Microorganism detection method

Abstract

The invention relates to a microbiological detection method, and relates to the field of microbiological detection, and the method comprises the following steps: obtaining historical microbiological detection records of a target scene, and extracting historical water quality data and historical microbiological detection data; performing clustering division on the historical water quality data, performing equivalent division on the historical microbiological detection data according to a clustering division result, obtaining a plurality of sample data groups, and storing the sample data groups as a sample detection database; according to the sample detection database, a multi-working-condition detection mapping model is constructed and trained, and the multi-working-condition detection mapping model is associated and marked with a working condition interval; and collecting water quality data of the target scene in real time, inputting the water quality data to the multi-working-condition detection mapping model, and obtaining a microbiological detection result.

Description

Technical Field

[0001] The present invention relates to the field of microbial detection, and in particular to a microbial detection method. Background Art

[0002] Microbial detection is crucial in water quality safety monitoring, especially in drinking water, industrial water and other scenarios. Accurate detection of microbial content and distribution in water can effectively ensure water safety. Existing microbial detection methods mostly rely on manual sampling and laboratory analysis. Sample collection and preservation costs are high, detection takes a long time, and is prone to operational errors. There are technical problems such as poor detection timeliness and high detection costs. Summary of the invention

[0003] The present invention provides a microorganism detection method to solve the technical problems of poor detection timeliness and high detection cost in the prior art.

[0004] The technical solution of the present invention to solve the above technical problems is as follows:

[0005] Obtain historical microbial detection records of target scenarios, and extract historical water quality data and historical microbial detection data.

[0006] The historical water quality data is clustered and divided, and according to the clustering result, the historical microbial detection data is equally divided to obtain multiple sample data groups, which are stored as a sample detection database.

[0007] Based on the sample detection database, a multi-operating condition detection mapping model is constructed and trained, wherein the multi-operating condition detection mapping model is associated with operating condition intervals.

[0008] The water quality data of the target scene is collected in real time, and the water quality data is input into the multi-condition detection mapping model to obtain the microbial detection result.

[0009] The beneficial effects of the present invention are: by acquiring the historical microbial detection records of the target scene, the corresponding historical water quality data and microbial detection data are extracted. The historical water quality data is clustered and divided, and the historical microbial detection data is similarly divided according to the clustering results to form multiple sample data groups, and these sample data groups are stored in the sample detection database. Using the sample detection database, a multi-condition detection mapping model is constructed and trained; the water quality data of the target scene is collected in real time, and the water quality data is input into the multi-condition detection mapping model to obtain the corresponding microbial detection results. Thereby achieving the technical effect of improving the timeliness and continuity of detection and reducing the detection cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of a process for detecting microorganisms provided by the present invention;

[0011] Figure 2 A schematic diagram of the structure of an electronic device provided by the present invention;

[0012] Figure 3 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0013] In the accompanying drawings, the components represented by the reference numerals are described as follows:

[0014] Electronic device 500 , memory 510 , processor 520 , first computer program 511 , computer-readable storage medium 600 , second computer program 611 . DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0016] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0017] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0018] Embodiment 1:

[0019] like Figure 1 As shown, an embodiment of the present invention provides a method for detecting microorganisms.

[0020] Obtain historical microbial detection records of target scenarios, and extract historical water quality data and historical microbial detection data;

[0021] Specifically, first identify the scenario that needs to be analyzed, such as a specific water source, supply area, treatment facility, or discharge area, and retrieve historical test records related to the target scenario from the database or archive system, including multiple microbial test results and corresponding water quality test data.

[0022] Specifically, historical water quality data is a collection of water quality-related index values, which is used to provide information on the physical and chemical properties of water bodies in target scenarios at different times. For example, water quality-related indicators include pH value, turbidity, dissolved oxygen, temperature, BOD, COD, TN, TP, heavy metal content, etc.

[0023] Specifically, historical microbial detection data are data related to microorganisms and composition, including microbial species such as bacteria, viruses, algae and their concentrations, which are used to characterize changes in microbial communities in target scenarios.

