Land value evaluation method, system, equipment and medium

Abstract

The invention relates to the technical field of land resource assessment, in particular to a land value assessment method, system and device and a medium, and the method comprises the steps: obtaining land initial data, analyzing the land initial data, and obtaining analysis result information; performing principal component analysis on the analysis result information to obtain a principal component feature set and a principal component score set corresponding to the principal component feature set; training the principal component score set to obtain a weight coincidence set corresponding to the principal component feature set, and performing evaluation according to the principal component score set and the weight coincidence set to obtain comprehensive value score information; the method comprises the steps of obtaining an evaluation threshold, judging whether comprehensive value score information is higher than the evaluation threshold, obtaining suitable storage information under the condition that the comprehensive value score information is higher than the evaluation threshold, and combining a plurality of pieces of suitable storage information into a storage area set, so that the land value evaluation result is more accurate, and the evaluation efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of land resource assessment, and in particular to a land value assessment method, system, equipment and medium. Background Art

[0002] Land resources are an important foundation for urban development and economic growth. With the acceleration of urbanization, the demand for land development and construction in complex areas is increasing, so there is a need to evaluate and utilize land resources in a more scientific and reasonable way.

[0003] At present, there are many factors that need to be considered in the assessment and utilization of land resources, and in the process of land preparation, most of them are handled manually, which mainly relies on manual experience. This method is not only inefficient, but also the assessment results and how to use them are easily affected by subjective factors, resulting in inaccurate and unfair decision-making results. The above problems need to be solved. Summary of the invention

[0004] In order to make the results of land value assessment more accurate and improve assessment efficiency, this application provides a land value assessment method, system, device and medium, which adopts the following technical solutions:

[0005] In a first aspect, the present application provides a land value assessment method, comprising:

[0006] Obtaining initial land data, parsing the initial land data, and obtaining parsing result information;

[0007] Perform principal component analysis on the parsing result information to obtain the principal component feature set and its corresponding principal component score set;

[0008] The principal component score set is trained to obtain the weight set corresponding to the principal component feature set, and the principal component score set and the weight set are evaluated to obtain the comprehensive value score information;

[0009] An assessment threshold is obtained to determine whether the comprehensive value score information is higher than the assessment threshold. When the comprehensive value score information is higher than the assessment threshold, suitable storage information is obtained, and several suitable storage information are merged into a storage area collection.

[0010] Preferably, it also includes:

[0011] According to the collection of purchase and storage areas, the corresponding economic data information and economic range thresholds are obtained, and the land transformation model results are obtained based on the economic data information and economic range thresholds.

[0012] Preferably, the analysis result information includes several land feature information.

[0013] Preferably, the specific steps of performing principal component analysis on the parsing result information to obtain a principal component feature set and its corresponding principal component score set are:

[0014] PCA is used to perform principal component analysis on several land characteristic information of the analysis result information to obtain a principal component feature set and a principal component score set, wherein the principal component feature set includes several principal component feature information, each principal component feature information includes at least one land characteristic information, and the principal component score set includes several principal component score information set corresponding to the principal component feature information.

[0015] Preferably, the specific steps of training the principal component score set to obtain the weight set corresponding to the principal component feature set are:

[0016] The random forest algorithm is used to train the principal component score set to obtain a number of weight information corresponding to the principal component score information, and the several weight information are combined into a weight set.

[0017] Preferably, the specific steps of evaluating according to the principal component score set and the weight set to obtain the comprehensive value score information are:

[0018] The calculation is performed based on the principal component score information and weight information corresponding to the same principal component feature information to obtain the first score information corresponding to each principal component feature information, and the comprehensive value score information is obtained by adding up several first score information.

[0019] In a second aspect, the present application provides a land value assessment system, comprising:

[0020] The data acquisition module is used to acquire the initial land data, analyze the initial land data, and obtain the analysis result information;

[0021] An analysis module is used to perform principal component analysis on the analysis result information to obtain a principal component feature set and its corresponding principal component score set;

[0022] An evaluation module is used to train the principal component score set to obtain the weight set corresponding to the principal component feature set, and to evaluate the principal component score set and the weight set to obtain comprehensive value score information;

[0023] The storage module is used to obtain the evaluation threshold and determine whether the comprehensive value score information is higher than the evaluation threshold. When the comprehensive value score information is higher than the evaluation threshold, suitable storage information is obtained, and several suitable storage information are merged into a storage area collection.

