随着互联网技术和人工智能的迅猛发展,医疗电商平台在现代医药服务中扮演着越来越重要的角色。本研究提出了一种基于大语言模型(LLM)的中文医学对话系统模型MedAsst,并探讨其在医疗电商平台中的应用。该模型以Qwen2-7B为基础,通过LoRA...随着互联网技术和人工智能的迅猛发展,医疗电商平台在现代医药服务中扮演着越来越重要的角色。本研究提出了一种基于大语言模型(LLM)的中文医学对话系统模型MedAsst,并探讨其在医疗电商平台中的应用。该模型以Qwen2-7B为基础,通过LoRA方法在147万条医学问答数据上进行监督微调。本文在医学多项选择题测试和自定义医学问答数据集上对MedAsst的有效性进行了全面评估。实验结果显示,MedAsst在BLEU-4、ROUGE-1、ROUGE-2和ROUGE-L等评价指标上均优于其他基线模型,特别是在医学问答能力上展现出显著优势。与LlaMa-3-8B、Gemma-7B、Mistral-7B和未经微调的Qwen2-7B模型相比,MedAsst通过合理的微调策略在特定领域的任务中表现出色,证明了监督微调的必要性和有效性。本文的研究不仅提升了模型在中文医学问答任务中的表现,也展示了大语言模型在医疗电商平台中的应用潜力,为未来在更复杂场景中的优化和实际应用提供了有力支持。With the rapid development of Internet technology and artificial intelligence, medical e-commerce platforms play an increasingly important role in modern pharmaceutical services. This study proposes a Chinese medical dialogue system model MedAsst based on Large Language Model (LLM) and explores its application in medical e-commerce platform. The model is based on Qwen2-7B, and supervised fine-tuning is performed on 1.47 million medical question and answer data by LoRA method. In this paper, the effectiveness of MedAsst is thoroughly evaluated on a medical multiple-choice test and a customised medical quiz dataset. The experimental results show that MedAsst outperforms other baseline models on the evaluation metrics of BLEU-4, ROUGE-1, ROUGE-2, and ROUGE-L, and in particular demonstrates a significant advantage in medical quizzing ability. Compared with LlaMa-3-8B, Gemma-7B, Mistral-7B, and the unfine-tuned Qwen2-7B model, MedAsst performs well in domain-specific tasks through reasonable fine-tuning strategies, demonstrating the necessity and effectiveness of supervised fine-tuning. The research in this paper not only improves the performance of the model in the Chinese medical Q&A task, but also demonstrates the potential application of large language models in medical e-commerce platforms, which provides strong support for future optimisation and practical application in more complex scenarios.展开更多
在各个领域逐渐智能化的情况下,电商经济也正在向智能化过渡,机器人导航技术的持续进步及其与物流运输的深度融合,正逐步推动室内物流运输向智能化方向发展。然而,当前大多数室内物流小车采用的基于同时定位与建图(SLAM)技术的导航方法...在各个领域逐渐智能化的情况下,电商经济也正在向智能化过渡,机器人导航技术的持续进步及其与物流运输的深度融合,正逐步推动室内物流运输向智能化方向发展。然而,当前大多数室内物流小车采用的基于同时定位与建图(SLAM)技术的导航方法存在一定的局限性。这类方法依赖于地图先验知识,不仅需要投入大量的人工成本和高精度的传感器,而且在环境发生变化时,物流小车往往难以有效完成导航任务,甚至在特定环境下可能引发安全问题。针对这一问题,本文提出了一种新型的基于深度强化学习的导航模型。该方法在TD3 (Twin Delayed Deep Deterministic Policy Gradient)这一经典深度强化学习算法的基础上,构建了适用于智能物流小车的导航框架。通过在仿真环境中的训练,本方法实现了移动机器人在未知环境中的自主导航。实验结果表明,相较于传统导航算法,本方法在导航准确率上具有显著优势。In the context of increasing intelligence across various fields, the e-commerce economy is also transitioning towards intelligence. The continuous advancement of robot navigation technology and its deep integration with logistics transportation are gradually driving the direction of indoor logistics towards intelligence. However, most indoor logistics vehicles currently adopt navigation methods based on Simultaneous Localization and Mapping (SLAM) technology, which have certain limitations. These methods rely on map prior knowledge, requiring significant manual labor and high-precision sensors. Moreover, when the environment changes, logistics vehicles often struggle to effectively complete navigation tasks and may even cause safety issues in specific environments. In response to this problem, this paper proposes a new type of navigation model based on deep reinforcement learning. This method constructs a navigation framework suitable for intelligent logistics vehicles on the basis of the classic deep reinforcement learning algorithm TD3 (Twin Delayed Deep Deterministic Policy Gradient). Through training in a simulation environment, this approach has achieved autonomous navigation of mobile robots in unknown environments. Experimental results show that this method has a significant advantage in navigation accuracy compared to traditional navigation algorithms.展开更多
