Building engineering equipment cost evaluation system based on big data
By counting and screening the cost ratio values of machinery and equipment in construction projects, forming a cost ratio range, the problems of inaccurate and low efficiency of mechanical equipment cost evaluation in the existing technology are solved, and more accurate and efficient cost evaluation is achieved.
Patent Information
- Application Number
- CN202411080365.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2025-02-18
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing construction engineering equipment cost evaluation system based on big data is difficult to provide accurate scope evaluation when evaluating the cost of mechanical equipment, resulting in problems with the accuracy of the evaluation results and the evaluation efficiency is not high.
By counting the cost ratio values of each mechanical equipment in n construction projects, filtering out the cost ratio values exceeding the evaluation threshold, extracting the maximum and minimum values, forming a cost ratio range of machinery and equipment, and using it to conduct a scope assessment of the cost of machinery and equipment. .
It improves the accuracy and efficiency of mechanical equipment cost assessment, and can conduct a more accurate scope assessment of mechanical equipment cost for unstarted construction projects.
Smart Images
Figure CN119477363A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of construction engineering cost, and in particular to a construction engineering equipment cost evaluation system based on big data. Background Art
[0002] Construction project cost technology refers to a technology that comprehensively manages and controls the project cost during the planning, design, construction and operation stages of a construction project. Specifically, it includes the following: Budget preparation: According to the building plan or construction drawings, a budget list for the project is prepared by calculating the quantities of various projects and the unit prices of materials; Bidding and tendering: According to project requirements, suppliers are selected and contracts are signed to obtain the most favorable price and quality for the project; Project progress control: By formulating a construction schedule, the progress of the project is mastered, and timely tracking and adjustments are made to ensure that the construction progress and construction period meet expectations; Cost control: During the construction stage, cost factors such as material consumption, labor resources, and equipment investment are monitored to promptly discover and resolve problems that cause cost increases; By applying construction project cost technology, the cost of the project can be effectively controlled, the economic benefits of the project can be improved, and the sustainable development of the project can be achieved while ensuring the quality and progress of the project.
[0003] The existing authorization announcement number is CN111415205B, and the technical solution given in the patent named "A construction project cost evaluation system based on big data" includes the connection between the foundation soil environment detection module and the foundation soil environment analysis and processing module, the storage database is connected to the foundation soil environment analysis and processing module, the underground engineering building volume measurement module, the engineering quantity cost calculation module and the cloud server, the cloud server is connected to the foundation soil environment analysis and processing module, the engineering quantity cost calculation module and the output display terminal, and the execution terminal device is connected to the foundation soil environment detection module and the output display terminal; it improves the existing soil drilling and sampling equipment, embeds the corresponding soil environment parameter detection module software into the hardware of the drill rod that goes deep into the underground, and combines it with the database required for the relevant cost, so that the underground foundation engineering cost after preliminary evaluation can be obtained after real-time operation at the construction site. Although it is convenient and fast to operate and has strong on-site operability, it cannot make further improvements in evaluation efficiency.
[0004] In combination with the above-mentioned patents and prior art, when applying big data technology to evaluate the cost of construction equipment, if only the costs related to mechanical equipment are evaluated, the traditional approach is to obtain cost reference values related to mechanical equipment, such as: the purchase cost reference value of mechanical equipment, and then accumulate the various cost reference values related to mechanical equipment, and obtain the required predicted evaluation value through big data analysis. However, the predicted evaluation value does not give a corresponding range, resulting in problems with the accuracy of its evaluation results. If you want to improve the accuracy of the evaluation results, you need to manually check the data or perform calculations and analysis, and the efficiency of the entire evaluation operation cannot be improved. Summary of the invention
[0005] 1. Technical issues to be solved
[0006] In view of the shortcomings of the prior art, the present invention provides a construction engineering equipment cost evaluation system based on big data, which calculates the cost ratio value Pvo of each mechanical equipment in n construction projects. t , and screen out the cost ratio values Pvo of each mechanical equipment that exceeds the evaluation threshold Pt t , extract the maximum value Pmax and the minimum value Pmin, so as to form a range value, namely the mechanical equipment cost ratio interval [Pmin, Pmax]. When dealing with subsequent construction projects that have not yet started, a more accurate range assessment can be made for the mechanical equipment cost. At the same time, the efficiency of the mechanical equipment cost assessment for construction projects has also been greatly improved, solving the problems raised in the background technology.
