Urban wading infrastructure efficiency evaluation method, device and equipment and storage medium

Abstract

This invention relates to the field of urban infrastructure efficiency evaluation technology, and discloses a method, device, equipment, and storage medium for evaluating the efficiency of urban water-related infrastructure. This invention acquires current data and predicted data for future planning stages for various indicators of the urban water-related infrastructure to be evaluated, and integrates these two types of data to construct an indicator dataset, comprehensively reflecting the status of urban water-related infrastructure at different stages. The indicator dataset is divided into two dimensions: time and water-related cycle, constructing a full-process indicator system that comprehensively covers all aspects and stages of urban water-related infrastructure, solving the problem of single evaluation dimensions in existing technologies. This invention introduces characteristic correlation factors and sets upper limits for slack variables in the DEA model objective function, which can accurately quantify the complex relationships between urban water-related infrastructure indicators, prevent excessive amplification of slack variables, and improve the accuracy of evaluation results.

Description

Technical Field

[0001] This invention relates to the field of urban living facility efficiency evaluation technology, specifically to methods, devices, equipment, and storage media for evaluating the efficiency of urban water-related infrastructure. Background Technology

[0002] Urban water-related infrastructure refers to the system of facilities directly related to water resource utilization, sewage treatment and related supporting services within a city, including but not limited to water supply systems, sewage treatment systems, sludge disposal facilities and related hardware facilities formed by water-related fixed asset investment. Water supply systems include water intake facilities and water transmission networks, while sewage treatment systems include sewage treatment plants and sewage collection networks. Urban water-related infrastructure is the core hardware support for ensuring urban water resource circulation and water environment governance.

[0003] Efficiency analysis refers to the quantitative evaluation of the conversion efficiency between resource consumption and functional output of urban water-related infrastructure through specific data analysis methods and based on an indicator system. It identifies issues of redundant inputs or insufficient outputs. Resource consumption includes total water consumption and fiscal investment, while functional outputs include wastewater treatment volume and GDP contribution. Efficiency analysis is an analytical process that provides a basis for decision-making regarding the optimal allocation of facilities.

[0004] Data Envelopment Analysis (DEA) is a nonparametric efficiency evaluation method based on linear programming, primarily used to measure the relative efficiency levels of multiple decision units (DMUs). Currently, there are various methods for facility efficiency assessment based on DEA models.

[0005] The application of the DEA model in water resources and environmental efficiency assessment adopts the Bootstrap-DEA model to evaluate the efficiency of urban sewage treatment. It selects the length of sewage pipe network and the daily treatment capacity of sewage treatment plant as input indicators and the total amount of sewage treated as output indicator. It solves the problem of missing statistical attributes in the traditional DEA model. However, it only focuses on the single link of sewage treatment and does not cover the whole process of urban water-related infrastructure from water supply to water use to sewage treatment to sludge disposal.

[0006] The application of the DEA model in multi-stage efficiency decomposition decomposes water resource efficiency into production efficiency and governance efficiency, constructs a two-stage network DEA model, and incorporates undesirable outputs, such as wastewater discharge. However, this technical solution is designed for the provincial scale and does not focus on the specific characteristics of urban-level water-related infrastructure, such as facility-level indicators like pipeline length and sludge disposal volume, and does not consider the dynamic redundancy optimization of input-output indicators.

[0007] The partial application of DEA model in infrastructure evaluation: Based on DEA, this paper evaluates highway pavement maintenance measures and proposes a technical logic of using K-nearest neighbor algorithm to filter noisy data and DEA model to evaluate benefits. It is applicable to highway pavement maintenance scenarios. However, its input indicators, such as maintenance costs and pavement performance indicators, are significantly different from the indicator system of urban water-related infrastructure and cannot be directly transferred and applied.

[0008] Therefore, the above-mentioned DEA model still faces the following technical problems in various application scenarios of facility efficiency evaluation:

[0009] The assessment is based on a single dimension and does not cover the entire process of water-related facilities. It only focuses on the sewage treatment stage and does not consider water supply-use-sewage treatment-sludge disposal as a complete system. It ignores key facility investments such as pipeline length and water-related fixed asset investment, as well as end-point outputs such as the amount of dry sludge disposed of, resulting in a disconnect between efficiency assessment and the actual operation scenario of urban water-related facilities.

[0010] The indicator system lacks dynamic optimization and does not consider slack variable constraints. Although traditional DEA models and improved SBM-DEA models introduce undesirable outputs, they do not set dynamic upper limit constraints for the redundancy of urban water-related facilities and the insufficiency of outputs. This can easily lead to excessive amplification of slack variables. For example, if a city's primary industry water consumption needs to be reduced by 80%, it would far exceed the actual operational feasibility, causing the efficiency results to deviate from reality.

[0011] The existing technology does not take into account the characteristics of space and facilities, thus limiting its applicability. It does not consider the population size matching degree and pipeline coverage density of urban-level water-related facilities, and does not introduce spatial kernel density analysis to optimize the spatial matching of facility efficiency, resulting in insufficient guidance for urban-level decision-making based on the assessment results.

[0012] The lack of data preprocessing leads to insufficient accuracy in efficiency results. When existing DEA models are applied to water-related fields, noise filtering is not performed on data that is susceptible to outliers. For example, an abnormally high total water consumption in a city may be due to statistical errors. In the above application scenarios, the K-nearest neighbor noise filtering technology has not been transferred to water-related scenarios, resulting in low accuracy of the basic data for efficiency calculation and insufficient reliability of the results. Summary of the Invention

[0013] This invention provides a method, apparatus, equipment, and storage medium for evaluating the efficiency of urban water-related infrastructure, in order to solve the technical problems of existing technologies that only focus on a single aspect, excessive amplification of slack variables in traditional DEA models, and low data accuracy.

