A method and system for evaluating the priority of low-utility land redevelopment

Abstract

The application belongs to the technical field of urban planning, and discloses a low-utility land redevelopment priority evaluation method and system. The method introduces the identification of inter-block correlation characteristics, and iteratively corrects the priority score of the block based on the correlation characteristics and a preset correlation effect quantification rule to generate a plurality of block development sequences. Finally, the overall benefit of each sequence is calculated to determine the optimal development strategy, thereby solving the problems that the existing method cannot consider the interaction relationship between blocks, leading to unreasonable evaluation results and being unable to perform combination optimization, and realizing the maximization of regional value.

Description

Technical Field

[0001] The present application relates to the field of urban planning technology, and in particular to a method and system for evaluating the priority of redevelopment of low-efficiency land. Background Art

[0002] In the daily work of urban management departments, inventorying, evaluating, and prioritizing inefficient land use within their jurisdictions for redevelopment is a core task in promoting the intensive use of land resources and optimizing and upgrading urban functions. To this end, management departments generally use a decision-making support system. This system inputs detailed data on various plots in the city, covering a wide range of dimensions, including multiple basic attributes, economic attributes, and social attributes.

[0003] When the system is operational, decision-makers first assign weights to various evaluation indicators based on the city's macro-strategic goals. Once the weights are set, the system scores each parcel of low-efficiency land and calculates its overall priority score through weighted summation or other multi-criteria decision-making models. Finally, the system outputs a list ranked from highest to lowest by score, providing data support for decision-makers to prioritize redevelopment plots. This approach, based on static data and a fixed weight model, can provide effective decision-making guidance during periods of stable urban development and slow external environmental change.

[0004] However, urban development is not static and is often impacted by major projects or policy adjustments. If decision-makers continue to rely on decision-support systems based on historical data and pre-defined weights, their assessment results will be severely distorted. Existing technologies typically rely on operators to manually adjust weights, but this method is crude and fails to accurately reflect the complex and ever-changing needs of urban development.

[0005] Existing decision-making support methods, whether static or heavily manually adjusted, rely on an isolated, independent evaluation of each plot. This assumes that the redevelopment value of each plot is a function of its own attributes, while ignoring the interplay between redevelopment projects. In reality, the redevelopment of a plot is not an isolated event but rather has radiating impacts on surrounding areas. The redevelopment of different plots can have synergistic or antagonistic effects. For example, the successful redevelopment of one plot may increase the value of surrounding plots or create favorable conditions for their subsequent development; conversely, inappropriate development may negatively impact the surrounding environment.

[0006] Such synergistic or antagonistic effects among projects are ubiquitous, but are completely ignored by the existing isolated evaluation methods. This leads to the results of redevelopment priority evaluation being not scientific and reasonable enough, and the overall value of the region cannot be fully tapped. The essence of the problem has changed from "which single plot is optimal" to "which plot combination and development timing is optimal". Decision makers no longer need a simple priority ranking list, but a holistic development strategy that can reveal the inherent relationship among projects and deduce the future urban form and benefits under different development combinations. The existing decision support tools cannot handle such combination optimization problems, so that the decision makers may miss the opportunity to maximize the value of the region through linked development, or make a suboptimal decision that leads to conflicts in regional functions.

[0007] The prior art needs to be improved in view of the above problems. SUMMARY

[0008] In order to solve the problems of the prior art, the present application provides a low-utility land redevelopment priority evaluation method and system, which can effectively solve the problem of isolated evaluation of low-utility land redevelopment priority in the prior art, generate a plot development sequence based on overall benefit optimization by considering the correlation characteristics and mutual influence among plots, and thus provide a more scientific and reasonable redevelopment priority, which helps to maximize the value of the region.

[0009] In a first aspect, the present application provides a low-utility land redevelopment priority evaluation method for evaluating the redevelopment priority of urban low-utility land. The steps of the method include:

[0010] A1. Obtain attribute data of each plot to be evaluated to evaluate the initial priority score of each plot to be evaluated; the attribute data includes basic attribute data, economic attribute data and social attribute data;

[0011] A2. According to the geographical location, intended use and traffic network connection information of each plot to be evaluated, identify the correlation characteristics among the plots to be evaluated; the correlation characteristics include spatial proximity, mutual influence degree and traffic correlation degree;

[0012] A3. For each plot to be evaluated, determine a set of associated plots of the plot to be evaluated according to the correlation characteristics;

[0013] A4. According to the initial priority score, the set of associated plots, the correlation characteristics and a preset correlation effect quantification rule, iteratively select plots to be evaluated and correct the priority scores of associated plots to generate a plurality of plot development sequences based on priority score ranking;

[0014] A5. Calculate the overall benefit of each of the land development sequences, and determine the priority of each of the land plots to be evaluated based on the land development sequence corresponding to the maximum overall benefit.

[0015] In a second aspect, the present application provides a low-utility land redevelopment priority evaluation system for evaluating the redevelopment priority of urban low-utility land. The system comprises:

[0016] An initial evaluation module for obtaining attribute data of each land plot to be evaluated, for evaluating the initial priority score of each land plot to be evaluated; the attribute data comprises basic attribute data, economic attribute data and social attribute data;

[0017] An associated feature identification module for identifying the associated features between each land plot to be evaluated according to the geographical location, intended use and traffic network connection information of each land plot to be evaluated; the associated features comprise spatial proximity, mutual influence degree and traffic correlation degree;

[0018] An associated plot determination module for determining, for each land plot to be evaluated, an associated plot set of the land plot to be evaluated according to the associated features;

[0019] A sequence generation module for iteratively selecting land plots to be evaluated and correcting the priority scores of associated plots according to the initial priority scores, the associated plot sets, the associated features and a preset associated effect quantification rule, to generate a plurality of land development sequences ranked based on priority scores;

[0020] A priority determination module for calculating the overall benefit of each of the land development sequences, and determining the priority of each of the land plots to be evaluated based on the land development sequence corresponding to the maximum overall benefit.

[0021] In summary, the low-utility land redevelopment priority evaluation method and system provided by the present application solves the problems of the prior art that the interaction between land plots cannot be considered, the evaluation result is unreasonable and combination optimization cannot be performed, by introducing the identification of associated features between land plots, iteratively correcting the priority scores of land plots based on the associated features and a preset associated effect quantification rule to generate a plurality of land development sequences, and finally determining the optimal development strategy by calculating the overall benefit of each sequence, thereby achieving the maximization of regional value. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 A flowchart of a low-utility land redevelopment priority evaluation method provided by the present application.

[0023] Figure 2 A schematic diagram of a low-utility land redevelopment priority evaluation system provided by the present application.

[0024] In the figure: 1, initial evaluation module; 2, associated feature identification module; 3, associated plot determination module; 4, sequence generation module; 5, priority determination module. DETAILED DESCRIPTION

[0025] The technical solutions in the present application will be described in detail below with reference to the accompanying drawings in the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the present application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0026] It should be noted that: similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0027] Reference Figure 1 The present application provides a low-utility land redevelopment priority evaluation method for evaluating the redevelopment priority of urban low-utility land. The steps of the method include:

[0028] A1. Obtain attribute data of each plot to be evaluated to evaluate the initial priority score of each plot to be evaluated; the attribute data includes basic attribute data, economic attribute data and social attribute data;

[0029] A2. According to the geographical location, intended use and traffic network connection information of each plot to be evaluated, identify the associated features between each plot to be evaluated; the associated features include spatial proximity, mutual influence degree and traffic association degree;

[0030] A3. For each plot to be evaluated, determine the associated plot set of the plot to be evaluated according to the associated features;

[0031] A4. According to the initial priority score, the associated plot set, the associated features and the preset associated effect quantification rule, iteratively select the plot to be evaluated and correct the priority score of the associated plot to generate a plurality of plot development sequences based on the priority score ranking;

[0032] A5. Calculate the overall benefits of the development sequences of each plot, and determine the priority of each plot to be evaluated based on the plot development sequence corresponding to the maximum overall benefit.

[0033] Among them, attribute data refers to various types of information used to evaluate the value and potential of land plots. It can be obtained through data collection, database query or geographic information system (GIS) integration. It is mainly used to conduct preliminary and independent value assessments of each land plot to be evaluated and obtain an initial priority score.

[0034] Among them, correlation characteristics refer to the characteristics of the interaction relationships between plots, which can be identified using technologies such as geographic spatial analysis, functional matching analysis or transportation network analysis. They are mainly used to quantify the synergistic or antagonistic effects between plot redevelopment projects and provide a basis for subsequent priority adjustments.

[0035] Among them, the associated plot set refers to a combination of other plots that have obvious interaction relationships with the specific plot to be evaluated. It can be determined by methods such as association strength threshold screening or network topology analysis. It is mainly used to clarify which plots’ priority will be affected by the development of the current plot, thereby achieving accurate priority correction.

[0036] Among them, the association effect quantification rule refers to a model or algorithm used to calculate the degree of influence of plot redevelopment on the priority of associated plots. It can be constructed using regression analysis models, expert system rules or machine learning algorithms. It is mainly used to quantify the positive or negative externalities generated by plot development and provide a calculation basis for iteratively correcting plot priorities.

[0037] Among them, the plot development sequence refers to a list of plots to be evaluated arranged in a specific order, representing a possible redevelopment timing plan. It can be generated using optimization strategies such as greedy algorithms, heuristic searches, or dynamic programming. It is mainly used to simulate the dynamic changes in plot priorities under different development paths and provide alternative plans for overall benefit evaluation.

[0038] Among them, overall benefit refers to the comprehensive value that a land development sequence can bring. It can be calculated by the weighted sum of economic benefits, social benefits and environmental benefits or multi-objective optimization function. It is mainly used to quantify the comprehensive value brought by different development combinations and time sequences, so as to determine the optimal redevelopment strategy.

[0039] The core innovation of the present application is that the correlation characteristics between plots are introduced, and based on the correlation characteristics and preset correlation effect quantification rules, the priority scores of the plots are iteratively corrected to generate a plurality of plot development sequences, and finally the optimal development strategy is determined by calculating the overall benefits of each sequence, thereby solving the problems that the existing method cannot consider the interaction relationship between plots, leading to unreasonable evaluation results and being unable to perform combination optimization, and realizing the maximization of regional value.

[0040] Specifically, the present method aims to solve the problems in the existing low-utility land redevelopment priority evaluation method, i.e., isolated evaluation of plots, ignoring the interaction between plots, and being unable to perform combination optimization. First, by obtaining attribute data of the plots to be evaluated, a preliminary value assessment is performed on each plot to be evaluated to obtain an initial priority score, which provides a basis for subsequent dynamic correction. Then, by using the geographical location, intended use and traffic network connection information of the plots to be evaluated, the spatial proximity, mutual influence and traffic correlation between the plots to be evaluated are identified, and these characteristics are the key to quantifying the synergistic effect or antagonistic effect between plots. On this basis, for each plot to be evaluated, its associated plot set is determined according to the identified correlation characteristics, so as to determine which plots will be affected by the development of the current plot. Subsequently, the present method introduces an iterative correction mechanism, which simulates the influence of plot redevelopment on the priority of surrounding associated plots according to the initial priority score, the associated plot set, the correlation characteristics and the preset correlation effect quantification rules. By iteratively selecting plots and correcting the priority scores of associated plots, the influence of plot development on the overall region can be dynamically reflected, and a plurality of different plot development sequences can be generated to explore different development paths. Finally, by calculating the overall benefits of each plot development sequence, the comprehensive value brought by different development combinations and timing is quantified, and the plot development sequence with the maximum overall benefit is selected, and the final priority of each plot to be evaluated is determined according to the sequence. This ensures that the evaluation result not only considers the value of a single plot, but more importantly, realizes the maximization of regional value.

[0041] Through the above scheme, the present application solves the problem that the existing low-utility land redevelopment priority evaluation method cannot consider the interaction relationship between plots, making the evaluation result more reasonable. The present method can handle the synergistic effect or antagonistic effect between plot redevelopment projects, avoiding the limitations of isolated evaluation. At the same time, by iteratively correcting and generating plot development sequences, the present method realizes the consideration of plot combination optimization and development timing, can reveal the internal relationship between projects, deduce the future urban form and benefits under different development combinations, thereby providing the decision maker with an overall development strategy, effectively avoiding suboptimal decisions, and promoting the maximization of regional value.

[0042] As a preferred embodiment, the scheme of the present application is implemented as follows: in practical application, the attribute data of the land plots to be evaluated can be first obtained through a city geographic information system (GIS). After standardization and quantization processing, the initial priority score of each land plot is calculated in combination with the preset weight. Subsequently, the Euclidean distance or road distance between the land plots to be evaluated is calculated by using the geographic coordinate information of the land plots to be evaluated to determine the spatial proximity; the functional mutual influence degree between the land plots to be evaluated is evaluated according to the planning use (i.e. the intended use, such as residence, business, industry) of the land plots to be evaluated and the predefined functional compatibility matrix; at the same time, the traffic accessibility between the land plots to be evaluated is evaluated by analyzing the connection of the land plots to be evaluated with the urban rail transit, bus lines, main roads and other traffic networks, so as to determine the traffic correlation degree. For each land plot to be evaluated, a comprehensive correlation strength threshold value can be set to filter out other land plots whose comprehensive correlation strength with the land plot to be evaluated exceeds the threshold value, thereby forming a correlation land plot set of the land plot. In generating the land plot development sequence, an optimization method such as simulated annealing algorithm or genetic algorithm can be used. Finally, for each generated land plot development sequence, a comprehensive benefit evaluation model can be constructed, which can consider multiple dimensions such as economic benefit (such as land value increment, tax contribution), social benefit (such as employment opportunity, public service improvement) and environmental benefit (such as greening rate, pollution control), and give corresponding weights for weighted summation to calculate the overall benefit of each sequence. The sequence with the highest overall benefit is selected as the optimal development scheme, and the final redevelopment priority of each land plot to be evaluated is determined according to the development order or final score of the land plots in the sequence.

[0043] Preferably, the basic attribute data includes area, current use, property ownership and volume rate;

[0044] The economic attribute data includes benchmark land price, surrounding real estate market price and potential development cost;

[0045] The social attribute data includes surrounding population density, public transportation site coverage rate, education facility accessibility score and medical facility accessibility score.

[0046] Among them, the basic attribute data refers to a data set reflecting the inherent physical characteristics, utilization status and legal status of the land plot, which can be obtained by means of on-site measurement of the land plot, planning drawing analysis, real estate registration information query, etc. The economic attribute data refers to a data set measuring the market value, potential income and development input of the land plot, which can be obtained by means of market research, land valuation report, project budget analysis, etc. The social attribute data refers to a data set evaluating the influence of the land plot on the surrounding community and residents' life, which can be obtained by means of population statistics, public service facility distribution map analysis, traffic network data analysis, etc.