文摘随着互联网技术和人工智能的迅猛发展,医疗电商平台在现代医药服务中扮演着越来越重要的角色。本研究提出了一种基于大语言模型(LLM)的中文医学对话系统模型MedAsst,并探讨其在医疗电商平台中的应用。该模型以Qwen2-7B为基础,通过LoRA方法在147万条医学问答数据上进行监督微调。本文在医学多项选择题测试和自定义医学问答数据集上对MedAsst的有效性进行了全面评估。实验结果显示,MedAsst在BLEU-4、ROUGE-1、ROUGE-2和ROUGE-L等评价指标上均优于其他基线模型,特别是在医学问答能力上展现出显著优势。与LlaMa-3-8B、Gemma-7B、Mistral-7B和未经微调的Qwen2-7B模型相比,MedAsst通过合理的微调策略在特定领域的任务中表现出色,证明了监督微调的必要性和有效性。本文的研究不仅提升了模型在中文医学问答任务中的表现,也展示了大语言模型在医疗电商平台中的应用潜力,为未来在更复杂场景中的优化和实际应用提供了有力支持。With the rapid development of Internet technology and artificial intelligence, medical e-commerce platforms play an increasingly important role in modern pharmaceutical services. This study proposes a Chinese medical dialogue system model MedAsst based on Large Language Model (LLM) and explores its application in medical e-commerce platform. The model is based on Qwen2-7B, and supervised fine-tuning is performed on 1.47 million medical question and answer data by LoRA method. In this paper, the effectiveness of MedAsst is thoroughly evaluated on a medical multiple-choice test and a customised medical quiz dataset. The experimental results show that MedAsst outperforms other baseline models on the evaluation metrics of BLEU-4, ROUGE-1, ROUGE-2, and ROUGE-L, and in particular demonstrates a significant advantage in medical quizzing ability. Compared with LlaMa-3-8B, Gemma-7B, Mistral-7B, and the unfine-tuned Qwen2-7B model, MedAsst performs well in domain-specific tasks through reasonable fine-tuning strategies, demonstrating the necessity and effectiveness of supervised fine-tuning. The research in this paper not only improves the performance of the model in the Chinese medical Q&A task, but also demonstrates the potential application of large language models in medical e-commerce platforms, which provides strong support for future optimisation and practical application in more complex scenarios.
文摘在各个领域逐渐智能化的情况下,电商经济也正在向智能化过渡,机器人导航技术的持续进步及其与物流运输的深度融合,正逐步推动室内物流运输向智能化方向发展。然而,当前大多数室内物流小车采用的基于同时定位与建图(SLAM)技术的导航方法存在一定的局限性。这类方法依赖于地图先验知识,不仅需要投入大量的人工成本和高精度的传感器,而且在环境发生变化时,物流小车往往难以有效完成导航任务,甚至在特定环境下可能引发安全问题。针对这一问题,本文提出了一种新型的基于深度强化学习的导航模型。该方法在TD3 (Twin Delayed Deep Deterministic Policy Gradient)这一经典深度强化学习算法的基础上,构建了适用于智能物流小车的导航框架。通过在仿真环境中的训练,本方法实现了移动机器人在未知环境中的自主导航。实验结果表明,相较于传统导航算法,本方法在导航准确率上具有显著优势。In the context of increasing intelligence across various fields, the e-commerce economy is also transitioning towards intelligence. The continuous advancement of robot navigation technology and its deep integration with logistics transportation are gradually driving the direction of indoor logistics towards intelligence. However, most indoor logistics vehicles currently adopt navigation methods based on Simultaneous Localization and Mapping (SLAM) technology, which have certain limitations. These methods rely on map prior knowledge, requiring significant manual labor and high-precision sensors. Moreover, when the environment changes, logistics vehicles often struggle to effectively complete navigation tasks and may even cause safety issues in specific environments. In response to this problem, this paper proposes a new type of navigation model based on deep reinforcement learning. This method constructs a navigation framework suitable for intelligent logistics vehicles on the basis of the classic deep reinforcement learning algorithm TD3 (Twin Delayed Deep Deterministic Policy Gradient). Through training in a simulation environment, this approach has achieved autonomous navigation of mobile robots in unknown environments. Experimental results show that this method has a significant advantage in navigation accuracy compared to traditional navigation algorithms.
