Land value evaluation method, device and equipment for land development, medium and product

Abstract

The invention discloses a land value evaluation method and device for land development, equipment, a medium and a product, and the method comprises the steps: obtaining a value influence factor of a target stock land, and carrying out the standardization processing of the value influence factor; according to the processed value influence factors, an optimized land comprehensive value evaluation model is adopted to carry out value evaluation on the target stock land, and the comprehensive value of the target stock land is obtained; wherein the land comprehensive value evaluation model is optimized by adopting a genetic algorithm. Various factors influencing the land parcel value can be comprehensively considered, a land comprehensive value evaluation model is established to evaluate the value of the developed land, scientific evaluation of the land parcel value is realized, and the demand of refined land management is met; and the land comprehensive value evaluation model is optimized through the genetic algorithm to improve the accuracy and credibility of the evaluation result.

Description

Technical Field

[0001] This invention relates to the field of land value assessment technology, and in particular to a method, apparatus, equipment, medium and product for land value assessment in land development. Background Technology

[0002] With the acceleration of urbanization, land resources are becoming increasingly scarce, and how to efficiently utilize existing land resources has become an urgent problem to be solved. Therefore, the valuation of land resources is particularly important. Traditional land valuation methods often focus on single factors, such as geographical location and transportation conditions, lacking a comprehensive consideration of land development potential and failing to meet the needs of refined land management. Summary of the Invention

[0003] This invention provides a method, apparatus, equipment, medium, and product for land value assessment in land development. It comprehensively considers various factors affecting land value and establishes a comprehensive land value assessment model to assess the value of developed land in order to meet the needs of refined land management.

[0004] To achieve the above objectives, embodiments of the present invention provide a land value assessment method for land development, comprising:

[0005] Obtain the value-influencing factors of the target existing land and standardize the value-influencing factors;

[0006] Based on the processed value-influencing factors, the target existing land is valued using an optimized land comprehensive value assessment model to obtain the comprehensive value of the target existing land; wherein, the land comprehensive value assessment model is optimized using a genetic algorithm.

[0007] As an improvement to the above scheme, the method for constructing the comprehensive land value assessment model includes:

[0008] Based on the processed value-influencing factors, a basic value model for the target stock land is constructed using multiple linear regression analysis.

[0009] Based on the aforementioned basic value model and industry correction coefficients, a development potential model for the target existing land is constructed.

[0010] The comprehensive land value assessment model for the target existing land is obtained by weighting the basic value model, the development potential model, and the environmental cost.

[0011] As an improvement to the above scheme, the optimization method for the land comprehensive value assessment model includes:

[0012] Obtain the actual value data and value influencing factors of several existing land parcels in the target area;

[0013] Based on the actual value data and the values ​​of the value influencing factors, a genetic algorithm is used to optimize the regression coefficients of the basic value model to obtain the optimized regression coefficients.

[0014] The industry correction coefficients are optimized using a preset Bayesian network to obtain optimized industry correction coefficients;

[0015] The optimized regression coefficients and industry correction coefficients are input into the land comprehensive value assessment model to obtain the optimized land comprehensive value assessment model.

[0016] As an improvement to the above scheme, the step of optimizing the regression coefficients of the basic value model using a genetic algorithm based on the actual value data and the values ​​of value influencing factors to obtain optimized regression coefficients includes:

[0017] With the goal of minimizing fitness values, an initial population is constructed based on the combination of regression coefficients, where each individual in the population represents a set of regression coefficients to be optimized.

[0018] Substitute each individual and the value influencing factors into the basic value model to obtain the basic value model prediction value of all existing land for each individual;

[0019] Based on the actual value data and the predicted value of the basic value model, the fitness value of each individual is calculated using the fitness function.

[0020] The initial population is iteratively optimized based on the fitness value through selection, crossover, and mutation. When the number of iterations reaches a preset threshold or the fitness value tends to stabilize, the individual with the smallest fitness value in the current population is selected as the optimized regression coefficient.

[0021] The fitness function is:

[0022]

[0023] In the formula, f(θ) represents the fitness function, θ is the set of regression coefficients to be optimized; K represents the sample size, which is the total number of existing land parcels; V k This refers to the actual value data of the kth existing land use. This is the predicted value of the basic value model for the kth existing land.

