Batch statistical analysis method and system based on land acquisition cost data

Abstract

The invention belongs to the field of statistical analysis, and discloses a batch statistical analysis method and system based on land acquisition cost data, and the method comprises the steps: obtaining land acquisition data, carrying out the preprocessing of the land acquisition data, obtaining land acquisition standardized data, extracting land acquisition key features from the land acquisition standardized data through a statistical analysis method, and generating land acquisition feature data; utilizing a generative adversarial network model to perform feature enhancement on the land acquisition feature data to obtain enhanced land acquisition feature data, and constructing a multi-modal analysis model based on a space-time convolutional network model; and carrying out batch analysis on the enhanced land acquisition characteristic data by utilizing a multi-modal analysis model, outputting an influence factor analysis result of the land acquisition data, and carrying out encrypted storage after carrying out statistics on the influence factor analysis result and the land acquisition data. Through key feature extraction and feature enhancement, scientificity, accuracy and safety of land acquisition cost analysis are greatly improved, and resource optimization configuration and social harmonious development are promoted.

Description

Technical Field

[0001] The present invention relates to the field of statistical analysis, and in particular to a batch statistical analysis method and system based on land acquisition cost data. Background Art

[0002] Land acquisition costs refer to the economic compensation that needs to be paid for occupying collectively or individually owned land when carrying out public construction, urban development or other large-scale projects. It not only covers the market value of the land itself, but also includes compensation for the attachments on the ground. Reasonable calculation and payment of land acquisition costs are prerequisites for ensuring the smooth progress of the project. Therefore, it is necessary to conduct batch statistical analysis of land acquisition cost data to further improve the scientificity and accuracy of land acquisition costs. However, when conducting batch statistical analysis of land acquisition cost data, existing technologies usually rely on simple statistical methods, such as basic descriptive statistics such as mean and standard deviation, and linear regression models to evaluate the influencing factors of land acquisition costs. This method often ignores the complex patterns and spatiotemporal correlations in the data, resulting in incomplete and in-depth analysis results.

[0003] First, traditional analysis fails to fully consider the temporal and spatial dimensions of data, making it difficult to compare and analyze data from different sources under the same standards, reducing the consistency and explanatory power of the analysis. In addition, feature extraction is relatively simple, making it difficult to capture all key factors and their interrelationships, limiting the depth and breadth of the analysis. Moreover, due to limited data volume or sample bias, model training results are poor and generalization capabilities are weak. Finally, traditional analysis lacks measures for data security and privacy protection, posing a risk of data leakage. These shortcomings make it difficult for traditional methods to meet the needs of modern land acquisition cost analysis. Summary of the Invention

[0004] The embodiments of the present invention provide a batch statistical analysis method and system based on land acquisition fee data to solve the above technical problems in the prior art.

[0005] To provide a basic understanding of some aspects of the disclosed embodiments, the following is a brief summary. This summary is not intended to be an extensive review, identify key or critical elements, or delineate the scope of these embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the detailed description that follows.

[0006] According to a first aspect of an embodiment of the present invention, a batch statistical analysis method based on land acquisition fee data is provided.

[0007] In one embodiment, a batch statistical analysis method based on land acquisition cost data includes: Acquire land acquisition data, pre-process the land acquisition data to obtain standardized land acquisition data, and use statistical analysis methods to extract key land acquisition features from the standardized land acquisition data to generate land acquisition feature data; The generative adversarial network model is used to enhance the land acquisition feature data to obtain enhanced land acquisition feature data, and a multimodal analysis model is constructed based on the spatiotemporal convolutional network model; The multimodal analysis model is used to perform batch analysis on the enhanced land acquisition feature data, output the analysis results of the influencing factors of the land acquisition data, and implement encrypted storage after statistics are taken on the analysis results of the influencing factors and the land acquisition data.