[0024] Preferably, it also includes:

[0025] The mode selection module is used to obtain the corresponding economic data information and economic interval thresholds based on the collection of storage areas, and to determine the land transformation mode results based on the economic data information and economic interval thresholds.

[0026] In a third aspect, the present application provides a land value assessment device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the land value assessment method as described above.

[0027] In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the land value assessment method as described above when run.

[0028] In summary, compared with the prior art, the technical solution provided by this application has at least the following beneficial effects:

[0029] The present application parses the acquired initial land data to obtain parsing result information including multiple land feature information, performs principal component analysis on the parsing result information to obtain a principal component feature set and its corresponding principal component score set, divides the principal component feature set and analyzes its score to provide a reference for subsequent judgment of the value of the land, trains the principal component score set to obtain a weight set corresponding to the principal component feature set, calculates and evaluates the principal component score set and the weight set to obtain comprehensive value score information representing the land, and uses an evaluation threshold to determine whether the comprehensive value score information is suitable for storage, thereby reducing human intervention, making the results of land value assessment more accurate, and improving assessment efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a flow chart of a land value assessment method described in an embodiment of the present application.

[0031] Figure 2 It is a module schematic diagram of a land value assessment system described in an embodiment of the present application.

[0032] Description of reference numerals:

[0033] 1. Data acquisition module; 2. Analysis module; 3. Evaluation module; 4. Storage module. DETAILED DESCRIPTION

[0034] The following combination Figure 1-Figure 2 The present application is described in further detail. The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to be limiting.

[0035] Reference Figure 1, a land value assessment method involved in this application specifically includes:

[0036] Step S1: Acquire initial land data, analyze the initial land data, and obtain analysis result information;

[0037] Step S2: Perform principal component analysis on the parsing result information to obtain a principal component feature set and its corresponding principal component score set;

[0038] Step S3: training the principal component score set to obtain the weight set corresponding to the principal component feature set, and evaluating the principal component score set and the weight set to obtain comprehensive value score information;

[0039] Step S4: Obtain an evaluation threshold, determine whether the comprehensive value score information is higher than the evaluation threshold, and if the comprehensive value score information is higher than the evaluation threshold, obtain suitable storage information, and merge several suitable storage information into a storage area collection.

[0040] Specifically, in the process of land preparation, how to judge which areas are suitable for storage is a key issue. The traditional approach mainly relies on manual experience, which is not only inefficient, but also easily affected by subjective factors, resulting in inaccurate and unfair decision-making results. In order to solve this problem, this application constructs a comprehensive land value identification system that can combine multiple factors, such as rail, subway, superstructure building volume, mountainous areas, rigid control elements, basic farmland, ecological corridors, river management scope lines, ecological red lines, and development boundaries, to make a comprehensive judgment. This application parses the acquired initial land data to obtain parsing result information containing multiple land feature information. After principal component analysis of the parsed result information, the principal component feature set and its corresponding principal component score set are obtained. The division of the principal component feature set and the analysis of its score provide a reference for the subsequent judgment of the value of the land. The principal component score set is trained to obtain the weight collection corresponding to the principal component feature set. The principal component score set and the weight collection are calculated and evaluated to obtain the comprehensive value score information representing the land. The evaluation threshold is used to determine whether the comprehensive value score information is suitable for storage, thereby reducing human intervention, making the results of land value assessment more accurate, and improving assessment efficiency.