[0014] In a first aspect, the present invention provides a method for evaluating the efficiency of urban water-related infrastructure. The method includes: acquiring current data and predicted data for future planning stages of various indicators of the urban water-related infrastructure to be evaluated, obtaining an indicator dataset; dividing the indicator dataset into different stages according to the time dimension and the water-related cycle dimension, obtaining a stage indicator dataset corresponding to each stage; calculating characteristic correlation factors corresponding to each indicator based on the current data and predicted data of each indicator; solving the improved DEA model using the indicator datasets of each stage and the characteristic correlation factors of each indicator, obtaining the weights corresponding to each indicator in the indicator datasets of each stage; the improved DEA model introduces characteristic correlation factors into the objective function of the DEA-BCC model and sets upper limits for slack variables; and obtaining the efficiency and comprehensive efficiency of the urban water-related infrastructure to be evaluated at each stage based on the indicator datasets of each stage, the characteristic correlation factors of each indicator, and the weights of each indicator.

[0015] This invention acquires current data on various indicators of urban water-related infrastructure under evaluation, enabling precise understanding of the infrastructure's current operational status, including key information such as input and output. Simultaneously, it obtains predictive data for future planning stages, allowing for advance understanding of the infrastructure's development trajectory and expected goals over a future period. Integrating these two types of data to construct an indicator dataset covers comprehensive information about the infrastructure from its current state to its future, fully reflecting the status of urban water-related infrastructure at different stages and avoiding the one-sidedness of evaluation based solely on current data. The indicator dataset is divided into two dimensions: time and water-related cycle. The time dimension distinguishes operational data within different time periods, reflecting changes in efficiency over different periods. The water-related cycle dimension incorporates all aspects of water supply, water use, sewage treatment, and sludge disposal into the evaluation scope, forming a complete water-related process. This two-dimensional approach to construct a full-process indicator system comprehensively covers all aspects and stages of urban water-related infrastructure, solving the problem of single evaluation dimensions in existing technologies and accurately assessing the efficiency of each aspect and overall operational efficiency.

[0016] This invention introduces a characteristic correlation factor into the objective function of the DEA model and sets an upper limit constraint on slack variables. Based on multi-dimensional data and weighted calculations, the characteristic correlation factor can accurately quantify the complex relationships between urban water-related infrastructure indicators, enabling the model to more accurately reflect the actual contribution of each indicator when calculating efficiency, making the efficiency assessment more realistic and scientifically sound. The upper limit constraint on slack variables prevents excessive amplification of slack variables, solving the problem of efficiency results deviating from reality due to excessive amplification of slack variables in traditional DEA models, thus improving the accuracy of the assessment results.

[0017] In one optional implementation, the indicators for the urban water-related infrastructure to be evaluated include multiple input indicators and multiple output indicators. Specifically, current data for each input indicator and each output indicator of the urban water-related infrastructure to be evaluated in the current stage are obtained, and predicted data for each input indicator and each output indicator of the urban water-related infrastructure to be evaluated in the future planning stage are obtained to construct an indicator dataset. The indicator dataset is then divided into different stages according to the time dimension and the water-related cycle dimension to obtain the stage indicator dataset corresponding to each stage.

[0018] In this embodiment, the current dataset and the predicted dataset of the indicators are constructed separately and then integrated into a complete dataset. This approach ensures that the evaluation is based not only on the current input and output data of actual operation, but also on the predicted data of the future planning stage. It comprehensively covers the development status of urban water-related infrastructure from the present to the future, avoids the one-sidedness of evaluation based solely on current data, and provides a richer and more complete data foundation for scientific evaluation.

[0019] In one optional implementation, the step of dividing the indicator dataset into different stages according to the time dimension and the water-related cycle dimension to obtain the stage indicator dataset corresponding to each stage includes: dividing the indicator dataset into the current stage and the future planning stage in the time dimension, and dividing the current stage and the future planning stage in the water-related cycle dimension to obtain multiple different stages and the stage indicator dataset corresponding to each stage, wherein the water-related cycle dimension includes the water production stage and the treatment and disposal stage.

[0020] In this implementation, the assessment is divided into two main phases: current and future planning. Each phase is further subdivided into water production and treatment / disposal stages. This refined breakdown can accurately pinpoint the specific location of inefficiency, such as whether there is resource waste in the current water production stage or technical shortcomings in the future planned treatment / disposal stage. This provides a clear direction for subsequent targeted improvements and greatly enhances the accuracy and practicality of the assessment.

[0021] In one optional implementation, the step of calculating the characteristic correlation factor corresponding to each indicator based on the current data and predicted data of each indicator includes: obtaining the current data and predicted data of each indicator in several sample cities, and calculating the mean of the current data and the mean of the predicted data of each indicator in several sample cities; determining the weight of the current data and the weight of the predicted data in each indicator of the city to be evaluated; and calculating the characteristic correlation factor of each indicator based on the current data of each indicator of the city to be evaluated, the predicted data of each indicator of the city to be evaluated, the mean of the current data of each indicator of several sample cities, the mean of the predicted data of each indicator of several sample cities, and the weight of the current data and the weight of the predicted data in each indicator of the city to be evaluated.

[0022] This implementation method introduces the current and predicted average values ​​of various indicators in sample cities as benchmarks, and combines them with the current and predicted data of the city to be evaluated to quantify the impact of each indicator on the efficiency of water-related infrastructure. This effectively solves the problem of low efficiency assessment accuracy caused by the neglect of differences between indicators in traditional DEA models. At the same time, by setting the weights of the current and predicted data of the city to be evaluated, the assessment bias caused by differences in city size and development stage can be corrected, making the assessment results more in line with the actual operation scenario and development trend of the city, and significantly improving the scientific nature and decision-making guidance value of efficiency assessment.

[0023] In one optional implementation, the improved DEA model introduces characteristic correlation factors into the objective function of the DEA-BCC model and sets upper limits for slack variables. This includes: the objective function of the DEA-BCC model includes various indicators and slack variables for each indicator; introducing characteristic correlation factors corresponding to each indicator into the objective function to form a new objective function; calculating the current and future potential slack variables for each indicator respectively; and determining upper limits for slack variables corresponding to each indicator in the objective function based on the potential slack variables.

[0024] This implementation introduces a characteristic correlation factor into the objective function, quantifying and incorporating the city's differentiated characteristics into the model, thus solving the problem of traditional DEA models neglecting the spatial heterogeneity among indicators. The combination of the characteristic correlation factor and the objective function can simultaneously optimize input redundancy and output insufficiency, achieving improvements in both the current and future dimensions.

