基于战场热点图的MOBA类游戏战术分析研究

计算机科学 ›› 2018, Vol. 45 ›› Issue (11A): 149-151.

基于战场热点图的MOBA类游戏战术分析研究

于诚¹, 朱皖宁^1,2

金陵科技学院软件工程学院南京211169¹
东南大学计算机科学与工程学院南京 211189²

出版日期:2019-02-26 发布日期:2019-02-26
通讯作者: 朱皖宁(1983-),男,博士,讲师,主要研究方向为量子计算,E-mail:granny025@163.com
作者简介:于诚(1997-),男,主要研究方向为人工智能,E-mail:1072038904@qq.com
基金资助:
本文受金陵科技学院高层次人才科研启动基金:基于量子算法的Web用户行为分析与研究项目(jit-b-201624)资助。

Tactical Analysis of MOBA Games Based on Hotspot Map of Battlefield

YU Cheng¹, ZHU Wan-ning^1,2

Department of Software Engineering,Jinling Institute of Technology,Nanjing 211169,China¹
Department of Computer Science and Engineering,Southeast University,Nanjing 211189,China²

Online:2019-02-26 Published:2019-02-26

摘要/Abstract

摘要： 摘要随着电子竞技产业不断发展,除了经验、天赋、技巧等决胜因素外,数据分析对MOBA游戏的胜负手影响越来越大。针对某些MOBA类游戏无法直接通过接口获得准确数据的问题,提出根据官方提供的热点图来对核心人物的位置数据进行预处理,利用原型聚类算法思想的PNN(Probabilistic Nearest Neighbor)算法对热点图进行战术分析,最后以概率的形式导出战术:对战方核心人物去往战场核心点的移动概率。本算法加入了加权距离以改善KNN利用欧氏距离计算样本点之间差异的不足,并利用最小二乘法来取得最优的常数解;同时对所有的距离数据进行归一化处理,提高了算法准确度。最终实验表明了所提方法预测战场核心人物去往核心点的概率的有效性。

关键词: MOBA战术分析, PNN算法, 电子竞技, 加权距离, 最小二乘法

Abstract: With the continuous development of the e-sports industry,except for the decisive factors such as experience,talent and skills,data analysis has an increasing influence on the winners and losers of MOBA games.For the problem that some MOBA games are unable to obtain accurate data directly through the interface,this paper proposed a method that gives pretreatment for position data according to the official heat maps and used PNN (Probabilistic Nearest Neighbor) with the idea of prototype clustering for tactical analysis.Finally,tactics is derived in the form of a probability:mobile probability for core characteristics of sides to core of the battle.In this algorithm,weighted distance is added to improve KNN’s shortcoming of using Euclidean distance to calculate the difference between sample points,and the least square method is used to obtain the optimal constant solution.At the same time,all distance data are normalized to improve the accuracy of the algorithm.The final experiment shows that this method is effective in predicting the probability of the core point of the battlefield.

Key words: E-sports, Least square method, MOBA tactical analysis, PNN algorithm, Weighted distance

中图分类号:

TP391

于诚, 朱皖宁. 基于战场热点图的MOBA类游戏战术分析研究[J]. 计算机科学, 2018, 45(11A): 149-151. https://doi.org/

YU Cheng, ZHU Wan-ning. Tactical Analysis of MOBA Games Based on Hotspot Map of Battlefield[J]. Computer Science, 2018, 45(11A): 149-151. https://doi.org/

参考文献

[1]何培奕.中国电子竞技产业的现状和发展研究[D].上海:上海外国语大学,2013.
[2]张锐.中国电子竞技进入最好的时代[N].证券时报,2017-10-10(A03).
[3]任一彬.中国电竞英雄联盟中国队S5季中赛制胜因素分析[D].西北师范大学,2016.
[4]田绍兴,陈劲杰.基于KNN的手写数字的识别[J/OL].农业装备与车辆工程,2017(10):96-97,100.http://kns.cnki.net/kcms/detail/37.1433.TH.20171024.0703.044.html.
[5]SEBASTIANI F.Machine learning in automated text catagori-zaition [J].ACM Computing Surveys,2002,31(2):1-17.
[6]李航.统计学习方法 [M].北京:清华大学出版社,2012:37-45.
[7]丁克良,沈云中,欧吉坤.整体最小二乘法直线拟合[J].辽宁工程技术大学学报(自然科学版),2010,29(1):44-47.
[8]ALISON J,DUFFIELD S J,MORECROFT M D,et al.Successful restoration of moth abundance and species-richness in grassland created under agri-environment schemes[J].Biological Conservation,2017,213:51-58.
[9]KIM J,HONG T,JEONG J,et al.An integrated psychological response score of the occupants based on their activities and the indoor environmental quality condition changes[J].Building and Environment,2017,123:66-77.
[10]DECUYPER J,DE TROYER T,RUNACRES M C,et al.Nonlinear state-space modelling of the kinematics of an oscillating circular cylinder in a fluid flow[J].Mechanical Systems and Signal Processing,2018,98:209-230.
[11]LIN Z Y,ZHANG L X.Convergence to a self-normalized G-Brownian motion[J].Probability,Uncertainty and Quantitative Risk,2017,2(1):4.