[0024] As an improvement to the above scheme, the method for constructing the preset Bayesian network includes:

[0025] Obtain historical planning adjustment data for several existing land parcels in the target area;

[0026] The historical planning adjustment data is defined as the parent node of the Bayesian network, and the land price sensitivity parameter is defined as the child node of the Bayesian network.

[0027] The dependencies between nodes of the Bayesian network are determined based on domain knowledge, and the conditional probability table of the Bayesian network is constructed using expert experience based on the historical planning adjustment data.

[0028] The historical planning adjustment data is used to train the Bayesian network and conditional probability table to calculate the posterior probability distribution of land price sensitivity parameters under different industries.

[0029] If the deviation of the posterior probability distribution is greater than a preset deviation threshold, then after adjusting the network structure of the Bayesian network and the conditional probability table, the adjusted Bayesian network and conditional probability table are trained using the historical planning adjustment data until the posterior probability distribution is not greater than the preset deviation threshold, thus obtaining the preset Bayesian network.

[0030] As an improvement to the above scheme, the optimization of the industry correction coefficient using a preset Bayesian network to obtain the optimized industry correction coefficient includes:

[0031] Obtain the planning adjustment data of the target existing land, and input the planning adjustment data into a preset Bayesian network;

[0032] Using the pre-defined structure and conditional probability table of a Bayesian network, the target posterior probability distribution of the land price sensitivity parameter corresponding to the target stock land is calculated through maximum likelihood estimation or Markov chain Monte Carlo method.

[0033] The expected value or most likely value is extracted from the target posterior probability distribution and used as the optimized industry correction coefficient.

[0034] To achieve the above objectives, embodiments of the present invention provide a land value assessment device for land development, comprising:

[0035] The influencing factor acquisition module is used to acquire the value influencing factors of the target existing land and to standardize the value influencing factors.

[0036] The land value assessment module is used to assess the value of the target existing land using an optimized land comprehensive value assessment model based on the processed value influencing factors, and to obtain the comprehensive value of the target existing land; wherein, the land comprehensive value assessment model is optimized using a genetic algorithm.

[0037] To achieve the above objectives, embodiments of the present invention provide a land value assessment device for land development, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the land value assessment method for land development described above.

[0038] To achieve the above objectives, embodiments of the present invention also provide a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the above-described land value assessment method for land development.

[0039] To achieve the above objectives, embodiments of the present invention also provide a computer program product, which is stored in a storage medium and executed by at least one processor to implement the steps of the land value assessment method for land development described above.

[0040] Compared with existing technologies, the present invention discloses a land value assessment method, apparatus, equipment, medium, and product for land development. This method acquires the value-influencing factors of a target existing land parcel and standardizes these factors. Based on the processed value-influencing factors, an optimized comprehensive land value assessment model is used to assess the value of the target existing land parcel, yielding its comprehensive value. The comprehensive land value assessment model is optimized using a genetic algorithm. This approach comprehensively considers multiple factors affecting land parcel value, establishing a comprehensive land value assessment model to assess the value of development land, achieving a scientific assessment of land parcel value to meet the needs of refined land management. Furthermore, the genetic algorithm optimization of the comprehensive land value assessment model enhances the accuracy and reliability of the assessment results. Attached Figure Description

[0041] Figure 1 This is a flowchart illustrating a land value assessment method for land development provided in an embodiment of the present invention;

[0042] Figure 2 This is a schematic diagram of the structure of a land value assessment device for land development provided in an embodiment of the present invention;

[0043] Figure 3 This is a structural block diagram of a land value assessment device for land development provided in an embodiment of the present invention. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] It should be noted that the terms "comprising" and "specific" in this invention, and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or device.

[0046] Please see Figure 1 , Figure 1 This is a flowchart illustrating a land value assessment method for land development provided in an embodiment of the present invention. The land value assessment method for land development includes:

[0047] S1, Obtain the value influencing factors of the target existing land, and standardize the value influencing factors;

[0048] S2, based on the processed value influencing factors, the target existing land is valued using an optimized land comprehensive value assessment model to obtain the comprehensive value of the target existing land; wherein, the land comprehensive value assessment model is optimized using a genetic algorithm.

