Time series exception detection system based on deep learning

• Main Authors: MA PENGBIN, ZHANG FENGBIN, LIANG LU
• Format: Patent
• Language: Chinese; English
• Published: 11.06.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS

The invention discloses a time sequence exception detection system based on deep learning. The system comprises a user, a detection module, a display module, an alarm module and a power supply module, the user is connected with the detection module, the display module and the alarm module are both connected with the detection module, and the power supply module supplies power to the alarm module, the detection module and the display module separately. According to the method, the time sequence data is detected in real time by keeping the standard and threshold value of data exception, the time required for exceeding the threshold value can be calculated according to the trend of the current time sequence, and an alarm is given in advance, so that the safety of a patient is further guaranteed, and a large amount of manpower and material resources are saved. 本发明公开了一种基于深度学习的时间序列异常检测系统，包括用户、检测模块、显示模块、报警模块和电源模块，用户和检测模块相连接，显示模块和报警模块均与检测模块相连接，电源模块分别为报警模块、检测模块和显示模块供电，本发明中，通过保持数据异常的标准以及阈值，实时检测时间序列数据，并且能够根据当前时间序列的趋势，进而