[0047] In some embodiments, step A1 comprises:

[0048] A101. Obtain attribute data of each plot to be evaluated; the attribute data comprises basic attribute data, economic attribute data and social attribute data;

[0049] A102. According to the preset classification scoring standard, the current use and property ownership in the basic attribute data are converted into corresponding quantitative scores;

[0050] A103. For the area and volume rate in the basic attribute data, the benchmark land price, surrounding real estate market price and potential development cost in the economic attribute data, and the surrounding population density, public transportation site coverage, education facility accessibility score and medical facility accessibility score in the social attribute data, according to the preset quantification rule, they are converted into corresponding quantitative scores;

[0051] A104. According to each quantitative score and a preset weight, an initial priority score of each plot to be evaluated is calculated.

[0052] Wherein, the preset classification scoring standard refers to a set of rules or tables defined in advance for data with classification or qualitative characteristics, such as the current use or property ownership of the plot, to convert these non-numerical information into quantitative scores with specific meanings. For example, different scores can be assigned according to the influence degree of different uses on redevelopment, or different scores can be assigned according to the clarity of property rights, so that qualitative data can be involved in numerical calculation.

[0053] Wherein, the preset quantification rule refers to a set of conversion methods preset for attribute data with numerical type but possibly with different dimensions or ranges, such as plot area, volume rate, land price or population density. These rules can include linear normalization, logarithmic conversion, piecewise function mapping, etc., the purpose of which is to eliminate the dimensional differences between different data, map them into a comparable numerical interval, and ensure the fairness of evaluation.

[0054] Wherein, the preset weight refers to the importance coefficient assigned to the quantitative scores of different categories or different items when calculating the initial priority score. These weights can be flexibly set according to the macro strategy of urban development, specific policy guidance or expert experience, to reflect the relative importance of different attributes in the evaluation system, so that the final priority score can more accurately reflect the decision-making needs.

[0055] The scheme realizes the evaluation of the initial priority score of each land parcel to be evaluated through a series of ordered and logically rigorous steps. First, by obtaining the basic attribute data, economic attribute data and social attribute data of each land parcel to be evaluated, a comprehensive data foundation is laid for subsequent quantification and calculation. Second, for the qualitative information contained in the attribute data, such as current use and property ownership, the application of pre-set classification scoring standards is used to convert it into a unified quantitative score. This conversion process effectively solves the problem of qualitative data being difficult to directly participate in numerical calculation, ensuring the objectivity and operability of the evaluation. At the same time, for numerical attribute data such as area, plot ratio, benchmark land price, surrounding real estate market price, potential development cost, surrounding population density, public transportation station coverage, education facility accessibility score and medical facility accessibility score, pre-set quantification rules are applied to standardize or normalize them into unified quantitative scores. This eliminates the dimensional differences between different data types, ensuring the comparability of all data in subsequent calculations. Finally, after all attribute data has been converted into unified quantitative scores, the pre-set weights are used to comprehensively calculate these quantitative scores, thereby obtaining the initial priority score of each land parcel to be evaluated.

[0056] The entire process ensures that the evaluation process of the initial priority score is systematic, standardized and objective, avoiding subjective judgment and inconsistency. Thus, it provides a solid and reliable starting point for subsequent land parcel association feature recognition, associated land parcel set determination, and iterative generation and correction of land development sequence, enabling the entire low-utility land redevelopment priority evaluation method to be based on accurate and reliable data, significantly improving the scientificity and effectiveness of the evaluation results.

[0057] In one specific embodiment, the method can be implemented as follows: in collecting attribute data of each plot to be evaluated, data can be collected from various channels such as urban planning database, land and resources management system, statistical yearbook and field survey. For example, the area and plot ratio in the basic attribute data can be directly obtained from the cadastral information; the benchmark land price and surrounding real estate market price in the economic attribute data can be obtained from the land transaction market or the evaluation agency; the surrounding population density in the social attribute data can be obtained from the population census data, and the public transportation site coverage rate, the education facility accessibility score and the medical facility accessibility score can be obtained based on the spatial analysis results of the geographic information system (GIS). In converting the current use and the property ownership in the basic attribute data into corresponding quantitative scores according to the preset classification scoring standard, a detailed scoring table can be set. For example, for the "current use", "industrial land" can be rated as a lower quantitative score, "commercial land" can be rated as a medium quantitative score, and "idle or inefficient residential land" can be rated as a higher quantitative score to encourage its redevelopment. For the "property ownership", "state-owned sole ownership" can be rated as a high score because its development resistance is smaller; and "collective ownership" or "multi-party ownership" can be rated as a lower score because its development coordination is more difficult. For the area and plot ratio in the basic attribute data, the benchmark land price, the surrounding real estate market price and the potential development cost in the economic attribute data, and the surrounding population density, the public transportation site coverage rate, the education facility accessibility score and the medical facility accessibility score in the social attribute data, different standardization or normalization methods can be used in converting them into corresponding quantitative scores according to the preset quantitative rules. For example, for positive indicators such as the area and plot ratio, linear normalization method can be used to map them to the interval of 0 to 1. For the benchmark land price and the surrounding real estate market price, positive quantification can be performed according to their contribution to the development value. For the potential development cost, reverse quantification can be used, i.e. the higher the cost, the lower the quantitative score. For the surrounding population density, the public transportation site coverage rate, the education facility accessibility score and the medical facility accessibility score, these are usually numerical data, which can be directly standardized or appropriately interval mapped. In calculating the initial priority score of each plot to be evaluated according to the quantitative scores and the preset weights, a weighted summation model can be used. For example, the weight of the basic attribute data can be set as a1, the weight of the economic attribute data can be set as a2, and the weight of the social attribute data can be set as a3. Then, the initial priority score of a plot can be calculated as: initial priority score = (basic attribute quantitative score * a1) + (economic attribute quantitative score * a2) + (social attribute quantitative score * a3).The base attribute quantitative score can be obtained by weighted average of the quantitative scores of area, volume rate, current use, and property ownership; the economic attribute quantitative score can be obtained by weighted average of the quantitative scores of benchmark land price, surrounding real estate market price, and potential development cost; and the social attribute quantitative score can be obtained by weighted average of the quantitative scores of surrounding population density, public transportation station coverage rate, education facility accessibility score, and medical facility accessibility score. In this way, the value of the land plot in different dimensions can be comprehensively reflected, and an objective and comparable initial priority score can be obtained.

[0058] In some embodiments, step A2 comprises:

[0059] A201. Obtain geographical position information of each land plot to be evaluated, for calculating distances between the center points of the land plots to be evaluated, so as to determine the spatial proximity between each pair of land plots to be evaluated; the spatial proximity is negatively correlated with the distance;

[0060] A202. Determine the mutual influence degree between each pair of land plots to be evaluated according to the expected use of each land plot to be evaluated and a preset functional relationship rule;

[0061] A203. Obtain traffic network connection information of each land plot to be evaluated, for evaluating the traffic connection degree between the land plots to be evaluated, so as to determine the traffic correlation degree between each pair of land plots to be evaluated; the traffic correlation degree is positively correlated with the traffic connection degree; the traffic network connection information of the land plot to be evaluated comprises connection information of the land plot to be evaluated with a traffic network.