[0025] In one optional implementation, the step of calculating the current and future potential slack variables of each indicator, and determining the upper limit constraint of the slack variables corresponding to each indicator in the objective function based on the potential slack variables, includes: obtaining current and predicted data of each indicator in several sample cities; calculating the current potential slack variables of each indicator in each sample city based on the current data of each indicator in several sample cities, and calculating the future planning potential slack variables of each indicator in each sample city based on the predicted data of each indicator in several sample cities; performing a weighted summation of the current and future planning potential slack variables of each indicator to obtain the comprehensive potential slack variables of each indicator; calculating the initial upper limit constraint based on the comprehensive potential slack variables of each indicator; and introducing a prediction correction parameter for the initial upper limit constraint to obtain the upper limit constraint of the slack variables corresponding to each indicator.

[0026] This implementation effectively addresses the problem of excessive amplification of slack variables in traditional DEA models by calculating and weighting the current and future potential slack variables for the sample cities. Specifically, potential slack variables are calculated based on both current and projected data for the sample cities, reflecting the redundancy or inadequacy of facilities in current operation and future planning. Weighted summation balances short-term efficiency and long-term adaptability by integrating the slack variables, avoiding biases caused by single-dimensional assessment. Furthermore, a prediction correction parameter is introduced to further quantify the impact of future prediction errors on the slack variables, ensuring that the constraints are practically feasible.

[0027] In one optional implementation, the steps of obtaining the efficiency and overall efficiency of the urban water-related infrastructure to be evaluated at each stage, based on the indicator datasets of each stage, the characteristic correlation factors of each indicator, and the weights of each indicator, include: calculating the stage efficiency of each stage included in the current stage and the overall efficiency of the current stage based on the stage indicator datasets of each stage included in the current stage, the characteristic correlation factors of each indicator, and the weights of each indicator; calculating the stage efficiency of each stage included in the future planning stage and the overall efficiency of the future planning stage based on the stage indicator datasets of each stage included in the future planning stage, the characteristic correlation factors of each indicator, and the weights of each indicator; and obtaining the overall efficiency of the urban water-related infrastructure to be evaluated based on the overall efficiency of the current stage and the overall efficiency of the future planning stage.

[0028] This implementation first calculates the efficiency assessment results for each stage. Then, based on the overall efficiency and comprehensive efficiency of each stage, it provides a clear understanding of the operational status of water-related infrastructure at different stages and stages, offering scientific quantitative data for subsequent investment decisions and urban planning. When calculating efficiency, this implementation introduces characteristic correlation factors to fully consider the impact of urban differences on the efficiency of water-related infrastructure. Different cities differ in geographical environment, population size, and economic development level, all of which affect the operational efficiency of water-related infrastructure. Quantifying these differences through characteristic correlation factors allows for a more objective and scientific assessment of the true efficiency of water-related infrastructure in different cities, avoiding distortion of assessment results due to neglecting urban characteristics, and making the assessment results more accurate.

[0029] Secondly, the present invention provides an efficiency assessment device for urban water-related infrastructure, comprising: a data acquisition module, used to acquire current data and predicted data for future planning stages of various indicators of the urban water-related infrastructure to be assessed, and to divide them into different stages according to time and water-related cycle dimensions, thereby obtaining stage indicator datasets corresponding to each stage; a characteristic correlation factor calculation module, used to calculate characteristic correlation factors corresponding to each indicator based on the current and predicted data of each indicator; an indicator weight calculation module, used to solve the problem using an improved DEA model based on the stage indicator datasets and the characteristic correlation factors of each indicator, thereby obtaining the weights corresponding to each indicator in each stage indicator dataset; wherein the improved DEA model introduces characteristic correlation factors into the objective function of the DEA-BCC model and sets upper limits for slack variables; and an efficiency assessment module, used to obtain the efficiency and overall efficiency of the urban water-related infrastructure to be assessed at each stage based on the stage indicator datasets, the characteristic correlation factors of each indicator, and the weights of each indicator.

[0030] Thirdly, the present invention provides an electronic 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 computer instructions to perform the urban water-related infrastructure efficiency assessment method described in the first aspect or any corresponding embodiment thereof.

[0031] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the urban water-related infrastructure efficiency assessment method described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0032] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0033] Figure 1 This is a schematic diagram of the first process of the urban water-related infrastructure efficiency assessment method according to an embodiment of the present invention;

[0034] Figure 2 This is a schematic diagram of the second process of the urban water-related infrastructure efficiency assessment method according to an embodiment of the present invention;

[0035] Figure 3 This is a structural block diagram of an urban water-related infrastructure efficiency evaluation device according to an embodiment of the present invention;

[0036] Figure 4 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0039] Urban water-related infrastructure is the core hardware support for ensuring urban water resource circulation and water environment management, and efficiency analysis can provide a basis for decision-making on its optimal allocation. Currently, DEA models are used in various applications for water resource and environmental efficiency assessment, multi-stage efficiency decomposition, and infrastructure evaluation. However, they suffer from technical problems such as a single assessment dimension failing to cover the entire process, a lack of dynamic optimization in the indicator system, limited applicability due to a failure to consider spatial and facility characteristics, and insufficient accuracy of efficiency results due to inadequate data preprocessing. Therefore, this invention provides a method, device, equipment, and storage medium for evaluating the efficiency of urban water-related infrastructure to address the technical problems of existing technologies focusing only on a single aspect, excessive amplification of slack variables in traditional DEA models, and low data accuracy.

[0040] According to an embodiment of the present invention, an embodiment of a method for evaluating the efficiency of urban water-related infrastructure is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0041] This embodiment provides a method for evaluating the efficiency of urban water-related infrastructure, which can be used on mobile terminals such as mobile phones and tablets. Figure 1 This is a flowchart of an urban water-related infrastructure efficiency assessment method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0042] Step S101: Obtain the current data and the predicted data of various indicators of the urban water-related infrastructure to be evaluated in the current stage and the future planning stage, and divide them into different stages according to the time dimension and the water-related cycle dimension to obtain the stage indicator dataset corresponding to each stage.

