Building engineering cost management system and method based on big data

Abstract

The invention discloses a building engineering cost management system and method based on big data. The method comprises the steps of obtaining engineering stage information according to building engineering process information; obtaining stage cost information according to the engineering stage information, establishing a price prediction model through the stage cost information by using a big data technology, and obtaining primary optimal stage cost information; transaction companies are selected and acquired according to the optimal cost by using a big data technology, the transaction risk of each transaction company is evaluated, and the cost information of the optimal stage is acquired; obtaining optimal engineering cost information according to the optimal stage cost information, establishing a BIM model, updating the BIM model in real time, and adjusting the optimal stage cost information; obtaining actual engineering cost information, comparing the optimal engineering cost information with the actual engineering cost information to obtain cost difference information, and adjusting the cost information of the optimal stage; under the condition that the engineering cost quality is guaranteed, the cost input is reduced to the maximum extent, and the maximum benefits of enterprises are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of construction cost management, and in particular to a construction project cost management system and method based on big data. Background Art

[0002] In recent years, the cost control of construction projects is an important prerequisite for ensuring the sustainable and healthy development of construction enterprises. In the information age, computer technology has an important guiding significance for the development of construction project cost control, which can greatly improve the quality and efficiency of construction project cost control. Therefore, combining computer technology with cost control in construction enterprises can effectively promote the development of construction enterprises.

[0003] At present, the Chinese invention patent with publication number CN116167576A provides a BIM-based housing construction cost control method and system. Although it realizes the overall construction cost control by controlling the cost of each stage of construction, and can complete cost control while controlling efficiency, effectively achieving the balance between efficiency and cost, it does not collect and analyze data on construction costs, lacks information asymmetry, and cannot guarantee the lowest cost investment in construction within a reasonable range, and cannot maximize the benefits of the enterprise. Summary of the invention

[0004] The technical problem solved by the present invention is that the existing technology does not collect and analyze data on construction costs, lacks information asymmetry, cannot guarantee the lowest cost investment in construction within a reasonable range, and cannot maximize the benefits of the enterprise.

