| 96 | 0 | 129 |
| 下载次数 | 被引频次 | 阅读次数 |
表现分析是足球比赛数据分析中的关键环节之一，能够帮助分析师和教练员分析球队的优缺点，提高未来比赛的获胜概率。随着人工智能技术的发展，众多研究者致力于将人工智能技术应用到足球表现分析中。从比赛行为表现分析、球员表现分析、球队表现分析3个层面，对人工智能技术在足球表现分析中的应用进行总结。在此基础上，提出了足球表现智能分析的研究框架，并对目前面临的挑战以及未来研究方向进行展望，包括基于大语言模型的足球表现智能分析以及结合多源数据的足球表现智能分析。
Abstract：Performance analysis is one of the key components of soccer match data analysis, as it enables analysts and coaches to evaluate a team's strengths and weaknesses, thereby increasing the probability of winning future matches. With the advancement of artificial intelligence(AI)technologies, many researchers have been dedicated to applying AI to football performance analysis. This paper summarizes the applications of AI in football performance analysis from three perspectives: match behavior analysis, player performance analysis, and team performance analysis. On this basis, it proposes a research framework for intelligent football performance analysis and discusses the current challenges as well as future research directions, including AIbased performance analysis driven by large language models and intelligent performance analysis that integrates multi-source data.
[1]FIFA. Tournaments[EB/OL].[2025-12-25]. https://www.fifa.com/en/tournaments.
[2]龚炳南.足球比赛表现分析理论与应用研究[D].北京：北京体育大学,2020.
[3]易清,黎涌明,张铭鑫,等.运动表现分析：过去、现在与未来[J].上海体育学院学报,2023,47(2):88-103.
[4]BEAL R, NORMAN T J, RAMCHURN S D. Artificial intelligence for team sports:A survey[J]. The Knowledge Engineering Review, 2019, 34:e28.
[5]PAPPALARDO L, CINTIA P, ROSSI A, et al. A public data set of spatio-temporal match events in soccer competitions[J]. Scientific Data, 2019, 6:236.
[6]CIOPPA A, DELIEGE A, GIANCOLA S, et al. A contextaware loss function for action spotting in soccer videos[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Seattle, WA, USA. IEEE,2020:13123-13133.
[7]CIOPPA A, GIANCOLA S, DELIEGE A, et al. SoccerNet-tracking:Multiple object tracking dataset and benchmark in soccer videos[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW). New Orleans, LA, USA. IEEE, 2022:3490-3501.
[8]DECROOS T, BRANSEN L, VAN HAAREN J, et al.Actions speak louder than goals:Valuing player actions in soccer[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery&Data Mining. Anchorage AK USA. ACM, 2019:1851-1861.
[9]FERN??NDEZ J. BORNN L, CERVONE D. Decomposing the immeasurable sport:A DeepLearning expected possession value framework for soccer[C]. 2019 MIT Sloan Sports Analytics Conference, 2019.
[10]MERHEJ C, BEAL R J, MATTHEWS T, et al. What happened next? Using deep learning to value defensive actions in football event-data[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery&Data Mining. Virtual Event Singapore. ACM, 2021:3394-3403.
[11]ROBBERECHTS P, VAN ROY M, DAVIS J. Un-xPass:Measuring soccer player's creativity[C]//Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Long Beach CA USA. ACM,2023:4768-4777.
[12]POWER P, RUIZ H, WEI X Y, et al. Not all passes are created equal:Objectively measuring the risk and reward of passes in soccer from tracking data[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Halifax NS Canada. ACM, 2017:1605-1613.
[13]LIU G L, LUO Y D, SCHULTE O, et al. Deep soccer analytics:Learning an action-value function for evaluating soccer players[J]. Data Mining and Knowledge Discovery, 2020, 34(5):1531-1559.
[14]CAO A Q, XIE X, ZHOU M X, et al. Action-evaluator:A visualization approach for player action evaluation in soccer[J]. IEEE Transactions on Visualization and Computer Graphics, 2024, 30(1):880-890.
[15]MCHALE I G, SCARF P A, FOLKER D E. On the development of a soccer player performance rating system for the English premier league[J]. Interfaces, 2012, 42(4):339-351.
[16]BROOKS J, KERR M, GUTTAG J. Developing a datadriven player ranking in soccer using predictive model weights[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco California USA. ACM, 2016:49-55.
