A fault analysis method and system for nucleic acid detector

Abstract

This application provides a fault analysis method and system for nucleic acid testing instruments. Based on the fault triggering data of acquired candidate fault log data under multiple fault linkage evaluation indicators, the system determines the representational feature vector of the candidate fault log data under multiple fault linkage evaluation indicators. This determines the fault linkage confidence value between each candidate fault log data, and based on the fault linkage confidence value between each candidate fault log data, the system determines the target fault linkage feature of each candidate fault log data. Thus, based on multiple fault linkage evaluation indicators, the system more comprehensively determines the fault linkage confidence value between candidate fault log data, making the evaluation of the fault linkage confidence value between candidate fault log data more reasonable and improving the calculation accuracy of the fault linkage feature. This, in turn, improves the accuracy of subsequent fault service nodes in retrieving relevant fault linkage features.

Description

Technical Field

[0001] The present application relates to the field of operation and maintenance technology of nucleic acid detection systems, and specifically, to a fault analysis method and system applied to nucleic acid detection instruments. Background Art

[0002] The nucleic acid detector searches for the presence of nucleic acid of foreign invading viruses in human respiratory specimens, blood or feces to determine whether the patient is infected with the new coronavirus. Therefore, once the nucleic acid test is positive, it can be proved that the virus exists in the patient's body. Therefore, in the laboratory, the equipment operation stability of the nucleic acid detector is crucial to the test results. In the related art, when a nucleic acid detector fails, the inventor of the present application found that there is often a linkage correlation between the various fault log data generated by it, while the related art only analyzes a single fault log data, lacks the evaluation of the fault linkage characteristics, resulting in the relevant reference data provided to the subsequent fault service node cannot meet the actual needs. Summary of the invention

[0003] In view of this, the purpose of the present application is to provide a fault analysis method and system for nucleic acid detection instruments.

[0004] According to the first aspect of the present application, a fault analysis method for a nucleic acid detector is provided, which is applied to a cloud server platform, and the method comprises:

[0005] Obtaining fault triggering data of each candidate fault log data of the target nucleic acid detector under multiple fault linkage evaluation indicators;

[0006] Determine, based on the fault triggering data of the candidate fault log data under the multiple fault linkage evaluation indicators, a characterizing feature vector of the candidate fault log data under the multiple fault linkage evaluation indicators;

[0007] Based on the characterization feature vectors of the candidate fault log data under the multiple fault linkage evaluation indicators, obtaining the fault linkage confidence value between each of the candidate fault log data;

[0008] Based on the fault linkage confidence values ​​between the candidate fault log data, target fault linkage features of the candidate fault log data are determined, and the target fault linkage features are uploaded to the fault service node.

[0009] In a possible implementation of the first aspect, obtaining fault trigger data of each candidate fault log data of the target nucleic acid detector under multiple fault linkage evaluation indicators includes:

[0010] Collect candidate fault log data of the target nucleic acid detector within a specified nucleic acid detection cycle and nucleic acid collaborative feature data of the nucleic acid collaborative service for the candidate fault log data;

[0011] Based on the candidate fault log data within the specified nucleic acid detection period and the nucleic acid collaborative feature data of the nucleic acid collaborative service for the candidate fault log data, obtaining the fault trigger data of the candidate fault log data under multiple fault linkage evaluation indicators within the specified nucleic acid detection period;

[0012] The fault linkage evaluation index includes a first fault linkage evaluation index, a second fault linkage evaluation index and a third fault linkage evaluation index;

[0013] The acquisition of the fault triggering data of the candidate fault log data under multiple fault linkage evaluation indicators within the specified nucleic acid detection cycle based on the candidate fault log data within the specified nucleic acid detection cycle and the nucleic acid collaborative feature data of the nucleic acid collaborative service for the candidate fault log data includes:

[0014] Based on the nucleic acid collaborative feature data of the candidate fault log data for the nucleic acid collaborative service, determining a nucleic acid collaborative tag between the nucleic acid collaborative service and the candidate fault log data within a specified nucleic acid detection cycle as fault trigger data of the candidate fault log data under the first fault linkage evaluation indicator;

[0015] parsing significant fault activities from the candidate fault log data;

[0016] Obtaining the participation characterization data of the significant fault activity in the candidate fault log data within the specified nucleic acid detection cycle, and identifying the participation characterization data as the fault triggering data of the candidate fault log data under the second fault linkage evaluation indicator;

[0017] Based on the nucleic acid collaborative label between the nucleic acid collaborative service and the candidate fault log data within the specified nucleic acid detection cycle, and the participation characterization data of the significant fault activity in the candidate fault log data, the relationship between the nucleic acid collaborative service and the participation characterization data of the significant fault activity in the candidate fault log data is confirmed as the fault trigger data of the candidate fault log data under the third fault linkage evaluation indicator.

[0018] In a possible implementation manner of the first aspect, determining, based on the fault triggering data of the candidate fault log data under the multiple fault linkage evaluation indicators, a characterizing feature vector of the candidate fault log data under the multiple fault linkage evaluation indicators includes:

[0019] Based on the fault triggering data of the candidate fault log data under the multiple fault linkage evaluation indicators, generating a feature vector space of the candidate fault log data under the multiple fault linkage evaluation indicators;

[0020] Splitting the feature vector space to obtain the representation feature vectors of the candidate fault log data under the multiple fault linkage evaluation indicators;

[0021] Based on the fault triggering data of the candidate fault log data under multiple fault linkage evaluation indicators, generating a feature vector space of the candidate fault log data under the multiple fault linkage evaluation indicators, including:

[0022] Based on the fault trigger data of the candidate fault log data under multiple fault linkage evaluation indicators, a first feature vector space, a second feature vector space and a third feature vector space are generated respectively; the first feature vector space is used to represent the nucleic acid collaborative service representation vector and the nucleic acid collaborative label between the representation feature vectors, the second feature vector space is used to represent the nucleic acid collaborative label between the representation feature vector and the significant fault representation vector, and the third feature vector space is used to represent the nucleic acid collaborative service representation vector and the nucleic acid collaborative label between the significant fault representation vector;

[0023] Identify the first feature vector space, the second feature vector space, and the third feature vector space as feature vector spaces of the candidate fault log data under the multiple fault linkage evaluation indicators respectively;

[0024] If the feature vector space is the first feature vector space or the second feature vector space, splitting the feature vector space to obtain the characterizing feature vectors of the candidate fault log data under the multiple fault linkage evaluation indicators includes:

[0025] Splitting the feature vector space to obtain a characterizing feature vector as a characterizing feature vector of the candidate fault log data under a corresponding fault linkage evaluation index;

[0026] If the feature vector space is the third feature vector space, splitting the feature vector space to obtain the characterizing feature vectors of the candidate fault log data under the multiple fault linkage evaluation indicators includes:

[0027] Splitting the feature vector space to obtain significant fault characterization vectors in the candidate fault log data;

[0028] Acquire participation characterization data of the significant fault activity in the candidate fault log data as participation characterization data corresponding to the significant fault characterization vector;

[0029] Based on the significant fault characterization vector and the corresponding participating characterization data, a characterization feature vector is obtained as the characterization feature vector of the candidate fault log data under the corresponding fault linkage evaluation index.