[0008] In one embodiment, the acquiring of land acquisition data, preprocessing of the land acquisition data to obtain standardized land acquisition data, and extracting key land acquisition features from the standardized land acquisition data using statistical analysis to generate land acquisition feature data include: Acquire land acquisition data, perform missing value processing on the land acquisition data using a mean filling method, and perform filtering processing by outlier filtering to obtain filtered land acquisition data; the land acquisition data includes land acquisition cost data, land acquisition location data, land acquisition time data, land acquisition area data, land acquisition income data, and market data; Based on Z-score standardization, the filtered land acquisition data is formatted to obtain formatted land acquisition data, and the formatted land acquisition data is subjected to spatiotemporal alignment to obtain standardized land acquisition data; Using statistical analysis methods, we extract statistical characteristic data of land acquisition from standardized data, and obtain spatiotemporal correlation characteristic data based on the spatiotemporal Moran index. By calculating the net present value rate of land acquisition costs, we obtain the characteristic data of the net present value of land acquisition costs. The land acquisition statistical characteristic data, spatiotemporal correlation characteristic data and net present value characteristic data of land acquisition costs are integrated to obtain land acquisition characteristic data.

[0009] In one embodiment, performing spatiotemporal alignment processing on the formatted land acquisition data to obtain standardized land acquisition data includes: Convert the formatted land acquisition data into a unified timestamp format and adjust the unified time interval by interpolation to obtain time-aligned land acquisition data; The time-aligned land acquisition data were converted into a unified coordinate system and the unified spatial resolution was adjusted by resampling to obtain the standardized land acquisition data.

[0010] In one embodiment, the method of using a generative adversarial network model to enhance the land acquisition feature data to obtain enhanced land acquisition feature data, and constructing a multimodal analysis model based on a spatiotemporal convolutional network model includes: Design the generator and discriminator network structures, build a generative adversarial network model, train the generative adversarial network model based on land acquisition feature data, and use the trained generator to generate enhanced land acquisition feature data; Based on the enhanced land acquisition feature data, the spatiotemporal convolutional network model is trained to obtain the initial multimodal analysis model; The comprehensive loss function is used to optimize the parameters of the initial multimodal analysis model. The optimizer is used to update the parameters according to the parameter optimization results to obtain the multimodal analysis model.

[0011] In one embodiment, generating enhanced land acquisition feature data using a trained generator includes: The trained generator is used to generate new land acquisition feature data, and the Spearman correlation coefficient is used to evaluate the correlation between the new land acquisition data and the land acquisition data. Based on the correlation results, redundant features of the new land acquisition data are deleted to obtain optimized land acquisition data. According to the preset proportion, the optimized land acquisition data and the land acquisition data are mixed using the stratified sampling method to obtain mixed land acquisition feature data; The distribution consistency of mixed land acquisition feature data was verified by Kolmogorov-Smirnov test, and the mixing ratio was adjusted using Bayesian optimization based on the distribution consistency results; Based on the adjusted mixing ratio, the optimized land acquisition data were mixed with the land acquisition data using the stratified sampling method again to obtain the enhanced land acquisition feature data.

[0012] In one embodiment, the method of batch analyzing the enhanced land acquisition feature data using a multimodal analysis model, outputting an analysis result of factors influencing the land acquisition data, and performing encrypted storage after statistics of the analysis result of factors influencing the land acquisition data includes: Based on the multimodal analysis model, the enhanced land acquisition feature data is batch analyzed to obtain the influencing factors of land acquisition data; Calculate the correlation coefficient and significance level of each influencing factor using statistical test methods, and analyze the contribution of each influencing factor to land acquisition costs based on the correlation coefficient and significance level results to obtain the influencing factor analysis results; The influencing factor analysis results and land acquisition data are encrypted through encryption algorithms, and the encrypted data and encrypted keys are stored using communication protocols.

[0013] According to a second aspect of an embodiment of the present invention, a batch statistical analysis system based on land acquisition fee data is provided.

