Engineering cost risk monitoring method and engineering cost management platform

Abstract

The invention discloses a project cost risk monitoring method and a project cost management platform, and the method comprises the steps: S1, carrying out the real-time collection and standardization processing of multi-source data: collecting dynamic data in real time through an Internet of Things device at a construction site, carrying out the butt joint of a design drawing, a financial system and the like, obtaining static data, and employing a data cleaning, conversion and integration technology; s2, carrying out risk factor identification and correlation analysis based on a knowledge graph; s3, implementing risk quantitative prediction and early warning driven by artificial intelligence; s4, real-time monitoring and automatic verification of contract performance of blockchain enabling are realized; s5, providing dynamic cost adjustment and optimization decision support; through real-time collection and standardization processing of multi-source data, data islands of all parties participating in a project are broken, and accuracy, integrity and timeliness of key data such as construction progress and cost expenditure are ensured. Based on big data analysis and artificial intelligence prediction, more accurate risk assessment and cost prediction are provided for project managers.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of engineering cost management, and particularly relates to an engineering cost risk monitoring method and an engineering cost management platform. BACKGROUND

[0002] Under the traditional engineering cost management system, there are many severe challenges: serious data island phenomenon: project participants (owners, design units, construction units, supervision units, cost consulting units, etc.) use their own independent information systems, which leads to the fact that key data such as engineering progress, cost expenditure, material price, design change, etc. cannot be shared and interacted in real time. According to industry research, about 60% of projects have cost disputes caused by inconsistent data, and the average additional cost of each project caused by data problems is about 8% to 12%. For example, in a large commercial complex project, the actual completed engineering quantity statistics of a certain stage of the construction party and the owner party differ by 15%, and the two parties spend a lot of time and manpower to check, which delays the progress of engineering settlement and increases the cost of funds.

[0003] The existing risk monitoring means mostly rely on manual regular inspection and experience judgment, and it is difficult to capture and warn dynamic risk factors such as sudden fluctuations in material prices, changes in construction technology, adjustments in policies and regulations in real time. For the fulfillment of key clauses such as engineering progress, quality, and payment conditions in the contract, there is a lack of effective real-time monitoring and automatic verification mechanism. In most cases, only after the event, through manual checking of paper documents or scattered electronic documents, human errors and fraud are prone to occur.

[0004] When engineering cost disputes occur, due to the lack of reliable evidence chain support, it is difficult for all parties to reach an agreement on responsibility identification and compensation amount. The traditional paper or centralized electronic storage data is easy to be tampered with, and its authenticity and integrity are difficult to be effectively guaranteed at the legal level. Although some current engineering cost management systems try to introduce information technology, they only stay at the level of data recording and simple report generation, and cannot fundamentally solve the above-mentioned problems. With the acceleration of the digital transformation of the construction industry, there is an urgent need for an innovative and intelligent engineering cost risk monitoring method and an efficient management platform to improve the overall management level and economic benefits of the industry. Therefore, in view of the above problems, the present application provides an engineering cost risk monitoring method and an engineering cost management platform. SUMMARY

[0005] The purpose of the present application is to at least solve one of the technical problems existing in the prior art, provide an engineering cost risk monitoring method and an engineering cost management platform, through multi-source data real-time collection and standardized processing, break the data island of all parties involved in the project, and ensure the accuracy, integrity and timeliness of key data such as construction progress and cost expenditure. Based on big data analysis and artificial intelligence prediction, more accurate risk assessment and cost prediction are provided for project managers, effectively reducing the decision-making error rate.

[0006] The present application also provides an engineering cost management platform with the above-mentioned engineering cost risk monitoring method, which integrates big data collection, artificial intelligence analysis and blockchain evidence storage modules, comprising the following steps:

[0007] S1, multi-source data real-time collection and standardized processing: real-time collection of dynamic data through Internet of Things devices on the construction site, static data obtained by connecting design drawings, financial systems, etc., using data cleaning, conversion and integration technology, pre-processing multi-source heterogeneous data according to unified data standards;

[0008] S2, risk factor identification and correlation analysis based on knowledge graph: build an engineering cost risk knowledge graph, use natural language processing technology to analyze the semantics of text data, identify potential risk factors using machine learning algorithms, and analyze the causal relationship of risk factors through a knowledge graph reasoning engine;