[0030] In a possible implementation manner of the first aspect, obtaining the fault linkage confidence value between each of the candidate fault log data based on the characterization feature vectors of the candidate fault log data under the multiple fault linkage evaluation indicators includes:

[0031] Based on the characterization feature vectors of the candidate fault log data under multiple fault linkage evaluation indicators, calculating the evaluation values ​​of every two candidate fault log data under multiple fault linkage evaluation indicators;

[0032] Based on the evaluation values ​​of each two candidate fault log data under multiple fault linkage evaluation indicators, obtaining the fault linkage confidence value between each of the candidate fault log data;

[0033] The obtaining of the fault linkage confidence value between each of the candidate fault log data based on the evaluation values ​​of each two candidate fault log data under multiple fault linkage evaluation indicators includes:

[0034] Inputting evaluation values ​​of each two candidate fault log data under multiple fault linkage evaluation indicators into a factorization machine network that meets the model convergence condition;

[0035] Based on the factorization machine network, determining factorization values ​​between the evaluation values;

[0036] Obtaining the participating characterization data of each of the evaluation values ​​and the participating characterization data of each of the factor decomposition values;

[0037] Determine a fault linkage confidence value between each of the candidate fault log data based on each of the evaluation values ​​and the corresponding participating characterization data, each of the factor decomposition values ​​and the corresponding participating characterization data;

[0038] The configuration steps of the factorization machine network include:

[0039] Obtaining evaluation values ​​of the training fault log data under multiple fault linkage evaluation indicators and the corresponding first participating characterization data, factor decomposition values ​​between each of the evaluation values ​​and the corresponding second participating characterization data, and true fault linkage confidence values ​​between each of the training fault log data;

[0040] Based on the evaluation values ​​of the training fault log data under multiple fault linkage evaluation indicators and the corresponding first participating characterization data, the factor decomposition values ​​between the evaluation values ​​and the corresponding second participating characterization data, the factor decomposition machine network is updated with network weight parameters to obtain the factor decomposition machine network with updated network weight parameters;

[0041] Obtaining a loss function value between a fault linkage confidence value generated by the factorization machine network with updated network weight parameters and a corresponding true fault linkage confidence value;

[0042] When the loss function value is not less than a threshold loss function value, the first participating characterization data and the second participating characterization data are updated based on the loss function value, and the factor decomposition machine network is traversed and cyclically updated based on the updated first participating characterization data and the second participating characterization data until the loss function value generated by the factor decomposition machine network updated based on the network weight parameters is less than the threshold loss function value.

[0043] In a possible implementation manner of the first aspect, determining a target fault linkage feature of each of the candidate fault log data based on a fault linkage confidence value between each of the candidate fault log data includes:

[0044] Based on the fault linkage confidence value between each of the candidate fault log data, the candidate fault log data whose fault linkage confidence value between each of the candidate fault log data is greater than the first target fault linkage confidence value and less than the second target fault linkage confidence value is used as the target fault linkage feature of each of the candidate fault log data.

[0045] In a possible implementation manner of the first aspect, after determining the target fault linkage feature of each of the candidate fault log data, the method includes:

[0046] Obtaining log tag attributes of the candidate fault log data;

[0047] The target fault linkage feature of the candidate fault log data is uploaded to a fault linkage knowledge base corresponding to the log tag attribute, and the fault linkage knowledge base is loaded into a fault service node.

[0048] In a possible implementation of the first aspect, the method further includes:

[0049] Receiving a fault linkage loading instruction sent by a fault data retrieving node; the fault linkage loading instruction carries a log tag attribute;

[0050] Parsing target fault linkage features from a fault linkage knowledge base corresponding to the log tag attribute;

[0051] The target fault linkage feature is sent to the fault data retrieving node.

[0052] According to the second aspect of the present application, a cloud server platform is provided, wherein the nucleic acid detector includes a machine-readable storage medium and a processor, wherein the machine-readable storage medium stores machine-executable instructions, and when the processor executes the machine-executable instructions, the cloud server platform implements the aforementioned fault analysis method applied to the nucleic acid detector.

[0053] According to the third aspect of the present application, a computer-readable storage medium is provided, in which computer-executable instructions are stored. When the computer-executable instructions are executed, the aforementioned fault analysis method applied to the nucleic acid detection instrument is implemented.

[0054] According to any of the above aspects, in the present application, based on the acquired fault trigger data of the candidate fault log data under multiple fault linkage evaluation indicators, the characterization feature vector of the candidate fault log data under multiple fault linkage evaluation indicators is determined, thereby determining the fault linkage confidence value between each candidate fault log data, and based on the fault linkage confidence value between each candidate fault log data, determining the target fault linkage feature of each candidate fault log data, thereby more perfectly determining the fault linkage confidence value between the candidate fault log data based on multiple fault linkage evaluation indicators, making the evaluation of the fault linkage confidence value between the candidate fault log data more reasonable, improving the calculation accuracy of the fault linkage feature, and thereby facilitating improving the accuracy of subsequent fault service nodes in retrieving relevant fault linkage features. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0056] Figure 1 A schematic diagram of a process flow of a fault analysis method applied to a nucleic acid detector provided in an embodiment of the present application;

[0057] Figure 2 A schematic diagram of the component structure of a cloud server platform provided in an embodiment of the present application for implementing the above-mentioned fault analysis method applied to a nucleic acid detector is shown. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below based on the drawings in the embodiments of the present application. It should be understood that the drawings in the present application are only for the purpose of illustration and description, and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowcharts used in this application illustrate the operations implemented in some embodiments of the embodiments of the present application. It should be understood that the operations of the flowchart may not be implemented in sequence, and steps without logical contextual relationships may be reversed in order or implemented simultaneously. In addition, under the guidance of the VR running behavior of the present application, those skilled in the art may add one or more other operations to the flowchart, or may destroy one or more operations from the flowchart.

