CN109725119B

CN109725119B - Water quality information processing method, system, storage medium and computer equipment

Info

Publication number: CN109725119B
Application number: CN201811524359.3A
Authority: CN
Inventors: 郑一; 鲁海燕; 张敬杰; 姜继平; 熊剑智
Original assignee: Southwest University of Science and Technology
Current assignee: Southwest University of Science and Technology
Priority date: 2018-12-13
Filing date: 2018-12-13
Publication date: 2021-04-23
Anticipated expiration: 2038-12-13
Also published as: CN109725119A

Abstract

The application relates to a water quality information processing method, a system, a storage medium and computer equipment, which are used for acquiring water quality detection parameters of a target water body; predicting the change condition of the total amount of bacteria according to the physical and chemical parameters and the total amount of bacteria to obtain a predicted value of the total amount of bacteria and a predicted value of the content of specific pathogenic bacteria of the target water body; and when the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria exceed the water quality health standard, determining a corresponding water quality treatment strategy according to the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria. The water quality condition can be predicted in advance by predicting the total amount of bacteria and the content of specific pathogenic bacteria in the water body, and a corresponding water quality treatment strategy is provided when the water quality condition exceeds the water quality health standard, so that the aim of monitoring the water quality condition in real time can be fulfilled, and the safety influence and property loss caused by water quality information lag can be reduced to a certain extent.

Description

Water quality information processing method, system, storage medium and computer equipment

Technical Field

The application relates to the technical field of water quality monitoring, in particular to a water quality information processing method, a water quality information processing system, a storage medium and computer equipment.

Background

Along with the improvement of living standard, people also attach more and more importance to water quality safety, for example: generally speaking, the total amount of bacteria in a water body can be used as a measure for water quality safety, such as water quality safety of drinking water used in daily life of people and water quality safety of other application scenes (fishery, aquaculture, etc.).

In order to ensure the water quality safety, the prior art obtains a water body sample by sampling the water body, and analyzes the water quality of the water body sample through a laboratory, thereby obtaining the water quality health condition information of the water body. However, since the water quality analysis needs a certain time, the real-time water quality information of the water body cannot be obtained, and the situation of information lag easily occurs, that is, when the total bacteria amount of the detected water body exceeds the standard, the corresponding water body has safety influence on the public, fishery, breeding industry and the like, and a certain loss is caused.

Disclosure of Invention

In view of the above, it is necessary to provide a water quality information processing method, system, storage medium, and computer device that can predict the water quality state in advance and provide a water quality control strategy when necessary, in order to solve the problems of the prior art.

A water quality information processing method comprises the following steps:

acquiring water quality detection parameters of the object water body, wherein the water quality detection parameters comprise: physical and chemical parameters and total bacterial count;

predicting the change condition of the total bacteria amount according to the physical and chemical parameters and the total bacteria amount to obtain a predicted value of the total bacteria amount and a predicted value of the content of specific pathogenic bacteria of the target water body;

and when the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria exceed the water quality health standard, determining a corresponding water quality treatment strategy according to the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria.

In one embodiment, the specific pathogenic bacteria are pathogenic bacteria corresponding to different application environments.

In one embodiment, predicting the change of the total bacteria amount according to the physicochemical parameter and the total bacteria amount to obtain a predicted value of the total bacteria amount and a predicted value of the content of specific pathogenic bacteria in the subject water body includes:

predicting the change condition of the total bacteria amount through a water quality ecological mechanism model according to the physical and chemical parameters and the total bacteria amount, and obtaining a predicted value of the total bacteria amount of the target water body according to the total bacteria amount and the prediction result of the change condition;

and predicting the content of the specific pathogenic bacteria through a neural network model according to the total bacterial quantity predicted value to obtain the specific pathogenic bacteria content predicted value of the target water body.

In one embodiment, any one of the following is included:

the first item: carrying out parameter calibration and parameter verification on the water quality ecological mechanism model according to sample data, and adding bacterial regrowth parameters into the water quality ecological mechanism model, wherein the sample data comprises physical and chemical parameters and corresponding bacterial total amount change data;

the second term is: training the neural network model by taking the types of the specific pathogenic bacteria and the content of the specific pathogenic bacteria corresponding to different total bacteria as training data;

and when the error between the predicted value of the specific pathogenic bacteria content obtained by the neural network model according to the current total bacteria amount and the actual specific pathogenic bacteria content corresponding to the current total bacteria amount is within a preset range, determining that the training of the neural network model is finished.

In one embodiment, determining a corresponding water quality treatment strategy according to the predicted value of the total bacteria amount and/or the predicted value of the content of the specific pathogenic bacteria comprises:

and according to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value, performing prediction evaluation on the water quality treatment condition corresponding to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value through a water quality ecological mechanism model and a neural network model, and determining a corresponding water quality treatment strategy according to a prediction evaluation result.

In one embodiment, according to the predicted value of the total amount of bacteria and/or the predicted value of the content of the specific pathogenic bacteria, a water quality ecological mechanism model and a neural network model are used for performing prediction evaluation on the water quality treatment condition corresponding to the predicted value of the total amount of bacteria and/or the predicted value of the content of the specific pathogenic bacteria, and a corresponding water quality treatment strategy is determined according to the prediction evaluation result, wherein the water quality treatment strategy comprises any one of the following items:

the first item: when the predicted value of the total amount of bacteria and the predicted value of the content of the specific pathogenic bacteria exceed the water quality health standard, predicting the regrowth condition of the treated bacteria through the water quality ecological mechanism model according to the predicted value of the total amount of bacteria and a preset treatment strategy to obtain a secondary predicted value of the total amount of bacteria, wherein the secondary predicted value of the total amount of bacteria is a predicted value of the total amount of bacteria corresponding to the predicted value of the total amount of bacteria and after treatment;

predicting the content of the corresponding specific pathogenic bacteria through the neural network model according to the secondary predicted value of the total amount of the bacteria to obtain a corresponding secondary predicted value of the content of the specific pathogenic bacteria, wherein the secondary predicted value of the content of the specific pathogenic bacteria is a predicted value of the content of the treated specific pathogenic bacteria corresponding to the predicted value of the content of the specific pathogenic bacteria;

