Water quality evaluation method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of water treatment, and discloses a water quality evaluation method and device, computer equipment and a storage medium. Performing comprehensive analysis on the water quality analysis result to determine the weight ratio of the water quality index in the water quality analysis result; determining a target index based on the weight ratio of the water quality index; and determining a water quality evaluation result based on the target evaluation model and the target index. According to the method, the weight ratio of the water quality indexes is objectively determined by obtaining the water quality analysis result in the target area and comprehensively analyzing the water quality analysis result, and the weight ratio of each water quality index can be more objectively determined by a weight distribution mode based on data driving, so that the target index can be conveniently determined, and the water quality evaluation model can be conveniently obtained; and the accuracy and objectivity of an output result are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of water treatment, and in particular to a water quality evaluation method, device, computer equipment and storage medium. Background Art

[0002] Water quality evaluation is an important part of the field of water treatment technology. Water quality evaluation refers to the selection of corresponding water quality parameters, water quality standards and evaluation methods according to the evaluation objectives, and the evaluation of the quality utilization value of water bodies and water treatment requirements. Water quality evaluation is not only a key tool for environmental protection and water resources management, but also a basis for protecting human health and promoting sustainable economic development. There are many water quality evaluation methods, such as index evaluation method, fuzzy evaluation method, gray evaluation method, matter element analysis method and artificial neural network method. Among them, artificial neural network method is a nonlinear simulation technology that can be applied to multiple disciplines. Its advantages are large-scale parallel processing, distributed storage, adaptability, fault tolerance, etc., and it is widely used in many fields such as pattern recognition, intelligent control, knowledge processing and prediction. It is one of the most active frontier disciplines at present, especially suitable for processing nonlinear systems. The disadvantage is that when applied to water quality evaluation, the selection of training sample indicators is relatively subjective, and when all water quality analysis results are used for artificial neural network calculations, unnecessary calculations will be time-consuming and labor-intensive. Summary of the invention

[0003] In view of this, the present invention provides a water quality evaluation method, device, computer equipment and storage medium to solve the problem of long time consumption in the water quality evaluation process.

[0004] In a first aspect, the present invention provides a method for evaluating water quality, the method comprising:

[0005] Obtain water quality analysis results within the target area;

[0006] Conduct a comprehensive analysis on the water quality analysis results to determine the weight of the water quality indicators in the water quality analysis results;

[0007] Determine the target indicator based on the weight ratio of the water quality indicator;

[0008] The water quality evaluation result is determined based on the target evaluation model and the target indicators.

[0009] In an optional implementation, the water quality analysis result includes at least one analysis result of a water quality indicator, and the analysis result includes at least a first preset amount of data.

[0010] In an optional implementation, the comprehensive analysis of the water quality analysis results to determine the weight ratio of the water quality indicators in the water quality analysis results includes:

[0011] Determine the water quality analysis result matrix based on water quality indicators and evaluation objects;

[0012] The entropy of the water quality index is defined based on the elements in the water quality analysis result matrix, and the entropy weight of the water quality index is calculated to determine the weight ratio of the water quality index according to the entropy weight.

[0013] In an optional implementation, the entropy of the water quality indicator is determined according to the following formula:

[0014]

[0015] in, Represents the elements in the water quality analysis result matrix, H i represents the entropy of the i-th water quality index, k = 1 / lnn, there are n evaluation objects, m water quality indexes, i = 1, 2, 3, ..., m, j = 1, 2, 3, ..., n, when f ij = 0, f ij lnf ij =0;

[0016] The entropy weight of the water quality index is determined according to the following formula:

[0017]

[0018] Among them, w i represents the entropy weight of the i-th water quality index, 0≤w i ≤1.

[0019] In an optional implementation, determining the target indicator based on the weight ratio of the water quality indicator includes:

[0020] The water quality indicators whose weights exceed the preset weight thresholds are determined as target indicators.

