Data processing method and system based on sewage monitoring of perfluorinated compounds

Abstract

The present invention relates to a data processing method and system based on sewage monitoring of perfluorinated compounds, and relates to the field of data processing, including: configuring multiple pollution influences according to multiple discharge times and multiple discharge distances, combining multiple training contributions, compensating and summarizing multiple predicted perfluorinated compound contents, and obtaining a predicted perfluorinated compound content interval; configuring a first detection number according to the predicted perfluorinated compound content interval, adjusting the first detection number according to floating parameters of multiple training contributions and multiple pollution influences, obtaining a second detection number to perform sewage detection, and obtaining the actual perfluorinated compound content. Through this application, the technical problem that traditional methods usually rely on fixed sampling detection schemes, which makes detection blind and random, and difficult to achieve efficient and accurate detection can be solved; the sewage detection strategy can be dynamically adjusted according to the prediction results, and the detection resource configuration can be optimized, thereby achieving the technical goal of efficient and accurate detection.

Description

Technical Field

[0001] The invention relates to the field of data processing, and in particular to a data processing method and system based on sewage monitoring of perfluorinated compounds. Background Art

[0002] Perfluorinated compounds are a class of highly stable and difficult-to-degrade chemical substances. Due to their high stability and persistence, they are widely present in the environment, especially in urban sewage.

[0003] At present, traditional methods for detecting perfluorinated compounds usually rely on fixed sampling detection schemes, and conduct detection according to preset time intervals, sampling points and sampling detection times. They lack specificity and flexibility, and do not take into account the dynamic changes in pollutant concentrations in sewage and the different impacts of different emission entities on pollution, making the detection blind and random, and difficult to achieve efficient and accurate perfluorinated compound detection. Summary of the invention

[0004] The present invention aims to solve the technical problem that traditional perfluorinated compound detection methods usually rely on fixed sampling detection schemes, which makes the detection blind and random, and difficult to achieve efficient and accurate detection. A data processing method and system based on sewage monitoring of perfluorinated compounds are provided to solve the problem.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] In a first aspect, the present invention provides a data processing method based on sewage monitoring of perfluorinated compounds, comprising: obtaining a sewage sample, and tracing back to obtain the discharge time, discharge distance and discharge subject characteristic information of multiple discharge entities related to the sewage sample according to the sewage discharge topological relationship, wherein each discharge subject characteristic information includes the discharge category and the discharge amount; predicting the perfluorinated compound content in the sewage sample according to the multiple discharge subject characteristic information, and obtaining multiple predicted perfluorinated compound contents, wherein the prediction is performed through a pre-trained perfluorinated content prediction path, and multiple discharge entities are configured with multiple training contribution degrees in the supervised training data of the perfluorinated content prediction path; configuring multiple pollution influence degrees for the multiple discharge entities according to multiple discharge times and multiple discharge distances, and compensating and summarizing the multiple predicted perfluorinated compound contents in combination with the multiple training contribution degrees to obtain a predicted perfluorinated compound content range; configuring a first detection number for sampling and detecting the perfluorinated compound content of the sewage sample according to the predicted perfluorinated compound content range, compensating and adjusting the first detection number according to the floating parameters of the multiple training contribution degrees and the multiple pollution influence degrees to obtain a second detection number, performing sewage detection, and obtaining the actual perfluorinated compound content.

[0007] In a second aspect, the present invention provides a data processing system based on sewage monitoring of perfluorinated compounds, including: an emission subject information acquisition module, used to obtain sewage samples, and trace the source to obtain the emission time, emission distance and emission subject characteristic information of multiple emission subjects related to the sewage samples according to the sewage emission topological relationship, wherein each emission subject characteristic information includes emission category and emission amount; a perfluorinated compound content prediction module, used to predict the perfluorinated compound content in the sewage sample according to the plurality of emission subject characteristic information, and obtain a plurality of predicted perfluorinated compound contents, wherein the prediction is performed through a pre-trained perfluorinated content prediction path, and the plurality of emission subjects are in the supervised training data of the perfluorinated content prediction path. It is configured with multiple training contribution degrees; a predicted perfluorinated compound content compensation module is used to configure multiple pollution influence degrees for the multiple emission entities according to multiple emission times and multiple emission distances, and compensate and summarize the multiple predicted perfluorinated compound contents in combination with the multiple training contribution degrees to obtain a predicted perfluorinated compound content range; a detection number compensation adjustment module is used to configure a first detection number for sampling and detecting the perfluorinated compound content of the sewage sample according to the predicted perfluorinated compound content range, and compensate and adjust the first detection number according to the floating parameters of the multiple training contribution degrees and multiple pollution influence degrees to obtain a second detection number, conduct sewage detection, and obtain the actual perfluorinated compound content.

[0008] In a third aspect, the present invention further provides an electronic device, comprising:

[0009] At least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so that the at least one processor can perform the steps of any one of the methods described in the first aspect above.

[0010] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed, the steps of the method described in any one of the first aspects are implemented.