according to the preset treatment strategy, predicting the content of the treated harmful byproducts through the neural network model to obtain a corresponding predicted value of the content of the harmful byproducts;

when the secondary predicted value of the total amount of bacteria, the secondary predicted value of the content of the specific pathogenic bacteria and the predicted value of the content of the harmful byproducts reach preset standards, determining the preset treatment strategy as the water quality treatment strategy;

the second term is: when the total bacterial quantity predicted value exceeds the water quality health standard, predicting the regrowth condition of the treated bacteria through the water quality ecological mechanism model according to the total bacterial quantity predicted value and a preset treatment strategy to obtain a secondary predicted value of the total bacterial quantity;

when the secondary predicted value of the total amount of bacteria and the predicted value of the content of the harmful byproducts reach preset standards, determining the preset treatment strategy as the water quality treatment strategy;

the third item: when the predicted value of the content of the specific pathogenic bacteria exceeds the water quality health standard, predicting the regrowth condition of the treated bacteria through the water quality ecological mechanism model according to the predicted value of the total bacteria amount and a preset treatment strategy to obtain a secondary predicted value of the total bacteria amount;

predicting the content of the corresponding specific pathogenic bacteria through the neural network model according to the secondary predicted value of the total amount of the bacteria to obtain a corresponding secondary predicted value of the content of the specific pathogenic bacteria;

and when the secondary predicted value of the content of the specific pathogenic bacteria and the predicted value of the content of the harmful byproducts reach preset standards, determining the preset treatment strategy as the water quality treatment strategy.

In one embodiment, the neural network model is trained by:

training the neural network model by taking different preset treatment strategies and corresponding harmful byproduct contents as training data;

and when the error between the predicted value of the content of the harmful byproducts obtained by the neural network model according to the current treatment strategy and the actual content of the harmful byproducts corresponding to the current treatment strategy is within a preset range, determining that the training of the neural network model is finished.

A water quality information processing system comprising: the water quality monitoring device, the data transmission device and the water quality management platform;

the water quality monitoring device is used for acquiring water quality detection parameters of the object water body through monitoring, and the water quality detection parameters comprise: physical and chemical parameters and total bacterial count;

the data transmission device is used for transmitting the water quality detection parameters acquired by the water quality monitoring device to the water quality management platform;

the water quality management platform is used for predicting the change condition of the total bacteria amount according to the physical and chemical parameters and the total bacteria amount to obtain a predicted value of the total bacteria amount and a predicted value of the content of specific pathogenic bacteria of the target water body; and when the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria exceed the water quality health standard, determining a corresponding water quality treatment strategy according to the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria.

A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the water quality information processing method when executing the computer program.

A computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the steps of the water quality information processing method described above.

The water quality information processing method, the water quality information processing system, the storage medium and the computer equipment obtain water quality detection parameters of the object water body, wherein the water quality detection parameters comprise: physical and chemical parameters and total bacterial count; predicting the change condition of the total amount of bacteria according to the physical and chemical parameters and the total amount of bacteria to obtain a predicted value of the total amount of bacteria and a predicted value of the content of specific pathogenic bacteria of the target water body; and when the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria exceed the water quality health standard, determining a corresponding water quality treatment strategy according to the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria. The water quality condition can be predicted in advance by predicting the total amount of bacteria and the content of specific pathogenic bacteria in the water body, and a corresponding water quality treatment strategy is provided when the water quality condition exceeds the water quality health standard, so that the aim of monitoring the water quality condition in real time can be fulfilled, and the safety influence and property loss caused by water quality information lag can be reduced to a certain extent.

Drawings

FIG. 1 is a schematic flow chart of a water quality information processing method according to an embodiment;

FIG. 2 is a flowchart showing the whole water quality information processing method in one embodiment;

FIG. 3 is a schematic view of a water quality information processing apparatus according to an embodiment;

fig. 4 is a schematic structural diagram of a water quality information processing system in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.

In one embodiment, as shown in fig. 1, a water quality information processing method is provided, which is explained by taking an example of applying the method to a water quality management platform capable of performing water quality information processing, and the method includes the following steps:

and S100, acquiring water quality detection parameters of the object water body.

The water quality detection parameters comprise physical and chemical parameters and the total amount of bacteria, and the physical and chemical parameters can represent the types and the amount of impurities in the water body and are important measurement scales for judging the water pollution degree. The physical parameters include sensory physical indexes such as temperature, chromaticity, turbidity, transparency and the like, and other physical water quality indexes such as total solid, suspended solid, fixed solid, conductivity (resistivity) and the like. Chemical parameters comprise pH value, hardness, alkalinity, various ions, general organic substances and the like, and the total amount of bacteria indicates the pollution degree of the water body from the bacteriology perspective and comprises the total amount of bacteria, the total coliform number, various pathogenic bacteria, viruses and the like.

The water quality detection parameters acquired by the water quality management platform can be pre-acquired water quality detection parameters or water quality detection parameters acquired in real time, the water quality detection parameters can be detected by water quality monitoring equipment and a bacterial sensor, in addition, other parameters which cannot be monitored by the equipment can also be included, and the parameters of the type can be parameters obtained by manual sampling analysis.

S200, predicting the change condition of the total bacteria amount according to the physical and chemical parameters and the total bacteria amount to obtain a predicted value of the total bacteria amount and a predicted value of the content of specific pathogenic bacteria in the target water body;

after the water quality management platform acquires the water quality detection parameters, the future growth condition of bacteria can be predicted according to the physical and chemical parameters and the total amount of bacteria in the water quality detection parameters and the growth condition of the bacteria, namely the change condition of the total amount of the bacteria is predicted, and a corresponding predicted value of the total amount of the bacteria and a predicted value of the content of specific pathogenic bacteria are obtained.

And S300, when the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value exceed the water quality health standard, determining a corresponding water quality treatment strategy according to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value.