[0009] S3, implement artificial intelligence-driven risk quantification prediction and early warning: establish a multi-dimensional risk prediction model, use deep learning, time series analysis and other technologies to deeply analyze the data, predict the occurrence probability, impact degree and time node of different types of risk factors, set multi-level risk warning thresholds and trigger the warning;

[0010] S4, realize real-time monitoring and automatic verification of contract performance enabled by blockchain: digitize project contract terms into smart contract code and deploy them to the blockchain platform, real-time collection of contract performance related data and smart contract performance condition comparison and verification, record contract performance abnormal events and start the breach of contract processing flow;

[0011] S5, provide dynamic cost adjustment and optimization decision support: update the engineering cost data in real time according to the risk prediction results, contract performance and actual project progress, use optimization algorithms combined with project resource constraints to provide cost optimization schemes.

[0012] The application solves the data island problem in engineering cost management through real-time collection and standardized processing of multi-source data, ensuring the accuracy and timeliness of key information such as construction progress and cost expenditure. Based on knowledge graph, risk factor identification and correlation analysis can fully explore potential risks and their causal relationships, improving the depth and breadth of risk identification. Combined with artificial intelligence prediction and blockchain storage, risk quantification and early warning and contract performance automatic verification are realized, greatly reducing the risk of human intervention and improving the intelligent level and credibility of engineering cost management.

[0013] According to the engineering cost risk monitoring method provided by the application, in the multi-source data real-time collection and standardized processing, the Internet of Things device includes intelligent sensors, high-definition cameras and unmanned aerial vehicles, static data includes project basic information, cost budget and payment records, and unified data standards comply with engineering cost data exchange standards. The application collects dynamic data of the construction site in real time through the Internet of Things device, combines static data such as project basic information, cost budget and payment records, forms comprehensive data support, adopts engineering cost data exchange standards for standardized processing, ensures seamless integration of data from different sources, and improves the accuracy and efficiency of subsequent risk analysis.

[0014] According to the engineering cost risk monitoring method provided by the application, in the risk factor identification and correlation analysis based on the knowledge graph, the risk factors include market price fluctuation, policy and regulation change, construction technology risk and contract performance risk, and the knowledge graph reasoning engine is used to analyze the risk propagation path. The application uses knowledge graph technology to perform semantic analysis and correlation analysis on key factors such as market price fluctuation, policy and regulation change, construction technology risk and contract performance risk, can intuitively display the risk propagation path, help managers to develop prevention and control strategies in advance, and reduce the problem of cost out of control caused by risk chain reaction.

[0015] According to the engineering cost risk monitoring method provided by the application, in the risk quantification prediction and early warning driven by artificial intelligence, the deep learning algorithm includes long short-term memory network LSTM and convolutional neural network CNN, the machine learning regression algorithm includes random forest regression and gradient boosting tree, and the early warning level is divided into blue, yellow, orange and red. In the application, LSTM, CNN and other deep learning algorithms and random forest regression, gradient boosting tree and other machine learning methods are used to perform multi-dimensional prediction on engineering cost risk, improve the accuracy of risk quantification evaluation, and through the four-level early warning mechanism of blue, yellow, orange and red, managers can take differentiated measures according to the risk level, and enhance the initiative and controllability of risk management.

[0016] According to the engineering cost risk monitoring method provided by the application, in the real-time monitoring and automatic verification of the contract performance enabled by the block chain, the distributed ledger, encryption algorithm and consensus mechanism of the block chain are used to ensure that the contract data is not tamperable and traceable, and the contract performance process data and operation records are traced back through the block chain tracing function. The distributed ledger, encryption algorithm and consensus mechanism based on the block chain used in the application can ensure that the contract data is not tamperable and traceable throughout the process, and enhance the transparency and credibility of contract performance. The smart contract automatically compares the performance conditions, reduces the cost of manual audit, improves the efficiency of contract execution, and reduces the risk of breach of contract.

[0017] According to the engineering cost risk monitoring method provided by the application, in the real-time monitoring and automatic verification of the contract performance enabled by the block chain, the distributed ledger, encryption algorithm and consensus mechanism of the block chain are used to ensure that the contract data is not tamperable and traceable, and the contract performance process data and operation records are traced back through the block chain tracing function. The distributed ledger, encryption algorithm and consensus mechanism based on the block chain used in the application can ensure that the contract data is not tamperable and traceable throughout the process, and enhance the transparency and credibility of contract performance. The smart contract automatically compares the performance conditions, reduces the cost of manual audit, improves the efficiency of contract execution, and reduces the risk of breach of contract.

[0018] According to the engineering cost management platform provided by the application, the function modules are mutually coordinated, and the function modules comprise:

[0019] The data acquisition and access module has a plurality of data acquisition interfaces, supports seamless docking with Internet of Things devices, information management systems and file storage systems, and provides data acquisition task configuration functions.

[0020] The big data storage and management module adopts a distributed storage technology to build a massive data storage cluster, establishes a data warehouse and a data mart, and provides data backup, recovery, cleaning and other management functions.

[0021] The risk knowledge graph construction and management module provides a knowledge graph editing tool, has an automatic knowledge graph updating function, and provides knowledge graph query and reasoning services.

[0022] The artificial intelligence analysis and prediction module integrates a plurality of artificial intelligence algorithm frameworks, has a data labeling tool, supports model automatic training and incremental learning, and provides risk prediction result visualization display functions.

[0023] The block chain service module builds a block chain platform based on a consortium chain, provides block chain node management functions, and protects user privacy and data security by using block chain encryption technology.

[0024] The user interaction and decision support module provides a multi-terminal access interface, has data visualization display and drilling functions, provides decision support tools, and supports real-time communication and collaboration of users.

[0025] The engineering cost management platform of the application realizes intelligent management of the whole process from data collection, storage, analysis to decision support through the collaborative operation of multiple modules. Among them, the data collection and access module supports the docking of diversified data sources, the big data storage and management module guarantees the efficient processing of massive data, the risk knowledge graph and AI prediction module provides accurate risk insight, the blockchain service module enhances data security and credibility, and the user interaction module optimizes the decision-making experience, comprehensively improving the scientific nature and efficiency of engineering cost management.

[0026] According to the engineering cost management platform provided by the application, the information management system in the data collection and access module includes ERP, CRM and BIM system, and the file storage system includes NAS and cloud disk. The application supports seamless docking with information systems such as ERP, CRM and BIM, and storage systems such as NAS and cloud disk, ensures efficient integration of various business data, reduces data redundancy and transmission delay, and improves the collaboration and data availability of engineering cost management.

[0027] According to the engineering cost management platform provided by the application, the big data storage and management module includes Hadoop distributed file system HDFS and Ceph distributed storage. Here, HDFS and Ceph distributed storage technology is used to build a big data storage cluster, which can provide high scalability and high reliability of data management capability, ensure fast access and long-term safe storage of massive engineering cost data, and meet the needs of large-scale engineering projects.

[0028] According to the engineering cost management platform provided by the application, the blockchain service module in the alliance chain blockchain platform includes Hyperledger Fabric and Quorum. The application builds a blockchain platform based on Hyperledger Fabric and Quorum alliance chain technology, realizes a trusted environment for multi-party collaboration under the premise of ensuring data privacy and security, and improves the traceability and tamper-proofing capability of key businesses such as contract management and risk monitoring.

[0029] The application has the following beneficial effects compared with the prior art:

[0030] 1. First, at the data integration level, through the construction of a multi-source data real-time collection and standardization processing system, the dispersed data of design units, construction units, material suppliers and other participants is effectively integrated. This system uses unified data standards and interface specifications, not only breaks the data island phenomenon existing in traditional engineering cost management, but also ensures the accuracy, integrity and timeliness of key data such as construction progress, cost expenditure and material price, providing a reliable data foundation for subsequent analysis and decision-making.

[0031] 2、Secondly, in terms of intelligent analysis, the platform innovatively integrates big data analysis technology and artificial intelligence prediction algorithm, can monitor the risk indicators such as engineering cost deviation, construction period delay and material price fluctuation in real time through establishing multi-dimensional risk assessment model, and make intelligent prediction based on historical data and real-time data. This intelligent analysis method greatly improves the accuracy of risk assessment, so that project managers can identify potential risks in advance and develop more targeted prevention and control measures, and change the traditional post-processing into pre-prevention.