[0021] In an optional implementation, determining the water quality evaluation result based on the target evaluation model and the target indicator includes:

[0022] Establishing a target evaluation model according to the target indicators;

[0023] The water quality evaluation result is output based on the target evaluation model.

[0024] In an optional implementation, establishing a target evaluation model according to the target indicator includes:

[0025] Obtaining the level and training samples corresponding to the target indicator, and normalizing the training samples;

[0026] An evaluation model is established and trained to obtain a trained target evaluation model, wherein the input layer neurons of the target evaluation model correspond to the target indicator, and the output layer neurons of the target evaluation model are used to output the ideal value of the target indicator.

[0027] The water quality evaluation method provided in this embodiment includes obtaining the water quality analysis results in the target area; conducting a comprehensive analysis of the water quality analysis results to determine the weight ratio of the water quality index in the water quality analysis results; determining the target index based on the weight ratio of the water quality index; and determining the water quality evaluation results based on the target evaluation model and the target index. This method obtains the water quality analysis results in the target area and conducts a comprehensive analysis thereof, thereby objectively determining the weight ratio of the water quality index. This data-driven weight allocation method can more objectively determine the weight ratio of each water quality index, thereby facilitating the determination of the target index, obtaining the water quality evaluation model, and improving the accuracy and objectivity of the output results.

[0028] In a second aspect, the present invention provides a water quality evaluation device, the device comprising:

[0029] An analysis result acquisition module is used to obtain water quality analysis results in the target area;

[0030] A proportion determination module is used to perform a comprehensive analysis on the water quality analysis results to determine the weight proportion of the water quality indicators in the water quality analysis results;

[0031] A target indicator determination module, used to determine the target indicator based on the weight ratio of the water quality indicator;

[0032] The evaluation result determination module is used to determine the water quality evaluation result based on the target evaluation model and the target indicator.

[0033] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the water quality evaluation method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0034] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the water quality assessment method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 is a schematic flow chart of a water quality evaluation method according to an embodiment of the present invention;

[0037] Figure 2 is a schematic diagram of another water quality evaluation method according to an embodiment of the present invention;

[0038] Figure 3 is a structural block diagram of a water quality evaluation device according to an embodiment of the present invention;

[0039] Figure 4 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0041] Scientifically constructing water quality evaluation methods is an important part of the water treatment field. Since its emergence, artificial neural network methods have been rapidly developed and applied. Their significant advantages include large-scale parallel processing capabilities, distributed storage, high adaptability and strong fault tolerance. These characteristics have made artificial neural networks widely used in many fields such as pattern recognition, intelligent control, knowledge processing and prediction, and have become one of the most active frontier disciplines. Especially for processing complex nonlinear systems, artificial neural networks have shown unique advantages. However, when artificial neural networks are applied to water quality evaluation, there are also some challenges. First, the selection of training sample indicators is often highly subjective, which may affect the accuracy and reliability of the evaluation results. Secondly, if all water quality analysis results are included in the calculation process of the artificial neural network, not only will unnecessary calculations be increased, but more time and resources will also be consumed. Based on this, the present invention provides a water quality evaluation method that can scientifically select training indicators, reduce unnecessary time and energy consumption, and make water quality evaluation results more scientific and objective.

[0042] According to an embodiment of the present invention, a water quality assessment method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0043] In this embodiment, a water quality evaluation method is provided, which can be applied to terminals such as computers, tablet computers, and mobile phones. Figure 1 is a flow chart of a water quality evaluation method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0044] Step S101, obtaining water quality analysis results in a target area.

[0045] The target area is a specific water area. The water quality analysis results in the target area are collected, and the analysis results of as many indicators as possible are obtained in order to comprehensively analyze the water quality of the target water area.

[0046] In some optional implementations, the water quality analysis result includes at least one analysis result of a water quality indicator, and the analysis result includes at least a first preset amount of data.

