A data management method for multi-target biohazard factor immunoassay analyzer

Abstract

The present invention discloses a data management method for a multi-target biohazard factor immunoassay analyzer, which relates to the field of biological monitoring data management technology. It solves the technical problems of difficulty in ensuring the confidentiality of sample data, providing only a digital record of a single test result, lacking multi-factor correlation analysis, and affecting the accuracy of immunoassays. By real-time monitoring of the data storage saturation coefficient, operation saturation coefficient, and operation abnormality coefficient of edge nodes, potential operating pressures of edge nodes can be discovered in a timely manner, thereby taking corresponding measures for prevention and optimization to avoid degradation of edge node system performance. According to the comprehensive operating pressure analysis results, data storage and computing tasks of edge nodes can be more reasonably allocated to ensure that resources are fully utilized. The cloud processing platform can analyze the detection configuration parameters, experimental signal data, and quality control data of reagent card experiments of different categories in real time to ensure the accuracy and reliability of the data.

Description

Technical Field

[0001] The invention belongs to the field of biological monitoring data management, and in particular relates to a data management method for a multi-target biohazard factor immunoassay analyzer. Background Art

[0002] Recent advances in biotechnology, particularly in molecular biology, immunology, and bioinformatics, have provided a solid theoretical foundation and technical support for the development of multi-target biohazard agent immunoassay analyzers. These technological advances have enabled researchers to gain a deeper understanding of the structure and function of biomolecules, enabling the design of more accurate and efficient immunoassay methods. Immunoassay technology is one of the core technologies for multi-target biohazard agent detection. Continuous innovations in areas such as antibody preparation, fluorescent labeling, and quantum dot immunochromatography have significantly improved the sensitivity and accuracy of immunoassays. These innovative technologies have enabled the development of multi-target biohazard agent immunoassay analyzers with more sensitive, accurate, and efficient detection methods. Multi-target biohazard agent immunoassay analyzers are advanced instruments used to detect and analyze multiple biohazard agents and are widely used in public health, food safety, and environmental monitoring. With the rapid development of biotechnology and the increasing demand for biosafety, the importance of data management systems in this field has become increasingly prominent.

[0003] Traditional systems rely on manual export-analysis processes, which delays decision-making; large amounts of sample data are uploaded directly to the cloud, making it difficult to ensure the confidentiality of sample data; at the same time, most data management solutions for immunoassays analyze various data sequentially, only providing digital records of single test results, lacking multi-factor correlation analysis, which affects the accuracy of immunoassays. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a data management method for a multi-target biohazard factor immunoassay analyzer, which is used to solve the technical problems of difficulty in ensuring the confidentiality of sample data, providing only a digital record of a single test result, lacking multi-factor correlation analysis, and affecting the accuracy of immunoassay.

[0005] To solve the above problems, the first aspect of the present invention provides a data management method for a multi-target biohazard factor immunoassay analyzer, comprising the following steps:

[0006] An edge node is set up on the immunoassay analyzer to store sample information and environmental data at the edge, while test configuration parameters, experimental signal data, and quality control data are stored in the cloud. By constructing key-value pairs based on SampleID, data association between corresponding data is achieved.

[0007] A unique RFID tag is embedded in the reagent card, which records the reagent card number, SampleID and sample data storage address;

[0008] Record the device ID, device type, device location, and usage frequency in the device management table. Group the immunoassay analyzers into high-frequency, sub-high-frequency, medium-frequency, and low-frequency groups based on the device usage frequency within different threshold ranges.

[0009] Detect the data storage saturation coefficient, operation saturation coefficient, and operation abnormality coefficient of the edge nodes of each immunoassay analyzer group, analyze the comprehensive operation pressure, and allocate the data storage and computing tasks of the edge nodes according to the comprehensive operation pressure analysis results, and modify the corresponding data tables;

[0010] The cloud processing platform performs real-time analysis on the detection configuration parameters, experimental signal data and quality control data of different categories of reagent cards during experiments, conducts reliability analysis on the experimental data, and conducts re-experiments on experimental data that may have fault detection until there is no fault detection in the experimental data detection, and records the corresponding experimental signal data as final data in the data table of the cloud processing platform.

[0011] Optionally, in an example of the above aspect, an edge node is set at the immunoassay analyzer end, sample information and environmental data are stored at the edge end, detection configuration parameters, experimental signal data and quality control data are stored in the cloud, and data association between corresponding data is achieved by constructing a key-value pair about SampleID, including the following steps:

[0012] An edge node is set up at the immunoassay analyzer to obtain sample information of biological samples detected by the edge end and collect the detection configuration parameters of the immunoassay analyzer. During the biological sample detection process, the experimental signal data, quality control data, and environmental data of the immunoassay analyzer are received in parallel through the multimodal sensor interface.

[0013] The collected data is timestamp aligned, and the signal baseline is corrected based on the noise filtering technology of wavelet transform. The detection configuration parameters, experimental signal data and quality control data are encrypted and sent to the cloud processing platform. The corresponding data table is generated with SampleID as the foreign key. Based on the sample information and environmental data stored on the edge, the sample and environmental data table is generated with SampleID as the foreign key, and the storage address of the sample and environmental data table corresponding to the SampleID is sent to the cloud processing platform;

[0014] Establish a reagent card management list and device management table in the database of the cloud processing platform, classify the reagent cards, label each classified reagent card, record the device ownership of the reagent card, add the SampleID of the reagent card test sample to the reagent card management list, and form a SampleID list by counting the SampleIDs corresponding to the device test samples, and use the corresponding device ID as the foreign key of the SampleID list.