[0024] By obtaining historical water quality data and microbial data, detailed background information and reliable data support can be provided for establishing a mapping relationship between water quality and microbial distribution in the target scenario.

[0025] In some embodiments, obtaining historical microbial detection records of a target scene and extracting historical water quality data and historical microbial detection data include:

[0026] Based on predetermined target collection points, the historical microbial detection records are obtained; according to a preset set of key water quality indicators, the historical microbial detection records are cleaned to obtain the historical water quality data and the historical microbial detection data.

[0027] Specifically, first, determine the target collection points of the target scene, such as water sources, discharge points, treatment facility outlets, user terminals, etc. Then, collect the microbial detection records corresponding to the target collection points as the above-mentioned historical microbial detection records.

[0028] Specifically, the preset key water quality indicators include multiple water quality indicators that have a high correlation with the types and quantity distribution of microorganisms, such as pH value, dissolved oxygen, ammonia nitrogen, chemical oxygen demand (COD), turbidity, total organic carbon (TOC), heavy metal ion concentration (such as lead, copper, etc.), temperature, etc.

[0029] Specifically, through the key water quality indicator set, the historical microbial detection records are cleaned, including retaining the data corresponding to the water quality indicator items in the historical microbial detection records that appear in the key water quality indicator set, and eliminating the data of the water quality indicator items in the non-key water quality indicator set, thereby improving the data quality of the acquired historical microbial detection records, and helping to reduce the interference of non-highly correlated data. The cleaned data is stored as the above-mentioned historical water quality data set, and the historical microbial detection data with the corresponding timestamp is retained for analyzing the relationship between water quality and microbial composition.

[0030] Clustering the historical water quality data, and equally dividing the historical microbial detection data according to the clustering results, obtaining multiple sample data groups, and storing them as a sample detection database;

[0031] Specifically, historical water quality data are clustered to identify different water quality status groups, thereby achieving a refined division of water quality status, which in turn helps to improve the recognition and mapping accuracy of the mapping relationship between water quality data and microbial detection data under different water quality conditions.

[0032] Specifically, a clustering algorithm based on unsupervised learning, such as K-means, hierarchical clustering or DBSCAN, is used, with key water quality indicators (such as pH value, dissolved oxygen, turbidity, chemical oxygen demand, heavy metal content, etc.) as clustering feature inputs to perform clustering of the historical water quality data, thereby ensuring that the clustering results can fully reflect the different states of water quality.

[0033] Furthermore, the clustering results of historical water quality data are mapped to the corresponding historical microbial detection data, that is, the microbial data are divided into the same group as the water quality data according to the correspondence between the time series or the collection points, so as to ensure the consistency of the microbial detection data and the water quality data. The divided microbial detection data and the corresponding water quality data are combined into a sample data group, and each sample data group represents the microbial status under specific water quality conditions.

[0034] Furthermore, according to data management requirements, the sample data group is stored as a structured database to facilitate subsequent calls and analysis. The sample detection database includes clustering labels, water quality parameters, microbial species and concentrations, etc., providing high-quality reference data for subsequent analysis.

[0035] In some embodiments, clustering the historical water quality data includes:

[0036] Based on the data dimensions of the historical water quality data, a multidimensional data space is constructed, and the historical water quality data is mapped to the multidimensional data space; in the multidimensional data space, according to the discreteness of the historical water quality data, the k value of clustering is determined by calculating the intra-cluster sum of squares under different k values ​​and combining the elbow method; the historical water quality data is clustered according to the k value to obtain k clusters, and the clustering division results are output.

[0037] Specifically, based on the key indicators in the historical water quality data, data dimensions are defined, each key indicator represents a dimension, and a corresponding multidimensional data space is established, so that each record of the historical water quality data set can be regarded as a data point in the multidimensional space. Then, all records of the historical water quality data are mapped to the above-mentioned multidimensional data space to form a set of data point distributions in the multidimensional data space.