[0043] This step collects actual data on various indicators of the urban water-related infrastructure to be evaluated at the current stage, as well as predicted data for the future planning stage. These indicators cover multiple aspects of urban water-related infrastructure, such as indicators related to water intake facilities and water transmission networks in the water supply system, daily treatment capacity of sewage treatment plants and sewage collection networks in the sewage treatment system, and indicators related to sludge disposal facilities. To analyze the data more systematically and comprehensively, this step divides the acquired data according to two dimensions: first, the data is divided into different time periods according to chronological order, thus clearly understanding the efficiency transformation of urban water-related infrastructure at different time periods. Considering that urban water-related infrastructure involves a complete cycle of water supply, water use, sewage treatment, and sludge disposal, this step also divides the data according to different stages of this cycle to fully present the data status of each stage in the entire water-related process. After the above two-dimensional division, multiple data sets of different stages will be obtained. Each set corresponds to a specific stage. These sets are called stage indicator datasets. Each stage indicator dataset contains data on various indicators under that stage, providing a data foundation for subsequent operations such as calculating characteristic correlation factors, solving weights using improved DEA models, and improving computational efficiency based on these data.

[0044] Step S102: Based on the current and predicted data of each indicator, calculate the characteristic correlation factor corresponding to each indicator.

[0045] This step uses current and predicted data for each indicator as the basis for calculation, determining the characteristic correlation factors. Current data reflects the actual operational status of urban water-related infrastructure at the present stage, while predicted data reflects its development trend and expected situation in the future planning stage. By comprehensively considering both types of data, we can more fully grasp the changing characteristics of indicators under different times and conditions, making the calculated characteristic correlation factors more scientific and forward-looking. The calculated characteristic correlation factors will serve as important input parameters for subsequent steps. The improved DEA model will incorporate these characteristic correlation factors into its objective function to more accurately consider the impact of each indicator on efficiency, thereby obtaining more reasonable indicator weights. This helps improve the accuracy and reliability of urban water-related infrastructure efficiency assessment, providing strong support for the subsequent formulation of scientific and reasonable optimization strategies and decisions.

[0046] Step S103: Based on the indicator datasets of each stage and the characteristic correlation factors of each indicator, the improved DEA model is used to solve the problem and obtain the weights of each indicator in the indicator datasets of each stage. The improved DEA model introduces characteristic correlation factors into the objective function of the DEA-BCC model and sets upper limit constraints on slack variables.

[0047] This step improves upon the DEA-BCC model, a commonly used data envelopment analysis model capable of evaluating the relative efficiency of multiple decision units (DMUs) while considering variable returns to scale. Specific improvements include introducing characteristic correlation factors and upper limits for slack variables. Introducing characteristic correlation factors into the objective function of the improved DEA model ensures that the model fully considers these relationships when evaluating efficiency, rather than viewing each indicator in isolation. Upper limits for slack variables prevent inaccurate efficiency assessments caused by excessive amplification of slack variables. The indicator datasets obtained in step S101 and the characteristic correlation factors calculated in step S102 are used as input data and substituted into the improved DEA model. After model computation, the weights corresponding to each indicator in each stage's dataset are obtained. These weights reflect the importance of each indicator in evaluating the efficiency of urban water-related infrastructure; a larger weight indicates a more significant impact of the indicator on efficiency.

[0048] Step S104: Based on the indicator datasets of each stage, the characteristic correlation factors of each indicator, and the weights of each indicator, the efficiency and overall efficiency of the urban water-related infrastructure to be evaluated at each stage are obtained.

[0049] For each stage's indicator dataset, the data for each indicator is combined with its corresponding characteristic correlation factors and weights. A specific efficiency calculation formula is then used to calculate the efficiency for each stage. After obtaining the efficiency for each stage, an appropriate weighting method is employed to synthesize the efficiencies of each stage, yielding the overall efficiency of the urban water-related infrastructure to be evaluated. The results of the efficiency at each stage and the overall efficiency can intuitively reflect the operational status of the urban water-related infrastructure at different stages and overall. If the efficiency of a certain stage is low, it indicates that there are problems in resource utilization or functional output at that stage, requiring further analysis of the causes and corresponding improvement measures.

[0050] The urban water-related infrastructure efficiency assessment method provided in this embodiment obtains current data on various indicators of the urban water-related infrastructure to be assessed at the current stage, enabling precise understanding of the actual operational status of the facilities, including key information such as input and output. Simultaneously, it acquires predictive data for the future planning stage, allowing for advance understanding of the infrastructure's development trajectory and expected goals over a future period. Integrating these two types of data to construct an indicator dataset covers comprehensive information about the facilities from their current state to the future, fully reflecting the status of urban water-related infrastructure at different stages and avoiding the one-sidedness of assessments based solely on current data. The indicator dataset is divided into two dimensions: time and water-related cycle. The time dimension distinguishes the operational data of the facilities within different time periods, reflecting changes in efficiency over different periods. The water-related cycle dimension incorporates all aspects of water supply, water use, sewage treatment, and sludge disposal into the assessment scope, forming a complete water-related process. This two-dimensional approach to construct a full-process indicator system comprehensively covers all aspects and stages of urban water-related infrastructure, solving the problem of single assessment dimensions in existing technologies and accurately assessing the efficiency of each aspect and the overall operational efficiency.

[0051] This embodiment introduces a characteristic correlation factor into the objective function of the DEA model and sets an upper limit constraint on slack variables. Based on multi-dimensional data and weighted calculations, the characteristic correlation factor can accurately quantify the complex relationships between urban water-related infrastructure indicators, enabling the model to more accurately reflect the actual contribution of each indicator when calculating efficiency, making the efficiency assessment more realistic and scientifically sound. Setting an upper limit constraint on slack variables prevents excessive amplification of slack variables, addressing the problem of traditional DEA models where excessive amplification of slack variables leads to efficiency results deviating from reality, thus improving the accuracy of the assessment results.

[0052] This embodiment provides a method for evaluating the efficiency of urban water-related infrastructure, which can be used on mobile terminals such as mobile phones and tablets. Figure 2 This is a flowchart of an urban water-related infrastructure efficiency assessment method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0053] Step S201: Obtain the current data and predicted data of various indicators of the water-related infrastructure in the city to be evaluated in the current stage and the future planning stage, and divide them into different stages according to the time dimension and the water-related cycle dimension to obtain the stage indicator dataset corresponding to each stage.

[0054] The indicators for the urban water-related infrastructure to be evaluated include multiple input indicators and multiple output indicators. Specifically, the current data of each input indicator and each output indicator of the urban water-related infrastructure to be evaluated in the current stage are obtained, and the predicted data of each input indicator and each output indicator of the urban water-related infrastructure to be evaluated in the future planning stage are obtained to construct an indicator dataset. The indicator dataset is then divided into different stages according to the time dimension and the water-related cycle dimension to obtain the stage indicator dataset corresponding to each stage.

[0055] The indicator dataset is divided into the current stage and the future planning stage in the time dimension, and the current stage and the future planning stage are further divided in the water-related cycle dimension, resulting in multiple different stages and the corresponding stage indicator datasets for each stage. The water-related cycle dimension can include the water production stage and the treatment and disposal stage.

[0056] For example, collecting current data on the water-related infrastructure of the city to be evaluated at the current stage and projected data for the next 5 years during the future planning stage, as detailed below:

[0057] The current input indicators include: the actual total water consumption of planned water users (x1a0, 10,000 cubic meters), the current total population (x1b0, 10,000 people), the current fiscal budget expenditure (x1c0, 10,000 yuan), the existing fixed asset investment in water-related infrastructure (x2a0, 10,000 yuan), the existing pipeline length (x2b0, kilometers), and the current pipeline density. ,in S represents the urban built-up area, measured in square kilometers.

[0058] The output indicators for the current stage include: current GDP (y1a0, 10,000 yuan), current total wastewater treatment volume (y2a0, 10,000 cubic meters), and current dry sludge disposal volume (y2b0, tons).

[0059] The following are the investment indicators for the next five years in the future planning phase: total population (x1b5, 10,000 people) in five years, obtained from a population migration prediction model based on a gravity model and household registration policy; total water consumption (x1a5, 10,000 cubic meters) in five years, revised under the IPCC RCP4.5 climate scenario; projected annual fiscal budget expenditure in five years (x1c5); existing fixed asset investment in water-related infrastructure in five years, matching the projected population (x2a5, 10,000 yuan); planned pipeline length in five years, matching the projected population (x2b5, kilometers); and pipeline density in five years, matching the projected population. ,in S5 represents the urban built-up area five years from now, expressed in square kilometers.

[0060] Output indicators for the next 5 years in the future planning stage: GDP forecast for the next 5 years (y1a5, 10,000 yuan), total wastewater treatment volume for the next 5 years (y2a5, 10,000 cubic meters), and dry sludge disposal volume for the next 5 years (y2b5, 10,000 cubic meters).

[0061] The aforementioned current data and projected data for the next 5 years can be obtained through relevant reports or prediction models. After obtaining this extensive data, noise filtering can be performed. Specifically, K-nearest neighbor (KNN) noise filtering can be implemented, employing a bi-subset cross-validation logic. A collaborative filtering rule between current and projected data is designed, and a KNN classification model is constructed based on Euclidean distance. The model is first trained using the current data of the input indicators, and then validated against the current data of the output indicators. Data where the actual label contradicts the classification label is removed, such as data from a certain city. kilometers, but 10,000 cubic meters; then based on the input indicator forecast data ( , Optimize the model for output indicator prediction data (etc.) ) to verify and remove data with conflicting prediction logic (such as data from a certain city). Growth of 10%, but (A 20% decrease) ultimately yields a clean base + prediction dataset.

[0062] After obtaining the current data and the forecast data for the next 5 years, the process is divided into the current stage and the future planning stage in terms of time dimension, according to the stage division method of this step. The current stage and the future planning stage are further divided in terms of water cycle dimension. The water cycle dimension can include the water production stage and the treatment and disposal stage. The input-output indicator system of the whole process obtained by the division is shown in Table 1, including the current stage-water production stage, the current stage-treatment and disposal stage, the future planning stage-water production stage, and the future planning stage-treatment and disposal stage.

[0063] Table 1

[0064]

[0065] Step S202: Based on the current and predicted data of each indicator, calculate the characteristic correlation factor corresponding to each indicator.

[0066] Specifically, step S202 above includes:

[0067] Step S2021: Obtain the current data and predicted data of various indicators in several sample cities, and calculate the mean of the current data and the mean of the predicted data of various indicators in several sample cities.

[0068] Step S2022: Determine the weight of the current data and the weight of the predicted data in each indicator of the city to be evaluated.

[0069] Step S2023: Based on the current data of various indicators of the city to be evaluated, the predicted data of various indicators of the city to be evaluated, the mean of the current data of various indicators of several sample cities, the mean of the predicted data of various indicators of several sample cities, and the weight of the current data and the weight of the predicted data in the various indicators of the city to be evaluated, calculate the characteristic correlation factor of each indicator.

[0070] Based on the current total population For example, first, following step S2021, obtain current data and projected data for the total population of several sample cities over the next five years, and calculate the mean of the current total population data. and the mean of the predicted data Then, the weight α of the current data and the weight β of the predicted data can be determined according to empirical formulas or other weight determination methods. The characteristic correlation factor corresponding to this total population indicator is then... ,in, The average total population of the sample cities. The sample cities are projected to have an average total population over the next five years. Characteristic correlation factors are used for subsequent model corrections to reflect the impact of indicators such as total population on efficiency.

[0071] In some alternative implementations, the weight α is 0.6 and the weight β is 0.4.

[0072] Step S203: Based on the indicator datasets of each stage and the characteristic correlation factors of each indicator, the improved DEA model is used to solve the problem and obtain the weights of each indicator in the indicator datasets of each stage.

[0073] The improved DEA model introduces a characteristic correlation factor into the objective function of the DEA-BCC model and sets upper limit constraints on slack variables. The specific improvements include the following two aspects:

[0074] On the one hand, characteristic correlation factors corresponding to each indicator are introduced into the objective function of the DEA-BCC model to form a new objective function.

