基于人工智能的实验动物中心信息化升级及应用实践探讨

doi:10.12300/j.issn.1674-5817.2024.181

摘要/Abstract

摘要：

目的针对传统实验动物中心管理中存在的笼位调度效率低、人员行为监管不到位、设备老化难升级等问题，本研究旨在通过应用多模态大模型技术升级现有实验动物中心，实现实验动物笼位状态的实时感知、实验人员行为的智能监管以及业务流程的自动化处理，从而提升管理效率与精细化水平。方法提出了一个基于人工智能的实验动物中心信息化升级方式，能够兼容不同饲养设备。该系统架构自下而上依次包括硬件设施层、核心算法层和应用功能层。硬件设施层配备摄像头和高速网络传输设备用于笼位和人员信息采集；核心算法层通过多阶段图像预处理技术和多模态大模型识别技术实现图片信息抽取和识别；应用功能层将识别结果和已有动物中心信息相整合，生产实时笼位占有热力图，直观、清晰展示实验动物中心的笼位使用密度分布情况。结果基于人工智能的管理系统笼位识别准确率达到98.5%，实验服正确识别率为98.8%。图片平均处理时间3.7 秒/张，笼位有效使用率提升23%，周转效率提高35%。此外，管理系统能够实时追踪并警告不规范行为，综合违规行为的发现次数在通过智能化识别后暴露更多，违规行为发现率提升90.6%，持续使用三个月后，周平均违规行为同比下降54.0%。结论本研究创新性地将多模态大模型应用于实验动物管理领域，实现笼位标识实时监控与自动化管理，提升管理效率和精确度。系统整合视觉识别和行为分析等多源数据，构建了对实验人员的全方位智能监管体系。为科研机构提供高效、精准、价廉的管理工具，推动实验动物管理的智能化发展。

关键词: 实验动物, 大模型, 智能识别, 信息系统

Abstract:

Objective In traditional laboratory animal centers, there are issues such as low cage scheduling efficiency, insufficient supervision of personnel behavior, and difficulty in upgrading aging equipment. This study aims to upgrade existing laboratory animal centers by applying multimodal large-model technology. This upgrade intends to achieve real-time perception of the status of animal cages, intelligent supervision of experimental personnel behavior, and automated management of business workflows, thereby improving management efficiency and refinement. Methods This study proposes an artificial-intelligence-based informatization approach for upgrading laboratory animal centers, which can be compatible with different breeding equipment. The system architecture, from the bottom up, consists of three layers: the hardware facilities layer, the core algorithm layer, and the application functions layer. The hardware facilities layer is equipped with cameras and high-speed network transmission devices for collecting information on cages and personnel. The core algorithm layer utilizes multi-stage image preprocessing technology and multimodal large-model recognition technology to extract and identify image information. The application functions layer integrates the recognition results with the existing information of the animal center to generate real-time cage occupancy heatmaps, which can visually and clearly show the density distribution of cage usage in the laboratory animal center. Results The artificial-intelligence-based management system has achieved a cage recognition accuracy of 98.5% and a correct identification rate of laboratory coats of 98.8%. The average image processing time is 3.7 seconds per image, the effective utilization rate of cages has increased by 23%, and the turnover efficiency has improved by 35%. In addition, the management system can track and warn against non-compliant behaviors in real time. After intelligent recognition, the system has detected more violations, with the violation detection rate rising by 90.6%. After continuous use for three months, the weekly average number of violations decreased by 54.0% compared to the baseline period. Conclusion This study innovatively applies multimodal large models to the field of laboratory animal management, achieving real-time monitoring and automated management of cage marking, thereby improving management efficiency and precision. The system integrates multi-source data such as visual recognition and behavior analysis, establishing a comprehensive intelligent supervision system for experimental personnel. It provides research institutions with efficient, accurate, and cost-effective management tools, promoting the intelligent development of laboratory animal management.

Key words: Experimental animals, Large language model, Intelligent recognition, Information system

中图分类号:

Q95-33

王庭君,罗浩,陈琦.基于人工智能的实验动物中心信息化升级及应用实践探讨[J]. 实验动物与比较医学.. DOI: 10.12300/j.issn.1674-5817.2024.181.

WANG Tingjun,LUO Hao,CHEN Qi. Informationization Upgrade and Application of Laboratory Animal Center Based on Artificial Intelligence[J]. Laboratory Animal and Comparative Medicine. DOI: 10.12300/j.issn.1674-5817.2024.181.

图/表 4

图1 AI笼位模式实现组图注：AI笼位系统模式图（左上），二维码笼位卡牌（左下），笼位管理系统页面（右侧）。

Figure 1 Group diagram of AI cage positioning modeNote：AI cage positioning system diagram （left superior panel）， qr code cage positioning card （left inferior panel）， cage management system interface （right panel）.