[0038] Specifically, different k values ​​(i.e., the number of clusters) are selected, and cluster division is performed for different k values ​​to obtain the clustering results corresponding to each k value; then, the sum of squares of each data point and the cluster center point in each cluster is calculated to obtain the intra-cluster sum of squares under each k value; then, a curve graph of multiple intra-cluster sums of squares versus multiple k values ​​is drawn. As the k value increases, the intra-cluster sum of squares gradually decreases. When the k value reaches a certain critical point, the decrease in WCSS becomes smaller, and an "elbow" position appears in the curve graph. The k value at this position is considered to be the optimal value for clustering.

[0039] Furthermore, based on the determined optimal k value, k-means clustering is performed on the historical water quality data in the multidimensional data space. Exemplarily, k initial center points are first randomly selected, and then each data point is assigned to the nearest center point to form a cluster, and the center point of each cluster is recalculated, and it is iterated repeatedly until the allocation of each data point no longer changes or the set convergence condition is reached, and k clusters are output, each cluster representing a data group with similar water quality characteristics, including corresponding data points and water quality indicators.

[0040] The above steps, by constructing a multidimensional data space and determining the optimal k value, reasonably clustered the historical water quality data, providing a basis and data support for further analysis of the relationship between water quality characteristics and microorganisms.

[0041] In some embodiments, the historical microbial detection data is equally divided according to the clustering results to obtain multiple sample data groups, including:

[0042] Based on the mapping relationship between the historical water quality data and the historical microbial detection data, the historical microbial detection data is extracted according to the k clusters and stored in the k clusters; based on the k clusters, multiple water quality parameter spaces are established and output as k operating condition intervals; the k operating condition intervals are associated with the k clusters to form the sample detection database.

[0043] Specifically, first, based on the k clusters of the above clustering results, combined with the mapping relationship between historical water quality data and historical microbial detection data, the historical microbial detection data corresponding to the water quality data in each cluster is extracted and stored in the corresponding cluster. Then, for each cluster, a water quality parameter space is established. The water quality parameter space is constructed based on the maximum values ​​of the water quality parameters of all data in the cluster, and is used to quantitatively characterize the water quality conditions covered by each cluster. The k parameter spaces are output as k operating condition intervals. Finally, the k operating condition intervals are associated with the k clusters to form a sample detection database, which contains all sample data and the operating condition intervals and clusters corresponding to these data, thereby facilitating subsequent data analysis and processing for multiple operating conditions.

[0044] According to the sample detection database, a multi-operating condition detection mapping model is constructed and trained, wherein the multi-operating condition detection mapping model is associated with a marking of an operating condition interval;

[0045] Specifically, a multi-condition detection mapping model is constructed and trained based on the sample detection database. The multi-condition detection mapping model is used to call corresponding condition detection channels / sub-models according to the condition interval of the unknown sample to perform microbial detection on the unknown sample.

[0046] Optionally, the multi-condition detection mapping model includes an input layer, a distributor, multiple parallel-connected condition detection mapping sub-models and an output layer. Among them, the multiple parallel-connected condition detection mapping sub-models can be decision trees, random forests, support vector machines, neural networks, etc.; the choice of which algorithm mainly depends on the complexity of the problem, the characteristics of the data, and the required prediction accuracy; the input layer is the first layer of the model, responsible for receiving input data. The distributor is the second layer of the model, which is used to distribute data to the corresponding condition detection mapping sub-model according to the condition interval of the input data; each sub-model in the multiple parallel-connected condition detection mapping sub-models corresponds to a condition interval. When the distributor distributes data to a sub-model, the sub-model will start microbial detection; the output layer is the last layer of the model, which is used to collect the detection results of all sub-models and integrate these results into a complete output. Optionally, the output is a microbial detection report, which contains information such as the number and type of various microorganisms.