[0047] Water quality indicators are indicator parameters used to evaluate water quality. First, the water quality indicators that need to be analyzed can be clearly identified. Water quality indicators can cover various aspects of water quality, including but not limited to physical properties, chemical properties, microbial properties, and radioactive substances. For example, water quality indicators may include temperature, pH value, conductivity, dissolved oxygen, biochemical oxygen demand, etc. In this embodiment, it is necessary to obtain water quality analysis results of one or more water quality indicators. Each water quality indicator includes a first preset number of data, and the first preset number can be set according to demand. In addition, the analysis interval of the data corresponding to the water quality indicator can also be set.

[0048] As an example, each water quality indicator includes at least 10 sets of data, and the analysis interval of each set of data is 1-2 months, so that more water quality changes can be obtained. The same set of data for each water quality indicator needs to be analyzed by multiple samples and tested by at least three detection instruments, and the final results are averaged to reduce equipment errors.

[0049] The following is a detailed explanation. In order to capture the changes in water quality over time, at least 10 sets of data should be collected for each water quality indicator, and the analysis interval for each set of data is 1-2 months, so that seasonal changes can be captured and long-term trends in water quality can be reflected. In terms of sampling locations, multiple representative sampling points are selected in the target area, such as upstream and downstream of rivers, different areas of lakes, nearshore and farshore, etc. Depending on the water depth, water samples of different depths are collected at each sampling point to understand the differences in water quality in the vertical direction.

[0050] Step S102, comprehensively analyzing the water quality analysis results to determine the weight ratio of the water quality indicators in the water quality analysis results.

[0051] After obtaining the water quality analysis results, a comprehensive analysis is performed on the water quality analysis results, thereby weighting each water quality index to reflect the importance of these water quality indexes in water quality evaluation. In some optional implementations, the entropy weight method, the coefficient of variation method, and other methods can be used to determine the weight ratio of water quality indexes.

[0052] Specifically, taking the entropy weight method as an example, the comprehensive analysis process includes calculating the entropy value of each indicator, using the concept of information entropy to calculate the entropy value of each indicator. The larger the entropy value, the greater the amount of information provided by the indicator, and the greater the impact on the evaluation result. The weight of each water quality indicator is determined according to the calculated entropy value.

[0053] Step S103, determining the target index based on the weight ratio of the water quality index.

[0054] After determining the weights of water quality indicators, we can further select target indicators that have a significant impact on water quality evaluation. The target indicators can be one or more indicators with large weights that have a significant impact on water quality. By determining the target indicators, we can focus on the most critical water quality issues, thereby more effectively managing and improving water quality.

[0055] Step S104, determining a water quality evaluation result based on the target evaluation model and the target index.

[0056] The target evaluation model is an artificial neural network evaluation model. First, a target evaluation model needs to be trained for water quality evaluation. After determining the target indicator, standard division is carried out to determine the evaluation level of the target indicator. When the target indicator is not clearly divided into grades in the standard, it is necessary to divide it according to the annual average value range of the water body in the target area.

[0057] For example, after determining the target indicator, it is necessary to set clear standards to evaluate the quality of the target indicator. The standards can be divided into different evaluation levels, and different evaluation levels can correspond to different indicator value ranges. If the existing standards do not clearly provide the evaluation level division of the target indicator, it is divided according to the annual average value of the water body in the target area. Therefore, the values ​​of the target indicator in the water body in the target area within a certain period of time can be collected and analyzed, and then the corresponding average value interval is determined, and the evaluation level is divided according to the average value interval.

[0058] When establishing the target evaluation model, the input layer and output layer of the artificial neural network evaluation model are established according to the needs. The input layer corresponds to the target indicator, and the output layer corresponds to the ideal expected value of the target indicator, which can correspond to the evaluation level of the target indicator above. Select an appropriate method to determine the number of neurons in the hidden layer, and determine the number of neurons in the hidden layer through repeated simulations, so as to establish the artificial neural network model structure of the target evaluation model.

[0059] Appropriate functions can be selected to calculate the target evaluation model, including the model training function, network learning function and performance function. After model training, the target evaluation model is determined, and then the water quality evaluation results are output according to the target evaluation model.

[0060] The water quality evaluation method provided in this embodiment includes obtaining the water quality analysis results in the target area; conducting a comprehensive analysis of the water quality analysis results to determine the weight ratio of the water quality index in the water quality analysis results; determining the target index based on the weight ratio of the water quality index; and determining the water quality evaluation results based on the target evaluation model and the target index. This method obtains the water quality analysis results in the target area and conducts a comprehensive analysis thereof, thereby objectively determining the weight ratio of the water quality index. This data-driven weight allocation method can more objectively determine the weight ratio of each water quality index, thereby facilitating the determination of the target index, obtaining the water quality evaluation model, and improving the accuracy and objectivity of the output results.

[0061] In some optional implementations, step S103 includes: determining the water quality index whose weight ratio exceeds a preset weight threshold as the target index.

[0062] The water quality indicators whose weights exceed the preset weight threshold are determined as target indicators, which means that in the comprehensive water quality evaluation process, the weight threshold is set as a screening criterion. When the weight of a water quality indicator is higher than the weight threshold, the corresponding water quality indicator is regarded as a key factor that has a significant impact on the water quality status, and is therefore determined as a target indicator. The target indicator can be used as a key factor in subsequent model training, which helps to identify and solve water quality problems more accurately.

[0063] In this embodiment, a water quality evaluation method is provided, which can be applied to terminals such as computers, tablet computers, and mobile phones. The method includes the following steps:

[0064] Step S201, obtaining water quality analysis results in the target area.

[0065] For details, please see Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0066] Step S202: Comprehensively analyze the water quality analysis results to determine the weight of the water quality indicators in the water quality analysis results.

[0067] Specifically, the above step S202 includes:

[0068] Step S2021, determining a water quality analysis result matrix based on water quality indicators and evaluation objects.

[0069] A water quality analysis result matrix is ​​established based on water quality indicators and the evaluation objects of water quality indicators. Water quality indicators are various parameters used to evaluate water quality. Water quality indicators may include parameters of multiple dimensions of water quality evaluation, such as dissolved oxygen, chemical oxygen demand, ammonia nitrogen, total phosphorus, etc. The evaluation object refers to the object of water quality evaluation in the target area (such as a water body).

[0070] In some optional implementations, a water quality analysis result matrix consisting of m water quality indicators and n evaluation objects is established.

[0071] Step S2022, defining the entropy of the water quality index based on the elements in the water quality analysis result matrix, and calculating the entropy weight of the water quality index to determine the weight ratio of the water quality index according to the entropy weight.

[0072] In some optional implementations, before executing step S2022, the water quality analysis result matrix needs to be standardized to eliminate the problem that different dimensions and types of different water quality indicators are difficult to compare. Specifically, the water quality indicators can be normalized to a dimensionless interval, thereby converting the water quality analysis result matrix into a standardized matrix.

[0073] For example, the normalization matrix is ​​R=(r ij ) m×n , where r ij Represents the elements in the normalized matrix, 0≤r ij ≤1, m represents the number of water quality indicators, and n represents the number of evaluation objects.

[0074] In some optional implementations, the entropy of the water quality indicator is determined according to the following formula:

[0075]

[0076] in, r ij Represents the elements in the water quality analysis result matrix, H i represents the entropy of the i-th water quality index, k = 1 / lnn, there are n evaluation objects, m water quality indexes, i = 1, 2, 3, ..., m, j = 1, 2, 3, ..., n, when f ij = 0, f ij lnf ij =0.

[0077] The entropy weight of the water quality index is determined according to the following formula:

[0078]

[0079] Among them, w i represents the entropy weight of the i-th water quality index, 0≤w i ≤1.