[0011] The beneficial effects of the present invention are as follows: by obtaining sewage samples, and tracing back to obtain the discharge time, discharge distance and discharge subject characteristic information of multiple discharge subjects related to the sewage samples according to the sewage discharge topological relationship, wherein each discharge subject characteristic information includes the discharge category and the discharge amount; then, the perfluorinated compound content in the sewage sample is predicted according to the characteristic information of the multiple discharge subjects, and multiple predicted perfluorinated compound contents are obtained, wherein the prediction is performed through a pre-trained perfluorinated content prediction path, and multiple discharge subjects are configured with multiple training contribution degrees in the supervised training data of the perfluorinated content prediction path; then, according to multiple discharge times and multiple discharge distances, multiple pollution influence degrees are configured for the multiple discharge subjects, and the multiple pollution influence degrees are combined with the multiple training contribution degrees. Predicting the perfluorinated compound content, compensating and summarizing, and obtaining a predicted perfluorinated compound content range; further configuring a first number of detection times for sampling and detecting the perfluorinated compound content in the sewage sample according to the predicted perfluorinated compound content range, and compensating and adjusting the first number of detection times according to the floating parameters of the multiple training contribution degrees and the multiple pollution influence degrees to obtain a second number of detection times; finally, conducting sewage detection according to the second number of detection times to obtain the actual perfluorinated compound content; the above steps can improve the accuracy and reliability of perfluorinated compound content prediction, and then dynamically adjust the sewage detection strategy according to the prediction results, optimize the detection resource allocation, thereby achieving the technical goal of efficient and accurate detection, and significantly improving the efficiency, accuracy and reliability of perfluorinated compound detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic flow chart of a data processing method for monitoring perfluorinated compounds in wastewater provided by the present invention;

[0013] Figure 2 A logical schematic diagram of a data processing method for monitoring perfluorinated compounds in wastewater provided by the present invention;

[0014] Figure 3 A logical schematic diagram of tracing the source of emission entities in the data processing method for monitoring perfluorinated compounds in sewage provided by the present invention;

[0015] Figure 4 A schematic diagram of the structure of a data processing system based on monitoring perfluorinated compounds in sewage provided by the present invention;

[0016] Figure 5 A schematic diagram of the structure of an electronic device provided by the present invention;

[0017] Figure 6 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0018] In the accompanying drawings, the components represented by the reference numerals are described as follows:

[0019] Emission subject information acquisition module 01, perfluorinated compound content prediction module 02, predicted perfluorinated compound content compensation module 03, detection times compensation adjustment module 04, electronic device 500, memory 510, processor 520, first computer program 511, computer readable storage medium 600, second computer program 611. DETAILED DESCRIPTION

[0020] 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.

[0021] 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.

[0022] 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.

[0023] Embodiment 1, as Figure 1 and Figure 2 As shown, the embodiment of the present invention provides a data processing method based on wastewater monitoring of perfluorinated compounds, which specifically includes the following steps:

[0024] S100: Obtain a sewage sample, and trace the source to obtain the discharge time, discharge distance and discharge subject characteristic information of multiple discharge entities related to the sewage sample according to the sewage discharge topological relationship, wherein each discharge subject characteristic information includes the discharge category and discharge amount.

[0025] Further, if Figure 3 As shown, step S100 of the present invention further includes:

[0026] S110: Collect sewage samples within the sewage detection area; S120: Obtain the sewage discharge pipe network in the sewage detection area and construct a sewage discharge topological relationship; S130: According to the sewage discharge topological relationship, trace back to obtain multiple discharge entities related to the sewage sample; S140: Collect the discharge time, the distance from the discharge pipe of the sewage detection area, and the discharged sewage category and discharge amount of the multiple discharge entities, integrate multiple discharged sewage categories and multiple discharge amounts, and obtain multiple discharge entity characteristic information.

[0027] Specifically, first, sewage samples are collected in the sewage detection area (such as an urban sewage treatment pool). The sampling process needs to ensure the representativeness and coverage of the samples, that is, it can reflect the actual concentration level of perfluorinated compounds in the sewage in the area; then, the sewage discharge pipe network of the sewage detection area (such as an urban sewage treatment pool) is obtained, which can be obtained through urban infrastructure data; further, the sewage discharge topological relationship is constructed based on the sewage discharge pipe network, wherein the sewage discharge topological relationship includes detailed spatial distribution, connection relationship, flow direction and related discharge points of the sewage discharge pipes.

[0028] Then, based on the sewage discharge topological relationship, multiple discharge entities of the sewage samples are traced and analyzed. These discharge entities include but are not limited to residential areas, shopping malls, factories, etc. By tracing the source, it is possible to determine which discharge entities the sewage samples come from, which helps identify potential pollution sources. Further collect the discharge time of the multiple discharge entities, the discharge pipeline distance from the sewage detection area (that is, the pipeline distance between the sewage discharge entity and the sewage detection area), and the discharged sewage category (such as industrial wastewater, domestic sewage, etc.) and emission volume. Next, integrate multiple discharged sewage categories and multiple emission volumes, that is, for each discharge entity, match its sewage category with its emission volume to form complete discharge entity characteristic information, for example, discharge entity 1 (residential community), sewage category (domestic sewage), emission volume (500m 3 / d), obtain multiple emission subject characteristic information, wherein each emission subject characteristic information includes emission category and emission amount.

[0029] S200: Predicting the content of perfluorinated compounds in the sewage sample according to characteristic information of multiple emission entities respectively to obtain multiple predicted perfluorinated compound contents, wherein the prediction is performed through a pre-trained perfluorinated content prediction path, and multiple emission entities are configured with multiple training contribution degrees in the supervised training data of the perfluorinated content prediction path.