[0015] Optionally, in an example of the above aspect, classifying the reagent cards includes:

[0016] According to the reaction mechanism of the reagent card, it can be classified into: enzyme-linked immunosorbent assay reagent card, fluorescent immunoassay reagent card and chemiluminescent immunoassay reagent card;

[0017] A reagent card management list is set for each category of reagent cards, and the target type of the corresponding reagent card is marked in the reagent card management list, including: bacterial target, viral target, toxin target and parasite target.

[0018] Optionally, in an example of the above aspect, the device ID, device type, device location, and usage frequency are recorded in a device management table, and the immunoassay analyzers are grouped into a high-frequency usage group, a sub-high-frequency usage group, a medium-frequency usage group, and a low-frequency usage group according to the usage frequencies of the devices falling within different threshold ranges, including the following steps:

[0019] Record the device ID, device type, device location, and usage frequency in the device management table, set a detection time period, and count the device usage frequency during the detection time period;

[0020] Obtain the device's usage frequency data for several past detection time periods, calculate the average value to obtain the average frequency data, and perform a weighted average of the average frequency data and the device's usage frequency data for the most recent detection time period to obtain the usage frequency data used for device grouping;

[0021] Collect historical device usage frequency data and rank them, taking the top 20%, top 40%, and top 60% of the usage frequency data nodes as the corresponding usage frequency thresholds;

[0022] According to the usage frequencies of the obtained devices being within different threshold ranges, the immunoassay analyzers are grouped into a high-frequency usage group, a sub-high-frequency usage group, a medium-frequency usage group, and a low-frequency usage group, and the groups are updated regularly.

[0023] Optionally, in an example of the above aspect, detecting the edge node data storage saturation coefficient, operation saturation coefficient, and operation abnormality coefficient of each immune analyzer group includes the following steps:

[0024] For the immunoassay analyzers in the high-frequency usage group and the sub-high-frequency usage group, the memory usage data, CPU usage data, and operation abnormality data of the immunoassay analyzers were tested in each testing time period.

[0025] For the immunoassay analyzers in the medium-frequency usage group, the memory usage data, CPU usage data, and operation abnormality data of the immunoassay analyzers were tested at intervals of several test time periods.

[0026] For the immunoassay analyzers in the low-frequency use group, the trigger condition is to receive three or more error messages during the detection period to detect the memory usage data, CPU usage data, and operation abnormality data of the immunoassay analyzers;

[0027] The edge node data storage saturation coefficient, operation saturation coefficient and operation abnormality coefficient are calculated respectively based on the memory usage data, CPU usage data and operation abnormality data.

[0028] Optionally, in an example of the above aspect, respectively calculating the edge node data storage saturation coefficient, the operation saturation coefficient, and the operation abnormality coefficient according to the memory usage data, the CPU usage data, and the operation abnormality data includes the following steps:

[0029] The data storage saturation coefficient of the edge node is calculated using the following formula:

[0030] ;

[0031] Among them, SSI is the data storage saturation coefficient, Ct is the currently occupied storage space, C is the total storage capacity of the node, St is the hourly increment of node data, α and β are the corresponding weights, and the default α=0.6, β=0.4;

[0032] The operating saturation coefficient of the edge node is calculated using the following formula:

[0033] ;

[0034] Where OSI is the ‌operation saturation coefficient, CPUt / CPU is the current CPU occupancy, Ct / C is the current memory occupancy, N is the maximum concurrent task capacity, Nt is the number of tasks in the pending task queue, γ is the queue pressure weight, and the default γ=0.2;

[0035] The number of occurrences of different types of abnormal events in different detection time periods is counted, and the operational abnormality coefficient of the edge node is calculated using the following formula:

[0036] ;

[0037] Where OAI is the operational anomaly coefficient, Eti is the number of occurrences of the i-th abnormal event within the detection period, Ebasei is the benchmark frequency of similar abnormal events, which is set to the historical mean of similar abnormal events, t0 is the length of the detection period, Wi is the event severity weight, for example: hardware failure λ=0.1, communication delay λ=0.3, μ is the time decay factor, and the default μ=0.1.

[0038] Optionally, in an example of the above aspect, analyzing the comprehensive operating pressure includes the following steps:

[0039] For the immunoassay analyzers in the high-frequency and sub-high-frequency usage groups, the comprehensive operating pressure is analyzed using the following formula based on the edge node data storage saturation coefficient, operation saturation coefficient, and operation abnormality coefficient:

[0040] ;

[0041] Among them, Health1 is the comprehensive operating stress analysis value of the immunoassay analyzers in the high-frequency usage group and the sub-high-frequency usage group, SSI is the data storage saturation coefficient, OSI is the operation saturation coefficient, OAI is the operation abnormality coefficient, σ is the node health correction factor, σ=1-(Fhardware / Fmax), Fhardware is the current hardware aging score, and Fmax is the initial value of the node hardware aging score;

[0042] For the immunoassay analyzers in the medium frequency group, the comprehensive operating pressure is analyzed using the following formula:

[0043] ;

[0044] Among them, Health2 is the comprehensive operating pressure analysis value of the immunoassay analyzer in the medium frequency use group;

[0045] For the immunoassay analyzers in the low-frequency use group, the comprehensive operating pressure is analyzed using the following formula:

[0046] ;

[0047] Among them, Health3 is the comprehensive operating pressure analysis value of the immunoassay analyzer in the low-frequency usage group.