[0007] (II) Technical solution
[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:
[0009] A construction engineering equipment cost evaluation system based on big data, the system comprising:
[0010] The data collection module obtains data related to the cost of mechanical equipment, and the data related to the cost of mechanical equipment includes the type, specification, brand, model, purchase price, rental period and corresponding price, and driving cost of mechanical equipment;
[0011] The analysis and modeling module uses big data analysis technology to establish purchase cost prediction models, rental cost prediction models, and driving cost prediction models based on the acquired data related to the cost of mechanical equipment;
[0012] The cost estimation module, based on the established prediction models, predicts the estimated cost of purchasing machinery and equipment, the estimated cost of renting machinery and equipment, and the estimated cost of operating machinery and equipment for the construction project by inputting the construction project parameters, and builds a data calculation model to obtain the total estimated cost;
[0013] The calculation and evaluation module uses various prediction models based on the historical machinery and equipment costs of n construction projects, and uses each prediction model to predict the estimated cost of purchasing machinery and equipment, the estimated cost of renting machinery and equipment, and the estimated cost of driving machinery and equipment for the corresponding construction project, obtains the total estimated cost of the corresponding construction project, builds a cost evaluation analysis model, and generates n machinery and equipment cost ratio values Pvo t , forming a data set of mechanical equipment cost ratio values;
[0014] Adjust the execution module to convert each mechanical equipment cost ratio value Pvo in the mechanical equipment cost ratio value data set t They are all compared with the preset evaluation threshold Pt, and the cost ratio values Pvo of each mechanical equipment that exceeds the evaluation threshold Pt are screened out. t , and extract the cost ratio value Pvo of each mechanical equipment t The maximum value Pmax and the minimum value Pmin in the formula form the mechanical equipment cost ratio interval [Pmin, Pmax]. According to the mechanical equipment cost ratio interval [Pmin, Pmax] and the total estimated cost of the corresponding construction project, the predicted total cost of the corresponding project can be obtained.
[0015] Furthermore, the operating cost of mechanical equipment includes driver cost, fuel cost during the operation of the mechanical equipment, and maintenance cost.
[0016] Furthermore, a purchase cost prediction model is established: based on the equipment type, specification, brand, model and purchase price as features, regression analysis is used to establish a purchase cost prediction model; a rental cost prediction model is established: based on the equipment type, specification, brand, model and rental period and the corresponding price as features, regression analysis is used to establish a rental cost prediction model; a driving cost prediction model is established: based on the driving cost data of mechanical equipment, after statistical analysis, regression analysis is used to establish a driving cost prediction model.
[0017] Furthermore, construction project parameters include the type of equipment required, the number of mechanical equipment, and the lease period.
[0018] Furthermore, the historical machinery and equipment costs of n construction projects are the actual total costs of purchasing machinery and equipment in several different construction projects within one month, and the actual total cost includes the purchase price, leasing period and corresponding price, and machinery and equipment driving cost, which corresponds to part of the data related to the obtained machinery and equipment costs.
[0019] Further, generate the mechanical equipment cost ratio value Pvo t The formula is as follows:
[0020]
[0021] In the formula, Yg t represents the total estimated cost of the corresponding construction project, Sj t represents the actual total cost of the corresponding construction project, t=1, 2, ..., n, n is a positive integer, and t represents the number of the corresponding construction project.
[0022] Furthermore, the resulting mechanical equipment cost ratio value data set is {Pvo 1 、Pvo 2 , …, Pvo t}.
[0023] Furthermore, the adjustment execution module also includes a verification training unit, which selects each mechanical equipment cost ratio value Pvo that exceeds the evaluation threshold Pt. t After that, extract the cost ratio value Pvo of each mechanical equipment that does not exceed the evaluation threshold Pt t The quantity S is measured and compared with a preset standard quantity value;
[0024] If the quantity S does not exceed the standard quantity value, no response action will be taken;
[0025] If the quantity S exceeds the standard quantity value, a warning signal is issued and the training evaluation strategy is executed.
[0026] Furthermore, the training and evaluation strategy includes using corresponding historical data to train each prediction model, and verifying and evaluating each prediction model based on the mean square error. After verifying that the mean square error does not exceed the preset standard value, the corresponding prediction model is output, otherwise, the training continues; wherein the corresponding historical data include the actual purchase price, the lease period and the corresponding price, and the driving cost of the mechanical equipment.
[0027] A construction project cost assessment method based on big data includes the following specific steps:
[0028] S1. Obtaining data related to the cost of mechanical equipment, including the type, specification, brand, model, purchase price, rental period and corresponding price, and driving cost of mechanical equipment;
[0029] S2. Based on the acquired data related to the cost of mechanical equipment, use big data analysis technology to establish a purchase cost prediction model, a rental cost prediction model, and a driving cost prediction model;
[0030] S3. Based on the established prediction models, by inputting the construction project parameters, the estimated cost of purchasing machinery and equipment, the estimated cost of renting machinery and equipment, and the estimated cost of driving machinery and equipment for the construction project are predicted, and a data calculation model is built to obtain the total estimated cost;
[0031] S4. Based on the historical machinery and equipment costs of n construction projects, and using various prediction models based on the historical machinery and equipment costs of each construction project, complete the prediction of the estimated cost of purchasing machinery and equipment, the estimated rental cost of machinery and equipment, and the estimated driving cost of machinery and equipment for the corresponding construction project, obtain the total estimated cost of the corresponding construction project, build a cost evaluation analysis model, and generate n machinery and equipment cost ratio values Pvo t , forming a data set of mechanical equipment cost ratio values;
[0032] S5. The mechanical equipment cost ratio values Pvo in the mechanical equipment cost ratio value data set are t They are all compared with the preset evaluation threshold Pt, and the cost ratio values Pvo of each mechanical equipment that exceeds the evaluation threshold Pt are screened out. t , and extract the cost ratio value Pvo of each mechanical equipment t The maximum value Pmax and the minimum value Pmin in the formula form the mechanical equipment cost ratio interval [Pmin, Pmax]. According to the mechanical equipment cost ratio interval [Pmin, Pmax] and the total estimated cost of the corresponding construction project, the predicted total cost of the corresponding project can be obtained.
[0033] S6, after screening out the cost ratio values Pvo of each mechanical equipment that exceeds the evaluation threshold Pt t After that, extract the cost ratio value Pvo of each mechanical equipment that does not exceed the evaluation threshold Pt t The quantity S is measured and compared with a preset standard quantity value;
[0034] If the quantity S does not exceed the standard quantity value, no response action will be taken;
[0035] If the quantity S exceeds the standard quantity value, a warning signal is issued and a training evaluation strategy is executed. The training evaluation strategy includes using the corresponding historical data to train each prediction model, and verifying and evaluating each prediction model based on the mean square error. After verifying that the mean square error does not exceed the preset standard value, the corresponding prediction model is output. Otherwise, training continues.
[0036] (III) Beneficial effects
[0037] The present invention provides a construction equipment cost evaluation system based on big data, which has the following beneficial effects:
[0038] 1. The present invention calculates the cost ratio of each mechanical equipment in n construction projects Pvo t , and screen out the cost ratio values Pvo of each mechanical equipment that exceeds the evaluation threshold Pt t , extract the maximum value Pmax and the minimum value Pmin, thus forming a range value, namely the mechanical equipment cost ratio interval [Pmin, Pmax]. When dealing with subsequent construction projects that have not yet started, a more accurate range assessment can be made for the mechanical equipment cost. At the same time, the efficiency of the mechanical equipment cost assessment for construction projects has also been greatly improved;
[0039] 2. When the present invention establishes a corresponding prediction model based on the acquired mechanical equipment cost-related data, it is not necessary to train and evaluate the model, but to extract the cost proportion value Pvo of each mechanical equipment that does not exceed the evaluation threshold Pt. t The quantity S is compared with the standard quantity value, and then whether to train and evaluate each prediction model is selected according to the comparison result. If the quantity S does not exceed the standard quantity value, there is no need to train and evaluate the prediction model, thereby saving the operations of training and evaluating the prediction model, which can improve the efficiency of the entire cost assessment system to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 This is a schematic diagram of the modular structure of a construction equipment cost evaluation system based on big data according to the present invention;
[0041] Figure 2 The present invention is a flowchart of the overall steps of a construction project cost assessment method based on big data. DETAILED DESCRIPTION
[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0043] Example 1: Please refer to Figure 1 This embodiment provides a construction engineering equipment cost evaluation system based on big data, which includes a data acquisition module, an analysis and modeling module, a cost estimation module, a calculation and evaluation module, and an adjustment and execution module. The application scenario of the system is aimed at the cost evaluation of mechanical equipment costs in the construction engineering cost;
[0044] Data collection module, to obtain data related to mechanical equipment costs;
[0045] The data related to the cost of mechanical equipment include the type, specification, brand, model, purchase price, rental period and corresponding price, and driving cost of mechanical equipment;
[0046] The types, specifications, brands, models, and purchase prices of mechanical equipment are obtained by crawling supplier websites and collecting market price reports. The rental periods and corresponding prices are obtained by collecting rental contract information.
