CN116911884A - Natural resource public land price management system and method based on big data - Google Patents

Abstract

The application discloses a natural resource public land price management system and method based on big data, wherein the system comprises the following steps: the data crawling module crawls the original data of public land price system construction result information on the network; the big data processing module performs data cleaning and screening processing on the original data to obtain processed data; the land price management module extracts the public land price related information, and correspondingly fills the public land price related information into a public land price management table of the unified template; the input information acquisition module acquires to-be-estimated object information input by a user; the query module queries the public land price information, the calculation factors and the correction factors; the calculation module calculates the land block price of the object to be estimated. And acquiring public land price system construction result information data of each region by adopting a big data technology, extracting public land price related information to form public land price management data of a unified template after big data processing, and enabling a user to quickly inquire automatic valuations of objects to be estimated in the corresponding region for auxiliary reference.

Description

A natural resource public land price management system and method based on big data

Technical field

The present invention relates to the technical field of public land price management, and specifically relates to a natural resource public land price management system and method based on big data.

Background technique

Land price can be understood as the income obtained by land owners from transferring land use rights to land demanders, and is a reflection of land owners' rights and interests. Publicly announced land prices are my country's legal land price system, including benchmark land prices, demarcated land prices, etc. As the core of land prices, they maintain the steady development of the market economy and promote the fair disclosure of market values. The Urban Real Estate Management Law of the People's Republic of China stipulates that benchmark land prices and demarcated land prices should be determined and announced regularly. As an important part of the public land price, these two results have a wide range of application scenarios in daily land valuation. The benchmark land price reflects the average land price in the region, focusing on the macro scale. The price level is significantly lower than the market price. Municipal and county departments in various places The benchmark land price must be comprehensively updated every three years; the calibrated land price reflects the market land price of a specific parcel, focusing on the micro scale, which is equivalent to or slightly lower than the market price level, and is more guiding for the market. The calibrated land price update cycle is One year. The land price system is complex and diverse. Although their respective scopes of use are generally clarified, there are still overlaps in application. The announcement of multiple types of land prices can also easily cause cognitive interference to the public and weaken the guiding effect of land price results on market participants. , there is an urgent need to integrate and optimize the current land price system. Therefore, it is necessary to build an information-based public land price management system to facilitate users to query land prices in various regions.

Contents of the invention

In view of the shortcomings in the existing technology, the present invention provides a natural resource public land price management system and method based on big data. By using big data technology, the public land price system construction achievement information data of each region is comprehensively obtained, and processed by big data. , extract relevant information about public land prices to form a unified template of public land price management data. Users only need to enter the information of the object to be valued to realize automatic valuation, quickly reflect the potential market value of the object to be valued, and provide important reference for users to make decisions.

In the first aspect, an embodiment of the present invention provides a natural resource publicity land price management system based on big data, including: a data crawling module, a big data processing module, a land price management module, an input information acquisition module, a query module and a calculation module;

The data crawling module is used to crawl the original data of public land price system construction achievement information published by relevant departments in various places on the Internet through a web crawler;

The big data processing module is used to perform data cleaning and screening processing on the original data to obtain processed data;

The land price management module is used to extract relevant information about public land prices from the processed data, and fill in the relevant information about public land prices into the public land price management form of a unified template;

The input information acquisition module is used to obtain the information of the object to be evaluated input by the user;

The query module is used to query the corresponding public land price information, calculation factors and correction coefficients from the public land price management table according to the information of the object to be estimated;

The calculation module is used to calculate the land price of the object to be valued based on the published land price information, calculation factors and correction coefficients.

In the second aspect, an embodiment of the present invention provides a natural resource public land price management method based on big data, including:

Use a web crawler to crawl the original data of information on public land price system construction achievements published by relevant departments in various places on the Internet;

Perform data cleaning and screening processing on the original data to obtain processed data;

Extract the information related to the public land price from the processed data, and fill in the relevant information about the public land price into the corresponding public land price management form;

Obtain the information of the object to be valued input by the user;

Query the corresponding public land price information, calculation factors and correction coefficients from the public land price management table according to the information of the object to be valued;

Calculate the land price of the object to be valued based on the published land price information, calculation factors and correction coefficients.

