple real-time event actions, are received by one or more processors; The one or more processors receive multiple user data, including multiple user actions; One or more real-time user interactions with the interactive display are captured by the one or more processors; The one or more processors generate a unique correlation threshold using the plurality of real-time event actions, the plurality of user actions, and the one or more real-time user interactions, wherein the unique correlation threshold is generated in real time when the plurality of real-time event data and the one or more real-time user interactions are received; The unique intelligent overlay generated in real time by the one or more processors has at least one correlation exceeding the unique correlation threshold; and The interactive display, which has at least one unique intelligent overlay, is updated in real time by the one or more processors.

2. The computer-implemented method according to claim 1, wherein the at least one unique intelligent overlay is an interactive interface overlaid on a live video stream on a user device.

3. The computer-implemented method according to claim 1, wherein the position of the at least one unique intelligence superimposed within the interactive display is automatically determined based on one or more of the plurality of real-time event actions, the plurality of user actions, the one or more real-time user interactions, and the camera angle of the live video stream.

4. The computer-implemented method according to claim 1, wherein the at least one unique intelligent overlay is generated and / or updated based on one or more of the plurality of real-time event actions, the plurality of user actions, and the one or more real-time user interactions.

5. The computer-implemented method according to claim 1, wherein the interactive display is displayed on a user mobile device.

6. The computer-implemented method of claim 1, wherein the plurality of real-time event actions include at least one of scoring a goal, completing a pass, interception, conceding a goal, or no action.

7. The computer-implemented method of claim 1, wherein one or more of the unique relevance threshold, the plurality of real-time event actions, the plurality of user actions, and the one or more real-time user interactions are provided as input to one or more artificial intelligence models.

8. A system for generating intelligent overlays in an interactive display, the system comprising: A memory for storing instructions and a processor, the processor being operatively connected to the memory and configured to execute the instructions to perform operations, the operations including: Multiple real-time event data, including multiple real-time event actions, are received by one or more processors; The one or more processors receive multiple user data, including multiple user actions; One or more real-time user interactions with the interactive display are captured by the one or more processors; The one or more processors generate a unique correlation threshold using the plurality of real-time event actions, the plurality of user actions, and the one or more real-time user interactions, wherein the unique correlation threshold is generated in real time when the plurality of real-time event data and the one or more real-time user interactions are received; The unique intelligent overlay generated in real time by the one or more processors has at least one correlation exceeding the unique correlation threshold; and The interactive display, which has at least one unique intelligent overlay, is updated in real time by the one or more processors.

9. The system of claim 8, wherein the at least one unique intelligent overlay is an interactive interface overlaid on a live video stream on a user device.

10. The system of claim 8, wherein the position of the at least one unique intelligent overlay within the interactive display is automatically determined based on one or more of the plurality of real-time event actions, the plurality of user actions, the one or more real-time user interactions, and camera angles of the live video stream.

11. The system of claim 8, wherein the at least one unique intelligent overlay is generated and / or updated based on one or more of the plurality of real-time event actions, the plurality of user actions, and the one or more real-time user interactions.

12. The system of claim 8, wherein the interactive display is displayed on the user's mobile device.

13. The system of claim 8, wherein the plurality of real-time event actions include at least one of scoring a goal, completing a pass, interception, losing possession, or no action.

14. The system of claim 8, wherein one or more of the unique relevance threshold, the plurality of real-time event actions, the plurality of user actions, and the one or more real-time user interactions are provided as input to one or more artificial intelligence models.

15. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, perform a method for generating a smart overlay in an interactive display, the method comprising: Multiple real-time event data, including multiple real-time event actions, are received by one or more processors; The one or more processors receive multiple user data, including multiple user actions; One or more real-time user interactions with the interactive display are captured by the one or more processors; The one or more processors generate a unique correlation threshold using the plurality of real-time event actions, the plurality of user actions, and the one or more real-time user interactions, wherein the unique correlation threshold is generated in real time when the plurality of real-time event data and the one or more real-time user interactions are received; The unique intelligent overlay generated in real time by the one or more processors has at least one correlation exceeding the unique correlation threshold; and The interactive display, which has at least one unique intelligent overlay, is updated in real time by the one or more processors.

16. The non-transitory computer-readable medium of claim 15, wherein the at least one unique smart overlay is an interactive interface overlaid on a live video stream on a user device.

17. The non-transitory computer-readable medium of claim 15, wherein the position of the at least one unique intelligence superimposed within the interactive display is automatically determined based on one or more of the plurality of real-time event actions, the plurality of user actions, the one or more real-time user interactions, and camera angles of the live video stream.

18. The non-transitory computer-readable medium of claim 15, wherein the at least one unique intelligent overlay is generated and / or updated based on one or more of the plurality of real-time event actions, the plurality of user actions, and the one or more real-time user interactions.

19. The non-transitory computer-readable medium of claim 15, wherein the interactive display is displayed on a user mobile device.

20. The non-transitory computer-readable medium of claim 15, wherein one or more of the unique relevance threshold, the plurality of real-time event actions, the plurality of user actions, and the one or more real-time user interactions are provided as input to one or more artificial intelligence models.

Images