[0047] The operating cost of mechanical equipment includes driver cost, fuel cost during the operation of mechanical equipment, and maintenance cost. Driver cost is estimated by collecting salary data of related industries, fuel cost is estimated by collecting historical data or cooperating with suppliers to obtain reference data under actual operation, and maintenance cost is estimated by historical maintenance records and maintenance cost provided by suppliers;
[0048] After obtaining the relevant data on mechanical equipment costs, the acquired data also needs to be cleaned and preprocessed to remove missing values, outliers and duplicate values, and unify the data format and units. At the same time, the data can be converted and standardized as needed to adapt to subsequent analysis and modeling processing.
[0049] The analysis and modeling module uses big data analysis technology to establish purchase cost prediction models, rental cost prediction models, and driving cost prediction models based on the acquired data related to the cost of mechanical equipment;
[0050] Establish a purchase cost prediction model: Based on the equipment type, specification, brand, model and purchase price as features, use regression analysis or decision tree algorithm to establish a purchase cost prediction model for predicting the purchase cost of mechanical equipment;
[0051] Therefore, the big data analysis techniques used above include regression analysis or decision tree algorithms;
[0052] Regression analysis is a statistical method used to explore and establish relationships between variables, and linear regression is a commonly used regression analysis method that fits a straight line or curve based on historical data to predict the cost of mechanical equipment;
[0053] The decision tree algorithm is a type of machine learning algorithm. Machine learning is a method of learning rules and patterns from data by building models. The decision tree algorithm is used to model and predict equipment and machinery costs.
[0054] Establish a rental cost prediction model: Based on the equipment type, specification, brand, model, rental period and corresponding price as features, use regression analysis or decision tree algorithm to establish a rental cost prediction model for predicting the rental cost of purchasing mechanical equipment. The principle of establishing a rental cost prediction model is the same as that of predicting mechanical equipment costs, so I will not elaborate on it here;
[0055] Establishing a driving cost prediction model: Based on the driving cost data of mechanical equipment, after statistical analysis, a driving cost prediction model for predicting driving costs is established using regression analysis;
[0056] Among them, statistical analysis is a descriptive statistical analysis of the data, including the calculation of statistical indicators such as mean, median, standard deviation, maximum, minimum and total, to help understand the distribution of mechanical equipment costs. The median of this application requires the cumulative sum of driver costs, fuel costs during mechanical equipment operation, and maintenance costs.
[0057] Taking a concrete mixer truck as an example, assume that based on the collected data and analytical modeling, the following results are obtained:
[0058] Reference price for purchase cost: A regression model is established based on the equipment type (concrete mixer truck), specifications, brand, and model characteristics. For example, based on historical data, it is concluded that the purchase cost is related to factors such as vehicle load capacity, rated power, and production year, and the final predicted reference price for purchase cost is RMB 500,000; Reference price for rental cost: A regression model is established based on the equipment type (concrete mixer truck), specifications, brand, and rental cycle characteristics. For example, based on the data provided by the rental company, it is concluded that the rental cost is related to factors such as rental cycle, brand, market supply and demand, and the final predicted reference price for rental cost is RMB 10,000 per month; Reference price for use cost: A comprehensive estimate is made based on the driver cost, fuel cost, and maintenance cost data. For example, based on the salary survey data of driver-related industries, vehicle fuel consumption statistics, and maintenance records, the reference price for use cost is predicted to be RMB 100,000 per year.