Beneficial effects of the present invention:

The embodiments of the present invention provide a natural resource public land price management system and method based on big data. The public land price system construction achievement information data of each region is comprehensively obtained by using big data technology, and through big data processing, the public land price related information is extracted. The publicized land price management data forms a unified template. Users only need to input the information of the object to be evaluated to realize automatic valuation, quickly reflect the potential market value of the object to be evaluated, and provide an important reference for users to make decisions.

Description of the drawings

In order to more clearly explain the specific embodiments of the present invention or the technical solutions in the prior art, the drawings that need to be used in the description of the specific implementations or the prior art will be briefly introduced below. Throughout the drawings, similar elements or portions are generally identified by similar reference numerals. In the drawings, elements or parts are not necessarily drawn to actual scale.

Figure 1 shows a structural block diagram of a natural resource public land price management system based on big data provided by the first embodiment of the present invention;

Figure 2 shows a flow chart of a big data-based natural resource public land price management method provided by another embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

It should be understood that, when used in this specification and the appended claims, the terms "comprises" and "comprises" indicate the presence of described features, integers, steps, operations, elements and/or components but do not exclude the presence of one or The presence or addition of multiple other features, integers, steps, operations, elements, components and/or collections thereof.

It should also be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly dictates otherwise.

It will be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "once" or "in response to determining" or "in response to detecting" depending on the context. . Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be interpreted, depending on the context, to mean "once determined" or "in response to a determination" or "once the [described condition or event] is detected ]" or "in response to detection of [the described condition or event]".

It should be noted that, unless otherwise stated, the technical terms or scientific terms used in this application should have the usual meanings understood by those skilled in the art to which this invention belongs.

As shown in Figure 1, a structural block diagram of a natural resource publicity land price management system based on big data provided by the first embodiment of the present invention is shown. The system includes: a data crawling module, a big data processing module, and a land price management system. module, input information acquisition module, query module and calculation module. Among them, the data crawling module is used to crawl the original data of the public land price system construction achievement information published by relevant departments in various places on the network through a web crawler; the big data processing module is used to Perform data cleaning and filtering processing on the original data to obtain processed data; the land price management module is used to extract relevant information about public land prices from the processed data, and fill in the relevant information about public land prices into the publicized land prices of the unified template. In the management form; the input information acquisition module is used to obtain the information of the object to be estimated input by the user; the query module is used to query the corresponding public land price information, calculation factors and correction coefficients from the public land price management table according to the information of the object to be valued; the calculation module is used to Calculate the land price of the object to be valued based on the published land price information, calculation factors and correction coefficients.

Since relevant departments in various places publish information on the construction results of the land price system, and the time for disclosing the information is inconsistent, a big data crawling module is set up in this application to crawl the original data of the information on the construction results of the land price system published on the Internet through a web crawler. , the original data includes: benchmark land price and calibrated land price. The main categories of benchmark land prices in various places are: ① Construction land prices include urban benchmark land prices, collective construction land benchmark land prices, and allocated construction land benchmark land prices; ② Agricultural land prices include state-owned agricultural land benchmark land prices and collective agricultural land benchmark land prices; ③ Other types include Benchmark land prices for underground space, benchmark land prices for new industrial land, etc. The big data processing module performs data cleaning and screening on the original data to obtain processed data. The land price management module extracts the required relevant public land price information from the processed data, and fills the extracted information into the public land price management form. The public land price management form in the embodiment of the present invention adopts a unified template. Use a unified template for all public land price information to build a unified benchmark land price for urban and rural areas. The user enters the information of the object to be valued in the search box. The object to be valued is a land parcel in a certain area. The information of the object to be valued includes the name, level, area, etc. of the land parcel. The query module queries the corresponding public land price information, calculation factors and correction coefficients from the public land price management table based on the information of the object to be estimated input by the user. The calculation module calculates the land price to be estimated based on the relationship between the public land price information, calculation factors and correction coefficients. The object's land price. Calculation factors include regional factors, floor area ratio factors, land development degree factors and remaining land use life factors.

The embodiment of the present invention provides a natural resource public land price management system based on big data. By using big data technology, the public land price system construction achievement information data of each region is comprehensively obtained, and through big data processing, the public land price related information is extracted to form a unified For the public land price management data of the template, users only need to enter the information of the object to be valued to realize automatic valuation, quickly reflect the potential market value of the object to be valued, and provide an important reference for users to make decisions.

