Abstract: The present invention is a system and method for optimizing the narrative text generated by one or more narrative frameworks that utilize data input from one or more data sources to drive the creation of a narrative text output. Narrative text is generated in accordance with sets of data that provide the scope of text to be generated. A Quality Assurance module presents the narrative text output to a user that reviews both the condition and the logic evaluation associated with the scope, and the quality of the generated text. A log of Quality Assurance items is created upon review of the generated text. These items are then later resolved by locating them in a narrative text generation data structure to resolve the identified issues.

Abstract: A system and method for generating a role summary associated with one or more players are disclosed herein. A computing system retrieves event information for a plurality of teams for a plurality of events. The computing system generates a spatial output that describes each player. The computing system identifies a playing style associated with each team. The computing system identifies a subset of paths a player or team takes between two zones. The computing system identifies each player's involvement in a team's process. The computing system generates a score corresponding to a value of a player's involvement in a given play based on the event information. The computing system generates a score associated with each player's passing ability based on the event information. The computing system determines a shot style of each player based on the event information. The computing system identifies a role associated with each player.

Abstract: Metadata for highlights of audiovisual content depicting a sporting event or other event are extracted from audiovisual content. The highlights may be segments of the content, such as a broadcast of a sporting event, that are of particular interest. Audio data for the audiovisual content is stored, and portions of the audio data indicating crowd excitement (noise) is automatically identified by analyzing an audio signal in the joint time and frequency domains. Multiple indicators are derived and subsequently processed to detect, validate, and render occurrences of crowd noise. Metadata are automatically generated, including time of occurrence, level of noise (excitement), and duration of cheering. Metadata may be stored, comprising at least a time index indicating a time, within the audiovisual content, at which each of the portions occurs. Periods of intense crowd noise may be used to identify highlights and/or to indicate crowd excitement during viewing of a highlight.

Abstract: A system is described for analyzing plays of a sporting event based on body-pose information in conjunction with real-world positional tracking data. The system permits segmentation of sporting event plays into discrete time periods and the labeling of appropriate body-pose characteristics for each period. The system allows for comparison and fine-grained analysis of plays with respect to either a series of body-pose vertices that exist in continuous space (i.e., skeleton) or map directly to attributes, using the positional tracking data and play information to account for contextual differences. To enable analysis for the former, the system performs a projection to 3D space, followed by a spatiotemporal alignment step. Through the system, the importance of particular body-pose motions or specific attributes to the success of particular sporting event plays is quantified.

Abstract: A computing system retrieves player tracking data for a plurality of players across a plurality of events. The player tracking data includes coordinates of player positions during each event. The computing system initializes the player tracking data based on an average position of each player in the plurality of events. The computing system learns an optimal formation of player positions based on the player tracking data using a Gaussian mixture model. The computing system aligns the optimal formation of player positions to a global template by identifying a distance between each distribution in the optimal formation and each distribution in the global template to generate a learned formation template. The computing system assigns a role to each player in the learned template.

Abstract: A system and method for generating a play prediction for a team is disclosed herein. A computing system retrieves trajectory data for a plurality of plays from a data store. The computing system generates a predictive model using a variational autoencoder and a neural network by generating one or more input data sets, learning, by the variational autoencoder, to generate a plurality of variants for each play of the plurality of plays, and learning, by the neural network, a team style corresponding to each play of the plurality of plays. The computing system receives trajectory data corresponding to a target play. The predictive model generates a likelihood of a target team executing the target play by determining a number of target variants that correspond to a target team identity of the target team.

Abstract: A system is described for analyzing plays of a sporting event based on body-pose information in conjunction with real-world positional tracking data. The system permits segmentation of sporting event plays into discrete time periods and the labeling of appropriate body-pose characteristics for each period. The system allows for comparison and fine-grained analysis of plays with respect to either a series of body-pose vertices that exist in continuous space (i.e., skeleton) or map directly to attributes, using the positional tracking data and play information to account for contextual differences. To enable analysis for the former, the system performs a projection to 3D space, followed by a spatiotemporal alignment step. Through the system, the importance of particular body-pose motions or specific attributes to the success of particular sporting event plays is quantified.

