管理评论

管理评论 ›› 2026, Vol. 38 ›› Issue (9): 248-261.

• 运营与供应链管理 • 上一篇    

基于前景理论的电商平台生成式人工智能虚假信息治理演化博弈分析

李世勇1,2, 杨铮铮1,2, 孙微1,2   

  1. 1. 燕山大学经济管理学院, 秦皇岛 066004;
    2. 燕山大学新质生产力研究中心, 秦皇岛 066004
  • 收稿日期:2024-09-23 发布日期:2026-10-09
  • 作者简介:李世勇，燕山大学经济管理学院教授，燕山大学新质生产力研究中心主任，博士生导师，博士；杨铮铮，燕山大学经济管理学院博士研究生，燕山大学新质生产力研究中心研究助理；孙微（通讯作者），燕山大学经济管理学院、燕山大学新质生产力研究中心教授，博士生导师，博士。
  • 基金资助:
    国家自然科学基金项目(71971188)；教育部人文社会科学研究项目(22YJCZH086；24YJAZH135)。

Evolutionary Game Analysis of Generative Artificial Intelligence Disinformation Governance for E-commerce Platforms Based on Prospect Theory

Li Shiyong1,2, Yang Zhengzheng1,2, Sun Wei1,2   

  1. 1. School of Economics and Management, Yanshan University, Qinhuangdao 066004;
    2. Research Center for New Productive Forces, Yanshan University, Qinhuangdao 066004
  • Received:2024-09-23 Published:2026-10-09

PDF (PC)

16

摘要： 生成式人工智能虚假信息加大了电商平台的信息治理难度，造成AI信息污染问题日益突出。本文基于信息生成与传播视角，将前景理论与演化博弈相结合，构建了包括生成式AI服务提供者、商家、电商平台以及政府在内的四方演化博弈模型，刻画了生成式人工智能虚假信息治理的最优策略，并进行仿真分析。结果表明，对于生成式AI服务提供者来说，技术限制成本和社会影响力会影响其策略选择，并且提高用户的使用费用以及对违规用户的罚金可以有效遏制商家违规使用生成式AI服务；对于电商平台来说，较高的审核专业性可以促进电商行业的信息管理趋于成熟，同时，提高对商家的奖惩力度有助于商家合规使用生成式AI服务，且针对异质性商家应进行差异化治理；对于政府来说，适当提高对生成式AI服务提供者以及电商平台的奖惩力度可以促进二者协同治理，且政府监管水平与社会影响力的提高可以使治理环境更加稳定。

关键词: 生成式人工智能, 虚假信息, 电商平台, 前景理论, 演化博弈, 信息管理

Abstract: Disinformation created by generative AI models has increased the difficulty of information governance on e-commerce platforms, which results in the increasingly prominent problem of AI information pollution. Based on the perspective of information generation and dissemination, this paper integrates the prospect theory into evolutionary game to construct a four-party evolutionary game model including generative AI service providers, merchants, e-commerce platforms, and the government, characterizes the optimal strategies for generative AI disinformation governance, and performs simulation analysis. The results show that for generative AI service providers, the cost of technological constraints and social influence affect their strategy choices, and increasing user fees and fines for non-compliant users can effectively curb non-compliant use by merchants. For e-commerce platforms, higher auditing professionalism can promote the maturity of information management in the e-commerce industry, and at the same time, a higher level of incentives and penalties is helpful for merchants to comply with the proper use of generative AI services, and differentiated governance should be implemented for heterogeneous merchants. For the government, appropriately increasing the rewards and punishments for generative AI service providers and e-commerce platforms can promote collaborative governance between the two parties, and the improvement of the level of government supervision and social influence can make the governance environment more stable.

Key words: generative artificial intelligence, disinformation, e-commerce, prospect theory, evolutionary game, information management