图2 笼位识别操作与结果图注：原始图片（左），局部识别结果（中），汇总导出图（右）。

Figure 2 Cage identification operations and resultsNote：Original image （left panel），partial identification result （middle panel）， summarized export image （ right panel）.

表1 笼位监管方案对比分析表

Table 1 Comparative analysis of cage location monitoring plans

对比项目 Comparison items	本方案（多模态大模型) This solution (Multimodal large model)	人工监管方法 Manual supervision method	信息化系统 + YOLO Information system + YOLO
识别技术 Recognition technology	GPT-4o大模型	人工目视核查	YOLO目标检测
识别准确率 Recognition accuracy	98.5%（持续优化）	90%(易疲劳)	> 98%*（理论推测值）
改造要求 Renovation requirements	摄像头，网络系统，普通计算机	无	摄像头，网络系统，配备主流高性能显卡的计算器
改造成本 Renovation cost	低	无	高
使用成本 Usage cost	低	高	低
工作效率 Work efficiency	高(3.7秒/笼架)	低(5~10分钟/笼架)	极快（1 s以内）
适应性 Adaptability	强(可适应多种场景)	强	弱(需要与训练数据类似)
拓展性 Scalability	完善	无	支持的，但是成本高昂，需要重新训练模型

图3 实验动物中心违规行为周均发现次数变化图

Figure 3 Trend of Weekly Average Number of Detected Non-Compliance Cases in the Laboratory Animal Center