[0041] In the process of land preparation, combining multiple factors is of great significance for land value assessment and development decision-making. The initial land data usually consists of relevant information such as rail, subway, building volume of superstructure, mountain, rigid control elements, basic farmland, ecological corridor, river management scope line, ecological red line, and development boundary. Among them, since rail and subway are important components of the urban transportation network, their existence can improve the accessibility and convenience of surrounding land, thereby increasing the value of land, so the relevant data of rail and subway are used as sub-data of the initial land data. The building volume of superstructure reflects the utilization intensity and development potential of land, so the building volume of superstructure is used as sub-data of the initial land data. Mountainous terrain has a great impact on land development. Its slope, vegetation coverage rate and other factors will affect the difficulty and utilization efficiency of land development, so the relevant data of mountainous terrain are used as sub-data of the initial land data. Rigid control elements, such as basic farmland, ecological corridor, river management scope line, ecological red line, etc., are important restrictive factors in urban planning, and play a key role in protecting the ecological environment and the rational use of land resources, so the rigid control elements are used as sub-data of the initial land data. The development boundary is an important reference line in urban planning. It determines the scope and direction of urban development and has guiding significance for the development and utilization of land. Therefore, the development boundary is used as a sub-data of the initial land data. Taking the above factors into consideration, the value of land can be more comprehensively evaluated and a scientific basis can be provided for land development decisions. Through the comprehensive analysis of these factors, it is possible to more accurately determine which areas are suitable for storage and select appropriate transformation models. At the same time, it helps to protect the ecological environment, ensure the rational use of land resources, and promote the sustainable development of cities.

[0042] As one implementation method, the analysis result information includes some land feature information.

[0043] Specifically, since there is usually more than one terminal for acquiring the initial land data, the acquired data needs to extract key information for storage. The extracted parsing result information includes several land feature information. The embodiment of the present application can efficiently obtain the key information required for land value assessment and development decision-making by utilizing the public data interface and commercial data services of relevant units. The process includes executing an API request to obtain data, parsing the obtained data, and storing the parsed data in a database for standby use. This series of operations lays an accurate and real-time data foundation for the decision support system.

[0044] As one of the implementation methods, principal component analysis is performed on the analysis result information to obtain a principal component feature set and its corresponding principal component score set. The specific steps are: PCA is used to perform principal component analysis on several land characteristic information of the analysis result information to obtain a principal component feature set and a principal component score set, wherein the principal component feature set includes several principal component feature information, each principal component feature information includes at least one land characteristic information, and the principal component score set includes several principal component score information corresponding to the principal component feature information settings.

[0045] Specifically, PCA, principal component analysis, is a statistical method that converts the original data into a new coordinate system through an orthogonal transformation, so that the first largest variance direction of the projection of any data, that is, the first principal component feature information, has the largest variance, that is, the data changes the most in this direction. And each new coordinate axis, that is, each principal component, is orthogonal to the previous coordinate axis, and orthogonal coordinate axes indicate no correlation. After the embodiment of the present application obtains the original data set in step S1, the result information is parsed, including but not limited to land area, location, surrounding facilities, traffic conditions, historical transaction prices, etc.

[0046] One implementation method is as follows: suppose there are 5 plots of land, each of which has the following 5 features: A-land area (square meters), B-location (1 for city center, 2 for suburbs, 3 for remote suburbs), C-number of surrounding facilities (such as schools, hospitals, shopping centers), D-traffic conditions (1 for convenient, 2 for general, 3 for inconvenient), E-historical transaction price (average price per square meter), each feature in the land information contains a corresponding score or parameter. However, since the scoring criteria for each land feature information are different, in the process of analyzing the initial land data, it is necessary to standardize the data. First, standardize each feature so that the value of each feature is in a similar range, such as between 0 and 1. Then, calculate the covariance matrix of these standardized data, the matrix knows the correlation between each feature, and finally calculate the eigenvalues ​​and eigenvectors of the covariance matrix.

[0047] The importance of each principal component is known through the eigenvalue, and the direction of each principal component is known through the eigenvector. According to the size of the eigenvalue, the first few most important principal components are selected. Assuming that the two most important principal components are selected, the set of selected principal components is called the principal component feature set. The two principal components in the embodiment of the present application are weighted combinations of the original features. For example: the first principal component is "comprehensive value", which is mainly represented by a weighted combination of land area, location, and historical transaction price. The second principal component is "traffic convenience", which is mainly represented by a weighted combination of location and traffic conditions. That is, the principal component feature set in the embodiment of the present application is composed of two principal component feature information, and the principal component feature information is obtained by principal component analysis, PCA, from the parsing result information. This allows the land characteristics of the plot to be divided more accurately and more targeted, so that more accurate comprehensive value score information can be obtained later.