[17]PAPPALARDO L, CINTIA P, FERRAGINA P, et al.PlayeRank:Data-driven performance evaluation and player ranking in soccer via a machine learning approach[J]. ACM Transactions on Intelligent Systems and Technology, 2019, 10(5):1-27.
[18]JANETZKO H, SACHA D, STEIN M, et al. Featuredriven visual analytics of soccer data[C]//2014 IEEE Conference on Visual Analytics Science and Technology(VAST). Paris, France. IEEE, 2015:13-22.
[19]CAO A Q, XIE X, ZHANG R J, et al. Team-scouter:Simulative visual analytics of soccer player scouting[J].IEEE Transactions on Visualization and Computer Graphics, 2025, 31(1):1-11.
[20]DECROOS T, VAN HAAREN J, DAVIS J. Automatic discovery of tactics in spatio-temporal soccer match data[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery&Data Mining.London United Kingdom. ACM, 2018:223-232.
[21]MALQUI J L S, ROMERO N M L, GARCIA R, et al.How do soccer teams coordinate consecutive passes? A visual analytics system for analysing the complexity of passing sequences using soccer flow motifs[J]. Computers&Graphics, 2019, 84:122-133.
[22]LUCEY P, OLIVER D, CARR P, et al. Assessing team strategy using spatiotemporal data[C]//Proceedings of the19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Chicago Illinois USA.ACM, 2013:1366-1374.
[23]WANG Z, VELI??KOVI??P, HENNES D, et al. TacticAI:An AI assistant for football tactics[J]. Nature Communications, 2024, 15:1906.
[24]SHAO L, SACHA D, NELDNER B, et al. Visual-interactive search for soccer trajectories to identify interesting game situations[J]. Electronic Imaging, 2016, 28(1):1-10.
[25]SACHA D, AL-MASOUDI F, STEIN M, et al. Dynamic visual abstraction of soccer movement[J]. Computer Graphics Forum, 2017, 36(3):305-315.
[26]Anzer G, Bauer P, Brefeld U, et al. Detection of tactical patterns using semi-supervised graph neural networks[C].2022 MIT Sloan Sports Analytics Conference, 2022.
[27]BIALKOWSKI A, LUCEY P, CARR P, et al. Identifying team style in soccer using formations learned from spatiotemporal tracking data[C]//2014 IEEE International Conference on Data Mining Workshop. Shenzhen, China.IEEE, 2015:9-14.
[28]BEAL R, CHANGDER N, NORMAN T, et al. Learning the value of teamwork to form efficient teams[J]. Proceedings of the AAAI Conference on Artificial Intelligence,2020, 34(5):7063-7070.
[29]BRANSEN L, VAN HAAREN J. Player chemistry:Striving for a perfectly balanced soccer team[EB/OL].[2025-12-25]. https://arxiv.org/abs/2003.01712.
[30]XIE X, WANG J C, LIANG H Y, et al. PassVizor:Toward better understanding of the dynamics of soccer passes[J]. IEEE Transactions on Visualization and Computer Graphics, 2021, 27(2):1322-1331.
[31]PERIN C, VUILLEMOT R, FEKETE J D. SoccerStories:A kick-off for visual soccer analysis[J]. IEEE Transactions on Visualization and Computer Graphics, 2013, 19(12):2506-2515.
[32]ANDRIENKO G, ANDRIENKO N, ANZER G, et al.Constructing spaces and times for tactical analysis in football[J]. IEEE Transactions on Visualization and Computer Graphics, 2021, 27(4):2280-2297.
[33]SEEBACHER D, POLK T, JANETZKO H, et al. Investigating the sketchplan:A novel way of identifying tactical behavior in massive soccer datasets[J]. IEEE Transactions on Visualization and Computer Graphics, 2023, 29(4):1920-1936.
[34]CAO A Q, LAN J, XIE X, et al. Team-builder:Toward more effective lineup selection in soccer[J]. IEEE Transactions on Visualization and Computer Graphics, 2023, 29(12):5178-5193.
[35]曹安琪,陈泓宇,谢潇,等.足球比赛数据可视分析[J].大数据,2021,7(2):15-31.
基本信息:
中图分类号:G843
引用信息:
[1]曹安琪,谢潇,刘子奥,等.人工智能技术在足球表现分析中的应用[J].体育科研,2026,47(01):56-63+104.
基金信息:
国际足联“前进计划”
2026-01-15
2026-01-15