游戏AI行为规划方法、装置、设备及存储介质
By selecting and evolving primary behavioral actions from a pool of behavioral targets, generating and calculating weights, the problem of low efficiency in action path planning for game AI is solved, improving the gaming experience and reducing costs.
CN116173510BActive Publication Date: 2026-07-17SHENZHEN SIMPLE PLAY INFORMATION TECHNOLOGY CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN SIMPLE PLAY INFORMATION TECHNOLOGY CO LTD
- Filing Date
- 2022-12-06
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
In existing technologies, game AI cannot find the most favorable route for game progress when performing intelligent path planning, resulting in a significant waste of time and manpower.
Method used
By selecting a first-level behavior action from the behavior target pool, using a preset algorithm to evolve it, multiple behavior plans are generated, and the fitting weights are calculated to obtain the target behavior plan.
Benefits of technology
It improves the player's gaming experience, reduces reliance on dedicated servers, lowers training costs, and enables behavior planning that is more in line with the game scenario.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116173510B_ABST
Abstract
本发明属于人工智能技术领域，公开了一种游戏AI行为规划方法、装置、设备及存储介质；该发明包括：根据当前参考信息从行为目标池中选择一级行为动作；通过预设算法对一级行为动作进行演化，得到目标行为动作后，根据一级行为动作与目标行为动作生成多个行为规划；计算每个行为规划的拟合权重；根据拟合权重得到基于当前参考信息的目标行为规划；本发明通过当前参考信息选择游戏AI的一级行为动作，对一级行为动作不断分解后得到的行为动作作为目标行为动作，该目标行为动作更符合当前游戏场景，再将每个分解的行为动作连接成一条行为动作规划；后台根据行为动作不断进行权重更新得到最优体验感的行为规划，有效提高玩家游戏体验感。
Need to check novelty before this filing date? Find Prior Art