Low-carbon city subjective and objective mixed planning interval entropy weighting evaluation method

Abstract

The invention discloses a low-carbon city subjective and objective mixed planning interval entropy weighting evaluation method, and relates to the technical field of city management and low-carbon evaluation, and the method comprises the steps: collecting and preprocessing index data in real time, building a user behavior prediction model according to the index data, and predicting the index data of a user; dynamically adjusting weight distribution of subjective and objective evaluation indexes based on the predicted index data, and constructing a comprehensive evaluation model to calculate a comprehensive score of each region in the city; and formulating optimization measures of each region according to the comprehensive score. A prediction model is established by using a support vector machine, an evaluation result is highly matched with real-time data through dynamic weight adjustment, the hysteresis problem of traditional static evaluation is avoided, and more accurate and flexible low-carbon city evaluation is realized through dynamic adjustment of weight distribution and construction of a comprehensive evaluation model. And the comprehensive score of the urban area is calculated by adopting a nonlinear transformation function, so that the marginal effect change of the evaluation index under different load conditions can be better reflected.

Description

Technical Field

[0001] The invention relates to the technical field of urban management and low-carbon evaluation, in particular to an interval entropy weighted evaluation method for subjective and objective mixed planning of a low-carbon city. Background Art

[0002] With the intensification of global climate change and increasingly serious environmental problems, the construction of low-carbon cities has gradually become one of the important goals of sustainable development in countries around the world. In this context, the evaluation and planning of low-carbon development in cities is particularly critical. Most of the existing low-carbon city evaluation methods rely on a static evaluation system, that is, fixed evaluation indicators and weights are used to measure the carbon emissions, energy consumption and environmental participation of residents in different areas of the city. However, factors such as the carbon emission characteristics, energy consumption and resident behavior of cities are highly dynamic, resulting in the inability of the static evaluation system to fully reflect the actual situation at various times during the urban development process. The evaluation results are lagging and inaccurate. In addition, the traditional low-carbon city evaluation method has certain limitations in the integration of subjective and objective factors, and it is difficult to fully balance and integrate residents' environmental awareness with actual low-carbon performance. This leads to a lack of accurate reference based on real-time data when city managers formulate low-carbon policies, which affects the effective implementation of low-carbon policies.

[0003] Existing technologies also have obvious deficiencies in the weight allocation of low-carbon city evaluation. Most methods use fixed weights set by default or expert experience, which are difficult to cope with the dynamic changes of various regions at different stages of development. There are large differences in carbon emission characteristics, energy use habits and resident behavior patterns in different urban areas. These differences are constantly adjusted with time and environmental changes. If the weights cannot be dynamically adjusted according to real-time data, the evaluation results may not reflect the actual situation, resulting in the low-carbon performance of some areas being underestimated or overestimated. Traditional methods have failed to make full use of big data technology and find it difficult to analyze and process complex multi-dimensional data in real time, resulting in large deviations in evaluation results. Especially in the prediction of user behavior, existing technologies generally lack the ability to dynamically predict user behavior and carbon emission trends by combining historical data and real-time data, which further limits the accuracy and reliability of the low-carbon city evaluation system. Summary of the invention

[0004] In view of the problems existing in the above-mentioned existing low-carbon city subjective and objective mixed planning interval entropy weighting evaluation method, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is to solve the problems of static evaluation, inflexible weight allocation, delayed data processing, etc. in the prior art.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a low-carbon city subjective and objective mixed planning interval entropy weighted evaluation method, which includes: Collect and pre-process indicator data in real time, build a user behavior prediction model based on the indicator data, and predict the user's indicator data; Dynamically adjust the weight distribution of subjective and objective evaluation indicators based on the predicted indicator data, and build a comprehensive evaluation model to calculate the comprehensive score of each area in the city; Formulate optimization measures for each region based on the comprehensive scores; Store and back up your data.

[0007] As a preferred solution of the low-carbon city subjective and objective mixed planning interval entropy weighted evaluation method of the present invention, wherein: the real-time collection of index data refers to establishing a comprehensive evaluation index system, including subjective evaluation indicators and objective evaluation indicators, and collecting index data of different areas in the city from different target data sources in real time; The target data sources include online feedback platforms, community management departments, urban transportation management bureaus, energy companies, and environmental protection departments; The subjective evaluation indicators include resident satisfaction, policy support and community participation; The objective evaluation indicators include traffic flow, energy consumption and carbon emission intensity.

[0008] As a preferred scheme of the interval entropy weighted evaluation method for the subjective and objective mixed planning of low-carbon cities described in the present invention, the preprocessing refers to the preprocessing of the collected indicator data, including using the Z-score method to detect outliers on the indicator data, deleting the detected outliers and using the interpolation method to fill in the missing data, and normalizing all indicator data.