[0075] The new objective function formula is:

[0076]

[0077] In the formula, The objective function aims to minimize the inefficiency value, specifically by minimizing the combined inefficiency of adjusted input redundancy and output insufficiency, thereby indirectly maximizing the efficiency of the decision-making unit (DMU). Here, m represents the number of input indicators, and s represents the number of output indicators. Let represent the slack variable of the i-th input indicator, used to reflect input redundancy, such as fiscal budget surplus, etc. This represents the actual value of the i-th input indicator, such as... Ten thousand yuan; This represents the characteristic correlation factor of the i-th input indicator; This represents a slack variable for the r-th output indicator, reflecting insufficient output, such as failure to meet wastewater treatment standards. This represents the actual value of the r-th output indicator, such as... 10,000 cubic meters; This represents the characteristic correlation factor of the r-th output indicator.

[0078] The constraints are:

[0079]

[0080] Where: n represents the number of decision-making units, such as 30 cities. ; This represents the weight coefficient of the j-th decision-making unit, reflecting the city's contribution to the efficiency frontier. This represents the value of the i-th input indicator for the j-th decision-making unit, such as the value of the 5th city. 10,000 cubic meters; This represents the r-th output indicator value of the j-th decision-making unit, such as the 5th city. 10,000 cubic meters.

[0081] On the other hand, the potential slack variables for each indicator in the present and future are calculated separately. Based on the potential slack variables, the upper limit constraints of the slack variables corresponding to each indicator in the objective function are determined. The steps are as follows:

[0082] Step a1: Obtain current and predicted data for various indicators in several sample cities.

[0083] For example, select the best basic sample, which is the top 5 cities with the lowest current input and the highest output, and the best planning sample, which is the top 5 cities with the most reasonable input and the best output predicted for the next five years.

[0084] Step a2: Based on the current data of various indicators in several sample cities, calculate the current potential slack variables of each indicator in each sample city. Based on the predicted data of various indicators in several sample cities, calculate the future planning potential slack variables of each indicator in each sample city. Let the i-th input indicator... For example, the calculation method is as follows:

[0085] The optimal basic indicator quantity is , This represents the actual value of the i-th input indicator for the k-th sample city.

[0086] Optimal indicator quantity for planning: , Let i be the predicted value of the i-th input indicator for the k-th sample city over the next five years;

[0087] Current potential slack variables: , Let be the actual value of the i-th input indicator for the city to be evaluated;

[0088] Potential slack variables for future planning: , Let be the five-year forecast value of the i-th input indicator for the city to be evaluated.

[0089] Step a3: Weight the current potential slack variables and future planning potential slack variables of each indicator to obtain the comprehensive potential slack variables of each indicator.

[0090] Then the i-th input indicator The combined potential slack variables are represented as follows: Current operating weight It can be 60%, and the weighting for future planning. It could be 40%.

[0091] Similarly, the combined potential slack variables for the r-th output indicator: ,in Let r be the current potential slack variable for the r-th output indicator. Let r be the potential slack variable for future planning of the r-th output indicator.

[0092] Step a4: Calculate the initial upper limit constraint based on the comprehensive potential slack variables of each indicator.

[0093] In some alternative implementations, take , The average of the first few maximum values ​​is used as the initial upper limit constraint UB.

[0094] Step a5: For the initial upper limit constraint, introduce the prediction correction parameter to obtain the upper limit constraint of the slack variables corresponding to each indicator.

[0095] Based on the Charnes-Cooper transform, a prediction uncertainty coefficient is introduced. ( (This reflects the error in future population and climate predictions), the formula is: ,in These are the top 5 smallest parameter values ​​of the current data. The t obtained from the top 5 smallest parameter values ​​of the predicted data is the prediction correction parameter.

[0096] The final constraint is To avoid excessive amplification of slack variables, for example, if a city's UB = 3 million yuan and t = 0.9, the actual redundancy limit is 2.7 million yuan, which is in line with the feasibility of fiscal adjustment.

[0097] Step S204: Based on the indicator datasets of each stage, the characteristic correlation factors of each indicator, and the weights of each indicator, the efficiency and overall efficiency of the urban water-related infrastructure to be evaluated at each stage are obtained.

[0098] Specifically, step S204 above includes:

[0099] Step S2041: Based on the stage indicator datasets of each stage included in the current stage, the characteristic correlation factors of each indicator, and the weights of each indicator, calculate the stage efficiency of each stage included in the current stage and the total efficiency of the current stage.

[0100] Specifically, based on the current stage-water production stage's indicator dataset, the characteristic correlation factors of each indicator, and the weights of each indicator, the stage efficiency of the current stage-water production stage is calculated:

[0101]

[0102] In the formula, for The corresponding weights for Corresponding characteristic correlation factors; for The corresponding weights for Corresponding characteristic correlation factors; for The corresponding weights for Corresponding characteristic correlation factors; for The corresponding weights for The corresponding characteristic correlation factor.

[0103] Based on the current stage-processing and disposal stage indicator dataset, the characteristic correlation factors of each indicator, and the weights of each indicator, calculate the stage efficiency of the current stage-processing and disposal stage:

[0104]

[0105] In the formula, for The corresponding weights for Corresponding characteristic correlation factors; for The corresponding weights for Corresponding characteristic correlation factors; for The corresponding weights for Corresponding characteristic correlation factors; for The corresponding weights for Corresponding characteristic correlation factors; for The corresponding weights for The corresponding characteristic correlation factor.

[0106] Based on the current stage efficiency of water production and the current stage efficiency of treatment and disposal, calculate the overall efficiency of the current stage: .

[0107] Step S2042: Based on the stage indicator datasets of each stage included in the future planning stage, the characteristic correlation factors of each indicator, and the weights of each indicator, calculate the stage efficiency of each stage included in the future planning stage and the total efficiency of the future planning stage.

[0108] Based on the dataset of phase indicators for the future planning phase - water production phase, the characteristic correlation factors of each indicator, and the weights of each indicator, the phase efficiency of the future planning phase - water production phase is calculated:

[0109]

[0110] In the formula, for The corresponding weights for Corresponding characteristic correlation factors; for The corresponding weights for Corresponding characteristic correlation factors; for The corresponding weights for Corresponding characteristic correlation factors; for The corresponding weights for The corresponding characteristic correlation factor.

[0111] Based on the stage indicator dataset of the future planning phase and the treatment and disposal phase, the characteristic correlation factors of each indicator, and the weights of each indicator, the stage efficiency of the future planning phase and the treatment and disposal phase is calculated:

[0112]

[0113] In the formula, for The corresponding weights for Corresponding characteristic correlation factors; for The corresponding weights for Corresponding characteristic correlation factors; for The corresponding weights for Corresponding characteristic correlation factors; for The corresponding weights for Corresponding characteristic correlation factors; for The corresponding weights for The corresponding characteristic correlation factor.

