基于Attention机制与LRUA模块的ESports行为模式预测模型

计算机科学 ›› 2019, Vol. 46 ›› Issue (11A): 76-79.

基于Attention机制与LRUA模块的ESports行为模式预测模型

于诚¹, 朱皖宁¹, 游坤¹, 朱金付²

(金陵科技学院软件工程学院南京211169)¹;
(中国传媒大学南广学院南京211172)²

出版日期:2019-11-10 发布日期:2019-11-20
通讯作者: 朱皖宁(1983－),男,博士,主要研究方向为量子计算,E-mail:zhuwanning@jit.edu。
作者简介:于诚(1997-),男,主要研究方向为机器学习,E-mail:17766006696@foxmail.com。
基金资助:
本文受江苏省高等学校自然科学研究面上项目(17KJB510054),云环境服务质量保障技术(jit-b-201705),金陵科技学院高层次人才科研启动基金资助(jit-b-201624),国家自然科学基金(61502101),江苏省品牌软件工程(40715108)资助。

Prediction Model of E-sports Behavior Pattern Based on Attention Mechanism and LRUA Module

YU Cheng¹, ZHU Wan-ning¹, YOU Kun¹, ZHU Jin-fu²

(Department of Software Engineering,Jinling Institute of Technology,Nanjing 211169,China)¹;
(Communication University of China,Nanjing 211172,China)²

Online:2019-11-10 Published:2019-11-20

摘要/Abstract

摘要： 随着电子竞技产业的不断发展,对电子竞技比赛进行准确且快速的数据分析显得越来越重要。文中对电子竞技行为模式预测这一重要问题进行了研究。从度量学习的角度出发,通过引入修正余弦度量替代余弦度量的方法,改善了行为模式预测因为队伍评价尺度不同而导致模型不精确的问题。同时,为了进一步提高模型的精确度,从文中数据的特征出发,考虑到该问题较为注重数据的内容,因此引入LRUA模块进行内存的存取。实验表明,所提模型具有较高的准确率以及较低的波动性。

关键词: 电子竞技, 度量学习, 匹配网络, 行为模式预测, 元学习

Abstract: With the development of e-sports industry,it is more and more important to analyze data accurately and quickly.This paper studied the prediction of e-sports behavior pattern .From the perspective of measurement learning,the model inaccuracy of the prediction of e-sports behavior pattern caused by different evaluation scales of teams is improved by introducing modified cosine measure instead of cosine measure.Meanwhile,in order to further improve the accuracy of the model,this paper started from the characteristics of the data in this paper.Considering that this paper pays more attention to the content of data,LRUA module is introduced for memory access.Experiments show that the proposed model has high accuracy and low volatility.

Key words: Behavioral model prediction, Esports, Matching networks, Meta-learning, Metric learning

中图分类号:

TP18

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[J]. 计算机科学, 2019, 46(11A): 76-79. https://doi.org/

YU Cheng, ZHU Wan-ning, YOU Kun, ZHU Jin-fu. Prediction Model of E-sports Behavior Pattern Based on Attention Mechanism and LRUA Module[J]. Computer Science, 2019, 46(11A): 76-79. https://doi.org/

参考文献

[1]王竟成.我国电子竞技发展的机遇和挑战[J].河南教育学院学报(自然科学版),2018(4).
[2]SEMENOV A,ROMOV P,KOROLEV S,et al.Performance of Machine Learning Algorithms in Predicting Game Outcome from Drafts in Dota 2[C]∥International Conference on Analysis of Images.2016.
[3]RIOULT F,MÉTIVIER J P,HELLEU B,et al.Mining Tracks of Competitive Video Games [J].Aasri Procedia,2014,8:82-87.
[4]WANG K,SHANG W.Outcome prediction of DOTA2 based on Naïve Bayes classifier[C]∥IEEE/ACIS International Conference on Computer & Information Science.2017.
[5]CHEN Z X,et al.Modeling Game Avatar Synergy and Opposition through Embedding in Multiplayer Online Battle Arena Games[J].aarXiv:1803.10402,2018.
[6]朱益立.关联规则算法研究及其在电子竞技中的应用[D].桂林:桂林电子科技大学,2017.
[7]YU C,ZHU W N,LI L L,et al.Research on E-sports session identification[C]∥MATEC Web of Conferences.EDP Sciences,2018:10011.
[8]LI L L,ZHU W N,YU C,et al.Esports analysis data acquisition algorithm based on convolutional neural network[C]∥MATEC Web of Conferences.EDP Sciences,2018,189:03003.
[9]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(S2):149-151,175.
[10]VINYALS O,BLUNDELL C,LILLICRAP T,et al.Matchingnetworks for one shot learning[C]∥Advances in Neural Information Processing Systems.2016:3630-3638.
[11]SANTORO A,BARTUNOV S,BOTVINICK M,et al.Meta-learning with memory-augmented neural networks[C]∥International Conference on Machine Learning.2016:1842-1850.
[12]VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[C]∥Advances in Neural Information Processing Systems.2017:5998-6008.
[13]李海林,郭崇慧.时间序列数据挖掘中特征表示与相似性度量研究综述[J].计算机应用研究,2013,30(5):1285-1291.
[14]马宏伟,张光卫,李鹏.协同过滤推荐算法综述[J].小型微型计算机系统,2009,30(7):1282-1288.
[15]SAHU S K,ANAND A.Drug-Drug Interaction Extraction from Biomedical Text Using Long Short Term Memory Network[J].Journal of Biomedical Informatics,2017:S1532046418301606.