参考文献 26

1	中华人民共和国国家质量监督检验检疫总局, 中国国家标准化管理委员会. 实验动物环境及设施: [S]. 北京:中国标准出版社, 2010.
	General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China, Standardization Administration of the People's Republic of China. Environment and Facilities for Laboratory Animals: [S]. Beijing: China Standards Press, 2010.
2	刘莲莲, 张成梅, 张海艇, 等. 高校动物房屏障系统高效管理初探[J]. 医学动物防制, 2020, 36(7):661-667. DOI: 10. 7629 /yxdwfz202007015
	LIU L L, ZHANG C M, ZHANG H T, et al. Preliminary Exploration on the efficient management of barrier systems in university animal houses [J]. Journal of Medical Pest Control, 2020, 36(7):661-667. DOI:10.7629 /yxdwfz202007015 .
3	刘琪帅, 李朝, 任晓霞. "双一流"高校建设背景下新型实验动物中心的建设与管理[J]. 实验技术与管理, 2022, 39(9):265-268. DOI: 10.16791/j.cnki.sjg.2022.09.045 .
	LIU Q S, LI C, REN X X.Construction and management of a new-type laboratory animal center under the background of "Double First-Class" university construction [J]. Experimental Technology and Management, 2022, 39(9): 265-268. DOI: 10.16791/j.cnki.sjg.2022.09.045 .
4	陈晓娟. 高校实验动物管理流程信息化探索:以浙江大学为例[J]. 实验动物与比较医学, 2021, 41:554-558. DOI:10.12300/j.issn.1674-5817.2021.045 .
	CHEN X J.Exploration on the Informatization of Laboratory Animal Management Processes in Universities: Taking Zhejiang University as an Example [J]. Laboratory Animals and Comparative Medicine, 2021, 41: 554-558. DOI: 10.12300/j.issn.1674-5817.2021.045 .
5	中华人民共和国国家质量监督检验检疫总局, 中国国家标准化管理委员会. .实验动物福利伦理审查指南 [S]. 北京:中国标准出版社, 2018.
	General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China, Standardization Administration of the People's Republic of China. . Guidelines for the Ethical Review of Laboratory Animal Welfare [S]. Beijing: China Standards Press, 2018.
6	陆伟,刘家伟,马永强,等.ChatGPT为代表的大模型对信息资源管理的影响[J].图书情报知识,2023,2(40):006-009.DOI:10.13366/j.dik.2023.02.006 .
	LU W, LIU J W, MA Y Q, et al. The Impact of large models represented by ChatGPT on information resource management[J]. Knowledge of Library and Information Studies, 2023, 2(40): 006-009.DOI: 10.13366/j.dik.2023.02.006 .
7	徐敏. "一院多区"医院管理的探索与思考[J]. 中国卫生质量管理, 2017(7):107-109. DOI:10.13912/j.cnki.chqm.2017.24.4.35 .
	XU M. Exploration and reflection on the management of "One Hospital with Multiple Districts"[J].Chinese Health Quality Management, 2017(7): 107-109. DOI: 10.13912/j.cnki.chqm.2017.24.4.35 .
8	陈玲. 高校实验室安全管理面临的问题与对策[J]. 实验室研究与探索, 2017, 36(1) : 283-286.
	CHEN L. Problems and countermeasures in the safety management of university laboratories [J]. Research and Exploration in Laboratory, 2017, 36(1): 283-286.
9	胡永艳, 陶迎红, 孔申申. 一种基于互联网的实验动物管理系统介绍[J]. 实验动物与比较医学, 2020(3):257-261. DOI:10.3969/j.issn.1674-5817.2020.03.015 .
	HU Y Y, TAO Y H, KONG S S.Introduction to an internet-based laboratory animal management system[J].
	Laboratory Animals and Comparative Medicine, 2020(3): 257-261. DOI: 10.3969/j.issn.1674-5817.2020.03.015 .
10	宋予震, 郭素琴, 史洪涛, 等. 动物医学虚拟仿真实验教学平台的建设与应用[J]. 高教学刊, 2020, 6(21) : 79-81. DOI:10.19980/j.cn23-1593/g4.2020.21.023 .
	SONG Y Z, GUO S Q, SHI H T, et al. Construction and application of a virtual simulation experimental teaching platform for veterinary medicine[J]. Journal of Higher Education, 2020, 6(21): 79-81. DOI: 10.19980/j.cn23-1593/g4.2020.21.023 .
11	黄术兵, 姚文茜, 侯豹, 等. 高校实验动物管理工作的现状和对策研究[J]. 实验室科学, 2023, 26(6) : 147-150. DOI: 10.3969/j.issn.1672-4305.2023.06.035 .
	HUANG S B, YAO W X, HOU B, et al. Research on the Current Situation and Countermeasures of Laboratory Animal Management in Universities[J].Laboratory Science, 2023, 26(6): 147-150. DOI: 10.3969/j.issn.1672-4305.2023.06.035 .
12	李秀, 陈晓梅, 商可心, 等. 使用型高校实验动物中心信息化管理模式开发应用[J]. 上海畜牧兽医通讯, 2020, 4:61-65. DOI:10.14170/j.cnki.cn31-1278/s.2020.04.025 .
	LI X, CHEN X M, SHANG K X, et al.Development and application of an informatized management model for the laboratory animal center in application-oriented universities[J]. Shanghai Journal of Animal Husbandry and Veterinary Medicine, 2020, 4: 61-65. DOI: 10.14170/j.cnki.cn31-1278/s.2020.04.025 .
13	胡瑚. 基于MySQL的科研信息管理系统数据库设计[J]. 信息与电脑, 2024(4):169-171.
	HU H. Database design of a scientific research information management system based on MySQL [J]. China Journal of Information and Computer, 2024(4): 169-171.
14	郭全中, 苏刘润薇. 作为新基础设施的AGI:以GPT-4O等新一代生成式人工智能为例[J]. 新闻爱好者, 2024(7):16-21. DOI:10.16017/j.cnki.xwahz.20240527.001 .
	GUO Q Z, SU L R W. AGI as new infrastructure: taking new-generation generative artificial intelligence like GPT-4O as an example [J]. Journalism Lover, 2024(7): 16-21.DOI: 10.16017/j.cnki.xwahz.20240527.001 .
15	郭全中, 张金熠. ChatGPT的技术特征与应用前景[J]. 中国传媒科技, 2023(1):159-160.
	GUO Q Z, ZHANG J Y. The technical characteristics and application prospects of ChatGPT[J].
	China Media Science and Technology, 2023(1): 159-160.
16	LI J J, GUAN Z Y, WANG J. Integrated image-based deep learning and language models for primary diabetes care[J]. Nat Med, 2024.30(10):2886-2896. DOI:10.1038/s41591-024-03139-8 .
17	大经中医. 岐黄问道大模型[EB/OL]. (2023-08-01). .
	Dajing Chinese Medicine.Qihuang Wendao Large Model [EB/OL]. (2023-08-01). .
18	YANG S., ZHAO H., ZHU S.,et al. Zhongjing: Enhancing the Chinese Medical Capabilities of large language model through expert feedback and real-world multi-turn dialogue[J]. arXiv preprint arXiv:2308.03549. [19]THAWKARO., SHAKERA., MULLAPPILLYS, et al. XrayGPT:Chest Radiographs Summarization using Large Medical Vision-Language Models[J]. arXiv preprint arXiv:.
20	LIU J L, WANG Z M, YE Q C. Qilin-Med-VL:TowardsChinese Large Vision-Language Model for General Healthcare[J]. arXiv preprint arXiv:.
21	吴琪. 基于信息化的实验动物中心管理新模式实践[J]. 畜牧业环境, 2022, 17:53-54.
	WU Q. Practice of a new management mode for laboratory animal centers based on informatization [J]. Animal Husbandry Environment, 2022, 17: 53-54.
22	朱玉, 秦嫘, 辛丹, 等. 高等院校实验动物的信息化管理体系建设探讨[J]. 畜牧兽医科技信息, 2022(6): 19-21. DOI:10.3969/J.ISSN.1671-6027.2022.06.007 .
	ZHU Y, QIN L, XIN D, et al. Discussion on the construction of an informatized management system for laboratory animals in colleges and universities[J]. Information on Animal Husbandry and Veterinary Science, 2022(6): 19-21. DOI: 10.3969/J.ISSN.1671-6027.2022.06.007 .
23	赵朝阳, 朱贵波, 王金桥. ChatGPT给语言大模型带来的启示和多模态大模型新的发展思路[J]. 数据分析与知识发现, 2023, 7(3):26-35.
	ZHAO Z Y, ZHU G B, WANG J Q. Insights from ChatGPT for large language models and new development ideas for multimodal large models[J]. Data Analysis and Knowledge Discovery, 2023, 7(3): 26-35.
24	郭君斌, 于琳, 于传强. 改进YOLOv5s算法在交通标志检测识别中的应用[J]. 国防科技大学学报, 2024,46 (25):123-130.
	GUO J B, YU L, YU C Q. Application of improved YOLOv5s algorithm in traffic sign detection and recognition [J]. Journal of National University of Defense Technology, 2024, 46(25): 123-130.
25	韩冬, 李其花, 蔡巍. 人工智能在医学影像中的研究与应用[J]. 大数据, 2019,5(1):39-67.
	HAN D, LI Q H, CAI W. Research and application of artificial intelligence in medical imaging[J]. Big Data, 2019, 5(1): 39-67.
26	BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: Optimal speed and accuracy of object detection[EB/OL].

