Method and device for estimating construction cost

Abstract

The application discloses a kind of methods and devices for estimating engineering construction cost, the method comprises: obtaining the design file including the building information of target engineering;First feature information is parsed from the design file, and the first feature information is input into pre-trained cost sub-item model, to obtain the type corresponding to the cost sub-item of the target engineering;Second feature information is parsed from the design file, and the second feature information is input into pre-trained unit price estimation model, to obtain the unit price of each type of cost sub-item of the target engineering;The engineering quantity of each type of cost sub-item of the target engineering is obtained from the design file;According to the unit price and engineering quantity of each type of cost sub-item of the target engineering, the total construction cost of the target engineering is calculated;The building cost in engineering construction is intelligently estimated by the trained model, and the efficiency and accuracy of cost estimation are improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and apparatus for estimating engineering construction costs. Background Technology

[0002] In today's construction industry, cost estimation is a specialized task performed by cost estimators. When conducting cost estimations, cost estimators often require architects to manually measure and calculate various parts of the building, and they also need industry knowledge. Finally, cost estimators integrate all collected data and information to calculate the overall project price. In this way, cost estimators can provide the project management team with a detailed cost report, helping the owner determine the overall project implementation cost. However, the process of interpreting design documents is cumbersome and time-consuming for cost estimators, and errors in extraction and input are possible. Furthermore, the work of organizing and classifying data is both tedious and prone to omissions, requiring precise recording and tracking to ensure cost control. In addition, non-cost estimators often find it difficult to understand cost estimation data, resulting in low efficiency in obtaining cost information.

[0003] Therefore, how to intelligently estimate the construction costs in the construction industry has become a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of this invention is to provide a method and apparatus for estimating engineering construction costs. By using a trained model, the construction costs in engineering projects can be intelligently estimated, thereby improving the efficiency and accuracy of cost estimation.

[0005] According to one aspect of the present invention, a method for estimating engineering construction costs is provided, the method comprising: Obtain design documents that include architectural information for the target project; The first feature information is parsed from the design file and input into the pre-trained cost item model to obtain the type of cost item corresponding to the target project; The second feature information is parsed from the design file and input into the pre-trained unit price estimation model to obtain the unit price of each type of cost item in the target project; Obtain the quantities of each type of cost item for the target project from the design documents; The total construction cost of the target project is calculated based on the unit price and quantity of each type of cost item in the target project.

[0006] Optionally, before obtaining the design documents including the building information of the target project, the method further includes: Obtain historical design data for historical building projects; The historical design data is standardized, and feature data is selected from the standardized historical design data to form a feature data set. The preset classification model is trained using the feature data set to obtain the cost breakdown model; The cost items of various types are traversed sequentially, and the regression model associated with the current cost item is trained using the feature data set to obtain the unit price estimation model corresponding to the current cost item.

[0007] Optionally, after obtaining the design documents including the building information of the target project, the method further includes: The graphic data representing the architectural form of the target project and the structured data representing the design parameter information of the target project are parsed from the design documents. Building scale parameters are extracted from the graphic data; wherein the building scale parameters include at least one of the following: number of floors, floor height, building elevation, and building area; Key design parameters are extracted from the structured data; wherein the key design parameters include at least one of the following: project type, project address, building structure type, seismic resistance level, interior decoration standard, and exterior facade material.

[0008] Optionally, the step of parsing the first feature information from the design file and inputting the first feature information into a pre-trained cost item model to obtain the type of cost item corresponding to the target project includes: Set the project business type, project address, and building structure type in the key design parameters as the first feature information; The first feature information is input into the cost item model, and the type of cost item corresponding to the target project is determined based on the output of the cost item model. The cost items corresponding to the target project include at least one of the following: construction cost items, electromechanical installation cost items, consulting fee items, and equipment cost items.

[0009] Optionally, the step of parsing the second feature information from the design file and inputting the second feature information into a pre-trained unit price estimation model to obtain the unit price of each type of cost item in the target project includes: Iterate through the various types of cost items of the target project in sequence to obtain the target unit price estimation model corresponding to the currently traversed cost item; The building scale parameters and the key design parameters are input as second feature information into the target unit price estimation model, and the unit price of the currently traversed cost item is determined based on the output of the target unit price estimation model.

[0010] Optionally, calculating the total construction cost of the target project based on the unit price and quantity of each type of cost item of the target project includes: The cost items of each type of the target project are traversed sequentially, and the cost of the current cost item is calculated based on the unit price and quantity of the current cost item. Calculate the total construction cost of the target project based on the cost of all types of cost items of the target project; Based on the unit price, quantity, and cost of various cost items of the target project, as well as the total construction cost of the target project, a cost information table for the target project is formed.

[0011] To achieve the above objectives, the present invention also provides an apparatus for estimating engineering construction costs, the apparatus comprising: The acquisition module is used to acquire design documents that include architectural information of the target project; The parsing module is used to parse the first feature information from the design file and input the first feature information into the pre-trained cost item model to obtain the type of cost item corresponding to the target project; The estimation module is used to parse the second feature information from the design file and input the second feature information into the pre-trained unit price estimation model to obtain the unit price of each type of cost item of the target project; An extraction module is used to obtain the quantity of each type of cost item of the target project from the design file; The calculation module is used to calculate the total construction cost of the target project based on the unit price and quantity of each type of cost item in the target project.

[0012] Optionally, the device further includes: The training module is used to acquire historical design data of historical building projects; standardize the historical design data and select feature data from the standardized historical design data to form a feature data set; use the feature data set to train a preset classification model to obtain the cost item model; sequentially traverse various types of cost items, and use the feature data set to train a regression model pre-associated with the currently traversed cost item to obtain a unit price estimation model corresponding to the currently traversed cost item.

[0013] To achieve the above objectives, the present invention also provides a computer device, which specifically includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for estimating engineering construction costs described above.

[0014] To achieve the above objectives, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for estimating engineering construction costs described above.

[0015] The method and apparatus for estimating construction costs provided by this invention automatically parse the design documents of building engineering information, input the parsed partial data into the cost item model to generate the cost items required for estimation with one click, ensuring cost control and improving efficiency. The parsed partial data and engineering quantities are input into the unit price estimation model to form the final cost list with one click. Through the linkage between the estimation model and the data, the design document information of the target project's building information and the estimated cost are updated in real time, avoiding inconsistencies between data, models, and estimates. Attached Figure Description

[0016] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A schematic diagram of an optional process for estimating engineering construction costs provided in Embodiment 1; Figure 2 A schematic diagram of another optional process for estimating engineering construction costs provided in Example 1; Figure 3 A schematic diagram of an optional component structure of the apparatus for estimating engineering construction costs provided in Embodiment 2; Figure 4 This is a schematic diagram of an optional hardware structure for the computer device provided in Embodiment 3. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0018] Example 1 This invention provides a method for estimating engineering construction costs, such as... Figure 1 As shown, the method specifically includes the following steps: S101: Obtain design documents that include architectural information for the target project.

[0019] The design files are CAD drawings or other design files containing architectural information, such as 3D architectural design files, structured JSON files, and structured CSV files. No specific restrictions are placed on the type of design files.

[0020] Preferably, the design file is a CAD file.

[0021] S102: Parse the first feature information from the design file and input the first feature information into the pre-trained cost item model to obtain the type of cost item corresponding to the target project.

[0022] Among them, cost items are the specific detailed cost items that constitute the cost, that is, the cost is composed of multiple cost items.

[0023] Specifically, the first feature information includes at least one of the following: project type, project address, and building structure type; the cost item type includes at least one of the following: construction cost item, electromechanical installation cost item, consulting fee item, and equipment cost item.

[0024] In this embodiment, the first feature information is parsed from CAD drawings or other design files containing architectural information, and the first feature information is input as an input parameter into a pre-trained cost item model. The type of cost item corresponding to the target project is obtained based on the output of the cost item model.

[0025] S103: Parse the second feature information from the design file and input the second feature information into the pre-trained unit price estimation model to obtain the unit price of each type of cost item of the target project.

[0026] Specifically, the second feature information includes at least one of the following: number of building floors, building floor height, building elevation, building area, project type, project address, building structure type, seismic resistance level, interior decoration standard, and exterior facade material.

[0027] In this embodiment, the second feature information is parsed from CAD drawings or other design documents containing building information, and the second feature information is used as an input parameter to a pre-trained unit price estimation model. The unit price of each type of cost item of the target project is obtained based on the output of the unit price estimation model.

[0028] S104: Obtain the quantities of each type of cost item for the target project from the design documents.

[0029] Specifically, the quantities of work for each cost item include: a detailed breakdown of the quantities for each cost item, such as: the area of ​​the item and the floor height of the item.

[0030] It also allows designers to manually input engineering quantities into the model.

[0031] In this embodiment, the quantities of each type of cost item of the target project are obtained from the design documents or manually entered information.

[0032] S105: Calculate the total construction cost of the target project based on the unit price and quantity of each type of cost item of the target project.

[0033] In this embodiment, the total construction cost of the target project is calculated based on the unit price and quantity of each type of cost item in the target project.

[0034] In this embodiment, the design documents, which include building project information, are parsed and calculated using a cost itemization model and a unit price estimation model, thereby intelligently estimating the total construction cost of the building project and improving the efficiency and accuracy of cost estimation.

[0035] Specifically, before obtaining the design documents including the building information of the target project in step S101, the method further includes: Step A1: Obtain historical design data for historical building projects; This involves collecting historical design data from multiple building projects. This historical design data includes at least the following characteristics: number of building floors, building floor height, building elevation, building area, project type, project address, building structure type, seismic resistance level, interior decoration standard, exterior facade materials, type of cost item corresponding to the building project, and individual cost items for each type of building project.

[0036] Step A2: Standardize the historical design data and select feature data from the standardized historical design data to form a feature data set; The historical design data may contain missing data and anomalies. The historical design data is standardized and then classified to select a set of feature data to ensure data quality and consistency of model input.

[0037] In addition, correlation analysis and feature selection will be used to screen key features that affect cost estimation, such as building height, building area and building structure type, in order to optimize the feature set, improve the predictive performance of the model and ensure the applicability of different features.

[0038] Step A3: Train the preset classification model using the feature data set to obtain the cost breakdown model; The preset classification model can use one of the following models: decision tree regression model, linear regression model, SVM regression model, KNN regression model, random forest regression model, Adaboost regression model, GBRT regression model, Bagging regression model, or ExtraTree extreme random tree regression model.

[0039] Step A4: Iterate through various types of cost items in sequence, and use the feature data set to train the regression model that is pre-associated with the cost item being iterated, so as to obtain the unit price estimation model corresponding to the cost item being iterated. Among them, regression models include multiple linear regression models and nonlinear regression models, such as support vector regression (SVR) and decision tree regression.

[0040] In addition, cross-validation is used to evaluate the model's stability, and error metrics are calculated to measure predictive performance. Overfitting is prevented by adjusting model parameters, ensuring the model's generalization ability. After encapsulating the model as a callable service, users can directly obtain unit price estimates based on relevant building information. In practical applications, the trained regression model can also be encapsulated to form an externally callable unit price estimation module. This module determines the unit price corresponding to different types of cost analysis, ensuring the flexibility and applicability of the estimation results.

[0041] In this embodiment, the corresponding model is selected according to the characteristics of different projects to ensure the interpretability and computational efficiency of the model. In addition, corresponding models are built for different types of cost items to improve the accuracy and efficiency of the estimation.

[0042] Specifically, after obtaining the design documents including the building information of the target project in step S101, the method further includes: Step B1: Parse the graphic data representing the architectural form of the target project and the structured data representing the design parameter information of the target project from the design file.

[0043] Step B2: Extract building scale parameters from the graphic data; wherein the building scale parameters include at least one of the following: number of building floors, building floor height, building elevation, and building area.

[0044] Preferably, the number of building floors includes: the number of floors above ground and the number of floors below ground; the building floor height includes: the floor height above ground and the floor height below ground; the building area includes: the total building area, the building area above ground, the building area below ground, the base area, and the civil defense building area.

[0045] Step B3: Extract key design parameters from the structured data; wherein the key design parameters include at least one of the following: project type, project address, building structure type, seismic resistance level, interior decoration standard, and exterior facade material.

[0046] Preferred project types include: residential, commercial properties, public buildings, transportation hubs, supporting facilities, government offices, and infrastructure; building structure types include: brick-wood structure, brick-concrete structure, reinforced concrete structure, and steel structure.

[0047] Typically, cost estimators rely on design documents such as CAD files for information. However, interpreting and extracting data from these documents is cumbersome, time-consuming, and prone to errors. In this embodiment, the system automatically parses CAD files to extract usable building scale parameters and key design parameters, significantly improving extraction efficiency.

[0048] Specifically, step S102, which involves parsing the first feature information from the design file and inputting it into a pre-trained cost item model to obtain the type of cost item corresponding to the target project, includes: Step C1: Set the project business type, project address, and building structure type in the key design parameters as the first feature information; The model also allows users to manually add key design parameters, such as project address, structure type, and facade material.

[0049] Step C2: Input the first feature information into the cost item model, and determine the type of cost item corresponding to the target project based on the output of the cost item model; The cost items corresponding to the target project include at least one of the following: construction cost items, electromechanical installation cost items, consulting fee items, and equipment cost items.

[0050] Preferably, since the training data and the estimated final output data are classified differently, post-processing of the data is required, and a mapping relationship between the data needs to be established. Then, the output value of the cost item model is used to determine the type of the corresponding cost item through a pre-defined mapping table; mapping existing subjects to the classification standards of the data system ensures the completeness of the output results.

[0051] In addition, the construction cost items include: foundation and earthwork, above-ground structure, underground structure, waterproofing and insulation, roof, exterior facade and curtain wall, and doors and windows; the mechanical and electrical installation cost items include: exterior facade decoration, general contracting primary decoration, interior decoration, electrical, water supply and drainage, fire protection, ventilation and air conditioning, building intelligence and communication, and gas; other items may also be included, such as: outdoor power, outdoor water supply and drainage, outdoor heating, outdoor gas, outdoor roads, landscaping, and gatehouse and parking lot.

[0052] In the construction industry, cost estimation typically involves multiple sub-items such as materials, labor, equipment, and management expenses. Organizing and classifying these items is both tedious and prone to omissions. However, in this embodiment, by inputting feature information into a pre-trained cost item model, the required cost item types can be directly obtained from the model's output, ensuring cost control and improving efficiency.

[0053] Specifically, step S103, which involves parsing the second feature information from the design file and inputting it into a pre-trained unit price estimation model to obtain the unit price of each type of cost item in the target project, includes: Step D1: Iterate through the various types of cost items of the target project in sequence to obtain the target unit price estimation model corresponding to the currently iterated cost item; Step D2: Input the building scale parameters and the key design parameters as second feature information into the target unit price estimation model, and determine the unit price of the cost item currently being traversed based on the output of the target unit price estimation model.

[0054] Preferably, the output value of the unit price estimation model can be multiplied by a preset inflation coefficient to obtain the final unit price of the cost item. The inflation coefficient represents the allowance that the industry needs to make; for example, if the output value is 100 million, the estimate might be 105 million.

[0055] Typically, in existing technologies, cost estimators need to determine the unit price of each cost item based on their experience from past projects and their familiarity with market and industry prices. However, estimators need to find suitable unit prices based on project characteristics, which usually involves extensive market research and data comparison, is time-consuming, easily affected by market fluctuations, and has poor accuracy and timeliness. In this embodiment, building scale parameters and key design parameters are input into the target unit price estimation model, and the unit price of each cost item can be obtained from the output of the unit price estimation model.

[0056] Specifically, in step S105, calculating the total construction cost of the target project based on the unit price and quantity of each type of cost item of the target project includes: Step E1: Iterate through the various types of cost items of the target project in sequence, and calculate the cost of the current cost item based on the unit price and quantity of the current cost item. Step E2: Calculate the total construction cost of the target project based on the cost of all types of cost items of the target project; Step E3: Based on the unit price, quantity, and cost of various cost items of the target project, as well as the total construction cost of the target project, form a cost information table for the target project.

[0057] In this cost information table, each row corresponds to a type of cost item, and each column corresponds to the unit price, quantity of work, and cost, respectively.

[0058] Furthermore, after step S106, the method further includes: Step F1: Receive adjustment instructions; Step F2: Identify the objects related to the adjustment instruction from the cost information table; Step F3: Adjust the value of the object according to the adjustment instruction to update the cost information table.

[0059] Typically, in current technology, cost estimators integrate all collected data and information into an Excel file and calculate the overall project price using formulas and functions. This allows them to provide the project management team with a detailed cost report, helping the owner determine the overall project implementation cost. However, estimates often change frequently with design adjustments, and currently, relying solely on estimators to manually maintain the relationship between the estimate Excel sheet and the design CAD files lacks a systematic, data-level connection, sometimes resulting in discrepancies between the estimates and the design documents.

[0060] In this embodiment, the linkage between the cost itemization module, the unit price estimation module, and the data ensures that the design document information and estimated cost of the target project are updated in real time, avoiding inconsistencies between data, models, and estimates.

[0061] like Figure 2As shown, in this embodiment, a design file including the building information of the target project is first obtained, and feature information is parsed from the design file; wherein, the feature information includes at least one of the following: number of building floors, building floor height, building elevation, building area, project type, project address, building structure type, seismic resistance level, decoration standard, facade material, and quantity of work; then, the feature information is input into a pre-trained cost itemization model and a pre-trained unit price estimation model, and the total construction cost of the target project is determined based on the output.

[0062] Through this embodiment, the design documents of the building project are analyzed and the total construction cost is calculated using the model intelligence, which can achieve the following technical effects: (1) The system automatically analyzes the design documents including CAD files and generates data that can be used for estimation, which greatly improves the extraction efficiency; (2) Through the training of the estimation model, it supports one-click generation of the cost items required for estimation, which ensures cost control and improves efficiency; (3) Through the training of the estimation model, it supports matching the details with the corresponding engineering quantity and unit price information, and forming the final cost list with one click; (4) Through the linkage between the estimation model and the data, it ensures that the design document information of the building information of the target project and the estimated cost are updated in real time, avoiding inconsistencies between data, model and estimation.

[0063] Example 2, This invention provides an apparatus for estimating engineering construction costs, such as... Figure 3 As shown, the device specifically includes the following components: Module 301 is used to acquire design documents that include architectural information of the target project. The parsing module 302 is used to parse the first feature information from the design file and input the first feature information into the pre-trained cost item model to obtain the type of cost item corresponding to the target project; The estimation module 303 is used to parse the second feature information from the design file and input the second feature information into the pre-trained unit price estimation model to obtain the unit price of each type of cost item of the target project; Extraction module 304 is used to obtain the quantity of each type of cost item of the target project from the design file; The calculation module 305 is used to calculate the total construction cost of the target project based on the unit price and quantity of each type of cost item of the target project.

[0064] Specifically, the device further includes: The training module is used to acquire historical design data of historical building projects; standardize the historical design data and select feature data from the standardized historical design data to form a feature data set; use the feature data set to train a preset classification model to obtain the cost item model; sequentially traverse various types of cost items, and use the feature data set to train a regression model pre-associated with the currently traversed cost item to obtain a unit price estimation model corresponding to the currently traversed cost item.

[0065] Furthermore, the acquisition module 301 is also used for: The graphic data representing the architectural form of the target project and the structured data representing the design parameter information of the target project are parsed from the design documents. Building scale parameters are extracted from the graphic data; wherein the building scale parameters include at least one of the following: number of floors, floor height, building elevation, and building area; Key design parameters are extracted from the structured data; wherein the key design parameters include at least one of the following: project type, project address, building structure type, seismic resistance level, interior decoration standard, and exterior facade material.

[0066] Furthermore, the parsing module 302 is specifically used for: Set the project business type, project address, and building structure type in the key design parameters as the first feature information; The first feature information is input into the cost item model, and the type of cost item corresponding to the target project is determined based on the output of the cost item model. The cost items corresponding to the target project include at least one of the following: construction cost items, electromechanical installation cost items, consulting fee items, and equipment cost items.

[0067] Furthermore, the estimation module 303 is specifically used for: Iterate through the various types of cost items of the target project in sequence to obtain the target unit price estimation model corresponding to the currently traversed cost item; The building scale parameters and the key design parameters are input as second feature information into the target unit price estimation model, and the unit price of the currently traversed cost item is determined based on the output of the target unit price estimation model.

[0068] Furthermore, the computing module 305 is specifically used for: The cost items of each type of the target project are traversed sequentially, and the cost of the current cost item is calculated based on the unit price and quantity of the current cost item. Calculate the total construction cost of the target project based on the cost of all types of cost items of the target project; Based on the unit price, quantity, and cost of various cost items of the target project, as well as the total construction cost of the target project, a cost information table for the target project is formed.

[0069] This embodiment automatically parses the design documents of building engineering information, inputs the parsed partial data into the cost item model to generate the cost items required for estimation with one click, ensuring cost control and improving efficiency. The parsed partial data and engineering quantities are input into the unit price estimation model to form the final cost list with one click. Through the linkage between the estimation model and the data, the design document information and estimated cost of the target project are updated in real time, avoiding inconsistencies between data, models and estimates.

[0070] Example 3 This embodiment also provides a computer device, such as a smartphone, tablet computer, laptop computer, desktop computer, rack server, blade server, tower server, or cabinet server (including a standalone server or a server cluster composed of multiple servers), etc., capable of executing programs. Figure 4 As shown, the computer device 40 in this embodiment includes, but is not limited to, a memory 401 and a processor 402 that are communicatively connected to each other via a system bus. It should be noted that... Figure 4 Only a computer device 40 with components 401-402 is shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0071] In this embodiment, the memory 401 (i.e., the readable storage medium) includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 401 may be an internal storage unit of the computer device 40, such as the hard disk or memory of the computer device 40. In other embodiments, the memory 401 may also be an external storage device of the computer device 40, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 40. Of course, the memory 401 may include both the internal storage unit and its external storage device of the computer device 40. In this embodiment, the memory 401 is typically used to store the operating system and various application software installed on the computer device 40. In addition, the memory 401 may also be used to temporarily store various types of data that have been output or will be output.

[0072] In some embodiments, processor 402 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. This processor 402 is typically used to control the overall operation of computer device 40.

[0073] Specifically, in this embodiment, the processor 402 is used to execute a program stored in the memory 401 for estimating the cost of engineering construction. When the program for estimating the cost of engineering construction is executed, it performs the following steps: Obtain design documents that include architectural information for the target project; The first feature information is parsed from the design file and input into the pre-trained cost item model to obtain the type of cost item corresponding to the target project; The second feature information is parsed from the design file and input into the pre-trained unit price estimation model to obtain the unit price of each type of cost item in the target project; Obtain the quantities of each type of cost item for the target project from the design documents; The total construction cost of the target project is calculated based on the unit price and quantity of each type of cost item in the target project.

[0074] For a detailed description of the above method steps, please refer to Example 1. This example will not be repeated here.

[0075] Example 4 This embodiment also provides a computer-readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, server, app store, etc., which stores a computer program. When the computer program is executed by a processor, it implements the following method steps: Obtain design documents that include architectural information for the target project; The first feature information is parsed from the design file and input into the pre-trained cost item model to obtain the type of cost item corresponding to the target project; The second feature information is parsed from the design file and input into the pre-trained unit price estimation model to obtain the unit price of each type of cost item in the target project; Obtain the quantities of each type of cost item for the target project from the design documents; The total construction cost of the target project is calculated based on the unit price and quantity of each type of cost item in the target project.

[0076] For a detailed description of the above method steps, please refer to Example 1. This example will not be repeated here.

[0077] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0078] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0079] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0080] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for estimating engineering construction costs, characterized in that, The method includes: Obtain design documents that include architectural information for the target project; The first feature information is parsed from the design file and input into the pre-trained cost item model to obtain the type of cost item corresponding to the target project; The second feature information is parsed from the design file and input into the pre-trained unit price estimation model to obtain the unit price of each type of cost item in the target project; Obtain the quantities of each type of cost item for the target project from the design documents; The total construction cost of the target project is calculated based on the unit price and quantity of each type of cost item in the target project.

2. The method for estimating engineering construction costs according to claim 1, characterized in that, Prior to obtaining the design documents including the architectural information of the target project, the method further includes: Obtain historical design data for historical building projects; The historical design data is standardized, and feature data is selected from the standardized historical design data to form a feature data set. The preset classification model is trained using the feature data set to obtain the cost breakdown model; The cost items of various types are traversed sequentially, and the regression model associated with the current cost item is trained using the feature data set to obtain the unit price estimation model corresponding to the current cost item.

3. The method for estimating engineering construction costs according to claim 2, characterized in that, After obtaining the design documents including the architectural information of the target project, the method further includes: The graphic data representing the architectural form of the target project and the structured data representing the design parameter information of the target project are parsed from the design documents. Building scale parameters are extracted from the graphic data; wherein the building scale parameters include at least one of the following: number of floors, floor height, building elevation, and building area; Key design parameters are extracted from the structured data; wherein the key design parameters include at least one of the following: project type, project address, building structure type, seismic resistance level, interior decoration standard, and exterior facade material.

4. The method for estimating engineering construction costs according to claim 3, characterized in that, The step of parsing the first feature information from the design file and inputting the first feature information into a pre-trained cost item model to obtain the type of cost item corresponding to the target project includes: Set the project business type, project address, and building structure type in the key design parameters as the first feature information; The first feature information is input into the cost item model, and the type of cost item corresponding to the target project is determined based on the output of the cost item model. The cost items corresponding to the target project include at least one of the following: construction cost items, electromechanical installation cost items, consulting fee items, and equipment cost items.

5. The method for estimating engineering construction costs according to claim 3, characterized in that, The step of parsing the second feature information from the design file and inputting the second feature information into a pre-trained unit price estimation model to obtain the unit price of each type of cost item in the target project includes: Iterate through the various types of cost items of the target project in sequence to obtain the target unit price estimation model corresponding to the currently traversed cost item; The building scale parameters and the key design parameters are input as second feature information into the target unit price estimation model, and the unit price of the currently traversed cost item is determined based on the output of the target unit price estimation model.

6. The method for estimating engineering construction costs according to claim 1, characterized in that, The step of calculating the total construction cost of the target project based on the unit price and quantity of each type of cost item includes: The cost items of each type of the target project are traversed sequentially, and the cost of the current cost item is calculated based on the unit price and quantity of the current cost item. Calculate the total construction cost of the target project based on the cost of all types of cost items of the target project; Based on the unit price, quantity, and cost of various cost items of the target project, as well as the total construction cost of the target project, a cost information table for the target project is formed.

7. An apparatus for estimating engineering construction costs, characterized in that, The device includes: The acquisition module is used to acquire design documents that include architectural information of the target project; The parsing module is used to parse the first feature information from the design file and input the first feature information into the pre-trained cost item model to obtain the type of cost item corresponding to the target project; The estimation module is used to parse the second feature information from the design file and input the second feature information into the pre-trained unit price estimation model to obtain the unit price of each type of cost item of the target project; An extraction module is used to obtain the quantity of each type of cost item of the target project from the design file; The calculation module is used to calculate the total construction cost of the target project based on the unit price and quantity of each type of cost item in the target project.

8. The apparatus for estimating engineering construction costs according to claim 7, characterized in that, The device further includes: The training module is used to acquire historical design data of historical building projects; standardize the historical design data and select feature data from the standardized historical design data to form a feature data set; use the feature data set to train a preset classification model to obtain the cost item model; sequentially traverse various types of cost items, and use the feature data set to train a regression model pre-associated with the currently traversed cost item to obtain a unit price estimation model corresponding to the currently traversed cost item.

9. A computer device, the computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the steps of the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images