[0049] For example, the land value assessment method for land development described in this embodiment of the invention can be implemented by an assessment server capable of interacting with target users. The assessment server acquires the value-influencing factors of the target existing land (e.g., individual factors include land area, shape index, plot ratio, etc.; location factors include subway distance, industrial radiation intensity, etc.; neighborhood factors include school density, PM2.5 concentration, etc.), and standardizes these value-influencing factors (e.g., standardizing all value-influencing factors, unifying data format and scope). Based on the processed value-influencing factors, an optimized comprehensive land value assessment model is used to assess the value of the target existing land, obtaining its comprehensive value. The comprehensive land value assessment model is optimized using a genetic algorithm. This optimization of the comprehensive land value assessment model through a genetic algorithm improves the accuracy and reliability of the assessment results; it comprehensively considers multiple value-influencing factors to achieve a scientific assessment of land value; and it proposes different development directions based on the comprehensive value, guiding users to rationally utilize land resources, improve land use efficiency, revitalize existing land resources, optimize urban spatial layout, and promote sustainable urban development.

[0050] It is worth noting that land area directly reflects the scale of development and the economic scale effect; shape index reflects land use efficiency, with more regular shapes resulting in lower development costs; subway distance reflects accessibility, a core factor influencing land prices, and this distance uses network distance rather than straight-line distance; industrial radiation intensity X4 is calculated based on a gravity model to determine the GDP of surrounding industrial parks. d The attenuation effect of distance d is calculated using the following formula: School density reflects the increased value of residential and commercial land due to high-quality educational resources; PM2.5 concentration x6 is a negative indicator of environmental quality, processed using a reverse Z-score; the higher this value, the lower the land price. Its calculation formula is... Where X6 is the original value of PM2.5 concentration; μ is the mean of PM2.5 concentration in the sample; σ is the standard deviation of PM2.5 concentration in the sample; and X′6 is the standardized value after processing.

[0051] Specifically, the method for constructing the comprehensive land value assessment model includes:

[0052] Based on the processed value-influencing factors, a basic value model for the target stock land is constructed using multiple linear regression analysis.

[0053] Based on the aforementioned basic value model and industry correction coefficients, a development potential model for the target existing land is constructed.

[0054] The comprehensive land value assessment model for the target existing land is obtained by weighting the basic value model, the development potential model, and the environmental cost.

[0055] For example, based on the processed value-influencing factors, a basic value model for the target existing land is constructed using multiple linear regression analysis. Planning adjustment factors (e.g., planning grade coefficient, current plot ratio) and industry correction coefficients are introduced. Based on the basic value model, planning adjustment factors, and industry correction coefficients, a development potential model for the target existing land is constructed. The basic value model, the development potential model, and environmental costs are weighted and calculated to obtain a comprehensive land value assessment model for the target existing land. The expression for the basic value model is:

[0056]

[0057] The expression for the potential development model is:

[0058]

[0059] The expression for the comprehensive land value assessment model is as follows:

[0060] V total =ω1V base +ω2V potential -ω3E,

[0061] In the formula, V base X1 represents the basic value of the target existing land; X2, X3, and X5 represent the processed land area, subway distance, and school density, respectively; α is a constant term; β1, β2, and β4 are regression coefficients; τ is a threshold (e.g., a baseline value for school density); e is the natural index; V potential γ represents the development potential of the target existing land; γ is the industry correction coefficient; P is the planning grade coefficient of the target existing land; C is the current plot ratio of the target existing land, wherein the planning grade coefficient and the current plot ratio are adjusted using a dynamic ratio mechanism; V total ω1 represents the comprehensive value of the target existing land; ω2 and ω3 are the weights corresponding to the basic value, development potential, and environmental cost, respectively, which can be determined by the analytic hierarchy process (AHP); E represents the environmental cost, which is calculated based on the treated PM2.5 concentration, combined with actual data such as the environmental governance cost and ecological restoration investment of the target existing land, and through expert experience or historical case fitting, the environmental quality index (PM2.5 concentration) is converted into a quantifiable cost value (such as the environmental governance cost per unit area).

[0062] Specifically, the optimization method for the land comprehensive value assessment model includes:

[0063] Obtain the actual value data and value influencing factors of several existing land parcels in the target area;

[0064] Based on the actual value data and the values ​​of the value influencing factors, a genetic algorithm is used to optimize the regression coefficients of the basic value model to obtain the optimized regression coefficients.

[0065] The industry correction coefficients are optimized using a preset Bayesian network to obtain optimized industry correction coefficients;

[0066] The optimized regression coefficients and industry correction coefficients are input into the land comprehensive value assessment model to obtain the optimized land comprehensive value assessment model.

[0067] For example, the key parameters (regression coefficients, industry correction coefficients) of the land comprehensive value assessment model are iteratively optimized to obtain the actual value data and value influencing factors of several existing land parcels in the target area; the mean square error (MSE) between the actual value and the model prediction value of several existing land parcel samples is used as the objective function to initialize the regression coefficient combination (population); iterative optimization is performed through selection (retaining combinations with low error coefficients), crossover (recombining coefficients to generate new combinations), and mutation (randomly adjusting coefficients to avoid local optima); after the iteration is terminated, the optimal coefficient set that minimizes MSE is output to ensure that the basic value can accurately reflect the actual impact of factors such as land area and subway distance. The industry correction coefficient reflects the land price sensitivity of different industries to planning adjustments. Based on a pre-set Bayesian network (parent nodes are industry type, planning level, and plot ratio change; child nodes are land price sensitivity parameter λ), historical planning changes and plot ratio adjustment data are input to train the network. The conditional probability table is updated through maximum likelihood estimation or Markov chain Monte Carlo method to optimize the network's prediction accuracy for the land price sensitivity parameter λ. For the industry type and planning adjustment status of the target plot, the expected value of the land price sensitivity parameter λ is output as the optimized industry correction coefficient γ to ensure that the development potential can dynamically adapt to industry characteristics and planning changes. The optimized regression coefficient and industry correction coefficient are input into the land comprehensive value assessment model to obtain the optimized land comprehensive value assessment model.

[0068] More specifically, the step of optimizing the regression coefficients of the basic value model using a genetic algorithm based on the actual value data and the values ​​of value influencing factors to obtain optimized regression coefficients includes:

[0069] With the goal of minimizing fitness values, an initial population is constructed based on the combination of regression coefficients, where each individual in the population represents a set of regression coefficients to be optimized.

[0070] Substitute each individual and the value influencing factors into the basic value model to obtain the basic value model prediction value of all existing land for each individual;

[0071] Based on the actual value data and the predicted value of the basic value model, the fitness value of each individual is calculated using the fitness function.

[0072] The initial population is iteratively optimized based on the fitness value through selection, crossover, and mutation. When the number of iterations reaches a preset threshold or the fitness value tends to stabilize, the individual with the smallest fitness value in the current population is selected as the optimized regression coefficient.

[0073] The fitness function is:

[0074]

[0075] In the formula, f(θ) represents the fitness function, θ is the set of regression coefficients to be optimized; K represents the sample size, which is the total number of existing land parcels; V k This refers to the actual value data of the kth existing land use. This is the predicted value of the basic value model for the kth existing land.

[0076] For example, the actual value data and value influencing factor values ​​(standardized feature variable values ​​corresponding to each sample) of existing land use samples are used as input data for the genetic algorithm. An initial population of a certain size (e.g., 50-100 individuals) is randomly generated, with each individual representing a set of regression coefficients to be optimized. For each individual (regression coefficient combination) in the population, the predicted value for each existing land use sample is calculated using the basic value model. The fitness function is then used to evaluate its performance; a smaller fitness value indicates a better prediction performance for the regression coefficient combination. The higher the accuracy of the prediction, the more efficient the selection process. Based on fitness values, high-quality individuals are selected, with individuals having lower fitness values ​​having a higher probability of being selected (e.g., using roulette wheel selection). Coefficient combinations with high prediction accuracy are retained. Selected individuals undergo gene recombination (e.g., randomly exchanging some coefficient values) to generate new coefficient combinations (offspring), expanding the search range. The coefficient values ​​of some offspring are randomly changed (e.g., adjusting the value of β1 with a small probability) to avoid the population getting trapped in local optima. The iteration is terminated when the number of iterations reaches a preset value (e.g., 100 times) or when the fitness values ​​of several generations tend to stabilize (i.e., the mean squared error no longer decreases significantly). The individual with the lowest fitness value in the population is selected, and its corresponding regression coefficient combination is the optimized regression coefficient. Through the above process, the optimized regression coefficient minimizes the deviation between the model's predicted value and the actual value, ensuring that the basic value model more accurately reflects the actual impact of various influencing factors (such as land area, transportation conditions, and educational resources) on land value, providing reliable parameters for subsequent development potential and comprehensive benefit assessment.