[0059] The cost estimation module, based on the established prediction models, predicts the estimated cost of purchasing machinery and equipment, the estimated cost of renting machinery and equipment, and the estimated cost of operating machinery and equipment for the construction project by inputting the construction project parameters, and builds a data calculation model to obtain the total estimated cost;
[0060] Among them, the construction project parameters include the required equipment type, the number of mechanical equipment and the rental period. According to the construction project parameters, the estimated cost of purchasing mechanical equipment, the estimated rental cost of mechanical equipment and the estimated driving cost of mechanical equipment can be obtained. Each cost here is the estimated sum of the corresponding costs in the entire construction project;
[0061] When obtaining the total estimated cost, the estimated cost of purchasing machinery and equipment, the estimated cost of renting machinery and equipment, and the estimated cost of driving machinery and equipment are added up. The total value is the total estimated cost. Since the units of the estimated cost of purchasing machinery and equipment, the estimated cost of renting machinery and equipment, and the estimated cost of driving machinery and equipment are the same, there is no need to perform dimensionless processing to complete the subsequent calculation operations.
[0062] The calculation and evaluation module uses various prediction models based on the historical machinery and equipment costs of n construction projects, and uses each prediction model to predict the estimated cost of purchasing machinery and equipment, the estimated cost of renting machinery and equipment, and the estimated cost of driving machinery and equipment for the corresponding construction project, obtains the total estimated cost of the corresponding construction project, builds a cost evaluation analysis model, and generates n machinery and equipment cost ratio values Pvo t , forming a data set of mechanical equipment cost ratio values;
[0063] Among them, the historical machinery and equipment costs of n construction projects are the actual total costs of purchasing machinery and equipment in several different construction projects in the past month. The actual total cost includes the purchase price, the rental period and the corresponding price, and the driving cost of the machinery and equipment, which corresponds to part of the data related to the obtained machinery and equipment costs. Since the purchase price and rental price of machinery and equipment fluctuate in different time periods, it is necessary to obtain data within one month to ensure the accuracy of the subsequent use of the entire evaluation system;
[0064] Generate mechanical equipment cost ratio value Pvo t The formula is as follows:
[0065]
[0066] In the formula, Yg t represents the total estimated cost of the corresponding construction project, Sj t represents the actual total cost of the corresponding construction project, t=1, 2, ..., n, n is a positive integer, t represents the number of the corresponding construction project, and each construction project can be marked according to actual needs to obtain different numbers to distinguish each construction project;
[0067] The resulting mechanical equipment cost ratio value data set is {Pvo 1 、Pvo 2 , …, Pvo t}.
[0068] Adjust the execution module to convert each mechanical equipment cost ratio value Pvo in the mechanical equipment cost ratio value data set t They are all compared with the preset evaluation threshold Pt, and the cost ratio values Pvo of each mechanical equipment that exceeds the evaluation threshold Pt are screened out. t, and extract the cost ratio value Pvo of each mechanical equipment t The maximum value Pmax and the minimum value Pmin in the formula form the mechanical equipment cost ratio interval [Pmin, Pmax]. According to the mechanical equipment cost ratio interval [Pmin, Pmax] and the total estimated cost of the corresponding construction project, the predicted total cost of the corresponding project can be obtained. The staff can know the mechanical equipment cost required for the construction project in advance based on the predicted total cost, which is convenient for adjusting the budget between different projects.
[0069] For example, the maximum value Pmax in the mechanical equipment cost ratio data set corresponds to Pvo 4 The minimum value Pmin in the mechanical equipment cost ratio data set corresponds to Pvo 1 , then the mechanical equipment cost ratio interval [Pmin, Pmax] = [Pvo 1 , Pvo 4 ];
[0070] The adjustment execution module also includes a verification training unit, which selects the cost ratio values Pvo of each mechanical equipment that exceeds the evaluation threshold Pt. t , extract the cost ratio value Pvo of each mechanical equipment that does not exceed the evaluation threshold Pt t The quantity S is measured and compared with a preset standard quantity value;
[0071] If the quantity S does not exceed the standard quantity value, no response action will be taken;
[0072] If the quantity S exceeds the standard quantity value, it means that there are problems with each prediction model, for example: low accuracy, a warning signal is issued, and a training evaluation strategy is executed. The training evaluation strategy includes using the corresponding historical data to train each prediction model, and verifying and evaluating each prediction model according to certain indicators, such as mean square error or determination coefficient, to ensure the accuracy and reliability of the model. Specifically, the mean square error is used for verification and evaluation. After verifying that the mean square error does not exceed the preset standard value, the corresponding prediction model is output. Otherwise, training continues.
[0073] Specifically, by counting the cost ratio values Pvo of each mechanical equipment in n construction projects t , and screen out the cost ratio values Pvo of each mechanical equipment that exceeds the evaluation threshold Pt t , extract the maximum value Pmax and the minimum value Pmin, thus forming a range value, namely the mechanical equipment cost ratio interval [Pmin, Pmax]. When dealing with subsequent construction projects that have not yet started, a more accurate range assessment can be made for the mechanical equipment cost. At the same time, the efficiency of the mechanical equipment cost assessment for construction projects has also been greatly improved;
[0074] When establishing a corresponding prediction model based on the acquired mechanical equipment cost-related data, there is no need to train and evaluate the model. Instead, the cost proportion values Pvo of each mechanical equipment that do not exceed the evaluation threshold Pt are extracted later. t The quantity S is compared with the standard quantity value, and then whether to train and evaluate each prediction model is selected according to the comparison result. If the quantity S does not exceed the standard quantity value, there is no need to train and evaluate the prediction model, thereby saving the operations of training and evaluating the prediction model, which can improve the efficiency of the entire cost assessment system to a certain extent.
[0075] Example 2: Please refer to Figure 2 Based on Example 1, this example further provides a construction project cost assessment method based on big data, which includes the following specific steps:
[0076] S1. Obtaining data related to the cost of mechanical equipment, including the type, specification, brand, model, purchase price, rental period and corresponding price, and driving cost of mechanical equipment;
[0077] S2. Based on the acquired data related to the cost of mechanical equipment, use big data analysis technology to establish a purchase cost prediction model, a rental cost prediction model, and a driving cost prediction model;
[0078] S3. Based on the established prediction models, by inputting the construction project parameters, the estimated cost of purchasing machinery and equipment, the estimated cost of renting machinery and equipment, and the estimated cost of driving machinery and equipment for the construction project are predicted, and a data calculation model is built to obtain the total estimated cost;
[0079] S4. Based on the historical machinery and equipment costs of n construction projects, and using various prediction models based on the historical machinery and equipment costs of each construction project, complete the prediction of the estimated cost of purchasing machinery and equipment, the estimated rental cost of machinery and equipment, and the estimated driving cost of machinery and equipment for the corresponding construction project, obtain the total estimated cost of the corresponding construction project, build a cost evaluation analysis model, and generate n machinery and equipment cost ratio values Pvo t , forming a data set of mechanical equipment cost ratio values;
[0080] S5. The mechanical equipment cost ratio values Pvo in the mechanical equipment cost ratio value data set are t They are all compared with the preset evaluation threshold Pt, and the cost ratio values Pvo of each mechanical equipment that exceeds the evaluation threshold Pt are screened out. t , and extract the cost ratio value Pvo of each mechanical equipment tThe maximum value Pmax and the minimum value Pmin in the formula form the mechanical equipment cost ratio interval [Pmin, Pmax]. According to the mechanical equipment cost ratio interval [Pmin, Pmax] and the total estimated cost of the corresponding construction project, the predicted total cost of the corresponding project can be obtained.
[0081] S6, after screening out the cost ratio values Pvo of each mechanical equipment that exceeds the evaluation threshold Pt t After that, extract the cost ratio value Pvo of each mechanical equipment that does not exceed the evaluation threshold Pt t The quantity S is measured and compared with a preset standard quantity value;
[0082] If the quantity S does not exceed the standard quantity value, no response action will be taken;
[0083] If the quantity S exceeds the standard quantity value, a warning signal is issued and a training evaluation strategy is executed. The training evaluation strategy includes using the corresponding historical data to train each prediction model, and verifying and evaluating each prediction model based on the mean square error. After verifying that the mean square error does not exceed the preset standard value, the corresponding prediction model is output. Otherwise, training continues.
[0084] In the application, the several formulas involved are all calculated by removing the dimensions and taking their numerical values. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The formula is set by technical personnel in this field according to actual conditions.
[0085] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.
[0086] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0087] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.
Claims
1. A construction equipment cost evaluation system based on big data, characterized in that: include: The data collection module obtains data related to the cost of mechanical equipment, and the data related to the cost of mechanical equipment includes the type, specification, brand, model, purchase price, rental period and corresponding price, and driving cost of mechanical equipment; The analysis and modeling module uses big data analysis technology to establish purchase cost prediction models, rental cost prediction models, and driving cost prediction models based on the acquired data related to the cost of mechanical equipment; The cost estimation module, based on the established prediction models, predicts the estimated cost of purchasing machinery and equipment, the estimated cost of renting machinery and equipment, and the estimated cost of operating machinery and equipment for the construction project by inputting the construction project parameters, and builds a data calculation model to obtain the total estimated cost; The calculation and evaluation module uses various prediction models based on the historical machinery and equipment costs of n construction projects, and uses each prediction model to predict the estimated cost of purchasing machinery and equipment, the estimated cost of renting machinery and equipment, and the estimated cost of driving machinery and equipment for the corresponding construction project, obtains the total estimated cost of the corresponding construction project, builds a cost evaluation analysis model, and generates n machinery and equipment cost ratio values Pvo t , forming a data set of mechanical equipment cost ratio values; Adjust the execution module to convert each mechanical equipment cost ratio value Pvo in the mechanical equipment cost ratio value data set t They are all compared with the preset evaluation threshold Pt, and the cost ratio values Pvo of each mechanical equipment that exceeds the evaluation threshold Pt are screened out. t , and extract the cost ratio value Pvo of each mechanical equipment t The maximum value Pmax and the minimum value Pmin in the formula form the mechanical equipment cost ratio interval [Pmin, Pmax]. According to the mechanical equipment cost ratio interval [Pmin, Pmax] and the total estimated cost of the corresponding construction project, the predicted total cost of the corresponding project can be obtained.
2. The construction equipment cost evaluation system based on big data according to claim 1 is characterized by: The operating costs of mechanical equipment include driver costs, fuel costs during the operation of mechanical equipment, and maintenance costs.
3. The construction equipment cost evaluation system based on big data according to claim 2 is characterized by: Establish a purchase cost prediction model: Based on the equipment type, specification, brand, model and purchase price as features, use regression analysis to establish a purchase cost prediction model; establish a rental cost prediction model: Based on the equipment type, specification, brand, model and rental period and corresponding price as features, use regression analysis to establish a rental cost prediction model; establish a driving cost prediction model: Based on the driving cost data of mechanical equipment, after statistical analysis, use regression analysis to establish a driving cost prediction model.
4. The construction equipment cost evaluation system based on big data according to claim 3 is characterized by: Construction project parameters include the type of equipment required, the quantity of machinery and equipment, and the lease period.
5. The construction equipment cost evaluation system based on big data according to claim 4 is characterized by: The historical machinery and equipment costs of n construction projects are the actual total costs of purchasing machinery and equipment in several different construction projects within one month, and the actual total costs include the purchase price, leasing period and corresponding price, and the driving cost of the machinery and equipment, which corresponds to part of the data related to the obtained machinery and equipment costs.
6. The construction equipment cost evaluation system based on big data according to claim 5 is characterized by: Generate mechanical equipment cost ratio value Pvo t The formula used is as follows: In the formula, Yg t represents the total estimated cost of the corresponding construction project, Sj t represents the actual total cost of the corresponding construction project, t=1, 2, ..., n, n is a positive integer, and t represents the number of the corresponding construction project.
7. The construction equipment cost evaluation system based on big data according to claim 6 is characterized by: The resulting mechanical equipment cost ratio value data set is {Pvo1, Pvo2, …, Pvo t }.
8. The construction equipment cost evaluation system based on big data according to claim 7 is characterized by: The adjustment execution module also includes a verification training unit, which selects the cost ratio value Pvo of each mechanical equipment that exceeds the evaluation threshold Pt. t After that, extract the cost ratio value Pvo of each mechanical equipment that does not exceed the evaluation threshold Pt t The quantity S is measured and compared with a preset standard quantity value; If the quantity S does not exceed the standard quantity value, no response action will be taken; If the quantity S exceeds the standard quantity value, a warning signal is issued and the training evaluation strategy is executed.
9. The construction equipment cost evaluation system based on big data according to claim 8 is characterized by: The training and evaluation strategy includes using the corresponding historical data to train each prediction model, and verifying and evaluating each prediction model based on the mean square error. After verifying that the mean square error does not exceed the preset standard value, the corresponding prediction model is output, otherwise, training continues; wherein the corresponding historical data include the actual purchase price, leasing period and corresponding price, and the driving cost of mechanical equipment.
Citation Information
Patent Citations
A Big Data-Based Construction Project Cost Assessment System
CN111415205B