In another embodiment of the present invention, the difference from the above-mentioned first embodiment is that the system also includes a map module. The map module displays maps of administrative regions in various places, and displays the calculated results on the regional map of the object to be evaluated. The land parcel price makes it easy for users to intuitively see the information and land parcel price through the map module.

In another embodiment of the present invention, the difference from the above-mentioned first embodiment is that the big data processing module of the system includes a data cleaning unit. The data cleaning unit is used to denoise and analyze the original data using text processing technology. and word segmentation to obtain text data, and use data mining technology to analyze the attributes of the text data to obtain clean data. The big data processing module also includes a data screening unit. The data screening unit is used to screen out the information published by relevant departments at the municipal and county levels from the cleaned data, and compare the land prices published by the county-level departments according to the connotation of the land prices published by the municipal departments. The connotations are unified and revised to obtain data with the same connotative elements of land prices. The land price management module includes an information extraction unit, which is used to extract information on the benchmark land price for construction land, the benchmark land price for agricultural land, and the calibrated land price from data with the same land price connotation elements, where the benchmark land price for construction land includes urban land prices. Benchmark land prices, collective construction land benchmark land prices and allocated construction land benchmark land prices. The agricultural land benchmark land prices include state-owned agricultural land benchmark land prices and collective agricultural land benchmark land prices.

The data cleaning process includes data preprocessing, feature selection, data cleaning and cleaning results. Data preprocessing refers to simple constraint processing of original data; feature selection refers to extracting data features and eliminating redundant information; data cleaning refers to cleaning dirty data according to actual application conditions; cleaning result inspection refers to cleaning standards based on Check data quality. Using Hadoop's distributed data cleaning method can effectively improve the efficiency of big data cleaning. Preliminary work for distributed data cleaning using Hadoop: divide the data into a storage layer and a cleaning computing layer. Use HDFS for data storage, use Hive data warehouse on HDFS to transfer data, and then process the database data according to the specified format to complete the preliminary preparations for data cleaning. The process of distributed data cleaning using Hadoop includes: (1) Data source loading: using Sqoop and Hive to load and dump the collected data. (2) Data preprocessing: Comprehensive analysis based on data requirements to ensure data availability during data analysis. (3) Feature selection: Select the main features that affect data quality, eliminate redundant features, and achieve dimensionality reduction processing of big data. (4) Identify abnormal data: The improved K-means algorithm is used. The larger the distance difference, the stronger the abnormality of the data, and the MapReduce method is used to achieve parallel computing. (5) Cleaning result inspection: Perform data quality inspection on the cleaned data to ensure data quality.

Specific methods to identify abnormal data:

From the training samples {x ₁ ,..., x _m }, x _i ∈R _n , k center points are randomly selected.

Step 1: Randomly select k samples from {x ₁ ,..., x _m } and record them as initial clustering centers μ ₁ , μ ₂ ,..., μ _k ∈R _n .

Step 2: Find the distance between other data and the center sample. The data samples are divided into categories according to the distance, as shown in Equation (1):

Step 3: For each class j, find the average value to determine the center point, as shown in Equation (2):

In the formula, each sample contains d attributes, and there are m data in the jth category. The sample x _i belongs to the jth category, and the Dth feature of the sample x _i belonging to the jth category is summed and then averaged, that is is the centroid of the Dth feature.

Step 4: If the objective function converges, terminate the program; otherwise, go to Step 2.

The specific steps of using the Canopy algorithm to optimize the K-means algorithm are as follows:

(1) The original data is stored in data set D.

(2) Randomly determine the center point, put it into canopy centerlist, and delete the data from D.

(3) Calculate the distance between other data and canopy centerlist. The samples of Dist[i]<T1 are regarded as one category, and the classified samples are deleted from D. According to this classification method, the remaining sample data are classified into T ₂ , T ₃ ,... until all the data in D are classified.

(4) After classification, k Canopy are obtained.

(5) Calculate k cluster center points.

(6) Calculate the distance between each data and the center point. Classify the data into the smallest class Dist[i].

