CogChat：结合知识图谱与异构图变换器的对话式人工智能，用于设计生成中的认知接地
CogChat: Knowledge Graph-Augmented Conversational AI with Heterogeneous Graph Transformer for Cognitive Grounding in Design Generation
AI总结：
本研究提出结合异构图变换器的CogChat框架，以设计师专属动态知识图谱为基础，提升设计对话的上下文保留度与意图解读效果，降低认知负荷，为LLM交互的长期上下文管理提供新方法。
AI中文摘要：
基于大语言模型（LLM）的聊天系统已成为设计实践中的重要工具，可实现快速创意构思与灵活任务支持。然而，这类系统将设计师的话语视为通用序列，仅通过近期性维持上下文，而非基于说话者组织知识的模型。在设计对话中，这一差距会加剧：轮次间关系上下文衰减，不同设计师的相同词汇无法得到解决，对话会循环或重启而非深化。本文提出CogChat，一种实时聊天框架，其将对话式人工智能建立在从每位设计师输入构建的个人异质知识图谱（KG）基础上。该系统提取带类型的实体与关系，形成异构图，随后应用异构图变换器（Heterogeneous Graph Transformer，HGT）选择与结构相关的节点以生成响应，并生成意向性与探索性探测问题。技术评估显示，基于HGT的实体选择性能优于无接地的LLM交互与朴素KG增强，后者会引入噪声降低响应质量。针对9名专业设计师的被试内研究表明，将对话建立在关系结构化、设计师专属的语义上下文基础上，可提升上下文保留度、个性化意图解读与对话深度，同时降低认知负荷。这些发现表明，将设计师表达的概念与关系构建为动态知识图谱，可保留轮次间衰减的关系上下文，为基于图的LLM交互长期上下文管理提供了可行方法。
英文摘要：
LLM-based chat systems have become valuable tools for design practice, enabling rapid ideation and flexible task support. Yet these systems process designer utterances as generic sequences, maintaining context through recency rather than through any model of how the speaker organizes knowledge. In design conversation, this gap compounds as relational context decays between turns, identical words go unresolved across designers, and the conversation loops or restarts rather than deepens. We present CogChat, a real-time chat framework that grounds conversational AI in a personal heterogeneous knowledge graph constructed from each designer's input. The system extracts typed entities and relations into a heterogeneous graph, then applies a HGT (Heterogeneous Graph Transformer) to select structurally relevant nodes for response generation and to generate both intentional and exploratory probing questions. Technical evaluation shows that HGT-based entity selection outperforms both ungrounded LLM interaction and naive KG augmentation, which introduces noise that degrades response quality. A within-subjects study with nine professional designers indicates that grounding conversation in a relationally structured, designer-specific semantic context improves context retention, personalized intent interpretation, and conversational depth while reducing cognitive load. These findings suggest that structuring a designer's expressed concepts and relations as a dynamic knowledge graph can preserve relational context that fades across turns, pointing toward a graph-grounded approach to long-term context management in LLM-based interaction.