[0005] In order to solve the above technical problems, in a first aspect, the present invention provides a construction project cost management method based on big data, comprising the following steps: Step S1, obtaining construction engineering process information according to the construction engineering process file, dividing the construction engineering process information into construction stages, and obtaining engineering stage information; Step S2, obtaining stage cost information from the historical building database according to the project stage information, obtaining cost selection data of each cost type through the stage cost information using big data technology, establishing a price prediction model according to the cost selection data, predicting the cost price of different periods using the price prediction model, and evaluating the cost price and cost quality respectively, and obtaining the primary optimal stage cost information according to the evaluation results; Step S3, using big data technology to select and obtain trading companies based on the best cost, and evaluate the trading risks of each trading company based on the historical trading records of the entire network of each trading company, and put the trading companies with a trading risk index less than or equal to the expected threshold into the trading whitelist, and determine the final trading company through the decision of the marketing department, and obtain the optimal stage cost information based on the final trading company; Step S4, obtaining optimal project cost information according to the optimal stage cost information, establishing a BIM model using the construction project process information and the optimal project cost information, and updating the BIM model in real time during the construction process of the construction project. If any cost parameter in the BIM model is greater than an expected threshold, a warning message is generated according to the cost parameter and sent to the optimal cost module, and the optimal stage cost information is adjusted in real time; Step S5, after the construction of the building project is completed, the actual project cost information is obtained according to the BIM model, the optimal project cost information is compared with the actual project cost information, the cost difference information is obtained, and the cost difference information is analyzed to obtain the reason for the cost difference, and the optimal stage cost information is adjusted according to the reason for the cost difference, and the adjusted optimal stage cost information is stored in the historical building database; As a preferred solution of the construction project cost management method based on big data described in the present invention, the step S2 specifically includes the following steps: Step S201, matching the historical optimal stage cost information in the historical building database according to the project stage number of the project stage information, if the match is successful, updating the historical optimal stage cost information according to the project date, and defining the updated historical optimal stage cost information as the optimal stage cost information of this construction project; Step S202, if the matching fails, matching the stage cost information according to the project stage number, the stage cost information includes the first stage cost information, the second stage cost information and the third stage cost information, the first stage cost information includes the construction material cost information, the second stage cost information includes the construction labor cost information, and the third stage cost information includes the construction equipment cost information; Step S203, obtaining engineering cost information from various building network information platforms using big data crawler technology according to the stage cost information, and obtaining cost selection from the engineering cost information according to the cost type in the stage cost information, wherein the cost type represents a class of different engineering cost inputs having the same engineering function, and the cost selection represents different engineering input selections having the same engineering function; Step S204, establishing a price prediction model for each cost option using machine learning technology based on the project cost information, and obtaining the cost price of each cost option in each period through the price prediction model; Step S205, obtaining the price evaluation value of the cost options for each period according to the standard price of each cost option, obtaining the quality evaluation value of each cost option according to the standard quality of each cost option, performing weighted calculation on the price evaluation value and the quality evaluation value of each cost option, obtaining the cost evaluation value of each period of each cost option, and screening out the cost option with the highest cost evaluation value in the same cost type, defining it as the optimal cost option, and obtaining the primary optimal stage cost information; As a preferred solution of the construction project cost management method based on big data described in the present invention, step S3 specifically includes the following steps: Step S301, using big data crawler technology to obtain each trading company selected with the best cost and the entire network historical transaction records of the trading company according to each optimal cost selection; Step S302, obtaining historical risk transactions in the historical transaction records of the entire network, and obtaining risk indexes according to the risk types of the historical risk transactions, and performing weighted calculation on the risk indexes of the various historical risk transactions to obtain transaction risk indexes, wherein the risk types and risk indexes are in a one-to-one correspondence, and the weights for weighted processing are determined according to the risk types of the various historical risk transactions; Step S303, each trading company whose trading risk index is less than or equal to the expected threshold is included in the trading white list, and the marketing department determines the final trading company according to the trading white list; Step S304, the final transaction company is included in the primary optimal stage cost information according to the cost selection, and the cost procurement period is determined according to the optimal cost selection to obtain the optimal stage cost information; As a preferred solution of the construction project cost management method based on big data described in the present invention, the step S4 specifically includes the following steps: Step S401, merging the cost information of each optimal stage to obtain the optimal engineering cost information; Step S402, establishing a BIM model according to the construction engineering process information and the optimal engineering cost information; Step S403, performing engineering construction according to the BIM model, and updating the BIM model in real time according to the progress of the engineering construction; Step S404: if any cost parameter in the BIM model is greater than an expected threshold, the cost parameter is defined as an abnormal cost parameter, an optimal cost option is obtained according to the abnormal cost parameter, a warning message of the optimal cost option is generated, and the warning message is sent to an optimal cost module, and the optimal cost module adjusts the optimal stage cost information according to the warning message; As a preferred solution of the construction project cost management method based on big data described in the present invention, step S5 specifically includes the following steps: Step S501, after the construction of the building project is completed, actual project cost information is obtained according to various cost parameters in the BIM model; Step S502, comparing the actual engineering cost information with the optimal engineering cost information according to the optimal cost selection, obtaining the difference between the optimal cost selections, and generating cost difference information; Step S503, the construction personnel analyze the cost difference information, obtain the cost difference reason, adjust the corresponding optimal stage cost information according to the cost difference reason, and store the optimal stage cost information in the historical building database; As a preferred solution of the construction project cost management method based on big data described in the present invention, step S204 specifically includes: Obtain relevant price fluctuation factors according to the price fluctuations of each cost option in the engineering cost information, input the price fluctuation factors and the cost price into a machine learning model, train the model with the price fluctuation factors as input and the cost price as output until the model fit reaches an expected threshold, and obtain a price prediction model for the cost option; As a preferred solution of the construction project cost management method based on big data described in the present invention, the use of big data crawler technology to obtain project cost information from various construction network information platforms includes: Obtain the name of each engineering stage according to the stage cost information, extract the URL of each building network information platform, generate an HTTP request according to the name and URL of each engineering stage, send the HTTP request to the corresponding building network information platform, obtain the request response of the building network information platform, and use regular expressions to extract the engineering cost information of the engineering stage, wherein the engineering cost information includes cost selection, cost price, cost date and cost fluctuation related factors of each cost type of the engineering stage; As a preferred solution of the construction project cost management method based on big data described in the present invention, step S402 specifically includes the following steps: Step S4021, obtaining information of each engineering component according to the construction engineering process information and the optimal engineering cost information, wherein the engineering component information includes the shape of the engineering component, the size of the engineering component, the material of the engineering component, the cost of the engineering component, the construction process of the engineering component, and the connection method of the engineering component; Step S4022, using the engineering component information to build each engineering component according to the construction engineering process, and assigning corresponding engineering component attributes to each engineering component according to the corresponding engineering component information, to obtain a primary BIM model; Step S4043: perform collision detection on the primary BIM model, optimize the primary BIM model according to the detection result, and obtain the BIM model.