[0062] The spatial proximity refers to a quantitative index of the degree of spatial proximity between two land plots to be evaluated. The spatial proximity can be simply defined as the reciprocal of the distance, or represented by an exponential decay function (such as e^(-k*L), where k is a decay coefficient and L is the distance).

[0063] The expected use refers to a functional positioning that the land plot to be evaluated can be assigned after re-development in the future, which can be represented by a preset functional classification system, such as residence, business, industry, public service, or green land, etc.

[0064] The functional relationship rule refers to a preset logic or model defining the functional interaction between different types of land plots, which can be implemented by a matrix, a graph, or a rule set of an expert system, for quantifying the synergistic or antagonistic effect between land plots in terms of function.

[0065] The mutual influence degree refers to a quantitative index of the influence of re-development of one land plot to be evaluated on another land plot to be evaluated in terms of function or value, which can be represented by a numerical value, a level, or a percentage, reflecting the positive or negative correlation between land plots in terms of function.

[0066] The traffic network connection information refers to data describing the connection condition between the land to be evaluated and the urban traffic infrastructure, which can be represented by road network data, public transportation line data, or traffic hub location data, and is used to evaluate the accessibility of the land.

[0067] The traffic connection degree refers to a quantitative evaluation of the convenience or efficiency of mutual accessibility between two lands to be evaluated through the traffic network, which can be measured by indicators such as shortest path time, traffic flow, or traffic facility density.

[0068] The traffic correlation degree refers to a quantitative indicator of the impact of the redevelopment of one land to be evaluated on the traffic accessibility or traffic load of another land to be evaluated, which can be represented by a numerical value, a grade, or a percentage, reflecting the mutual dependence between lands in terms of traffic.

[0069] The present scheme provides a specific and quantitative method by refining the steps of identifying associated features, thereby solving the generalization problem of associated feature identification in the prior art. By obtaining geographic location information and calculating distances to determine spatial proximity, the spatial proximity between lands can be objectively reflected. By determining the mutual influence degree according to the intended use and functional relationship rules, the functional impact of land redevelopment on surrounding lands can be finely evaluated. By obtaining traffic network connection information and evaluating the traffic connection degree to determine the traffic correlation degree, the interaction between lands due to traffic conditions can be accurately reflected. These quantitative and accurate associated feature identifications provide a reliable data foundation for the determination of associated land sets, the generation of land development sequences, and the correction of priority scores in subsequent steps, effectively improving the objectivity and effectiveness of the low-utility land redevelopment priority evaluation results.

[0070] Preferably, step A202 can include:

[0071] According to the intended use of each land to be evaluated and the preset functional relationship rules, an initial functional interaction score between each pair of lands to be evaluated is obtained;

[0072] A correction factor affecting the functional interaction score is obtained; the correction factor includes a spatial correction factor determined based on the geographic location information of each land to be evaluated, a traffic correction factor determined based on the traffic network connection information of each land to be evaluated, and an environmental correction factor determined based on the attribute data of each land to be evaluated;

[0073] According to the initial functional interaction score and the correction factor, a final mutual influence degree between each pair of lands to be evaluated is calculated.

[0074] The initial functional interaction score refers to a value that preliminarily quantifies the degree of mutual promotion or inhibition in function between plots according to the intended use of the plots and preset functional relationship rules, which can be obtained by using a predefined functional relationship matrix, an expert scoring table or a functional correlation model based on historical data.

[0075] The correction factor is a parameter for adjusting the initial functional interaction score to reflect the influence of external or internal conditions on the actual interaction between plots, which can be represented by a multiplication factor or an additive term.

[0076] The spatial correction factor is a parameter for adjusting the functional interaction score based on the spatial relationship between plots, which can be determined by using a distance decay function, a spatial weight matrix or a correction model based on spatial topological relationship. For example, the spatial correction factor can be determined based on the Euclidean distance between the center points of the plots, and a distance decay function such as an exponential decay function or a power-law decay function can be used to convert the distance into a correction coefficient between 0 and 1. The farther the distance, the smaller the correction coefficient.

[0077] The traffic correction factor is a parameter for adjusting the functional interaction score based on the traffic accessibility between plots, which can be determined by using indicators such as the shortest path time of the traffic network, traffic flow data or public transportation coverage. For example, the traffic correction factor can be determined based on the accessibility between plots through the traffic network, and the shortest travel time of public transportation or road network between the two plots can be calculated and converted into a correction coefficient by a reverse mapping function. The shorter the travel time, the larger the correction coefficient.

[0078] The environmental correction factor is a parameter for adjusting the functional interaction score based on the environmental attributes of the plots themselves, which can be determined by using indicators such as the surrounding population density, green coverage, air quality index and public service facility coverage. For example, the population density, green coverage, air quality index and number of public service facilities within a preset radius around the plot can be considered comprehensively, and an environmental quality score can be calculated by weighted summation or fuzzy comprehensive evaluation method, and then converted into a correction coefficient. The higher the environmental quality score, the larger the correction coefficient.

[0079] The final mutual influence degree can be obtained by superimposing or multiplying the initial functional interaction score and each correction factor.

[0080] The method first obtains initial functional interaction scores between each pair of the to-be-evaluated plots according to the intended use of each to-be-evaluated plot and a preset functional relationship rule. This initial score is a basic quantification of the functional correlation between plots, which reflects the potential synergistic or antagonistic relationship of plots at the planning function level. On this basis, the method further obtains correction factors affecting the functional interaction scores. These correction factors are the core of the scheme, which include a spatial correction factor determined based on the geographic location information of each to-be-evaluated plot, a traffic correction factor determined based on the traffic network connection information of each to-be-evaluated plot, and an environmental correction factor determined based on the attribute data of each to-be-evaluated plot. The spatial correction factor can quantify the attenuation or enhancement effect of plot distance or spatial layout on functional interaction, ensuring that the mutual influence degree conforms to the actual spatial law. The traffic correction factor assesses the promotion or hindering effect of traffic conditions on functional interaction, so that the mutual influence degree takes into account the actual accessibility. The environmental correction factor takes into account the micro-environmental factors of the plot itself, such as surrounding population density, environmental quality or infrastructure perfection, which will affect the actual effect of plot functional interaction. Finally, according to the initial functional interaction scores and the above-mentioned various correction factors, the final mutual influence degree between each pair of to-be-evaluated plots is calculated. By comprehensively operating the initial functional interaction scores and the spatial, traffic, environmental and other correction factors, an accurate and comprehensive mutual influence degree can be obtained.

[0081] This multi-dimensional correction mutual influence degree calculation method can accurately reflect the complex linkage effect in the plot redevelopment process when identifying the correlation characteristics between plots. Compared with the traditional method of determining the mutual influence degree based only on the intended use and functional relationship rule, this method can improve the accuracy of plot interaction evaluation. This accurate mutual influence degree, as an important part of the correlation characteristics between plots, can provide a reliable basis for subsequent determination of the associated plot set of plots. Furthermore, in generating a plurality of plot development sequences based on priority score ranking, the corrected correlation plot priority score will be closer to the actual situation, so that the final determined plot development sequence and priority evaluation result is scientific and reasonable, avoiding suboptimal decisions due to inaccurate plot interaction evaluation, thereby improving the overall accuracy and practicality of low-utility land redevelopment priority evaluation.