[0059] Figure 1 The flowchart of the fault analysis method applied to the nucleic acid detector provided by the embodiment of the present application is shown. It should be understood that in other embodiments, the order of some steps in the fault analysis method applied to the nucleic acid detector of this embodiment can be shared with each other according to actual needs, or some steps can be omitted or maintained. The details of the fault analysis method applied to the nucleic acid detector include:

[0060] Step S102, obtaining the fault triggering data of each candidate fault log data of the target nucleic acid detector under multiple fault linkage evaluation indicators.

[0061] Among them, candidate fault log data refers to the fault log data of the target nucleic acid detector that requires evaluation of the fault linkage confidence value.

[0062] Among them, the fault linkage evaluation index can represent the evaluation dimension of the fault linkage confidence value between each candidate fault log data.

[0063] Step S104: determining a characterizing feature vector of the candidate fault log data under multiple fault linkage evaluation indicators based on the fault triggering data of the candidate fault log data under multiple fault linkage evaluation indicators.

[0064] The characterization feature vector refers to a vector obtained by encoding the fault log data, for example, a real-valued vector of a specified dimension.

[0065] Exemplarily, based on the fault triggering data of the candidate fault log data under multiple fault linkage evaluation indicators, the feature vector space of the candidate fault log data under multiple fault linkage evaluation indicators can be obtained; the feature vector space is split to obtain the characterizing feature vectors of the candidate fault log data under each fault linkage evaluation indicator.

[0066] Step S106, obtaining a fault linkage confidence value between each candidate fault log data based on the characterization feature vectors of the candidate fault log data under multiple fault linkage evaluation indicators.

[0067] The fault linkage confidence value is used to describe the possibility of fault linkage between candidate fault log data; for example, the higher the fault linkage confidence value between candidate fault log data, the higher the possibility of fault linkage between candidate fault log data.

[0068] Exemplarily, based on the characterizing feature vectors of the candidate fault log data under multiple fault linkage evaluation indicators, the evaluation values ​​of every two candidate fault log data under multiple fault linkage evaluation indicators can be determined; based on the evaluation values ​​of every two candidate fault log data under multiple fault linkage evaluation indicators, the fault linkage confidence value between every two candidate fault log data can be determined, thereby obtaining the fault linkage confidence value between each candidate fault log data.

[0069] Step S108: determining target fault linkage features of each candidate fault log data based on the fault linkage confidence values ​​between each candidate fault log data, and uploading the target fault linkage features to a fault service node.

[0070] The target fault linkage feature refers to fault data that may be linked to each candidate fault log data; for example, fault data whose fault linkage confidence value with each candidate fault log data is greater than 0.8.

[0071] Exemplarily, based on the fault linkage confidence value between each candidate fault log data, fault data whose fault linkage confidence value between each candidate fault log data is greater than the first target fault linkage confidence value and less than the second target fault linkage confidence value can be determined as the target fault linkage feature of each candidate fault log data.

[0072] In some exemplary design ideas, after determining the target fault linkage characteristics of each candidate fault log data, the cloud server platform can also receive the fault linkage loading instruction of the fault data retrieval node, and the fault linkage loading instruction carries the log tag attribute; parse the fault linkage loading instruction to obtain the log tag attribute; determine the candidate fault log data corresponding to the log tag attribute, and determine the target fault linkage characteristic corresponding to the candidate fault log data from the target fault linkage characteristics of each candidate fault log data; and upload the target fault linkage characteristic to the fault data retrieval node.

[0073] Based on the above steps, based on the acquired fault trigger data of the candidate fault log data under multiple fault linkage evaluation indicators, the characterization feature vector of the candidate fault log data under multiple fault linkage evaluation indicators is determined, thereby determining the fault linkage confidence value between each candidate fault log data, and based on the fault linkage confidence value between each candidate fault log data, determining the target fault linkage feature of each candidate fault log data, thereby more perfectly determining the fault linkage confidence value between the candidate fault log data based on multiple fault linkage evaluation indicators, making the evaluation of the fault linkage confidence value between the candidate fault log data more reasonable, improving the calculation accuracy of the fault linkage feature, and further facilitating improving the accuracy of subsequent fault service nodes in retrieving relevant fault linkage features.

[0074] In some exemplary design ideas, obtaining the fault triggering data of each candidate fault log data of the target nucleic acid detector under multiple fault linkage evaluation indicators in step S102 can be achieved by the following scheme:

[0075] Step S202, collecting candidate fault log data of the target nucleic acid detector within a specified nucleic acid detection cycle and nucleic acid collaborative feature data of the nucleic acid collaborative service for the candidate fault log data.

[0076] Step S204, based on the candidate fault log data within the specified nucleic acid detection cycle and the nucleic acid collaborative feature data of the nucleic acid collaborative service for the candidate fault log data, obtain the fault trigger data of the candidate fault log data under multiple fault linkage evaluation indicators within the specified nucleic acid detection cycle.

[0077] Exemplarily, multiple fault linkage evaluation indicators can be obtained, and based on the fault linkage evaluation indicators, statistical analysis is performed on the candidate fault log data within the specified nucleic acid detection cycle and the data of the nucleic acid collaborative service on the candidate fault log data to obtain the fault triggering data of the candidate fault log data under each fault linkage evaluation indicator within the specified nucleic acid detection cycle.

[0078] Based on the above steps, by analyzing the candidate fault log data within the specified nucleic acid detection cycle and the data of the nucleic acid collaborative service for the candidate fault log data, the fault trigger data of the candidate fault log data under each fault linkage evaluation indicator within the specified nucleic acid detection cycle is obtained; the purpose of obtaining the fault trigger data of the candidate fault log data under multiple fault linkage evaluation indicators within the specified nucleic acid detection cycle is achieved, which facilitates the subsequent analysis of the fault linkage confidence value between the candidate fault log data from multiple fault linkage evaluation indicators, thereby improving the calculation accuracy of the fault linkage feature.