[0006] In a second aspect, the present invention provides a construction project cost management system based on big data, including a construction data acquisition module, an optimal construction cost module, a construction model module, and a construction cost analysis module; The building data acquisition module is used to acquire project phase information based on the construction project process file and to acquire project cost information from each building network information platform; The optimal construction cost module is used to obtain the optimal stage cost information according to the project stage information by using big data technology, and cross-merge the optimal stage cost information to obtain the optimal project cost information, and obtain warning information and cost difference information, and adjust the optimal stage cost information according to the warning information and the cost difference information; The building model module is used to establish a BIM model according to the construction process information and the optimal project cost information, and to update the BIM model in real time according to the construction progress, obtain abnormal cost parameters and generate warning information according to the abnormal cost parameters and send it to the optimal building cost module; The construction cost analysis module is used to obtain actual project cost information after construction is completed, compare the optimal project cost information with the actual project cost information, obtain cost difference information, analyze the cost difference information to obtain the reason for the cost difference, and send the cost difference information to the optimal construction cost module.

[0007] The beneficial effects of the present invention are as follows: the present invention utilizes big data technology to obtain engineering cost information based on stage cost information, and establishes a price prediction model for cost options in the engineering cost information, respectively obtains cost prices for different periods of each cost option, and evaluates the cost price and cost quality of the cost options, and obtains primary optimal stage cost information based on the cost option with the highest cost evaluation value, thereby minimizing cost input while ensuring engineering cost quality, thereby ensuring maximum benefits for the enterprise.

[0008] Big data technology is used to acquire and analyze the historical transaction records of the entire network of trading companies, obtain the transaction risk index of each trading company, and select the final trading company based on the transaction risk index, thereby ensuring transaction security and transaction quality during procurement costs and reducing ineffective cost investment caused by transaction risks.

[0009] Establish a BIM model, adjust the optimal stage cost information in real time according to the cost parameters of the BIM model, complete real-time control of project costs, and help engineering personnel directly and conveniently understand the details of project costs.

[0010] According to the construction project process information, the information of each project stage is obtained, and the optimal stage cost information of each project stage is obtained using big data technology. The optimal stage cost information is stored in the historical building database for use in the next project, saving the computing power resources and manpower and material resources invested in obtaining the optimal stage cost information again in the same project stage. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A basic flow chart of a construction project cost management method based on big data provided by one embodiment of the present invention; Figure 2 A basic flow chart of a construction project cost management system based on big data is provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0012] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0013] Example 1, reference Figure 1 , as an embodiment of the present invention, provides a construction project cost management method based on big data, comprising the following steps: Step S1, obtaining construction engineering process information according to the construction engineering process file, dividing the construction engineering process information into construction stages, and obtaining engineering stage information; Step S2, obtaining stage cost information from the historical building database according to the project stage information, obtaining cost selection data of each cost type through the stage cost information using big data technology, establishing a price prediction model according to the cost selection data, predicting the cost price of different periods using the price prediction model, and evaluating the cost price and cost quality respectively, and obtaining the primary optimal stage cost information according to the evaluation results; Step S3, using big data technology to select and obtain trading companies based on the best cost, and evaluate the trading risks of each trading company based on the historical trading records of the entire network of each trading company, and put the trading companies with a trading risk index less than or equal to the expected threshold into the trading whitelist, and determine the final trading company through the decision of the marketing department, and obtain the optimal stage cost information based on the final trading company; Step S4, obtaining optimal project cost information according to the optimal stage cost information, establishing a BIM model using the construction project process information and the optimal project cost information, and updating the BIM model in real time during the construction process of the construction project. If any cost parameter in the BIM model is greater than an expected threshold, a warning message is generated according to the cost parameter and sent to the optimal cost module, and the optimal stage cost information is adjusted in real time; Step S5, after the construction of the building project is completed, the actual project cost information is obtained according to the BIM model, the optimal project cost information is compared with the actual project cost information, the cost difference information is obtained, and the cost difference information is analyzed to obtain the reason for the cost difference, and the optimal stage cost information is adjusted according to the reason for the cost difference, and the adjusted optimal stage cost information is stored in the historical building database.