[0077] More specifically, the method for constructing the preset Bayesian network includes:

[0078] Obtain historical planning adjustment data for several existing land parcels in the target area;

[0079] The historical planning adjustment data is defined as the parent node of the Bayesian network, and the land price sensitivity parameter is defined as the child node of the Bayesian network.

[0080] The dependencies between nodes of the Bayesian network are determined based on domain knowledge, and the conditional probability table of the Bayesian network is constructed using expert experience based on the historical planning adjustment data.

[0081] The historical planning adjustment data is used to train the Bayesian network and conditional probability table to calculate the posterior probability distribution of land price sensitivity parameters under different industries.

[0082] If the deviation of the posterior probability distribution is greater than a preset deviation threshold, then after adjusting the network structure of the Bayesian network and the conditional probability table, the adjusted Bayesian network and conditional probability table are trained using the historical planning adjustment data until the posterior probability distribution is not greater than the preset deviation threshold, thus obtaining the preset Bayesian network.

[0083] For example, historical planning adjustment data (industry type, such as commercial, industrial, and residential land use; planning level, referring to the current and target planning use level of the land parcel, such as upgrading from industrial to commercial; plot ratio changes, such as approval records for increasing, decreasing, or maintaining the current plot ratio) of several existing land parcels in the target area are obtained. The historical planning adjustment data is cleaned to remove outliers or missing values; the data format is standardized to ensure consistency; planning level and plot ratio changes are classified and coded; the pre-processed industry type (e.g., commercial, industrial, residential), planning level, and plot ratio changes are defined as parent nodes of a Bayesian network, and the land price sensitivity parameter is defined as a child node of the Bayesian network; the dependencies between nodes are determined based on domain knowledge or data relevance; for example, commercial land may be more sensitive to plot ratio changes than industrial land; an upgrade in planning level (e.g., from industrial to commercial) will significantly affect land prices. Based on historical data statistics or expert experience, the conditional probabilities of each node are filled in to obtain a conditional probability table used to quantify the probability distribution of child nodes (land price sensitivity parameters) under different combinations of parent nodes. For example: given the industry as "commercial" and the plot ratio is increased, what is the probability distribution of land price sensitivity? Given the planning level as "high", what is the expected value of the land price sensitivity parameter? A Bayesian network is trained using historical planning adjustment data. Node parameters are learned through maximum likelihood estimation or Markov chain Monte Carlo methods. The posterior probability distribution of land price sensitivity under different industries is calculated. The model accuracy is verified through cross-validation or a reserved test set. If the model bias is large, the network structure needs to be adjusted or supplemented with data. If the posterior probability distribution is not greater than the preset bias threshold, the preset Bayesian network is obtained.

[0084] More specifically, the optimization of the industry correction coefficient using a preset Bayesian network to obtain the optimized industry correction coefficient includes:

[0085] Obtain the planning adjustment data of the target existing land, and input the planning adjustment data into a preset Bayesian network;

[0086] Using the pre-defined structure and conditional probability table of a Bayesian network, the target posterior probability distribution of the land price sensitivity parameter corresponding to the target stock land is calculated through maximum likelihood estimation or Markov chain Monte Carlo method.

[0087] The expected value or most likely value is extracted from the target posterior probability distribution and used as the optimized industry correction coefficient.

[0088] For example, the planning adjustment data is input into a preset Bayesian network. Using the network's structure and conditional probability table, and employing maximum likelihood estimation or Markov chain Monte Carlo methods, combined with model parameters trained from historical data, the posterior probability distribution of the land price sensitivity parameter corresponding to the target existing land is calculated. The expected value or most probable value is extracted from the posterior probability distribution of the land price sensitivity parameter as the optimized industry correction coefficient. For instance, if the plot ratio of an industrial land plot increases by 10%, the network calculation outputs λ = 1.2, which is the optimized industry correction coefficient.

[0089] This invention discloses a land value assessment method for land development, which involves acquiring the value-influencing factors of a target existing land, standardizing these factors, and then using an optimized land comprehensive value assessment model to assess the value of the target existing land based on the processed value-influencing factors, thereby obtaining the comprehensive value of the target existing land. The land comprehensive value assessment model is optimized using a genetic algorithm. This method improves the accuracy and reliability of the assessment results by optimizing the land comprehensive value assessment model through a genetic algorithm, and by comprehensively considering multiple value-influencing factors, achieves a scientific assessment of the land parcel's value.

[0090] See Figure 2 , Figure 2 This is a schematic diagram of the structure of a land value assessment device 10 for land development provided in an embodiment of the present invention. The land value assessment device 10 for land development includes:

[0091] The influencing factor acquisition module 11 is used to acquire the value influencing factors of the target existing land and to standardize the value influencing factors.

[0092] The land value assessment module 12 is used to assess the value of the target existing land by using an optimized land comprehensive value assessment model based on the processed value influencing factors, and to obtain the comprehensive value of the target existing land; wherein, the land comprehensive value assessment model is optimized using a genetic algorithm.

[0093] The land value assessment device 10 for land development provided in this embodiment of the invention can realize all the processes of the land value assessment method for land development in the above embodiments. The functions and technical effects of each module in the device are the same as those of the land value assessment method for land development in the above embodiments, and will not be repeated here.

[0094] See Figure 3 , Figure 3This is a schematic diagram of the structure of a land value assessment device 20 for land development provided in an embodiment of the present invention. The land value assessment device 20 for land development in this embodiment includes: a processor 21, a memory 22, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program, it implements the steps in the above-described land value assessment method embodiment for land development. Alternatively, when the processor 21 executes the computer program, it implements the functions of each module in the above-described land value assessment device embodiment for land development.

[0095] For example, the computer program may be divided into one or more modules, which are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the land value assessment device 20 for land development.

[0096] The land value assessment device 20 for land development can be a desktop computer, laptop, handheld computer, or cloud server, etc. The land value assessment device 20 for land development may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will understand that the schematic diagram is merely an example of the land value assessment device 20 for land development and does not constitute a limitation on the device. It may include more or fewer components than shown in the diagram, or combine certain components, or use different components. For example, the land value assessment device 20 for land development may also include input / output devices, network access devices, buses, etc.

[0097] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The processor 21 is the control center of the land valuation equipment 20 for the land development, connecting all parts of the land valuation equipment 20 through various interfaces and lines.

[0098] The memory 22 can be used to store the computer programs and / or modules. The processor 21 implements various functions of the land value assessment device 20 for land development by running or executing the computer programs and / or modules stored in the memory 22 and calling the data stored in the memory 22. The memory 22 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0099] If the integrated module of the land value assessment equipment 20 for land development is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by the processor 21, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium may be appropriately added to or subtracted from the content as required by the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium may not include electrical carrier signals and telecommunication signals.

[0100] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0101] This invention also provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform a land value assessment method for land development as described in the above embodiments.

[0102] Furthermore, embodiments of the present invention also provide a computer program product, which is stored in a storage medium and executed by at least one processor to implement the steps of the land value assessment method for land development described above.

[0103] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for assessing land value in land development, characterized in that, include: Obtain the value-influencing factors of the target existing land and standardize the value-influencing factors; Based on the processed value-influencing factors, the target existing land is valued using an optimized land comprehensive value assessment model to obtain the comprehensive value of the target existing land; wherein, the land comprehensive value assessment model is optimized using a genetic algorithm.