[0048] The embodiment of the present application calculates the score of each piece of land on these two principal components. These scores are obtained by multiplying the original features with the corresponding feature vectors. For example: Land A scores very high on "comprehensive value" because it has a large area, a good location, and a high price, refer to the above ABE. Land B scores very high on "transportation convenience" because it is located in the city center and has good traffic conditions, refer to the above CD. The principal component feature set of this application is used as two new "labels" to describe the characteristics of the land, such as "comprehensive value" and "transportation convenience." The principal component score set is the score of each piece of land based on these two "labels", and the higher the score, the more outstanding the land is in these aspects.

[0049] Among them, the area and location of the land are set as the key factors to determine its value. A large area of ​​land means higher development potential, and a superior geographical location means better accessibility and higher rent or sales price. Historical transaction prices provide a direct assessment of the market's value of the land. Therefore, the "comprehensive value" principal component occupies a core position in land value assessment. "Comprehensive value" is a principal component, which is usually a weighted linear combination of original features such as land area, location, historical transaction prices, etc., reflecting the overall economic value of the land. This principal component attempts to capture the key factors of land value, including but not limited to: Land area: The size of the land directly affects its potential development value and use value. Location: The geographical location of the land is an important factor in determining its value, such as land in the city center is usually more valuable than land in the suburbs. Historical transaction price: The historical land transaction price can reflect the market's recognition and evaluation of the value of a particular piece of land. In PCA, these features are combined into a single indicator, and each feature is assigned a different weight according to its contribution to the value of the land. A high score on this principal component means that the land performs well in these key factors and therefore has a high comprehensive value.

[0050] Transportation accessibility directly affects the attractiveness and efficiency of land use. Good transportation connections can increase the commercial value of land, promote economic development, and improve the quality of life of residents. In urban development planning, transportation accessibility is an important factor in determining land use and development patterns. "Transportation accessibility" is another principal component that mainly reflects the accessibility and transportation connectivity of land. This principal component includes a combination of the following characteristics: Location, whether the land is located near a transportation hub, such as a subway station, bus station, or major road. Traffic conditions, the traffic conditions around the land, such as road quality, traffic congestion, etc. A high score on this principal component indicates that the land has good transportation connections, which is an important advantage for commercial development, residence, or any use that requires convenient transportation.

[0051] In practical applications, comprehensive value and transportation convenience are usually given higher weights because they have a significant impact on land value assessment and development decisions. The principal component scores obtained by PCA and the weights determined by the random forest algorithm can be used to calculate the weighted index score of each land sample, thereby providing a basis for land acquisition and transformation.

[0052] Among them, principal component analysis is used for dimensionality reduction, the purpose is to extract the most important features from the original data set, these features can represent the variability of the data to the greatest extent. The main basis of the selection process includes: the size of the eigenvalue. In PCA, each principal component has a corresponding eigenvalue, which indicates the size of the variance of the data in the direction of the principal component. The larger the eigenvalue, the more data variability explained by the principal component, so the principal component with a larger eigenvalue is selected; the cumulative contribution rate, usually several principal components are selected so that the cumulative contribution rate of these principal components reaches a predetermined threshold, such as 90% or 95%. The cumulative contribution rate refers to the sum of the variance contribution rates of the first n principal components, which indicates the percentage of the total variability of the original data that these principal components can explain; the explanatory power of the data, the selected principal components should be able to explain as much information in the original data set as possible, that is, they should have a high correlation with the variables in the original data set; practical significance, in some cases, the selected principal components should also have practical explanatory significance, that is, they should be able to correspond to certain characteristics or attributes in the real world, which is more helpful to understand the data. For example: there is a set of land data, including features such as land area, location, number of surrounding facilities, traffic conditions and historical transaction prices. After PCA processing, several principal components are obtained, each with an eigenvalue. The first principal component may be highly correlated with land area, location, and historical transaction price, with the largest eigenvalue, indicating that it explains the greatest variability in the data. The second principal component may be related to traffic conditions and the number of surrounding facilities, with the second largest eigenvalue. The third principal component may be related to some other less important features, with a smaller eigenvalue. In this case, the first two principal components will be selected because they have large eigenvalues, the cumulative contribution rate may have reached more than 90%, and they are related to the key factors in land value assessment and have practical significance. In this way, these two principal components can be used to construct a weighted indicator score model to evaluate the value of the land.

