CN-121188404-B - Biological sample intelligent storage supervision system

CN121188404BCN 121188404 BCN121188404 BCN 121188404BCN-121188404-B

Abstract

The invention relates to the technical field of data monitoring, in particular to an intelligent biological sample storage supervision system, which is used for acquiring data anomaly degree according to data discrete features at the current moment in a monitored data sequence, acquiring data credibility according to data difference features at the current moment and adjacent moment, recent data distribution features and data difference features of adjacent sensors, acquiring external isolation degree according to recent data change features, difference change features of recent data and preset door opening time period data and time interval features at the current moment and door opening time, acquiring abnormal feature confidence degree according to the data credibility and the external isolation degree, and acquiring enhancement coefficients according to change trend features of the monitored data sequence. According to the method and the device, the anomaly score at the current moment is obtained according to the data anomaly degree, the anomaly characteristic confidence degree and the enhancement coefficient, and the environmental anomaly early warning is carried out, so that the accuracy of the environmental anomaly early warning is improved.

Inventors

LIU HUI
JIN FENGQI
MA CHUANMIN
WANG HAIYAN
WANG YU
ZHANG SHUOSHUO
ZHUANG YAN

Assignees

山东凯景生物技术有限公司

Dates

Publication Date: 20260512
Application Date: 20250926

Claims (7)

1. A biological sample intelligent storage monitoring system, characterized in that the system comprises the following modules: the data acquisition module is used for acquiring a monitoring data sequence of any sensor in the sample library environment; The first data analysis module is used for obtaining data anomaly degree according to the data discrete characteristics of the current moment in the monitoring data sequence; obtaining data credibility according to the data difference characteristics of the current moment and the adjacent moment, the recent data distribution characteristics of the current moment and the data difference characteristics of the adjacent sensors, and obtaining external isolation according to the recent data change characteristics of the current moment, the difference change characteristics of the recent data of the current moment and the preset door opening time interval data and the time interval characteristics of the current moment and the door opening moment; The system comprises a data sequence monitoring module, a second data analysis module, an enhancement coefficient, an abnormality score and a data analysis module, wherein the data sequence monitoring module is used for monitoring the change trend characteristics of the data sequence; The environment early warning module is used for carrying out environment abnormality early warning according to the abnormality score; The step of obtaining the external isolation according to the recent data change characteristic of the current moment, the difference change characteristic of the recent data of the current moment and the preset door opening time period data, and the time interval characteristic of the current moment and the door opening moment comprises the following steps: The method comprises the steps of calculating the sum of the absolute value of the difference value of the change rate and the change rate mean value at each moment in a preset fluctuation period before the current moment to obtain a change dispersion, calculating the standard deviation of the difference value at all corresponding moments of the preset fluctuation period and preset door opening period data to obtain a difference change degree, and calculating the product of the time interval between the current moment and the latest door opening moment, the change dispersion and the difference change degree to obtain the external isolation degree.
2. The intelligent storage and supervision system for biological samples according to claim 1, wherein the step of obtaining the data anomaly from the discrete features of the data at the current time in the monitored data sequence comprises: And when the value at the current moment is not in the preset normal range, calculating the absolute value of the difference between the value at the current moment and the nearest boundary value of the preset normal range, and obtaining the data anomaly degree at the current moment.
3. The intelligent storage and supervision system for biological samples according to claim 1, wherein the step of obtaining the data reliability according to the data difference characteristics of the current time and the adjacent time, the recent data distribution characteristics of the current time, and the data difference characteristics of the adjacent sensors comprises: Calculating the absolute value of the difference between the current moment and the previous moment in the monitoring data sequence to obtain an instantaneous difference value, calculating standard deviation in a preset short window which does not comprise the current moment to obtain a first value, calculating standard deviation in the preset short window which comprises the current moment to obtain a second value, calculating the ratio of the second value to the first value to obtain a fluctuation difference value, calculating the absolute value of the difference between any sensor at the current moment and other sensors closest to the current moment to obtain a local difference value, and calculating the product and negative correlation mapping of the instantaneous difference value, the fluctuation difference value and the local difference value to obtain the data reliability of any sensor at the current moment.
4. The intelligent storage and supervision system for biological samples according to claim 1, wherein the step of obtaining the confidence level of the abnormal feature according to the data confidence level and the external isolation level comprises: And calculating the product of the data credibility and the external isolation degree to obtain the abnormal feature credibility.
5. The intelligent storage and supervision system for biological samples according to claim 1, wherein the step of obtaining the enhancement coefficient according to the change trend characteristic of the monitored data sequence comprises: and carrying out linear fitting on the monitoring data sequence, and taking the absolute value of the slope of the fitting result as an enhancement coefficient.
6. The biological sample intelligent storage monitoring system of claim 1, wherein the step of obtaining an anomaly score for the current time based on the data anomalies, the anomaly feature confidence level, and the enhancement coefficients comprises: wherein W represents an abnormality score, And (3) representing normalization, wherein Q represents the data anomaly degree, K represents the enhancement coefficient, and F represents the anomaly characteristic confidence degree.
7. The intelligent storage and supervision system for biological samples according to claim 1, wherein the step of performing environmental anomaly pre-warning according to the anomaly score comprises: and when the abnormal score exceeds a preset threshold, early warning is carried out, and the early warning degree and the abnormal score are positively correlated.