相关文章 12

[1]	齐秀秀, 王佳昊, 李文雄, 周帆. 基于概率元学习的矩阵补全预测融合算法 Fusion Algorithm for Matrix Completion Prediction Based on Probabilistic Meta-learning 计算机科学, 2022, 49(7): 18-24. https://doi.org/10.11896/jsjkx.210600126
[2]	侯夏晔, 陈海燕, 张兵, 袁立罡, 贾亦真. 一种基于支持向量机的主动度量学习算法 Active Metric Learning Based on Support Vector Machines 计算机科学, 2022, 49(6A): 113-118. https://doi.org/10.11896/jsjkx.210500034
[3]	周颖, 常明新, 叶红, 张燕. 基于元迁移的太阳能电池板缺陷图像超分辨率重建方法 Super Resolution Reconstruction Method of Solar Panel Defect Images Based on Meta-transfer 计算机科学, 2022, 49(3): 185-191. https://doi.org/10.11896/jsjkx.210100234
[4]	刘洋, 李凡长. 基于变分贝叶斯的纤维丛元学习算法 Fiber Bundle Meta-learning Algorithm Based on Variational Bayes 计算机科学, 2022, 49(3): 225-231. https://doi.org/10.11896/jsjkx.201100111
[5]	吴少波, 傅启明, 陈建平, 吴宏杰, 陆悠. 基于相对熵的元逆强化学习方法 Meta-inverse Reinforcement Learning Method Based on Relative Entropy 计算机科学, 2021, 48(9): 257-263. https://doi.org/10.11896/jsjkx.200700044
[6]	陆嘉猷, 凌兴宏, 刘全, 朱斐. 基于自适应调节策略熵的元强化学习算法 Meta-reinforcement Learning Algorithm Based on Automating Policy Entropy 计算机科学, 2021, 48(6): 168-174. https://doi.org/10.11896/jsjkx.200600133
[7]	王一丰, 郭渊博, 李涛, 孔菁. 小样本下未知内部威胁检测的方法研究 Method for Unknown Insider Threat Detection with Small Samples 计算机科学, 2019, 46(11A): 496-501.
[8]	于诚, 朱皖宁. 基于战场热点图的MOBA类游戏战术分析研究 Tactical Analysis of MOBA Games Based on Hotspot Map of Battlefield 计算机科学, 2018, 45(11A): 149-151.
[9]	文俊浩, 戴大文, 余俊良, 高旻, 张宜浩. 融合矩阵分解与距离度量学习的社会化推荐算法 Social Recommendation Method Integrating Matrix Factorization and Distance Metric Learning 计算机科学, 2018, 45(10): 196-201. https://doi.org/10.11896／j.issn.1002-137X.2018.10.036
[10]	梁路,龚奔龙,黎剑,滕少华. 一种缓解分类面交错的样本点扩散方法 Diffusion Method of Sample Points for Alleviating Staggered Situation of Classification 计算机科学, 2017, 44(9): 286-289. https://doi.org/10.11896/j.issn.1002-137X.2017.09.053
[11]	. 知识网格环境下基于TMs的协同认知计算机科学, 2006, 33(5): 222-226.
[12]	. 非平衡数据训练方法概述计算机科学, 2005, 32(10): 181-186.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed