Engineering cost data analysis method and system

Abstract

The invention relates to a project cost data analysis method and system. The method comprises the steps of obtaining a plurality of historical project cost data samples; training the plurality of initial network models according to engineering materials, construction processes, engineering costs and cost analysis information of the historical engineering cost data samples of the plurality of engineering categories to obtain cost data analysis models corresponding to the various engineering categories; according to the engineering geological information and the building height of the target engineering cost data, performing clustering analysis on the target engineering cost data to obtain a target engineering category; determining a cost data analysis model corresponding to the target project category as a target model; and inputting the engineering material, the construction process and the engineering cost of the target engineering cost data into the target model, and obtaining a target engineering cost analysis result output by the target model, so that the efficiency and the accuracy of obtaining the engineering cost data analysis can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of engineering cost analysis, and particularly to an analysis method and system for engineering cost data. Background Art

[0002] A construction project refers to an engineering entity formed by the construction of various building structures and their ancillary facilities, as well as the installation of associated pipelines and equipment. For different locations and construction requirements, there are differences in construction techniques, engineering materials, and construction costs due to different engineering geological conditions and building heights. Among them, the engineering cost data of construction projects often requires extremely large amounts of funds, and users need to carefully analyze to determine whether the engineering cost data is reasonable and what its advantages and disadvantages are. However, due to the large amount of data involved in engineering cost data, simply analyzing the engineering cost data manually has technical defects of low efficiency and low accuracy. Summary of the Invention

[0003] Based on this, the purpose of the present application is to provide an analysis method and system for engineering cost data, which can overcome the deficiencies of the prior art.

[0004] To achieve the above purpose, the technical solution adopted in the present application is as follows:

[0005] An analysis method for engineering cost data, comprising:

[0006] Obtaining a plurality of historical engineering cost data samples, each of the historical engineering cost data samples being labeled with engineering geological information, building height, engineering materials, construction techniques, engineering cost, and cost analysis results; the cost analysis results include the analysis content of the engineering materials and construction techniques based on the engineering cost;

[0007] Performing clustering analysis on the plurality of historical engineering cost data samples according to the engineering geological information and the building height to obtain several engineering categories;

[0008] Training a plurality of initial network models according to the engineering materials, construction techniques, engineering cost, and cost analysis information of the historical engineering cost data samples of the several engineering categories to obtain cost data analysis models corresponding to each engineering category;

[0009] Performing clustering analysis on the target engineering cost data according to the engineering geological information and the building height of the target engineering cost data to obtain a target engineering category;

[0010] Determining the cost data analysis model corresponding to the target engineering category as the target model;

[0011] Input the engineering materials, construction techniques, and project cost of the target project cost data into the target model to obtain the target project cost analysis result output by the target model.

[0012] As an embodiment, the step of performing clustering analysis on the multiple historical project cost data samples according to the engineering geological information and the building height to obtain several project categories includes:

[0013] According to the engineering geological information and the building height, map the multiple historical project cost data samples to a pre-constructed clustering coordinate system as data points to obtain a clustering coordinate map including multiple data points; the engineering geological information corresponds to the first coordinate axis parameter of the coordinate system, and the building height corresponds to the second coordinate axis parameter of the coordinate system;

[0014] Obtain several category data clusters according to the distribution density of the data points in the clustering coordinate map;

[0015] Obtain the several project categories according to the several category data clusters.

[0016] As an embodiment, the step of obtaining several category data clusters according to the distribution density of the data points in the clustering coordinate map includes:

[0017] Obtain several initial data clusters according to the distribution density of the data points in the clustering coordinate map;

[0018] Obtain the central data point with the smallest average distance according to the average distance between each data point and other data points in the initial data clusters;

[0019] Construct the category data cluster corresponding to the central data point according to a preset radius value.

[0020] As an embodiment, the step of performing clustering analysis on the target project cost data according to the engineering geological information and the building height of the target project cost data to obtain the target project category includes:

[0021] Map the target project cost data to the clustering coordinate map according to the engineering geological information and the building height of the target project cost data;

[0022] Obtain the target project category according to the category data cluster where the target project cost data is located in the clustering coordinate map.

[0023] As an embodiment, the step of training multiple initial network models according to the engineering materials, construction techniques, project cost, and cost analysis information of the historical project cost data samples of the several project categories to obtain cost data analysis models corresponding to each project category includes:

[0024] Taking the engineering materials, construction techniques, and project costs of the historical project cost data samples of each of the said engineering categories as training inputs, and taking the said cost analysis information as training outputs, train each of the said initial network models to obtain cost data analysis models corresponding to each of the said engineering categories.

[0025] The second embodiment of the present application provides an analysis system for project cost data, including:

[0026] A sample acquisition module, configured to acquire a plurality of historical project cost data samples, each of the said historical project cost data samples being labeled with engineering geological information, building height, engineering materials, construction techniques, project cost, and cost analysis results; the said cost analysis results include analysis content of the said engineering materials and construction techniques based on the said project cost;

[0027] A sample analysis module, configured to perform cluster analysis on the plurality of historical project cost data samples according to the said engineering geological information and the said building height to obtain several engineering categories;

[0028] A model training module, configured to train a plurality of initial network models according to the engineering materials, construction techniques, project cost, and cost analysis information of the historical project cost data samples of the said several engineering categories to obtain cost data analysis models corresponding to each engineering category;

[0029] A cluster analysis module, configured to perform cluster analysis on target project cost data according to the engineering geological information and building height of the target project cost data to obtain a target engineering category;

[0030] A target model acquisition module, configured to determine the cost data analysis model corresponding to the said target engineering category as the target model;

[0031] A project cost analysis module, configured to input the engineering materials, construction techniques, and project cost of the said target project cost data into the said target model to obtain a target project cost analysis result output by the said target model.

[0032] As an embodiment, the said sample analysis module includes:

[0033] A cluster coordinate graph acquisition sub-module, configured to map the plurality of historical project cost data samples to a pre-constructed cluster coordinate system as data points according to the said engineering geological information and the said building height to obtain a cluster coordinate graph including a plurality of data points; the said engineering geological information corresponds to the first coordinate axis parameter of the coordinate system, and the said building height corresponds to the second coordinate axis parameter of the coordinate system;

[0034] A category data cluster acquisition sub-module, configured to obtain a plurality of category data clusters according to the distribution density of data points in the clustering coordinate map;

[0035] A project category acquisition sub-module, configured to obtain the plurality of project categories according to the plurality of category data clusters.

[0036] As an embodiment, the category data cluster acquisition sub-module includes:

[0037] An initial data cluster acquisition unit, configured to obtain a plurality of initial data clusters according to the distribution density of data points in the clustering coordinate map;

[0038] A central data point acquisition unit, configured to obtain a central data point with the smallest average distance according to the average distance between each data point and other data points in the initial data cluster;

[0039] A category data cluster acquisition unit, configured to construct a category data cluster corresponding to the central data point according to a preset radius value.

[0040] As an embodiment, the steps of the clustering analysis module include:

[0041] A mapping sub-module, configured to map the target project cost data to the clustering coordinate map according to the engineering geology information and building height of the target project cost data;

[0042] A target project category acquisition sub-module, configured to obtain the target project category according to the category data cluster where the target project cost data is located in the clustering coordinate map.

[0043] As an embodiment, the model training module is configured to: use the engineering materials, construction techniques, and project costs of the historical project cost data samples of each project category as training inputs, and use the cost analysis information as training outputs to train each initial network model to obtain a cost data analysis model corresponding to each project category.

[0044] Compared with the traditional technology, the beneficial effects of this application are:

[0045] After clustering and analyzing multiple historical project cost data samples according to engineering geological information and building height, this application obtains several project categories. Then, based on the engineering materials, construction techniques, project costs, and cost analysis information of the historical project cost data samples of the project categories, the initial network model is trained to obtain a cost data analysis model corresponding to each project category. After clustering and analyzing the target project cost data according to the engineering geological information and building height, the target project category corresponding to the target project cost data is obtained, and the cost data analysis model corresponding to the target project category is determined as the target model. Then, the engineering materials, construction techniques, and project costs of the target project cost data are input into the target model, and an accurate target project cost analysis result can be quickly obtained, achieving the effect of improving the efficiency and accuracy of obtaining project cost data analysis.

[0046] For better understanding and implementation, the present application will be described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flowchart of an analysis method for project cost data according to an embodiment of the present application;

[0048] Figure 2 It is a schematic diagram of module connections of an analysis system for project cost data according to an embodiment of the present application;

[0049] 10. Analysis system for project cost data; 11. Sample acquisition module; 12. Sample analysis module; 13. Model training module; 14. Clustering analysis module; 15. Target model acquisition module; 16. Project cost analysis module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] To make the objectives, technical solutions, and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0051] It should be clear that the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts fall within the scope of protection of the embodiments of the present application.

[0052] When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. In the description of the present application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and do not have to be used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances. In the present application and the appended claims, the singular forms "a", "the", and "said" are also intended to include the plural forms unless the context clearly indicates otherwise. The words "if" / "when" used herein can be interpreted as "when...", "when...", or "in response to a determination".

[0053] In addition, in the description of the present application, unless otherwise specified, "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0054] Please refer to Figure 1 , which is a flowchart of the analysis method of engineering cost data in the first embodiment of the present application. The method includes:

[0055] S1: Obtain a plurality of historical engineering cost data samples, and each of the historical engineering cost data samples is labeled with engineering geological information, building height, engineering materials, construction technology, engineering cost, and cost analysis results; the cost analysis results include the analysis content of the engineering materials and construction technology based on the engineering cost.

[0056] Among them, engineering materials, construction technology, and engineering cost refer to the materials, technologies, and costs corresponding to each project of the project. The cost analysis result is the content of cost analysis of its own building engineers and the engineering geological information, building height, engineering materials, construction technology, and engineering cost of historical engineering cost data, which may include the performance - price ratio score and advantages and disadvantages analysis of all items of historical engineering cost data, the performance - price ratio score and advantages and disadvantages analysis of the engineering materials of each item, and the performance - price ratio score and advantages and disadvantages analysis of the construction technology of each item.

[0057] S2: Perform clustering analysis on the plurality of historical engineering cost data samples according to the engineering geological information and the building height to obtain several engineering categories.

[0058] S3: Train multiple initial network models based on the engineering materials, construction techniques, project costs, and cost analysis information of the historical project cost data samples for the several engineering categories, to obtain cost data analysis models corresponding to each engineering category.

[0059] Among them, the initial network model is an algorithm model with training and learning capabilities, such as a random forest algorithm model, a neural network algorithm model, a deep learning algorithm model, etc.

[0060] S4: Perform clustering analysis on the target project cost data based on the engineering geological information and building height of the target project cost data, to obtain the target engineering category.

[0061] Among them, the target project cost data can be project cost data provided by each contractor or construction party.

[0062] S5: Determine the cost data analysis model corresponding to the target engineering category as the target model.

[0063] S6: Input the engineering materials, construction techniques, and project cost of the target project cost data into the target model, to obtain the target project cost analysis result output by the target model.

[0064] Through step S6, the user can obtain multiple target project cost analysis results, to select the adopted project cost data from multiple target project cost data based on the multiple target project cost analysis results, and start the construction project according to the adopted project cost data.

[0065] In a feasible embodiment, the step S2: Perform clustering analysis on the multiple historical project cost data samples based on the engineering geological information and the building height, to obtain several engineering categories, includes:

[0066] S21: Based on the engineering geological information and the building height, map the multiple historical project cost data samples to a pre-constructed clustering coordinate system as data points, to obtain a clustering coordinate map including multiple data points; the engineering geological information corresponds to the first coordinate axis parameter of the coordinate system, and the building height corresponds to the second coordinate axis parameter of the coordinate system.

[0067] S22: Obtain several category data clusters according to the distribution density of the data points in the clustering coordinate map.

[0068] Among them, step S22 obtains several category data clusters according to the density-based clustering method, and in other embodiments, the present application can also obtain several category data clusters through the partition-based clustering method or the hierarchical-based clustering method.

[0069] S23: Obtain the several engineering categories according to the several category data clusters.

[0070] In a feasible embodiment, the step S22 of obtaining several category data clusters according to the distribution density of the data points in the clustering coordinate map includes:

[0071] S221: Obtain several initial data clusters according to the distribution density of the data points in the clustering coordinate map.

[0072] S222: Obtain the central data point with the smallest average distance according to the average distance between each data point and other data points in the initial data clusters.

[0073] S223: Construct the category data cluster corresponding to the central data point according to a preset radius value.

[0074] In a feasible embodiment, the step S4 of performing clustering analysis on the target project cost data according to the engineering geological information and building height of the target project cost data to obtain the target engineering category includes:

[0075] S41: Map the target project cost data to the clustering coordinate map according to the engineering geological information and building height of the target project cost data.

[0076] S42: Obtain the target engineering category according to the category data cluster where the target project cost data is located in the clustering coordinate map.

[0077] In a feasible embodiment, the step of training multiple initial network models according to the engineering materials, construction techniques, project costs, and cost analysis information of the historical project cost data samples of the several engineering categories to obtain cost analysis models corresponding to each engineering category includes:

[0078] Use the engineering materials, construction techniques, and project costs of the historical project cost data samples of each engineering category as training inputs, and use the cost analysis information as training outputs to train each of the initial network models to obtain cost analysis models corresponding to each of the engineering categories.

[0079] After performing clustering analysis on multiple historical project cost data samples according to engineering geological information and building height, this application obtains several project categories. Then, based on the engineering materials, construction techniques, project costs, and cost analysis information of the historical project cost data samples of the project categories, the initial network model is trained to obtain a cost data analysis model corresponding to each project category. After performing clustering analysis on the target project cost data according to the engineering geological information and building height, the target project category corresponding to the target project cost data is obtained, and the cost data analysis model corresponding to the target project category is determined as the target model. Then, by inputting the engineering materials, construction techniques, and project cost of the target project cost data into the target model, an accurate target project cost analysis result can be quickly obtained, achieving the effect of improving the efficiency and accuracy of obtaining project cost data analysis. Moreover, since the geological differences and building height differences of projects will affect the cost analysis results, this application first obtains project categories through clustering analysis and then performs project cost analysis through the corresponding cost data analysis models, which can reduce the interference of geological differences and building height differences on the cost analysis results and improve the accuracy of the cost analysis results.

[0080] The second embodiment of this application provides an analysis system for project cost data, including:

[0081] A sample acquisition module, configured to acquire multiple historical project cost data samples, where each of the historical project cost data samples is labeled with engineering geological information, building height, engineering materials, construction techniques, project cost, and cost analysis results; the cost analysis results include the analysis content of the engineering materials and construction techniques based on the project cost.

[0082] A sample analysis module, configured to perform clustering analysis on the multiple historical project cost data samples according to the engineering geological information and the building height to obtain several project categories.

[0083] A model training module, configured to train multiple initial network models according to the engineering materials, construction techniques, project cost, and cost analysis information of the historical project cost data samples of the several project categories to obtain cost data analysis models corresponding to each project category.

[0084] A clustering analysis module, configured to perform clustering analysis on the target project cost data according to the engineering geological information and building height of the target project cost data to obtain a target project category.

[0085] A target model acquisition module, configured to determine the cost data analysis model corresponding to the target project category as the target model.

[0086] The project cost analysis module is used to input the engineering materials, construction techniques, and project costs of the target project cost data into the target model to obtain the target project cost analysis result output by the target model.

[0087] In a feasible embodiment, the sample analysis module includes:

[0088] The clustering coordinate map acquisition sub-module is used to map the multiple historical project cost data samples to a pre-constructed clustering coordinate system as data points according to the engineering geological information and the building height, to obtain a clustering coordinate map including multiple data points; the engineering geological information corresponds to the first coordinate axis parameter of the coordinate system, and the building height corresponds to the second coordinate axis parameter of the coordinate system;

[0089] The category data cluster acquisition sub-module is used to obtain several category data clusters according to the distribution density of the data points in the clustering coordinate map;

[0090] The project category acquisition sub-module is used to obtain the several project categories according to the several category data clusters.

[0091] In a feasible embodiment, the category data cluster acquisition sub-module includes:

[0092] The initial data cluster acquisition unit is used to obtain several initial data clusters according to the distribution density of the data points in the clustering coordinate map;

[0093] The central data point acquisition unit is used to obtain the central data point with the smallest average distance according to the average distance between each data point and other data points in the initial data cluster;

[0094] The category data cluster acquisition unit is used to construct the category data cluster corresponding to the central data point according to a preset radius value.

[0095] In a feasible embodiment, the steps of the clustering analysis module include:

[0096] The mapping sub-module is used to map the target project cost data to the clustering coordinate map according to the engineering geological information and the building height of the target project cost data;

[0097] The target project category acquisition sub-module is used to obtain the target project category according to the category data cluster where the target project cost data is located in the clustering coordinate map.

[0098] In a feasible embodiment, the model training module is configured to: use the engineering materials, construction techniques, and project costs of the historical project cost data samples of each engineering category as training inputs, and use the cost analysis information as training outputs to train each of the initial network models to obtain cost data analysis models corresponding to each engineering category.

[0099] It should be noted that when the analysis system for project cost data provided in the second embodiment of the present application executes the method for analyzing project cost data, only the above division of each functional module is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the analysis system for project cost data provided in the second embodiment of the present application and the method for analyzing project cost data in the first embodiment of the present application belong to the same concept. The implementation process is detailed in the method embodiment and will not be repeated here.

[0100] The device embodiments described above are merely illustrative. The components described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of the present application. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0101] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0102] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for realizing in the process Figure 1 one process or multiple processes and / or blocks Figure 1means for selected functions in one or more boxes. These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured article including an instruction means that implements the process Figure 1 one process or more processes and / or boxes Figure 1 selected functions in one box or more boxes.

[0103] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are performed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide for implementing the process Figure 1 one process or more processes and / or boxes Figure 1 steps for selected functions in one box or more boxes.

[0104] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0105] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

[0106] Computer-readable media includes permanent and non-permanent, removable and non-removable media and can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0107] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0108] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for analyzing project cost data, characterized in that, Including: Obtain a plurality of historical project cost data samples, each of the historical project cost data samples being labeled with engineering geological information, building height, engineering materials, construction techniques, project cost, and cost analysis results; the cost analysis results include analysis content of the engineering materials and construction techniques based on the project cost; Perform cluster analysis on the plurality of historical project cost data samples according to the engineering geological information and the building height to obtain a number of project categories; Train a plurality of initial network models according to the engineering materials, construction techniques, project cost, and cost analysis information of the historical project cost data samples of the number of project categories to obtain cost data analysis models corresponding to each project category; Perform cluster analysis on the target project cost data according to the engineering geological information and building height of the target project cost data to obtain a target project category; Determine the cost data analysis model corresponding to the target project category as the target model; Input the engineering materials, construction techniques, and project cost of the target project cost data into the target model to obtain the target project cost analysis result output by the target model.

2. The analysis method of engineering cost data according to claim 1, characterized in that The step of performing cluster analysis on the plurality of historical project cost data samples according to the engineering geological information and the building height to obtain a number of project categories includes: According to the engineering geological information and the building height, map the plurality of historical project cost data samples to a pre-constructed cluster coordinate system as data points to obtain a cluster coordinate map including a plurality of data points; the engineering geological information corresponds to the first coordinate axis parameter of the coordinate system, and the building height corresponds to the second coordinate axis parameter of the coordinate system; Obtain a number of category data clusters according to the distribution density of the data points in the cluster coordinate map; Obtain the number of project categories according to the number of category data clusters.

3. The analysis method of project cost data according to claim 2, characterized in that The step of obtaining a number of category data clusters according to the distribution density of the data points in the cluster coordinate map includes: Obtain a number of initial data clusters according to the distribution density of the data points in the cluster coordinate map; Obtain a central data point with the smallest average distance according to the average distance between each data point and other data points in the initial data clusters; Construct a category data cluster corresponding to the central data point according to a preset radius value.

4. The analysis method of engineering cost data according to claim 3, characterized in that, The step of performing cluster analysis on the target project cost data according to the engineering geological information and building height of the target project cost data to obtain a target project category includes: Map the target project cost data to the cluster coordinate map according to the engineering geological information and building height of the target project cost data; Obtain the target project category according to the category data cluster where the target project cost data is located in the cluster coordinate map.

5. The analysis method of project cost data according to claim 1, characterized in that, The step of training a plurality of initial network models according to the engineering materials, construction techniques, project cost, and cost analysis information of the historical project cost data samples of the number of project categories to obtain cost data analysis models corresponding to each project category includes: Taking the engineering materials, construction techniques, and project costs of the historical project cost data samples of each of the engineering categories as training inputs, and taking the cost analysis information as training outputs, train each of the initial network models to obtain cost data analysis models corresponding to each of the engineering categories.

6. An analysis system for project cost data, characterized in that, It includes: A sample acquisition module for acquiring multiple historical project cost data samples, where each of the historical project cost data samples is labeled with engineering geological information, building height, engineering materials, construction techniques, project cost, and cost analysis results; the cost analysis results include analysis content of the engineering materials and construction techniques based on the project cost. A sample analysis module for performing cluster analysis on the multiple historical project cost data samples according to the engineering geological information and the building height to obtain several engineering categories. A model training module for training multiple initial network models according to the engineering materials, construction techniques, project costs, and cost analysis information of the historical project cost data samples of the several engineering categories to obtain cost data analysis models corresponding to each engineering category. A cluster analysis module for performing cluster analysis on target project cost data according to the engineering geological information and building height of the target project cost data to obtain a target engineering category. A target model acquisition module for determining the cost data analysis model corresponding to the target engineering category as the target model. A project cost analysis module for inputting the engineering materials, construction techniques, and project cost of the target project cost data into the target model to obtain the target project cost analysis result output by the target model.

7. The analysis system for project cost data according to claim 6, wherein The sample analysis module includes: A cluster coordinate map acquisition sub-module for mapping the multiple historical project cost data samples to a pre-constructed cluster coordinate system as data points according to the engineering geological information and the building height to obtain a cluster coordinate map including multiple data points; the engineering geological information corresponds to the first coordinate axis parameter of the coordinate system, and the building height corresponds to the second coordinate axis parameter of the coordinate system. A category data cluster acquisition sub-module for obtaining several category data clusters according to the distribution density of the data points in the cluster coordinate map. An engineering category acquisition sub-module for obtaining the several engineering categories according to the several category data clusters.

8. The analysis system for project cost data according to claim 7, characterized in that The category data cluster acquisition sub-module includes: An initial data cluster acquisition unit for obtaining several initial data clusters according to the distribution density of the data points in the cluster coordinate map. A central data point acquisition unit for obtaining the central data point with the smallest average distance according to the average distance between each data point and other data points in the initial data cluster. A category data cluster acquisition unit for constructing the category data cluster corresponding to the central data point according to a preset radius value.

9. The analysis system for project cost data according to claim 8, wherein The steps of the cluster analysis module include: A mapping sub-module for mapping the target project cost data to the cluster coordinate map according to the engineering geological information and building height of the target project cost data. A target project category acquisition sub-module, configured to obtain the target project category according to the category data cluster where the target project cost data is located in the clustering coordinate map.

10. The analysis system for project cost data according to claim 6, characterized in that The model training module is configured to: use the project materials, construction techniques, and project costs of the historical project cost data samples of each project category as training inputs, use the cost analysis information as training outputs, and train each of the initial network models to obtain cost data analysis models corresponding to each of the project categories.

Images