[0080] After calculating the entropy weight of the water quality index, the entropy weight is used as the weight ratio of the water quality index.

[0081] Step S203, determining the target index based on the weight ratio of the water quality index.

[0082] For details, please see Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0083] Step S204, determining a water quality evaluation result based on the target evaluation model and the target index.

[0084] For details, please see Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0085] The water quality evaluation method provided in this embodiment adopts the entropy weight method to determine the weight ratio of the water quality index, so that the determined target index is more objective and the error of the final result is reduced.

[0086] In this embodiment, a water quality evaluation method is provided, which can be applied to terminals such as computers, tablet computers, and mobile phones. The method includes the following steps:

[0087] Step S301, obtaining water quality analysis results in the target area.

[0088] Step S302: Comprehensively analyze the water quality analysis results to determine the weight of the water quality indicators in the water quality analysis results.

[0089] Step S303, determining the target index based on the weight ratio of the water quality index.

[0090] For details, please see Figure 1Steps S101 to S103 of the illustrated embodiment will not be described in detail here.

[0091] Step S304: determining a water quality evaluation result based on the target evaluation model and the target indicator.

[0092] Specifically, the above step S304 includes:

[0093] Step S3041, establishing a target evaluation model according to the target indicators.

[0094] A target evaluation model is established, which is an artificial neural network model, including an input layer, an output layer, and a hidden layer, etc. Among them, the neurons in the input layer correspond to the target indicators.

[0095] In some optional implementations, step S3041 includes:

[0096] Step a1, obtain the level and training samples corresponding to the target indicator, and normalize the training samples.

[0097] Step a2: establish an evaluation model and train the evaluation model to obtain a trained target evaluation model.

[0098] Among them, the input layer neurons of the target evaluation model correspond to the target indicator, and the output layer neurons of the target evaluation model are used to output the ideal value of the target indicator.

[0099] After determining the target indicators, standard division is carried out to determine the evaluation level of the target indicators. When the target indicators are not clearly divided into levels in the standards, they need to be divided according to the annual average value range of the water bodies in the target area.

[0100] For example, after determining the target indicator, it is necessary to set clear standards to evaluate the quality of the target indicator. The standards can be divided into different evaluation levels, and different evaluation levels can correspond to different indicator value ranges. If the existing standards do not clearly provide the evaluation level division of the target indicator, it is divided according to the annual average value of the water body in the target area. Therefore, the values ​​of the target indicator in the water body in the target area within a certain period of time can be collected and analyzed, and then the corresponding average value interval is determined, and the evaluation level is divided according to the average value interval.

[0101] The level corresponding to the target indicator is the above-mentioned evaluation level. To establish the training sample of the target indicator, the original matrix can be established based on the training sample, and the original matrix can be standardized to eliminate the problem of different dimensions and types of indicators being difficult to compare, and the indicator parameters can be normalized to a certain dimensionless interval to obtain a standardized matrix, thereby realizing the normalization of the training samples.

[0102] An evaluation model is established, in which the input layer neurons of the model correspond to the target index, and the output layer uses one neuron to determine the ideal value of the selected target index to correspond to the evaluation level of the water quality index. Specifically, a suitable method is selected to determine the number of neurons in the hidden layer, and the number of neurons in the hidden layer is determined by repeated simulation, thereby determining the artificial neural network model structure of the evaluation model.

[0103] To select a suitable function and perform evaluation model calculation, it is necessary to determine the training function, network learning function, and performance function.

[0104] In some optional implementations, the transfer between the input layer and the hidden layer uses the logsig function (S-type logarithmic function, an activation function), the transfer between the hidden layer and the output layer uses the purelin function (identity mapping function, an activation function), and the training result is obtained by the trainlm function (Levenberg-Marquardt, a training function of the back propagation neural network). After training, the target evaluation model is obtained.

[0105] It should be noted that when the error between the actual output value and the expected value is too large and does not meet the requirements, it is necessary to switch to the error direction propagation calculation, propagate the error value back layer by layer along the training path, and correct the connection weights of each layer layer by layer, so that the relative error between the ideal expected value and the actual output value meets the requirements. After the training is completed, the adjusted weights are recorded for calculation. In the above training parameter settings, the training error is as small as possible to ensure that the relative error between the actual output value and the ideal expected value is less than 1%.

[0106] Step S3042: output water quality evaluation results based on the target evaluation model.

[0107] After obtaining the target evaluation model, the water quality evaluation result output by the target evaluation model is obtained.

[0108] The present invention provides a method for evaluating water quality. Figure 2 As shown, including the following:

[0109] Obtain the water quality analysis results of the target area; use the entropy weight method to comprehensively analyze the water quality; obtain the weight ratio of each water quality index in the water quality; select the target index according to the weight ratio; calculate the artificial neural network model based on the target index; determine the water quality evaluation results through model calculation. Among them, analyzing water quality through the entropy weight method includes: a) establishing the original matrix of water quality analysis results; b) standardizing the original matrix; c) entropy defining the standardized original matrix; d) performing entropy weight calculation. Artificial neural network model calculation includes: 1) dividing the evaluation criteria; 2) establishing the target index training samples and performing normalization processing; 3) establishing the target index artificial neural network model; 4) selecting a function for model calculation.

[0110] The water quality evaluation method provided in this embodiment overcomes the problem of heavy subjectivity in the selection of artificial neural network training sample indicators and the problem of time-consuming and labor-intensive calculation when all water quality analysis results are used for artificial neural network calculation. The artificial neural network model calculation and the entropy weight method are combined to train the target evaluation model and objectively determine the weight ratio of water quality indicators. This data-driven weight distribution method can more objectively determine the weight ratio of each water quality indicator, thereby facilitating the determination of the target indicator, obtaining the water quality evaluation model, improving the calculation efficiency, and enhancing the accuracy and objectivity of the output results.

[0111] In the present embodiment, a water quality evaluation device is also provided, which is used to implement the above-mentioned embodiments and implementation methods, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0112] This embodiment provides a water quality evaluation device, such as Figure 3 As shown, including:

[0113] Analysis result acquisition module 401, used to obtain water quality analysis results in the target area;

[0114] A proportion determination module 402 is used to perform a comprehensive analysis on the water quality analysis results to determine the weight proportion of the water quality indicators in the water quality analysis results;

[0115] A target indicator determination module 403 is used to determine the target indicator based on the weight ratio of the water quality indicator;

[0116] The evaluation result determination module 404 is used to determine the water quality evaluation result based on the target evaluation model and the target indicator.

[0117] In some optional implementations, the water quality analysis result includes at least one analysis result of a water quality indicator, and the analysis result includes at least a first preset amount of data.

[0118] In some optional implementations, the proportion determination module 402 includes:

[0119] A matrix determination unit, used for determining a water quality analysis result matrix based on water quality indicators and evaluation objects;

[0120] A proportion determination unit is used to define the entropy of the water quality index based on the elements in the water quality analysis result matrix, and calculate the entropy weight of the water quality index to determine the weight proportion of the water quality index according to the entropy weight.

[0121] In some optional implementations, the entropy of the water quality indicator is determined according to the following formula:

[0122]

[0123] in, r ij Represents the elements in the water quality analysis result matrix, H i represents the entropy of the i-th water quality index, k = 1 / lnn, there are n evaluation objects, m water quality indexes, i = 1, 2, 3, ..., m, j = 1, 2, 3, ..., n, when f ij = 0, f ij lnf ij =0;

[0124] The entropy weight of the water quality index is determined according to the following formula:

[0125]

[0126] Among them, w i represents the entropy weight of the i-th water quality index, 0≤w i ≤1.

[0127] In some optional implementations, the target indicator determination module 403 includes:

[0128] The target indicator determination unit is used to determine the water quality indicator whose weight ratio exceeds the preset weight threshold as the target indicator.