When the predicted value of the total amount of bacteria and/or the predicted value of the content of the specific pathogenic bacteria, which is predicted by the water quality management platform through the step S200, exceeds the water quality health standard, the situation that the water quality exceeds the health standard in a corresponding future time period is shown. Therefore, the water quality management platform can determine a corresponding water quality treatment strategy according to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value, and related personnel can treat the water quality according to the water quality treatment strategy according to actual conditions, so that the water quality can be treated in advance, and the condition that the total bacterial quantity and/or the specific pathogenic bacterium content exceeds the standard is avoided.

The embodiment can predict the water quality condition in advance by predicting the total amount of bacteria and the content of specific pathogenic bacteria in the water body, and provides a corresponding water quality treatment strategy when the water quality condition exceeds the water quality health standard, thereby achieving the purpose of monitoring the water quality condition in real time and reducing the safety influence and property loss caused by water quality information lag to a certain extent.

In one embodiment, the specific pathogenic bacteria are pathogenic bacteria corresponding to different application environments, and specifically can be pathogenic bacteria corresponding to various aquaculture environments.

The pathogens causing the diseases of the aquaculture animals mainly comprise bacteria, viruses, fungi, parasites, algae and the like, wherein the common symptoms of the fishes caused by the bacteria comprise gill rot, white skin, red skin, erect scales, bacterial septicemia, bacterial enteritis, furuncle, printing diseases and the like, the common bacterial diseases of the crustaceans comprise red leg, gill rot, blind eyes, shell ulcer, fluorescence disease and the like, the common bacterial diseases of the turtles comprise Edwardsiellosis, perforation, red neck disease and gastric ulcer hemorrhage, and the common bacterial diseases of the frogs comprise Edwardsiellosis, red leg disease, streptococcicosis and the like. Specifically, the cause of gill rot is columnar fibrobacter, the cause of red skin is pseudomonas fluorescens, the cause of vertical scale is pseudomonas sp, the cause of bacterial septicemia of freshwater fish is aeromonas hydrophila, the cause of bacterial enteritis is aeromonas hydrophila, aeromonas caviae and enterotype pseudomonas sp, the print cause is pseudomonas sp, the cause of furuncle is aeromonas sporulata, leiocassis longirostris intestinal septicemia is caused by the infection of leiocassis longirostris to vibrio: the vibrio may be eel vibrio, parahaemolyticus vibrio, alginolytic vibrio, vibrio harveyi, etc.

In addition, because the content of the specific pathogenic bacteria may not be normally obtained through online monitoring, the content of the specific pathogenic bacteria can be obtained in a manual sampling and analyzing mode, and the content data of the specific pathogenic bacteria can be uploaded to a water quality management platform.

In one embodiment, the method further comprises: and carrying out parameter calibration and parameter verification on the water quality ecological mechanism model according to sample data, and adding the bacterial regrowth parameters into the water quality ecological mechanism model, wherein the sample data comprises physical and chemical parameters and corresponding bacterial total amount change data.

The water quality ecological mechanism model can adopt the existing mechanism model, and the model parameters of the mechanism model are adjusted according to the physicochemical parameters and the corresponding bacteria total amount change data, so that the mechanism model has the capability of predicting the bacteria total amount change condition according to the physicochemical parameters.

Specifically, parameter calibration is to substitute an assumed parameter into a mechanism model to obtain a corresponding calculation result (a total bacterial quantity prediction value), compare the calculation result with actual data (an actual total bacterial quantity), and if an error between the calculation result and the actual data is within a preset range, consider the parameter at this time as a parameter meeting a condition; and if the error between the calculation result and the actual data exceeds a preset range, adjusting the parameters, substituting the adjusted parameters into the mechanism model again, recalculating, and comparing until the error between the calculation result and the actual data is within the preset range. And parameter verification is further included after parameter calibration, namely, new sample data can be adopted to verify the mechanism model after parameter calibration, and when the error between the calculation result output by the mechanism model and the actual data is within a preset range, the mechanism model is determined to have the capability of predicting the total bacterial quantity change condition according to the physical and chemical parameters.

The bacteria regrowth parameter is a parameter indicating a rate of regrowth of bacteria after the object containing bacteria is sterilized, and the bacteria regrowth parameter is added to the water quality ecology mechanism model, so that the mechanism model can have a capability of predicting the bacteria regrowth.

In one embodiment, the method further comprises: training a neural network model by taking the types of the specific pathogenic bacteria and the content of the specific pathogenic bacteria corresponding to different total bacteria as training data; and when the error between the predicted value of the content of the specific pathogenic bacteria obtained by the neural network model according to the current total bacteria amount and the actual content of the specific pathogenic bacteria corresponding to the current total bacteria amount is within a preset range, determining that the training of the neural network model is finished.

Specifically, a training sample is obtained, the training sample comprises the total bacteria amount and the corresponding specific pathogenic bacteria content, the total bacteria amount is used as the input of a neural network model, the corresponding specific pathogenic bacteria content is used as the output of the neural network model, the neural network model is trained until the error between the predicted value of the specific pathogenic bacteria content, which is obtained by predicting the total bacteria amount, of the neural network model and the specific pathogenic bacteria content is within a preset range, and therefore the correlation between the total bacteria amount and the specific pathogenic bacteria content is established.

In the embodiment, the neural network model is trained according to the types of the specific pathogenic bacteria and the content of the specific pathogenic bacteria corresponding to different total bacteria amounts, so that the neural network model can predict according to the total bacteria amount to obtain a more accurate predicted value of the content of the specific pathogenic bacteria.

In one embodiment, the method for predicting the change condition of the total amount of bacteria according to the physicochemical parameters and the total amount of bacteria to obtain a predicted value of the total amount of bacteria and a predicted value of the content of specific pathogenic bacteria in a target water body comprises the following steps: predicting the change condition of the total bacteria amount through a water quality ecological mechanism model according to the physical and chemical parameters and the total bacteria amount, and obtaining a predicted value of the total bacteria amount of the target water body according to the total bacteria amount and the prediction result of the change condition; and predicting the content of the specific pathogenic bacteria through a neural network model according to the total bacterial quantity predicted value to obtain the specific pathogenic bacteria content predicted value of the target water body.