[0032] 3、Finally, in terms of management decision support, the visual risk warning system and intelligent decision suggestion function provided by the platform significantly reduce the error rate of human judgment, through intuitive risk heat map, trend prediction curve and other visual tools, help managers quickly grasp the overall risk situation of the project, and the optimization suggestion scheme generated by the system provides a scientific basis for key decisions such as project cost control and resource allocation, thereby effectively improving the overall efficiency and economic benefits of engineering cost management. BRIEF DESCRIPTION OF DRAWINGS

[0033] The present application will be further described below in conjunction with the drawings and examples;

[0034] Figure 1 The overall flowchart of the engineering cost risk monitoring method and engineering cost management platform of the present application;

[0035] Figure 2 The module collaborative work timing diagram of the engineering cost risk monitoring method and engineering cost management platform of the present application. DETAILED DESCRIPTION

[0036] This part will describe the specific embodiments of the present application in detail, the preferred embodiments of the present application are shown in the drawings, the role of the drawings is to supplement the description of the text part with figures, so that people can intuitively and visually understand each technical feature and the overall technical scheme of the present application, but it cannot be understood as a limitation on the protection scope of the present application.

[0037] Referring to Figure 1 , 2 The engineering cost risk monitoring method and engineering cost management platform of the present application embodiment includes the owner party, the design unit, the general construction contractor, the supervision unit and multiple subcontracting units, the project scale is large, the number of participants is large, the construction technology is complex, and the engineering cost risk control is difficult.

[0038] Among them, the data collection and standardization processing implementation includes:

[0039] (1) Dynamic data collection and deployment. Intelligent sensors and image acquisition devices are deployed, including: progress monitoring sensors: installed at key construction sites to collect real-time data on the progress of concrete pouring, steel bar binding, and other processes;

[0040] Personnel and equipment work time sensors: through intelligent safety helmets and equipment RFID tags, real-time records of construction personnel attendance and mechanical equipment operating time are recorded;

[0041] Environmental monitoring sensors: monitor environmental parameters such as temperature, humidity, noise, and dust at the construction site.

[0042] Deploy high-definition cameras to monitor the entire construction site in real time;

[0043] Equipped with drones to take aerial photographs at regular intervals to obtain construction site image data.

[0044] (2) Static data interface. Through data interface, the BIM system of the design unit is connected to obtain the three-dimensional design model, engineering quantity list, and other design-related static data of the commercial building. The financial system and contract management system of the owner are connected to obtain the project cost budget, contract text of each bid section, payment plan, and other static data.

[0045] (3) Data preprocessing. Use data cleaning tools to clean the collected dynamic data and imported static data, remove duplicate data, error data, and abnormal data.

[0046] Data conversion and integration: according to the national engineering cost data exchange standard, convert multi-source heterogeneous data into a unified format and perform integrated processing to build a unified data view of the project.

[0047] Risk factor identification and correlation analysis based on knowledge graph, including the following steps:

[0048] (1) Construction of risk knowledge graph: integrate expert experience, similar project historical case data (such as cost risk data of similar scale commercial projects), industry standards, and other knowledge sources related to the commercial building project. Use knowledge graph construction tools to build an engineering cost risk knowledge graph containing market price fluctuations, policy changes, construction technology risks, contract performance risks, and risk correlation relationships.

[0049] (II) Risk factor identification and correlation analysis: Utilize natural language processing techniques to perform semantic analysis on text data such as construction logs, supervision monthly reports, and design change notifications to identify potential risk factors. For example, from a design change notification, the information "basement structure design change" is parsed. Through the knowledge graph reasoning engine, the causal relationships between the identified risk factors are analyzed. For example, "basement structure design change" may trigger "steel reinforcement quantity increase," "concrete pouring process change," and other chain risks, which may further lead to "material cost increase" and "delayed construction period."

