Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Game non-player character (NPC) action based on neural network

A neural network and behavioral technology, applied in the field of artificial intelligence in game servers, can solve problems such as losing game fun, and achieve the effect of improving rationality and enriching game experience

Inactive Publication Date: 2013-02-13
SHENYANG XINDA INFORMATION SCI & TECH
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This approach results in Npcs having a fixed behavior model
And as the player's understanding of their behavior deepens, the player will eventually defeat the monster
But in this process, the cognition of the monster will not increase with the growth of the player's cognition, so that the player will lose the fun of the game

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] A kind of game Npc behavior based on neural network, its steps are as follows:

[0016] 1) According to the possible behaviors of Npc or monster, create the state set and strategy set of the agent;

[0017] 2) Generate a corresponding reward function according to the result that the agent wants to obtain;

[0018] 3) Construct a neural network according to the state machine and strategy set;

[0019] 4) Select an Npc behavior based on the input of the current neural network;

[0020] 5) Obtain the reward value generated by the behavior;

[0021] 6) The neural network is trained by the reward value acting on the neural network.

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 invention relates to the aspect of artificial intelligence, in particular to an artificial intelligence method in a game server. A neural network technology is added to the logic control of the game server so that the intelligent object of a game has a 'soul'. Actions of all non-player characters (NPC) are not arranged in advance any more, the longer the game is played, the more the game evolves and learns, and accordingly the game is good in adaptability. Therefore, the game can grow along with a player who cannot forecast game actions so that the life cycle of the game can be prolonged, various intelligent objects in the game can become smart, the reasonability of the scheme of the player can be continuously improved according to the scheme of the user, and accordingly the player can adjust the game, and game experience can be enriched.

Description

[0001] technical field [0002] The present invention relates to artificial intelligence, and more specifically, to an artificial intelligence method in a game server. Background technique [0003] The application of game artificial intelligence (AI) has made a qualitative leap in game development. High-quality game AI is no longer considered just to improve the frame rate, but a decisive factor that promotes or hinders the sales of game products. Therefore, game developers do their best to research new AI technologies to build better and smarter game AIs to attract as many players as possible and increase product sales. [0004] In today's large-scale online games, state machines are generally used to control the behavior of monsters and NPCs. This approach results in Npcs having a fixed behavior model. And as the player's understanding of their behavior deepens, eventually the player will defeat the monster. But in this process, the cognition of the monster will no...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/08G06F19/00
Inventor 不公告发明人
Owner SHENYANG XINDA INFORMATION SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products