After the water quality detection parameters of the target water body are obtained, the water quality ecological mechanism model passing the parameter calibration and parameter verification is used for predicting according to the physical and chemical parameters and the total bacteria amount in the water quality detection parameters, so that a more accurate predicted value of the total bacteria amount can be obtained, whether the predicted value of the total bacteria amount exceeds the standard or not is determined by comparing the predicted value of the total bacteria amount with the water quality health standard, and then the predicted value of the total bacteria amount can be treated in advance under the condition that the predicted value of the total bacteria amount exceeds the standard.

Furthermore, a total bacterial quantity predicted value is obtained according to the water quality ecological mechanism model, and the content of the specific pathogenic bacteria is predicted through the trained neural network model, so that a more accurate specific pathogenic bacteria content predicted value can be obtained, the specific pathogenic bacteria content predicted value can be treated in advance under the condition that the specific pathogenic bacteria content predicted value exceeds the standard, and property loss of the specific pathogenic bacteria to aquaculture is prevented or reduced.

It should be noted that, because the detection of specific pathogenic bacteria in water is complicated and time-consuming, which results in a difficult detection, the prior art generally performs a conventional detection of total bacteria amount first, and detects various pathogenic bacteria one by one when necessary. According to the embodiment, the prediction can be carried out through a trained neural network model according to the total bacterial quantity prediction value, and a more accurate specific pathogenic bacteria content prediction value can be obtained, so that the detection flow of specific pathogenic bacteria can be reduced, the specific pathogenic bacteria content prediction value can be controlled in advance when exceeding the standard, and the condition that the content of the specific pathogenic bacteria exceeds the standard is avoided.

In one embodiment, the corresponding water quality treatment strategy is determined according to the predicted value of the total bacteria amount and/or the predicted value of the content of the specific pathogenic bacteria, and comprises the following steps: and according to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value, performing prediction evaluation on the water quality treatment condition corresponding to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value through a water quality ecological mechanism model and a neural network model, and determining a corresponding water quality treatment strategy according to the prediction evaluation result.

In one embodiment, the neural network model is trained by: training a neural network model by taking different preset treatment strategies and corresponding harmful byproduct contents as training data; and when the error between the predicted value of the content of the harmful byproducts obtained by the neural network model according to the current treatment strategy and the actual content of the harmful byproducts corresponding to the current treatment strategy is within a preset range, determining that the training of the neural network model is finished.

Specifically, a training sample is obtained, the training sample comprises different treatment strategies and the content of the treated harmful byproducts corresponding to the different treatment strategies, the different treatment strategies are used as the input of a neural network model, the content of the treated harmful byproducts corresponding to the different treatment strategies is used as the output of the neural network model, and the neural network model is trained until the error between the predicted value of the content of the corresponding harmful byproducts predicted by the neural network model according to the different treatment strategies and the actual content of the harmful byproducts is within a preset range, so that the correlation between the output (the content of the treated harmful byproducts) and the input (the different treatment strategies) is established.

Taking chlorination as an example of a water quality treatment method, chlorination byproducts of drinking water include trihalomethanes, mainly refer to trichloromethane, bromodichloromethane, dibromochloromethane and tribromomethane, wherein the trichloromethane has the highest occurrence frequency and the highest content. Chlorinated disinfection by-products include haloacetic acids, haloketones, haloacrylonitriles, trichloronitromethane, chloral hydrate, cyanogen chloride, formaldehyde, acetaldehyde, 2, 4, 6-trichlorophenol, etc., in addition to trihalomethane, and chlorine disinfected drinking water also produces 3-chloro-4- (dichloromethyl) -5-hydroxy-2 (5H) -furan and E-2-chloro-3- (dichloromethyl) -4-oxo-butadienoic acid. These substances are harmful to human body and can cause cancer or mutation. Therefore, the prediction of the content of harmful byproducts is also particularly important.

In the embodiment, the neural network model is trained through the harmful byproduct information corresponding to different treatment strategies, so that the neural network model can be predicted according to different treatment strategies to obtain a more accurate predicted value of the content of the harmful byproducts after water quality treatment, and thus, the decision of the treatment strategies can be conveniently made by workers.

In one embodiment, according to the total bacterial amount predicted value and/or the specific pathogenic bacterium content predicted value, the water quality treatment condition corresponding to the total bacterial amount predicted value and/or the specific pathogenic bacterium content predicted value is predicted and evaluated through a water quality ecological mechanism model and a neural network model, and a corresponding water quality treatment strategy is determined according to the prediction and evaluation result, and the method comprises the following steps:

when the predicted value of the total amount of bacteria and the predicted value of the content of the specific pathogenic bacteria exceed the water quality health standard, predicting the regrowth condition of the treated bacteria through a water quality ecological mechanism model according to the predicted value of the total amount of bacteria and a preset treatment strategy to obtain a secondary predicted value of the total amount of bacteria, wherein the secondary predicted value of the total amount of bacteria is the predicted value of the total amount of the treated bacteria corresponding to the predicted value of the total amount of bacteria; predicting the content of the corresponding specific pathogenic bacteria through a neural network model according to the secondary predicted value of the total amount of the bacteria to obtain a corresponding secondary predicted value of the content of the specific pathogenic bacteria, wherein the secondary predicted value of the content of the specific pathogenic bacteria is a predicted value of the content of the treated specific pathogenic bacteria corresponding to the predicted value of the content of the specific pathogenic bacteria; according to a preset treatment strategy, predicting the content of the treated harmful byproducts through a neural network model to obtain a corresponding predicted value of the content of the harmful byproducts; and when the secondary predicted value of the total amount of bacteria, the secondary predicted value of the content of the specific pathogenic bacteria and the predicted value of the content of the harmful byproducts reach preset standards, determining a preset treatment strategy as a water quality treatment strategy.