[0053] Furthermore, the selection of principal components is usually performed automatically through statistical methods. In practical applications, especially in specific fields such as land value assessment, some specific principal components are preset according to professional knowledge and actual needs, and these principal components reflect the land attributes that are generally considered important.

[0054] Specifically, before starting PCA, according to the needs of land evaluation, some principal component targets are preset, such as "comprehensive value", "transportation convenience", "medical resource priority" and "teaching resource priority". For each preset principal component, you need to select related features. For example: "comprehensive value" is related to land area, location, historical transaction price, etc. "Transportation convenience" is related to traffic conditions, distance from the city center, accessibility of public transportation, etc. "Medical resource priority" is related to the number of hospitals, quality of medical services, coverage of medical facilities, etc. "Teaching resource priority" is related to the number of schools, quality of education, distribution of educational resources, etc. Although the features are pre-selected, PCA processing is still performed automatically. PCA calculates the covariance between these features and extracts the principal components that best represent the variability of the data.

[0055] After PCA is completed, each principal component is a linear combination of pre-selected features. Each principal component needs to be interpreted to see if it matches the preset target. For example, if the "comprehensive value" principal component is mainly composed of high weights for land area and historical transaction price, then it is believed that this principal component does reflect the comprehensive value of the land.

[0056] After determining the principal components, determine the weight of each feature in the principal components. These weights reflect the contribution of each feature to the principal components. It is necessary to verify whether the preset principal components are reasonable and adjust them according to the actual situation. If the preset principal components do not reflect the key attributes of the land well, or do not meet the actual needs, it is necessary to reselect the features or adjust the objectives of the principal components.

[0057] As one of the implementation methods, the specific steps of training the principal component score set to obtain the weight collection corresponding to the principal component feature set are: using the random forest algorithm to train the principal component score set to obtain several weight information corresponding to the principal component score information, and combining the several weight information into a weight collection.

[0058] Specifically, the embodiment of the present application uses a random forest algorithm for training. The random forest algorithm, RandomForest, is an integrated learning method for solving classification and regression problems. The task is completed by constructing multiple decision trees to improve the prediction accuracy. The random forest algorithm is used to train the principal component score set after principal component analysis conversion, and these principal component score sets are used as features to input the random forest model for training. The model learns the relationship between the feature and the target variable, for example, land value or other related indicators, to obtain the feature importance score. The feature importance score obtained by the random forest algorithm is directly used as the weight of each principal component to obtain a weight set. Among them, after the training is completed, the random forest model will provide an importance score for each principal component feature information. This score is based on the contribution of each feature to the prediction accuracy in the model. The feature importance score obtained by the random forest algorithm is used as the weight of each principal component. It means that if a principal component is considered to be more important in the random forest model, it will get a higher weight, so that the value of the plot can be more reasonably evaluated.

[0059] As one of the implementation modes, the specific steps for evaluating according to the principal component score set and the weight set to obtain the comprehensive value score information are as follows: calculating according to the principal component score information and weight information corresponding to the same principal component feature information to obtain the first score information corresponding to each principal component feature information, and adding up several first score information to obtain the comprehensive value score information.

