人机对话中的商业意图：网站销售代理的语料库审计与架构
Commercial Intent in Human-AI Conversations: A Corpus Audit and Architecture for Website Sales Agents
浏览论文内容
中文总结 AI 辅助
本研究对Aiso的725,219条人机对话记录进行元数据审计，提出区分商业意图与交易意图的参考架构，结合业务知识、来源状态和受限行动策略，以提升网站销售代理的决策质量。
中文摘要 AI 辅助
对话式销售代理必须区分关于产品的问题与购买承诺，保留明确的需求，并将下一步行动基于当前的业务信息。我们报告了对Aiso提供的可访问对话表中725,219条记录的总体普查，并为该场景开发了一个参考架构。所有记录具有不同的非空对话哈希值。现有元数据标签识别出41,800条商业记录（5.76%）和2,387条交易记录（0.33%）；它们的并集包含44,187条记录（6.09%）。在商业类别中，54.31%被标记为英语，41.59%的记录深度至少为2，13.51%的记录深度至少为4。商业标签的普遍性在三个来源批次中从4.87%到6.35%不等。这些测量结果促使明确区分语料库清单、商业相关性、训练资格和观察到的业务结果。所提出的架构结合了基于业务的知识、带有来源的对话状态和受限的下一步行动策略。质量规范涉及源权利、隐私、标签验证、去重和训练-测试分离。本研究是一项元数据审计和技术设计，而非标签准确性、模型训练量或销售转化的验证。未发布原始对话文本或个人标识符。
英文摘要
Conversational sales agents must distinguish questions about products from purchase commitments, preserve explicit requirements, and ground the next action in current business information. We report an aggregate census of 725,219 records in an accessible conversation table provided by Aiso and develop a reference architecture for this setting. All records have distinct non-null conversation hashes. Existing metadata labels identify 41,800 commercial records (5.76%) and 2,387 transactional records (0.33%); their union contains 44,187 records (6.09%). Within the commercial category, 54.31% are labeled English, 41.59% have recorded depth of at least two, and 13.51% have depth of at least four. Commercial-label prevalence varies from 4.87% to 6.35% across three source batches. These measurements motivate explicit separation of corpus inventory, commercial relevance, training eligibility, and observed business outcomes. The proposed architecture combines business-grounded knowledge, provenance-bearing conversation state, and a constrained next-action policy. A quality specification addresses source rights, privacy, label validation, deduplication, and training-test separation. The study is a metadata audit and technical design, not a validation of label accuracy, model training volume, or sales conversion. No raw conversation text or personal identifiers are released.
发表机构
- Javo
机构由 AI 辅助整理，请以论文原文为准。