[0030] Furthermore, step S200 of the present invention further includes:

[0031] S210: training a perfluorinated content prediction path based on historical perfluorinated compound emission detection data of multiple sample emission entities, wherein multiple training contribution degrees are configured according to the number of supervised training data of sample emission entities similar to the multiple emission entities.

[0032] Furthermore, step S210 of the present invention further includes:

[0033] S211: Based on the historical perfluorinated compound emission detection data of multiple sample emission entities, multiple sample emission feature information sets are collected from multiple sample emission entities, and multiple sample perfluorinated compound content sets are collected; S212: Using the multiple sample emission feature information sets and multiple sample perfluorinated compound content sets as supervised training data, supervised training of the perfluorinated content prediction path is performed until the training converges.

[0034] Specifically, first, based on the historical perfluorinated compound emission detection data of multiple sample emission entities, multiple sample emission characteristic information (historical emission categories and historical emission amounts) of multiple sample emission entities are collected, and the sample perfluorinated compound content corresponding to different sample emission characteristic information is further obtained to obtain multiple sample perfluorinated compound content sets.

[0035] The BP neural network is a multi-layer feedforward neural network consisting of an input layer, a hidden layer, and an output layer. It uses a back-propagation algorithm to optimize the weights of the network. It continuously adjusts the network parameters by forward propagating the input data and back-propagating the error to update the weights, so that the prediction results of the network gradually approach the actual values. Then, a perfluorinated content prediction path is constructed based on the BP neural network. The perfluorinated content prediction path is used to predict the perfluorinated compound content in the corresponding sewage sample through the input emission subject characteristic information, including an input layer, multiple hidden layers, and an output layer, wherein the input data of the input layer is multiple emission characteristic information, and the output data of the output layer is multiple perfluorinated compound contents.

[0036] Further, multiple sample emission characteristic information is used as input, multiple sample perfluorinated compound content is used as output, and the multiple sample emission characteristic information sets and multiple sample perfluorinated compound content sets are used as supervised training data to supervise the perfluorinated content prediction path. First, the output of each layer is calculated by forward propagation until the predicted value of the output layer, that is, the predicted value of the perfluorinated compound content, is finally obtained; then the error between the predicted result and the actual target value is calculated using a loss function (such as mean square error); the error is further back-propagated through the network from the output layer to the input layer. The goal of the back-propagation process is to calculate the contribution of each parameter (weight and bias) to the loss function, thereby adjusting the parameters to reduce the error, and using the gradient descent algorithm to update the weights and biases in the network; multiple iterations of training are performed, and each iteration forward and backward propagates through all the training data to update the weight parameters. As the training progresses, the model will gradually learn the relationship between the input features and the perfluorinated compound content, and the value of the loss function will gradually decrease; until the predetermined convergence constraint is met (such as until the value of the loss function tends to be stable or reaches a preset training round), the trained perfluorinated content prediction path is obtained. By constructing a prediction system for perfluorinated compound content based on BP neural network, the intelligence and scientificity of the prediction of perfluorinated compound content can be improved, thereby improving the efficiency and accuracy of the prediction.

[0037] S213: configuring a plurality of training contribution degrees according to the number of supervised training data of sample emission entities similar to the plurality of emission entities.

[0038] Further, step S213 of the present invention further includes:

[0039] S2131: Obtain multiple sample emission subject characteristic information of the multiple sample emission subjects; S2132: Obtain the characteristic similarity between the multiple emission subject characteristic information and the multiple sample emission subject characteristic information, and respectively select the sample emission subjects corresponding to the largest multiple maximum characteristic similarities as multiple matching sample emission subjects; S2133: Obtain the proportion of sample data of the multiple matching sample emission subjects in all supervised training data, and obtain multiple sample data proportions; S2134: Multiply the multiple maximum characteristic similarities by the multiple sample data proportions to obtain multiple training contribution degrees.

[0040] Specifically, first, obtain multiple sample emission subject characteristic information (sample sewage discharge category and sample emission amount) of the multiple sample emission subjects; then, randomly select any one characteristic information from the multiple emission subject characteristic information as the first emission subject characteristic information; then perform similarity traversal comparison on the first emission subject characteristic information and the multiple sample emission subject characteristic information to determine multiple first similarities. For example, the similarity between the characteristic information of two emission subjects can be measured by the Euclidean distance. The closer the characteristics are, the smaller the distance is, and the higher the similarity is. Then, select the sample emission subject of the sample emission subject characteristic information corresponding to the maximum similarity among the multiple first similarities and set it as the matching sample emission subject to obtain the first matching sample emission subject; use the same method to analyze other characteristic information in the multiple emission subject characteristic information to obtain multiple matching sample emission subjects.

[0041] Then, the proportion of the sample data of the multiple matching sample emission entities in the total supervised training data is counted respectively to obtain multiple sample data proportions, wherein the sample data proportion is the ratio of the data volume of the sample data of the matching sample emission entity to the data volume of the total supervised training data. Finally, the multiple maximum feature similarities are multiplied by the multiple sample data proportions, that is, the maximum feature similarity of the same matching sample emission entity is multiplied by the sample data proportion, and the product of the two is set as the training contribution, and multiple training contribution degrees are obtained, wherein the greater the training contribution, the greater the proportion of the training data representing the emission entity in the training of the perfluorinated content prediction path, and the more accurate the prediction result of the perfluorinated compound content of the emission entity.