[0047] Specifically, a multi-condition detection mapping model is constructed and trained. First, multiple sample data groups are extracted from the sample detection database as multiple groups of training and test data; then, a suitable machine learning algorithm is selected for each condition detection mapping sub-model, such as decision tree, random forest, support vector machine, neural network, etc. Preferably, different condition detection mapping sub-models are models of different types and sizes, so as to use a variety of detection conditions; then, multiple condition detection mapping sub-models are trained through multiple sample data groups respectively. During the training process, the condition detection mapping sub-model learns the mapping mode between water quality data and microbial data in the training data to obtain microbial detection capabilities; finally, the test data generated by multiple sample data groups is used to evaluate the performance of multiple condition detection mapping sub-models, which is achieved by calculating indicators such as the prediction accuracy, recall rate, and F1 score of the model.

[0048] Through the above steps, the corresponding working condition detection mapping sub-model is constructed for the working condition interval, which can effectively improve the efficiency and accuracy of microbial detection, and at the same time improve the flexibility of the application of multi-working condition detection mapping model.

[0049] The water quality data of the target scene is collected in real time, and the water quality data is input into the multi-condition detection mapping model to obtain the microbial detection result.

[0050] Specifically, water quality data is collected in real time in the target scene, and the collected data is preprocessed, including data cleaning, missing value processing, data standardization, etc. Then, the preprocessed data is input into the multi-condition detection mapping model. The multi-condition detection mapping model assigns the data to the corresponding condition detection mapping sub-model for microbial detection according to the condition interval of the input data, and predicts the type and quantity of microorganisms. Through the above process, real-time microbial detection can be achieved, and the efficiency and accuracy of microorganisms can be improved.

[0051] Furthermore, the method further comprises:

[0052] Access the historical microbial detection records and extract neighborhood sample data groups of the plurality of sample data groups; perform neighborhood direction analysis and neighborhood difference association based on the sample data group and the neighborhood sample data group to obtain a migration sample data group, wherein the migration sample data group includes associated upstream water quality data, downstream water quality data and upstream microbial detection data; construct and train a runoff migration model based on the migration sample data group, wherein the runoff migration model uses the upstream water quality data and the upstream microbial detection data as input.

[0053] Specifically, first, historical microbial detection records are accessed to find neighboring sample data groups of multiple sample data groups, where the neighboring sample data groups refer to data spatially adjacent to the target sample data group, such as data from a collection point downstream of a collection point of the target sample data group.

[0054] Specifically, based on the sample data group and the neighborhood sample data group, neighborhood direction analysis and neighborhood difference association are performed to determine the chronological relationship between the neighborhood data group and the sample data group, and the differences between the neighborhood sample data and the sample data group and the association between these differences and the microbial detection data are obtained to obtain the migration sample data group. The migration sample data group includes associated upstream water quality data, downstream water quality data and upstream microbial detection data, reflecting the impact of microbial detection data on water quality changes. In other words, different microbial detection data reflect different impact environments of microbial ecology on water quality.

[0055] Specifically, based on the above migration sample data set, a runoff migration model is constructed and trained. The runoff migration model is used to predict downstream water quality data with upstream water quality data and upstream microbial detection data as input, so as to better understand and predict changes in water quality and microorganisms, thereby improving the accuracy of detection.

[0056] In some embodiments, accessing the historical microorganism detection records and extracting neighboring sample data groups of the plurality of sample data groups further comprises:

[0057] Extract the first sampling points corresponding to the plurality of sample data groups; obtain the nearest downstream sampling point of the first sampling point as a neighborhood sampling point according to the runoff information of the target scene; access the historical microbial detection records, use the neighborhood sampling point as a first extraction constraint, use the data timestamps of the plurality of sample data groups as a second extraction constraint, and obtain neighborhood sample data groups of the plurality of sample data groups.

[0058] Specifically, first, access the historical microbial detection records and extract the first sampling point corresponding to the multiple sample data groups, where the first sampling point is the water body sampling point corresponding to the multiple sample data groups; then, according to the runoff information of the target scene, obtain the nearest downstream sampling point of the first sampling point as the neighborhood sampling point; wherein the runoff information includes the direction of the water flow and the distribution of the sampling points.

