# US 11,992,761 B2 · Artificial intelligence (AI) controlled camera perspective generator and AI broadcaster > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,992,761 B2 - Document ID: US11992761B2 - Status: Granted - Kind: B2 - Application number: 17/463,468 - Filed: 2021-08-31 - Published: 2021-12-16 - Granted: 2024-05-28 - Earliest claimed: 2019-09-26 - Assignees: Sony Interactive Entertainment Inc. - Applicants: Sony Interactive Entertainment Inc. - Inventors: Charles McCoy; True Xiong; Nathan Blaine Morgan - Web page: https://patentgrep.com/patent/US11992761B2 ## CPC - A63F 13/5258: by dynamically adapting the position of the virtual camera to keep a game object or game character in its viewing frustum, e.g. for tracking a character or a ball - H04N 21/4781: {Games} - A63F 13/35: Details of game servers - A63F 13/355: Performing operations on behalf of clients with restricted processing capabilities, e.g. servers transform changing game scene into an encoded video stream for transmitting to a mobile phone or a thin client - A63F 13/5252: using two or more virtual cameras concurrently or sequentially, e.g. automatically switching between fixed virtual cameras when a character changes room or displaying a rear-mirror view in a car-driving game - A63F 13/53: involving additional visual information provided to the game scene, e.g. by overlay to simulate a head-up display [HUD] or displaying a laser sight in a shooting game - A63F 13/537: using indicators, e.g. showing the condition of a game character on screen - A63F 13/54: involving acoustic signals, e.g. for simulating revolutions per minute [RPM] dependent engine sounds in a driving game or reverberation against a virtual wall - A63F 13/67: adaptively or by learning from player actions, e.g. skill level adjustment or by storing successful combat sequences for re-use - A63F 13/86: Watching games played by other players - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/084: Backpropagation, e.g. using gradient descent - G06N 3/09: Supervised learning - G06N 3/092: Reinforcement learning - H04N 21/2187: Live feed - H04N 21/4722: for requesting additional data associated with the content - H04N 21/8133: {specifically related to the content, e.g. biography of the actors in a movie, detailed information about an article seen in a video programme} - A63F 13/525: Changing parameters of virtual cameras - A63F 13/58: by computing conditions of game characters, e.g. stamina, strength, motivation or energy level - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/045: Combinations of networks - A63F: CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method for generating broadcasts including receiving game state data and user data of players participating in a gaming session of a video game. A spectator zone-of-interest in the gaming session is identified having a scene of a virtual gaming world that is viewable from camera perspectives in the virtual gaming world. Statistics and facts are generated for the gaming session based on the game state data and the user data using a first AI model trained to isolate game state data and user data that are of interest by spectators. Narration is generated for the scene using a second AI model configured to select statistics and facts from the statistics and facts generated using the first AI model, the selected statistics and facts having a highest potential spectator interest as determined by the second AI model configured to generate the narration using the selected statistics and facts. ## Claims ### Claim 1 A method, comprising: receiving at a server, game state data and user data from a plurality of game plays of a plurality of players playing a video game; generating at the server statistics and facts for a gaming session that is live of the video game based on the game state data and the user data, wherein the plurality of game plays includes game plays of the gaming session; generating at the server a camera perspective of a scene of the gaming session using artificial intelligence, wherein the camera perspective is selected by a spectator; and automatically generating in real-time at the server, using the artificial intelligence, machine based narration for the camera perspective of the scene of the gaming session based on the game state data and the user data. ### Claim 2 (depends on 1) The method of claim 1, wherein the generating the machine based narration includes: generating the machine based narration using an AI model configured to select for the machine based narration a subset of the statistics and facts generated for the gaming session having a potential spectator interest. ### Claim 3 (depends on 2) The method of claim 2, further comprising: selecting the subset of the statistics and the facts generated for the gaming session that have a highest potential spectator interest. ### Claim 4 (depends on 1) The method of claim 1, further comprising: identifying one or more spectator zones-of-interest that are likely to be viewed by at least one spectator, each of the one or more spectator zones-of-interest associated with one or more scenes of the gaming session, wherein one or more camera perspectives provide one or more views into each scene of the one or more scenes. ### Claim 5 (depends on 4) The method of claim 4, further comprising: streaming the camera perspective of the scene and the machine based narration to a device of the spectator over a network. ### Claim 6 (depends on 4) The method of claim 4, further comprising: wherein a spectator zone-of-interest that is identified is selected by the spectator. ### Claim 7 (depends on 4) The method of claim 4, further comprising: generating a highlight of the gaming session of the video game, wherein the highlight includes at least one camera perspective of a plurality of image frames of the scene and the machine based narration. ### Claim 8 (depends on 1) The method of claim 1, wherein the generating the machine based narration includes: determining a scenario of the scene