[0042] S220: Inputting the plurality of emission subject characteristic information into the perfluorinated content prediction path, and outputting predictions to obtain a plurality of predicted perfluorinated compound contents.

[0043] Specifically, the plurality of emission subject characteristic information are input into the perfluorinated content prediction path for prediction, and a plurality of predicted perfluorinated compound contents are output, wherein the predicted perfluorinated compound contents correspond to the emission subject characteristic information one by one.

[0044] S300: According to multiple emission times and multiple emission distances, multiple pollution influence degrees are configured for the multiple emission entities, and the multiple predicted perfluorinated compound contents are compensated and summarized in combination with the multiple training contribution degrees to obtain a predicted perfluorinated compound content range.

[0045] Furthermore, step S300 of the present invention further includes:

[0046] S310: Calculate the ratio of each emission time to the sum of multiple emission times to obtain multiple time pollution influences; S320: Calculate the ratio of each emission distance to the sum of multiple emission distances to obtain multiple distance ratios, calculate the ratio of the inverse of each distance ratio to the sum of the inverses of the multiple distance ratios to obtain multiple distance pollution influences; S330: Calculate the mean of the multiple time pollution influences and the multiple distance pollution influences to obtain multiple pollution influences; S340: Use the multiple training contribution degrees and the multiple pollution influences as error coefficients respectively, perform compensation calculations on the multiple predicted perfluorinated compound contents respectively, and obtain multiple compensated perfluorinated compound content intervals; S350: Extract the minimum and maximum interval endpoint values ​​within the multiple compensated perfluorinated compound content intervals to construct a predicted perfluorinated compound content interval.

[0047] Specifically, first, the ratio of each emission time to the sum of multiple emission times is calculated to obtain multiple time pollution impacts, where the longer the emission time, the greater the pollution impact, because the high stability of perfluorinated compounds means that long-term emissions will lead to higher pollution, and the emission time is relatively small. Next, the ratio of the sum of multiple emission distances for each emission distance is calculated to obtain multiple distance ratios; then the ratio of the reciprocal of each distance ratio to the sum of the reciprocals of the multiple distance ratios is calculated to obtain multiple distance pollution impacts, where the longer the emission distance, the smaller the pollution impact, because after a long distance of transmission, the concentration of perfluorinated compounds will gradually decrease and the pollution impact will be weakened; the closer the emission distance, the greater the pollution impact, because the pollutants can affect the target area more concentratedly.

[0048] Then, the average of the multiple time pollution impacts and the multiple distance pollution impacts is calculated, that is, for each emitter, the average of its time pollution impact and distance pollution impact is calculated, and the average calculation result is set as the overall pollution impact, and multiple pollution impacts are obtained. By combining these two factors, the overall impact of each emitter on perfluorinated compound pollution can be more accurately reflected.

[0049] Next, the multiple training contribution degrees are used to respectively perform compensation calculations on the multiple predicted perfluorinated compound contents, that is, the predicted perfluorinated compound contents are error expanded according to the training contribution degrees, wherein the larger the training contribution degree, the smaller the expanded error range. For example, assuming that the training contribution degree is 10%, and the predicted perfluorinated compound content is 10 mg / L, the compensated content interval is 10±10%=9 to 11 mg / L; multiple perfluorinated compound content intervals after training contribution degree compensation are obtained. On the other hand, using the same method, multiple pollution influence degrees are used as error coefficients to perform compensation calculations on the multiple predicted perfluorinated compound contents, that is, the predicted perfluorinated compound contents are error expanded according to the pollution influence degree, wherein the larger the pollution influence degree, the larger the expanded error range, and multiple perfluorinated compound content intervals after pollution influence degree compensation are obtained. Finally, multiple perfluorinated compound content intervals after training contribution compensation and multiple perfluorinated compound content intervals after pollution impact compensation are merged. For example, the perfluorinated compound content interval after training contribution compensation is 9 to 11 mg / L, and the perfluorinated compound content interval after pollution impact compensation is 8 to 12 mg / L. Then the overall compensated perfluorinated compound content interval is 8 to 12 mg / L, and multiple compensated perfluorinated compound content intervals are obtained.

[0050] Finally, the minimum and maximum interval endpoint values ​​within the multiple compensated perfluorinated compound content intervals are extracted, that is, the maximum compensated perfluorinated compound content and the minimum compensated perfluorinated compound content are extracted to construct a predicted perfluorinated compound content interval.

[0051] S400: According to the predicted perfluorinated compound content range, configure a first number of detection times for sampling and detecting the perfluorinated compound content in the sewage sample, and according to the floating parameters of the multiple training contribution degrees and the multiple pollution influence degrees, compensate and adjust the first number of detection times to obtain a second number of detection times, perform sewage detection, and obtain the actual perfluorinated compound content.

