[1]刘珂,刘盾,孙扬,等.面向在线医疗平台的医生推荐方法[J].智能系统学报,2025,20(1):206-218.[doi:10.11992/tis.202406012]
LIU Ke,LIU Dun,SUN Yang,et al.Doctor recommendation approach for online healthcare platforms[J].CAAI Transactions on Intelligent Systems,2025,20(1):206-218.[doi:10.11992/tis.202406012]
点击复制
LIU Ke,LIU Dun,SUN Yang,et al.Doctor recommendation approach for online healthcare platforms[J].CAAI Transactions on Intelligent Systems,2025,20(1):206-218.[doi:10.11992/tis.202406012]
面向在线医疗平台的医生推荐方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
20
期数:
2025年第1期
页码:
206-218
栏目:
学术论文—人工智能基础
出版日期:
2025-01-05
- Title:
- Doctor recommendation approach for online healthcare platforms
- Keywords:
- online healthcare platforms; doctor recommendation; sequential three-way decision; multi-granularity; data augmentation; negative samples; negative sampling; data sparsity
- 分类号:
- TP311
- 摘要:
- 近年来，随着智慧医疗的日益普及，在线医疗平台已逐步发展为满足大众基本医疗需求的重要渠道。为患者推荐合适的医生是在线问诊中的一个重要过程，优化推荐能力不仅可以提高患者的满意度，还能够推动在线医疗平台的发展。与传统推荐系统不同，医生推荐领域受到隐私保护限制，无法查看患者曾经的诊疗历史，因此模型训练时仅能利用每位患者最近一次的就诊记录，面临严峻的数据稀疏问题。同样，模型预测时也仅能根据患者当前的疾病描述文本进行推荐，而由于患者对疾病描述方式的差异性，模型对不同患者的推荐能力也存在差异，这会使部分患者的需求无法得到满足，进而影响模型整体的推荐能力。基于此，本文提出了一种基于数据增强的医生推荐方法(sequential three-way decision with data augmentation, STWD-NA)，通过引入不匹配的医患交互信息扩充训练数据，并利用序贯三支决策的思想训练模型。具体来说，该方法由两部分组成：一方面引入了不匹配交互信息的方法，以缓解训练冷启动问题；另一方面，提出了一种基于序贯三支决策的训练算法，以动态调整模型训练时的关注度。最后，通过好大夫平台上的真实数据集验证了本文所提STWD-NA方法的有效性。
- Abstract:
- Online healthcare platforms have become increasingly important in meeting the basic medical needs of the public, especially with the growing popularity of smart healthcare. A crucial step in the online consultation process is helping patients find a doctor with relevant expertise, as this not only enhances patient satisfaction but also fosters the development of online healthcare platforms. Unlike traditional recommendation systems, doctor recommendations are subject to privacy protection, and historical records for each patient cannot be accessed. As a result, models can only utilize the most recent consultation records for training, leading to severe data sparsity issues. Similarly, during prediction, recommendations are made solely based on the patient’s current disease description. However, different patients describe their conditions in different ways, which results in varying recommendation effectiveness across patients. This may fail to meet the needs of some, thereby affecting the overall performance of the recommendation system. Along this line, in this paper, we proposed a novel method called Sequential three-way decision with data augmentation (STWD-NA), which combined both matching and mismatched interaction information for doctor recommendation to expand training data. Specifically, this novel method consisted of two parts. On the one hand, it proposed a method to integrate the mismatched interaction information to alleviate the cold-start problem during training. On the other hand, an algorithm was proposed based on the idea of sequential three-way decisions to dynamically adjust the model’s attention during the training process. Evaluation based on real-world dataset haodf.com demonstrates the utility and the effectiveness of the proposed method.
- 参考文献/References:
-
[1] CHEN Min, YANG Jun, ZHOU Jiehan, et al. 5G-smart diabetes: toward personalized diabetes diagnosis with healthcare big data clouds[J]. IEEE communications magazine, 2018, 56(4): 16-23.
[2] 孟秋晴, 熊回香. 基于在线问诊文本信息的医生推荐研究[J]. 情报科学, 2021, 39(6): 152-160.
MENG Qiuqing, XIONG Huixiang. Doctor recommendation based on online consultation text information[J]. Information science, 2021, 39(6): 152-160.