In another embodiment, according to the total bacterial amount predicted value and/or the specific pathogenic bacterium content predicted value, the water quality treatment condition corresponding to the total bacterial amount predicted value and/or the specific pathogenic bacterium content predicted value is predicted and evaluated through a water quality ecological mechanism model and a neural network model, and a corresponding water quality treatment strategy is determined according to the prediction and evaluation result, and the method comprises the following steps:

when the total bacterial quantity predicted value exceeds the water quality health standard, predicting the regrowth condition of the treated bacteria through a water quality ecological mechanism model according to the total bacterial quantity predicted value and a preset treatment strategy to obtain a secondary predicted value of the total bacterial quantity; according to a preset treatment strategy, predicting the content of the treated harmful byproducts through a neural network model to obtain a corresponding predicted value of the content of the harmful byproducts; and when the secondary predicted value of the total amount of bacteria and the predicted value of the content of the harmful byproducts reach preset standards, determining a preset treatment strategy as a water quality treatment strategy.

when the content predicted value of the specific pathogenic bacteria exceeds the water quality health standard, predicting the regrowth condition of the treated bacteria through a water quality ecological mechanism model according to the total bacteria predicted value and a preset treatment strategy to obtain a secondary predicted value of the total bacteria; predicting the content of the corresponding specific pathogenic bacteria through a neural network model according to the secondary predicted value of the total amount of the bacteria to obtain a secondary predicted value of the content of the corresponding specific pathogenic bacteria; according to a preset treatment strategy, predicting the content of the treated harmful byproducts through a neural network model to obtain a corresponding predicted value of the content of the harmful byproducts; and when the secondary predicted value of the content of the specific pathogenic bacteria and the predicted value of the content of the harmful byproducts reach preset standards, determining a preset treatment strategy as a water quality treatment strategy.

In one embodiment, when the predetermined treatment strategy is determined to be a water quality treatment strategy, the adopted predetermined criterion may be specific parameter values, such as: setting a preset standard value of the total amount of bacteria As As, a preset standard value of the content of specific pathogenic bacteria As Bs, and a preset standard value of the content of harmful byproducts As Cs, then: when the secondary predicted value A of the total bacteria amount is lower than (or equal to) a preset standard value As, determining that the secondary predicted value of the total bacteria amount reaches the preset standard; when the secondary predicted value B of the content of the specific pathogenic bacteria is lower than (or equal to) a preset standard value Bs, determining that the secondary predicted value of the content of the specific pathogenic bacteria reaches a preset standard; and when the predicted value C of the content of the harmful byproducts is lower than (or equal to) a preset standard value Cs, determining that the predicted value of the content of the harmful byproducts reaches a preset standard.

In one embodiment, the corresponding predetermined criteria may be different for different water objects. For example: for the drinking water of daily life of people, the preset standard value of the content of the harmful byproducts can be set lower, so that the toxic byproducts are prevented from causing harm to human bodies. For the aquaculture water body, the preset standard value of the content of the specific pathogenic bacteria can be set lower, so that the specific pathogenic bacteria are prevented from influencing aquaculture products, and property loss is further prevented.

In one embodiment, an objective function for evaluating treatment effect may be used as a criterion for determining a preset treatment strategy as a water quality treatment strategy.

For example, the following table shows the secondary predicted value of the total bacterial amount, the secondary predicted value of the specific pathogenic bacteria content and the predicted value of the harmful byproduct content corresponding to different treatment strategies:

then the assessment of the effectiveness of the remediation can be performed by the following objective function:

Mi＝Ai*X+Bi*Y+Ci*Z

wherein M is a treatment effect evaluation result, X is a treatment effect evaluation parameter of bacteria, Y is a treatment effect evaluation parameter of specific pathogenic bacteria, Z is a treatment effect evaluation parameter of toxic by-products, and i represents a serial number which is a positive integer. The treatment effect evaluation parameter can be understood as a weight parameter, and in addition, the smaller the value of M is, the better the treatment effect of the treatment strategy is.

Further, different types of treatment effect evaluation parameters in the objective function can be adjusted according to different water body objects. For example: for drinking water in daily life of people, treatment effect evaluation parameters of toxic byproducts can be properly increased; for the water body of aquaculture, the evaluation parameters of the treatment effect of specific pathogenic bacteria can be properly increased.

In one embodiment, as shown in fig. 2, there is provided a water quality information processing method, including the steps of:

(1) acquiring a water quality ecological mechanism model, and constructing a neural network model for water quality information processing;

(2) carrying out parameter calibration and parameter verification on the water quality ecological mechanism model according to sample data, and adding bacterial regrowth parameters into the water quality ecological mechanism model, wherein the sample data comprises physical and chemical parameters and corresponding bacterial total amount change data;

(3) training a neural network model by taking the types of the specific pathogenic bacteria and the contents of the specific pathogenic bacteria corresponding to different total bacteria amounts as training data until the error between a predicted value of the content of the specific pathogenic bacteria obtained by the neural network model according to the current total bacteria amount and the actual content of the specific pathogenic bacteria corresponding to the current total bacteria amount is within a preset range;

(4) training the neural network model by taking different preset treatment strategies and corresponding harmful byproduct contents as training data until the error between a predicted value of the harmful byproduct content obtained by the neural network model according to the current treatment strategy and the actual harmful byproduct content corresponding to the current treatment strategy is within a preset range;

(5) when the water quality ecological mechanism model is adjusted through the step (2), the neural network model is trained through the steps (3) and (4), and the water quality detection parameters of the target water body are obtained after the water quality ecological mechanism model is adjusted and the neural network model is trained;

(6) predicting the change condition of the total bacteria amount through a water quality ecological mechanism model according to the physical and chemical parameters and the total bacteria amount, and obtaining a predicted value of the total bacteria amount of the target water body according to the total bacteria amount and the prediction result of the change condition;

predicting the content of the specific pathogenic bacteria through a neural network model according to the total bacterial quantity predicted value to obtain a predicted value of the content of the specific pathogenic bacteria in the target water body;

(7) judging whether the predicted value of the total amount of bacteria and/or the predicted value of the content of the specific pathogenic bacteria exceeds the standard or not; if yes, executing the step (8), and if not, determining that the target water body is a healthy water body;

(8) according to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value, performing prediction evaluation on the water quality treatment condition corresponding to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value through a water quality ecological mechanism model and a neural network model, and determining a corresponding water quality treatment strategy according to the prediction evaluation result;

(9) and outputting/displaying/pushing a message that the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value exceeds the standard and a corresponding water quality control strategy.

It should be understood that although the various steps in the flow charts of fig. 1-2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.