[0014] The engineering stage information includes engineering materials, construction equipment and construction process of this engineering stage; The big data technology refers to computer technology that mines the laws and conclusions between massive data through data collection, data storage, data management, data analysis and mining, data presentation, etc. The BIM model is a building model established based on various relevant information data of the construction project.

[0015] In this embodiment, big data technology is used to obtain project cost information based on stage cost information, and a price prediction model is established for the cost options in the project cost information, and the cost prices of different periods of each cost option are obtained respectively, and the cost prices and cost quality of the cost options are evaluated. The primary optimal stage cost information is obtained according to the cost option with the highest cost evaluation value, and the cost input is reduced to the greatest extent while ensuring the quality of the project cost, thereby ensuring the maximum benefits of the enterprise; Use big data technology to obtain and analyze the historical transaction records of the entire network of trading companies, obtain the transaction risk index of each trading company, and select the final trading company based on the transaction risk index, thereby ensuring the transaction security and transaction quality during procurement costs and reducing the ineffective cost investment caused by transaction risks; Establish a BIM model, adjust the optimal stage cost information in real time according to the cost parameters of the BIM model, complete the real-time control of project costs, and help engineering personnel directly and conveniently understand the details of project costs; According to the construction project process information, the information of each project stage is obtained, and the optimal stage cost information of each project stage is obtained using big data technology. The optimal stage cost information is stored in the historical building database for use in the next project, saving the computing power resources and manpower and material resources invested in obtaining the optimal stage cost information again in the same project stage.

[0016] The step S2 specifically includes the following steps: Step S201, matching the historical optimal stage cost information in the historical building database according to the project stage number of the project stage information, if the match is successful, updating the historical optimal stage cost information according to the project date, and defining the updated historical optimal stage cost information as the optimal stage cost information of this construction project; Step S202, if the matching fails, matching the stage cost information according to the project stage number, the stage cost information includes the first stage cost information, the second stage cost information and the third stage cost information, the first stage cost information includes the construction material cost information, the second stage cost information includes the construction labor cost information, and the third stage cost information includes the construction equipment cost information; Step S203, obtaining engineering cost information from various building network information platforms using big data crawler technology according to the stage cost information, and obtaining cost selection from the engineering cost information according to the cost type in the stage cost information, wherein the cost type represents a class of different engineering cost inputs having the same engineering function, and the cost selection represents different engineering input selections having the same engineering function; Step S204, establishing a price prediction model for each cost option using machine learning technology based on the project cost information, and obtaining the cost price of each cost option in each period through the price prediction model; Step S205, obtaining the price evaluation value of the cost options for each period according to the standard price of each cost option, obtaining the quality evaluation value of each cost option according to the standard quality of each cost option, performing weighted calculation on the price evaluation value and the quality evaluation value of each cost option, obtaining the cost evaluation value of each period of each cost option, and screening out the cost option with the highest cost evaluation value in the same cost type, defining it as the optimal cost option, and obtaining the primary optimal stage cost information; The said construction network information platform includes construction information platforms such as China Engineering Construction Information Network, Civil Engineering Network, Construction Information Network, Construction Engineering Cost Information Network and Construction Company Information Network; The machine learning model is a method that can learn from data to automatically discover laws and patterns in the data, and use these laws and patterns to make predictions and decisions.