[0060] Specifically, for each land sample, the system multiplies its score on each principal component by the corresponding weight, and then sums them up to get the weighted index score of the sample. This sum score is the comprehensive value score of the land sample. The principal component score set has multiple principal component scores. After training with the random forest algorithm, each principal component has an importance score. The weighted index score, that is, the comprehensive value score information, is obtained by multiplying the principal component score by the importance score. The weighted index score calculation example of the land sample is as follows:

[0061] Suppose that the scores of a land sample on the three principal components are PC1=1.2, PC2=0.8, and PC3=0.6, and the random forest model assigns weights of 0.5, 0.3, and 0.2 to these three principal components respectively.

[0062] The weighted indicator score is calculated as follows:

[0063] Weighted index score = (score of PC1 × weight of PC1) + (score of PC2 × weight of PC2) + (score of PC3 × weight of PC3);

[0064] Weighted index score = (1.2 × 0.5) + (0.8 × 0.3) + (0.6 × 0.2);

[0065] Weighted index score = 0.6 + 0.24 + 0.12;

[0066] Weighted index score = 0.96;

[0067] In summary, the comprehensive value score information of the land sample is obtained, that is, the weighted index score is 0.96. This score is used to evaluate the value of the land, or to compare with the scores of other land samples. This application reclassifies the land characteristics according to their importance or other criteria, which can more accurately distinguish the different characteristics or potential of the land. By introducing a weight coefficient for each feature category, the degree of influence of different features on the final comprehensive value score can be adjusted according to actual needs. For example, higher weights are given to certain important features, while lower weights are given to other minor features. The scores of each feature are multiplied by their corresponding weight coefficients, and the sum is added to obtain a comprehensive value score. This comprehensive score can help decision makers quickly evaluate and compare the comprehensive value of different lands, which helps to make more informed land use or investment decisions.

[0068] As one of the implementation methods, the corresponding economic data information and economic range threshold are obtained according to the collection of storage areas, and the land transformation model result is determined based on the economic data information and the economic range threshold.

[0069] Specifically, the weighted index score model established in step S3 is used to evaluate each potential storage area, calculate the score, that is, the above-mentioned comprehensive value score information, and set a score threshold to determine which areas are suitable for storage. The weighted index score of each area, that is, the comprehensive value score, is compared with the set threshold, and the scores of areas with scores higher than the threshold are taken as a score set, and the areas with scores higher than the threshold are selected as candidate areas suitable for storage, thereby obtaining an area set.

[0070] Based on the determined set of candidate areas suitable for acquisition and storage, obtain relevant economic data for the corresponding areas, such as the current market value of the land, expected development costs, future appreciation potential, etc.

[0071] Use financial models, such as net present value (NPV), to calculate the economic indicators of each region and obtain a set of economic indicator values. For example, the formula: Among them, R t is the expected income in year t. r is the discount rate, C is the initial investment cost, and T is the number of years considered.

[0072] Current market value of the land: as part of the initial investment cost C.

[0073] Expected development costs: This is an important component of the initial investment cost C and includes related costs such as construction, planning, legal procedures, etc.

[0074] Future value-added potential: This will affect R t , which is our estimate of the expected income brought by land development each year in the future.

[0075] Preset an economic interval threshold, corresponding to the micro-renovation, partial renovation, and comprehensive renovation modes respectively. Compare the economic indicator values of each region with the economic intervals, and allocate the renovation mode according to the falling interval. It includes: Micro-renovation mode: The economic indicator value is lower than the threshold of the first interval; Partial renovation mode: The economic indicator value is within the second interval; Comprehensive renovation mode: The economic indicator value is higher than the threshold of the third interval; Thus, the renovation mode of each region is determined. Example: Suppose we set the following economic interval thresholds: Micro-renovation mode: NPV ≤ 1 million yuan, Partial renovation mode: 1 million yuan < NPV ≤ 5 million yuan, Comprehensive renovation mode: NPV > 5 million yuan.