[0014] In one embodiment, the batch statistical analysis system based on land acquisition cost data includes: The land acquisition data acquisition module is used to acquire land acquisition data, pre-process the land acquisition data to obtain land acquisition standardized data, extract key land acquisition features from the land acquisition standardized data using statistical analysis methods, and generate land acquisition feature data; A multimodal analysis model construction module is used to enhance the land acquisition feature data using a generative adversarial network model to obtain enhanced land acquisition feature data, and to construct a multimodal analysis model based on a spatiotemporal convolutional network model; The batch analysis module is used to perform batch analysis on the enhanced land acquisition feature data using a multimodal analysis model, output the analysis results of the influencing factors of the land acquisition data, and implement encrypted storage after statistics on the analysis results of the influencing factors and the land acquisition data.

[0015] According to a third aspect of an embodiment of the present invention, a computer device is provided.

[0016] In some embodiments, the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0017] According to a fourth aspect of embodiments of the present invention, a computer-readable storage medium is provided.

[0018] In one embodiment, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0019] The technical solution provided by the embodiment of the present invention may have the following beneficial effects: 1. This invention processes missing values ​​and abnormal data through mean filling and outlier filtering, ensuring the quality and consistency of the original data and laying the foundation for subsequent precise analysis; and unifies the time and space dimensions of the data through spatiotemporal alignment technology, making the data more standardized and easy to analyze; at the same time, it extracts key features based on statistical methods and combines calculations such as the spatiotemporal Moran index and the net present value rate to generate comprehensive land acquisition feature data, which not only enhances the depth and breadth of data analysis, but also reveals potential spatial and temporal correlations, helping to identify the key factors affecting land acquisition costs and their changing patterns.

[0020] 2. The present invention performs feature enhancement through generative adversarial networks, further supplements data deficiencies or deviations, enriches the data set, improves the effect and robustness of model training, and provides richer and more reliable data support for building multimodal analysis models, so that multimodal analysis models can capture complex data patterns and provide efficient and accurate batch analysis capabilities. Finally, encryption algorithms are used to protect the security of analysis results and original data, ensuring the privacy and integrity of data during transmission and storage. After the above analysis steps, the scientificity, accuracy and security of land acquisition cost analysis are greatly improved, promoting the optimal allocation of resources and harmonious social development.

[0021] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0023] Figure 1 This is a flow chart showing a batch statistical analysis method based on land acquisition fee data according to an exemplary embodiment; Figure 2 This is a structural diagram of a batch statistical analysis system based on land acquisition fee data according to an exemplary embodiment; Figure 3 The figure is a schematic diagram showing the structure of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0024] The following description and accompanying drawings sufficiently illustrate the specific embodiments herein to enable those skilled in the art to practice them. Portions and features of some embodiments may be included in or substituted for portions and features of other embodiments. The scope of the embodiments herein includes the entire scope of the claims, including all available equivalents thereof. Herein, the terms "first," "second," and the like are used solely to distinguish one element from another and do not require or imply any actual relationship or order between these elements. In practice, the first element can also be referred to as the second element, and vice versa. Furthermore, the terms "comprise," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a structure, device, or apparatus comprising a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such structure, device, or apparatus. Without further limitation, an element defined by the phrase "comprising a..." does not preclude the presence of other identical elements in the structure, device, or apparatus comprising the element. The various embodiments herein are described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. Similar or identical parts between the various embodiments can be referenced to each other.

[0025] The terms "longitudinal", "transverse", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like used herein to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are intended only to facilitate the description of this document and simplify the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the present invention. In the description herein, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, they can be mechanical or electrical connections, or they can be internal connections between two elements, they can be directly connected, or they can be indirectly connected through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms can be understood according to the specific circumstances.

[0026] As used herein, unless otherwise specified, the term "plurality" means two or more.

[0027] In this document, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0028] In this article, the term "and / or" is used to describe the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0029] It should be understood that, although the various steps in the flowchart are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps may be performed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily performed at the same time, but may be performed at different times. The execution order of these sub-steps or stages is not necessarily to be performed in sequence, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0030] Each module in the device or system of the present application can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software so that the processor can call and execute the operations corresponding to the above modules.

[0031] In the absence of conflict, the embodiments of the present invention and the features thereof may be combined with each other.