Abstract: The present invention is a method and apparatus for narrative content generation using narrative frameworks by receiving a first phrase variation and a second phrase variation and displaying an error indication when the first phrase variation fails to satisfy a criterion relative to the second phrase variation. If there is an error indication, alternate phrase variations are received and compared against the first phrase variation until an alternate phrase variation is selected that has no error indication. Additionally, multiple sets of operators for updating one or more narrative phrases selected for inclusion in the narrative content framework may be utilized to update selected phrases after inclusion in the narrative framework but prior to finalizing the narrative content to be output.

Abstract: A system and method of re-identifying players in a broadcast video feed are provided herein. A computing system retrieves a broadcast video feed for a sporting event. The broadcast video feed includes a plurality of video frames. The computing system generates a plurality of tracks based on the plurality of video frames. Each track includes a plurality of image patches associated with at least one player. Each image patch of the plurality of image patches is a subset of the corresponding frame of the plurality of video frames. For each track, the computing system generates a gallery of image patches. A jersey number of each player is visible in each image patch of the gallery. The computing system matches, via a convolutional autoencoder, tracks across galleries. The computing system measures, via a neural network, a similarity score for each matched track and associates two tracks based on the measured similarity.

Abstract: A method of generating a multi-modal prediction is disclosed herein. A computing system retrieves event data from a data store. The event data includes information for a plurality of events across a plurality of seasons. Computing system generates a predictive model using a mixture density network, by generating an input vector from the event data learning, by the mixture density network, a plurality of values associated with a next play following each play in the event data. The mixture density network is trained to output the plurality of values near simultaneously. Computing system receives a set of event data directed to an event in a match. The set of event data includes information directed to at least playing surface position and current score. Computing system generates, via the predictive model, a plurality of values associated with a next event following the event based on the set of event data.

Abstract: A method of generating a player prediction is disclosed herein. A computing system retrieves data from a data store. The computing system generates a predictive model using an artificial neural network. The artificial neural network generates one or more personalized embeddings that include player-specific information based on historical performance. The computing system selects, from the data, one or more features related to each shot attempt captured in the data. The artificial neural network learns an outcome of each shot attempt based at least on the one or more personalized embeddings and the one or more features related to each shot attempt.

Abstract: A system and method of generating a player tracking prediction are described herein. A computing system retrieves a broadcast video feed for a sporting event. The computing system segments the broadcast video feed into a unified view. The computing system generates a plurality of data sets based on the plurality of trackable frames. The computing system calibrates a camera associated with each trackable frame based on the body pose information. The computing system generates a plurality of sets of short tracklets based on the plurality of trackable frames and the body pose information. The computing system connects each set of short tracklets by generating a motion field vector for each player in the plurality of trackable frames. The computing system predicts a future motion of a player based on the player's motion field vector using a neural network.

Abstract: A system and method of generating trackable frames from a broadcast video feed are provided herein. A computing system retrieves a broadcast video feed for a sporting event. The broadcast video feed includes a plurality of video frames. The computing system generates a set of frames for classification using a principal component analysis model. The set of frames are a subset of the plurality of video frames. The computing system partitions each frame of the set of frames into a plurality of clusters. The computing system classifies each frame of the plurality of frames as trackable or untrackable. Trackable frames capture a unified view of the sporting event. The computing system compares each cluster to a predetermined threshold to determine whether each cluster comprises at least a threshold number of trackable frames. The computing system classifies each cluster that includes at least the threshold number of trackable frames as trackable.