[0076] Refer to Figure 2 , and provide a land value evaluation system for the embodiments of this application. The system includes:

[0077] A data acquisition module, used to acquire the initial land data, parse the initial land data, and obtain the parsed result information;

[0078] An analysis module, used to perform principal component analysis on the parsed result information to obtain the principal component feature set and its corresponding principal component score set;

[0079] An evaluation module, used to train the principal component score set to obtain the weight set corresponding to the principal component feature set, and evaluate according to the principal component score set and the weight set to obtain the comprehensive value score information;

[0080] A storage module, used to acquire the evaluation threshold, judge whether the comprehensive value score information is higher than the evaluation threshold. In the case where the comprehensive value score information is higher than the evaluation threshold, obtain the suitable storage information, and merge several pieces of suitable storage information into the storage area set.

[0081] Specifically, it further includes: A mode selection module, used to obtain the corresponding economic data information and economic interval threshold according to the storage area set, and judge to obtain the land renovation mode result according to the economic data information and economic interval threshold.

[0082] The embodiments of this application provide a land value evaluation device, including a memory and a processor. The memory stores a computer program, and the processor is configured to run the computer program to execute the land value evaluation method as described above.

[0083] An embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the land value assessment method as described above when running.

[0084] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device and product can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0085] In several embodiments provided in this application, it should be understood that the disclosed methods, systems, devices and program products may be implemented in other ways.

[0086] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0087] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A land value assessment method, characterized in that: include: Obtaining initial land data, parsing the initial land data, and obtaining parsing result information; Perform principal component analysis on the parsing result information to obtain the principal component feature set and its corresponding principal component score set; The principal component score set is trained to obtain the weight set corresponding to the principal component feature set, and the principal component score set and the weight set are evaluated to obtain the comprehensive value score information; An assessment threshold is obtained to determine whether the comprehensive value score information is higher than the assessment threshold. When the comprehensive value score information is higher than the assessment threshold, suitable storage information is obtained, and several suitable storage information are merged into a storage area collection.

2. The land value assessment method according to claim 1, characterized in that: Also includes: According to the collection of purchase and storage areas, the corresponding economic data information and economic range thresholds are obtained, and the land transformation model results are obtained based on the economic data information and economic range thresholds.

3. The land value assessment method according to claim 1, characterized in that: The analysis result information includes several land feature information.

4. The land value assessment method according to claim 3, characterized in that: The specific steps of performing principal component analysis on the parsing result information to obtain the principal component feature set and its corresponding principal component score set are: PCA is used to perform principal component analysis on several land characteristic information of the analysis result information to obtain a principal component feature set and a principal component score set, wherein the principal component feature set includes several principal component feature information, each principal component feature information includes at least one land characteristic information, and the principal component score set includes several principal component score information set corresponding to the principal component feature information.

5. The land value assessment method according to claim 4, characterized in that: The specific steps of training the principal component score set to obtain the weight set corresponding to the principal component feature set are: The random forest algorithm is used to train the principal component score set to obtain a number of weight information corresponding to the principal component score information, and the several weight information are combined into a weight set.

6. The land value assessment method according to claim 5, characterized in that: The specific steps of evaluating the principal component score set and the weight set to obtain the comprehensive value score information are as follows: The calculation is performed based on the principal component score information and weight information corresponding to the same principal component feature information to obtain the first score information corresponding to each principal component feature information, and the comprehensive value score information is obtained by adding up several first score information.

7. A land value assessment system, characterized in that: include: The data acquisition module is used to acquire the initial land data, analyze the initial land data, and obtain the analysis result information; An analysis module is used to perform principal component analysis on the analysis result information to obtain a principal component feature set and its corresponding principal component score set; An evaluation module is used to train the principal component score set to obtain the weight set corresponding to the principal component feature set, and to evaluate the principal component score set and the weight set to obtain comprehensive value score information; The storage module is used to obtain the evaluation threshold and determine whether the comprehensive value score information is higher than the evaluation threshold. When the comprehensive value score information is higher than the evaluation threshold, suitable storage information is obtained, and several suitable storage information are merged into a storage area collection.

8. The land value assessment system according to claim 7, characterized in that: Also includes: The mode selection module is used to obtain the corresponding economic data information and economic interval thresholds based on the collection of storage areas, and to determine the land transformation mode results based on the economic data information and economic interval thresholds.

9. A land value assessment device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the land value assessment method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the land value assessment method according to any one of claims 1 to 6 when running.

Images