[0009] As a preferred solution of the interval entropy weighted evaluation method for the subjective and objective mixed planning of low-carbon cities described in the present invention, wherein: the user behavior prediction model is established based on the indicator data, and the indicator data of the user is predicted by integrating the pre-processed indicator data into a data set; Use support vector machine method to establish user behavior prediction model; Divide the dataset into training and testing sets; Substitute the training set into the user behavior prediction model for training; Select radial basis function as kernel function; Use grid search method to optimize model parameters, evaluate the accuracy of each set of parameters and select the optimal parameter combination; Use the test set to validate the model, calculate the evaluation index, and adjust the model based on the evaluation index; Substitute the real-time indicator data into the trained user behavior prediction model to obtain the predicted indicator data.

[0010] As a preferred solution of the interval entropy weighted evaluation method for subjective and objective mixed planning of low-carbon cities described in the present invention, wherein: the weight distribution of the subjective and objective evaluation indicators is dynamically adjusted based on the predicted indicator data, which refers to using the hierarchical analysis method to construct a subjective evaluation indicator judgment matrix and an objective evaluation indicator judgment matrix respectively; The subjective evaluation index judgment matrix is ​​obtained by comparing the importance of subjective evaluation indexes by experts in pairs, and constructing a third-order matrix C to represent the relative importance of the three subjective evaluation indexes. The subjective evaluation index judgment matrix is: , where C 12 Indicates the importance score of the first subjective evaluation index data relative to the second subjective evaluation index data; Calculating the weight of the subjective evaluation index according to the importance score, including calculating the product of the importance score of each row in the subjective evaluation index judgment matrix, taking the xth root of the product of each row to obtain the weight value of each row, and normalizing the weight value of each row; The objective evaluation index judgment matrix is ​​a matrix that is used to calculate the maximum and minimum values ​​of each objective evaluation index data and to perform forward normalization processing to obtain a standardized objective evaluation index judgment matrix; Calculate the entropy value of each objective evaluation indicator, and normalize the entropy value to obtain the weight of the objective evaluation indicator; Construct a time-varying weight function to dynamically adjust the weight. The formula is: , where P n (t) represents the value of the nth evaluation index in the index data at time point t, P n (t-1) represents the value of the nth evaluation index in the index data at time point t-1. is the regulating factor, represents the acceleration adjustment factor, represents the symbol of partial derivative, W n,0 Indicates the weight of the nth evaluation index before adjustment in the index data, W n (t) represents the adjusted weight of the nth evaluation indicator in the indicator data at time point t.

[0011] As a preferred solution of the low-carbon city subjective and objective mixed planning interval entropy weighted evaluation method of the present invention, wherein: the construction of a comprehensive evaluation model to calculate the comprehensive score of each area in the low-carbon city includes: A comprehensive evaluation model is constructed to calculate the comprehensive scores S(t) of different areas in the city. The formula is: , where W i (t) represents the adjusted weight of the i-th subjective evaluation index at time point t, is the S-type nonlinear function in the nonlinear transformation function, D i (t) represents the value of the i-th subjective evaluation index at time point t, represents the attenuation factor, dt represents the small change of the integral variable t, h represents the total number of subjective evaluation indicators, W j (t) represents the adjusted weight of the jth objective evaluation index at time point t, O j (t) represents the value of the jth objective evaluation index at time point t, m represents the total number of objective evaluation indicators, and T is the entire acquisition period.

[0012] As a preferred solution of the low-carbon city subjective and objective mixed planning interval entropy weighted evaluation method of the present invention, wherein: the optimization measures for each area are formulated according to the comprehensive score, which means setting the comprehensive score threshold according to the comprehensive score of different areas in the city. and And divide the interval into, including, like , indicating that the current target area of ​​the city is in the high score range, then maintain the existing advantages, continue to implement the existing low-carbon policies and measures, explore cutting-edge technologies, promote zero-carbon buildings, develop smart grids and introduce more clean energy technologies; like , indicating that the current city's target area is in the medium score range, then focus on the weak links, find the weak links that affect the comprehensive score by analyzing the indicator data, and perform targeted optimization. Optimize citizen participation. It is recommended to enhance residents' environmental awareness through publicity and education activities to promote the improvement of community environmental protection participation; like , indicating that the current target area of ​​the city is in the low-scoring range, emergency measures should be implemented and taken to deal with environmental problems in the area, including reducing high-emission industries and promoting green infrastructure construction, and strengthening policy supervision. Low-scoring areas usually have poor policy implementation. It is recommended to increase the implementation of environmental protection policies and strengthen environmental protection monitoring and supervision mechanisms.