(7) Use the average value of each category as the new center point.

(8) Then calculate the distance between the new center point and the Canopy center point, and classify according to step (3).

(9) If the convergence condition is reached, stop the cycle; otherwise, continue with steps (6) to (8).

When performing data cleaning, the Canopy algorithm is used to improve the K-means algorithm to clean abnormal data, and the MapReduce method for data with greater distance difference and stronger abnormality is used to implement parallel computing. After using the improved K-means algorithm to clean the data, it has higher accuracy and faster processing speed than the traditional K-means algorithm. When performing data screening and processing, Bayesian classification algorithm is used for screening, and the cleaned data is filtered again to improve the accuracy of data filtering.

The Bayesian classification algorithm uses the prior probability model of an object and uses the Bayesian formula to calculate its posterior probability; that is, to determine which category the object source belongs to, the class with the largest posterior probability is selected as the subject to which the object source belongs. Theme; by training the source data set, the probability of each data information in the small category is obtained through Bayesian theory, and a Bayesian model is constructed; Naive Bayes has the smallest error rate among the Bayesian classification models, and its There are few estimated parameters required, and the implementation algorithm is simple; the minimum risk Bayesian classification algorithm is based on Bayes and Naive Bayes to solve the error rate problem, and is optimization in the sense of minimum error rate.

This embodiment uses the minimum risk Bayesian algorithm to screen the cleaning data. The specific steps of screening include:

Given that P(ω _s ), P(X|ω _t ), s=1,2...,c and the X to be identified (data packet to be filtered), the posterior is calculated according to the Bayesian formula probability,

Among them, P(ω _s ) is the prior probability, which is obtained from the analysis of past users’ demand for network data; P(ω _t | , P(X|ω _s ) is the probability of judging whether the received X to be identified is spam network data based on the past user experience of network data demand;

Let the data loss be α, and define the decision-making rule as:

1) When the network data is junk data, judging it as junk data will not cause any loss, α = 0;

2) When junk network data is determined to be legitimate data, the loss α = 0;

3) When the network data required by users is judged to be junk data, the loss caused is immeasurable, 0<α<∞;

According to the calculated posterior probability and the set decision rules, the conditional risk of taking r _s , s = 1, 2,...a is calculated according to the following formula:

Taking into account the loss after the data is misjudged. α→0 is _reduced to the minimum, so the r conditional risk values R ₍ rs| decision making. The above big data processing method has higher filtering accuracy and system robustness, and can filter and process the cleaned sample data to obtain more accurate data.

The system of the embodiment of the present invention can obtain high-quality public land price data by setting up a big data processing module to clean and filter the crawled data. Due to the differences in land price systems in various places, for example: from the construction of the land price system in various places in a certain province, the benchmark land price of state-owned agricultural land is limited to the agricultural reclamation system, the value connotation is set to the transfer of use rights, and the maximum term is 50 years for each use. ; The benchmark land price for collective agricultural land is set as contracted management rights, and the maximum number of years is set in accordance with the Land Management Law, which is quite inconsistent with the state-owned benchmark land price; the benchmark land price for collective construction land is set (limited to rural collective housing) ) is an internal transfer of the village collective, which is quite different from state-owned residential land, and other commercial construction land also has certain differences in the setting of floor area ratio. The unification of connotation and form is the first step in building a unified land price system. In the embodiment of the present invention, the crawled data is processed through the big data processing module, the information published by relevant departments at the municipal and county levels is screened out from the cleaned data, and the county-level departments are evaluated according to the connotation of land prices published by the municipal departments. The published land price connotations are unified and revised to obtain data with the same land price connotation elements. The public land price management form adopts a unified template, and the connotative elements in the form are the same. Among them, the connotative elements include: right type, valuation date, etc. By unifying and revising the land price connotations of various prefecture-level cities in the province or districts and counties within the same prefecture-level city, a horizontally comparable and intuitive public land price system will be established to improve the applicability and practicality of the public land price system.

In another embodiment of the present invention, the difference from the above-mentioned first embodiment is that the system also includes a valuation comparison module. The valuation comparison module is used to compare the land price estimated based on the benchmark land price with the land price estimated based on the calibrated land price. Compare to get the comparison result, compare the comparison result with the set threshold. If it is less than the set threshold, two land prices will be displayed for the user's reference; if it is greater than the set threshold, two land prices will be displayed respectively, and the result of the large land price difference will be given. s reason. Through the valuation comparison module, users can intuitively and quickly obtain the difference in price of the object to be valued estimated based on the benchmark land price and the calibrated land price, as well as the reasons for the large differences. The system also includes an analysis module, which is used to analyze actual cases of public land price transfers and give selection suggestions to users. Through the set analysis module, users can make scientific choices with reference to the suggestions given.

In the above-mentioned first embodiment, a natural resource public land price management system based on big data is provided. Correspondingly, this application also provides a natural resource public land price management method based on big data. Please refer to Figure 2, which is a flow chart of a natural resource public land price management method based on big data provided by another embodiment of the present invention. Since the method embodiment is basically similar to the device embodiment, the description is relatively simple. For relevant details, please refer to the partial description of the device embodiment. The method embodiments described below are merely illustrative.

As shown in Figure 2, there is shown a flow chart of a big data-based natural resource public land price management method provided by another embodiment of the present invention. The method includes the following steps:

Use a web crawler to crawl the original data of information on public land price system construction achievements published by relevant departments in various places on the Internet;

Perform data cleaning and screening processing on the original data to obtain processed data;

Extract the information related to the public land price from the processed data, and fill in the relevant information about the public land price into the corresponding public land price management form;

Obtain the information of the object to be valued input by the user;

Query the corresponding public land price information, calculation factors and correction coefficients from the public land price management table according to the information of the object to be valued;

Calculate the land price of the object to be valued based on the published land price information, calculation factors and correction coefficients.

Through the above steps, the embodiment of the present invention provides a natural resource public land price management method based on big data. The big data technology is used to crawl the public land price system construction achievement information data of each region, and after big data processing, the public land price is extracted. Land price related information forms a unified template of public land price management data, and users can quickly query the automatic valuation of objects to be valued in the corresponding area for auxiliary reference.

In order to facilitate the user to intuitively see the information and the price of the queried land parcel through the map module, the method also includes: displaying a map of the administrative region of each place, and displaying the land parcel price on the regional map of the object to be evaluated.

Among them, the specific methods for data cleaning and screening of the original data include:

Perform denoising, parsing and word segmentation on the original data to obtain text data, and use data mining technology to analyze the attributes of the text data to obtain clean data;

The information released by relevant departments at the municipal and county levels were screened out from the cleaned data, and the land price connotations announced by the county-level departments were unified and corrected based on the land price connotations announced by the municipal departments to obtain data with the same land price connotation elements.

Specifically, the data cleaning process includes data preprocessing, feature selection, data cleaning and cleaning results. Data preprocessing refers to simple constraint processing of original data; feature selection refers to extracting data features and eliminating redundant information; data cleaning refers to cleaning dirty data according to actual application conditions; cleaning result inspection refers to cleaning standards based on Check data quality. Using Hadoop's distributed data cleaning method can effectively improve the efficiency of big data cleaning. When performing data cleaning, the Canopy algorithm is used to improve the K-means algorithm to clean abnormal data, and the MapReduce method for data with greater distance difference and stronger abnormality is used to implement parallel computing. After using the improved K-means algorithm to clean the data, it has higher accuracy and faster processing speed than the traditional K-means algorithm. When performing data screening and processing, Bayesian classification algorithm is used for screening, and the cleaned data is filtered again to improve the accuracy of data filtering. For the specific data processing process, please refer to the description of the above system. By unifying and revising the land price connotations of various prefecture-level cities in the province or districts and counties within the same prefecture-level city, a horizontally comparable and intuitive public land price system will be established to improve the applicability and practicality of the public land price system.

The specific method of extracting information related to public land prices from the processed data includes: extracting information on the benchmark land price for construction land, the benchmark land price for agricultural land, and the calibrated land price from data with the same land price connotation elements, wherein the benchmark land price for construction land is It includes urban benchmark land prices, collective construction land benchmark land prices and allocated construction land benchmark land prices. The agricultural land benchmark land prices include state-owned agricultural land benchmark land prices and collective agricultural land benchmark land prices.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention, but not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions described in the foregoing embodiments can still be modified, or some or all of the technical features can be equivalently replaced; and these modifications or substitutions do not deviate from the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention. scope, they should be covered by the claims and the scope of the description of the present invention.