相关文章 15

[1]	唐佳林, 张冲, 郭岩锋, 苏秉华, 苏清朗. 融合多颜色空间信息的彩色图像色差校正算法 Color Difference Correction Algorithm Based on Multi Colors Space Information 计算机科学, 2020, 47(6A): 157-160. https://doi.org/10.11896/JsJkx.190800026
[2]	宋瑞阳, 孟华, 龙治国. 基于数据分布特征的线性孪生支持向量机 Linear Twin Support Vector Machine Based on Data Distribution Characteristics 计算机科学, 2019, 46(6A): 407-411.
[3]	于诚, 朱皖宁, 游坤, 朱金付. 基于Attention机制与LRUA模块的ESports行为模式预测模型 Prediction Model of E-sports Behavior Pattern Based on Attention Mechanism and LRUA Module 计算机科学, 2019, 46(11A): 76-79.
[4]	李栋, 薛惠锋. 基于混合模型的中长期降水量预测 Forecasting of Medium and Long Term Precipitation Based on Hybrid Model 计算机科学, 2018, 45(9): 271-278. https://doi.org/10.11896／j.issn.1002-137X.2018.09.045
[5]	张福旺, 苑会娟. 基于多元线性回归的空腹血糖影响因素分析方法 Analysis of Factors Influencing Fasting Plasma Glucose Based on Multiple Linear Regression 计算机科学, 2018, 45(11A): 545-547.
[6]	陈海鹏,卢旭旺,申铉京,杨英卓. 基于多元线性回归的螺纹钢价格分析及预测模型 Analysis and Prediction on Rebar Price Based on Multiple Linear Regression Model 计算机科学, 2017, 44(Z11): 61-64. https://doi.org/10.11896/j.issn.1002-137X.2017.11A.011
[7]	冷亚洪. 移动最小二乘代理模型支持域半径的优化方法 Optimization Method of Support Domain Radius of Moving Least Squares Agent Model 计算机科学, 2016, 43(Z6): 95-98. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.023
[8]	许漂漂,卜旭辉. 数据丢失情况下的最小二乘参数辨识算法 System Identification with Data Dropout 计算机科学, 2016, 43(Z11): 42-44. https://doi.org/10.11896/j.issn.1002-137X.2016.11A.009
[9]	姚杏,朱福喜,阳小兰,郑麟,刘世超. 上下文分解机的自适应更新策略 Adaptive Parameters Updating Strategy of Context-aware Factorization Machines 计算机科学, 2016, 43(9): 71-76. https://doi.org/10.11896/j.issn.1002-137X.2016.09.013
[10]	陆成刚. 与数据挖掘相关的整数矩阵的左右可逆性研究 Research on Left-Right Invertibility for Integer Matrix Related with Data Mining 计算机科学, 2016, 43(5): 247-251. https://doi.org/10.11896/j.issn.1002-137X.2016.05.046
[11]	熊喆,贾杰,陈剑. 无线传感器网络中基于虚拟力的分布式节点定位 Distributed Localization Scheme Based on Virtual Force in Wireless Sensor Networks 计算机科学, 2016, 43(2): 109-112. https://doi.org/10.11896/j.issn.1002-137X.2016.02.025
[12]	徐洁. 补丁校准框架下的最大模糊边界投影 Maximum Fuzzy Marginal Projection via Patch Alignment Framework 计算机科学, 2016, 43(1): 282-285. https://doi.org/10.11896/j.issn.1002-137X.2016.01.060
[13]	吴迎昌,罗滇生,何洪英. 基于TLS估计的遗传小波红外图像去噪方法 Infrared Image De-noising Method Based on Genetic Wavelet of TLS 计算机科学, 2015, 42(4): 281-284. https://doi.org/10.11896/j.issn.1002-137X.2015.04.058
[14]	徐衍鲁,马燕,李顺宝,张相芬. 结合颜色不变量的SIFT和形状上下文图像匹配算法 Algorithm of Image Matching Based on Color SIFT and Shape Context 计算机科学, 2014, 41(Z11): 144-146.
[15]	张继法，梅雪，许松松，胡石. 一种基于双椭圆模型的视频人数统计方法 Method of Video People Counting Based on Double_ellipse Model 计算机科学, 2012, 39(Z6): 499-502.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed