Water quality prediction method, device, equipment, medium and computer program product

By standardizing the water quality index library and weighting, and calculating the comprehensive water quality score step by step, the problem of low accuracy of existing water quality prediction solutions is solved, and the accuracy and data independence of water quality prediction are improved.

CN119090327APending Publication Date: 2024-12-06SHANDONG VOCATIONAL COLLEGE OF ECONOMICS & TRADE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411051876.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing water quality prediction schemes through neural networks and machine learning methods have low prediction accuracy, and rely on the accuracy of collecting water quality data, and cannot provide reliable predictions without ensuring data accuracy.

Method used

By standardizing the final indexes in the multi-level water quality index database and empowering comprehensive weights, calculating the index scores and weights at each level step by step, and finally determining the comprehensive water quality score to improve the accuracy of water quality prediction.

Benefits of technology

Improve the accuracy of water quality prediction, reduce dependence on collected data, and enhance prediction capabilities under uncertain data conditions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119090327A_ABST
    Figure CN119090327A_ABST
Patent Text Reader

Abstract

The invention provides a water quality prediction method, device and equipment, a medium and a computer program product, and the method comprises the steps: carrying out the standardized scoring processing of a last-stage index in a multi-stage water quality index library, and obtaining a last-stage index score; the multi-stage water quality index library is constructed based on historical detection data of a to-be-predicted water resource; determining a final-stage index comprehensive weight based on a preset water quality comparison index and the final-stage index score; based on the final-stage index score and the final-stage index comprehensive weight, sequentially determining each-stage index score and each-stage index comprehensive weight; and determining a water quality comprehensive score according to the primary index score and the primary index comprehensive weight, and predicting the to-be-predicted water resource based on the water quality comprehensive score to obtain a water quality prediction result. The water resource to be predicted is predicted through the water quality comprehensive score obtained through step-by-step calculation of the multi-stage water quality indexes, and the accuracy of water quality prediction is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] The quality of water resources is a key factor for environmental assessment, aquaculture and residential water use. Most existing water quality prediction schemes are processed through neural networks and machine learning. However, both neural networks and machine learning require a large amount of data for training, which is time-consuming and costly. In addition, the neural network and machine learning methods rely on the accuracy of the collected water quality data. If the accuracy of the collected water quality data cannot be guaranteed, the existing water quality prediction schemes through neural networks and machine learning have low prediction accuracy. Summary of the invention

[0003] The present invention provides a water quality prediction method, device, equipment, medium and computer program product, which are used to solve the defect of low prediction accuracy in existing water quality prediction schemes through neural networks and machine learning, and achieve improved water quality prediction accuracy.

[0004] The present invention provides a water quality prediction method, comprising the following steps.

[0005] Performing standardized scoring processing on the final level indicators in the multi-level water quality indicator library to obtain final level indicator scores; the multi-level water quality indicator library is constructed based on historical detection data of water resources to be predicted; Determining the comprehensive weight of the final-level indicator based on the preset water quality comparison indicator and the final-level indicator score; Based on the final indicator score and the final indicator comprehensive weight, sequentially determine the indicator scores and comprehensive weights of each level; A comprehensive water quality score is determined according to the primary indicator score and the comprehensive weight of the primary indicators, and the water resources to be predicted are predicted based on the comprehensive water quality score to obtain a water quality prediction result.

[0006] According to a water quality prediction method provided by the present invention, the standardization and scoring of the final-level indicators in the multi-level water quality indicator library to obtain the final-level indicator score includes: Screen the final level indicators in the multi-level water quality indicator library and remove abnormal indicators; The final indicators after removing abnormal indicators are normalized, and the final indicator scores are determined based on the normalization results.

[0007] According to a water quality prediction method provided by the present invention, the determination of the comprehensive weight of the final-level indicator based on the preset water quality comparison index and the final-level indicator score includes: Determining the dispersion of the final-level indicator based on the final-level indicator score; Determining the information entropy value of the final-level indicator based on the comparison result of the preset water quality comparison indicator and the final-level indicator score; The comprehensive weight of the final-level indicator is determined according to the discreteness and the information entropy value.

[0008] According to a water quality prediction method provided by the present invention, determining the comprehensive weight of the final index according to the discreteness and the information entropy value includes: Normalizing the discreteness to obtain a discrete coefficient; the discrete coefficient corresponds to a first weight, and determining a first weight value based on the discrete coefficient and the first weight; The information entropy value is proportionally processed to obtain an information coefficient; the information coefficient corresponds to a second weight, and a second weight is determined based on the information coefficient and the second weight; The comprehensive weight of the final-level indicator is determined according to the first weight and the second weight.

[0009] According to a water quality prediction method provided by the present invention, the step of determining the scores of indicators at each level and the comprehensive weights of indicators at each level in sequence based on the final indicator score and the final indicator comprehensive weight includes: The final indicator score and the final indicator comprehensive weight are weighted and summed to obtain the first indicator score; the first indicator is adjacent to the final indicator in level; Based on the preset water quality comparison index and the score of the first index, a comprehensive weight of the first index is determined.

[0010] According to a water quality prediction method provided by the present invention, determining the comprehensive water quality score based on the primary indicator score and the comprehensive weight of the primary indicators includes: Performing weighted sum processing on the primary indicator score and the primary indicator comprehensive weight to obtain a target water quality score; Based on the comparison result between the target water quality score and the preset water quality score, a comprehensive water quality score is determined; the preset water quality score is determined based on the preset water quality comparison index.

[0011] The present invention also provides a water quality prediction device, comprising the following modules: The final index score determination module is used to perform standardized scoring processing on the final index in the multi-level water quality index library to obtain the final index score; the multi-level water quality index library is constructed based on the historical detection data of the water resources to be predicted; A final index comprehensive weight determination module, used to determine the final index comprehensive weight based on the preset water quality comparison index and the final index score; An indicator level-by-level determination module, used to determine the indicator scores and comprehensive weights of each level of indicators in turn based on the final level indicator score and the final level indicator comprehensive weight; The water quality prediction module is used to determine the comprehensive water quality score according to the primary indicator score and the comprehensive weight of the primary indicators, and predict the water resources to be predicted based on the comprehensive water quality score to obtain a water quality prediction result.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the water quality prediction methods described above is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the water quality prediction method as described above is implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the water quality prediction method as described above is implemented.

[0015] The water quality prediction method, device, equipment, medium and computer program product provided by the present invention obtain the final index score by performing standardized scoring processing on the final index in the multi-level water quality index library, wherein the multi-level water quality index library is constructed based on the historical detection data of the water resources to be predicted. First, based on the preset water quality comparison index and the final index score, the final index comprehensive weight is determined, and then based on the final index score and the final index comprehensive weight, the index scores of each level and the comprehensive weights of each level are determined in turn, and finally the water quality comprehensive score is determined according to the primary index scores and the primary index comprehensive weights obtained step by step, and the water resources to be predicted are predicted by the water quality comprehensive score obtained by step-by-step calculation of the multi-level water quality indicators, thereby improving the accuracy of water quality prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 This is one of the flow charts of the water quality prediction method provided by the present invention.

[0018] Figure 2 This is the second flow chart of the water quality prediction method provided by the present invention.

[0019] Figure 3This is the third flow chart of the water quality prediction method provided by the present invention.

[0020] Figure 4 It is a structural schematic diagram of the water quality prediction device provided by the present invention.

[0021] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] Combine the following Figure 1-Figure 5 The water quality prediction method, device, equipment, medium and computer program product of the present invention are described.

[0024] Figure 1 It is one of the flow charts of the water quality prediction method provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 100, performing standardized scoring processing on the final level indicators in the multi-level water quality indicator library to obtain final level indicator scores; the multi-level water quality indicator library is constructed based on historical detection data of water resources to be predicted; Specifically, the construction of the multi-level water quality index library is explained by taking the three-level water quality index as an example, such as the first-level physical index, chemical index, biological index and pollutant index, etc. Each index of water bodies with different uses has its corresponding normal range and abnormal range, and the ranges of different sizes are generally determined based on the degree of subdivision of the index.

[0025] Among them, the physical indicators and their meanings are as follows: temperature; chromaticity: the color of the water body, which may be caused by dissolved substances or suspended matter in the water; turbidity: indicates the turbidity of the water body, which is determined by the content of suspended matter in the water body; odor: is a sensory indicator of the water body. Clean water is odorless, while polluted water will emit odors such as mold, feces, gasoline and rotten eggs.

[0026] The chemical indicators and their meanings are as follows: Acidity (pH value): refers to the indicator of hydrogen ion concentration in water, indicating the acidity or alkalinity of the water. pH=7 means that the water is neutral, pH>7 means that the water is alkaline, and pH<7 means that the water is acidic; Hardness: includes total hardness and temporary hardness. Total hardness refers to the total amount of calcium and magnesium ions contained in the water, and temporary hardness refers to the hardness in the form of calcium bicarbonate and magnesium bicarbonate; Ammonia nitrogen, nitrite and nitrate content: These indicators reflect the circulation of nitrogen in the water, and are related to the self-purification capacity and pollution degree of the water; Chloride: refers to the content of chloride ions in water; Dissolved oxygen (DO): refers to the amount of dissolved oxygen in water, which is a measure of One of the important indicators of water self-purification capacity; Chemical oxygen demand (COD): It indicates the total amount of substances in water that can be oxidized by chemical oxidants. It is an important indicator to measure the degree of organic pollution in water. Biological oxygen demand (BOD): Especially BOD5 (5-day biological oxygen demand), it is an important indicator that uses the amount of dissolved oxygen consumed by microbial metabolism to indirectly indicate the degree of organic pollution in water. Total organic carbon (TOC): It indicates the total amount of all organic matter in water. It is a comprehensive indicator to measure the degree of organic pollution in water.

[0027] The biological indicators and their meanings are as follows: total bacteria count; total coliform count; pathogenic bacteria; viruses; radioactive material concentration, etc. These biological indicators are used to determine the degree of water contamination by pathogenic microorganisms. The determination of total bacteria count and total coliform count is used to assess the degree of microbial contamination in water bodies, and the detection of pathogenic bacteria and viruses can reflect the possible health risks in water bodies.

[0028] The secondary indicators under the pollutant index may include a heavy metal index and an organic pollutant index; the secondary indicators under the biological index may include a plankton index and a harmful algae index. The tertiary indicators under the heavy metal index may include various heavy metal contents. The final index in this embodiment, i.e., the tertiary index, is also a water quality index that can be directly obtained. By scoring the final index, the final index score can be obtained.

[0029] Before scoring the final indicators, the final indicators in the multi-level water quality indicator library can be cleaned, screened, and standardized to eliminate abnormal indicators.

[0030] Step 200: Determine the comprehensive weight of the final-level indicator based on the preset water quality comparison indicator and the final-level indicator score; The water quality prediction method provided by the present invention constructs an index system combined weighting method based on the normal distribution characteristics of data, and proposes a quantitative weighting method combining multiple weighting methods. The quantitative comprehensive weights of the three-level indicators are first calculated by weighted summing the weights obtained by the weighting methods. Among them, the basic idea of ​​the weighting method proposed by the present invention is as follows: a statistic used to measure the degree of asymmetry in a probability distribution or data set, describing which side of the mean the tail of the data distribution is heavier or longer. If it is greater than 0, the data set is distributed on the left side of the mean, indicating that the difficulty of completing the indicator is greater, and a greater weight should be given to the indicator; if the data skewness is less than 0, the data set is distributed on the right side of the mean, indicating that the difficulty of completing the indicator is less, and the weight given to the indicator should be appropriately weakened. The basis for calculating the comprehensive weight of the three-level indicators is the above-mentioned final indicator score and the preset water quality comparison index. The preset water quality comparison index here can be a normal indicator that meets the standard among the water quality indicators.

[0031] Step 300: Based on the final indicator score and the final indicator comprehensive weight, determine the indicator scores and comprehensive weights of each level in turn; The scores and comprehensive weights of indicators at all levels are calculated step by step through the quantitative weighting method combined with the above-mentioned multiple weighting methods. The process is as follows: by calculating from top to bottom, the comprehensive weight of the final indicator is calculated by the quantitative weighting method, and then the secondary indicator score is calculated based on the comprehensive weight of the final indicator and the final indicator score, and then the secondary indicator comprehensive weight is determined based on the secondary indicator score; then the primary indicator score is calculated based on the secondary indicator comprehensive weight and the secondary indicator score, and then the primary indicator comprehensive weight is determined based on the primary indicator score. Taking the combination of the two weighting methods as an example, as shown in Formula 1, is the quantitative comprehensive weight of the jth indicator at the i-th level; a is the weight of the result of a weighting method; is a weighting method weight of the jth indicator of the i-th level; Another weighting method weight for the j-th indicator at the i-th level.

[0032] ; (1)

[0033] Step 400: Determine a comprehensive water quality score according to the primary indicator score and the comprehensive weight of the primary indicators, and predict the water resources to be predicted based on the comprehensive water quality score to obtain a water quality prediction result.

[0034] Similar to the step-by-step calculation of the comprehensive weights of indicators at each level, the scores of indicators at each level in this embodiment are also calculated step by step. After obtaining the scores of the first-level indicators, the comprehensive score of computing power construction resources for each water quality indicator is determined by calculating the quantitative comprehensive weight of each first-level indicator score and its corresponding first-level indicator. The proportion of the comprehensive score of computing power construction resources for each water quality indicator is used as reference data for water quality prediction.

[0035] This embodiment obtains the final index score by performing standardized scoring processing on the final index in the multi-level water quality index library, wherein the multi-level water quality index library is constructed based on the historical detection data of the water resources to be predicted. First, the final index comprehensive weight is determined based on the preset water quality comparison index and the final index score, and then the index scores and comprehensive weights of each level are determined in turn based on the final index score and the final index comprehensive weight. Finally, the comprehensive water quality score is determined according to the primary index scores and the comprehensive weights of the primary indicators obtained step by step. The water resources to be predicted are predicted by the comprehensive water quality scores calculated step by step by the multi-level water quality indicators, thereby improving the accuracy of water quality prediction.

[0036] In one embodiment, the water quality prediction method provided in the embodiment of the present application may further include: Step 110, screening the final level indicators in the multi-level water quality indicator library to remove abnormal indicators; Step 120: normalize the final level indicators after removing abnormal indicators, and determine the final level indicator scores based on the normalization results.

[0037] Specifically, it can be known that the multi-level water quality index library provided by the present application is constructed through the historical detection data of the water resources to be predicted. There may be some abnormal index data in the historical detection data of the water resources to be predicted. The final index after removing the abnormal index is normalized, and the data is normalized by the "maximum and minimum value normalization method", that is, the highest score is 100, the lowest score is 0, and the intermediate linear score is obtained to obtain the standardized score of the index. Alternatively, the final index that does not conform to the normal distribution is screened out by normal distribution. The normalization process is shown in Formulas 2 and 3, where, is the normalized processing result of the data of the ath final level indicator under the ith first level indicator after removing abnormal indicators; The data of the ath final indicator under the ith first-level indicator after removing abnormal indicators; is the minimum value of the jth final-level indicator under the i-th first-level indicator; It is the maximum value of the jth final-level indicator under the i-th first-level indicator.

[0038] ; (2)

[0039] ; (3)

[0040] This embodiment obtains the final-level indicator score by performing standardized scoring processing on the final-level indicator.

[0041] Figure 2 This is the second flow chart of the water quality prediction method provided by the present invention, such as Figure 2As shown, the method may also include: Step 210: determining the dispersion of the final-level indicator based on the final-level indicator score; Step 220: Determine the information entropy value of the final-level indicator based on the comparison result of the preset water quality comparison indicator and the final-level indicator score; Step 230: Determine the comprehensive weight of the final-level indicator according to the discreteness and the information entropy value.

[0042] Specifically, the standardized score or weighted score of each indicator is obtained, and the user calculates the standardized score or weighted score of each indicator to obtain parameters such as the average score and the standard deviation of the indicator score. The degree of dispersion of the final indicator is calculated based on these parameters. Then, the preset water quality indicator and the final indicator score are compared to obtain the comparison result, and the information entropy value of the final indicator is determined based on the comparison result. Finally, the comprehensive weight of the final indicator is determined based on the comprehensive calculation of the dispersion and information entropy value.

[0043] The measurement formula of the discrete degree of the final index is shown in Formula 4. It is the measure of the degree of dispersion of the jth final indicator under the i-th first-level indicator; m is the sum of the data of the jth final indicator under the i-th first-level indicator; is the standardized score or weighted calculated score of the jth final indicator under the i-th first-level indicator; for The average value of is the standard deviation of the score of the jth final-level indicator under the i-th first-level indicator.

[0044] ; (4)

[0045] This embodiment determines the comprehensive weight of the final-level indicator by successively calculating the discreteness and information entropy value of the final-level indicator score and the preset water quality comparison indicator.

[0046] Figure 3 This is the second flow chart of the water quality prediction method provided by the present invention, such as Figure 3 As shown, the method may also include: Step 231: normalize the discreteness to obtain a discrete coefficient; the discrete coefficient corresponds to a first weight, and a first weight value is determined based on the discrete coefficient and the first weight; Step 232: scaling the information entropy value to obtain an information coefficient; the information coefficient corresponds to a second weight, and a second weight is determined based on the information coefficient and the second weight; Step 233: Determine the comprehensive weight of the final-level indicator according to the first weight and the second weight.

[0047] Specifically, the above-obtained dispersion is normalized to obtain a dispersion coefficient, which corresponds to the first weight, and the first weight is calculated based on the dispersion coefficient and the first weight. The calculation process of a weight of indicators at each level is as follows: determine the proportion of each third-level indicator in the total score of each third-level indicator, as well as the standardized score or weighted calculation score of each third-level indicator, through which the information entropy value and information utility value of each indicator can be calculated.

[0048] The information entropy value is proportionally processed to obtain the information coefficient, which corresponds to the second weight, and the second weight is determined according to the information coefficient and the second weight. Finally, the final index comprehensive weight is determined based on the first weight and the second weight.

[0049] This embodiment uses operations such as discreteness normalization processing and information entropy value proportionality processing to ultimately determine the final-level indicator comprehensive weight based on the first weight and the second weight.

[0050] In one embodiment, the water quality prediction method provided in the embodiment of the present application may further include: Step 310: Perform weighted sum processing on the final indicator score and the final indicator comprehensive weight to obtain the score of the first indicator; the level of the first indicator is adjacent to the final indicator; Step 320: Determine a comprehensive weight of the first indicator based on the preset water quality comparison indicator and the score of the first indicator.

[0051] Specifically, according to the above process of calculating multiple weights of indicators at each level step by step through multiple weighting methods, it can be known that the three-level indicator score is obtained by sequentially performing data cleaning, indicator screening and standardization on the three-level indicators, and the quantitative comprehensive weight of the three-level indicators is calculated based on the three-level indicator score; the secondary indicator score is calculated based on the three-level indicator score and the quantitative comprehensive weight of the three-level indicators, and the quantitative comprehensive weight of the secondary indicator is calculated by multiple weighting methods for the secondary indicator score; the primary indicator score is calculated based on the secondary indicator score and the quantitative comprehensive weight of the secondary indicator, and the quantitative comprehensive weight of the primary indicator is calculated by multiple weighting methods for the primary indicator score. By calculating the scores and quantitative comprehensive weights of indicators at each level step by step, a more standardized and reasonable data basis is provided for the final water quality prediction.

[0052] This embodiment provides a more standardized and reasonable data basis for the final water quality prediction by calculating the index scores and quantitative comprehensive weights at each level step by step.

[0053] In one embodiment, the water quality prediction method provided in the embodiment of the present application may further include: Step 410: Perform weighted sum processing on the primary indicator score and the primary indicator comprehensive weight to obtain a target water quality score; Step 420: Determine a comprehensive water quality score based on a comparison result between the target water quality score and a preset water quality score; the preset water quality score is determined based on the preset water quality comparison index.

[0054] Specifically, the primary indicator scores and the primary indicator comprehensive weights obtained above are weighted and summed to obtain a comprehensive score of the water quality to be predicted, i.e., the target water quality score in this embodiment. The above processing of the preset water quality comparison index can also obtain a comprehensive score, i.e., the preset water quality score in this embodiment. Finally, the target water quality score is compared with the preset water quality score to obtain a comparison result, and the comprehensive score of the water resources to be predicted is determined based on the comparison result as the data basis for water quality prediction.

[0055] This embodiment predicts the water resources to be predicted by calculating the comprehensive water quality scores obtained by multi-level water quality indicators step by step, thereby improving the accuracy of water quality prediction.

[0056] The water quality prediction device provided by the present invention is described below. The water quality prediction device described below and the water quality prediction method described above can be referenced to each other.

[0057] Please refer to Figure 4 The present invention also provides a water quality prediction device, comprising: The final index score determination module 401 is used to perform standardized scoring processing on the final index in the multi-level water quality index library to obtain the final index score; the multi-level water quality index library is constructed based on the historical detection data of the water resources to be predicted; The final index comprehensive weight determination module 402 is used to determine the final index comprehensive weight based on the preset water quality comparison index and the final index score; The indicator level-by-level determination module 403 is used to determine the indicator scores and the comprehensive weights of the indicators at each level in turn based on the final indicator score and the final indicator comprehensive weight; The water quality prediction module 404 is used to determine the comprehensive water quality score according to the primary indicator score and the comprehensive weight of the primary indicator, and predict the water resources to be predicted based on the comprehensive water quality score to obtain a water quality prediction result.

[0058] Optionally, the final indicator score determination module includes: The abnormal index screening unit is used to screen the final index in the multi-level water quality index library and remove the abnormal index; The final indicator score determination unit is used to normalize the final indicator after removing the abnormal indicator, and determine the final indicator score based on the normalization result.

[0059] Optionally, the final-level indicator comprehensive weight determination module includes: A final indicator dispersion determination unit, configured to determine the dispersion of the final indicator based on the final indicator score; A final-level indicator information entropy value determination unit, used to determine the information entropy value of the final-level indicator based on a comparison result of a preset water quality comparison indicator and the final-level indicator score; The final-level indicator comprehensive weight determination unit is used to determine the final-level indicator comprehensive weight according to the discreteness and the information entropy value.

[0060] Optionally, the final-level indicator comprehensive weight determination unit includes: A dispersion normalization processing unit, configured to perform normalization processing on the dispersion to obtain a dispersion coefficient; the dispersion coefficient corresponds to a first weight, and a first weight value is determined based on the dispersion coefficient and the first weight; An information coefficient determination unit, configured to perform proportional processing on the information entropy value to obtain an information coefficient; the information coefficient corresponds to a second weight, and a second weight is determined based on the information coefficient and the second weight; The final-level indicator comprehensive weight determination unit is used to determine the final-level indicator comprehensive weight according to the first weight and the second weight.

[0061] Optionally, the indicator step-by-step determination module includes: A weighted sum processing unit, used for performing weighted sum processing on the final indicator score and the final indicator comprehensive weight to obtain the score of the first indicator; the level of the first indicator is adjacent to the final indicator; The first indicator comprehensive weight determination unit is used to determine the comprehensive weight of the first indicator based on a preset water quality comparison indicator and a score of the first indicator.

[0062] Optionally, the water quality prediction module includes: A target water quality score determination unit is used to perform weighted sum processing on the primary indicator score and the primary indicator comprehensive weight to obtain a target water quality score; The water quality comprehensive score determination unit is used to determine the water quality comprehensive score based on the comparison result between the target water quality score and the preset water quality score; the preset water quality score is determined based on the preset water quality comparison index.

[0063] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5As shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530 and a communication bus 540, wherein the processor 510, the communication interface 520 and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the water quality prediction method, which includes: performing standardized scoring processing on the final index in the multi-level water quality index library to obtain the final index score; the multi-level water quality index library is constructed based on the historical detection data of the water resources to be predicted; based on the preset water quality comparison index and the final index score, determining the final index comprehensive weight; based on the final index score and the final index comprehensive weight, sequentially determining the index scores and the comprehensive weights of the indicators at each level; determining the water quality comprehensive score according to the primary index score and the primary index comprehensive weight, predicting the water resources to be predicted based on the water quality comprehensive score, and obtaining the water quality prediction result.

[0064] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0065] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the water quality prediction method provided by the above methods, which method includes: performing standardized scoring processing on the final-level indicators in the multi-level water quality indicator library to obtain the final-level indicator score; the multi-level water quality indicator library is constructed based on the historical detection data of the water resources to be predicted; based on the preset water quality comparison index and the final-level indicator score, determining the final-level indicator comprehensive weight; based on the final-level indicator score and the final-level indicator comprehensive weight, determining the indicator scores and the comprehensive weights of each level in turn; determining the comprehensive water quality score according to the primary indicator score and the primary indicator comprehensive weight, predicting the water resources to be predicted based on the comprehensive water quality score, and obtaining a water quality prediction result.