[0052] Furthermore, step S400 of the present invention further includes:

[0053] S410: Obtain the content interval span of the predicted perfluorinated compound content interval, and classify to obtain the first number of detection times for sampling and detecting the perfluorinated compound content of the sewage sample, wherein a set of sample content interval spans and a set of sample detection times are collected, and a mapping relationship is constructed to obtain a detection time classifier for classification; S420: Calculate the difference between the minimum and maximum training contribution degrees among the multiple training contribution degrees as the first floating parameter; S430: Calculate the difference between the minimum and maximum pollution influence degrees among the multiple pollution influence degrees as the second floating parameter; S440: Use the sum of the mean of the first floating parameter and the second floating parameter and 1, multiply it by the first detection number to perform amplification compensation adjustment calculation and round it to obtain the second detection number, perform sampling detection on the sewage sample, obtain multiple detection perfluorinated compound contents, and calculate the mean to obtain the actual perfluorinated compound content.

[0054] Specifically, first, collect the perfluorinated compound content interval span data of different samples and the corresponding sample detection times, wherein the sample detection times are positively correlated with the perfluorinated compound content, that is, the higher the perfluorinated compound content, the greater the detection times, and obtain the sample content interval span set and the sample detection times set. Then, construct a detection times classifier based on the mapping relationship between the content interval span and the detection times, that is, take the sample content interval span as input, the corresponding sample detection times as output, and take the sample content interval span set and the sample detection times set as construction data to construct a mapping model. Then, obtain the content interval span of the predicted perfluorinated compound content interval, and input the content interval span into the detection times classifier for classification and matching, and obtain the first detection times for the perfluorinated compound content sampling detection of the sewage sample.

[0055] Then, the minimum training contribution and the maximum training contribution are selected from the multiple training contributions, and the maximum training contribution is subtracted from the minimum training contribution, and the difference between the two is set as the first floating parameter; the maximum pollution influence and the minimum pollution influence are selected from the multiple pollution influences, and the difference between the maximum pollution influence and the minimum pollution influence is set as the second floating parameter. Then, the first floating parameter and the second floating parameter are averaged to obtain the floating parameter mean, and the floating parameter mean is added to 1, and the sum of the two is multiplied by the first detection number to perform amplification compensation adjustment calculation and rounding to obtain the second detection number. For example, assuming that the first detection number is 10, the first floating parameter is 0.2, and the second floating parameter is 0.3, then the floating parameter mean is 0.25, 10*(1+0.25)=12.5, and 13 is obtained after rounding, that is, the second detection number.

[0056] Finally, the sewage samples are sampled and tested according to the second detection times to obtain multiple detection perfluorinated compound contents, and the average of the multiple detection perfluorinated compound contents is calculated to obtain the actual perfluorinated compound content.

[0057] The data processing method based on sewage monitoring of perfluorinated compounds provided by the embodiment of the present invention has at least the following technical effects:

[0058] By obtaining a sewage sample, and tracing back to obtain the discharge time, discharge distance and discharge subject characteristic information of multiple discharge entities related to the sewage sample according to the sewage discharge topological relationship, wherein each discharge subject characteristic information includes discharge category and discharge amount; then, the perfluorinated compound content in the sewage sample is predicted according to the characteristic information of multiple discharge entities, and multiple predicted perfluorinated compound contents are obtained, wherein the prediction is performed through a pre-trained perfluorinated content prediction path, and multiple discharge entities are configured with multiple training contribution degrees in the supervised training data of the perfluorinated content prediction path; then, according to multiple discharge times and multiple discharge distances, multiple pollution influence degrees are configured for the multiple discharge entities, and the multiple predicted perfluorinated compounds are predicted in combination with the multiple training contribution degrees. The content of perfluorinated compounds is compensated and summarized to obtain a predicted range of perfluorinated compound content; further, according to the predicted range of perfluorinated compound content, a first detection number of sampling detection of perfluorinated compound content in the sewage sample is configured, and according to the floating parameters of the multiple training contribution degrees and the multiple pollution influence degrees, the first detection number is compensated and adjusted to obtain a second detection number; finally, sewage detection is performed according to the second detection number to obtain the actual perfluorinated compound content; the above steps can improve the accuracy and reliability of perfluorinated compound content prediction, and then the sewage detection strategy can be dynamically adjusted according to the prediction results, and the detection resource allocation is optimized, so as to achieve the technical goal of efficient and accurate detection, and significantly improve the efficiency, accuracy and reliability of perfluorinated compound detection.

[0059] Embodiment 2, as Figure 4 As shown, based on the same inventive concept as the data processing method for monitoring perfluorinated compounds in sewage provided in Example 1, the embodiment of the present invention also provides a data processing system for monitoring perfluorinated compounds in sewage, including:

[0060] The emission subject information acquisition module 01 is used to obtain sewage samples, and according to the sewage discharge topological relationship, trace the source to obtain the emission time, emission distance and emission subject characteristic information of multiple emission subjects related to the sewage samples, wherein each emission subject characteristic information includes emission category and emission amount; the perfluorinated compound content prediction module 02 is used to predict the perfluorinated compound content in the sewage sample according to the characteristic information of multiple emission subjects, and obtain multiple predicted perfluorinated compound contents, wherein the prediction is performed through a pre-trained perfluorinated content prediction path, and multiple emission subjects are configured with multiple training contribution degrees in the supervised training data of the perfluorinated content prediction path; predicting the perfluorinated compound content The material content compensation module 03 is used to configure multiple pollution influences for the multiple emission entities according to multiple emission times and multiple emission distances, and compensate and summarize the multiple predicted perfluorinated compound contents in combination with the multiple training contribution degrees to obtain the predicted perfluorinated compound content range; the detection number compensation adjustment module 04 is used to configure the first detection number for sampling and detecting the perfluorinated compound content of the sewage sample according to the predicted perfluorinated compound content range, and compensate and adjust the first detection number according to the floating parameters of the multiple training contribution degrees and multiple pollution influences to obtain the second detection number, conduct sewage detection, and obtain the actual perfluorinated compound content.