in the gaming session based on the statistics and the facts generated for the gaming session and the game state data and the user data from the plurality of game plays; and using a narration template built for the scenario. ### Claim 9 A non-transitory computer-readable medium for performing a method, the computer-readable medium comprising: program instructions for receiving at a server, game state data and user data from a plurality of game plays of a plurality of players playing a video game; program instructions for generating at the server statistics and facts for a gaming session of the video game based on the game state data and the user data, wherein the plurality of game plays includes game plays of the gaming session; program instructions for generating at the server a camera perspective of a scene of the gaming session using artificial intelligence, wherein the camera perspective is selected by a spectator; and program instructions for automatically generating in real-time at the server, using the artificial intelligence, machine based narration for the camera perspective of the scene of the gaming session based on the game state data and the user data. ### Claim 10 (depends on 9) The non-transitory computer-readable medium of claim 9, wherein the program instructions for generating the narration includes: program instructions for generating the machine based narration using an AI model configured to select for the machine based narration a subset of the statistics and the facts generated for the gaming session having a potential spectator interest. ### Claim 11 (depends on 10) The non-transitory computer-readable medium of claim 10, further comprising: program instructions for selecting the subset of the statistics and the facts generated for the gaming session that have a highest potential spectator interest. ### Claim 12 (depends on 9) The non-transitory computer-readable medium of claim 9, further comprising: program instructions for identifying one or more spectator zones-of-interest that are likely to be viewed by at least one spectator, each of the one or more spectator zones-of-interest associated with one or more scenes of the gaming session, wherein one or more camera perspectives provide one or more views into each scene of the one or more scenes; and program instructions for streaming the camera perspective of the scene and the narration to a device of a spectator over a network. ### Claim 13 (depends on 12) The non-transitory computer-readable medium of claim 12, further comprising: program instructions for generating a highlight of the gaming session of the video game, wherein the highlight includes at least one camera perspective of a plurality of image frames of the scene and the machine based narration. ### Claim 14 (depends on 9) The non-transitory computer-readable medium of claim 9, wherein the program instructions for generating the machine based narration includes: program instructions for determining a scenario of the scene in the gaming session based on the statistics and the facts generated for the gaming session and the game state data and the user data from the plurality of game plays; and program instructions for using a narration template built for the scenario. ### Claim 15 A computer system comprising: a processor; memory coupled to the processor and having stored therein instructions that, if executed by the computer system, cause the computer system to execute a method, comprising: receiving at a server, game state data and user data from a plurality of game plays of a plurality of players playing a video game; generating at the server statistics and facts for a gaming session of the video game based on the game state data and the user data, wherein the plurality of game plays includes game plays of the gaming session; generating at the server a camera perspective of a scene of the gaming session using artificial intelligence, wherein the camera perspective is selected by a spectator; and automatically generating in real-time at the server, using the artificial intelligence, machine based narration for the camera perspective of the scene of the gaming session based on the game state data and the user data. ### Claim 16 (depends on 15) The computer system of claim 15, wherein in the method the generating the machine based narration includes: generating the machine based narration using an AI model configured to select for the machine based narration a subset of the statistics and the facts generated for the gaming session having a potential spectator interest. ### Claim 17 (depends on 16) The computer system of claim 16, the method further comprising: selecting the subset of the statistics and the facts generated for the gaming session that have a highest potential spectator interest. ### Claim 18 (depends on 15) The computer system of claim 15, the method further comprising: identifying one or more spectator zones-of-interest that are likely to be viewed by at least one spectator, each of the one or more spectator zones-of-interest associated with one or more scenes of the gaming session, wherein one or more camera perspectives provide one or more views into each scene of the one or more scenes; and streaming the camera perspective of the scene and the machine based narration to a device of the spectator over a network. ### Claim 19 (depends on 18) The computer system of claim 18, the method further comprising: generating a highlight of the gaming session of the video game, wherein the highlight includes at least one camera perspective of a plurality of image frames of the scene and the machine based narration. ### Claim 20 (depends on 15) The computer system of claim 15, wherein in the method the generating the machine based narration includes: determining a scenario of the scene in the gaming session based on the statistics and the facts generated for the gaming session and the game state data and the user data from the plurality of game plays; and using a narration template built for the scenario.