[0013] A computer device comprises: a memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the entropy weighted evaluation method for the subjective and objective mixed planning interval of a low-carbon city are implemented.

[0014] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a method for evaluating the entropy weighting of intervals of subjective and objective mixed planning of a low-carbon city are implemented.

[0015] The beneficial effects of the present invention are as follows: a prediction model is established using a support vector machine, and the evaluation results are highly matched with real-time data through dynamic weight adjustment, thereby avoiding the lag problem of traditional static evaluation. A more accurate and flexible low-carbon city evaluation is achieved by dynamically adjusting weight distribution and building a comprehensive evaluation model. The comprehensive score of the urban area is calculated using a nonlinear transformation function, which can better reflect the changes in the marginal effect of the evaluation indicators under different load conditions. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0017] Figure 1 Flow chart of interval entropy weighted evaluation method for subjective and objective mixed planning of low-carbon cities.

[0018] Figure 2 Schematic diagram of the process of making optimization recommendations for each area based on the comprehensive score. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0020] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0021] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0022] Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a method for evaluating the entropy weighted interval of a low-carbon city's subjective and objective mixed planning. The method for evaluating the entropy weighted interval of a low-carbon city's subjective and objective mixed planning includes the following steps: S1. Collect and pre-process indicator data in real time, establish a user behavior prediction model based on the indicator data, and predict the user's indicator data; Specifically, real-time collection of indicator data refers to establishing a comprehensive evaluation indicator system, including subjective evaluation indicators and objective evaluation indicators, and collecting indicator data from different areas in the city from different target data sources in real time; The target data sources include online feedback platforms, community management departments, urban transportation management bureaus, energy companies, and environmental protection departments; The subjective evaluation indicators include residents' satisfaction (measures residents' acceptance and satisfaction with low-carbon policies), policy support (evaluates the support of policymakers for low-carbon city construction, reflects the willingness and actions of decision-makers) and community participation (measures residents' enthusiasm for participating in environmental protection activities, reflects citizens' awareness of participating in low-carbon city construction); The objective evaluation indicators include traffic flow (the number of vehicles per hour in the target area), energy consumption (the amount of energy consumed in the target area) and carbon emission intensity (the waste recycling rate in the target area).

[0023] By establishing a comprehensive evaluation index system and collecting subjective and objective indicator data from different areas of the city in real time, we can obtain key information on the development of low-carbon cities in a comprehensive and timely manner. Subjective evaluation indicators such as resident satisfaction, policy support and community participation reflect the attitudes and participation of citizens and policymakers in low-carbon policies; objective evaluation indicators such as traffic flow, energy consumption and carbon emission intensity provide actual data support for low-carbon development in the region. Overall, this process achieves comprehensive coverage and accurate collection of data, provides an efficient and reliable data basis for the subsequent comprehensive evaluation of low-carbon cities, and ensures that the evaluation is more scientific and accurate.

[0024] Furthermore, preprocessing refers to preprocessing the collected indicator data including detecting outliers on the indicator data using the Z-score method, deleting the detected outliers and filling the missing data using the interpolation method, and normalizing all indicator data.

[0025] Through the preprocessing steps, the Z-score method is used to detect outliers on the collected indicator data, effectively identify and delete abnormal data, and use the interpolation method to fill in missing data to ensure the integrity and reliability of the data. All indicators are normalized so that indicators of different dimensions are unified within the same range to facilitate subsequent analysis and calculation. The beneficial effect of this preprocessing method is to improve data quality, avoid model errors caused by outliers and missing data, and ensure that the results of the subsequent comprehensive evaluation model are more accurate and stable.

[0026] In addition, a user behavior prediction model is established based on the indicator data. Predicting the indicator data of the user means integrating the preprocessed indicator data into a data set; Use support vector machine method to establish user behavior prediction model; Divide the dataset into training and testing sets; Substitute the training set into the user behavior prediction model for training; Select radial basis function as kernel function; Use grid search method to optimize model parameters, evaluate the accuracy of each set of parameters and select the optimal parameter combination; Use the test set to validate the model, calculate the evaluation index, and adjust the model based on the evaluation index; Substitute the real-time indicator data into the trained user behavior prediction model to obtain the predicted indicator data.

[0027] The present invention integrates the preprocessed indicator data into a data set, adopts the support vector machine method to establish a user behavior prediction model, combines the radial basis function kernel and the grid search method to optimize the model parameters, ensures that the accuracy of the model on different data sets is maximized, and divides the data set into a training set and a test set. The trained model can effectively predict the user's indicator data and adjust and optimize according to the verification results of the test set. This method not only improves the prediction accuracy of the model, but also can dynamically adapt to real-time data changes, ensures that the prediction of user behavior and indicator data is more accurate, and provides a reliable basis for subsequent evaluation and decision-making.