[0114] Based on the stage efficiency of the future planning phase - water production phase and the stage efficiency of the future planning phase - treatment and disposal phase, calculate the overall efficiency of the future planning phase: .

[0115] Step S2043: Based on the total efficiency of the current stage and the total efficiency of the future planning stage, obtain the comprehensive efficiency of the urban water-related infrastructure to be evaluated: .

[0116] In some alternative implementations, It can be 0.5. In other implementations, the value is 0.5. It can be 0.6. It is 0.4.

[0117] In some alternative implementations, the efficiency value can be overlaid with population density kernel maps, pipeline density kernel maps, etc., to identify high-potential areas, such as... But predictions The new urban areas provide a basis for optimizing infrastructure layout.

[0118] The urban water infrastructure efficiency assessment method provided in this embodiment comprehensively covers the current and future development status of urban water infrastructure by constructing and integrating current and predicted datasets for each indicator. This avoids the one-sidedness of assessment based solely on current data and provides a richer and more complete data foundation for scientific assessment. The assessment is divided into two major stages: current and future planning. Each stage is further subdivided into water production and treatment processes, enabling precise identification of inefficiencies and improving the accuracy and practicality of the assessment. By introducing correlation factors based on the computational characteristics of sample city data, the impact of each indicator on the efficiency of water infrastructure is quantified, correcting assessment biases caused by differences in city size and development stage, thus enhancing the scientific rigor and decision-making guidance value of the efficiency assessment. The method is applied to the DEA-BCC model. The objective function incorporates characteristic correlation factors and sets upper limits for slack variables to address the problem of traditional models neglecting spatial heterogeneity among indicators, achieving improvements in both the present and future dimensions. Dynamically selecting samples to calculate potential slack variables in both dimensions and weighting them to determine upper limits for slack variables solves the problem of excessive amplification of slack variables in traditional models, balancing short-term efficiency with long-term adaptability. Introducing prediction correction parameters ensures that the constraints are realistically feasible. Based on indicator datasets at each stage, characteristic correlation factors, and indicator weights, the efficiency of each stage and the overall efficiency are calculated, providing a clear understanding of the operational status of water-related infrastructure and offering scientific quantitative data for investment decisions and urban planning. Furthermore, the introduction of characteristic correlation factors fully considers the differentiated characteristics of cities, making the evaluation results more accurate and objective.

[0119] This embodiment also provides an urban water-related infrastructure efficiency assessment device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0120] This embodiment provides a device for evaluating the efficiency of urban water-related infrastructure, such as... Figure 3 As shown, it includes:

[0121] The data acquisition module 301 is used to acquire the current data of various indicators of the water-related infrastructure in the city to be evaluated in the current stage and the predicted data in the future planning stage. It is divided into different stages according to the time dimension and the water-related cycle dimension to obtain the stage indicator dataset corresponding to each stage.

[0122] The characteristic correlation factor calculation module 302 is used to calculate the characteristic correlation factor corresponding to each indicator based on the current data and predicted data of each indicator.

[0123] The indicator weight calculation module 303 is used to solve the problem using the improved DEA model based on the indicator datasets of each stage and the characteristic correlation factors of each indicator, and to obtain the weights of each indicator in the indicator datasets of each stage. The improved DEA model introduces characteristic correlation factors into the objective function of the DEA-BCC model and sets upper limit constraints on slack variables.

[0124] The efficiency assessment module 304 is used to obtain the efficiency and overall efficiency of the urban water-related infrastructure to be evaluated at each stage based on the indicator datasets of each stage, the characteristic correlation factors of each indicator, and the weights of each indicator.

[0125] Specifically, the aforementioned characteristic correlation factor calculation module 302 includes:

[0126] The sample calculation unit is used to obtain the current and predicted data of various indicators in several sample cities, and to calculate the mean of the current data and the mean of the predicted data of various indicators in several sample cities.

[0127] The weight determination unit is used to determine the weight of the current data and the weight of the predicted data in each indicator of the city to be evaluated.

[0128] The characteristic correlation factor calculation unit is used to calculate the characteristic correlation factor of each indicator based on the current data of each indicator of the city to be evaluated, the predicted data of each indicator of the city to be evaluated, the mean of the current data of each indicator of several sample cities, the mean of the predicted data of each indicator of several sample cities, and the weight of the current data and the weight of the predicted data in each indicator of the city to be evaluated.

[0129] Specifically, the efficiency evaluation module 304 mentioned above includes:

[0130] The current stage efficiency calculation unit is used to calculate the stage efficiency of each stage and the total efficiency of the current stage based on the stage indicator dataset, the characteristic correlation factors of each indicator, and the weight of each indicator.

[0131] The efficiency calculation unit for the future planning phase is used to calculate the phase efficiency of each phase and the overall efficiency of the future planning phase based on the phase indicator datasets, characteristic correlation factors of each indicator, and weights of each indicator.

[0132] The comprehensive efficiency calculation unit is used to obtain the comprehensive efficiency of the urban water-related infrastructure to be evaluated based on the total efficiency of the current stage and the total efficiency of the future planning stage.

[0133] The urban water-related infrastructure efficiency assessment device provided in this embodiment of the invention can execute the urban water-related infrastructure efficiency assessment method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the various modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0134] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0135] The following is a detailed reference. Figure 4 This diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 402 or a program loaded from memory 408 into random access memory (RAM) 403. The RAM 403 also stores various programs and data required for the operation of the electronic device. The processor 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0136] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0137] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 409, or installed from a memory 408, or installed from a ROM 402. When the computer program is executed by the processor 401, it performs the functions defined in the urban water infrastructure efficiency assessment method of the embodiments of the present invention.

[0138] Figure 4The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0139] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the urban water infrastructure efficiency assessment method shown in the above embodiments is implemented.