[0059] Specifically, historical microbial detection records are accessed, neighborhood sampling points are used as the first extraction constraint, and data timestamps of multiple sample data groups are used as the second extraction constraint to obtain neighborhood sample data groups of multiple sample data groups, thereby ensuring that the neighborhood sample data groups are spatially adjacent to the sample data groups and temporally consistent.

[0060] The above steps utilize historical microbial detection records and runoff information to effectively extract neighborhood sample data sets, providing accurate structured data for subsequent data analysis and model training.

[0061] In some embodiments, constructing and training a runoff migration model, then comprising:

[0062] When collecting the water quality data in real time, the neighborhood water quality data of the neighborhood sampling point is collected synchronously; the water quality data and the microbial detection result are input into the runoff migration model to obtain the verification water quality data of the neighborhood sampling point; the verification water quality data is compared with the neighborhood water quality data to obtain water quality difference data, and if the water quality difference data is less than a preset water quality deviation constraint, the microbial detection result is output.

[0063] Specifically, when collecting water quality data in real time, the neighborhood water quality data of the neighborhood sampling points are collected synchronously; then, the collected water quality data and the microbial detection results corresponding to the water quality data are input into the runoff migration model to obtain the verification water quality data of the neighborhood sampling points. The verification water quality data is the ideal water quality data of the neighborhood sampling points corresponding to the microbial detection results predicted by the model, which is used to compare with the actually collected neighborhood water quality data to determine the accuracy of the microbial detection results.

[0064] Furthermore, the predicted verification water quality data is compared with the actually collected neighborhood water quality data to obtain water quality difference data. If the water quality difference data is less than the preset water quality deviation constraint, the microbial detection result is output. In other words, when the difference between the water quality data predicted by the model and the actual data is within an acceptable range, the microbial detection result can be considered accurate and the microbial detection result is output. Through the above verification steps, the accuracy of the output microbial detection result is effectively ensured.

[0065] A microbial detection method provided by an embodiment of the present invention has at least the following technical effects:

[0066] By obtaining the historical microbial detection records of the target scene, the corresponding historical water quality data and microbial detection data are extracted. The historical water quality data is clustered and divided, and the historical microbial detection data is similarly divided according to the clustering results to form multiple sample data groups, and these sample data groups are stored in the sample detection database. Using the sample detection database, a multi-condition detection mapping model is constructed and trained; the water quality data of the target scene is collected in real time, and the water quality data is input into the multi-condition detection mapping model to obtain the corresponding microbial detection results. This achieves the technical effect of improving the timeliness and continuity of detection and reducing detection costs.

[0067] Embodiment 2:

[0068] See also Figure 2 , Figure 2 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 2 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a first computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the first computer program 511, the following steps are implemented: obtaining historical microbial detection records of the target scene, extracting historical water quality data and historical microbial detection data; clustering the historical water quality data, and based on the clustering results, equally dividing the historical microbial detection data, obtaining multiple sample data groups, and storing them as a sample detection database; constructing and training a multi-condition detection mapping model based on the sample detection database, wherein the multi-condition detection mapping model is associated with a condition interval; collecting water quality data of the target scene in real time, inputting the water quality data into the multi-condition detection mapping model, and obtaining microbial detection results.

[0069] Embodiment three:

[0070] See also Figure 3 , Figure 3 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 3 As shown, this embodiment provides a computer-readable storage medium 600, on which a second computer program 611 is stored. When the second computer program 611 is executed by the processor, the following steps are implemented: obtaining historical microbial detection records of the target scene, extracting historical water quality data and historical microbial detection data; clustering the historical water quality data, and based on the clustering results, equally dividing the historical microbial detection data, obtaining multiple sample data groups, and storing them as a sample detection database; based on the sample detection database, constructing and training a multi-condition detection mapping model, wherein the multi-condition detection mapping model is associated with a condition interval; collecting water quality data of the target scene in real time, inputting the water quality data into the multi-condition detection mapping model, and obtaining microbial detection results.