[0028] S2. Dynamically adjust the weight distribution of subjective and objective evaluation indicators based on the predicted indicator data, and build a comprehensive evaluation model to calculate the comprehensive score of each area in the city; Specifically, dynamically adjusting the weight distribution of subjective and objective evaluation indicators based on predicted indicator data refers to using the analytic hierarchy process to construct a subjective evaluation indicator judgment matrix and an objective evaluation indicator judgment matrix respectively; The subjective evaluation index judgment matrix is ​​obtained by comparing the importance of subjective evaluation indexes by experts in pairs, and constructing a third-order matrix C to represent the relative importance of the three subjective evaluation indexes. The subjective evaluation index judgment matrix is: , where C 12 Indicates the importance score of the first subjective evaluation index data relative to the second subjective evaluation index data; Importance rating follows the following 9-level scale: 1: Both indicators are equally important; 3: One indicator is slightly more important than another indicator; 5: One indicator is significantly more important than another indicator; 7: One indicator is very important relative to another indicator; 9: One indicator is extremely important relative to another indicator; 2, 4, 6, 8: intermediate values ​​between the above scores, used for more detailed comparisons; Calculate the weight of the subjective evaluation index according to the importance score, including calculating the product of the importance score of each row in the subjective evaluation index judgment matrix, taking the xth root of the product of each row to obtain the weight value of each row (x is the order of the subjective evaluation index judgment matrix), and normalizing the weight value of each row so that the sum of the weight values ​​of each row is 1; If the weight value of the row is large, the corresponding indicator is more important than other indicators, indicating that experts believe that the indicator has a greater impact on the evaluation of low-carbon cities and is given a higher priority in the decision-making process; If the weight value of the row is small, the corresponding indicator is less important than other indicators, indicating that experts believe that the indicator has little impact on the evaluation of low-carbon cities and is given a lower priority in the decision-making process; In subjective evaluation, the traditional hierarchical analysis method simply compares two by two. However, the present invention further subdivides subjective evaluation indicators, such as resident satisfaction, policy support, and public participation indicators, and performs more detailed decomposition and pairwise comparison of the indicators. This more detailed hierarchical division helps to obtain more accurate weight distribution. The objective evaluation index judgment matrix is ​​a matrix that is used to calculate the maximum and minimum values ​​of each objective evaluation index data and to perform forward normalization processing to obtain a standardized objective evaluation index judgment matrix; Calculate the entropy value of each objective evaluation indicator, normalize the entropy value to obtain the weight of the objective evaluation indicator, and ensure that the sum of the weights is 1; In weight adjustment, the more common approach is static allocation or linear adjustment based on data, that is, weight calculation is performed based on direct changes in data. Common weight adjustment methods rarely consider the impact of accelerated changes in historical data on weights. The introduction of the historical change rate term captures the rate at which the indicator changes over time, thereby dynamically adjusting the current weight. This is different from the traditional static weight calculation method and enables the weight to reflect the changes in the indicator in real time. The expression is: , where P n (t) represents the value of the nth evaluation index in the index data at time point t, P n (t-1) represents the value of the nth evaluation indicator in the indicator data at time point t-1; The acceleration term is introduced to reflect the impact of the rate of change of indicator data on the weight. By capturing the acceleration trend of data changes, the weight can be adjusted more sensitively. If the data fluctuates greatly, the acceleration term can further smooth or intensify the change of weight, providing a more sensitive response mechanism. The expression is: ,in, Represents the symbol of partial derivative, which is used to represent the rate of change of a multivariable function relative to a specific variable, P n(t) represents the value of the nth evaluation indicator in the indicator data at time point t; The weight is adjusted according to the change of time and data through the time-varying weight function. The usual time-varying weight function formula is relatively simple. It only adjusts the weight according to a certain change trend of time or data. The formula is: ,in, It is an adjustment factor used to balance the weight changes caused by data changes and control the impact of current data changes on weights. It represents the change of the nth evaluation index in the index data at time point t, which is usually the difference between the current index data and the index data at the previous time point. n,0 Indicates the weight of the nth evaluation index before adjustment in the index data, W n (t) represents the adjusted weight of the nth evaluation indicator in the indicator data at time point t; Based on the existing time-varying weight function, a time-varying weight function is constructed to dynamically adjust the weight. The formula is: , where P n (t) represents the value of the nth evaluation index in the index data at time point t, P n (t-1) represents the value of the nth evaluation index in the index data at time point t-1. is the regulating factor, Represents the acceleration adjustment factor, which is used to smooth the impact of acceleration changes on weights. Represents the symbol of partial derivative, which is used to express the rate of change of a multivariable function relative to a specific variable, W n,0 Indicates the weight of the nth evaluation index before adjustment in the index data, W n (t) represents the adjusted weight of the nth evaluation indicator in the indicator data at time point t.