Description

Biological sample intelligent storage supervision system Technical Field The invention relates to the technical field of data monitoring, in particular to an intelligent storage supervision system for biological samples. Background In the fields of medical research and the like, the storage management of biological samples is particularly important, wherein the effectiveness and the safety of the vaccine serving as a special biological sample are closely related to storage conditions, and the environmental temperature and the humidity have great influence on the stability of the vaccine, so that when the biological samples such as the vaccine are stored, the storage environment is required to be monitored in real time, and the stability of the biological samples is ensured. The method can simply and rapidly alarm abnormal conditions, but cannot judge whether the moment exceeding the threshold is real abnormal, such as transient environment parameter fluctuation changes caused by instantaneous errors of sensors and opening of a sample library, and the like, the abnormal data cannot reflect real environment abnormality, but can cause frequent early warning of a monitoring system, influence the judgment of a manager on the abnormal conditions, even neglect the real environment abnormal conditions, so that the real environment abnormal conditions are difficult to accurately early warn by monitoring and early warning only through the threshold. Disclosure of Invention In order to solve the technical problems, the invention aims to provide an intelligent storage and supervision system for biological samples, which adopts the following technical scheme: the data acquisition module is used for acquiring a monitoring data sequence of any sensor in the sample library environment; The first data analysis module is used for obtaining data anomaly degree according to the data discrete characteristics of the current moment in the monitoring data sequence; obtaining data credibility according to the data difference characteristics of the current moment and the adjacent moment, the recent data distribution characteristics of the current moment and the data difference characteristics of the adjacent sensors, and obtaining external isolation according to the recent data change characteristics of the current moment, the difference change characteristics of the recent data of the current moment and the preset door opening time interval data and the time interval characteristics of the current moment and the door opening moment; The system comprises a data sequence monitoring module, a second data analysis module, an enhancement coefficient, an abnormality score and a data analysis module, wherein the data sequence monitoring module is used for monitoring the change trend characteristics of the data sequence; and the environment early warning module is used for carrying out environment abnormality early warning according to the abnormality score. Further, the step of obtaining the data anomaly degree according to the data discrete feature of the current moment in the monitoring data sequence comprises the following steps: And when the value at the current moment is not in the preset normal range, calculating the absolute value of the difference between the value at the current moment and the nearest boundary value of the preset normal range, and obtaining the data anomaly degree at the current moment. Further, the step of obtaining the data reliability according to the data difference characteristics of the current moment and the adjacent moment, the recent data distribution characteristics of the current moment and the data difference characteristics of the adjacent sensor comprises the following steps: Calculating the absolute value of the difference between the current moment and the previous moment in the monitoring data sequence to obtain an instantaneous difference value, calculating standard deviation in a preset short window which does not comprise the current moment to obtain a first value, calculating standard deviation in the preset short window which comprises the current moment to obtain a second value, calculating the ratio of the second value to the first value to obtain a fluctuation difference value, calculating the absolute value of the difference between any sensor at the current moment and other sensors closest to the current moment to obtain a local difference value, and calculating the product and negative correlation mapping of the instantaneous difference value, the fluctuation difference value and the local difference value to obtain the data reliability of any sensor at the current moment. Further, the step of obtaining the external isolation according to the recent data change feature of the current time, the difference change feature of the recent data of the current time and the preset door opening time period data, and the time interval feature of the current time and the door opening time includes