[0048] Optionally, in an example of the above aspect, allocating data storage and computing tasks to edge nodes according to the comprehensive operation pressure analysis results includes the following steps:

[0049] According to the results of the comprehensive operation pressure analysis, if the comprehensive operation pressure analysis value is greater than the first threshold, the nearest node will be selected from the nodes whose comprehensive operation pressure analysis value is less than the second threshold, 10% of the historical storage data will be transferred to the selected node, and the last 10% of the tasks in the pending task queue will be transferred to the cloud processing platform until the comprehensive operation pressure analysis value of the corresponding node is no greater than the first threshold.

[0050] Optionally, in an example of the above aspect, the cloud processing platform performs real-time analysis on the detection configuration parameters, experimental signal data, and quality control data of different categories of reagent card experiments to perform reliability analysis on the experimental data, including the following steps:

[0051] The cloud processing platform obtains reagent cards of different categories, detection configuration parameters for different target types, experimental signal data, and historical data of normal detection of quality control data, as well as historical data when detection failures occur, and adds normal detection and failure detection labels to the historical data;

[0052] Establish a multimodal deep confidence assessment model, and use data from target type detection of bacterial targets, viral targets, toxin targets, and parasite targets using different classifications of reagent cards to train the corresponding model;

[0053] The cloud processing platform obtains the detection configuration parameters, experimental signal data and quality control data of different categories of reagent cards in real time;

[0054] Through the trained model, the reliability analysis of the experimental data is performed to identify the data when the corresponding target type is detected by the corresponding classified reagent card, which is normal detection data or fault detection data. If fault detection data occurs, the data during the experiment is unreliable and is fault detection data. Otherwise, the data during the experiment is reliable.

[0055] Optionally, in an example of the above aspect, establishing a multimodal depth confidence assessment model includes the following steps:

[0056] Construct a multimodal deep belief network and set up a static parameter branch, a dynamic signal branch, and a quality control data branch in the input layer;

[0057] The static parameter branch is used to input detection configuration parameters and is set as a fully connected layer. The dynamic signal branch is used to input experimental signal data and is set as an LSTM network layer. The LSTM network layer processes the time series signals of the experimental signal data, and the sliding window length is set to 30 sampling periods. The quality control data branch is used to input quality control data and is set as a time series convolution layer. By constructing a time series convolution network, the cumulative effect of quality control deviations is captured, and the convolution kernel width matches the calibration period.

[0058] The fusion layer sets up a cross-modal attention mechanism to perform weighted fusion of the features of each branch;

[0059] The output layer uses the Sigmoid activation function to output data that is the classification of normal detection and fault detection.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] The present invention can timely discover the operating pressure of potential edge nodes by real-time monitoring of the data storage saturation coefficient, operation saturation coefficient and operation abnormality coefficient of edge nodes, so as to take corresponding measures for prevention and optimization to avoid edge node system crash or performance degradation. According to the comprehensive operation pressure analysis results, the data storage and computing tasks of edge nodes can be more reasonably allocated to ensure that resources are fully utilized and avoid resource waste and overload. This dynamic resource allocation method can be flexibly adjusted according to actual needs, thereby improving the flexibility and response speed of the system. By optimizing resource allocation and reducing system bottlenecks, the overall performance of the immunoassay group can be significantly improved.

[0062] The cloud-based processing platform of the present invention can analyze the detection configuration parameters, experimental signal data, and quality control data of different types of reagent card experiments in real time to ensure the accuracy and reliability of the data. For experimental data that may have fault detection, the platform will re-test until the data detection is no longer faulty, thereby further improving the reliability of the data. Through the automated analysis of the cloud-based processing platform, the possibility of manual intervention and errors is reduced, and the efficiency of the experiment is improved. The platform can intelligently manage the experimental process, including data entry, analysis, storage, and report generation, thereby realizing the automated management of the experiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0064] Figure 1 Schematic diagram of the process of the present invention;

[0065] Figure 2 This is a schematic diagram of the classification of reagent cards of the present invention. DETAILED DESCRIPTION

[0066] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0067] See also Figure 1-Figure 2 The first embodiment of the present invention provides a data management method for a multi-target biohazard factor immunoassay analyzer, comprising the following steps:

[0068] An edge node is set up on the immunoassay analyzer to store sample information and environmental data at the edge, while test configuration parameters, experimental signal data, and quality control data are stored in the cloud. By constructing key-value pairs based on SampleID, data association between corresponding data is achieved.

[0069] A unique RFID tag is embedded in the reagent card, which records the reagent card number, SampleID and sample data storage address;

[0070] Record the device ID, device type, device location, and usage frequency in the device management table. Group the immunoassay analyzers into high-frequency, sub-high-frequency, medium-frequency, and low-frequency groups based on the device usage frequency within different threshold ranges.