[0061] Furthermore, the data processing system based on sewage monitoring of perfluorinated compounds also includes: collecting sewage samples within the sewage detection area; obtaining the sewage discharge pipe network in the sewage detection area and constructing a sewage discharge topological relationship; tracing back to obtain multiple emission entities related to the sewage samples based on the sewage discharge topological relationship; collecting the discharge time of the multiple emission entities, the distance from the discharge pipe of the sewage detection area, and the type and amount of discharged sewage, integrating multiple types of discharged sewage and multiple discharge amounts, and obtaining characteristic information of multiple emission entities.

[0062] Furthermore, the data processing system based on sewage monitoring of perfluorinated compounds also includes: training a perfluorinated content prediction path based on historical perfluorinated compound emission detection data of multiple sample emission entities, wherein multiple training contribution degrees are configured according to the number of supervised training data of sample emission entities similar to the multiple emission entities; inputting the characteristic information of the multiple emission entities into the perfluorinated content prediction path, and predicting and outputting multiple predicted perfluorinated compound contents.

[0063] Furthermore, the data processing system based on sewage monitoring of perfluorinated compounds also includes: collecting multiple sample emission feature information sets of multiple sample emission subjects and collecting multiple sample perfluorinated compound content sets based on historical perfluorinated compound emission detection data of multiple sample emission subjects; using the multiple sample emission feature information sets and the multiple sample perfluorinated compound content sets as supervised training data to perform supervised training of perfluorinated content prediction paths until the training converges; and configuring multiple training contribution degrees according to the number of supervised training data of sample emission subjects similar to the multiple emission subjects.

[0064] Furthermore, the data processing system based on sewage monitoring of perfluorinated compounds also includes: obtaining characteristic information of multiple sample emission entities of the multiple sample emission entities; obtaining characteristic similarities between the characteristic information of the multiple emission entities and the characteristic information of the multiple sample emission entities, and selecting the sample emission entities corresponding to the largest multiple maximum characteristic similarities as multiple matching sample emission entities; obtaining the proportion of sample data of the multiple matching sample emission entities in all supervised training data to obtain multiple sample data proportions; and multiplying the multiple maximum characteristic similarities by the multiple sample data proportions to obtain multiple training contribution degrees.

[0065] Furthermore, the data processing system based on sewage monitoring of perfluorinated compounds also includes: calculating the ratio of each discharge time to the sum of multiple discharge times to obtain multiple time pollution influences; calculating the ratio of each discharge distance to the sum of multiple discharge distances to obtain multiple distance ratios, calculating the ratio of the reciprocal of each distance ratio to the sum of the reciprocals of the multiple distance ratios to obtain multiple distance pollution influences; calculating the mean of the multiple time pollution influences and the multiple distance pollution influences to obtain multiple pollution influences; using the multiple training contribution degrees and the multiple pollution influences as error coefficients, respectively, to perform compensation calculations on the multiple predicted perfluorinated compound contents, respectively, to obtain multiple compensated perfluorinated compound content intervals; extracting the minimum and maximum interval endpoint values ​​within the multiple compensated perfluorinated compound content intervals to construct predicted perfluorinated compound content intervals.

[0066] Furthermore, the data processing system based on sewage monitoring of perfluorinated compounds also includes: obtaining the content interval span of the predicted perfluorinated compound content interval, classifying and obtaining the first number of detection times for sampling and detecting the perfluorinated compound content of the sewage sample, wherein a set of sample content interval spans and a set of sample detection times are collected, and a mapping relationship is constructed to obtain a detection time classifier for classification; calculating the difference between the minimum and maximum training contribution degrees among the multiple training contribution degrees as the first floating parameter; calculating the difference between the minimum and maximum pollution influence degrees among the multiple pollution influence degrees as the second floating parameter; taking the sum of the mean of the first floating parameter and the second floating parameter and 1, multiplying it by the first detection number to perform amplification compensation adjustment calculation and rounding, obtaining the second detection number, performing sampling detection of the sewage sample, obtaining multiple detection perfluorinated compound contents, and calculating the mean to obtain the actual perfluorinated compound content.