In one embodiment, as shown in fig. 3, there is provided a water quality information processing apparatus including: a parameter acquisition module 100, a content prediction module 200, and a policy making module 300.

The parameter obtaining module 100 is configured to obtain water quality detection parameters of the target water body, where the water quality detection parameters include: physical and chemical parameters and total bacterial count;

the content prediction module 200 is used for predicting the change condition of the total bacteria amount according to the physicochemical parameters and the total bacteria amount to obtain a predicted value of the total bacteria amount and a predicted value of the content of the specific pathogenic bacteria in the target water body;

the strategy formulation module 300 is used for determining a corresponding water quality treatment strategy according to the total bacterial amount predicted value and/or the specific pathogenic bacterium content predicted value when the total bacterial amount predicted value and/or the specific pathogenic bacterium content predicted value exceed the water quality health standard.

For specific limitations of the water quality information processing device, reference may be made to the above limitations of the water quality information processing method, which are not described herein again. All or part of each module in the water quality information processing device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, as shown in fig. 4, there is provided a water quality information processing system, including: a water quality monitoring device 410, a data transmission device 420 and a water quality management platform 430.

The water quality monitoring device 410 comprises a water quality monitoring device and a bacteria sensor, and is used for acquiring water quality detection parameters of the object water body through monitoring, wherein the water quality detection parameters comprise: physical and chemical parameters and total bacterial count;

the data transmission device 420 is used for transmitting the water quality detection parameters acquired by the water quality monitoring device 410 to the water quality management platform 430;

the water quality management platform 430 is used for predicting the change condition of the total amount of bacteria according to the physical and chemical parameters and the total amount of bacteria to obtain a predicted value of the total amount of bacteria and a predicted value of the content of specific pathogenic bacteria in the target water body; and when the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria exceed the water quality health standard, determining a corresponding water quality treatment strategy according to the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria.

For the definition of the water quality management platform 420, reference may be made to the above definition of the water quality information processing method, which is not described herein again.

The working process of the water quality information processing system in the embodiment comprises core links such as real-time on-site monitoring, data transmission, model simulation, early warning forecast, intelligent management and control, processing scheme optimization and system feedback, the system makes full use of the technology and advantages of the Internet of things, carries out intelligent supervision on the total amount of water body bacteria on the basis of the Internet of things and environmental big data, collects physical and chemical parameters and the total amount of bacteria in real time through a water quality monitoring device and a bacteria sensor, constructs a complex model by taking the collected environmental data as driving parameters, carries out near real-time prediction on future water quality changes, particularly on the total amount of bacteria and the content of specific pathogenic bacteria, provides early warning information for the upcoming bacteria overproof event, and provides a corresponding solution through a model optimization method, so that the influence caused by the overproof of the water body bacteria is reduced The method has the advantages of solving the problems of harming public health and safety of aquaculture industry, changing the current situations of traditional laboratory monitoring and post-treatment, filling the blank of no early warning mechanism and optimized treatment scheme in the field, and being widely applied to rivers, lakes, estuaries, seashore, fishponds, water supply, drainage, drinking water related to water resources and public places.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program: acquiring water quality detection parameters of the object water body, wherein the water quality detection parameters comprise: physical and chemical parameters and total bacterial count; predicting the change condition of the total amount of bacteria according to the physical and chemical parameters and the total amount of bacteria to obtain a predicted value of the total amount of bacteria and a predicted value of the content of specific pathogenic bacteria of the target water body; and when the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria exceed the water quality health standard, determining a corresponding water quality treatment strategy according to the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria.

In one embodiment, the processor, when executing the computer program, further performs the steps of: predicting the change condition of the total bacteria amount through a water quality ecological mechanism model according to the physical and chemical parameters and the total bacteria amount, and obtaining a predicted value of the total bacteria amount of the target water body according to the total bacteria amount and the prediction result of the change condition; and predicting the content of the specific pathogenic bacteria through a neural network model according to the total bacterial quantity predicted value to obtain the specific pathogenic bacteria content predicted value of the target water body.

In one embodiment, the processor, when executing the computer program, further implements any of:

the first item: adjusting, calibrating and verifying model parameters of the water quality ecological mechanism model according to sample data, and adding bacterial regrowth parameters into the water quality ecological mechanism model, wherein the sample data comprises physical and chemical parameters and corresponding bacterial total amount change data;

the second term is: training a neural network model by taking the types of the specific pathogenic bacteria and the content of the specific pathogenic bacteria corresponding to different total bacteria as training data; and when the error between the predicted value of the content of the specific pathogenic bacteria obtained by the neural network model according to the current total bacteria amount and the actual content of the specific pathogenic bacteria corresponding to the current total bacteria amount is within a preset range, determining that the training of the neural network model is finished.

In one embodiment, the processor, when executing the computer program, further performs the steps of: and according to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value, performing prediction evaluation on the water quality treatment condition corresponding to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value through a water quality ecological mechanism model and a neural network model, and determining a corresponding water quality treatment strategy according to the prediction evaluation result.

the first item: when the predicted value of the total amount of bacteria and the predicted value of the content of the specific pathogenic bacteria exceed the water quality health standard, predicting the regrowth condition of the treated bacteria through a water quality ecological mechanism model according to the predicted value of the total amount of bacteria and a preset treatment strategy to obtain a secondary predicted value of the total amount of bacteria, wherein the secondary predicted value of the total amount of bacteria is the predicted value of the total amount of the treated bacteria corresponding to the predicted value of the total amount of bacteria; predicting the content of the corresponding specific pathogenic bacteria through a neural network model according to the secondary predicted value of the total amount of the bacteria to obtain a corresponding secondary predicted value of the content of the specific pathogenic bacteria, wherein the secondary predicted value of the content of the specific pathogenic bacteria is a predicted value of the content of the treated specific pathogenic bacteria corresponding to the predicted value of the content of the specific pathogenic bacteria; according to a preset treatment strategy, predicting the content of the treated harmful byproducts through a neural network model to obtain a corresponding predicted value of the content of the harmful byproducts; when the secondary predicted value of the total amount of bacteria, the secondary predicted value of the content of the specific pathogenic bacteria and the predicted value of the content of the harmful byproducts reach preset standards, determining a preset treatment strategy as a water quality treatment strategy;