[0066] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the water quality prediction method provided by the above-mentioned methods, the method comprising: performing standardized scoring processing on the final-level indicators in a multi-level water quality indicator library to obtain a final-level indicator score; the multi-level water quality indicator library is constructed based on historical detection data of water resources to be predicted; determining a final-level indicator comprehensive weight based on preset water quality comparison indicators and the final-level indicator score; determining the indicator scores and comprehensive weights of each level in turn based on the final-level indicator score and the final-level indicator comprehensive weight; determining a water quality comprehensive score based on the primary indicator score and the primary indicator comprehensive weight, predicting the water resources to be predicted based on the comprehensive water quality score, and obtaining a water quality prediction result.

[0067] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0068] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A water quality prediction method, characterized in that: include: Performing standardized scoring processing on the final level indicators in the multi-level water quality indicator library to obtain final level indicator scores; the multi-level water quality indicator library is constructed based on historical detection data of water resources to be predicted; Determining the comprehensive weight of the final-level indicator based on the preset water quality comparison indicator and the final-level indicator score; Based on the final indicator score and the final indicator comprehensive weight, sequentially determine the indicator scores and comprehensive weights of each level; A comprehensive water quality score is determined according to the primary indicator score and the comprehensive weight of the primary indicators, and the water resources to be predicted are predicted based on the comprehensive water quality score to obtain a water quality prediction result.

2. The water quality prediction method according to claim 1, characterized in that: The standardized scoring process of the final level indicators in the multi-level water quality indicator library to obtain the final level indicator score includes: Screen the final level indicators in the multi-level water quality indicator library and remove abnormal indicators; The final indicators after removing abnormal indicators are normalized, and the final indicator scores are determined based on the normalization results.

3. The water quality prediction method according to claim 1, characterized in that: Determining the comprehensive weight of the final-level indicator based on the preset water quality comparison indicator and the final-level indicator score includes: Determining the dispersion of the final-level indicator based on the final-level indicator score; Determining the information entropy value of the final-level indicator based on the comparison result of the preset water quality comparison indicator and the final-level indicator score; The comprehensive weight of the final-level indicator is determined according to the discreteness and the information entropy value.

4. The water quality prediction method according to claim 3, characterized in that: Determining the comprehensive weight of the final-level indicator according to the dispersion and the information entropy value includes: Normalizing the discreteness to obtain a discrete coefficient; the discrete coefficient corresponds to a first weight, and determining a first weight value based on the discrete coefficient and the first weight; The information entropy value is proportionally processed to obtain an information coefficient; the information coefficient corresponds to a second weight, and a second weight is determined based on the information coefficient and the second weight; The comprehensive weight of the final-level indicator is determined according to the first weight and the second weight.

5. The water quality prediction method according to claim 1, characterized in that: The step of sequentially determining the scores of indicators at each level and the comprehensive weights of indicators at each level based on the final level indicator score and the final level indicator comprehensive weight includes: The final indicator score and the final indicator comprehensive weight are weighted and summed to obtain the first indicator score; the first indicator is adjacent to the final indicator in level; Based on the preset water quality comparison index and the score of the first index, a comprehensive weight of the first index is determined.

6. The water quality prediction method according to claim 1, characterized in that: Determining the comprehensive water quality score based on the primary indicator score and the comprehensive weight of the primary indicators includes: Performing weighted sum processing on the primary indicator score and the primary indicator comprehensive weight to obtain a target water quality score; Based on the comparison result between the target water quality score and the preset water quality score, a comprehensive water quality score is determined; the preset water quality score is determined based on the preset water quality comparison index.

7. A water quality prediction device, characterized in that: include: The final index score determination module is used to perform standardized scoring processing on the final index in the multi-level water quality index library to obtain the final index score; the multi-level water quality index library is constructed based on the historical detection data of the water resources to be predicted; A final index comprehensive weight determination module, used to determine the final index comprehensive weight based on the preset water quality comparison index and the final index score; An indicator level-by-level determination module, used to determine the indicator scores and comprehensive weights of each level of indicators in turn based on the final level indicator score and the final level indicator comprehensive weight; The water quality prediction module is used to determine the comprehensive water quality score according to the primary indicator score and the comprehensive weight of the primary indicators, and predict the water resources to be predicted based on the comprehensive water quality score to obtain a water quality prediction result.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the water quality prediction method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the water quality prediction method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the water quality prediction method according to any one of claims 1 to 6 is implemented.