[0050] Risk quantification prediction and early warning implementation driven by artificial intelligence, including the following steps:

[0051] (I) Risk prediction model construction and application

[0052] Multi-dimensional risk prediction model: Using LSTM model, combined with historical price data of main building materials such as steel and cement, market supply and demand data, and macroeconomic indicators, to predict future price fluctuations in the next 3 months. For example, it is predicted that the steel price will rise by 75% in the next 2 months.

[0053] Using a random forest regression model, analyze construction progress data, personnel and equipment input, weather factors, etc., to predict key node construction period. The "main structure topping out" node may be delayed by 5-7 days.

[0054] Use historical data accumulated during the early stages of the project to train the model, and through incremental learning, continuously optimize model parameters as the project progresses to improve prediction accuracy.

[0055] (II) Risk early warning implementation

[0056] Early warning threshold setting: Set four levels of early warning thresholds: blue (low risk), yellow (medium risk), orange (high risk), and red (major risk). For example, if the predicted steel price rises by more than 5%, a blue alert is triggered, and if it rises by more than 8%, a yellow alert is triggered.

[0057] Early warning triggering and response: When the predicted risk indicator reaches the early warning threshold, the system automatically sends early warning information to relevant personnel through SMS, platform pop-up window, etc., and provides response suggestions. For example, when the steel price triggers a yellow alert, the procurement department is advised to sign a supplementary agreement with the supplier to lock in the price in advance.

[0058] Real-time monitoring and automatic verification of contract performance enabled by blockchain, including the following steps:

[0059] (I) Smart contract deployment

[0060] Contract clause digital disassembly: Digitally disassemble key clauses in the general contract and major subcontracts of the commercial building project into smart contract code, including:

[0061] Engineering progress node clauses: such as "pay the corresponding progress payment within 14 working days after the completion of the basement structure construction";

[0062] Quality acceptance clauses: such as "the next process can only be carried out after the concrete compressive strength test results meet the standards".

[0063] Smart contract deployment: deploy the disassembled smart contract code to the consortium chain platform based on Hyperledger Fabric.

[0064] (2) Contract performance monitoring and verification

[0065] Performance data collection and verification: Collect contract performance-related data in real time through Internet of Things devices and data interfaces, such as:

[0066] Engineering progress data: Real-time acquisition of completion of each construction node through progress monitoring sensors;

[0067] Quality detection data: Interface with third-party detection systems to obtain quality detection results such as concrete compressive strength.

[0068] The system automatically compares and verifies the collected data with the performance conditions in the smart contract. When the basement structure construction is completed and passes the supervision acceptance, the system automatically triggers the progress payment smart contract, and after verification, completes the fund payment through the blockchain and records the performance on the chain.

[0069] Abnormal event handling: If it is found that the compressive strength of a batch of concrete does not meet the standards, the system immediately records the abnormal event on the blockchain and sends a notice to the construction unit and the supervision unit, and starts the quality rectification and breach handling process.

[0070] Dynamic cost adjustment and optimization decision support implementation, including the following steps:

[0071] (1) Real-time cost update

[0072] Risk event cost impact calculation: When it is predicted that the steel price will rise by 8% to 12%, the system automatically calculates the possible increase in material procurement cost of about 12 million yuan based on the project steel consumption list and procurement plan, and updates the project total cost budget simultaneously.

[0073] Design change cost impact assessment: When the basement structure design changes, the system automatically updates the engineering quantity, material consumption and other parameters of the relevant components, quickly assesses the impact of the change on the cost, and calculates that the change results in an increase in cost of about 8 million yuan.

[0074] (II) Cost optimization scheme generation

[0075] Optimization algorithm application: Using linear programming algorithm, combined with project manpower, equipment, capital and other resource constraints, to provide cost optimization scheme for project managers:

[0076] Scheme one: purchase 3000 tons of steel in advance, lock in current price, expected to save procurement cost 9 million yuan, but need to increase storage cost 1 million yuan;

[0077] Scheme two: optimize construction sequence, advance some non-critical processes, reduce steel centralized procurement volume, expected to reduce price fluctuation impact 6 million yuan.

[0078] Scheme simulation and evaluation: Through simulation tools, the implementation effect of each optimization scheme is simulated and predicted, and the influence of the scheme on project duration and cost is evaluated to assist managers in decision-making. The project manager finally chooses scheme one, which saves steel procurement cost 8.5 million yuan after actual implementation.