the second term is: when the total bacterial quantity predicted value exceeds the water quality health standard, predicting the regrowth condition of the treated bacteria through a water quality ecological mechanism model according to the total bacterial quantity predicted value and a preset treatment strategy to obtain a secondary predicted value of the total bacterial quantity; according to a preset treatment strategy, predicting the content of the treated harmful byproducts through a neural network model to obtain a corresponding predicted value of the content of the harmful byproducts; when the secondary predicted value of the total amount of bacteria and the predicted value of the content of harmful byproducts reach preset standards, determining a preset treatment strategy as a water quality treatment strategy;

the third item: when the content predicted value of the specific pathogenic bacteria exceeds the water quality health standard, predicting the regrowth condition of the treated bacteria through a water quality ecological mechanism model according to the total bacteria predicted value and a preset treatment strategy to obtain a secondary predicted value of the total bacteria; predicting the content of the corresponding specific pathogenic bacteria through a neural network model according to the secondary predicted value of the total amount of the bacteria to obtain a secondary predicted value of the content of the corresponding specific pathogenic bacteria; according to a preset treatment strategy, predicting the content of the treated harmful byproducts through a neural network model to obtain a corresponding predicted value of the content of the harmful byproducts; and when the secondary predicted value of the content of the specific pathogenic bacteria and the predicted value of the content of the harmful byproducts reach preset standards, determining a preset treatment strategy as a water quality treatment strategy.

In one embodiment, the processor, when executing the computer program, further performs the steps of: training a neural network model by taking different preset treatment strategies and corresponding harmful byproduct contents as training data; and when the error between the predicted value of the content of the harmful byproducts obtained by the neural network model according to the current treatment strategy and the actual content of the harmful byproducts corresponding to the current treatment strategy is within a preset range, determining that the training of the neural network model is finished.

In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring water quality detection parameters of the object water body, wherein the water quality detection parameters comprise: physical and chemical parameters and total bacterial count; predicting the change condition of the total amount of bacteria according to the physical and chemical parameters and the total amount of bacteria to obtain a predicted value of the total amount of bacteria and a predicted value of the content of specific pathogenic bacteria of the target water body; and when the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria exceed the water quality health standard, determining a corresponding water quality treatment strategy according to the predicted value of the total amount of the bacteria and/or the predicted value of the content of the specific pathogenic bacteria.

In one embodiment, the computer program when executed by the processor further performs the steps of: predicting the change condition of the total bacteria amount through a water quality ecological mechanism model according to the physical and chemical parameters and the total bacteria amount, and obtaining a predicted value of the total bacteria amount of the target water body according to the total bacteria amount and the prediction result of the change condition; and predicting the content of the specific pathogenic bacteria through a neural network model according to the total bacterial quantity predicted value to obtain the specific pathogenic bacteria content predicted value of the target water body.

In one embodiment, the computer program when executed by the processor further implements any of:

In one embodiment, the computer program when executed by the processor further performs the steps of: and according to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value, performing prediction evaluation on the water quality treatment condition corresponding to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value through a water quality ecological mechanism model and a neural network model, and determining a corresponding water quality treatment strategy according to the prediction evaluation result.

In one embodiment, the computer program when executed by the processor further performs the steps of: training a neural network model by taking different preset treatment strategies and corresponding harmful byproduct contents as training data; and when the error between the predicted value of the content of the harmful byproducts obtained by the neural network model according to the current treatment strategy and the actual content of the harmful byproducts corresponding to the current treatment strategy is within a preset range, determining that the training of the neural network model is finished.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, the computer program can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims

1. A water quality information processing method is characterized by comprising the following steps:

when the predicted value of the total amount of bacteria and/or the predicted value of the content of the specific pathogenic bacteria exceed the water quality health standard, performing prediction evaluation on the water quality treatment condition corresponding to the predicted value of the total amount of bacteria and/or the predicted value of the content of the specific pathogenic bacteria through a water quality ecological mechanism model and a neural network model according to the predicted value of the total amount of bacteria and/or the predicted value of the content of the specific pathogenic bacteria, and determining a corresponding water quality treatment strategy according to the prediction evaluation result;

according to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value, performing prediction evaluation on the water quality treatment condition corresponding to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value through a water quality ecological mechanism model and a neural network model, and determining a corresponding water quality treatment strategy according to a prediction evaluation result, wherein the method comprises the following steps:

when the predicted value of the total amount of bacteria and the predicted value of the content of the specific pathogenic bacteria exceed the water quality health standard, predicting the regrowth condition of the treated bacteria through the water quality ecological mechanism model according to the predicted value of the total amount of bacteria and a preset treatment strategy to obtain a secondary predicted value of the total amount of bacteria, wherein the secondary predicted value of the total amount of bacteria is a predicted value of the total amount of bacteria corresponding to the predicted value of the total amount of bacteria and after treatment;

and when the secondary predicted value of the total amount of bacteria, the secondary predicted value of the content of the specific pathogenic bacteria and the predicted value of the content of the harmful byproducts reach preset standards, determining the preset treatment strategy as the water quality treatment strategy.

2. The water quality information processing method according to claim 1, wherein the specific pathogenic bacteria are pathogenic bacteria corresponding to different application environments.