[0082] Preferably, step A203 can include:

[0083] Obtaining connection information of each to-be-evaluated plot with different types of traffic networks; the connection information includes accessibility, carrying capacity and traffic efficiency;

[0084] Determining the dependence degree of the intended use on different types of traffic networks according to the intended use of each to-be-evaluated plot;

[0085] According to the connection information and the dependence degree, the degree of traffic connection between each of the to-be-evaluated plots is evaluated.

[0086] According to the degree of traffic connection, the traffic correlation degree between each of the to-be-evaluated plots is determined; the traffic correlation degree is positively correlated with the degree of traffic connection.

[0087] Different types of traffic networks refer to various types of traffic infrastructure in a city, which can include but are not limited to road networks, rail transit networks, bus line networks, waterway transportation networks, or air transportation networks.

[0088] The connection information refers to a quantitative indicator of the connection between the plot and the traffic network, where accessibility refers to the convenience of reaching or leaving a specific traffic network node from the to-be-evaluated plot, which can be measured by walking distance, commuting time, or number of transfers; carrying capacity refers to the traffic flow or passenger volume that a specific traffic network can accommodate in a unit of time, which can be represented by road grade, number of lanes, or density of public transportation vehicle schedules; traffic efficiency refers to the smoothness and speed of traffic flow in the traffic network, which can be reflected by average speed, congestion index, or delay time.

[0089] The dependence degree of the expected use on different types of traffic networks refers to the importance or demand intensity of the expected use on different types of traffic networks (such as roads, public transportation, freight railways, and water transportation), which can be determined by expert scoring, analytic hierarchy process, or fuzzy comprehensive evaluation method, etc. According to the traffic demand characteristics of different expected uses, a weight or dependence coefficient is assigned to each type of traffic network. For example, a plot planned as a commercial complex has a higher dependence degree on the accessibility and carrying capacity of public transportation, but a lower dependence degree on freight railways or water transportation.

[0090] According to the connection information and the dependence degree, the degree of traffic connection between each of the to-be-evaluated plots is evaluated.

[0091] Determining the traffic correlation between each pair of evaluated plots based on their degree of traffic connectivity involves quantifying the assessed degree of traffic connectivity into a traffic correlation index. Traffic correlation is positively correlated with the degree of traffic connectivity, meaning that higher traffic connectivity indicates a higher traffic correlation index. Specifically, the traffic correlation index can be represented by linear or nonlinear function mapping, or mapped to a specific numerical range using a monotonically increasing function.

[0092] This solution refines the determination of transportation connectivity during the step of identifying the interconnected characteristics between the parcels to be evaluated. First, the system obtains information on each parcel's connectivity to different types of urban transportation networks. This information goes beyond simply measuring connectivity strength to encompass multiple dimensions, including accessibility, carrying capacity, and efficiency. This multi-dimensional information collection enables the system to provide a more comprehensive and detailed picture of the parcel's transportation conditions, laying the foundation for subsequent evaluation. Furthermore, the system considers the intended use of each parcel. Because parcels with different intended uses have varying requirements for transportation networks—for example, commercial parcels have higher requirements for public transportation accessibility and road carrying capacity, while residential parcels prioritize a quiet living environment and walkability—the system determines the specific degree of dependence of the parcel on different types of transportation networks based on its intended use. This step introduces an inherent matching logic between parcel function and transportation network, making transportation assessments less general and more personalized for the parcel's future function. The system then combines the multi-dimensional connectivity information obtained above with the degree to which the intended use of the land parcel depends on the transportation network to assess the degree of transportation connectivity between each parcel to align with its intended use. This assessment process goes beyond simply measuring the physical strength of transportation connections to delve deeper into whether these connections truly meet the functional requirements of the land parcel after redevelopment. For example, even if a commercial parcel has numerous transportation routes nearby, if the carrying capacity or efficiency of these routes cannot meet the high passenger and logistics demands of commercial activities, its degree of transportation connectivity for its intended use will be considered low. This alignment assessment ensures that transportation connectivity considerations are targeted and practical, avoiding the bias of assessing high but inappropriate connectivity. Ultimately, based on this refined and personalized matching assessment, the system determines the degree of transportation correlation between each parcel to be evaluated, and the degree of transportation correlation and transportation connectivity show a positive correlation.

[0093] In this way, the obtained traffic correlation degree can more accurately reflect the mutual influence and synergistic effect between plots due to the traffic network. This more accurate traffic correlation degree, as an important part of identifying plot correlation characteristics, can provide a more reliable basis for subsequent determination of associated plot sets and iterative correction of plot priority scores. This makes the entire low-utility land redevelopment priority evaluation method more scientifically identify the internal relationship between plots, thereby improving the accuracy of the overall evaluation and decision support capability, and solving the problem of insufficient precision and matching in the traffic correlation degree evaluation in traditional methods.

[0094] In some embodiments, step A3 comprises:

[0095] A301. For each plot to be evaluated, according to the spatial proximity, the mutual influence degree and the traffic correlation degree between the plot to be evaluated and the remaining plots to be evaluated, the comprehensive correlation strength between the plot to be evaluated and the remaining plots to be evaluated is calculated.

[0096] A302. Screening the remaining plots to be evaluated whose comprehensive correlation strength is higher than the preset correlation strength threshold value to form an associated plot set of the plot to be evaluated.

[0097] Wherein, the comprehensive correlation strength refers to the overall strength of the interaction between plots after comprehensively considering multiple correlation characteristics, which can be calculated by weighted summation, multi-attribute decision model or machine learning algorithm. The correlation strength threshold refers to the strength threshold value for screening associated plots, which can be determined according to experience, statistical analysis or optimization algorithm. For example, the spatial proximity, the mutual influence degree and the traffic correlation degree between the plot to be evaluated and the remaining plots to be evaluated are normalized, and then the weighted sum of the normalized spatial proximity, the normalized mutual influence degree and the normalized traffic correlation degree is calculated as the comprehensive correlation strength.

[0098] Wherein, the correlation strength threshold can be set according to actual needs, for example, 0.6, but not limited to this.

[0099] By the technical solution, the application can objectively and quantitatively determine the associated plot set of each plot to be evaluated. Specifically, by comprehensively considering the multi-dimensional association characteristics such as spatial proximity, mutual influence degree and traffic association degree, and calculating the comprehensive association strength between plots, the problem that the associated plot determination in the traditional method lacks quantitative basis and multi-dimensional consideration is solved. Further, by setting a clear association strength threshold and screening, it is ensured that the determined associated plot set is based on objective standards rather than subjective judgment, thereby avoiding the influence of the effectiveness of subsequent priority score modification due to inaccurate or subjective associated plot set determination. This makes the redevelopment priority evaluation result more scientific and reasonable, and can more accurately reflect the interaction relationship between plots, thereby providing a more reliable basis for urban low-efficiency land redevelopment decision-making.