[0079] The modules of the project cost management platform are implemented in coordination, including the following steps:

[0080] (I) Data collection and access module

[0081] Through the various data collection interfaces of this module, seamless connection with intelligent sensors, BIM systems, financial systems, etc. is achieved, ensuring real-time data collection and transmission. The data collection task configuration function can flexibly adjust the data collection frequency and range according to the needs of different project stages, such as increasing the collection frequency of concrete pouring data during the main structure construction phase.

[0082] (II) Big data storage and management module

[0083] Using HDFS and Ceph distributed storage technology, a massive data storage cluster is built to efficiently store and manage collected construction progress, contract performance, and other data. The established data warehouse and data mart provide structured data support for data analysis of each module, and the data backup and recovery function ensures data security.

[0084] (III) Risk knowledge graph construction and management module

[0085] The provided knowledge graph editing tool facilitates domain experts to update and maintain risk knowledge. The knowledge graph automatic update function uses web crawler technology to obtain the latest information on building material price policies and regulations in real time, updates the risk knowledge graph, and ensures the timeliness of the knowledge. The knowledge graph query and reasoning service provides strong support for risk identification and correlation analysis.

[0086] (IV) Artificial intelligence analysis and prediction module

[0087] The integrated TensorFlow algorithm framework supports the training and optimization of risk prediction models. The data labeling tool provides high-quality sample data for model training, and the automatic training and incremental learning functions of the model continuously improve the prediction accuracy of the model. The risk prediction result visualization display function presents the results to the project manager in the form of charts and dashboards.

[0088] (V) Blockchain service module

[0089] The Hyperledger Fabric consortium chain platform built ensures the reliable operation of smart contracts and the tamper-proofing of contract performance data. The blockchain node management function ensures the stable operation of the blockchain network, and the encryption technology protects user privacy and data security.

[0090] (VI) User interaction and decision support module

[0091] The provided web and mobile access interfaces make it easy for project participants to view project information anytime, anywhere. Data visualization and drilling functions make complex cost data and risk information intuitive and easy to understand. The risk response strategy library and cost optimization scheme generator in the decision support tool provide strong decision support for managers, and real-time communication and collaboration functions improve the collaborative efficiency of the project team.

[0092] The present application provides an engineering cost risk monitoring method and management platform based on big data, artificial intelligence and blockchain technology. Through real-time collection and standardized processing of multi-source data, the information silos are broken, ensuring the accuracy, integrity and timeliness of the data. By using knowledge graph and AI prediction model, the correlation between risk factors is deeply mined to realize accurate risk assessment and multi-level early warning. Combined with the blockchain smart contract, the automatic verification and tamper-proofing of contract performance are realized, enhancing the transparency and credibility of engineering management. At the same time, based on the optimization algorithm, the cost scheme is dynamically adjusted to improve the resource utilization efficiency and cost control ability.

[0093] The engineering cost management platform adopted by the present application adopts a modular architecture, covering the whole process of data collection, storage, analysis, blockchain storage and decision support, supports seamless connection with Internet of Things devices, enterprise information systems and cloud storage, and relies on distributed storage and consortium chain technology to ensure data security and traceability. The present application effectively solves the problems of data fragmentation, risk prediction lag and unreliable contract execution in traditional engineering cost management, significantly improves the risk prevention and control ability and management efficiency of engineering projects, and has wide application prospect and practical value.

[0094] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not to limit the technical solutions. Although the applicant has made detailed description of the present application with reference to the preferred embodiments, those of ordinary skill in the art should understand that the modifications or equivalent replacements made to the technical solutions of the present application cannot deviate from the purpose and scope of the technical solutions and should be covered in the scope of the claims of the present application.