[0140] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0141] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for evaluating the efficiency of urban water-related infrastructure, characterized in that, The method includes: The current data of various indicators of the water-related infrastructure in the city to be evaluated at the current stage and the predicted data at the future planning stage are obtained to obtain an indicator dataset. The indicator dataset is then divided into different stages according to the time dimension and the water-related cycle dimension to obtain the stage indicator dataset corresponding to each stage. Based on the current and predicted data of each indicator, the characteristic correlation factors corresponding to each indicator are calculated, including: obtaining the current and predicted data of each indicator in several sample cities, and calculating the mean of the current data and the mean of the predicted data of each indicator in several sample cities; determining the weight of the current data and the weight of the predicted data in each indicator of the city to be evaluated; and calculating the characteristic correlation factors of each indicator based on the current data of each indicator of the city to be evaluated, the predicted data of each indicator of the city to be evaluated, the mean of the current data of each indicator of several sample cities, the mean of the predicted data of each indicator of several sample cities, and the weight of the current data and the weight of the predicted data in each indicator of the city to be evaluated. Based on the target datasets of each stage and the characteristic correlation factors of each indicator, the improved DEA model is used to solve the problem and obtain the weights of each indicator in each target dataset. The improved DEA model introduces characteristic correlation factors into the objective function of the DEA-BCC model and sets upper limits for slack variables. Based on the datasets of indicators for each stage, the characteristic correlation factors of each indicator, and the weights of each indicator, the efficiency and overall efficiency of the urban water-related infrastructure to be evaluated at each stage are obtained.

2. The method for evaluating the efficiency of urban water-related infrastructure according to claim 1, characterized in that, The indicators for the urban water-related infrastructure to be evaluated include multiple input indicators and multiple output indicators.

3. The method for evaluating the efficiency of urban water-related infrastructure according to claim 1, characterized in that, The step of dividing the indicator dataset into different stages according to the time dimension and the water immersion cycle dimension to obtain the stage indicator dataset corresponding to each stage includes: The indicator dataset is divided into the current stage and the future planning stage in the time dimension, and the current stage and the future planning stage are further divided in the water-related cycle dimension to obtain multiple different stages and the corresponding stage indicator datasets for each stage. The water-related cycle dimension includes the water production stage and the treatment and disposal stage.

4. The method for evaluating the efficiency of urban water-related infrastructure according to claim 1, characterized in that, The improved DEA model introduces a characteristic correlation factor into the objective function of the DEA-BCC model and sets upper limit constraints on slack variables, including: The objective function of the DEA-BCC model includes various indicators and slack variables for each indicator. By introducing characteristic correlation factors corresponding to each indicator into the objective function, a new objective function is formed. Calculate the current and future potential slack variables for each indicator, and based on the potential slack variables, determine the upper limit constraint of the slack variables corresponding to each indicator in the objective function.

5. The method for evaluating the efficiency of urban water-related infrastructure according to claim 4, characterized in that, The step of calculating the current and future potential slack variables for each indicator, and determining the upper limit constraint of the slack variables corresponding to each indicator in the objective function based on the potential slack variables, includes: Obtain current and predicted data for various indicators in several sample cities; Based on the current data of various indicators in several sample cities, calculate the current potential slack variables of various indicators in each sample city. Based on the predicted data of various indicators in several sample cities, calculate the future planning potential slack variables of various indicators in each sample city. The current potential slack variables and future planning potential slack variables of each indicator are weighted and summed to obtain the comprehensive potential slack variables of each indicator. The initial upper limit constraint is calculated based on the comprehensive potential slack variables of various indicators; For the initial upper limit constraint, a prediction correction parameter is introduced to obtain the upper limit constraint of the slack variables corresponding to each indicator.

6. The method for evaluating the efficiency of urban water-related infrastructure according to claim 3, characterized in that, The steps for obtaining the efficiency and overall efficiency of the urban water-related infrastructure to be evaluated at each stage, based on the datasets of indicators for each stage, the characteristic correlation factors of each indicator, and the weights of each indicator, include: Based on the stage indicator datasets of each stage included in the current stage, the characteristic correlation factors of each indicator, and the weights of each indicator, the stage efficiency of each stage included in the current stage and the total efficiency of the current stage are calculated. Based on the stage indicator datasets, characteristic correlation factors of each indicator, and weights of each indicator in the future planning phase, the stage efficiency of each stage in the future planning phase and the overall efficiency of the future planning phase are calculated. Based on the current overall efficiency and the overall efficiency of the future planning stage, the comprehensive efficiency of the urban water-related infrastructure to be evaluated is obtained.

7. A device for evaluating the efficiency of urban water-related infrastructure, characterized in that, The device includes: The data acquisition module is used to acquire the current data of various indicators of the water-related infrastructure in the city to be evaluated at the current stage and the predicted data at the future planning stage. It is divided into different stages according to the time dimension and the water-related cycle dimension to obtain the stage indicator dataset corresponding to each stage. The characteristic correlation factor calculation module is used to calculate the characteristic correlation factors corresponding to each indicator based on the current data and predicted data of each indicator. This includes: obtaining the current data and predicted data of each indicator in several sample cities, and calculating the mean of the current data and the mean of the predicted data of each indicator in several sample cities; determining the weight of the current data and the weight of the predicted data in each indicator of the city to be evaluated; and calculating the characteristic correlation factors of each indicator based on the current data of each indicator of the city to be evaluated, the predicted data of each indicator of the city to be evaluated, the mean of the current data of each indicator of several sample cities, the mean of the predicted data of each indicator of several sample cities, and the weight of the current data and the weight of the predicted data in each indicator of the city to be evaluated. The indicator weight calculation module is used to solve the problem using an improved DEA model based on the indicator datasets of each stage and the characteristic correlation factors of each indicator, and to obtain the weights of each indicator in each stage indicator dataset. The improved DEA model introduces characteristic correlation factors into the objective function of the DEA-BCC model and sets upper limits for slack variables. The efficiency assessment module is used to obtain the efficiency and overall efficiency of the urban water-related infrastructure to be evaluated at each stage based on the dataset of indicators for each stage, the characteristic correlation factors of each indicator, and the weight of each indicator.

8. An electronic device, characterized in that, include: A memory and a processor are interconnected, the memory storing computer instructions, and the processor executing the computer instructions to perform the urban water infrastructure efficiency assessment method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the urban water-related infrastructure efficiency assessment method according to any one of claims 1 to 6.

Images