[0067] For example 3, please refer to Figure 5 , Figure 5 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 5 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 a sewage sample, and tracing back to obtain the discharge time, discharge distance, and discharge subject characteristic information of multiple discharge subjects related to the sewage sample according to the sewage discharge topological relationship, wherein each discharge subject characteristic information includes a discharge category and a discharge amount; predicting the perfluorinated compound content in the sewage sample according to the multiple discharge subject characteristic information, and obtaining multiple predicted perfluorinated compound contents, wherein the perfluorinated compound content predicted by pre-training A prediction is made on a measurement path, and multiple emission entities are configured with multiple training contribution degrees in the supervised training data of the perfluorinated content prediction path; multiple pollution influence degrees are configured for the multiple emission entities according to multiple emission times and multiple emission distances, and the multiple predicted perfluorinated compound contents are compensated and summarized in combination with the multiple training contribution degrees to obtain a predicted perfluorinated compound content range; according to the predicted perfluorinated compound content range, a first detection number of sampling tests for the perfluorinated compound content of the sewage sample is configured, and according to the floating parameters of the multiple training contribution degrees and the multiple pollution influence degrees, the first detection number is compensated and adjusted to obtain a second detection number, and sewage detection is performed to obtain the actual perfluorinated compound content.

[0068] Example 4, please refer to Figure 6 , Figure 6 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 6As 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 a processor, the following steps are implemented: obtaining a sewage sample, and tracing back to obtain the discharge time, discharge distance and discharge subject characteristic information of multiple discharge subjects related to the sewage sample according to the sewage discharge topological relationship, wherein each discharge subject characteristic information includes a discharge category and a discharge amount; predicting the perfluorinated compound content in the sewage sample according to the multiple discharge subject characteristic information, and obtaining multiple predicted perfluorinated compound contents, wherein the prediction is performed through a pre-trained perfluorinated content prediction path, and the multiple discharge subjects are in the The supervised training data of the perfluorinated content prediction path is configured with multiple training contribution degrees; multiple pollution influence degrees are configured for the multiple emission entities according to multiple emission times and multiple emission distances, and the multiple predicted perfluorinated compound contents are compensated and summarized in combination with the multiple training contribution degrees to obtain a predicted perfluorinated compound content range; according to the predicted perfluorinated compound content range, a first detection number of sampling tests for the perfluorinated compound content of the sewage sample is configured, and according to the floating parameters of the multiple training contribution degrees and the multiple pollution influence degrees, the first detection number is compensated and adjusted to obtain a second detection number, and sewage detection is performed to obtain the actual perfluorinated compound content.

[0069] 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.

[0070] 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.

[0071] 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 1A device that provides the functions specified in a block or multiple blocks.

[0072] 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.

[0073] 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. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0074] 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.

[0075] 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 data processing method based on wastewater monitoring of perfluorinated compounds, characterized in that: Methods include: Obtaining a sewage sample, and tracing the source to obtain the discharge time, discharge distance and discharge subject characteristic information of multiple discharge entities related to the sewage sample according to the sewage discharge topological relationship, wherein the characteristic information of each discharge entity includes the discharge category and discharge amount; Predicting the content of perfluorinated compounds in the sewage sample according to characteristic information of multiple emission entities respectively to obtain multiple predicted perfluorinated compound contents, wherein the prediction is performed through a pre-trained perfluorinated content prediction path, and multiple emission entities are configured with multiple training contribution degrees in the supervised training data of the perfluorinated content prediction path; According to the multiple emission times and the multiple emission distances, multiple pollution influences are configured for the multiple emission entities, and the multiple predicted perfluorinated compound contents are compensated and summarized in combination with the multiple training contributions to obtain a predicted perfluorinated compound content range; According to the predicted perfluorinated compound content range, a first number of detection times for sampling and detecting the perfluorinated compound content in the sewage sample is configured, and according to the floating parameters of the multiple training contribution degrees and the multiple pollution influence degrees, the first number of detection times is compensated and adjusted to obtain a second number of detection times, and sewage detection is performed to obtain the actual perfluorinated compound content.

2. The data processing method based on sewage monitoring of perfluorinated compounds according to claim 1 is characterized in that: Obtain sewage samples, and trace the source to obtain characteristic information of multiple discharge entities related to the sewage samples based on the sewage discharge topology, including: Collect sewage samples within the sewage testing area; Acquire the sewage discharge pipe network in the sewage detection area and construct a sewage discharge topological relationship; According to the sewage discharge topological relationship, tracing back to obtain multiple discharge entities related to the sewage sample; The discharge time, the distance from the discharge pipe to the sewage detection area, and the discharged sewage category and discharge amount of the multiple discharge entities are collected, and the multiple discharged sewage categories and multiple discharge amounts are integrated to obtain the characteristic information of multiple discharge entities.

3. The data processing method based on sewage monitoring of perfluorinated compounds according to claim 1, characterized in that: The perfluorinated compound content in the sewage sample is predicted according to the characteristic information of multiple emission entities to obtain multiple predicted perfluorinated compound contents, including: Training a perfluorinated content prediction path based on historical perfluorinated compound emission detection data of multiple sample emission entities, wherein multiple training contribution degrees are configured according to the number of supervised training data of sample emission entities similar to the multiple emission entities; The plurality of emission subject characteristic information is input into the perfluorinated content prediction path, and a plurality of predicted perfluorinated compound contents are obtained by prediction output.

4. The data processing method based on sewage monitoring of perfluorinated compounds according to claim 3 is characterized in that: Based on the historical perfluorinated compound emission detection data of multiple sample emission entities, the perfluorinated content prediction pathway is trained, including: Collecting multiple sets of sample emission characteristic information of multiple sample emission subjects based on historical perfluorinated compound emission detection data of multiple sample emission subjects, and collecting multiple sets of sample perfluorinated compound content; Using the plurality of sample emission characteristic information sets and the plurality of sample perfluorinated compound content sets as supervised training data, and performing supervised training of the perfluorinated content prediction path until the training converges; A plurality of training contribution degrees are configured according to the number of supervised training data of sample emission entities similar to the plurality of emission entities.