Claims (10)

1. A natural resource public land price management system based on big data, characterized by including: a data crawling module, a big data processing module, a land price management module, an input information acquisition module, a query module and a calculation module; The data crawling module is used to crawl the original data of public land price system construction achievement information published by relevant departments in various places on the Internet through a web crawler; The big data processing module is used to perform data cleaning and screening processing on the original data to obtain processed data; The land price management module is used to extract relevant information about public land prices from the processed data, and fill in the relevant information about public land prices into the public land price management form of a unified template; The input information acquisition module is used to obtain the information of the object to be evaluated input by the user; The query module is used to query the corresponding public land price information, calculation factors and correction coefficients from the public land price management table according to the information of the object to be estimated; The calculation module is used to calculate the land price of the object to be valued based on the published land price information, calculation factors and correction coefficients. 2. The natural resource public land price management system based on big data according to claim 1, characterized in that it also includes a map module, the map module is used to display maps of administrative regions in various places, as well as regional maps of objects to be evaluated. The calculated land price is shown above. 3. The natural resource public land price management system based on big data according to claim 1, characterized in that the big data processing module includes a data cleaning unit, and the data cleaning unit is used to use text processing technology to perform processing on the original data. After denoising, parsing and word segmentation, text data is obtained, and data mining technology is used to analyze the attributes of the text data to obtain clean data. 4. The natural resource public land price management system based on big data according to claim 3, characterized in that the big data processing module further includes a data filtering unit, and the data filtering unit is used to filter out the clean data respectively. The information published by relevant departments at the municipal and county levels is unified and corrected based on the land price connotations published by the municipal departments, and the land price connotations published by the county-level departments are unified and revised to obtain data with the same land price connotation elements. 5. The natural resource publicity land price management system based on big data according to claim 4, characterized in that the land price management module includes an information extraction unit, and the information extraction unit is used to extract from data with the same land price connotation elements. Provide information on the benchmark land price for construction land, the benchmark land price for agricultural land, and the demarcated land price. The benchmark land price for construction land includes the benchmark land price for urban areas, the benchmark land price for collective construction land, and the benchmark land price for allocated construction land. The benchmark land price for agricultural land includes the benchmark land price for state-owned agricultural land. Base land price and collective agricultural land base price. 6. The natural resource publicity land price management system based on big data according to claim 1 or 5, characterized in that the calculation factors include regional factors, floor area ratio factors, land development degree factors and remaining land use life factors. 7. A natural resource public land price management method based on big data, which is characterized by including: Use a web crawler to crawl the original data of information on public land price system construction achievements published by relevant departments in various places on the Internet; Perform data cleaning and screening processing on the original data to obtain processed data; Extract the information related to the public land price from the processed data, and fill in the relevant information about the public land price into the corresponding public land price management form; Obtain the information of the object to be valued input by the user; Query the corresponding public land price information, calculation factors and correction coefficients from the public land price management table according to the information of the object to be valued; Calculate the land price of the object to be valued based on the published land price information, calculation factors and correction coefficients. 8. The natural resource public land price management method based on big data according to claim 7, characterized in that it also includes: displaying maps of administrative regions in various places, and displaying land parcel prices on the regional map of the object to be evaluated. 9. The natural resource public land price management method based on big data according to claim 7, characterized in that the specific method for data cleaning and screening of the original data includes: Perform denoising, parsing and word segmentation on the original data to obtain text data, and use data mining technology to analyze the attributes of the text data to obtain clean data; The information released by relevant departments at the municipal and county levels were screened out from the cleaned data, and the land price connotations announced by the county-level departments were unified and corrected based on the land price connotations announced by the municipal departments to obtain data with the same land price connotation elements. 10. The natural resource public land price management method based on big data according to claim 9, characterized in that the specific method of extracting the public land price related information from the processed data includes: extracting the data with the same connotation elements of the land price. Information on the benchmark land price for construction land, the benchmark land price for agricultural land, and the calibrated land price is extracted from The benchmark land price of state-owned agricultural land and the benchmark land price of collective agricultural land.