[0129] In some optional implementations, the evaluation result determination module 404 includes:

[0130] A model building unit, used to build a target evaluation model according to the target indicator;

[0131] A result output unit is used to output a water quality evaluation result based on the target evaluation model.

[0132] In some optional embodiments, the model building unit includes:

[0133] A normalization processing subunit, used to obtain the level and training samples corresponding to the target indicator, and perform normalization processing on the training samples;

[0134] The model determination subunit is used to establish an evaluation model and train the evaluation model to obtain a trained target evaluation model, wherein the input layer neurons of the target evaluation model correspond to the target indicator, and the output layer neurons of the target evaluation model are used to output the ideal value of the target indicator.

[0135] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0136] The water quality evaluation device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0137] The embodiment of the present invention also provides a computer device having the above Figure 3 The water quality evaluation device shown.

[0138] See also Figure 4 , Figure 4 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 4 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 A processor 10 is taken as an example.

[0139] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0140] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0141] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0142] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0143] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0144] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0145] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the present invention.

Claims

1. A water quality evaluation method, characterized in that: The method comprises: Obtain water quality analysis results within the target area; Conduct a comprehensive analysis on the water quality analysis results to determine the weight of the water quality indicators in the water quality analysis results; Determine the target indicator based on the weight ratio of the water quality indicator; The water quality evaluation result is determined based on the target evaluation model and the target indicators.

2. The method according to claim 1, characterized in that The water quality analysis result includes at least one analysis result of a water quality index, and the analysis result includes at least a first preset amount of data.

3. The method according to claim 1, characterized in that The comprehensive analysis of the water quality analysis results to determine the weight of water quality indicators in the water quality analysis results includes: Determine the water quality analysis result matrix based on water quality indicators and evaluation objects; The entropy of the water quality index is defined based on the elements in the water quality analysis result matrix, and the entropy weight of the water quality index is calculated to determine the weight ratio of the water quality index according to the entropy weight.

4. The method according to claim 3, characterized in that The entropy of the water quality index is determined according to the following formula: in, r ij Represents the elements in the water quality analysis result matrix, H i Represents the entropy of the i-th water quality index, k = 1 / lnn, there are n evaluation objects, m water quality indicators, i = 1, 2, 3, ..., m, j = 1, 2, 3, ..., n, when f ij = 0, f ij lnf ij =0; The entropy weight of the water quality index is determined according to the following formula: Among them, w i represents the entropy weight of the i-th water quality index, 0≤w i ≤1.

5. The method according to claim 1, characterized in that The target indicator is determined based on the weight ratio of the water quality indicator, including: The water quality indicators whose weights exceed the preset weight thresholds are determined as target indicators.

6. The method according to claim 1, characterized in that The determining of the water quality evaluation result based on the target evaluation model and the target indicator includes: Establishing a target evaluation model according to the target indicators; The water quality evaluation result is output based on the target evaluation model.

7. The method according to claim 6, characterized in that The step of establishing a target evaluation model according to the target indicator comprises: Obtaining the level and training samples corresponding to the target indicator, and normalizing the training samples; An evaluation model is established and trained to obtain a trained target evaluation model, wherein the input layer neurons of the target evaluation model correspond to the target indicator, and the output layer neurons of the target evaluation model are used to output the ideal value of the target indicator.

8. A water quality evaluation device, characterized in that: The device comprises: An analysis result acquisition module is used to obtain water quality analysis results in the target area; A proportion determination module is used to perform a comprehensive analysis on the water quality analysis results to determine the weight proportion of the water quality indicators in the water quality analysis results; A target indicator determination module, used to determine the target indicator based on the weight ratio of the water quality indicator; The evaluation result determination module is used to determine the water quality evaluation result based on the target evaluation model and the target indicator.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the water quality assessment method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the water quality evaluation method according to any one of claims 1 to 7.

Images