While the medical internet provides convenient medical services, it faces challenges such as false appointments, excessive downloads, resource exhaustion, and malicious visits, which constitute challenges to the high availability of services and the high credibility of user behavior. To address this issue, this paper proposes a trust measurement model for the utilization of medical internet resources based on user behavior profiling. The model constructs user behavior profiles by extracting statistical features and behavioral characteristics of the resource utilization behavior sequence of medical internet users, and measures the credibility of user resource utilization behavior sequences using these profiles. This research can be used for user management and risk monitoring in medical internet systems. Experimental results show that the model achieves an accuracy rate of 85.1% in measuring resource utilization behavior on the constructed medical internet behavior dataset, which is significantly better than mainstream LSTM and FBNN models.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

A Trusted Measurement Model for the Utilization of Medical Network Resources Based on User Behavior Portraits

  • Shuaidi Wang,
  • Lijuan Sun,
  • Jingchen Wu,
  • Xu Wu,
  • Yutong Gao

摘要

While the medical internet provides convenient medical services, it faces challenges such as false appointments, excessive downloads, resource exhaustion, and malicious visits, which constitute challenges to the high availability of services and the high credibility of user behavior. To address this issue, this paper proposes a trust measurement model for the utilization of medical internet resources based on user behavior profiling. The model constructs user behavior profiles by extracting statistical features and behavioral characteristics of the resource utilization behavior sequence of medical internet users, and measures the credibility of user resource utilization behavior sequences using these profiles. This research can be used for user management and risk monitoring in medical internet systems. Experimental results show that the model achieves an accuracy rate of 85.1% in measuring resource utilization behavior on the constructed medical internet behavior dataset, which is significantly better than mainstream LSTM and FBNN models.