Speculative rendering using historical player data

摘要

Technologies are presented for reducing lag time via speculative graphics rendering in cloud based gaming. In some examples, historical data about statistically relevant large populations of players is provided. The historical data may include state transitions through various game locations or situations. In some of the game locations there may be a correlation between a probability of a particular upcoming scene and a player state. Example game locations or situations may include areas that players tend to cross in one or more straight lines, corners that players may round in a particular fashion, spots where certain player motions are commonly engaged in, such as looking up, and the like. The historical data may be tested against a certain predictive strength and rendered predicted game states may be prepared ahead of player need.

主权项

1. A computing device configured to render graphics speculatively, the computing device comprising:
a memory embodied in a memory circuit; and a processor embodied in an integrated circuit and coupled to the memory, the processor configured to execute a game service application, wherein the game service application includes a speculative rendering graphics module that is configured to:
receive an input on a user interface;determine speculative input values of the input, wherein the speculative input values define a first game state of a first game client;transmit a search request to a data storage device configured to store a state transition database, wherein the state transition database includes state transition data for the first game client and a second game client;receive a response from the data storage device that identifies a state transition, wherein the state transition corresponds to the first game state;determine a probability threshold in response to the first state transition, wherein the probability threshold is determined based on a game rule stored in the memory and one or more of: a game scenario, a usage history of the first game client, a usage history of the first game client and the second game client, a computational cost, and a network cost;adjust the first game state according to the game rule stored in the memory;determine a predicted game state according to a comparison of the first state transition and the probability threshold;analyze the state transition data for the first game client against the predicted game state; anddisplay the predicted game state on the user interface.