Claims

1. An engineering cost risk monitoring method, characterized in that, The application relates to an engineering cost management platform applied to integrated large data collection, artificial intelligence analysis and a block chain storage module, and comprises the following steps: S1, real-time collection and standardization processing of multi-source data: real-time collection of dynamic data through Internet of Things equipment on a construction site, connection of design drawings, financial systems and the like to obtain static data, application of data cleaning, conversion and integration technology, and pre-processing of multi-source heterogeneous data according to a unified data standard; S2, identification and correlation analysis of risk factors based on a knowledge graph: construction of an engineering cost risk knowledge graph, semantic analysis of text data by using a natural language processing technology, identification of potential risk factors by combining a machine learning algorithm, and analysis of cause-effect correlation of risk factors by using a knowledge graph reasoning engine; S3, risk quantification prediction and early warning driven by artificial intelligence: establishment of a multi-dimensional risk prediction model, deep mining and analysis of data by using deep learning, time series analysis and the like, prediction of occurrence probability, influence degree and time node of different types of risk factors, setting of multi-level risk early warning thresholds and triggering of early warning; S4, real-time monitoring and automatic verification of contract performance enabled by a block chain: digital disassembly of project contract terms into smart contract codes and deployment of the smart contract codes to a block chain platform, real-time collection of contract performance related data and comparison and verification of smart contract performance conditions, recording of contract performance abnormal events and starting of a breach of contract processing flow; S5, dynamic cost adjustment and optimization decision support: real-time updating of engineering cost data according to risk prediction results, contract performance conditions and actual project progress, and provision of cost optimization schemes by using an optimization algorithm in combination with project resource constraint conditions.

2. The method according to claim 1, wherein, In the real-time collection and standardization processing of multi-source data, the Internet of Things equipment comprises intelligent sensors, high-definition cameras and unmanned aerial vehicles, the static data comprises project basic information, cost budget and payment records, and the unified data standard follows an engineering cost data exchange standard.

3. The method of claim 1, wherein, In the identification and correlation analysis of risk factors based on the knowledge graph, the risk factors comprise market price fluctuation, policy and regulation change, construction technology risk and contract performance risk, and the risk transmission path is analyzed by using the knowledge graph reasoning engine.

4. The method of claim 1, wherein, In the risk quantification prediction and early warning driven by the artificial intelligence, the deep learning algorithm comprises a long short-term memory network (LSTM) and a convolutional neural network (CNN), the machine learning regression algorithm comprises a random forest regression and a gradient boosting tree, and the early warning levels are divided into blue, yellow, orange and red.

5. The method of claim 1, wherein, In the real-time monitoring and automatic verification of contract performance enabled by the block chain, the distributed ledger, encryption algorithm and consensus mechanism of the block chain are used to ensure that contract data are non-tamperable and traceable, and the block chain tracing function is used to trace contract performance process data and operation records.

6. The method of claim 1, wherein, In the dynamic cost adjustment and optimization decision support, the optimization algorithm comprises linear programming and integer programming, and the project resource constraint conditions comprise manpower, equipment and funds.

7. An engineering cost management platform employing a method for monitoring engineering cost risks according to any one of claims 1-6. The engineering cost management platform comprises mutually cooperative functional modules, and the functional modules comprise: a data collection and access module: provided with a plurality of data collection interfaces, capable of being seamlessly connected with Internet of Things equipment, information management systems and file storage systems, and provided with a data collection task configuration function; Big data storage and management module: adopt distributed storage technology to build massive data storage cluster, establish data warehouse and data mart, provide data backup, recovery, cleaning and other management functions; Risk knowledge graph construction and management module: provides knowledge graph editing tool, with automatic knowledge graph updating function, provides knowledge graph query and reasoning service; Artificial intelligence analysis and prediction module: integrates multiple artificial intelligence algorithm frameworks, with data labeling tool, supports model automatic training and incremental learning, provides risk prediction result visualization display function; Blockchain service module: build a blockchain platform based on alliance chain, provide blockchain node management function, protect user privacy and data security by using blockchain encryption technology; User interaction and decision support module: provides multi-terminal access interface, with data visualization display and drilling function, provides decision support tool, supports real-time communication and collaboration of users.

8. The engineering cost management platform of claim 7, wherein, The data collection and access module, the information management system includes ERP, CRM, BIM system, the file storage system includes NAS, cloud disk.

9. The engineering cost management platform of claim 7, wherein, The big data storage and management module, the distributed storage technology includes Hadoop distributed file system HDFS, Ceph distributed storage.

10. The engineering cost management platform of claim 7, wherein, The blockchain service module, the blockchain platform of alliance chain includes HyperledgerFabric, Quorum.

Images