[0071] Detect the data storage saturation coefficient, operation saturation coefficient, and operation abnormality coefficient of the edge nodes of each immunoassay analyzer group, analyze the comprehensive operation pressure, and allocate the data storage and computing tasks of the edge nodes according to the comprehensive operation pressure analysis results, and modify the corresponding data tables;

[0072] The cloud processing platform performs real-time analysis on the detection configuration parameters, experimental signal data and quality control data of different categories of reagent cards during experiments, conducts reliability analysis on the experimental data, and conducts re-experiments on experimental data that may have fault detection until there is no fault detection in the experimental data detection, and records the corresponding experimental signal data as final data in the data table of the cloud processing platform.

[0073] Specifically, in this embodiment, an edge node is set at the immune analyzer end;

[0074] Edge node configuration, set to:‌

[0075] Hardware: NVIDIA Jetson Xavier, 16GB RAM + 256GB SSD;

[0076] Data compression: Using Apache Parquet column storage, the compression ratio reaches 5:1;

[0077] Sample information and environmental data are stored on the edge, while detection configuration parameters, experimental signal data, and quality control data are stored in the cloud. By constructing key-value pairs based on SampleID, data association between corresponding data is achieved.

[0078] ‌Secure transport protocol, set to:‌

[0079] Edge → Cloud: MQTT over TLS 1.3, batch transmission every 5 minutes;

[0080] Key field encryption: The sample ID is encrypted using the national encryption SM4 algorithm.

[0081] Data latency tests were conducted on the cloud and edge, and the results are shown in Table 1 below.

[0082] Table 1: Cloud and edge performance test table

[0083]

[0084] By making the edge lightweight, only small, frequently accessed data (such as the SampleID mapping table) is retained, reducing storage pressure on edge devices. Cloud storage facilitates on-demand expansion. Experimental signals and quality control data are often large in volume, and cloud storage can be elastically expanded on demand, avoiding overinvestment in local hardware.

[0085] Environmental data (such as temperature and humidity) and sample metadata (such as ID and type) are stored at the edge, supporting real-time reading and fast response, avoiding cloud transmission delays, and suitable for instant decision-making during the experiment.

[0086] Large-scale data such as experimental signals are processed centrally in the cloud, and the high-performance computing capabilities of cloud resources are used to complete complex analysis, balancing efficiency and flexibility.

[0087] The RFID tag records the reagent card number, SampleID, and sample data storage address. In this embodiment, the RFID reagent card settings include:

[0088] Reagent card number: RC-001-A;

[0089] SampleID: SMP-20240515-007;

[0090] Sample data storage address:

[0091] Edge node path: EdgeNode-3 / Samples / SMP-20240515-007.json;

[0092] Automatically match cloud quality control data, such as Cloud / QC / SMP-20240515-007.csv, with edge sample metadata through SampleID.

[0093] Record the device ID, device type, device location, and usage frequency in the device management table. The structure of the device management table is shown in Table 2 below:

[0094] Table 2: Device Management Table

[0095]

[0096] Use device logs to collect real-time statistics on the average daily usage of each immunoassay analyzer. For example, if device IA-003 tested 63 samples in the past 7 days, the average daily usage frequency is 9 times.

[0097] The system automatically runs the grouping algorithm every morning to update the device grouping labels.

[0098] Detect the data storage saturation coefficient, operation saturation coefficient, and operation abnormality coefficient of the edge nodes of each immunoassay analyzer group, analyze the comprehensive operation pressure, and allocate the data storage and computing tasks of the edge nodes according to the comprehensive operation pressure analysis results, and modify the corresponding data tables;

[0099] By real-time monitoring of the data storage saturation coefficient, operation saturation coefficient, and operation anomaly coefficient of edge nodes, potential operating pressure on edge nodes can be discovered in a timely manner, so that corresponding measures can be taken for prevention and optimization to avoid edge node system crashes or performance degradation. Based on the results of the comprehensive operation pressure analysis, the data storage and computing tasks of edge nodes can be more reasonably allocated to ensure that resources are fully utilized and to avoid resource waste and overload. This dynamic resource allocation method can be flexibly adjusted according to actual needs, improving the flexibility and response speed of the system. By optimizing resource allocation and reducing system bottlenecks, the overall performance of the immunoassay analyzer group can be significantly improved, including data processing speed and response time.

[0100] Analyze the comprehensive operating pressure and allocate data storage and computing tasks to edge nodes based on the results of the comprehensive operating pressure analysis, so as to facilitate the timely discovery and handling of potential problems and avoid increased maintenance costs caused by edge node system crashes or performance degradation; at the same time, reasonable resource allocation and optimized system performance also help reduce the frequency and cost of hardware and software updates.

[0101] The cloud processing platform performs real-time analysis on the detection configuration parameters, experimental signal data and quality control data of different categories of reagent cards during experiments, conducts reliability analysis on the experimental data, and conducts re-experiments on experimental data that may have fault detection until there is no fault detection in the experimental data detection, and records the corresponding experimental signal data as final data in the data table of the cloud processing platform.

[0102] The cloud processing platform can analyze in real time the detection configuration parameters, experimental signal data, and quality control data of reagent card experiments of different categories to ensure the accuracy and reliability of the data. For experimental data that may have faulty detection, the platform will conduct re-experiments until the data detection is no longer faulty, thereby further improving the reliability of the data. Through the automated analysis of the cloud processing platform, the possibility of manual intervention and errors is reduced, and experimental efficiency is improved. The platform can intelligently manage the experimental process, including data entry, analysis, storage, and report generation, thereby realizing the automated management of experiments. The cloud processing platform provides a safe and reliable data storage environment to ensure that experimental data will not be lost or tampered with. Cloud storage also means that users can access experimental data anytime and anywhere via the Internet, improving the availability and flexibility of data.