[0079] In some exemplary design ideas, if the fault linkage evaluation index includes a first fault linkage evaluation index, a second fault linkage evaluation index and a third fault linkage evaluation index; then, in step S204, based on the candidate fault log data in the specified nucleic acid detection cycle and the data of the nucleic acid collaborative service for the candidate fault log data, the fault triggering data of the candidate fault log data under each fault linkage evaluation index in the specified nucleic acid detection cycle is obtained, which can be implemented by the following scheme:

[0080] Step S302, based on the data of the nucleic acid collaborative service for the candidate fault log data, determine the nucleic acid collaborative label between the nucleic acid collaborative service and the candidate fault log data within the specified nucleic acid detection cycle as the fault trigger data of the candidate fault log data under the first fault linkage evaluation indicator.

[0081] Step S304: parsing significant fault activities from the candidate fault log data.

[0082] Exemplarily, candidate fault log data within a specified nucleic acid detection cycle can be identified based on the attention mechanism, and attention information of the candidate fault log data can be obtained, and the attention information can be used as significant fault activities of the candidate fault log data.

[0083] Step S306, obtaining the participating characterization data of significant fault activities in the candidate fault log data within the specified nucleic acid detection cycle, and identifying the participating characterization data as the fault triggering data of the candidate fault log data under the second fault linkage evaluation indicator.

[0084] Step S308, based on the nucleic acid collaborative label between the nucleic acid collaborative service and the candidate fault log data within the specified nucleic acid detection cycle, and the participation characterization data of significant fault activities in the candidate fault log data, confirm the relationship between the nucleic acid collaborative service and the participation characterization data of significant fault activities in the candidate fault log data as the fault trigger data of the candidate fault log data under the third fault linkage evaluation indicator.

[0085] Exemplarily, the nucleic acid collaborative tags between the nucleic acid collaborative service and the candidate fault log data within a specified nucleic acid detection cycle, as well as the participation characterization data of significant fault activities in the candidate fault log data can be analyzed to determine whether the nucleic acid collaborative service reads the candidate fault log data containing significant fault activities, thereby obtaining the relationship between the nucleic acid collaborative service and the participation characterization data of significant fault activities in the candidate fault log data; the relationship between the nucleic acid collaborative service and the participation characterization data of significant fault activities in the candidate fault log data is mapped into corresponding coordinates, and the coordinates are used as the fault trigger data of the candidate fault log data under the third fault linkage evaluation indicator within the specified nucleic acid detection cycle.

[0086] In this embodiment, by analyzing the candidate fault log data within the specified nucleic acid detection cycle and the data of the nucleic acid collaborative service for the candidate fault log data, the fault triggering data of the candidate fault log data under each fault linkage evaluation indicator within the specified nucleic acid detection cycle can be obtained; this is conducive to the subsequent analysis of the fault linkage confidence value between the candidate fault log data from multiple fault linkage evaluation indicators, thereby improving the calculation accuracy of the fault linkage feature.

[0087] In some exemplary design ideas, determining the characterization feature vector of the candidate fault log data under multiple fault linkage evaluation indicators based on the fault triggering data of the candidate fault log data under multiple fault linkage evaluation indicators in step S104 can be implemented by the following scheme:

[0088] Step S402 : generating a feature vector space of the candidate fault log data under multiple fault linkage evaluation indicators based on the fault triggering data of the candidate fault log data under multiple fault linkage evaluation indicators.

[0089] Step S404: split the feature vector space to obtain the representative feature vectors of the candidate fault log data under multiple fault linkage evaluation indicators.

[0090] In this embodiment, by analyzing the fault trigger data of the candidate fault log data under multiple fault linkage evaluation indicators, a characterizing feature vector of the candidate fault log data under multiple fault linkage evaluation indicators can be obtained, which facilitates the subsequent acquisition of the fault linkage confidence value between each candidate fault log data based on the characterizing feature vector.

[0091] In some exemplary design ideas, in step S402, based on the fault triggering data of the candidate fault log data under multiple fault linkage evaluation indicators, generating the feature vector space of the candidate fault log data under multiple fault linkage evaluation indicators can be implemented by the following scheme:

[0092] Step S502, based on the fault trigger data of the candidate fault log data under multiple fault linkage evaluation indicators, generate a first feature vector space, a second feature vector space, and a third feature vector space; the first feature vector space is used to represent the nucleic acid collaborative service representation vector and the nucleic acid collaborative label between the representation feature vectors, the second feature vector space is used to represent the nucleic acid collaborative label between the representation feature vector and the significant fault representation vector, and the third feature vector space is used to represent the nucleic acid collaborative service representation vector and the nucleic acid collaborative label between the significant fault representation vector.

[0093] Exemplarily, a first feature vector space can be generated based on the fault trigger data of the candidate fault log data under the first fault linkage evaluation index; a second feature vector space can be generated based on the fault trigger data of the candidate fault log data under the second fault linkage evaluation index; and a third feature vector space can be generated based on the fault trigger data of the candidate fault log data under the third fault linkage evaluation index.

[0094] Step S504: identifying the first feature vector space, the second feature vector space, and the third feature vector space as feature vector spaces of the candidate fault log data under multiple fault linkage evaluation indicators, respectively.

[0095] In this embodiment, based on the fault trigger data of the candidate fault log data under multiple fault linkage evaluation indicators, a feature vector space of the candidate fault log data under multiple fault linkage evaluation indicators is generated, which is conducive to the subsequent splitting of the feature vector space and obtaining the characterization feature vectors of the candidate fault log data under multiple fault linkage evaluation indicators.

[0096] In some exemplary design ideas, if the feature vector space is the first feature vector space or the second feature vector space, then in step S404, the feature vector space is split to obtain the characterization feature vector of the candidate fault log data under multiple fault linkage evaluation indicators, including: splitting the feature vector space to obtain the characterization feature vector as the characterization feature vector of the candidate fault log data under the corresponding fault linkage evaluation indicator.

[0097] For example, the first feature vector space can be split to obtain the nucleic acid collaborative service representation vector and the representation feature vector, and the representation feature vector is used as the representation feature vector of the candidate fault log data under the first fault linkage evaluation index; the second feature vector space can be split to obtain the representation feature vector and the significant fault representation vector, and the representation feature vector is used as the representation feature vector of the candidate fault log data under the second fault linkage evaluation index. In this way, the purpose of obtaining the representation feature vector of the candidate fault log data under the first fault linkage evaluation index and the second fault linkage evaluation index is achieved.