[0100] In some embodiments, step A4 comprises:

[0101] A401. Initialize a plot development sequence, and select one plot to be evaluated that has not been selected as a first development plot as a first development plot to be added to the plot development sequence; and initialize the current priority score of each plot to be evaluated as the corresponding initial priority score;

[0102] A402. Initialize a plot to be developed list, and add plots to be evaluated other than the first development plot to the plot to be developed list;

[0103] A403. Perform the following operations in a loop until the plot to be developed list is empty to generate a complete plot development sequence:

[0104] B1. From the plot to be developed list, select a plot to be developed with the highest current priority score as a selected plot;

[0105] B2. Add the selected plot to the current plot development sequence and remove it from the plot to be developed list;

[0106] B3. For each associated plot in the associated plot set of the selected plot, calculate a priority modification value of the associated plot according to the expected use of the selected plot, the associated characteristics and the preset association effect quantification rule, to modify the current priority score of the associated plot;

[0107] A404. Repeat steps A401 to A403 until all plots to be evaluated have been selected as a first development plot to generate a plurality of plot development sequences.

[0108] wherein the list of land parcels to be developed refers to a set of land parcels to be evaluated that have not been selected into the sequence of land development in the process of generating the sequence of land development, and the current priority score refers to a real-time priority evaluation value of a land parcel to be evaluated in the process of iterative selection.

[0109] wherein the correlation effect quantification rule refers to a pre-set mathematical model or logical rule for calculating the degree of mutual influence between land parcels to be evaluated, which can be implemented by using a scoring matrix based on expert experience, a regression model or a machine learning algorithm, etc.

[0110] The scheme of the present application aims to systematically generate a plurality of development sequences considering the correlation effect between land parcels, in order to overcome the limitations of isolated evaluation of land parcels in the prior art. This scheme achieves this goal through a series of carefully designed iterative steps. First, in step A401, the system initializes a land development sequence and strategically selects a land parcel to be evaluated that has not been the first land parcel to be developed as the starting point of the current sequence. This operation ensures that each land parcel to be evaluated can be used as a starting point to fully explore different development sequences, thereby avoiding the limitations that may be caused by a single fixed starting point. And the initial priority score of each land parcel to be evaluated is used as the current priority evaluation value. This provides a clear initial state for subsequent dynamic correction of iteration.

[0111] Next, in step A402, a list of land parcels to be developed is initialized, which includes all land parcels to be evaluated except the first land parcel to be developed. This provides a clear operation range for subsequent iterative selection.

[0112] Subsequently, in step A403, the system enters a core loop process, which continues to perform a series of operations until the list of land parcels to be developed is empty, thereby generating a complete land development sequence. In this loop, first, in step B1, the system selects the land parcel to be developed with the highest current priority score from the list of land parcels to be developed as the selected land parcel, which embodies the strategy of selecting the land parcel with the highest development value at each step, guiding the sequence to develop in the current optimal direction. Then, in step B2, the selected land parcel is added to the current land development sequence and removed from the list of land parcels to be developed, ensuring that each land parcel to be developed is selected only once and gradually building a complete development sequence.

[0113] The key is step B3, after a selected plot is included in the development sequence, its impact on the surrounding associated plots will be evaluated immediately. Specifically, for each associated plot in the associated plot set of the selected plot, according to the intended use of the selected plot, and the identified associated features (e.g. spatial proximity, mutual influence, traffic association) in the previous steps, and combined with the preset associated effect quantification rules, the priority modification value of these associated plots is calculated. These modification values are then used to dynamically modify the current priority score of the associated plots. This mechanism enables the subsequent plot selection to fully consider the dynamic interaction between plots, such as synergistic or antagonistic effects, thereby generating a development sequence that is more in line with the actual situation and more beneficial overall.

[0114] Finally, in step A404, the system repeatedly performs the above steps A401 to A403 until all plots to be evaluated have been selected as the first development plot. This repeated mechanism ensures that the system can fully explore all possible development timing and combinations, generating a diverse plot development sequence.

[0115] Through the organic combination of the above steps, the present scheme can fully utilize the initial priority score obtained previously as the basis for evaluation, and combine the identified associated features between plots and the determined associated plot set, to dynamically adjust the priority of the plots in the iterative selection process. This dynamic adjustment mechanism makes the development of plots no longer an isolated decision, but fully considers its radiation impact on surrounding plots, thereby generating a series of development sequences that reflect the complex interaction between plots. This not only provides a rich and diverse candidate scheme for subsequent overall benefit evaluation, but also enables the final determined development strategy to more fully reflect the overall value of the urban area, effectively avoiding the suboptimal decision-making in traditional methods due to the neglect of plot interrelation.

[0116] Preferably, step B3 can include:

[0117] B301. According to the intended use of the selected plot, an associated effect model corresponding to the intended use is obtained from the preset associated effect quantification rules;

[0118] B302. The spatial proximity, mutual influence and traffic association between the associated plot and the selected plot are input, and the initial priority modification contribution of the associated plot is calculated using the associated effect model;

[0119] B303. According to the distance between the selected plot and the associated plot, the attenuation coefficient of the initial priority modification contribution is determined;

[0120] B304. Calculate a final priority modification value for the associated plot based on the initial priority modification contribution and the decay coefficient;

[0121] B305. Superimpose the final priority modification value to the current priority score of the associated plot to obtain a modified current priority score.

[0122] wherein the pre-defined association effect quantification rule can be stored in a database or lookup table, which contains pre-trained or defined association effect models for different intended uses (e.g., commercial, residential, industrial, public service, etc.). These models can be weighted functions based on expert experience setting a set of weights, or functions trained by machine learning methods (e.g., regression analysis, neural network) using historical data. For example, the association effect model can be a weighted summation formula: initial priority modification contribution = w1* spatial proximity + w2* mutual influence + w3* traffic correlation, where w1, w2, w3 are weights that reflect the relative importance of different association features under a specific intended use. In addition, the association effect model can also be a more complex nonlinear function or decision tree model to capture the complex interactions between plot association features.

[0123] wherein the distance between the selected plot and the associated plot can refer to the Euclidean distance or actual traffic distance between the plot center points. The decay coefficient can be a distance-based function, such as an exponential decay function (e.g., exp(-K*l), where K is a decay constant and l is the distance between the selected plot and the associated plot) or a linear decay function (e.g., max(0, 1-l / l_max), where l_max is a pre-set distance threshold). The specific form and parameters of the decay function can be determined according to actual urban planning experience or through data analysis.

[0124] wherein the final priority modification value can be obtained by multiplying the initial priority modification contribution by the decay coefficient, i.e., final priority modification value = initial priority modification contribution * decay coefficient. This operation combines the multi-dimensional comprehensive influence (initial modification contribution) with the spatial decay effect, generating a final modification value that considers both functional association and spatial distance, so that the modification value can more accurately reflect the actual impact of the selected plot development on the priority of the associated plot.

[0125] wherein the superimposition operation can be a simple addition, i.e., modified current priority score = current priority score + final priority modification value. If the final priority modification value is negative (indicating a negative impact), the superimposition operation will accordingly reduce the current priority score. This operation is a key step in dynamically adjusting the priority, by applying the accurately calculated modification value to the current score of the associated plot, realizing real-time and dynamic updating of plot priority.

