Application of Generative Artificial Intelligence in Games

DOI: https://doi.org/10.62517/jike.202604229

Author(s)

Wanting Zhang

Affiliation(s)

Fujian Jiangxia University, Fuzhou, Fujian, China *Corresponding Author

Abstract

With the rapid expansion of the game industry, it is difficult for the traditional development model to meet the demand for personalised and real-time content. This study adopts information research and case study methods to study representative games using generative artificial intelligence (AIGC). Research results show that in game design, AIGC accelerates art generation, plot creation and scene construction; in game operation, it enhances user behaviour analysis, intelligent customer service and personalised recommendation; in game marketing, it achieves automatic advertising, social media content generation and user analysis. These applications significantly improve productivity, reduce costs, and optimise user experience. Based on these case-based findings, this paper puts forward actionable industry recommendations on technology integration, data governance, innovative applications and cost-effectiveness assessment.

Keywords

Generative Artificial Intelligence; Game Design; Game Operation; Game Marketing

References

[1] Holland, J. H. (1975). Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence. University of Michigan Press, Ann Arbor. [2] Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A.C., Bengio, Y. (2014) Generative Adversarial Nets. In: Advances in Neural Information Processing Systems 27. Montreal. pp. 2672-2680. [3] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I., (2017). Attention is all you need. https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf [4] Radford, A., Narasimhan, K., Salimans, T., & Sutskever, I., (2018). Improving language understanding by generative pre-training. https://cdn.openai.com/research-covers/language-unsupervised/language_ understanding_paper.pdf. [5] Li, W., Ma, J., Long, J., Li, J., Song, Y., Hu, J. (2024) SoftGAN: Improving GAN training with a dynamic boundary softening mechanism. Int. J. Autom. Comput., 21: 187–201. [6] Guo, Q. , Wan, J. , Xu, S. , Li, M. , & Wang, Y. (2024). HG-PIPE: Vision Transformer Acceleration with Hybrid-Grained Pipeline. https://doi.org/10.48550/arXiv.2407.17879 [7] Chen Fan, Chen Liu Ming, Wang Man, Xu Hongqi, & Zhou Xiaoyu. (2024). Controllable generation method for wind and solar power output scenarios based on improved information-maximization generative adversarial networks. Power Grid Technology, 4: 1477-1486. [8] Guo, Q., Wan, J., Xu, S., Li, M., Wang, Y. (2024) HG-PIPE: Vision Transformer Acceleration with Hybrid-Grained Pipeline. In: Proceedings of the 2024 IEEE International Symposium on High-Performance Computer Architecture. Edinburgh, United Kingdom. [9] Chen, D., Liu, Z., Mao, J., Liu, Y., Zhang, M., & Ma, S., (2024). THUIR at the NTCIR-18 Searching for Information about Tasks (Search as Tasks) Task. https://doi.org/10.48550/arXiv.2402.18510 [10] Togelius, J., & Schmidhuber, J. (2006). An experiment in automatic game design. In: Proceedings of the 2006 IEEE Symposium on Computational Intelligence and Games, pp. 111-118. [11] Togelius, J., & Schmidhuber, J. (2008). An experiment in automatic game design. In: Proceedings of the 2008 IEEE Symposium on Computational Intelligence and Games, pp. 111–118. [12] Catanzaro, B. (2018). AI software can dream up an entire digital world from a simple sketch. https://www.technologyreview.com/2018/12/03/138834/ai-software-can-dream-up-an-entire-digital-world-from-a-simple-sketch/ [13] OpenAI. (2020) GPT-3: Language models are few-shot learners. https://doi.org/10.48550/arXiv.2005.14165 [14] Wang, Y., Wang, Y., Yang, J., & Lin, Z. (2021). Reparameterized sampling for generative adversarial networks. https://doi.org/10.48550/arXiv.2107.00352 [15] Chen, X., Cohen-Or, D., Chen, B., & Mitra, N. J. (2021). Towards a neural graphics pipeline for controllable image generation. Computer Graphics Forum, 7: 253–264. [16] Chen, Z., Zhang, J., Xu, D., & Jia, J. (2022). Mip-NeRF 360: Unbounded anti-aliased neural radiance fields. https://doi.org/10.1109/CVPR52688.2022.01114 [17] Liu, Y., Wang, W., & Li, H. (2022). Fast and robust facial expression transfer for digital humans. In Proceedings of the 30th ACM International Conference on Multimedia (ACM MM 2022), 4567–4575. [18] Li, X., Zhang, Y., & Zhou, M. (2022). Adaptive dialogue generation for role-playing games. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2022), 6789–6798. [19] Nie, Y., Zheng, S., Zhuang, Z., & Song, X. (2023). Extend wave function collapse to large-scale content generation. arXiv preprint arXiv:2305.19713. [20] Yu, J., et al. (2023). Dialogue engagement estimation for human‑agent interaction in games. In Proceedings of the 31st ACM International Conference on Multimedia (ACM MM 2023). [21] Li, X., Wang, Y., & Liu, Z. (2023). LLM‑driven interactive story generation with plot control. arXiv preprint arXiv:2310.12053. [22] Huang, Z. (1998). Extensions to the k-means algorithm for clustering large data sets with categorical values. Data Mining and Knowledge Discovery, 2(3), 283–304. https://doi.org/10.1023/A:1009769707641 [23] Shmueli, G., Patel, N. R., & Bruce, P. C. (2005). Data mining for business intelligence: Concepts, techniques, and applications in Microsoft Office Excel with XLMiner. John Wiley & Sons. [24] Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., & Hassabis, D. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529–533. https://doi.org/10.1038/nature14236 [25] Gupta, A., Johnson, J., Fei-Fei, L., Savarese, S., & Alahi, A. (2018). Social GAN: Socially acceptable trajectories with generative adversarial networks. Advances in Neural Information Processing Systems, 31, 2255–2265. [26] Akoury, J., Cvicek, V., & Riedl, M. O. (2020). STORIUM: A dataset and evaluation platform for machine‑in‑the‑loop story generation. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 8001–8014. https://doi.org/10.18653/v1/2020.emnlp-main.656 [27] Ubisoft La Forge (Ubisoft's R&D Department). (2023) The convergence of AI and creativity: Introducing Ghostwriter. https://news.ubisoft.com/en-us/article/7Cm07zbBGy4Xml6WgYi25d/the-convergence-of-ai-and-creativity-presenting-ghostwriter [28] Ruan Jing, Song Jie. (2016). Practical Research on Statistical Methods for User Profiling in the Context of Big Data [D]. Peking University. [29] Lu Tangjie. (2023). AI has quietly transformed the entire process of game development and operation, with domestic manufacturers and generative AI advancing in tandem. http://www.china.com.cn/tech/2023-07/27/content_88954346.shtml [30] Xie, H., Devlin, S., & Kudenko, D. (2016). Predicting disengagement in free-to-play games with highly biased data. Proceedings of the AAAI Conference on Artificial Intelligence, 30(1). [31] Smith, A. M., & Smith, G. (2013). Artificial Intelligence in the Game Design Process: Papers from the 2013 AIIDE Workshop (AAAI Technical Report WS-13-20). AAAI Press. [32] Bau, D., Zhu, J.-Y., Strobelt, H., Zhou, B., Tenenbaum, J. B., & Torralba, A. (2018). GAN dissection: Visualizing and understanding generative adversarial networks. arXiv preprint arXiv:1811.10597. [33] Thanguturi, N. (2018). Automatic News Generation System based on Natural Language. http://rave.ohiolink.edu/etdc/vi ew ?acc_num=toledo1525973404437239 [34] Cai, T., Jiang, J., Zhang, W., Zhou, S., Song, X., Yu, L., Gu, L., Zeng, X., Gu, J., & Zhang, G. (2023). Marketing budget allocation with offline constrained deep reinforcement learning. In Proceedings of the 16th ACM International Conference on Web Search and Data Mining (pp. 243–251). Association for Computing Machinery. https://doi.org/10.1145/3539597.3570470 [35] Wang, H. A., et al. (2022). Ad creative generation using reinforced generative adversarial network. Electronic Commerce Research. https://doi.org/10.1007/s10660-022-09564-6 [36] Li, Y., Zhang, H., & Wang, L. (2023). Game marketing copy generation with Transformer-based pre-trained model on domain-specific corpus. Computational Intelligence and Neuroscience, 2023, 1-12. https://doi.org/10.1155/2023/8927451 [37] Zhuang, S., Li, K., Chen, X., Wang, Y., Liu, Z., Qiao, Y., & Wang, Y. (2024). Vlogger: Make your dream a vlog. arXiv:2401.09414. https://arxiv.org/abs/2401.09414