[0029] In the process of constructing weight distribution, the present invention fully combines the hierarchical analysis method and the entropy method to realize the dynamic adjustment of subjective evaluation indicators and objective evaluation indicators, and ensure the scientificity and flexibility of the evaluation system. In the process of constructing subjective evaluation indicators, the hierarchical analysis method is used, and the experts compare each subjective evaluation indicator in pairs, judge the importance of each indicator based on the 9-level scaling rule, and construct a third-order matrix to represent the relative importance of the three subjective evaluation indicators. By calculating the product of each indicator and taking the nth root, the normalized weight value is generated. This method can ensure the accuracy of weight distribution on the basis of subdividing subjective indicators, and further enhance the reliability of evaluation results. Compared with the traditional hierarchical analysis method, the present invention divides the subjective evaluation indicators more finely, which helps to improve the accuracy of the subjective indicator weights and avoid rough estimation. In the process of constructing objective evaluation indicators, the entropy method is used. First, the maximum and minimum values ​​of each objective evaluation indicator are normalized, so as to standardize Data, calculate the entropy value of each objective indicator, and distribute weights through the entropy value to ensure that the sum of the weights is 1. This step can dynamically reflect the actual impact of each objective indicator on the evaluation result, and avoids the deviation that may be caused by static weight distribution. The present invention introduces a time-varying weight function and innovatively adds a historical change rate term and an acceleration term, so that the weight can be dynamically adjusted according to the changing trend and acceleration of the data. The historical change rate term is used to capture the rate of change of data over time, and the acceleration term reflects the second-order derivative of the data change, that is, the acceleration or deceleration of the changing trend. Through these dynamic adjustment mechanisms, the weight distribution of the present invention can not only reflect data changes in real time, but also has a more sensitive response ability. Especially when the data fluctuates greatly, the acceleration term can smooth or amplify the amplitude of the weight adjustment, thereby improving the accuracy and flexibility of the evaluation model. This makes the evaluation system not only suitable for stable data, but also can effectively cope with complex and changing environments, and ultimately improve the accuracy and scientificity of low-carbon city evaluation.

[0030] Furthermore, a comprehensive evaluation model is constructed to calculate the comprehensive scores of each area in a low-carbon city, including: The use of nonlinear transformation functions can improve the sensitivity and accuracy of the comprehensive evaluation model by reasonably reflecting the characteristics of the data, especially in high-load situations, avoiding misjudgments caused by linear relationships and reflecting the decreasing characteristics of the editing effect of resource use; Use the S-type nonlinear function in the nonlinear transformation function Calculate the marginal decreasing effect value of the indicator data at time point t, the formula is:

[0031] , where D i (t) represents the value of the i-th subjective evaluation index at time point t, , is a function parameter used to control the shape of the function; It is used to perform nonlinear transformation on input data. This transformation can make the data show different sensitivities in different ranges, thus better reflecting the actual situation. w controls the initial gain of the indicator data, reflecting the influence of the data in the initial stage; q controls the impact of indicator data growth on the score. When it is large, it can slow down the score growth under high load conditions. Considering the decreasing effect of time on the index, to ensure that the long-term evaluation is more reasonable, the attenuation function is introduced, and the expression is: ,in, represents the attenuation factor; A comprehensive evaluation model is constructed to calculate the comprehensive scores S(t) of different areas in the city. The formula is: , where W i (t) represents the adjusted weight of the i-th subjective evaluation index at time point t, is the S-type nonlinear function in the nonlinear transformation function, D i (t) represents the value of the i-th subjective evaluation index at time point t, represents the attenuation factor, dt represents the small change of the integral variable t, h represents the total number of subjective evaluation indicators, W j (t) represents the adjusted weight of the jth objective evaluation index at time point t, O j (t) represents the value of the jth objective evaluation index at time point t, m represents the total number of objective evaluation indicators, and T is the entire acquisition period.

