<p>In the digital age, enterprise human resource management information systems (HRMIS) store a large amount of sensitive information of employees, such as personal information, performance data and salary records, etc. The input data of the algorithm may contain users’ sensitive information, and the output results may be maliciously exploited. This paper analyzes the existing data mining algorithms, studies their applicability and potential risks in the network information security environment, and proposes an incremental learning method based on fuzzy data mining algorithms. Combined with sensor network technology, the data extraction process is optimized. This paper designs a network information security framework for a low-cost human resource management information system (HRMIS), adopting multi-layer protection mechanisms such as encryption technology, access control, and intrusion detection systems to ensure the confidentiality, integrity, and availability of data. Through experimental verification, the fuzzy data mining algorithm proposed in this paper can effectively improve the accuracy and efficiency of data mining while protecting data privacy. In terms of network information security, the HRMIS framework designed in this paper can effectively resist common network attacks, such as SQL injection, cross-site scripting attacks, and distributed denial-of-service attacks, etc. The experimental results show that no data leakage incidents occurred during the data transmission and storage process of this framework, and the overall security of the system has been significantly improved. Yc, by integrating fuzzy data mining algorithms and network information security technologies, can effectively enhance the efficiency and security of enterprise human resource management. By adopting encryption technology, access control mechanisms and intrusion detection systems, enterprises can protect employees’ privacy while fully leveraging data mining technology to optimize the allocation of human resources.</p>