Unlock instant, AI-driven research and patent intelligence for your innovation.

Prediction method of game win rate and model generation method and device

A prediction model and winning rate technology, applied in the field of games, can solve problems such as non-real-time prediction

Active Publication Date: 2019-06-25
NETEASE (HANGZHOU) NETWORK CO LTD
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] At present, the prediction of the outcome of the game is only to predict the outcome of the game. It is either non-real-time prediction, non-combat prediction, or only prediction of the outcome. Therefore, a more reasonable and intuitive experience is needed. A better game outcome prediction solution

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Prediction method of game win rate and model generation method and device
  • Prediction method of game win rate and model generation method and device
  • Prediction method of game win rate and model generation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0094] In order to make the above objects, features and advantages of the present application more obvious and comprehensible, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0095] refer to figure 1 , which shows a flow chart of the steps of an embodiment of a method for predicting the winning rate of a game of the present application, which may specifically include the following steps:

[0096] Step 101, obtaining feature data of the predicted time point in the real-time game combat data;

[0097] For the convenience of description and understanding, the embodiment of the present application uses a multiplayer online battle arena (Multiplayer Online Battle Arena, MOBA) as an example for illustration. In the MOBA online game scene, players are usually divided into two teams, and the two teams compete with each other on a scattered game map. In the map, in addition to the vi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the invention provides a prediction method of the game win rate and a model generation method and device. The prediction method comprises the steps that feature data of a predictiontime point in real-time game combat data is acquired, comprises real-time state data and team position data and is input in a preset time-share prediction model corresponding to the prediction time point, wherein the time-share prediction model has a plurality of output nodes; a plurality of prediction results output by the output nodes of the time-share prediction model are acquired, and win rateprediction information is generated according to the prediction results. Through the preset time-share prediction model, the game win rate of each side participating in a game is predicted in real time, it can be achieved that in the game process, at the prediction time point, the win rate of each side participating in the game is dynamically predicted, and the game experience of users is improved; in the process of watching the game or during live broadcasting of the game, through prediction of the real-time win rate, people who watch the game can conveniently know the combat field situationbetter, and the interest of watching the game is added.

Description

technical field [0001] The present application relates to the technical field of games, in particular to a game winning rate prediction method, a time-sharing prediction model generation method, a game winning rate prediction device and a time-sharing prediction model generation device. Background technique [0002] Driven by the wave of artificial intelligence (AI) development, game AI has also entered the high-speed road of development in recent years. Whether it is the alpha go of Go or the open AI of DOTA2, it is a major breakthrough of AI in the field of games, subverting the In the past, people's perception of the limits of AI. [0003] The game itself can have a relatively complete mapping relationship with the real world. Solving game problems shows its ability to solve real-world problems to a certain extent. Therefore, the development of game AI also plays an important and positive role in the development of human society. effect. As far as the game AI itself is ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): A63F13/70A63F13/798A63F13/822
Inventor 蔡康
Owner NETEASE (HANGZHOU) NETWORK CO LTD