[0032] The comprehensive evaluation model introduces an S-type nonlinear transformation function to accurately adjust the data sensitivity of different intervals in order to better reflect the actual situation of each area in the low-carbon city. The traditional linear model may lead to oversimplified misjudgment when processing data, especially under high-load conditions, and it is difficult to fully reflect the marginal diminishing effect of resource use. The application of the S-type nonlinear function solves this problem. It can respond quickly when the data is small, and when the data grows to a certain extent, the response becomes gradually flat, thus avoiding the problem of excessive growth of scores under high-load conditions and ensuring the rationality and accuracy of the model. The marginal diminishing effect is reflected by this function, so that as the indicator grows, its impact on the score gradually decreases, reflecting the diminishing characteristics of resource use. The model also introduces an attenuation function to further consider the impact of time on the indicator. By setting the attenuation factor, the model can be used for long-term The influence of data is reasonably weakened to ensure that earlier data will not excessively affect the current evaluation results. This design makes the model more reasonable when conducting long-term evaluation and avoids the interference of historical data on current decision-making, thereby enhancing the adaptability of the model. When calculating the comprehensive scores of various regions in the city, the model dynamically adjusts the weights of subjective and objective evaluation indicators. The subjective indicators obtain weights through the expert scoring method, while the objective indicators are weighted through the entropy method. This method not only integrates the subjective judgment of experts, but also objectively measures the differences between different data in each region through the entropy method. The dynamic adjustment of weights enables the model to reflect the low-carbon development of each region in real time as the data changes. The model combines nonlinear functions, marginal diminishing effects, attenuation functions and dynamic weight adjustments to achieve accurate and comprehensive evaluation of various regions in low-carbon cities, providing a scientific basis for the formulation and optimization of low-carbon policies.

[0033] S3. Develop optimization measures for each region based on the comprehensive scores; Specifically, formulating optimization measures for each area based on the comprehensive scores means setting comprehensive score thresholds based on the comprehensive scores of different areas in the city. and And divide the interval into, including, like When , the target area of ​​the current city is judged to be in the high score range, indicating that the area performs very well in low-carbon development and meets the set high standards; Optimization suggestions for high-scoring ranges include: Maintain existing advantages and continue to implement existing low-carbon policies and measures; Explore cutting-edge technologies, promote zero-carbon buildings, develop smart grids and introduce more clean energy technologies; like When the target area of ​​the current city is judged to be in the medium score range, it means that the performance of the area in low-carbon development is average and has not reached the set high standard; Optimization suggestions for the medium score range include: Focus on weak links, find out the weak links that affect the comprehensive score by analyzing indicator data, and make targeted optimization; Optimize citizen participation. It is recommended to enhance residents' environmental awareness through publicity and education activities to promote the improvement of community environmental protection participation; like When , the current city's target area is judged to be in the low-score range, indicating that the area performs poorly in low-carbon development, and there may be significant environmental problems and inadequate implementation of low-carbon policies; Optimization suggestions for the low score range include: Implement urgent measures to address environmental issues in the region, including reducing high-emission industries and promoting green infrastructure; Strengthen policy supervision. Low-scoring areas usually have poor policy implementation. It is recommended to increase the implementation of environmental protection policies and strengthen environmental protection monitoring and supervision mechanisms.

[0034] The present invention achieves precise low-carbon development management by dividing regional performance according to comprehensive scores and formulating optimization measures for each region according to different score ranges. For high-scoring regions, it is recommended to maintain existing advantages and explore cutting-edge technologies, such as zero-carbon buildings and smart grids; medium-scoring regions are targeted for optimization by identifying weak links and increasing resident participation; low-scoring regions need to take urgent measures to improve environmental problems and strengthen policy supervision. Through this hierarchical optimization method, it is ensured that the performance of each region in low-carbon development can be improved and enhanced in a targeted manner, thereby improving the overall low-carbon management efficiency of the city.

[0035] S4, store data and back it up; Specifically, storing data and backing it up means designing a structured database and storing data in time series. The stored data includes evaluation indicators, weights, time decay factors, comprehensive scores and optimization suggestions, and implementing data backup and security management measures, including cloud storage, redundant backup and data encryption.

[0036] This design ensures the systematicness and continuity of data by constructing a structured database and storing evaluation indicators, weights, time decay factors, comprehensive scores and optimization suggestions in time series, providing reliable data support for low-carbon city evaluation. At the same time, security management measures such as cloud storage, redundant backup and data encryption are implemented to ensure the integrity, security and recoverability of data and prevent data loss and leakage. Overall, this solution improves the efficiency and security of data storage and provides a solid technical foundation for future low-carbon city management and decision-making.

[0037] This is the second embodiment of the present invention, and the difference between this embodiment and the previous embodiment is that:

[0038] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, 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. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments 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., which can store program codes.

[0039] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0040] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0041] The third embodiment of the present invention provides a method for evaluating the entropy weighted interval of a low-carbon city's subjective and objective mixed planning. In order to demonstrate the effectiveness of the method, a comprehensive evaluation index system is first established, including resident satisfaction, policy support, community participation (subjective evaluation index) and traffic flow, energy consumption and carbon emission intensity (objective evaluation index). The data collected are from online feedback platforms, community management departments, urban transportation management bureaus, energy companies and environmental protection departments.