[0017] In this embodiment, big data technology is used to obtain project cost information from the construction network information platform, and a machine learning model is used to obtain the optimal stage cost information, thereby minimizing cost investment while ensuring the quality of project costs, thereby ensuring the maximum benefits for the enterprise.

[0018] The step S3 specifically comprises the following steps: Step S301, using big data crawler technology to obtain each trading company selected with the best cost and the entire network historical transaction records of the trading company according to each optimal cost selection; Step S302, obtaining historical risk transactions in the historical transaction records of the entire network, and obtaining a risk index according to the risk type of the historical risk transactions, and performing weighted calculation on the risk index of each historical risk transaction to obtain a transaction risk index, wherein the risk type and the risk index are in a one-to-one correspondence, and the weight for weighted processing is determined according to the risk type of each historical risk transaction; Step S303, listing each transaction company whose transaction risk index is less than or equal to the expected threshold into a transaction whitelist, and the marketing department determines the final transaction company according to the transaction whitelist; Step S304, the final transaction company is included in the primary optimal stage cost information according to the cost selection, and the cost procurement period is determined according to the best cost selection to obtain the optimal stage cost information.

[0019] The risk types include market risk, credit risk, liquidity risk, operational risk and legal risk.

[0020] In this embodiment, the final transaction company and the optimal stage cost information are obtained based on the historical transaction records of each transaction company in the entire network, which ensures the transaction security and transaction quality when purchasing costs and reduces the ineffective cost investment caused by transaction risks.

[0021] The step S4 specifically comprises the following steps: Step S401, merging the cost information of each optimal stage to obtain the optimal engineering cost information; Step S402, establishing a BIM model according to the construction engineering process information and the optimal engineering cost information; Step S403, performing engineering construction according to the BIM model, and updating the BIM model in real time according to the progress of the engineering construction; Step S404: If any cost parameter in the BIM model is greater than an expected threshold, the cost parameter is defined as an abnormal cost parameter, the best cost option is obtained according to the abnormal cost parameter, a warning message of the best cost option is generated, and the warning message is sent to the optimal cost module, and the optimal cost module adjusts the optimal stage cost information according to the warning message.

[0022] In this embodiment, by establishing a BIM model to adjust the optimal stage cost information in real time, real-time control of project costs is achieved, project cost problems are discovered and solved in a timely manner, and it is beneficial for engineering personnel to directly and conveniently understand the project cost details and project construction details.

[0023] The step S5 specifically comprises the following steps: Step S501, after the construction of the building project is completed, actual project cost information is obtained according to various cost parameters in the BIM model; Step S502, comparing the actual engineering cost information with the optimal engineering cost information according to the optimal cost selection, obtaining the difference between the optimal cost selections, and generating cost difference information; Step S503: The construction personnel analyze the cost difference information, obtain the reasons for the cost difference, adjust the corresponding optimal stage cost information according to the reasons for the cost difference, and store the optimal stage cost information in the historical building database.

[0024] In this embodiment, by comparing the actual project cost information with the optimal project cost information, obtaining the cost difference information and the reasons for the cost difference, and adjusting the optimal stage cost information according to the reasons for the cost difference, it is helpful to reduce the gap between the expected cost and the actual cost and accurately manage the cost budget.

[0025] The step S204 specifically includes: Relevant price fluctuation factors are obtained according to the price fluctuations of each cost option in the engineering cost information, and the price fluctuation factors and the cost price are input into the machine learning model. The price fluctuation factors are used as input and the cost price is used as output for training until the model fit reaches the expected threshold, thereby obtaining a price prediction model for the cost option.

[0026] The model fit indicates the degree of consistency between the expected data obtained through the model and the actual data; In this embodiment, the expected threshold value of the model fit is 0.95; In this embodiment, the price prediction model is used to predict the price trend of each engineering option in real time, ensuring that engineering personnel understand the price trend of the engineering option in real time, providing specific price information for determining the primary optimal stage cost information, which is conducive to ensuring the low-cost characteristics of the primary optimal stage cost information.

[0027] Using big data crawler technology to obtain engineering cost information from various construction network information platforms includes: The name of each project stage is obtained according to the stage cost information, the URL of each building network information platform is extracted, an HPPT request is generated according to the name and URL of each project stage, the HTTP request is sent to the corresponding building network information platform, the request response of the building network information platform is obtained, and the project cost information of the project stage is extracted using a regular expression. The project cost information includes the cost selection, cost price, cost date and cost fluctuation related factors of each cost type of the project stage.

[0028] The URL is a uniform resource locator, which is a unique identifier used to locate a resource; The HTTP request is initiated by the client and sends a request for a specific resource to the server.

[0029] In this embodiment, big data technology is used to obtain project cost information, which provides detailed and specific data support for establishing a price prediction model, is conducive to real-time understanding of the price trend of each project selection, and ensures reasonable project cost investment.

[0030] The step S402 specifically includes the following steps: Step S4021, obtaining information of each engineering component according to the construction engineering process information and the optimal engineering cost information, wherein the engineering component information includes the shape of the engineering component, the size of the engineering component, the material of the engineering component, the cost of the engineering component, the construction process of the engineering component, and the connection method of the engineering component; Step S4022, using the engineering component information to build each engineering component according to the construction engineering process, and assigning corresponding engineering component attributes to each engineering component according to the corresponding engineering component information, to obtain a primary BIM model; Step S4043: perform collision detection on the primary BIM model, optimize the primary BIM model according to the detection result, and obtain the BIM model.

[0031] In this embodiment, a BIM model is established using construction project process information and optimal project cost information to achieve real-time control of project costs, and it is beneficial for engineering personnel to directly and conveniently understand the details of project costs.

[0032] Example 2, reference Figure 2 , which is another embodiment of the present invention, which is different from the first embodiment in that it provides a construction project cost management system based on big data, characterized in that it includes a construction data acquisition module, an optimal construction cost module, a construction model module, and a construction cost analysis module; The building data acquisition module is used to acquire project phase information based on the construction project process file and to acquire project cost information from each building network information platform; The optimal construction cost module is used to obtain the optimal stage cost information according to the project stage information by using big data technology, and cross-merge the optimal stage cost information to obtain the optimal project cost information, and obtain warning information and cost difference information, and adjust the optimal stage cost information according to the warning information and the cost difference information; The building model module is used to establish a BIM model according to the construction process information and the optimal project cost information, and to update the BIM model in real time according to the construction progress, obtain abnormal cost parameters and generate warning information according to the abnormal cost parameters and send it to the optimal building cost module; The construction cost analysis module is used to obtain actual project cost information after construction is completed, compare the optimal project cost information with the actual project cost information, obtain cost difference information, analyze the cost difference information to obtain the reason for the cost difference, and send the cost difference information to the optimal construction cost module.

[0033] In this embodiment, big data technology is used to obtain project cost information based on stage cost information, and a price prediction model is established for the cost options in the project cost information, and the cost prices of different periods of each cost option are obtained respectively, and the cost prices and cost quality of the cost options are evaluated. The primary optimal stage cost information is obtained according to the cost option with the highest cost evaluation value, and the cost input is reduced to the greatest extent while ensuring the quality of the project cost, thereby ensuring the maximum benefits of the enterprise; Use big data technology to obtain and analyze the historical transaction records of the entire network of trading companies, obtain the transaction risk index of each trading company, and select the final trading company based on the transaction risk index, thereby ensuring the transaction security and transaction quality during procurement costs and reducing the ineffective cost investment caused by transaction risks; Establish a BIM model, adjust the optimal stage cost information in real time according to the cost parameters of the BIM model, complete the real-time control of project costs, and help engineering personnel directly and conveniently understand the details of project costs; According to the construction project process information, the information of each project stage is obtained, and the optimal stage cost information of each project stage is obtained using big data technology. The optimal stage cost information is stored in the historical building database for use in the next project, saving the computing power resources and manpower and material resources invested in obtaining the optimal stage cost information again in the same project stage.