[0032] Figure 1 An embodiment of a batch statistical analysis method based on land acquisition fee data of the present invention is shown.

[0033] In this optional embodiment, the batch statistical analysis method based on land acquisition cost data includes: Step S101: acquiring land acquisition data, preprocessing the land acquisition data to obtain standardized land acquisition data, and extracting key land acquisition features from the standardized land acquisition data using statistical analysis to generate land acquisition feature data; Step S102: using a generative adversarial network model to enhance the land acquisition feature data to obtain enhanced land acquisition feature data, and constructing a multimodal analysis model based on a spatiotemporal convolutional network model; Step S103 , batch analysis is performed on the enhanced land acquisition feature data using a multimodal analysis model, and analysis results of factors influencing the land acquisition data are output. The analysis results of factors influencing the land acquisition data are statistically analyzed and encrypted and stored.

[0034] In this optional embodiment, the steps of acquiring land acquisition data, preprocessing the land acquisition data to obtain standardized land acquisition data, and extracting key land acquisition features from the standardized land acquisition data using statistical analysis to generate land acquisition feature data include: Acquire land acquisition data, perform missing value processing on the land acquisition data using a mean filling method, and perform filtering processing by outlier filtering to obtain filtered land acquisition data; the land acquisition data includes land acquisition cost data, land acquisition location data, land acquisition time data, land acquisition area data, land acquisition income data, and market data; Based on Z-score standardization, the filtered land acquisition data is formatted to obtain formatted land acquisition data, and the formatted land acquisition data is subjected to spatiotemporal alignment to obtain standardized land acquisition data; Using statistical analysis methods, we extract statistical characteristic data of land acquisition from standardized data, and obtain spatiotemporal correlation characteristic data based on the spatiotemporal Moran index. By calculating the net present value rate of land acquisition costs, we obtain the characteristic data of the net present value of land acquisition costs. The land acquisition statistical characteristic data, spatiotemporal correlation characteristic data and net present value characteristic data of land acquisition costs are integrated to obtain land acquisition characteristic data.

[0035] In this optional embodiment, performing spatiotemporal alignment processing on the formatted land acquisition data to obtain standardized land acquisition data includes: Convert the formatted land acquisition data into a unified timestamp format and adjust the unified time interval by interpolation to obtain time-aligned land acquisition data; The time-aligned land acquisition data were converted into a unified coordinate system and the unified spatial resolution was adjusted by resampling to obtain the standardized land acquisition data.

[0036] In this optional embodiment, the statistical analysis method is used to extract land acquisition statistical feature data from the standardized land acquisition data, and the spatiotemporal correlation feature data is obtained based on the spatiotemporal Moran index. The net present value rate of land acquisition costs is calculated to obtain the net present value feature data of land acquisition costs, which includes: Statistical analysis method is used to calculate the mean and standard deviation of the standardized data of land acquisition to obtain the statistical characteristic data of land acquisition; Based on the spatiotemporal Moran index, the spatiotemporal correlation characteristic data were calculated in combination with the standardized land acquisition data; The calculation formula of the spatiotemporal correlation feature data is: ; Where, I ST represents the spatiotemporal correlation feature data; t represents the tth land acquisition location; s represents the sth land acquisition location; N represents the total number of land acquisitions; w ts Represents the elements in the spatiotemporal weight matrix; X t represents the standardized land acquisition cost of the tth acquisition location; X s represents the standardized land acquisition cost of the sth acquisition location; represents the average land acquisition cost; Calculate the net present value rate of land acquisition costs based on standardized land acquisition data to obtain the characteristic data of the net present value of land acquisition costs; The calculation formula for the characteristic data of the net present value of land acquisition costs is: ; Where, R represents the characteristic data of the net present value of land acquisition costs; i represents the number of years of land acquisition; n represents the total number of years of land acquisition; I i represents the land acquisition revenue in year i; E i represents the land acquisition expenditure in year i; r represents the market discount rate; S0 represents the standardized land acquisition cost data.