[0042] In the data preprocessing stage, the Z-score method is used to detect outliers in the indicator data, and the interpolation method is used to fill the missing data, and then all the indicator data are normalized; secondly, the support vector machine (SVM) method is used to establish a user behavior prediction model, and the data set is divided into a training set and a test set; finally, the radial basis function is used as the kernel function, and the grid search method is used to optimize the model parameters, the optimal parameter combination is selected, and the test set is used to verify the model.

[0043] In the weight allocation stage, the hierarchical analysis method is used to construct the subjective evaluation index judgment matrix and the objective evaluation index judgment matrix. The importance scores are obtained by experts comparing the importance of subjective evaluation indicators one by one, and the weights of subjective evaluation indicators are calculated. For objective evaluation indicators, the entropy value of each indicator is calculated and normalized to obtain the weight. A time-varying weight function is constructed to dynamically adjust the weight to reflect the changes in indicator data over time.

[0044] Finally, a comprehensive evaluation model is constructed to calculate the comprehensive scores of different areas in the city, and optimization measures for each area are formulated based on the scores. The calculation of the comprehensive score takes into account the weights of subjective and objective evaluation indicators, as well as the S-type nonlinear function in the nonlinear transformation function.

[0045] Table 1 Comprehensive evaluation data of low-carbon urban areas

[0046] By comparing the data in the table, it is clear how each area performs on different indicators. For example, area A scores high in resident satisfaction and community participation, but low in energy consumption and carbon emission intensity, which may mean that the area performs well in resident quality of life and community activities, but needs to improve in energy use and environmental impact.

[0047] Region C performed well in all indicators and had the highest comprehensive score, indicating that it has done a relatively balanced job in low-carbon urban planning. Although Region D scored the highest in policy support, it scored high in energy consumption and carbon emission intensity, which may indicate that the region has received good support at the policy level, but still needs to strengthen energy efficiency and reduce carbon emissions in actual operations.

[0048] Through the calculation of the comprehensive score, it can be seen that region F has the highest comprehensive score, which shows that it performs well in all indicators, especially in resident satisfaction and community participation. This proves the advantages of the invention content in the embodiment compared with the prior art, that is, through real-time data collection and prediction model, dynamic adjustment of weight distribution, and construction of a comprehensive evaluation model, it can more accurately reflect the actual performance of each region and provide a scientific basis for policy formulation.

[0049] In summary, a low-carbon city subjective and objective mixed planning interval entropy weighted evaluation method can more flexibly respond to dynamic changes in urban development and provide more targeted optimization measures for each region by introducing time-varying weight functions and nonlinear transformation functions. This method not only improves the accuracy of the evaluation, but also provides a new perspective and tool for urban sustainable development.

[0050] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit with a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit with a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

Claims

1. A low-carbon city subjective and objective mixed planning interval entropy weighted evaluation method, characterized by: include, Collect and pre-process indicator data in real time, build a user behavior prediction model based on the indicator data, and predict the user's indicator data; Dynamically adjust the weight distribution of subjective and objective evaluation indicators based on the predicted indicator data, and build a comprehensive evaluation model to calculate the comprehensive score of each area in the city; Formulate optimization measures for each region based on the comprehensive scores; Store data and back it up; The dynamically adjusting the weight distribution of subjective and objective evaluation indicators based on the predicted indicator data refers to using the hierarchical analysis method to construct a subjective evaluation indicator judgment matrix and an objective evaluation indicator judgment matrix respectively; The subjective evaluation index judgment matrix is ​​obtained by comparing the importance of subjective evaluation indexes by experts in pairs, and constructing a third-order matrix C to represent the relative importance of the three subjective evaluation indexes. The subjective evaluation index judgment matrix is: , where C 12 Indicates the importance score of the first subjective evaluation index data relative to the second subjective evaluation index data; Calculating the weight of the subjective evaluation index according to the importance score, including calculating the product of the importance score of each row in the subjective evaluation index judgment matrix, taking the xth root of the product of each row to obtain the weight value of each row, and normalizing the weight value of each row; The objective evaluation index judgment matrix is ​​a matrix that is used to calculate the maximum and minimum values ​​of each objective evaluation index data and to perform forward normalization processing to obtain a standardized objective evaluation index judgment matrix; Calculate the entropy value of each objective evaluation indicator, and normalize the entropy value to obtain the weight of the objective evaluation indicator; Construct a time-varying weight function to dynamically adjust the weight. The formula is: , where P n (t) represents the value of the nth evaluation index in the index data at time point t, P n (t-1) represents the value of the nth evaluation index in the index data at time point t-1. is the regulating factor, represents the acceleration adjustment factor, represents the symbol of partial derivative, W n,0 Indicates the weight of the nth evaluation index before adjustment in the index data, W n (t) represents the adjusted weight of the nth evaluation indicator in the indicator data at time point t.