[3] HUANG Chao, CHEN Jiahui, XIA Lianghao, et al. Graph-enhanced multi-task learning of multi-level transition dynamics for session-based recommendation[C]//Proceedings of the AAAI conference on artificial intelligence. Menlo Park: AAAI, 2021, 35(5): 4123-4130.
[4] 叶佳鑫, 熊回香, 蒋武轩. 一种融合患者咨询文本与决策机理的医生推荐算法[J]. 数据分析与知识发现, 2020, 4(S1): 153-164.
YE Jiaxin, XIONG Huixiang, JIANG Wuxuan. A physician recommendation algorithm integrating inquiries and decisions of patients[J]. Data analysis and knowledge discovery, 2020, 4(S1): 153-164.
[5] 翟姗姗, 胡畔, 潘英增, 等. 融合知识图谱与用户病情画像的在线医疗社区场景化信息推荐研究[J]. 情报科学, 2021, 39(5): 97-105.
ZHAI Shanshan, HU Pan, PAN Yingzeng, et al. Scenario-based information recommendation of online medical community based on knowledge graph and disease portrait[J]. Information science, 2021, 39(5): 97-105.
[6] GU Zhiqiang, ZHANG Yuejin. Research on online medical community doctor recommendation based on information fusion[C]//IEEE/WIC/ACM International Conference on Web Intelligence. New York: ACM, 2021: 514-519.
[7] ZHENG Zhi, QIU Zhaopeng, XIONG Hui, et al. DDR: dialogue based doctor recommendation for online medical service[C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Washington: ACM, 2022: 4592-4600.
[8] LU Xiaoxin, ZHANG Yubo, LI Jing, et al. Doctor recommendation in online health forums via expertise learning[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Dublin: USAACL, 2022: 1111-1123.
[9] YUAN Hui, DENG Weiwei. Doctor recommendation on healthcare consultation platforms: an integrated framework of knowledge graph and deep learning[J]. Internet research, 2022, 32(2): 454-476.
[10] LI Quan, CHEN Lingwei, CAI Yong, et al. Hierarchical graph neural network for patient treatment preference prediction with external knowledge[M]//Advances in Knowledge Discovery and Data Mining. Cham: Springer Nature Switzerland, 2023: 204-215.
[11] YAO Yiyu. Three-way decisions with probabilistic rough sets[J]. Information sciences, 2010, 180(3): 341-353.
[12] YAO Yiyu, DENG Xiaofei. Sequential three-way decisions with probabilistic rough sets[C]//IEEE 10th International Conference on Cognitive Informatics and Cognitive Computing. Banff: IEEE, 2011: 120-125.
[13] CHE Mingxuan, ZHAO Lasheng, JIN Bo, et al. A doctor recommendation framework for online medical platforms using multi-source heterogeneous data[C]//Proceedings of the 2021 7th International Conference on Computing and Artificial Intelligence. Tianjin: ACM, 2021: 326-331.
[14] 梁建树, 叶晓庆, 刘盾. 面向在线问诊平台的三支推荐方法[J]. 西北大学学报(自然科学版), 2022, 52(5): 784-796.
LIANG Jianshu, YE Xiaoqing, LIU Dun. Three-way recommendations for online medical consultation platform[J]. Journal of northwest university (natural science edition), 2022, 52(5): 784-796.
[15] SINGH H, SINGH M B, SHARMA R, et al. Optimized doctor recommendation system using supervised machine learning[C]//Proceedings of the 24th International Conference on Distributed Computing and Networking. Kharagpur: ACM, 2023: 360-365.
[16] CHEN Yi, LI Chusong, TANG Minglu. Online doctor recommendation method for doctor-patient interaction data and doctor attributes[C]//2023 IEEE 17th International Conference on Application of Information and Communication Technologies. Baku: IEEE, 2023: 1-6.
[17] 聂卉, 蔡瑞昇. 引入注意力机制的在线问诊推荐研究[J]. 数据分析与知识发现, 2023, 7(8): 138-148.
NIE Hui, CAI Ruisheng. Online doctor recommendation system with attention mechanism[J]. Data analysis and knowledge discovery, 2023, 7(8): 138-148.
[18] LIANG Decui, YI Bochun, CAO Wen, et al. Exploring ensemble oversampling method for imbalanced keyword extraction learning in policy text based on three-way decisions and SMOTE[J]. Expert systems with applications, 2022, 188: 116051.