[0103] In one embodiment of the present invention, an edge node is set up at the immunoassay analyzer end, sample information and environmental data are stored at the edge end, and detection configuration parameters, experimental signal data and quality control data are stored in the cloud. By constructing a key-value pair based on SampleID, data association between corresponding data is achieved, including the following steps:

[0104] An edge node is set up at the immunoassay analyzer to obtain sample information of biological samples detected by the edge end and collect the detection configuration parameters of the immunoassay analyzer. During the biological sample detection process, the experimental signal data, quality control data, and environmental data of the immunoassay analyzer are received in parallel through the multimodal sensor interface.

[0105] The collected data is timestamp aligned, and the signal baseline is corrected based on the noise filtering technology of wavelet transform. The detection configuration parameters, experimental signal data and quality control data are encrypted and sent to the cloud processing platform. The corresponding data table is generated with SampleID as the foreign key. Based on the sample information and environmental data stored on the edge, the sample and environmental data table is generated with SampleID as the foreign key, and the storage address of the sample and environmental data table corresponding to the SampleID is sent to the cloud processing platform;

[0106] Establish a reagent card management list and device management table in the database of the cloud processing platform, classify the reagent cards, label each classified reagent card, record the device ownership of the reagent card, add the SampleID of the reagent card test sample to the reagent card management list, and form a SampleID list by counting the SampleIDs corresponding to the device test samples, and use the corresponding device ID as the foreign key of the SampleID list.

[0107] Furthermore, the reagent cards are classified into:

[0108] According to the reaction mechanism of the reagent card, it can be classified into: enzyme-linked immunosorbent assay reagent card, fluorescent immunoassay reagent card and chemiluminescent immunoassay reagent card;

[0109] A reagent card management list is set for each category of reagent cards, and the target type of the corresponding reagent card is marked in the reagent card management list, including: bacterial target, viral target, toxin target and parasite target.

[0110] Specifically, in this embodiment, the target types are divided into:

[0111] Bacterial target: An antibody or antigen that is directed against a specific bacterium.

[0112] Viral Target: An antibody or antigen that is specific to a specific virus.

[0113] Toxin targets: Detection of specific toxins, such as bacterial toxins, fungal toxins, etc.

[0114] Parasite target: An antibody or antigen that is directed against a specific parasite.

[0115] The multimodal sensing interface receives optical signals (fluorescence intensity), electrochemical signals (current / voltage), mass spectrometry data (m / z value), etc. in parallel, aligns the timestamps of the collected data, and corrects the signal baseline based on noise filtering technology based on wavelet transform.

[0116] In one embodiment of the present invention, the device ID, device type, device location, and usage frequency are recorded in a device management table, and the immunoassay analyzers are grouped into a high-frequency usage group, a sub-high-frequency usage group, a medium-frequency usage group, and a low-frequency usage group according to the usage frequencies of the devices within different threshold ranges, including the following steps:

[0117] Record the device ID, device type, device location, and usage frequency in the device management table, set a detection time period, and count the device usage frequency during the detection time period;

[0118] Obtain the device's usage frequency data for several past detection time periods, calculate the average value to obtain the average frequency data, and perform a weighted average of the average frequency data and the device's usage frequency data for the most recent detection time period to obtain the usage frequency data used for device grouping;

[0119] Collect historical device usage frequency data and rank them, taking the top 20%, top 40%, and top 60% of the usage frequency data nodes as the corresponding usage frequency thresholds;

[0120] According to the usage frequencies of the obtained devices being within different threshold ranges, the immunoassay analyzers are grouped into a high-frequency usage group, a sub-high-frequency usage group, a medium-frequency usage group, and a low-frequency usage group, and the groups are updated regularly.

[0121] In one embodiment of the present invention, detecting the data storage saturation coefficient, operation saturation coefficient, and operation abnormality coefficient of the edge node of each immune analyzer group includes the following steps:

[0122] For the immunoassay analyzers in the high-frequency usage group and the sub-high-frequency usage group, the memory usage data, CPU usage data, and operation abnormality data of the immunoassay analyzers were tested in each testing time period.

[0123] For the immunoassay analyzers in the medium-frequency usage group, the memory usage data, CPU usage data, and operation abnormality data of the immunoassay analyzers were tested at intervals of several test time periods.

[0124] For the immunoassay analyzers in the low-frequency use group, the trigger condition is to receive three or more error messages during the detection period to detect the memory usage data, CPU usage data, and operation abnormality data of the immunoassay analyzers;

[0125] The edge node data storage saturation coefficient, operation saturation coefficient and operation abnormality coefficient are calculated respectively based on the memory usage data, CPU usage data and operation abnormality data.