3. The water quality information processing method according to claim 2, wherein predicting the change of the total amount of bacteria according to the physicochemical parameter and the total amount of bacteria to obtain a predicted value of the total amount of bacteria and a predicted value of the content of specific pathogenic bacteria in the target water body comprises:

4. The water quality information processing method according to claim 3, comprising any one of:

5. The water quality information processing method according to claim 1, wherein the neural network model is obtained by training through the following steps:

6. A water quality information processing system, characterized by comprising: the water quality monitoring device, the data transmission device and the water quality management platform;

the water quality management platform is used for predicting the change condition of the total bacteria amount according to the physical and chemical parameters and the total bacteria amount to obtain a predicted value of the total bacteria amount and a predicted value of the content of specific pathogenic bacteria of the target water body; when the predicted value of the total amount of bacteria and/or the predicted value of the content of the specific pathogenic bacteria exceed the water quality health standard, performing prediction evaluation on the water quality treatment condition corresponding to the predicted value of the total amount of bacteria and/or the predicted value of the content of the specific pathogenic bacteria through a water quality ecological mechanism model and a neural network model according to the predicted value of the total amount of bacteria and/or the predicted value of the content of the specific pathogenic bacteria, and determining a corresponding water quality treatment strategy according to the prediction evaluation result;

according to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value, performing prediction evaluation on the water quality treatment condition corresponding to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value through a water quality ecological mechanism model and a neural network model, and determining a corresponding water quality treatment strategy according to a prediction evaluation result, wherein the method comprises the following steps: when the predicted value of the total amount of bacteria and the predicted value of the content of the specific pathogenic bacteria exceed the water quality health standard, predicting the regrowth condition of the treated bacteria through the water quality ecological mechanism model according to the predicted value of the total amount of bacteria and a preset treatment strategy to obtain a secondary predicted value of the total amount of bacteria, wherein the secondary predicted value of the total amount of bacteria is a predicted value of the total amount of bacteria corresponding to the predicted value of the total amount of bacteria and after treatment; predicting the content of the corresponding specific pathogenic bacteria through the neural network model according to the secondary predicted value of the total amount of the bacteria to obtain a corresponding secondary predicted value of the content of the specific pathogenic bacteria, wherein the secondary predicted value of the content of the specific pathogenic bacteria is a predicted value of the content of the treated specific pathogenic bacteria corresponding to the predicted value of the content of the specific pathogenic bacteria; according to the preset treatment strategy, predicting the content of the treated harmful byproducts through the neural network model to obtain a corresponding predicted value of the content of the harmful byproducts; and when the secondary predicted value of the total amount of bacteria, the secondary predicted value of the content of the specific pathogenic bacteria and the predicted value of the content of the harmful byproducts reach preset standards, determining the preset treatment strategy as the water quality treatment strategy.

7. A water quality information processing method is characterized by comprising the following steps:

when the total bacterial quantity predicted value exceeds the water quality health standard, predicting the regrowth condition of the treated bacteria through the water quality ecological mechanism model according to the total bacterial quantity predicted value and a preset treatment strategy to obtain a secondary predicted value of the total bacterial quantity;

and when the secondary predicted value of the total amount of bacteria and the predicted value of the content of the harmful byproducts reach preset standards, determining the preset treatment strategy as the water quality treatment strategy.

8. The water quality information processing method according to claim 7, wherein the specific pathogenic bacteria are pathogenic bacteria corresponding to different application environments.

9. The water quality information processing method according to claim 8, wherein predicting a change of the total amount of bacteria based on the physicochemical parameter and the total amount of bacteria to obtain a predicted value of the total amount of bacteria and a predicted value of a content of specific pathogenic bacteria in the target water body comprises:

10. The water quality information processing method according to claim 9, comprising any one of:

11. The water quality information processing method according to claim 7, wherein the neural network model is trained by the following steps:

12. A water quality information processing system, characterized by comprising: the water quality monitoring device, the data transmission device and the water quality management platform;

when the total bacterial quantity predicted value exceeds the water quality health standard, predicting the regrowth condition of the treated bacteria through the water quality ecological mechanism model according to the total bacterial quantity predicted value and a preset treatment strategy to obtain a secondary predicted value of the total bacterial quantity; according to the preset treatment strategy, predicting the content of the treated harmful byproducts through the neural network model to obtain a corresponding predicted value of the content of the harmful byproducts; and when the secondary predicted value of the total amount of bacteria and the predicted value of the content of the harmful byproducts reach preset standards, determining the preset treatment strategy as the water quality treatment strategy.

13. A water quality information processing method is characterized by comprising the following steps:

when the predicted value of the content of the specific pathogenic bacteria exceeds the water quality health standard, predicting the regrowth condition of the treated bacteria through the water quality ecological mechanism model according to the predicted value of the total bacteria amount and a preset treatment strategy to obtain a secondary predicted value of the total bacteria amount;

14. The water quality information processing method according to claim 13, wherein the specific pathogenic bacteria are pathogenic bacteria corresponding to different application environments.

15. The water quality information processing method according to claim 14, wherein predicting a change of the total amount of bacteria based on the physicochemical parameter and the total amount of bacteria to obtain a predicted value of the total amount of bacteria and a predicted value of a content of specific pathogenic bacteria in the target water body comprises:

16. The water quality information processing method according to claim 15, comprising any one of:

17. The water quality information processing method according to claim 13, wherein the neural network model is trained by the following steps:

18. A water quality information processing system, characterized by comprising: the water quality monitoring device, the data transmission device and the water quality management platform;

according to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value, performing prediction evaluation on the water quality treatment condition corresponding to the total bacterial quantity predicted value and/or the specific pathogenic bacterium content predicted value through a water quality ecological mechanism model and a neural network model, and determining a corresponding water quality treatment strategy according to a prediction evaluation result, wherein the method comprises the following steps: when the predicted value of the content of the specific pathogenic bacteria exceeds the water quality health standard, predicting the regrowth condition of the treated bacteria through the water quality ecological mechanism model according to the predicted value of the total bacteria amount and a preset treatment strategy to obtain a secondary predicted value of the total bacteria amount; predicting the content of the corresponding specific pathogenic bacteria through the neural network model according to the secondary predicted value of the total amount of the bacteria to obtain a corresponding secondary predicted value of the content of the specific pathogenic bacteria; according to the preset treatment strategy, predicting the content of the treated harmful byproducts through the neural network model to obtain a corresponding predicted value of the content of the harmful byproducts; and when the secondary predicted value of the content of the specific pathogenic bacteria and the predicted value of the content of the harmful byproducts reach preset standards, determining the preset treatment strategy as the water quality treatment strategy.

19. A computer apparatus comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the water quality information processing method according to any one of claims 1 to 5, 7 to 11, and 13 to 17 when executing the computer program.

20. A computer-readable storage medium on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the steps of the water quality information processing method according to any one of claims 1 to 5, 7 to 11, and 13 to 17.