[0034] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0035] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A construction project cost management method based on big data, characterized in that: The following steps are involved: Step S1, obtaining construction engineering process information according to the construction engineering process file, dividing the construction engineering process information into construction stages, and obtaining engineering stage information; Step S2, obtaining stage cost information from the historical building database according to the project stage information, obtaining cost selection data of each cost type through the stage cost information using big data technology, establishing a price prediction model according to the cost selection data, predicting the cost price of different periods using the price prediction model, and evaluating the cost price and cost quality respectively, and obtaining the primary optimal stage cost information according to the evaluation results; Step S3, using big data technology to select and obtain trading companies based on the best cost, and evaluate the trading risks of each trading company based on the historical trading records of the entire network of each trading company, and put the trading companies with a trading risk index less than or equal to the expected threshold into the trading whitelist, and determine the final trading company through the decision of the marketing department, and obtain the optimal stage cost information based on the final trading company; Step S4, obtaining optimal project cost information according to the optimal stage cost information, establishing a BIM model using the construction project process information and the optimal project cost information, and updating the BIM model in real time during the construction process of the construction project. If any cost parameter in the BIM model is greater than an expected threshold, a warning message is generated according to the cost parameter and sent to the optimal cost module, and the optimal stage cost information is adjusted in real time; Step S5, obtaining actual project cost information according to the BIM model, comparing the optimal project cost information with the actual project cost information, obtaining cost difference information, analyzing the cost difference information, obtaining the reason for the cost difference, adjusting the optimal stage cost information according to the reason for the cost difference, and storing the adjusted optimal stage cost information in the historical building database.

2. A construction project cost management method based on big data as claimed in claim 1, characterized in that: The step S2 specifically includes the following steps: Step S201, matching the historical optimal stage cost information in the historical building database according to the project stage number of the project stage information, if the match is successful, updating the historical optimal stage cost information according to the project date, and defining the updated historical optimal stage cost information as the optimal stage cost information of this construction project; Step S202, if the matching fails, matching the stage cost information according to the project stage number, the stage cost information includes the first stage cost information, the second stage cost information and the third stage cost information, the first stage cost information includes the construction material cost information, the second stage cost information includes the construction labor cost information, and the third stage cost information includes the construction equipment cost information; Step S203, obtaining engineering cost information from various building network information platforms using big data crawler technology according to the stage cost information, and obtaining cost selection from the engineering cost information according to the cost type in the stage cost information, wherein the cost type represents a class of different engineering cost inputs having the same engineering function, and the cost selection represents different engineering input selections having the same engineering function; Step S204, establishing a price prediction model for each cost option using machine learning technology based on the project cost information, and obtaining the cost price of each cost option in each period through the price prediction model; Step S205: Obtain the price evaluation value of the cost options for each period according to the standard price of each cost option, obtain the quality evaluation value of each cost option according to the standard quality of each cost option, perform weighted calculation on the price evaluation value and quality evaluation value of each cost option, obtain the cost evaluation value of each cost option for each period, and screen out the cost option with the highest cost evaluation value in the same cost type, define it as the optimal cost option, and obtain the primary optimal stage cost information.

3. A construction project cost management method based on big data as claimed in claim 1, characterized in that: The step S3 specifically comprises the following steps: Step S301, using big data crawler technology to obtain each trading company selected with the best cost and the entire network historical transaction records of the trading company according to each optimal cost selection; Step S302, obtaining historical risk transactions in the historical transaction records of the entire network, and obtaining risk indexes according to the risk types of the historical risk transactions, and performing weighted calculation on the risk indexes of the various historical risk transactions to obtain transaction risk indexes, wherein the risk types and risk indexes are in a one-to-one correspondence, and the weights for weighted processing are determined according to the risk types of the various historical risk transactions; Step S303, each trading company whose trading risk index is less than or equal to the expected threshold is included in the trading white list, and the marketing department determines the final trading company according to the trading white list; Step S304, the final transaction company is included in the primary optimal stage cost information according to the cost selection, and the cost procurement period is determined according to the best cost selection to obtain the optimal stage cost information.