5. The data processing method based on sewage monitoring of perfluorinated compounds according to claim 4 is characterized in that: According to the number of supervised training data of sample emission entities similar to the plurality of emission entities, a plurality of training contribution degrees are configured, including: Acquire characteristic information of multiple sample emission subjects of the multiple sample emission subjects; Acquire the characteristic similarities between the characteristic information of the plurality of emission entities and the characteristic information of the plurality of sample emission entities, and select the sample emission entities corresponding to the largest plurality of maximum characteristic similarities as the plurality of matching sample emission entities; Obtaining the proportion of the sample data of the multiple matching sample emission entities in the entire supervised training data, and obtaining the proportion of multiple sample data; The multiple maximum feature similarities are multiplied by the multiple sample data proportions to obtain multiple training contribution degrees.

6. The data processing method based on sewage monitoring of perfluorinated compounds according to claim 1, characterized in that: According to multiple emission times and multiple emission distances, multiple pollution influences are configured for the multiple emission entities, and the multiple predicted perfluorinated compound contents are compensated and summarized in combination with the multiple training contributions to obtain a predicted perfluorinated compound content range, including: Calculate the ratio of each emission time to the sum of multiple emission times to obtain the pollution impact of multiple times; Calculating the ratio of each emission distance to the sum of multiple emission distances to obtain multiple distance ratios, calculating the ratio of the reciprocal of each distance ratio to the sum of the reciprocals of the multiple distance ratios to obtain multiple distance pollution impacts; Calculating the average of the multiple time pollution impact degrees and the multiple distance pollution impact degrees to obtain multiple pollution impact degrees; Using the plurality of training contribution degrees and the plurality of pollution influence degrees as error coefficients respectively, respectively performing compensation calculations on the plurality of predicted perfluorinated compound contents, and obtaining a plurality of compensated perfluorinated compound content intervals; The minimum and maximum interval endpoint values ​​within the plurality of compensated perfluorinated compound content intervals are extracted to construct a predicted perfluorinated compound content interval.

7. The data processing method based on sewage monitoring of perfluorinated compounds according to claim 1, characterized in that: According to the predicted perfluorinated compound content interval, a first detection number of sampling detection of the perfluorinated compound content of the sewage sample is configured, and according to the floating parameters of the multiple training contribution degrees and the multiple pollution influence degrees, the first detection number is compensated and adjusted to obtain a second detection number, and sewage detection is performed to obtain the actual perfluorinated compound content, including: Obtaining the content interval span of the predicted perfluorinated compound content interval, and classifying to obtain the first detection times of the perfluorinated compound content sampling detection of the sewage sample, wherein a sample content interval span set and a sample detection times set are collected, and a mapping relationship is constructed to obtain a detection times classifier for classification; Calculate the difference between the minimum and maximum training contribution degrees among the multiple training contribution degrees as the first floating parameter; Calculating a difference between a minimum and a maximum pollution impact degree among the plurality of pollution impact degrees as a second floating parameter; The sum of the mean of the first floating parameter and the second floating parameter and 1 is multiplied by the first detection number to perform amplification compensation adjustment calculation and round up to obtain the second detection number, and the sewage sample is sampled and tested to obtain multiple detection perfluorinated compound contents, and the mean is calculated to obtain the actual perfluorinated compound content.

8. A data processing system based on wastewater monitoring of perfluorinated compounds, characterized in that: The steps for implementing the data processing method for monitoring perfluorinated compounds in wastewater according to any one of claims 1 to 7 include: The emission subject information acquisition module is used to obtain sewage samples and, based on the sewage discharge topology, trace the source to obtain the discharge time, discharge distance and emission subject characteristic information of multiple emission subjects related to the sewage samples, wherein each emission subject characteristic information includes the discharge category and discharge amount; A perfluorinated compound content prediction module, used to predict the perfluorinated compound content in the sewage sample according to the characteristic information of multiple emission entities, and obtain multiple predicted perfluorinated compound contents, wherein the prediction is performed through a pre-trained perfluorinated content prediction path, and multiple emission entities are configured with multiple training contribution degrees in the supervised training data of the perfluorinated content prediction path; A predicted perfluorinated compound content compensation module is used to configure multiple pollution influences for the multiple emission entities according to multiple emission times and multiple emission distances, and to compensate and summarize the multiple predicted perfluorinated compound contents in combination with the multiple training contributions to obtain a predicted perfluorinated compound content interval; The detection times compensation adjustment module is used to configure a first detection times for sampling and detecting the perfluorinated compound content in the sewage sample according to the predicted perfluorinated compound content range, and to compensate and adjust the first detection times according to the floating parameters of the multiple training contribution degrees and the multiple pollution influence degrees to obtain a second detection times, conduct sewage testing, and obtain the actual perfluorinated compound content.

9. 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 the steps of the data processing method based on sewage monitoring of perfluorinated compounds as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, which, when executed by a processor, implements the steps of the data processing method based on wastewater monitoring of perfluorinated compounds as described in any one of claims 1 to 7.

Images