[0098] If the feature vector space is the third feature vector space, then the feature vector space is split in step S404 to obtain the representative feature vectors of the candidate fault log data under multiple fault linkage evaluation indicators, which can be achieved by the following scheme:

[0099] Step S602: split the feature vector space to obtain significant fault characterization vectors in the candidate fault log data.

[0100] Exemplarily, the third feature vector space may be split to obtain nucleic acid collaborative service characterization vectors and significant fault characterization vectors in the candidate fault log data.

[0101] Step S604: obtaining participation characterization data of significant fault activities in the candidate fault log data as participation characterization data corresponding to the significant fault characterization vector.

[0102] Step S606: Based on the significant fault characterization vector and the corresponding participating characterization data, a characterization feature vector is obtained as a characterization feature vector of the candidate fault log data under the corresponding fault linkage evaluation index.

[0103] In some exemplary design ideas, obtaining the fault linkage confidence value between each candidate fault log data based on the characterization feature vector of the candidate fault log data under multiple fault linkage evaluation indicators in step S106 can be implemented by the following scheme:

[0104] Step S702: Calculate evaluation values ​​of every two candidate fault log data under multiple fault linkage evaluation indicators based on the characterization feature vectors of the candidate fault log data under multiple fault linkage evaluation indicators.

[0105] Step S704: obtaining a fault linkage confidence value between each candidate fault log data based on evaluation values ​​of each pair of candidate fault log data under multiple fault linkage evaluation indicators.

[0106] In some exemplary design ideas, in step S704, based on the evaluation values ​​of each two candidate fault log data under multiple fault linkage evaluation indicators, obtaining the fault linkage confidence value between each candidate fault log data can be implemented by the following scheme:

[0107] Step S802 : calculating factor decomposition values ​​between respective evaluation values ​​based on evaluation values ​​of each pair of candidate fault log data under a plurality of fault linkage evaluation indicators.

[0108] The factor decomposition value refers to the cross term of two evaluation values. For example, the factor decomposition value of evaluation value a and evaluation value b is a×b.

[0109] Step S804: obtaining the participating characterization data of each evaluation value and the participating characterization data of each factor decomposition value.

[0110] Among them, the data involved in representing each evaluation value and the data involved in representing each factor decomposition value are generated based on prior sample data training.

[0111] Step S806: determining the fault linkage confidence value between each candidate fault log data based on each evaluation value and the corresponding participating characterization data, each factor decomposition value and the corresponding participating characterization data.

[0112] In step S704, based on the evaluation values ​​of each two candidate fault log data under multiple fault linkage evaluation indicators, the fault linkage confidence value between each candidate fault log data is obtained, which can be achieved by the following scheme:

[0113] Step S902 : inputting the evaluation values ​​of every two candidate fault log data under multiple fault linkage evaluation indicators into a factorization machine network that meets the model convergence condition.

[0114] Step S904, confirm the factor decomposition values ​​between each evaluation value through the factor decomposition machine network; obtain the participating characterization data of each evaluation value and the participating characterization data of each factor decomposition value; based on each evaluation value and the corresponding participating characterization data, each factor decomposition value and the corresponding participating characterization data, determine the fault linkage confidence value between each candidate fault log data.

[0115] The end server platform inputs the evaluation values ​​of each two candidate fault log data under each fault linkage evaluation index into a factor decomposition machine network that meets the model convergence conditions, and calculates the fault linkage confidence value between each candidate fault log data through the factor decomposition machine network, fully considering the factor decomposition value of the evaluation value, thereby improving the calculation accuracy of the fault linkage confidence value between the candidate fault log data.

[0116] In some exemplary design ideas, the factorization machine network is trained through the following steps:

[0117] Step S1002, obtaining evaluation values ​​of the training fault log data under multiple fault linkage evaluation indicators and the corresponding first participating characterization data, factor decomposition values ​​between each evaluation value and the corresponding second participating characterization data, and true fault linkage confidence values ​​between each training fault log data.

[0118] Among them, the fault log data for training refers to the fault log data collected in the past.

[0119] Step S1004, based on the evaluation values ​​of the training fault log data under multiple fault linkage evaluation indicators and the corresponding first participating characterization data, the factor decomposition values ​​between the evaluation values ​​and the corresponding second participating characterization data, the network weight parameters of the factor decomposition machine network are updated to obtain the factor decomposition machine network with updated network weight parameters.

[0120] Exemplarily, the network weight parameters of the factor decomposition machine network can be updated through the evaluation values ​​of different training fault log data under multiple fault linkage evaluation indicators and the corresponding first participating characterization data, the factor decomposition values ​​between each evaluation value and the corresponding second participating characterization data.

[0121] Step S1006, obtaining a loss function value between a fault linkage confidence value generated by the factorization machine network with updated network weight parameters and a corresponding true fault linkage confidence value.

[0122] Step S1008, when the loss function value is not less than the threshold loss function value, the first participating characterization data and the second participating characterization data are updated based on the loss function value, and the factor decomposition machine network is traversed and updated based on the updated first participating characterization data and the second participating characterization data until the loss function value generated by the factor decomposition machine network updated based on the network weight parameters is less than the threshold loss function value.

[0123] For example, on the basis that the loss function value is not less than the threshold loss function value, the cloud server platform continuously updates the first participating characterization data and the second participating characterization data in the factor decomposition machine network to traverse and loop update the factor decomposition machine network until the loss function value generated by the factor decomposition machine network based on the updated network weight parameters is less than the threshold loss function value, and the current factor decomposition machine network is used as the factor decomposition machine network with updated network weight parameters.

[0124] The cloud server platform can improve the accuracy of the fault linkage confidence value between the fault log data predicted and generated by the factorization machine network by traversing and cyclically updating the factorization machine network, thereby improving the calculation accuracy of the fault linkage confidence value between the fault log data.

[0125] In some exemplary design ideas, in step S108, the target fault linkage features of each candidate fault log data are determined based on the fault linkage confidence value between each candidate fault log data, specifically including: based on the fault linkage confidence value between each candidate fault log data, the candidate fault log data whose fault linkage confidence value between each candidate fault log data is greater than the first target fault linkage confidence value and less than the second target fault linkage confidence value is used as the target fault linkage feature of each candidate fault log data.

[0126] For example, based on the fault linkage confidence value between other fault log data and fault log data 1, fault log data whose fault linkage confidence value with fault log data 1 is greater than 0.65 and less than 0.85 are determined, and these fault log data are used as the target fault linkage features of fault log data 1.