[0126] By the technical solution, the application can accurately and comprehensively quantize the correlation effect between plots, comprehensively consider various correlation characteristics such as spatial proximity, mutual influence degree, and traffic correlation degree, and consider the characteristics that the influence decays with distance, thereby generating a priority modification value accurately reflecting the actual influence. This makes the modified priority score fully reflect the complex interaction between plots, effectively solves the problem that the modification value calculation is not fine and comprehensive in the prior scheme, and further improves the optimization degree of the finally generated plot development sequence

[0127] In some embodiments, step A5 comprises:

[0128] A501. Based on the final priority score of each plot to be evaluated in the plot development sequence (i.e. the final current priority score obtained after completing iteration in step A403), the intended use and development sequence, obtaining the expected benefit of each plot to be evaluated in the plot development sequence;

[0129] A502. Identify the external influence of each plot to be evaluated in the plot development sequence on the surrounding area; the external influence includes economic spillover effect, social spillover effect and environmental spillover effect;

[0130] A503. According to the external influence, quantize the overall external contribution of the plot development sequence;

[0131] A504. According to the expected benefit of each plot to be evaluated in the plot development sequence and the overall external contribution, calculate the overall benefit of the plot development sequence;

[0132] A505. Based on the plot development sequence corresponding to the maximum overall benefit, determine the priority of each plot to be evaluated.

[0133] In step A501, a pre-set benefit evaluation model can be used to obtain the expected benefit, which takes the final priority score of the plot (reflecting the individual value of the plot after considering the associated effects), its planned future use and development sequence as input, and outputs the direct economic value, social value or functional value that the plot can generate within a pre-set planning period after development is completed. For example, for a plot planned for commercial use, its expected benefit can be calculated by a commercial value evaluation model according to its area, volume rate, surrounding commercial activity and final priority score; for a plot planned for residential use, its expected benefit can be calculated by a residential value evaluation model according to its residential density, accessibility of public service facilities and final priority score. By using the final priority score iteratively corrected in step A403, it is ensured that the evaluation of the individual benefit of the plot is based on considering its interaction with associated plots, rather than isolated initial evaluation, so that the calculation of expected benefit is more close to reality.

[0134] In step A502, external influence includes economic spillover effect, social spillover effect and environmental spillover effect. Various methods such as expert evaluation, geographic information system (GIS) analysis, big data mining, etc. can be used to achieve this. For example, economic spillover effect can be identified as the driving effect of plot development on surrounding land prices, commercial activities and employment opportunities; social spillover effect can be identified as the impact of plot development on the accessibility of surrounding public service facilities (such as schools, hospitals), community safety and cultural activities; environmental spillover effect can be identified as the impact of plot development on surrounding air quality, water environment, green coverage and noise level. These influences can be positive (spillover effect) or negative (negative externality).

[0135] In step A503, multi-criteria decision analysis (MCDA) method, value engineering method or cost-benefit analysis based method can be used to achieve this. For example, for economic spillover effect, at least one of the following can be quantified: surrounding plot value-added, new tax revenue, number of new jobs; for social spillover effect, at least one of the following can be quantified: increase in population served by public service facilities, community satisfaction improvement index; for environmental spillover effect, at least one of the following can be quantified: air quality improvement index, increase in green area, reduction in pollutant emissions. These quantified indicators can be weighted and summed according to pre-set weights to obtain a comprehensive externality contribution value. This quantification makes it possible to calculate and compare the indirect benefits or costs that are otherwise difficult to measure, so as to more accurately reflect the comprehensive impact of a development sequence on the entire region, providing an important supplementary dimension for subsequent overall benefit calculation.

[0136] In step A504, a weighted summation model can be used to achieve the sum of the expected benefits of all plots and the overall externality contribution. The expected benefits of the plot itself (internal benefits) and the overall externality contribution generated by the plot development (external benefits) are calculated comprehensively. In this way, the final "overall benefits" not only contain the value of the plot itself, but also more comprehensively reflect its positive or negative impact on the surrounding area and even the entire urban system, so that the comparison of different development sequences is more scientific and reasonable.

[0137] In step A505, a comparison sorting method can be used to achieve the highest overall benefit sequence among the multiple generated plot development sequences, and the sequence of the plot in the optimal development sequence is determined as the final redevelopment priority.

[0138] Through the above technical solutions, the overall benefits of each plot development sequence can be accurately and comprehensively evaluated, solving the problem of ignoring the interaction and external effect between projects in the traditional evaluation method, so that the redevelopment priority of the plot can be more scientifically and accurately determined to maximize the value of the region.

[0139] Reference Figure 2 The present application provides a low-utility land redevelopment priority evaluation system for evaluating the redevelopment priority of urban low-utility land, which comprises:

[0140] An initial evaluation module 1 is used to obtain attribute data of each plot to be evaluated, so as to evaluate the initial priority score of each plot to be evaluated; the attribute data includes basic attribute data, economic attribute data and social attribute data (the specific process can be referred to step A1 in the foregoing description) ;

[0141] An associated feature identification module 2 is used to identify the associated features between each plot to be evaluated according to the geographical location, intended use and traffic network connection information of each plot to be evaluated; the associated features include spatial proximity, mutual influence degree and traffic correlation degree (the specific process can be referred to step A2 in the foregoing description) ;

[0142] An associated plot determination module 3 is used to determine the associated plot set of each plot to be evaluated according to the associated features (the specific process can be referred to step A3 in the foregoing description) ;

[0143] A sequence generation module 4 is used to iteratively select plots to be evaluated and correct the priority scores of associated plots according to the initial priority scores, the associated plot set, the associated features and the preset associated effect quantification rules, so as to generate multiple plot development sequences based on the priority score sorting (the specific process can be referred to step A4 in the foregoing description) ;

[0144] A priority determination module 5 is configured to calculate the overall benefit of each plot development sequence, and determine the priority of each plot to be evaluated based on the plot development sequence corresponding to the maximum overall benefit (the specific process can refer to step A5 in the foregoing).

[0145] The above merely provides an example of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for evaluating the redevelopment priority of low-efficiency land, which is used to evaluate the redevelopment priority of low-efficiency land in cities, characterized by: The method comprises the following steps: A1. Obtain attribute data of each land plot to be evaluated to evaluate an initial priority score of each land plot to be evaluated; the attribute data comprises basic attribute data, economic attribute data and social attribute data; A2. Identify correlation characteristics between each land plot to be evaluated according to geographical positions, intended uses and traffic network connection information of each land plot to be evaluated; the correlation characteristics comprise spatial proximity, mutual influence degree and traffic correlation degree; A3. For each land plot to be evaluated, determine a correlation land plot set of the land plot to be evaluated according to the correlation characteristics; A4. Iteratively select land plots to be evaluated and correct priority scores of correlation land plots according to the initial priority scores, the correlation land plot set, the correlation characteristics and a preset correlation effect quantification rule to generate a plurality of land plot development sequences ranked according to priority scores; A5. Calculate overall benefits of each land plot development sequence and determine priorities of each land plot to be evaluated based on the land plot development sequence corresponding to the maximum overall benefit; Step A4 comprises: A401. Initialize a land plot development sequence, select a land plot to be evaluated that has not been selected as a first development land plot as a first development land plot and add the first development land plot to the land plot development sequence; and initialize current priority scores of each land plot to be evaluated as the initial priority scores corresponding thereto; A402. Initialize a land plot to be developed list and add land plots to be evaluated other than the first development land plot to the land plot to be developed list; A403. Perform the following operations in a loop until the land plot to be developed list is empty to generate a complete land plot development sequence: B1. Select a land plot to be developed with the highest current priority score from the land plot to be developed list as a selected land plot; B2. Add the selected land plot to the current land plot development sequence and remove the selected land plot from the land plot to be developed list; B3. For each correlation land plot in the correlation land plot set of the selected land plot, calculate a priority correction value of the correlation land plot according to an intended use of the selected land plot, the correlation characteristics and the preset correlation effect quantification rule to correct a current priority score of the correlation land plot; A404. Repeat steps A401 to A403 until all land plots to be evaluated are selected as first development land plots to generate a plurality of land plot development sequences; Step B3 comprises: B301. Obtain a correlation effect model corresponding to an intended use of a selected land plot from the preset correlation effect quantification rule according to the intended use of the selected land plot; B302. Calculate an initial priority correction contribution of a correlation land plot by taking the spatial proximity, the mutual influence degree and the traffic correlation degree between the correlation land plot and the selected land plot as inputs and using the correlation effect model; B303. Determine an attenuation coefficient of the initial priority correction contribution according to a distance between the selected land plot and the correlation land plot; B304. Calculate a final priority correction value of the correlation land plot according to the initial priority correction contribution and the attenuation coefficient; B305. superimpose the final priority correction value to the current priority score of the associated plot to obtain a corrected current priority score.