Abstract: A system and method of calibrating moving cameras capturing a sporting event is disclosed herein. A computing system retrieves a broadcast video feed for a sporting event. The broadcast video feed includes a plurality of video frames. The computing system labels, via a neural network, components of a playing surface captured in each video frame. The computing system matches a subset of labeled video frames to a set of templates with various camera perspectives. The computing system fits a playing surface model to the set of labeled video frames that were matched to the set of templates. The computing system identifies camera motion in each video frame using an optical flow model. The computing system generates a homography matrix for each video frame based on the fitted playing surface model and camera motion. The computing system calibrates each camera based on the homography matrix generated for each video frame.

Abstract: The present invention is a system and method for generating narrative text utilizing data input from one or more data sources to drive the creation of a narrative text output. Narrative text is generated in accordance with sets of data that provide the scope of text to be generated. A narrative text editor permits automatic generation of narrative text automatically using pre-defined scope for the generated text, or under the guidance of scope input by a user. Generated text retains links to the origin structure and scope used in creation of the narrative text permitting quick troubleshooting of issues in the narrative text generation and rapid review and updating under the guidance of established rule sets or system users.

Abstract: A method of generating an outcome for a sporting event is disclosed herein. A computing system retrieves tracking data from a data store. The computing system generates a predictive model using a deep neural network. The one or more neural networks of the deep neural network generates one or more embeddings comprising team-specific information and agent-specific information based on the tracking data. The computing system selects, from the tracking data, one or more features related to a current context of the sporting event. The computing system learns, by the deep neural network, one or more likely outcomes of one or more sporting events. The computing system receives a pre-match lineup for the sporting event. The computing system generates, via the predictive model, a likely outcome of the sporting event based on historical information of each agent for the home team, each agent for the away team, and team-specific features.

Abstract: A system and method for predicting multi-agent locations is disclosed herein. A computing system retrieves tracking data from a data store. The computing system generates a predictive model using a conditional variational autoencoder. The conditional variational autoencoder learns one or more paths a subset of agents of the plurality of agents are likely to take. The computing system receives tracking data from a tracking system positioned remotely in a venue hosting a candidate sporting event. The computing system identifies one or more candidate agents for which to predict locations. The computing system infers, via the predictive model, one or more locations of the one or more candidate agents. The computing system generates a graphical representation of the one or more locations of the one or more candidate agents.

Abstract: A method of generating an outcome for a sporting event is disclosed herein. A computing system retrieves tracking data from a data store. The computing system generates a predictive model using a deep neural network. The one or more neural networks of the deep neural network generates one or more embeddings comprising team-specific information and agent-specific information based on the tracking data. The computing system selects, from the tracking data, one or more features related to a current context of the sporting event. The computing system learns, by the deep neural network, one or more likely outcomes of one or more sporting events. The computing system receives a pre-match lineup for the sporting event. The computing system generates, via the predictive model, a likely outcome of the sporting event based on historical information of each agent for the home team, each agent for the away team, and team-specific features.

Abstract: A method of identifying a defensive alignment and an offensive alignment in a set-piece is disclosed herein. A computing system receives one or more streams of tracking data. The computing system identifies a set-piece contained in the one or more streams of tracking data. The computing system identifies a defensive alignment of a first team and an offensive alignment of a second team. The computing system extracts, via a convolutional neural network, one or more features corresponding to a type of defensive alignment implemented by the first team by passing the set-piece through the convolutional neural network. The computing system scans the set-piece, via a machine learning algorithm, to identify one or more features indicative of a type of offensive alignment implemented by the second team. The computing system infers the type of defensive alignment implemented by the first team.

Abstract: A system is described for interactively analyzing plays of a sporting event based on real-world positional tracking data. Using positional information regarding the players and/or ball and/or other objects obtained from a tracking system, along with identified event data and contextual information, the system processes a library of plays (e.g., one or more seasons' worth of a league's contests) into a searchable database of plays using multiple alignment templates and discriminative clustering techniques. A user interface is described for interacting with the database in a graphical manner, whereby users can query a graphical depiction of a play and receive the most similar plays from the library, along with statistical information relating to the plays. The user interface further permits the user to modify the query graphically (e.g., moving or exchanging players, ball trajectories, etc.) and obtain updated statistical information for comparison.