[0127] Therefore, the purpose of determining the target fault linkage feature of each candidate fault log data based on the fault linkage confidence value between each candidate fault log data is achieved, thereby improving the calculation accuracy of the fault linkage feature.

[0128] In some exemplary design ideas, after determining the target fault linkage features of each candidate fault log data in step S108, a step of storing the target fault linkage features of the candidate fault log data is also included, which can be implemented by the following scheme:

[0129] Step S1102: obtaining log tag attributes of candidate fault log data.

[0130] The log tag attribute refers to ID information used to identify candidate fault log data.

[0131] Step S1104 , uploading the target fault linkage feature of the candidate fault log data to the fault linkage knowledge base corresponding to the log tag attribute.

[0132] Among them, the fault linkage knowledge base is a file that stores the target fault linkage features of the candidate fault log data, and has a one-to-one correspondence with the log tag attributes of the candidate fault log data. For example, fault linkage knowledge base 1 stores the target fault linkage features of candidate fault log data 1, fault linkage knowledge base 2 stores the target fault linkage features of candidate fault log data 2, and fault linkage knowledge base 3 stores the target fault linkage features of candidate fault log data 3.

[0133] Taking candidate fault log data as fault log data as an example, the cloud server platform uploads the first N fault log data that have fault linkage with a single fault log data to a fault linkage knowledge base corresponding to the fault log data identifier of the fault log data.

[0134] Step S1106: Load the fault linkage knowledge base into the fault service node.

[0135] In some exemplary design ideas, the above method may further include the following steps, which may be implemented by the following schemes:

[0136] Step S1202, receiving a fault linkage loading instruction sent by a fault data retrieving node; the fault linkage loading instruction carries a log tag attribute.

[0137] Step S1204: parse the target fault linkage feature from the fault linkage knowledge base corresponding to the log tag attribute.

[0138] The fault linkage knowledge base corresponding to the log tag attribute stores target fault linkage features of the fault log data corresponding to the log tag attribute.

[0139] Exemplarily, based on the correspondence between the log tag attribute and the fault linkage knowledge base, the fault linkage knowledge base corresponding to the log tag attribute can be found, and the target fault linkage feature of the fault log data corresponding to the log tag attribute can be parsed from the fault linkage knowledge base.

[0140] Furthermore, in addition to parsing the target fault linkage features of the fault log data corresponding to the log tag attributes from the pre-stored fault linkage knowledge base, the cloud server platform can also recall the target fault linkage features of the fault log data corresponding to the log tag attributes in real time.

[0141] For example, the cloud server platform obtains the fault triggering data of the candidate fault log data on the network under multiple fault linkage evaluation indicators in real time; determines the characterization feature vector of the candidate fault log data under multiple fault linkage evaluation indicators based on the fault triggering data of the candidate fault log data under multiple fault linkage evaluation indicators; obtains the fault linkage confidence value between each candidate fault log data based on the fault linkage confidence value between each candidate fault log data; determines the target fault linkage feature of the fault log data corresponding to the log label attribute based on the fault linkage confidence value between each candidate fault log data; and recalls the target fault linkage feature of the fault log data corresponding to the log label attribute.

[0142] Step S1206: Send the target fault linkage feature to the fault data retrieval node.

[0143] In some exemplary design ideas, sending the target fault linkage feature to the fault data retrieval node in step S1206 can be implemented by the following scheme:

[0144] Step S1302: sort the target fault linkage features according to the fault linkage confidence values.

[0145] Step S1304: Send the sorted target fault linkage features to the fault data retrieval node based on the sending strategy.

[0146] Figure 2 The diagram schematically shows a cloud server platform 100 that can be used to implement the various embodiments described in the present application.

[0147] For one embodiment, Figure 2A cloud server platform 100 is shown, which has one or more processors 102, a control module (chip set) 104 coupled to one or more of the (one or more) processors 102, a memory 106 coupled to the control module 104, a non-volatile memory (NVM) / storage device 108 coupled to the control module 104, one or more input / output devices 110 coupled to the control module 104, and a network interface 112 coupled to the control module 104.

[0148] The processor 102 may include one or more single-core or multi-core processors, and the processor 102 may include any combination of general-purpose processors or special-purpose processors (such as graphics processors, application processors, baseband processors, etc.). In some exemplary design ideas, the cloud server platform 100 can be used as a cloud server platform device such as a gateway described in the embodiments of the present application.

[0149] In some exemplary design concepts, the cloud server platform 100 may include one or more computer-readable media (e.g., memory 106 or NVM / storage device 108) having instructions 114 and one or more processors 102 integrated with the one or more computer-readable media and configured to execute instructions 114 to implement a module to perform the actions described in the present disclosure.

[0150] For one embodiment, the control module 104 may include any suitable interface controller to provide any suitable interface to one or more of the processor(s) 102 and / or any suitable device or component in communication with the control module 104 .

[0151] The control module 104 may include a memory controller module to provide an interface to the memory 106. The memory controller module may be a hardware module, a software module, and / or a firmware module.

[0152] The memory 106 may be used, for example, to load and store data and / or instructions 114 for the cloud server platform 100. For one embodiment, the memory 106 may include any suitable volatile memory, such as a suitable DRAM. In some exemplary designs, the memory 106 may include a double data rate clustered tag four synchronous dynamic random access memory (DDR4 SDRAM).

[0153] For one embodiment, control module 104 may include one or more input / output controllers to provide interfaces to NVM / storage device 108 and input / output device(s) 110 .

[0154] For example, NVM / storage 108 may be used to store data and / or instructions 114. NVM / storage 108 may include any suitable non-volatile memory (e.g., flash memory) and / or may include any suitable non-volatile storage device(s) (e.g., one or more hard disk drives (HDDs), one or more compact disk (CD) drives, and / or one or more digital versatile disk (DVD) drives).

[0155] NVM / storage device 108 may include storage resources that are physically part of the device on which cloud server platform 100 is installed, or it may be accessible to the device without being part of the device. For example, NVM / storage device 108 may be accessed via (one or more) input / output devices 110 over a network.