[0037] In this optional embodiment, the method of using a generative adversarial network model to enhance the land acquisition feature data to obtain enhanced land acquisition feature data, and constructing a multimodal analysis model based on a spatiotemporal convolutional network model includes: Design the generator and discriminator network structures, build a generative adversarial network model, train the generative adversarial network model based on land acquisition feature data, and use the trained generator to generate enhanced land acquisition feature data; Based on the enhanced land acquisition feature data, the spatiotemporal convolutional network model is trained to obtain the initial multimodal analysis model; The comprehensive loss function is used to optimize the parameters of the initial multimodal analysis model. The optimizer is used to update the parameters according to the parameter optimization results to obtain the multimodal analysis model.

[0038] In this optional embodiment, generating enhanced land acquisition feature data using the trained generator includes: The trained generator is used to generate new land acquisition feature data, and the Spearman correlation coefficient is used to evaluate the correlation between the new land acquisition data and the land acquisition data. Based on the correlation results, redundant features of the new land acquisition data are deleted to obtain optimized land acquisition data. According to the preset proportion, the optimized land acquisition data and the land acquisition data are mixed using the stratified sampling method to obtain mixed land acquisition feature data; The distribution consistency of mixed land acquisition feature data was verified by Kolmogorov-Smirnov test, and the mixing ratio was adjusted using Bayesian optimization based on the distribution consistency results; Based on the adjusted mixing ratio, the optimized land acquisition data were mixed with the land acquisition data using the stratified sampling method again to obtain the enhanced land acquisition feature data.

[0039] In this optional embodiment, the method of optimizing the parameters of the initial multimodal analysis model using a comprehensive loss function and updating the parameters using an optimizer according to the parameter optimization results to obtain the multimodal analysis model includes: Based on the classification loss function, regression loss function and regularization loss function, the comprehensive loss function is calculated using the linear weighted method; The comprehensive loss function is used to calculate the comprehensive loss value of the initial multimodal analysis model, and the adaptive learning rate optimizer is used to calculate the parameter gradient; According to the parameter gradient, the parameters of the initial multimodal analysis model are updated through the back propagation algorithm to obtain the multimodal analysis model.

[0040] In this optional embodiment, the method of batch analyzing the enhanced land acquisition feature data using a multimodal analysis model, outputting an analysis result of factors affecting the land acquisition data, and performing encrypted storage after statistics of the analysis result of factors affecting the land acquisition data include: Based on the multimodal analysis model, the enhanced land acquisition feature data is batch analyzed to obtain the influencing factors of land acquisition data; Calculate the correlation coefficient and significance level of each influencing factor using statistical test methods, and analyze the contribution of each influencing factor to land acquisition costs based on the correlation coefficient and significance level results to obtain the influencing factor analysis results; The influencing factor analysis results and land acquisition data are encrypted through encryption algorithms, and the encrypted data and encrypted keys are stored using communication protocols.

[0041] In this optional embodiment, encrypting the influencing factor analysis results and the land acquisition data using an encryption algorithm includes: The influencing factor analysis results and land acquisition data are encrypted using the Advanced Encryption Standard to obtain encrypted data and an Advanced Encryption Standard key, and the Advanced Encryption Standard key is encrypted based on an asymmetric encryption algorithm to obtain an encrypted key.

[0042] Figure 2 An embodiment of a batch statistical analysis system based on land acquisition fee data of the present invention is shown.

[0043] In this optional embodiment, the batch statistical analysis system based on land acquisition fee data includes: The land acquisition data acquisition module 201 is used to acquire land acquisition data, pre-process the land acquisition data to obtain land acquisition standardized data, extract key land acquisition features from the land acquisition standardized data using statistical analysis methods, and generate land acquisition feature data; A multimodal analysis model construction module 202 is used to enhance the land acquisition feature data using a generative adversarial network model to obtain enhanced land acquisition feature data, and to construct a multimodal analysis model based on a spatiotemporal convolutional network model; The batch analysis module 203 is used to perform batch analysis on the enhanced land acquisition feature data using a multimodal analysis model, output analysis results of factors affecting the land acquisition data, and perform encrypted storage after statistics on the analysis results of factors affecting the land acquisition data.

