| 摘要: |
| 当前软件市场呈现出产品同质化加重趋势, 功能性创新已成为决定软件竞争优势的关键因素. 这促使现代需求工程研究范式从被动的需求提取转向主动的创新需求捕获. 在提升需求创新性的实践中, 现有研究主要呈现两条路径: (1)通过情景建模与引导方法改进工作坊流程, 激发人类团队协作创新; (2)基于组合创新理论对既有需求进行解构重组, 快速生成新需求方案. 但两种方法均面临创新质量与参与成本难以有效平衡的核心矛盾. 生成式AI技术的突破性进展为应对这一挑战提供了新思路. 提出一种业务建模驱动下注入TRIZ理论的人-多智能体协作式创新需求捕获框架BMHACT, 该框架以统一过程业务建模协作架构为蓝本, 设计提示词定义业务流程分析员、业务设计员等5个智能体职责. 多智能体团队通过“系统愿景收集-流程痛点识别-技术矛盾分析-TRIZ创新原理匹配-需求方案生成”的协作流程生成创新需求, 并由领域专家和客户代表对需求进行创新性评估. 以工程机械领域某企业门户网站建设项目为例的实证研究表明: 相较基于需求重用的自动化方法和基于对抗样本的追溯式需求生成方法, BMHACT迭代次数分别降低50%和28.6%, 全过程耗时减少66.7%和33.3%, 同时, 创新潜力指数(clarity novelty usefulness, CNU)分别提升22.9%和10.7%, 且CNU单轮平均增益分别提高2.16倍和2.14倍. 证明了BMHACT在提升需求创新质量和降低协作成本上的优越性. |
| 关键词: 创新需求 大语言模型 人-多智能体协作 注入TRIZ理论的提示词工程 多阶段质量门控机制 创新潜力指数 |
| DOI：10.13328/j.cnki.jos.007562 |
| 分类号:TP311 |
| 基金项目:国家重点研发计划(2023YFC3503404); 湖南省自然科学基金(2025JJ50343) |
|
| Business-modeling-driven Human-AI Multi-agent Collaborative Framework with TRIZ Infusion for Creative Requirements Capture |
|
LIU Xin-Hua, JIN Min, YU Meng-Jiao, XIE Wen-Tao
|
|
College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China
|
| Abstract: |
| The current software market is witnessing an intensified trend of product homogenization, where functional innovation has become a decisive factor in maintaining competitive advantage. This shift has transformed the paradigm of modern requirements engineering from passive requirements extraction to proactive creative requirements capture. Existing approaches to enhancing requirements creativity primarily follow two paths: (1) fostering collaborative innovation in workshops through scenario modeling and facilitation methods, and (2) rapidly generating novel solutions by deconstructing and recombining existing requirements based on combinatorial innovation theory. However, both methods face a core challenge in balancing innovation quality with participation costs. The breakthrough advancements in generative AI technologies offer new opportunities to address this dilemma. This study proposes a business modeling-driven human-AI multi-agent collaborative framework with TRIZ infusion for creative requirements capture (BMHACT). The framework adopts the unified process business modeling collaborative architecture to design prompt-based definitions for five agent roles: business process analyst, business designer, and other relevant roles. The multi-agent team collaboratively generates creative requirements through a structured workflow: system vision collection→process pain point identification→technical contradiction analysis→TRIZ innovation principle matching→requirement solution generation. Domain experts and client representatives then evaluate the requirements for creativity. An empirical study on a portal system for a small-scale mechanical manufacturing enterprise demonstrates that, compared to the requirement reuse-based method and the adversarial-sample-based retrospective requirement generation method, BMHACT reduces iteration cycles by 50% and 28.6%, shortens total process duration by 66.7% and 33.3%, increases the clarity novelty usefulness (CNU) by 22.9% and 10.7%, and achieves a 2.16× and 2.14× higher per-round CNU improvement rate. These results validate BMHACT’s superiority in enhancing requirements innovation quality while reducing collaboration costs. |
| Key words: creative requirement large language model (LLM) human-AI multi-agent collaboration TRIZ-infused prompt engineering multi-stage quality gating mechanism clarity novelty usefulness (CNU) |