[19] SHEN Feng, YANG Zhiyuan, ZHAO Xingchao, et al. Reject inference in credit scoring using a three-way decision and safe semi-supervised support vector machine[J]. Information sciences, 2022, 606: 614-627.
[20] ZHOU Jing, LIU Yu, LIANG Decui, et al. Two-stage three-way enhanced multi-criteria classification optimization for risk-averse product design programming[J]. Information sciences, 2023, 632: 757-775.
[21] LIU Dun, YE Xiaoqing. A matrix factorization based dynamic granularity recommendation with three-way decisions[J]. Knowledge-based systems, 2020, 191: 105243.
[22] YE Xiaoqing, LIU Dun. A cost-sensitive temporal-spatial three-way recommendation with multi-granularity decision[J]. Information sciences, 2022, 589: 670-689.
[23] LI Huaxiong, ZHANG Libo, HUANG Bing, et al. Sequential three-way decision and granulation for cost-sensitive face recognition[J]. Knowledge-based systems, 2016, 91: 241-251.
[24] YANG Xin, LOUA M A, WU Meijun, et al. Multi-granularity stock prediction with sequential three-way decisions[J]. Information sciences, 2023, 621: 524-544.
[25] LIANG Decui, WU Yiqi, DUAN Weiyi. Multiple granularity user intention fairness recognition of intelligent government Q & A system via three-way decision[J]. Information sciences, 2023, 631: 305-326.
[26] ROBINSON J, CHUANG C Y, SRA S, et al. Contrastive learning with hard negative samples[EB/OL]. (2020-10-09)[2024-06-10]. https://arxiv.org/abs/2010.04592v2.
[27] LIANG Decui, YI Bochun. Two-stage three-way enhanced technique for ensemble learning in inclusive policy text classification[J]. Information sciences, 2021, 547: 271-288.
[28] DEVLIN J, CHANG Mingwei, LEE K, et al, Bert: pre-training of deep bidirectional transformers for language understanding[C]//Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Minneapolis: NAACL, 2019: 4171–4186.
[29] REIMERS N, GUREVYCH I. Sentence-BERT: sentence embeddings using Siamese BERT-networks[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Hong-Kong: USAACL, 2019.
[30] HADSELL R, CHOPRA S, LECUN Y. Dimensionality reduction by learning an invariant mapping[C]//2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2006: 1735-1742.
[31] LI Huaxiong, ZHANG Libo, ZHOU Xianzhong, et al. Cost-sensitive sequential three-way decision modeling using a deep neural network[J]. International journal of approximate reasoning, 2017, 85: 68-78.
[32] ZHANG Ningyu, JIA Qianghuai, YIN Kangping, et al. Conceptualized representation learning for Chinese biomedical text mining[EB/OL]. (2020-08-25)[2024-06-10]. https://arxiv.org/abs/2008.10813v1.
[33] HUANG Posen, HE Xiaodong, GAO Jianfeng, et al. Learning deep structured semantic models for web search using clickthrough data[C]//Proceedings of the 22nd ACM International Conference on Information & Knowledge Management. San Francisco: ACM, 2013: 2333-2338.
[34] MIKOLOV T, CHEN Kai, CORRADO G, et al. Efficient estimation of word representations in vector space[EB/OL]. (2013-01-16)[2024-06-10]. https://arxiv.org/abs/1301.3781v3.
备注/Memo
收稿日期:2024-6-10。
基金项目:国家自然科学基金项目(62276217, 61876157)；四川省青年科学基金项目(2022JDJQ0034)；中央高校基本科研科技创新项目（2682024KJ005，2682024ZTPY021）.
作者简介:刘珂，硕士研究生，中国人工智能学会会员、中国计算机学会会员，主要研究方向为推荐系统、自然语言处理。E-mail：liukepp100@163.com。;刘盾，教授，中国人工智能学会高级会员、中国计算机学会杰出会员、IEEE高级会员，主要研究方向为数据挖掘与知识发现、粗糙集理论与粒计算、决策支持系统、管理信息系统。发表学术论文200余篇。E-mail：newton83@163.com。;孙扬，博士研究生，中国人工智能学会会员、中国计算机学会会员，主要研究方向为粒计算与知识发现、数据科学与方法。E-mail：sunyangxyr@163.com。
通讯作者:刘盾. E-mail：newton83@163.com
更新日期/Last Update:
2025-01-05