[0044] It should be noted that the land acquisition time data refers to the time of land acquisition; the land acquisition income data refers to the income obtained from public construction, urban development or other large-scale projects after land acquisition; and the market situation data refers to the price of local land acquisition fees and the local economic output value.

[0045] It should be noted that the outliers in the land acquisition data are filtered out, specifically by using visual tools such as box plots or scatter plots to visually detect outliers and then deleting the detected outliers.

[0046] It should be noted that the Kolmogorov-Smirnov test is a non-parametric test used to compare whether two independent samples come from the same distribution. The land acquisition data and the mixed land acquisition feature data are marked as data set A and data set B respectively. The Kolmogorov-Smirnov test is performed on the two data sets. The test will calculate the maximum difference between the empirical distribution functions of the two data sets and give a statistic. At the same time, a significance level is selected and a critical value is determined based on the level. If the calculated statistic is greater than the critical value, the null hypothesis is rejected, that is, the distributions of the two data sets are considered inconsistent; if it is less than or equal to the critical value, the null hypothesis cannot be rejected, that is, the distributions of the two data sets are considered consistent.

[0047] If the distributions of the two data sets are inconsistent, the mixing ratio is adjusted using Bayesian optimization. An objective function is set that evaluates the distribution consistency of the data under a given mixing ratio. The Bayesian algorithm finds the minimum value of the objective function by systematically exploring the parameter space. The optimal mixing ratio found is applied to the data mixing process to generate the final enhanced land acquisition feature dataset.

[0048] It should be noted that the Pearson correlation coefficient is used to calculate the linear correlation between each influencing factor and the land acquisition cost, and each correlation coefficient is tested for significance. The p-value test is usually used to determine the significance level (such as α=0.05 or 0.01) to determine whether the correlation coefficient is statistically significant. According to the size and direction of the correlation coefficient (positive correlation or negative correlation), the contribution of each influencing factor to the land acquisition cost is analyzed, the factors that have a significant impact on the land acquisition cost are identified, and the intensity of their impact is evaluated; if a factor is positively correlated with the land acquisition cost, then an increase in this factor will generally lead to an increase in the land acquisition cost; that is, the closer the correlation coefficient is to 1, the stronger the impact of the increase in land acquisition costs; if another factor is negatively correlated with the land acquisition cost, then an increase in this factor will generally lead to a decrease in the land acquisition cost; that is, the closer the correlation coefficient is to -1, the stronger the impact of the reduction in land acquisition costs.

[0049] It should be noted that the encrypted data and encrypted keys are transmitted to the target database through the established transport layer security communication protocol. During the entire transmission process, all data is protected by the encryption provided by the communication protocol to prevent third parties from eavesdropping or tampering with the data. The transport layer security communication protocol also provides a message integrity check mechanism to ensure that the data has not been tampered with. At the same time, the target database is set with strict access rights to ensure that only authorized users can access the encrypted data and keys, and all operations on the database are logged to facilitate tracking of potential security threats or illegal operations. In order to further enhance security, a dedicated hardware security module is used to manage and protect encryption keys to effectively resist attacks.

[0050] Among them, for the encrypted data storage, the land acquisition data and the corresponding influencing factor analysis results need to be stored accordingly, so that the corresponding analysis results can be clearly queried to provide a reference basis for future land acquisition costs.

[0051] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the steps of the above-mentioned method embodiment are implemented.

[0052] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0053] In addition, the present invention also provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiment when executing the computer program.