2. The method of claim 1, wherein The basic attribute data includes area, current use, property ownership, and plot ratio; The economic attribute data includes benchmark land price, surrounding real estate market price, and potential development cost; The social attribute data includes surrounding population density, public transportation site coverage, education facility accessibility score, and medical facility accessibility score.

3. The method according to claim 2, wherein Step A1 includes: A101. Obtain attribute data of each plot to be evaluated; the attribute data includes basic attribute data, economic attribute data, and social attribute data; A102. According to the preset classification scoring standard, convert the current use and property ownership in the basic attribute data into corresponding quantitative scores; A103. For the area and plot ratio in the basic attribute data, the benchmark land price, surrounding real estate market price, and potential development cost in the economic attribute data, and the surrounding population density, public transportation site coverage, education facility accessibility score, and medical facility accessibility score in the social attribute data, according to the preset quantification rule, convert them into corresponding quantitative scores; A104. According to each quantitative score and a preset weight, calculate the initial priority score of each plot to be evaluated.

4. The method of claim 1, wherein Step A2 includes: A201. Obtain geographic location information of each plot to be evaluated, which is used to calculate the distance between the center points of each plot to be evaluated to determine the spatial proximity between each pair of plots to be evaluated; the spatial proximity is negatively correlated with the distance; A202. According to the intended use of each plot to be evaluated and a preset functional relationship rule, determine the mutual influence degree between each pair of plots to be evaluated; A203. Obtain traffic network connection information of each plot to be evaluated, which is used to evaluate the traffic connection degree between each pair of plots to be evaluated to determine the traffic correlation degree between each pair of plots to be evaluated; the traffic correlation degree is positively correlated with the traffic connection degree; the traffic network connection information of the plot to be evaluated includes the connection information of the plot to be evaluated and the traffic network.

5. The method of claim 4, wherein Step A202 includes: According to the intended use of each plot to be evaluated and the preset functional relationship rule, obtain an initial functional interaction score between each pair of plots to be evaluated; Obtain correction factors affecting the functional interaction score; the correction factors include a spatial correction factor determined based on the geographic location information of each plot to be evaluated, a traffic correction factor determined based on the traffic network connection information of each plot to be evaluated, and an environmental correction factor determined based on the attribute data of each plot to be evaluated; According to the initial functional interaction score and the correction factors, calculate the final mutual influence degree between each pair of plots to be evaluated.

6. The method of claim 4, wherein the low-utility land redevelopment priority evaluation method is characterized by, Step A203 includes: Obtain the connection information of each plot to be evaluated and different types of traffic networks; the connection information includes accessibility, carrying capacity, and traffic efficiency; According to the intended use of each plot to be evaluated, determine the dependence degree of the intended use on different types of traffic networks; According to the connection information and the dependence degree, a traffic connection degree between each of the to-be-evaluated plots is evaluated; According to the traffic connection degree, the traffic correlation degree between each of the to-be-evaluated plots is determined; the traffic correlation degree is positively correlated with the traffic connection degree.

7. The method of claim 1, wherein the low-utility redevelopment priority evaluation method is characterized by, Step A3 comprises: A301. For each of the to-be-evaluated plots, according to the spatial proximity, the mutual influence degree and the traffic correlation degree between the to-be-evaluated plot and the rest of the to-be-evaluated plots, a comprehensive correlation strength between the to-be-evaluated plot and the rest of the to-be-evaluated plots is calculated; A302. The rest of the to-be-evaluated plots with the comprehensive correlation strength higher than a preset correlation strength threshold are screened out to form a correlation plot set of the to-be-evaluated plot.

8. A low-efficiency land redevelopment priority evaluation system for evaluating the redevelopment priority of low-efficiency urban land, characterized by: The system comprises: An initial evaluation module configured to acquire attribute data of each of the to-be-evaluated plots, and to evaluate an initial priority score of each of the to-be-evaluated plots; the attribute data comprises basic attribute data, economic attribute data and social attribute data; An association feature identification module configured to identify association features between each of the to-be-evaluated plots according to geographical positions, intended uses and traffic network connection information of the to-be-evaluated plots; the association features comprise spatial proximity, mutual influence degree and traffic correlation degree; An association plot determination module configured to, for each of the to-be-evaluated plots, determine a correlation plot set of the to-be-evaluated plot according to the association features; A sequence generation module configured to, according to the initial priority score, the correlation plot set, the association features and a preset association effect quantification rule, iteratively select to-be-evaluated plots and correct priority scores of the correlation plots to generate a plurality of plot development sequences based on priority score ranking; A priority determination module configured to calculate overall benefits of each of the plot development sequences, and determine priorities of each of the to-be-evaluated plots based on the plot development sequence corresponding to the maximum overall benefit. When the sequence generation module generates a plurality of plot development sequences based on priority score ranking according to the initial priority score, the correlation plot set, the association features and a preset association effect quantification rule, the sequence generation module performs: A401. initializes a plot development sequence, selects a to-be-evaluated plot that has not been selected as a first development plot as the first development plot, and adds the first development plot to the plot development sequence; and initializes current priority scores of each of the to-be-evaluated plots as corresponding initial priority scores; A402. initializes a to-be-developed plot list, and adds to-be-evaluated plots other than the first development plot to the to-be-developed plot list; A403. performs the following operations in a loop until the to-be-developed plot list is empty to generate a complete plot development sequence: B1. selects a to-be-developed plot with the highest current priority score from the to-be-developed plot list as a selected plot; B2. adds the selected plot to the current plot development sequence, and removes the selected plot from the to-be-developed plot list; B3. For each of the associated plots in the associated plot set of the selected plot, according to the intended use of the selected plot, the associated feature, and the preset associated effect quantification rule, a priority modification value of the associated plot is calculated to modify the current priority score of the associated plot; A404. Repeating steps A401 to A403 until all plots to be evaluated are selected as the first development plot to generate a plurality of plot development sequences; Step B3 includes: B301. According to the intended use of the selected plot, an associated effect model corresponding to the intended use is obtained from the preset associated effect quantification rule; B302. The spatial proximity, the mutual influence degree, and the traffic correlation between the associated plot and the selected plot are taken as inputs, and the initial priority modification contribution of the associated plot is calculated by using the associated effect model; B303. According to the distance between the selected plot and the associated plot, an attenuation coefficient of the initial priority modification contribution is determined; B304. According to the initial priority modification contribution and the attenuation coefficient, a final priority modification value of the associated plot is calculated; B305. The final priority modification value is superimposed on the current priority score of the associated plot to obtain a modified current priority score.

Images