[0156] (One or more) input / output devices 110 may provide an interface for the cloud server platform 100 to communicate with any other appropriate device, and the input / output device 110 may include a communication component, a phonetic component, a sensor component, etc. The network interface 112 may provide an interface for the cloud server platform 100 to communicate based on one or more networks, and the cloud server platform 100 may wirelessly communicate with one or more components of a wireless network based on any of one or more wireless network standards and / or protocols, such as accessing a wireless network based on a communication standard.

[0157] For one embodiment, one or more of the processor(s) 102 may be loaded together with the logic of one or more controllers (e.g., a memory controller module) of the control module 104. For one embodiment, one or more of the processor(s) 102 may be loaded together with the logic of one or more controllers of the control module 104 to form a system level load. For one embodiment, one or more of the processor(s) 102 may be integrated on the same die with the logic of one or more controllers of the control module 104. For one embodiment, one or more of the processor(s) 102 may be integrated on the same die with the logic of one or more controllers of the control module 104 to form a system on chip (SoC).

[0158] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A fault analysis method applied to a nucleic acid detector, characterized in that: Applied to a cloud server platform, the method includes: Obtaining fault triggering data of each candidate fault log data of the target nucleic acid detector under multiple fault linkage evaluation indicators; Determine, based on the fault triggering data of the candidate fault log data under the multiple fault linkage evaluation indicators, a characterizing feature vector of the candidate fault log data under the multiple fault linkage evaluation indicators; Based on the characterization feature vectors of the candidate fault log data under the multiple fault linkage evaluation indicators, obtaining the fault linkage confidence value between each of the candidate fault log data; Determine target fault linkage features of each candidate fault log data based on the fault linkage confidence value between each candidate fault log data, and upload the target fault linkage features to the fault service node; The method of obtaining the fault triggering data of each candidate fault log data of the target nucleic acid detector under multiple fault linkage evaluation indicators includes: Collect candidate fault log data of the target nucleic acid detector within a specified nucleic acid detection cycle and nucleic acid collaborative feature data of the nucleic acid collaborative service for the candidate fault log data; Based on the candidate fault log data within the specified nucleic acid detection period and the nucleic acid collaborative feature data of the nucleic acid collaborative service for the candidate fault log data, obtaining the fault trigger data of the candidate fault log data under multiple fault linkage evaluation indicators within the specified nucleic acid detection period; The fault linkage evaluation index includes a first fault linkage evaluation index, a second fault linkage evaluation index and a third fault linkage evaluation index; The acquisition of the fault triggering data of the candidate fault log data under multiple fault linkage evaluation indicators within the specified nucleic acid detection cycle based on the candidate fault log data within the specified nucleic acid detection cycle and the nucleic acid collaborative feature data of the nucleic acid collaborative service for the candidate fault log data includes: Based on the nucleic acid collaborative feature data of the candidate fault log data for the nucleic acid collaborative service, determining a nucleic acid collaborative tag between the nucleic acid collaborative service and the candidate fault log data within a specified nucleic acid detection cycle as fault trigger data of the candidate fault log data under the first fault linkage evaluation indicator; parsing significant fault activities from the candidate fault log data; Obtaining the participation characterization data of the significant fault activity in the candidate fault log data within the specified nucleic acid detection cycle, and identifying the participation characterization data as the fault triggering data of the candidate fault log data under the second fault linkage evaluation indicator; Based on the nucleic acid collaborative label between the nucleic acid collaborative service and the candidate fault log data within the specified nucleic acid detection cycle, and the participation characterization data of the significant fault activity in the candidate fault log data, the relationship between the nucleic acid collaborative service and the participation characterization data of the significant fault activity in the candidate fault log data is confirmed as the fault trigger data of the candidate fault log data under the third fault linkage evaluation indicator.

2. The fault analysis method for a nucleic acid detector according to claim 1, characterized in that: The determining, based on the fault triggering data of the candidate fault log data under the multiple fault linkage evaluation indicators, a characterizing feature vector of the candidate fault log data under the multiple fault linkage evaluation indicators comprises: Based on the fault triggering data of the candidate fault log data under the multiple fault linkage evaluation indicators, generating a feature vector space of the candidate fault log data under the multiple fault linkage evaluation indicators; Splitting the feature vector space to obtain the representation feature vectors of the candidate fault log data under the multiple fault linkage evaluation indicators; Based on the fault triggering data of the candidate fault log data under multiple fault linkage evaluation indicators, generating a feature vector space of the candidate fault log data under the multiple fault linkage evaluation indicators, including: Based on the fault trigger data of the candidate fault log data under multiple fault linkage evaluation indicators, a first feature vector space, a second feature vector space and a third feature vector space are generated respectively; the first feature vector space is used to represent the nucleic acid collaborative service representation vector and the nucleic acid collaborative label between the representation feature vectors, the second feature vector space is used to represent the nucleic acid collaborative label between the representation feature vector and the significant fault representation vector, and the third feature vector space is used to represent the nucleic acid collaborative service representation vector and the nucleic acid collaborative label between the significant fault representation vector; Identify the first feature vector space, the second feature vector space, and the third feature vector space as feature vector spaces of the candidate fault log data under the multiple fault linkage evaluation indicators respectively; If the feature vector space is the first feature vector space or the second feature vector space, splitting the feature vector space to obtain the characterizing feature vectors of the candidate fault log data under the multiple fault linkage evaluation indicators includes: Splitting the feature vector space to obtain a characterizing feature vector as a characterizing feature vector of the candidate fault log data under a corresponding fault linkage evaluation index; If the feature vector space is the third feature vector space, splitting the feature vector space to obtain the characterizing feature vectors of the candidate fault log data under the multiple fault linkage evaluation indicators includes: Splitting the feature vector space to obtain significant fault characterization vectors in the candidate fault log data; Acquire participation characterization data of the significant fault activity in the candidate fault log data as participation characterization data corresponding to the significant fault characterization vector; Based on the significant fault characterization vector and the corresponding participating characterization data, a characterization feature vector is obtained as the characterization feature vector of the candidate fault log data under the corresponding fault linkage evaluation index.