[0054] In addition, the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0055] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware using a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes in the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0056] The present invention is not limited to the structures described above and shown in the drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A batch statistical analysis method based on land acquisition cost data, characterized in that: The batch statistical analysis method based on land acquisition cost data includes: Acquire land acquisition data, pre-process the data to obtain standardized data, extract key features of land acquisition from the standardized data using statistical analysis methods, and generate land acquisition feature data; including: Using statistical analysis methods, we extract statistical characteristic data of land acquisition from standardized data, and obtain spatiotemporal correlation characteristic data based on the spatiotemporal Moran index. By calculating the net present value rate of land acquisition costs, we obtain the characteristic data of the net present value of land acquisition costs. Performing feature integration on land acquisition statistical feature data, spatiotemporal correlation feature data and net present value feature data of land acquisition costs to obtain land acquisition feature data; The generative adversarial network model is used to enhance the land acquisition feature data to obtain enhanced land acquisition feature data, and a multimodal analysis model is constructed based on the spatiotemporal convolutional network model; The multimodal analysis model is used to perform batch analysis on the enhanced land acquisition feature data, output the analysis results of the influencing factors of the land acquisition data, and implement encrypted storage after statistics are taken on the analysis results of the influencing factors and the land acquisition data.

2. The batch statistical analysis method based on land acquisition cost data according to claim 1 is characterized in that: The acquiring of land acquisition data, preprocessing of the land acquisition data to obtain standardized land acquisition data, and extracting key features of land acquisition from the standardized land acquisition data using statistical analysis to generate land acquisition feature data further includes: Acquire land acquisition data, perform missing value processing on the land acquisition data using a mean filling method, and perform filtering processing by outlier filtering to obtain filtered land acquisition data; the land acquisition data includes land acquisition cost data, land acquisition location data, land acquisition time data, land acquisition area data, land acquisition income data, and market data; Based on Z-score standardization, the filtered land acquisition data is formatted to obtain formatted land acquisition data, and the formatted land acquisition data is subjected to spatiotemporal alignment to obtain standardized land acquisition data.

3. The batch statistical analysis method based on land acquisition cost data according to claim 2 is characterized in that: The step of performing spatiotemporal alignment processing on the formatted land acquisition data to obtain standardized land acquisition data includes: Convert the formatted land acquisition data into a unified timestamp format and adjust the unified time interval by interpolation to obtain time-aligned land acquisition data; The time-aligned land acquisition data were converted into a unified coordinate system and the unified spatial resolution was adjusted by resampling to obtain the standardized land acquisition data.

4. The batch statistical analysis method based on land acquisition cost data according to claim 1 is characterized in that: The statistical analysis method is used to extract land acquisition statistical characteristic data from the standardized land acquisition data, and the spatiotemporal correlation characteristic data is obtained based on the spatiotemporal Moran index. The net present value characteristic data of land acquisition costs is obtained by calculating the net present value rate of land acquisition costs, including: Statistical analysis method is used to calculate the mean and standard deviation of the standardized data of land acquisition to obtain the statistical characteristic data of land acquisition; Based on the spatiotemporal Moran index, the spatiotemporal correlation characteristic data were calculated in combination with the standardized land acquisition data; The calculation formula of the spatiotemporal correlation feature data is: ； Where, I ST represents the spatiotemporal correlation feature data; t represents the tth land acquisition location; s represents the sth land acquisition location; N represents the total number of land acquisitions; w ts Represents the elements in the spatiotemporal weight matrix; X t represents the standardized land acquisition cost of the tth acquisition location; X s represents the standardized land acquisition cost of the sth acquisition location; represents the average land acquisition cost; Calculate the net present value rate of land acquisition costs based on standardized land acquisition data to obtain the characteristic data of the net present value of land acquisition costs; The calculation formula for the characteristic data of the net present value of land acquisition costs is: ； Where, R represents the characteristic data of the net present value of land acquisition costs; i represents the number of years of land acquisition; n represents the total number of years of land acquisition; I i represents the land acquisition revenue in year i; E i represents the land acquisition expenditure in year i; r represents the market discount rate; S0 represents the standardized land acquisition cost data.

5. The batch statistical analysis method based on land acquisition cost data according to claim 1 is characterized in that: The method of utilizing a generative adversarial network model to enhance the land acquisition feature data to obtain enhanced land acquisition feature data, and constructing a multimodal analysis model based on a spatiotemporal convolutional network model includes: Design the generator and discriminator network structures, build a generative adversarial network model, train the generative adversarial network model based on land acquisition feature data, and use the trained generator to generate enhanced land acquisition feature data; Based on the enhanced land acquisition feature data, the spatiotemporal convolutional network model is trained to obtain the initial multimodal analysis model; The comprehensive loss function is used to optimize the parameters of the initial multimodal analysis model. The optimizer is used to update the parameters according to the parameter optimization results to obtain the multimodal analysis model.