[0071] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0072] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0073] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0074] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0075] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0076] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0077] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A method for detecting microorganisms, characterized in that: The method comprises: Obtain historical microbial detection records of target scenarios, and extract historical water quality data and historical microbial detection data; Clustering the historical water quality data, and equally dividing the historical microbial detection data according to the clustering results, obtaining multiple sample data groups, and storing them as a sample detection database; According to the sample detection database, a multi-operating condition detection mapping model is constructed and trained, wherein the multi-operating condition detection mapping model is associated with a marking of an operating condition interval; The water quality data of the target scene is collected in real time, and the water quality data is input into the multi-condition detection mapping model to obtain the microbial detection result.

2. A microbial detection method according to claim 1, characterized in that: Obtain historical microbial detection records of the target scene, extract historical water quality data and historical microbial detection data, including: Based on predetermined target collection points, obtaining the historical microbial detection records; According to a preset set of key water quality indicators, the historical microbial detection records are cleaned to obtain the historical water quality data and the historical microbial detection data.

3. A microbial detection method according to claim 2, characterized in that: The historical water quality data is clustered and divided, including: Based on the data dimensions of the historical water quality data, construct a multidimensional data space, and map the historical water quality data to the multidimensional data space; In the multidimensional data space, according to the discreteness of the historical water quality data, the k value of clustering is determined by calculating the intra-cluster sum of squares under different k values ​​and combining the elbow method; The historical water quality data is clustered according to the k value to obtain k clusters, and the clustering results are output.

4. A microbial detection method according to claim 3, characterized in that: According to the clustering results, the historical microbial detection data is equally divided to obtain multiple sample data groups, including: Based on the mapping relationship between the historical water quality data and the historical microbial detection data, according to the k clusters, the historical microbial detection data is correspondingly extracted and stored in the k clusters; Based on the k clusters, multiple water quality parameter spaces are established and output as k operating condition intervals; The k operating condition intervals are associated with the k clusters to form the sample detection database.

5. A microbial detection method according to claim 1, characterized in that: The method further comprises: Accessing the historical microorganism detection records, and extracting neighboring sample data groups of a plurality of the sample data groups; Based on the sample data group and the neighborhood sample data group, neighborhood direction analysis and neighborhood difference association are performed to obtain a migration sample data group, wherein the migration sample data group includes associated upstream water quality data, downstream water quality data and upstream microbial detection data; A runoff migration model is constructed and trained based on the migration sample data set, wherein the runoff migration model takes the upstream water quality data and the upstream microorganism detection data as input.

6. A microbial detection method according to claim 5, characterized in that: Accessing the historical microorganism detection records and extracting neighboring sample data groups of the plurality of sample data groups also includes: Extracting first sampling points corresponding to a plurality of the sample data groups; According to the runoff information of the target scene, the nearest downstream sampling point of the first sampling point is obtained as a neighborhood sampling point; The historical microorganism detection records are accessed, the neighborhood sampling points are used as the first extraction constraint, the data timestamps of the plurality of sample data groups are used as the second extraction constraint, and the neighborhood sample data groups of the plurality of sample data groups are obtained.

7. A microorganism detection method according to claim 6, characterized in that: Build and train the runoff migration model, then: When collecting the water quality data in real time, the neighborhood water quality data of the neighborhood sampling points are collected synchronously; Inputting the water quality data and the microbial detection results into the runoff migration model to obtain the verified water quality data of the neighborhood sampling points; The verification water quality data is compared with the neighborhood water quality data to obtain water quality difference data. If the water quality difference data is less than a preset water quality deviation constraint, the microbial detection result is output.

8. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing a microorganism detection method as described in any one of claims 1-7.

9. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the microorganism detection method according to any one of claims 1 to 7 is implemented.

Images