3. The fault analysis method for nucleic acid detector according to claim 1, characterized in that: The obtaining, based on the characterizing feature vectors of the candidate fault log data under the multiple fault linkage evaluation indicators, the fault linkage confidence values ​​between the candidate fault log data includes: Based on the characterization feature vectors of the candidate fault log data under multiple fault linkage evaluation indicators, calculating the evaluation values ​​of every two candidate fault log data under multiple fault linkage evaluation indicators; Based on the evaluation values ​​of each two candidate fault log data under multiple fault linkage evaluation indicators, obtaining the fault linkage confidence value between each of the candidate fault log data; The obtaining of the fault linkage confidence value between each of the candidate fault log data based on the evaluation values ​​of each two candidate fault log data under multiple fault linkage evaluation indicators includes: Inputting evaluation values ​​of each two candidate fault log data under multiple fault linkage evaluation indicators into a factorization machine network that meets the model convergence condition; Based on the factorization machine network, determining factorization values ​​between the evaluation values; Obtaining the participating characterization data of each of the evaluation values ​​and the participating characterization data of each of the factor decomposition values; Determine a fault linkage confidence value between each of the candidate fault log data based on each of the evaluation values ​​and the corresponding participating characterization data, each of the factor decomposition values ​​and the corresponding participating characterization data; The configuration steps of the factorization machine network include: Obtaining evaluation values ​​of the training fault log data under multiple fault linkage evaluation indicators and the corresponding first participating characterization data, factor decomposition values ​​between each of the evaluation values ​​and the corresponding second participating characterization data, and true fault linkage confidence values ​​between each of the training fault log data; Based on the evaluation values ​​of the training fault log data under multiple fault linkage evaluation indicators and the corresponding first participating characterization data, the factor decomposition values ​​between the evaluation values ​​and the corresponding second participating characterization data, the factor decomposition machine network is updated with network weight parameters to obtain the factor decomposition machine network with updated network weight parameters; Obtaining a loss function value between a fault linkage confidence value generated by the factorization machine network with updated network weight parameters and a corresponding true fault linkage confidence value; When the loss function value is not less than a threshold loss function value, the first participating characterization data and the second participating characterization data are updated based on the loss function value, and the factor decomposition machine network is traversed and cyclically updated based on the updated first participating characterization data and the second participating characterization data until the loss function value generated by the factor decomposition machine network updated based on the network weight parameters is less than the threshold loss function value.

4. The fault analysis method for a nucleic acid detector according to claim 1, characterized in that: The determining of target fault linkage features of each candidate fault log data based on the fault linkage confidence value between each candidate fault log data includes: Based on the fault linkage confidence value between each of the candidate fault log data, the candidate fault log data whose fault linkage confidence value between each of the candidate fault log data is greater than the first target fault linkage confidence value and less than the second target fault linkage confidence value is used as the target fault linkage feature of each of the candidate fault log data.

5. The fault analysis method for a nucleic acid detector according to any one of claims 1 to 4, characterized in that: After determining the target fault linkage features of each of the candidate fault log data, the following steps are included: Obtaining log tag attributes of the candidate fault log data; The target fault linkage feature of the candidate fault log data is uploaded to a fault linkage knowledge base corresponding to the log tag attribute, and the fault linkage knowledge base is loaded into a fault service node.

6. The fault analysis method for nucleic acid detector according to claim 5, characterized in that: The method further comprises: Receiving a fault linkage loading instruction sent by a fault data retrieving node; the fault linkage loading instruction carries a log tag attribute; Parsing target fault linkage features from a fault linkage knowledge base corresponding to the log tag attribute; The target fault linkage feature is sent to the fault data retrieving node.

7. A fault analysis system applied to a nucleic acid detector, characterized in that: The fault analysis system applied to the nucleic acid detector includes a cloud server platform and a nucleic acid detector connected to the cloud server platform for communication. The cloud server platform is specifically used for: Obtaining fault triggering data of each candidate fault log data of the target nucleic acid detector under multiple fault linkage evaluation indicators; Determine, based on the fault triggering data of the candidate fault log data under the multiple fault linkage evaluation indicators, a characterizing feature vector of the candidate fault log data under the multiple fault linkage evaluation indicators; Based on the characterization feature vectors of the candidate fault log data under the multiple fault linkage evaluation indicators, obtaining the fault linkage confidence value between each of the candidate fault log data; Determine target fault linkage features of each candidate fault log data based on the fault linkage confidence value between each candidate fault log data, and upload the target fault linkage features to the fault service node; The method of obtaining the fault triggering data of each candidate fault log data of the target nucleic acid detector under multiple fault linkage evaluation indicators includes: Collect candidate fault log data of the target nucleic acid detector within a specified nucleic acid detection cycle and nucleic acid collaborative feature data of the nucleic acid collaborative service for the candidate fault log data; Based on the candidate fault log data within the specified nucleic acid detection period and the nucleic acid collaborative feature data of the nucleic acid collaborative service for the candidate fault log data, obtaining the fault trigger data of the candidate fault log data under multiple fault linkage evaluation indicators within the specified nucleic acid detection period; The fault linkage evaluation index includes a first fault linkage evaluation index, a second fault linkage evaluation index and a third fault linkage evaluation index; The acquisition of the fault triggering data of the candidate fault log data under multiple fault linkage evaluation indicators within the specified nucleic acid detection cycle based on the candidate fault log data within the specified nucleic acid detection cycle and the nucleic acid collaborative feature data of the nucleic acid collaborative service for the candidate fault log data includes: Based on the nucleic acid collaborative feature data of the candidate fault log data for the nucleic acid collaborative service, determining a nucleic acid collaborative tag between the nucleic acid collaborative service and the candidate fault log data within a specified nucleic acid detection cycle as fault trigger data of the candidate fault log data under the first fault linkage evaluation indicator; parsing significant fault activities from the candidate fault log data; Obtaining the participation characterization data of the significant fault activity in the candidate fault log data within the specified nucleic acid detection cycle, and identifying the participation characterization data as the fault triggering data of the candidate fault log data under the second fault linkage evaluation indicator; Based on the nucleic acid collaborative label between the nucleic acid collaborative service and the candidate fault log data within the specified nucleic acid detection cycle, and the participation characterization data of the significant fault activity in the candidate fault log data, the relationship between the nucleic acid collaborative service and the participation characterization data of the significant fault activity in the candidate fault log data is confirmed as the fault trigger data of the candidate fault log data under the third fault linkage evaluation indicator.

8. A cloud server platform, characterized in that: The cloud server platform includes a processor and a computer-readable storage medium, wherein the computer-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by a computer, the fault analysis method applied to the nucleic acid detector described in any one of claims 1-6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores machine executable instructions, and when the machine executable instructions are executed by a computer, the fault analysis method applied to a nucleic acid detector as described in any one of claims 1-6 is implemented.

Images