6. The batch statistical analysis method based on land acquisition cost data according to claim 5 is characterized in that: The method of using the trained generator to generate enhanced land acquisition feature data includes: The trained generator is used to generate new land acquisition feature data, and the Spearman correlation coefficient is used to evaluate the correlation between the new land acquisition data and the land acquisition data. Based on the correlation results, redundant features of the new land acquisition data are deleted to obtain optimized land acquisition data. According to the preset proportion, the optimized land acquisition data and the land acquisition data are mixed using the stratified sampling method to obtain mixed land acquisition feature data; The distribution consistency of mixed land acquisition feature data was verified by Kolmogorov-Smirnov test, and the mixing ratio was adjusted using Bayesian optimization based on the distribution consistency results; Based on the adjusted mixing ratio, the optimized land acquisition data were mixed with the land acquisition data using the stratified sampling method again to obtain the enhanced land acquisition feature data.

7. The batch statistical analysis method based on land acquisition cost data according to claim 5 is characterized in that: The method of optimizing the parameters of the initial multimodal analysis model using the comprehensive loss function and updating the parameters using the optimizer according to the parameter optimization results to obtain the multimodal analysis model includes: Based on the classification loss function, regression loss function and regularization loss function, the comprehensive loss function is calculated using the linear weighted method; The comprehensive loss function is used to calculate the comprehensive loss value of the initial multimodal analysis model, and the adaptive learning rate optimizer is used to calculate the parameter gradient; According to the parameter gradient, the parameters of the initial multimodal analysis model are updated through the back propagation algorithm to obtain the multimodal analysis model.

8. The batch statistical analysis method based on land acquisition cost data according to claim 1 is characterized in that: The method of using a multimodal analysis model to batch analyze the enhanced land acquisition feature data, outputting the analysis results of factors affecting the land acquisition data, and performing encrypted storage after statistics of the analysis results of factors affecting the land acquisition data include: Based on the multimodal analysis model, the enhanced land acquisition feature data is batch analyzed to obtain the influencing factors of land acquisition data; Calculate the correlation coefficient and significance level of each influencing factor using statistical test methods, and analyze the contribution of each influencing factor to land acquisition costs based on the correlation coefficient and significance level results to obtain the influencing factor analysis results; The influencing factor analysis results and land acquisition data are encrypted through encryption algorithms, and the encrypted data and encrypted keys are stored using communication protocols.

9. The batch statistical analysis method based on land acquisition cost data according to claim 8 is characterized in that: The encryption processing of the influencing factor analysis results and land acquisition data by using an encryption algorithm includes: The influencing factor analysis results and land acquisition data are encrypted using the Advanced Encryption Standard to obtain encrypted data and an Advanced Encryption Standard key, and the Advanced Encryption Standard key is encrypted based on an asymmetric encryption algorithm to obtain an encrypted key.

10. A batch statistical analysis system based on land acquisition cost data, characterized in that: The batch statistical analysis system based on land acquisition cost data includes: The land acquisition data acquisition module is used to acquire land acquisition data, pre-process the land acquisition data to obtain land acquisition standardized data, extract key land acquisition features from the land acquisition standardized data using statistical analysis methods, and generate land acquisition feature data; A multimodal analysis model construction module is used to enhance the land acquisition feature data using a generative adversarial network model to obtain enhanced land acquisition feature data, and to construct a multimodal analysis model based on a spatiotemporal convolutional network model; The batch analysis module is used to perform batch analysis on the enhanced land acquisition feature data using a multimodal analysis model, output the analysis results of the influencing factors of the land acquisition data, and implement encrypted storage after statistics on the analysis results of the influencing factors and the land acquisition data.

Images