2. The interval entropy weighted evaluation method for subjective and objective mixed planning of low-carbon cities as claimed in claim 1 is characterized by: The real-time collection of index data refers to establishing a comprehensive evaluation index system, including subjective evaluation indicators and objective evaluation indicators, and collecting index data from different areas in the city from different target data sources in real time; The target data sources include online feedback platforms, community management departments, urban transportation management bureaus, energy companies, and environmental protection departments; The subjective evaluation indicators include resident satisfaction, policy support and community participation; The objective evaluation indicators include traffic flow, energy consumption and carbon emission intensity.

3. The interval entropy weighted evaluation method for subjective and objective mixed planning of low-carbon cities as claimed in claim 2 is characterized by: The preprocessing refers to preprocessing the collected indicator data, including using the Z-score method to detect outliers on the indicator data, deleting the detected outliers and using the interpolation method to fill in the missing data, and normalizing all the indicator data.

4. The interval entropy weighted evaluation method for subjective and objective mixed planning of low-carbon cities as claimed in claim 3 is characterized by: The user behavior prediction model is established based on the indicator data, and predicting the indicator data of the user refers to integrating the pre-processed indicator data into a data set; Use support vector machine method to establish user behavior prediction model; Divide the dataset into training and testing sets; Substitute the training set into the user behavior prediction model for training; Select radial basis function as kernel function; Use grid search method to optimize model parameters, evaluate the accuracy of each set of parameters and select the optimal parameter combination; Use the test set to validate the model, calculate the evaluation index, and adjust the model based on the evaluation index; Substitute the real-time indicator data into the trained user behavior prediction model to obtain the predicted indicator data.

5. The interval entropy weighted evaluation method for subjective and objective mixed planning of low-carbon cities as claimed in claim 4 is characterized by: The construction of the comprehensive evaluation model to calculate the comprehensive scores of each area in the low-carbon city includes: A comprehensive evaluation model is constructed to calculate the comprehensive scores S(t) of different areas in the city. The formula is: , where W i (t) represents the adjusted weight of the i-th subjective evaluation index at time point t, is the S-type nonlinear function in the nonlinear transformation function, D i (t) represents the value of the i-th subjective evaluation index at time point t, represents the attenuation factor, dt represents the small change of the integral variable t, h represents the total number of subjective evaluation indicators, W j (t) represents the adjusted weight of the jth objective evaluation index at time point t, O j (t) represents the value of the jth objective evaluation index at time point t, m represents the total number of objective evaluation indicators, and T is the entire acquisition period.

6. The interval entropy weighted evaluation method for subjective and objective mixed planning of low-carbon cities as claimed in claim 5 is characterized by: The optimization measures for each area according to the comprehensive score are formulated to set the comprehensive score threshold according to the comprehensive scores of different areas in the city. and And divide the intervals, include, like , indicating that the current target area of ​​the city is in the high score range, then maintain the existing advantages, continue to implement the existing low-carbon policies and measures, explore cutting-edge technologies, promote zero-carbon buildings, develop smart grids and introduce more clean energy technologies; like , indicating that the current city's target area is in the medium score range, then focus on the weak links, find the weak links that affect the comprehensive score by analyzing the indicator data, and perform targeted optimization. Optimize citizen participation. It is recommended to enhance residents' environmental awareness through publicity and education activities to promote the improvement of community environmental protection participation; like , indicating that the current target area of ​​the city is in the low-scoring range, emergency measures should be implemented and taken to deal with environmental problems in the area, including reducing high-emission industries and promoting green infrastructure construction, and strengthening policy supervision. Low-scoring areas usually have poor policy implementation. It is recommended to increase the implementation of environmental protection policies and strengthen environmental protection monitoring and supervision mechanisms.

7. The interval entropy weighted evaluation method for subjective and objective mixed planning of low-carbon cities according to claim 6 is characterized by: The data storage and backup mentioned above refers to designing a structured database and storing data in time series. The stored data includes evaluation indicators, weights, time decay factors, comprehensive scores and optimization suggestions, and implementing data backup and security management measures, including cloud storage, redundant backup and data encryption.

8. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the low-carbon city subjective and objective mixed planning interval entropy weighted evaluation method described in any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the interval entropy weighted evaluation method for subjective and objective mixed planning of a low-carbon city are implemented according to any one of claims 1 to 7.

Images