4. A construction project cost management method based on big data as claimed in claim 1, characterized in that: The step S4 specifically comprises the following steps: Step S401, merging the cost information of each optimal stage to obtain the optimal engineering cost information; Step S402, establishing a BIM model according to the construction engineering process information and the optimal engineering cost information; Step S403, performing engineering construction according to the BIM model, and updating the BIM model in real time according to the progress of the engineering construction; Step S404: If any cost parameter in the BIM model is greater than an expected threshold, the cost parameter is defined as an abnormal cost parameter, the best cost option is obtained according to the abnormal cost parameter, a warning message of the best cost option is generated, and the warning message is sent to the optimal cost module, and the optimal cost module adjusts the optimal stage cost information according to the warning message.

5. The construction project cost management method based on big data as claimed in claim 1, characterized in that: The step S5 specifically comprises the following steps: Step S501, after the construction of the building project is completed, actual project cost information is obtained according to various cost parameters in the BIM model; Step S502, comparing the actual engineering cost information with the optimal engineering cost information according to the optimal cost selection, obtaining the difference between the optimal cost selections, and generating cost difference information; Step S503: The construction personnel analyze the cost difference information, obtain the reasons for the cost difference, adjust the corresponding optimal stage cost information according to the reasons for the cost difference, and store the optimal stage cost information in the historical building database.

6. A construction project cost management method based on big data as claimed in claim 2, characterized in that: The step S204 specifically includes: Relevant price fluctuation factors are obtained according to the price fluctuations of each cost option in the engineering cost information, and the price fluctuation factors and the cost price are input into the machine learning model. The price fluctuation factors are used as input and the cost price is used as output for training until the model fit reaches the expected threshold, thereby obtaining a price prediction model for the cost option.

7. A construction project cost management method based on big data as claimed in claim 1, characterized in that: Using big data crawler technology to obtain engineering cost information from various construction network information platforms includes: The name of each project stage is obtained according to the stage cost information, the URL of each building network information platform is extracted, an HPPT request is generated according to the name and URL of each project stage, the HTTP request is sent to the corresponding building network information platform, the request response of the building network information platform is obtained, and the project cost information of the project stage is extracted using a regular expression. The project cost information includes the cost selection, cost price, cost date and cost fluctuation related factors of each cost type of the project stage.

8. A construction project cost management method based on big data as claimed in claim 4, characterized in that: The step S402 specifically includes the following steps: Step S4021, obtaining information of each engineering component according to the construction engineering process information and the optimal engineering cost information, wherein the engineering component information includes the shape of the engineering component, the size of the engineering component, the material of the engineering component, the cost of the engineering component, the construction process of the engineering component, and the connection method of the engineering component; Step S4022, using the engineering component information to build each engineering component according to the construction engineering process, and assigning corresponding engineering component attributes to each engineering component according to the corresponding engineering component information, to obtain a primary BIM model; Step S4043: perform collision detection on the primary BIM model, optimize the primary BIM model according to the detection result, and obtain the BIM model.

9. A construction project cost management system based on big data, characterized in that: It includes building data acquisition module, optimal building cost module, building model module and building cost analysis module; The building data acquisition module is used to acquire project phase information based on the construction project process file and to acquire project cost information from each building network information platform; The optimal construction cost module is used to obtain the optimal stage cost information according to the project stage information by using big data technology, and cross-merge the optimal stage cost information to obtain the optimal project cost information, and obtain warning information and cost difference information, and adjust the optimal stage cost information according to the warning information and the cost difference information; The building model module is used to establish a BIM model according to the construction process information and the optimal project cost information, and to update the BIM model in real time according to the construction progress, obtain abnormal cost parameters and generate warning information according to the abnormal cost parameters and send it to the optimal building cost module; The construction cost analysis module is used to obtain actual project cost information after construction is completed, compare the optimal project cost information with the actual project cost information, obtain cost difference information, analyze the cost difference information to obtain the reason for the cost difference, and send the cost difference information to the optimal construction cost module.

Images