从工业产品文档到自动化数字产品护照生成:大语言模型的实验研究
From Industrial Product Documentation to Automated Digital Product Passport Generation: An Experimental Study of Large Language Models
Marco Buecheler · Grant Richards · Nathan Hartman
中文摘要
计划在欧盟(EU)销售特定产品的制造企业将需要提供强制性的数字产品护照(DPP)。DPP 用于在循环经济中跨多个产品生命周期提供标准化产品信息。所需护照信息(如技术规格、材料成分和环境足迹)存在于制造商的数据源中,但分散在不同的异构系统、文档和数据格式中。论文研究使用大语言模型(LLM)基于资产管理壳(AAS)自动生成 DPP。采用检索增强生成(RAG)方法从工业文档中提取产品信息并生成填充的 AAS 实例。产品文档被处理并切分为文本块,随后通过向量嵌入存入持久化 ChromaDB 向量数据库。检索过程结合语义与词汇搜索,依据标准化 AAS 子模型模板要求识别相关信息。检索到的信息提供给五个 LLM 生成结构化 AAS 实例。实验覆盖不同工业产品和 AAS 子模型,考察四个级别的提示引导对生成质量的影响。生成的护照对照真实值评估,实验评估包含 76 个产品-子模型组合的 4,560 次执行。生成输出中 97.4% 为有效 JSON,44.9% 通过完整 AAS 验证流程。确定性评分下,平均完整性、条件准确率和总体字段正确率分别为 49.6%、58.3% 和 30.8%。LLM-as-a-judge 对相同输出给出更高分数:66.5%、88.9% 和 60.4%。
关键要点
- 01欧盟将强制要求数字产品护照,但所需信息分散在异构系统与文档中
- 02采用 RAG 从工业文档提取信息并生成基于 AAS 的结构化护照实例
- 034,560 次执行中 97.4% 输出为有效 JSON,仅 44.9% 通过完整 AAS 验证
- 04确定性评分下字段正确率仅 30.8%,LLM-as-a-judge 评分为 60.4%
解读
尚无解读。
原始英文摘要
arXiv:2611.24998v1 Announce Type: new Abstract: Manufacturing companies that are planning to sell certain products in the European Union (EU) will be required to provide mandatory digital product passports (DPPs). The use of DPPs is to provide standardized product information throughout multiple product life cycles in a circular economy. Required passport information, such as technical specifications, material composition, and environmental product footprint, is available in manufacturers' data sources but is scattered across different heterogeneous systems, documents, and data formats. The given paper investigates using large language models (LLMs) to automate the generation of DPPs based on the asset administration shell (AAS). A retrieval-augmented generation (RAG) approach is used to extract product information from industrial documentation and generate populated AAS instances. Product documentation is processed and divided into text chunks. The text chunks are then stored in a persistent ChromaDB vector database using vector embeddings. The retrieval process combines semantic and lexical search to identify relevant information based on standardized AAS submodel template requirements. The retrieved information is provided to five LLMs to generate structured AAS instances. The experiments cover different industrial products and AAS submodels. Four levels of prompt guidance are investigated to assess their influence on generation quality. The generated passports are evaluated against a ground truth. The experimental evaluation includes 4,560 executions across 76 product-submodel combinations. Of the generated passport outputs, 97.4% are valid JSON, while 44.9% pass the full AAS validation procedure. Under deterministic scoring, mean completeness, conditional accuracy, and overall field correctness are 49.6%, 58.3%, and 30.8%, respectively. An LLM-as-a-judge yields better scores of 66.5%, 88.9%, and 60.4% for the same outputs.