[1]	张倩, 邓青秀, 蔡林. 国内普通高校实验动物从业人员职业健康风险防控概述[J]. 实验动物与比较医学, 2025, 45(2): 206-213.
[2]	许超, 孙秋芳, 邵奇鸣. 实验动物机构职业健康档案建立内容及要点[J]. 实验动物与比较医学, 2025, 45(2): 214-220.
[3]	蔡梦诗, 苏醒, 邵奇鸣. 实验动物机构建设项目职业健康防护设施“三同时”的实施要求[J]. 实验动物与比较医学, 2025, 45(2): 221-228.
[4]	邵奇鸣, 卞勇, 施爱民. 实验动物机构职业健康安全管理体系建设要点[J]. 实验动物与比较医学, 2025, 45(2): 188-196.
[5]	肖文娴, 吕龙宝. 非人灵长类实验动物用于人类卵巢衰老研究进展[J]. 实验动物与比较医学, 2025, 45(1): 47-54.
[6]	侯冬霞, 铁祚庥, 陆勇, 南盼盼, 鲍洁. 实验动物屏障环境设施安全准入体系建设的探索与实践——以南京大学仙林校区为例[J]. 实验动物与比较医学, 2025, 45(1): 96-100.
[7]	刘巍, 张心妍, 侯丰田, 许中衎, 马丽颖. 实验动物设施换气次数检测能力验证结果评价[J]. 实验动物与比较医学, 2025, 45(1): 87-95.
[8]	刘丽达, 陈兵, 谢娜, 刘丽, 庄思琪, 邹弈星. 2017—2023年四川省实验动物寄生虫和微生物质量抽检报告分析[J]. 实验动物与比较医学, 2024, 44(6): 654-660.
[9]	刘意抒, 蔡丽萍. 实验猪在达芬奇手术机器人培训中的应用进展及挑战[J]. 实验动物与比较医学, 2024, 44(6): 667-674.
[10]	赵丽娟, 肖春兰, 盛雅洁, 鲁希, 周正宇. 风雨五十载，奋斗半世纪——记苏州市实验动物产业发展五十年[J]. 实验动物与比较医学, 2024, 44(6): 645-653.
[11]	杜小燕, 刘云波. 中国实验动物资源鉴定与评价工作进展分析[J]. 实验动物与比较医学, 2024, 44(5): 469-474.
[12]	朱婵, 张栋梁, 赵德莉, 石雪琴, 千磊, 张玄, 金艳, 段伟, 戚若晨, 刘超华, 杨薛康, 韩军涛, 潘登科. 基因编辑猪-猴异种组织器官移植围手术期动物护理[J]. 实验动物与比较医学, 2024, 44(5): 495-501.
[13]	陈兵, 邹弈星, 王敬东. 基于行政许可的四川省实验动物管理现状与对策分析[J]. 实验动物与比较医学, 2024, 44(5): 560-566.
[14]	赵勇. 动物实验伦理的三个维度：基于生命价值、动物福利和风险防范的阐析[J]. 实验动物与比较医学, 2024, 44(4): 445-454.
[15]	邓少嫦, 林丹荣, 梁楚军, 雷伟侨, 杨锦淳, 赵维波. 《广东省实验动物管理条例》制度特点及近十年实施情况分析[J]. 实验动物与比较医学, 2024, 44(4): 455-462.