[0126] In one embodiment of the present invention, the edge node data storage saturation coefficient, the operation saturation coefficient, and the operation abnormality coefficient are calculated based on the memory usage data, the CPU usage data, and the operation abnormality data, including the following steps:

[0127] The data storage saturation coefficient of the edge node is calculated using the following formula:

[0128] ;

[0129] Among them, SSI is the data storage saturation coefficient, Ct is the currently occupied storage space, C is the total storage capacity of the node, St is the hourly increment of node data, α and β are the corresponding weights, and the default α=0.6, β=0.4;

[0130] The operating saturation coefficient of the edge node is calculated using the following formula:

[0131] ;

[0132] Where OSI is the ‌operation saturation coefficient, CPUt / CPU is the current CPU occupancy, Ct / C is the current memory occupancy, N is the maximum concurrent task capacity, Nt is the number of tasks in the pending task queue, γ is the queue pressure weight, and the default γ=0.2;

[0133] The number of occurrences of different types of abnormal events in different detection time periods is counted, and the operational abnormality coefficient of the edge node is calculated using the following formula:

[0134] ;

[0135] Where OAI is the operational anomaly coefficient, Eti is the number of occurrences of the i-th abnormal event within the detection period, Ebasei is the benchmark frequency of similar abnormal events, which is set to the historical mean of similar abnormal events, t0 is the length of the detection period, Wi is the event severity weight, for example: hardware failure λ=0.1, communication delay λ=0.3, μ is the time decay factor, and the default μ=0.1.

[0136] In one embodiment of the present invention, analyzing the comprehensive operating pressure includes the following steps:

[0137] For the immunoassay analyzers in the high-frequency and sub-high-frequency usage groups, the comprehensive operating pressure is analyzed using the following formula based on the edge node data storage saturation coefficient, operation saturation coefficient, and operation abnormality coefficient:

[0138] ;

[0139] Among them, Health1 is the comprehensive operating stress analysis value of the immunoassay analyzers in the high-frequency usage group and the sub-high-frequency usage group, SSI is the data storage saturation coefficient, OSI is the operation saturation coefficient, OAI is the operation abnormality coefficient, σ is the node health correction factor, σ=1-(Fhardware / Fmax), Fhardware is the current hardware aging score, and Fmax is the initial value of the node hardware aging score;

[0140] For the immunoassay analyzers in the medium frequency group, the comprehensive operating pressure is analyzed using the following formula:

[0141] ;

[0142] Among them, Health2 is the comprehensive operating pressure analysis value of the immunoassay analyzer in the medium frequency use group;

[0143] For the immunoassay analyzers in the low-frequency use group, the comprehensive operating pressure is analyzed using the following formula:

[0144] ;

[0145] Among them, Health3 is the comprehensive operating pressure analysis value of the immunoassay analyzer in the low-frequency usage group.

[0146] In one embodiment of the present invention, allocating data storage and computing tasks to edge nodes based on comprehensive operational pressure analysis results includes the following steps:

[0147] According to the results of the comprehensive operation pressure analysis, if the comprehensive operation pressure analysis value is greater than the first threshold, the nearest node will be selected from the nodes whose comprehensive operation pressure analysis value is less than the second threshold, 10% of the historical storage data will be transferred to the selected node, and the last 10% of the tasks in the pending task queue will be transferred to the cloud processing platform until the comprehensive operation pressure analysis value of the corresponding node is no greater than the first threshold.

[0148] Specifically, a large number of operating data of immune analyzers at edge nodes are obtained, and the comprehensive operating pressure analysis values ​​of the immune analyzers are calculated. The corresponding comprehensive operating pressure analysis values ​​are obtained from the data with significantly increased edge node data delay and prolonged response time, and the average is taken as the first threshold; the comprehensive operating pressure analysis values ​​of the immune analyzers at the edge end with an edge node data delay time of less than 50ms are statistically counted, and the average is taken as the second threshold.

[0149] In one embodiment of the present invention, a cloud processing platform performs real-time analysis of the detection configuration parameters, experimental signal data, and quality control data of different types of reagent card experiments to perform reliability analysis on the experimental data, including the following steps:

[0150] The cloud processing platform obtains reagent cards of different categories, detection configuration parameters for different target types, experimental signal data, and historical data of normal detection of quality control data, as well as historical data when detection failures occur, and adds normal detection and failure detection labels to the historical data;

[0151] Establish a multimodal deep confidence assessment model, and use data from target type detection of bacterial targets, viral targets, toxin targets, and parasite targets using different classifications of reagent cards to train the corresponding model;

[0152] The cloud processing platform obtains the detection configuration parameters, experimental signal data and quality control data of different categories of reagent cards in real time;

[0153] Through the trained model, the reliability analysis of the experimental data is performed to identify the data when the corresponding target type is detected by the corresponding classified reagent card, which is normal detection data or fault detection data. If fault detection data occurs, the data during the experiment is unreliable and is fault detection data. Otherwise, the data during the experiment is reliable.

[0154] Furthermore, a multimodal deep confidence assessment model is established, which includes the following steps:

[0155] Construct a multimodal deep belief network and set up a static parameter branch, a dynamic signal branch, and a quality control data branch in the input layer;

[0156] The static parameter branch is used to input detection configuration parameters and is set as a fully connected layer. The dynamic signal branch is used to input experimental signal data and is set as an LSTM network layer. The LSTM network layer processes the time series signals of the experimental signal data, such as fluorescence intensity fluctuations and robotic arm acceleration. The sliding window length is set to 30 sampling periods. The quality control data branch is used to input quality control data and is set as a time series convolution layer. By constructing a time series convolution network, the cumulative effect of quality control deviations is captured. The convolution kernel width matches the calibration period.