2. The land value assessment method for land development as described in claim 1, characterized in that, The method for constructing the comprehensive land value assessment model includes: Based on the processed value-influencing factors, a basic value model for the target stock land is constructed using multiple linear regression analysis. Based on the aforementioned basic value model and industry correction coefficients, a development potential model for the target existing land is constructed. The comprehensive land value assessment model for the target existing land is obtained by weighting the basic value model, the development potential model, and the environmental cost.

3. The land value assessment method for land development as described in claim 2, characterized in that, The optimization method for the land comprehensive value assessment model includes: Obtain the actual value data and value influencing factors of several existing land parcels in the target area; Based on the actual value data and the values ​​of the value influencing factors, a genetic algorithm is used to optimize the regression coefficients of the basic value model to obtain the optimized regression coefficients. The industry correction coefficients are optimized using a preset Bayesian network to obtain optimized industry correction coefficients; The optimized regression coefficients and industry correction coefficients are input into the land comprehensive value assessment model to obtain the optimized land comprehensive value assessment model.

4. The land value assessment method for land development as described in claim 3, characterized in that, The step involves optimizing the regression coefficients of the basic value model using a genetic algorithm based on the actual value data and the values ​​of value influencing factors, to obtain optimized regression coefficients, including: With the goal of minimizing fitness values, an initial population is constructed based on the combination of regression coefficients, where each individual in the population represents a set of regression coefficients to be optimized. Substitute each individual and the value influencing factors into the basic value model to obtain the basic value model prediction value of all existing land for each individual; Based on the actual value data and the predicted value of the basic value model, the fitness value of each individual is calculated using the fitness function. The initial population is iteratively optimized based on the fitness value through selection, crossover, and mutation. When the number of iterations reaches a preset threshold or the fitness value tends to stabilize, the individual with the smallest fitness value in the current population is selected as the optimized regression coefficient. The fitness function is: In the formula, f(θ) represents the fitness function, θ is the set of regression coefficients to be optimized; K represents the sample size, which is the total number of existing land parcels; V k This refers to the actual value data of the kth existing land use. This is the predicted value of the basic value model for the kth existing land.

5. The land value assessment method for land development as described in claim 3, characterized in that, The method for constructing the preset Bayesian network includes: Obtain historical planning adjustment data for several existing land parcels in the target area; The historical planning adjustment data is defined as the parent node of the Bayesian network, and the land price sensitivity parameter is defined as the child node of the Bayesian network. The dependencies between nodes of the Bayesian network are determined based on domain knowledge, and the conditional probability table of the Bayesian network is constructed using expert experience based on the historical planning adjustment data. The historical planning adjustment data is used to train the Bayesian network and conditional probability table to calculate the posterior probability distribution of land price sensitivity parameters under different industries. If the deviation of the posterior probability distribution is greater than a preset deviation threshold, then after adjusting the network structure of the Bayesian network and the conditional probability table, the adjusted Bayesian network and conditional probability table are trained using the historical planning adjustment data until the posterior probability distribution is not greater than the preset deviation threshold, thus obtaining the preset Bayesian network.

6. The land value assessment method for land development as described in claim 3, characterized in that, The process of optimizing the industry correction coefficient using a preset Bayesian network to obtain the optimized industry correction coefficient includes: Obtain the planning adjustment data of the target existing land, and input the planning adjustment data into a preset Bayesian network; Using the pre-defined structure and conditional probability table of a Bayesian network, the target posterior probability distribution of the land price sensitivity parameter corresponding to the target stock land is calculated through maximum likelihood estimation or Markov chain Monte Carlo method. The expected value or most likely value is extracted from the target posterior probability distribution and used as the optimized industry correction coefficient.

7. A land value assessment device for land development, characterized in that, include: The influencing factor acquisition module is used to acquire the value influencing factors of the target existing land and to standardize the value influencing factors. The land value assessment module is used to assess the value of the target existing land using an optimized land comprehensive value assessment model based on the processed value influencing factors, and to obtain the comprehensive value of the target existing land; wherein, the land comprehensive value assessment model is optimized using a genetic algorithm.

8. A land value assessment device for land development, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the land value assessment method for land development as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the land value assessment method for land development as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product is stored in a storage medium, and the program product is executed by at least one processor to implement the steps of the land value assessment method for land development as described in any one of claims 1-6.

Images