In-game dynamic camera angle adjustment

1. A method for dynamically adjusting a camera angle in a video game, comprising:

receiving a dataset of a plurality of video sequences that are associated with tagging data in metadata that identify characteristics of actions occurring in each of the plurality of video sequences, the metadata further includes the camera angle used in each of the plurality of video sequences and said tagging data includes preference information for said camera angle, wherein the plurality of video sequences include video sequences from the video game and other non-video game video sequences, and wherein said tagging data is received from a respective viewer that identifies the preference information for said camera angle;

generating an artificial intelligence (AI) model from the dataset, the AI model is trained using said plurality of video sequences by examining image content to produce video feature data and examining metadata associated with said examined image content to produce metadata feature data, the video feature data and metadata feature data is classified and used by said AI model;

accessing the AI model during gameplay of the video game by a user, the AI model further using as input snapshots of video sequences being generated during said gameplay of the video game, the snapshots of video sequences are from camera angles presented to the user, wherein the snapshots of video sequences include multiple video frames, and said snapshots of video sequences are generated responsive to metadata produced during said gameplay being indicative that an action scene is occurring or about to occur; and

adjusting a game camera angle for the user dynamically during the gameplay by the user, the adjusting is responsive to adjustment instructions derived from said AI model based in part on examining image content and metadata associated with said snapshots used as input to said AI model.

2. The method of claim 1 , wherein the adjusting of the game camera angle causes a developer camera angle of the game to be modified.

3. The method of claim 1 , wherein

the AI model is configured to process the video feature data and the metadata feature data to label said characteristics of actions occurring in each of the plurality of video sequences;

wherein generating said AI model occurs during a training process.

4. The method of claim 1 , wherein said snapshots of video are generated periodically during said gameplay to trigger processing of said adjustment instructions for adjusting the game camera angle for presenting scenes of the video game during said gameplay.

5. The method of claim 1 , wherein the tagging data is obtained from a database of user generated data (UGD), the UGD includes frames sequences that include said camera angle being marked as preferred, and said marking as preferred used to select the plurality of video sequences to use as training data for said AI model, and said preference information includes said marking as preferred.

6. The method of claim 1 , wherein the tagging data is generated automatically based on a viewing popularity detected for frame sequences that include the camera angle, the viewing popularity used to select the plurality of video sequences to use as training data for said AI model.

7. The method of claim 1 , wherein the plurality of video sequences in the dataset are sourced from one or more of a plurality of movies, a plurality of video game recordings, a recording of a live sporting event, or a recording that includes one or more action scenes, and said plurality of video sequences are used for training said AI model;

wherein the AI model is used during said gameplay to adjust the game camera angle in the video game during said gameplay.

8. The method of claim 1 ,

wherein said plurality of video sequences are used for training said AI model;

wherein the AI model is used during said gameplay to adjust the game camera angle in the video game during said gameplay.

9. The method of claim 8 , wherein said game camera angle provides an alternate field of view into scenes of the video game than a field of view programmed by a developer of the video game.

10. A system for dynamically adjusting a camera angle in a video game, comprising:

a game server for executing one or more games for streaming to a client device;

an artificial intelligence (AI) camera angle processor for examining snapshots of video sequences produced and taken during gameplay of the video game from the client device, wherein the snapshots of video sequences include multiple video frames, and said snapshots of video sequences are generated responsive to metadata produced during said gameplay being indicative that an action scene is occurring or about to occur, the snapshots of video sequences are taken from camera angles presented for display to the client device, the examining of the snapshots uses an AI model for identifying a game camera angle to use in producing scenes of the gameplay during said gameplay at the client device, and wherein image content and metadata associated with said snapshots are used by the AI model during said identifying of said game camera angle, wherein said AI model is trained using a dataset of a plurality of video sequences that are associated with tagging data in metadata that identify characteristics of actions occurring in each of the plurality of video sequences, the metadata further includes the camera angle used in each of the plurality of video sequences and said tagging data includes preference information for said camera angle, wherein the plurality of video sequences include video sequences from the video game and other non-video game video sequences, and wherein said tagging data is received from a respective viewer that identifies the preference information for said camera angle;

wherein the game camera angle used for producing the scenes of the gameplay provide an alternate field of view into said scenes than a field of view programmed by a developer of the video game;

a streaming server configured to compress video frames for said produced scenes that include said camera angle having said alternate field of view, the streaming server configured to transmit the compressed video frames to said client for presentation on a display that is viewable during said gameplay.

11. The system of claim 10 , wherein the examining of the snapshots using an AI model to identify a game camera angle is processed during periods of times when gaming activity exceeds a predefined threshold.

12. The system of claim 10 , wherein the examining of the snapshots using an AI model to identify the game camera angle is not processed during periods of times when gaming activity does not exceed a predefined threshold.

13. The system of claim 10 , wherein said snapshots are additionally not generated during periods of times when gaming activity does not exceed a predefined threshold.

14. The system of claim 10 , wherein the game camera angle, when selected to change from one programmed by the developer, is executed by a game engine so that said scenes into the video game are produced for rendering said video frames being streamed to said client.