[0157] The fusion layer sets up a cross-modal attention mechanism to perform weighted fusion of the features of each branch;

[0158] The output layer uses the Sigmoid activation function to output data that is the classification of normal detection and fault detection.

[0159] The above embodiments are only used to illustrate the technical method of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A data management method for a multi-target biohazard factor immunoassay analyzer, characterized in that: The following steps are involved: An edge node is set up on the immunoassay analyzer to store sample information and environmental data at the edge, while test configuration parameters, experimental signal data, and quality control data are stored in the cloud. By constructing key-value pairs based on SampleID, data association between corresponding data is achieved. A unique RFID tag is embedded in the reagent card, which records the reagent card number, SampleID and sample data storage address; Record the device ID, device type, device location, and usage frequency in the device management table. Group the immunoassay analyzers into high-frequency, sub-high-frequency, medium-frequency, and low-frequency groups based on the device usage frequency within different threshold ranges. Detect the data storage saturation coefficient, operation saturation coefficient, and operation abnormality coefficient of the edge nodes of each immunoassay analyzer group, analyze the comprehensive operation pressure, and allocate the data storage and computing tasks of the edge nodes according to the comprehensive operation pressure analysis results, and modify the corresponding data tables; The cloud processing platform performs real-time analysis of the test configuration parameters, experimental signal data, and quality control data of different types of reagent cards during experiments, and performs reliability analysis on the experimental data. For experimental data with fault detection, the platform conducts re-experiments until the data detection during the experiment is free of fault detection. The corresponding experimental signal data is recorded as the final data in the data table of the cloud processing platform. The data association between the corresponding data is achieved by constructing a key-value pair about SampleID, including the following steps: An edge node is set up at the immunoassay analyzer to obtain sample information of biological samples detected by the edge end and collect the detection configuration parameters of the immunoassay analyzer. During the biological sample detection process, the experimental signal data, quality control data, and environmental data of the immunoassay analyzer are received in parallel through the multimodal sensor interface. The collected data is timestamp aligned, and the signal baseline is corrected based on the noise filtering technology of wavelet transform. The detection configuration parameters, experimental signal data and quality control data are encrypted and sent to the cloud processing platform. The corresponding data table is generated with SampleID as the foreign key. Based on the sample information and environmental data stored on the edge, the sample and environmental data table is generated with SampleID as the foreign key, and the storage address of the sample and environmental data table corresponding to the SampleID is sent to the cloud processing platform; Establish a reagent card management list and device management table in the database of the cloud processing platform, classify the reagent cards, label each classified reagent card, record the device affiliation of the reagent card, add the SampleID of the reagent card test sample to the reagent card management list, and form a SampleID list by counting the SampleIDs corresponding to the device test samples, and use the corresponding device ID as the foreign key of the SampleID list; Analyzing the comprehensive operating pressure includes the following steps: The data storage saturation coefficient of the edge node is calculated using the following formula: , Among them, SSI is the data storage saturation coefficient, Ct is the currently occupied storage space, C is the total storage capacity of the node, St is the hourly increment of node data, and α and β are the corresponding weights; The operating saturation coefficient of the edge node is calculated using the following formula: , Where OSI is the ‌operation saturation coefficient, CPUt / CPU is the current CPU occupancy, Ct / C is the current memory occupancy, N is the maximum concurrent task capacity, Nt is the number of tasks in the pending task queue, and γ is the queue pressure weight; The number of occurrences of different types of abnormal events in different detection time periods is counted, and the operational abnormality coefficient of the edge node is calculated using the following formula: , Among them, OAI is the operational anomaly coefficient, Eti is the number of occurrences of the i-th abnormal event within the detection period, Ebasei is the benchmark frequency of similar abnormal events, which is set to the historical mean of similar abnormal events, t0 is the length of the detection period, Wi is the event severity weight, and μ is the time decay factor; For the immunoassay analyzers in the high-frequency and sub-high-frequency usage groups, the comprehensive operating pressure is analyzed using the following formula based on the edge node data storage saturation coefficient, operation saturation coefficient, and operation abnormality coefficient: , Among them, Health1 is the comprehensive operating stress analysis value of the immunoassay analyzers in the high-frequency usage group and the sub-high-frequency usage group, SSI is the data storage saturation coefficient, OSI is the operation saturation coefficient, OAI is the operation abnormality coefficient, σ is the node health correction factor, σ=1-(Fhardware / Fmax), Fhardware is the current hardware aging score, and Fmax is the initial value of the node hardware aging score; For the immunoassay analyzers in the medium frequency group, the comprehensive operating pressure is analyzed using the following formula: , Among them, Health2 is the comprehensive operating pressure analysis value of the immunoassay analyzer in the medium frequency use group; For the immunoassay analyzers in the low-frequency use group, the comprehensive operating pressure is analyzed using the following formula: , Among them, Health3 is the comprehensive operating pressure analysis value of the immunoassay analyzer in the low-frequency usage group.

2. A data management method for a multi-target biohazard factor immunoassay analyzer according to claim 1, characterized in that: Classify the reagent cards, including: According to the reaction mechanism of the reagent card, it can be classified into: enzyme-linked immunosorbent assay reagent card, fluorescent immunoassay reagent card and chemiluminescent immunoassay reagent card; A reagent card management list is set for each category of reagent cards, and the target type of the corresponding reagent card is marked in the reagent card management list, including: bacterial target, viral target, toxin target and parasite target.

3. The data management method for a multi-target biohazard factor immunoassay analyzer according to claim 1, characterized in that: Record the device ID, device type, device location, and usage frequency in the device management table. Group the immunoassay analyzers into high-frequency usage group, sub-high-frequency usage group, medium-frequency usage group, and low-frequency usage group according to the different threshold ranges of the device usage frequency, including the following steps: Record the device ID, device type, device location, and usage frequency in the device management table, set a detection time period, and count the device usage frequency during the detection time period; Obtain the device's usage frequency data for several past detection time periods, calculate the average value to obtain the average frequency data, and perform a weighted average of the average frequency data and the device's usage frequency data for the most recent detection time period to obtain the usage frequency data used for device grouping; Collect historical device usage frequency data and rank them, taking the top 20%, top 40%, and top 60% of the usage frequency data nodes as the corresponding usage frequency thresholds; According to the usage frequencies of the obtained devices being within different threshold ranges, the immunoassay analyzers are grouped into a high-frequency usage group, a sub-high-frequency usage group, a medium-frequency usage group, and a low-frequency usage group, and the groups are updated regularly.

4. The data management method for a multi-target biohazard factor immunoassay analyzer according to claim 1, characterized in that: Detecting the data storage saturation coefficient, operation saturation coefficient, and operation abnormality coefficient of the edge node of each immune analyzer group includes the following steps: For the immunoassay analyzers in the high-frequency usage group and the sub-high-frequency usage group, the memory usage data, CPU usage data, and operation abnormality data of the immunoassay analyzers were tested in each testing time period. For the immunoassay analyzers in the medium-frequency usage group, the memory usage data, CPU usage data, and operation abnormality data of the immunoassay analyzers were tested at intervals of several test time periods. For the immunoassay analyzers in the low-frequency use group, the trigger condition is to receive three or more error messages during the detection period to detect the memory usage data, CPU usage data, and operation abnormality data of the immunoassay analyzers; The edge node data storage saturation coefficient, operation saturation coefficient and operation abnormality coefficient are calculated respectively based on the memory usage data, CPU usage data and operation abnormality data.

5. The data management method for a multi-target biohazard factor immunoassay analyzer according to claim 1, characterized in that: Based on the comprehensive operational pressure analysis results, data storage and computing tasks are allocated to edge nodes, including the following steps: Obtain historical operating data of the immune analyzer at the edge node, calculate the comprehensive operating pressure analysis value of the immune analyzer, obtain the corresponding comprehensive operating pressure analysis value from the data where the edge node data delay increases significantly and the response time prolongs, and take the average as the first threshold; count the comprehensive operating pressure analysis values ​​of the immune analyzer at the edge end where the edge node data delay time is less than 50ms, and take the average as the second threshold; According to the results of the comprehensive operation pressure analysis, if the comprehensive operation pressure analysis value is greater than the first threshold, the nearest node will be selected from the nodes whose comprehensive operation pressure analysis value is less than the second threshold, 10% of the historical storage data will be transferred to the selected node, and the last 10% of the tasks in the pending task queue will be transferred to the cloud processing platform until the comprehensive operation pressure analysis value of the corresponding node is no greater than the first threshold.

6. The data management method for a multi-target biohazard factor immunoassay analyzer according to claim 1, characterized in that: The cloud processing platform performs real-time analysis of the test configuration parameters, experimental signal data, and quality control data of different types of reagent cards during experiments, and performs reliability analysis on the experimental data, including the following steps: The cloud processing platform obtains reagent cards of different categories, detection configuration parameters for different target types, experimental signal data, and historical data of normal detection of quality control data, as well as historical data when detection failures occur, and adds normal detection and failure detection labels to the historical data; Establish a multimodal deep confidence assessment model, and use data from target type detection of bacterial targets, viral targets, toxin targets, and parasite targets using different classifications of reagent cards to train the corresponding model; The cloud processing platform obtains the detection configuration parameters, experimental signal data and quality control data of different categories of reagent cards in real time; Through the trained model, the reliability analysis of the experimental data is performed to identify the data when the corresponding target type is detected by the corresponding classified reagent card, which is normal detection data or fault detection data. If fault detection data occurs, the data during the experiment is unreliable and is fault detection data. Otherwise, the data during the experiment is reliable.

7. The data management method for a multi-target biohazard factor immunoassay analyzer according to claim 6, characterized in that: Building a multimodal deep confidence assessment model includes the following steps: Construct a multimodal deep belief network and set up a static parameter branch, a dynamic signal branch, and a quality control data branch in the input layer; The static parameter branch is used to input detection configuration parameters and is set as a fully connected layer. The dynamic signal branch is used to input experimental signal data and is set as an LSTM network layer. The LSTM network layer processes the time series signals of the experimental signal data, and the sliding window length is set to 30 sampling periods. The quality control data branch is used to input quality control data and is set as a time series convolution layer. By constructing a time series convolution network, the cumulative effect of quality control deviations is captured, and the convolution kernel width matches the calibration period. The fusion layer sets up a cross-modal attention mechanism to perform weighted fusion of the features of each branch; The output layer uses the Sigmoid activation function to output data that is the classification of normal detection and fault detection.

Images