Embedded full-coverage engineering project intelligent auditing and supervising system

Abstract

The invention discloses an embedded full-coverage engineering project intelligent auditing and supervising system, and particularly relates to the technical field of engineering project auditing and supervising. A data acquisition layer comprises an Internet of Things sensor unit which is used for deploying various sensors on an engineering project site, acquiring environment data and engineering structure data in an engineering construction process in real time, and transmitting the environment data and the engineering structure data to a data processing layer; the sensors include but not limited to a temperature sensor, a pressure sensor, a displacement sensor, a humidity sensor, a vibration sensor and an image sensor, and data are transmitted to the data storage layer through the wireless communication module. Intelligent auditing supervision of the whole process of the engineering project is achieved by integrating advanced technologies, responsibility definition and tracing are enhanced, auditing efficiency and accuracy are remarkably improved, project risks are reduced, and compliance and safety of the engineering project are ensured.

Description

Technical Field

[0001] The present invention relates to the field of engineering project audit supervision, and more specifically, to an embedded full-coverage engineering project intelligent audit supervision system. Background Art

[0002] In today's engineering project management field, with the continuous expansion of project scale, increasing complexity and continuous increase in investment amount, the traditional audit supervision model faces many severe challenges and can no longer meet the needs of modern engineering project management, such as:

[0003] 1. The disconnection between the construction parties leads to difficulties in communication and collaboration, unclear definition of responsibilities, frequent buck-passing and wrangling, which affects the project progress and benefits;

[0004] 2. Poor on-site management leads to frequent false visas, which breeds engineering risks, wastes resources, delays in construction schedules and various hidden risks;

[0005] 3. In terms of auditing, the audit department has a weak sense of initiative, an unbalanced professional structure of personnel, and backward methods and techniques. It is difficult to effectively dig out clues in the face of massive data. The professional levels of external audit institutions vary, and the selection management lacks standardization. There is a risk of fraud, and the integrity risk of auditors also threatens the fairness and authority of audits.

[0006] In order to solve the above problems, the present invention provides an embedded full-coverage engineering project intelligent audit supervision system. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art, the present invention provides an embedded full-coverage engineering project intelligent audit supervision system to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above purpose, the present invention provides the following technical solution: an embedded full-coverage engineering project intelligent audit supervision system, specifically comprising the following components:

[0009] The data collection layer includes an IoT sensor unit, which is used to deploy various sensors at the project site to collect environmental data and engineering structure data in real time during the construction process. The sensors include but are not limited to temperature sensors, pressure sensors, displacement sensors, humidity sensors, vibration sensors, and image sensors. The data is transmitted to the data storage layer through the wireless communication module.

[0010] The system docking unit is connected with the project management system, financial system, contract management system, material management system and human resource management system through the data interface to obtain information on project progress, cost, contract execution, material procurement and use, and personnel working hours and attendance;

[0011] The document digitization unit uses OCR and NLP to digitize paper documents, extract key information and convert it into structured data. The paper documents include engineering drawings, construction logs, acceptance reports, change notices, meeting minutes, and correspondence. The document digitization unit has the functions of automatic classification, keyword extraction, and content summary generation;

[0012] The data storage layer includes a distributed database storage unit for storing the collected massive data. The data partitioning, data backup and recovery strategies are used to ensure the security and availability of the data. The distributed database storage unit supports horizontal expansion and can dynamically increase storage nodes according to the growth of data volume. The data partition strategy is divided according to data type and business module.

[0013] Data warehouse unit, used to archive and manage historical data and provide data support for data analysis and mining;

[0014] The data analysis layer includes a big data analysis unit, which uses big data to analyze and process the stored data in real time, establish a risk assessment model, and predict project risks by analyzing multi-dimensional data on project progress, cost, quality, safety, and environment. The risk assessment model formula is: R = f(P, C, Q, S, E), where R represents project risk, P represents project progress, C represents cost, Q represents quality, S represents safety, E represents environment, and f represents risk assessment function;

[0015] Machine learning analysis unit, which uses machine learning algorithms to analyze engineering change data, identify abnormal changes, evaluate supplier performance, and optimize procurement decisions. Machine learning algorithms include but are not limited to decision trees, neural networks, and support vector machines;

[0016] The audit supervision layer includes a full-process audit monitoring unit, which conducts audit supervision on the entire process of the project based on the analysis results, and conducts real-time monitoring of key nodes such as project approval, feasibility study, design, bidding, construction, completion acceptance and settlement to ensure that the project is implemented in accordance with specifications and standards;

[0017] The audit workflow management unit is used to establish an audit workflow management system to realize the allocation, tracking and management of audit tasks, support multi-person collaborative auditing, allocate tasks according to the roles and permissions of auditors, and provide task progress tracking and reminder functions;

[0018] The user interaction layer includes a multi-terminal application unit, which is used to develop web and mobile applications and provide a convenient access portal for auditors, project managers, and corporate executives;

[0019] The visual display unit displays audit results, risk warnings, project progress, cost trends and quality indicators through a visual interface, realizing real-time sharing and interaction of information.

[0020] Preferably, it also includes a responsibility definition and traceability module, which uses blockchain technology to establish a responsibility ledger for project participants, records every operation and decision in the project construction process, and automatically defines and executes the responsibilities of all parties through smart contracts. When problems arise, the responsible party can be quickly located. Blockchain technology adopts a consortium chain architecture, and the participants include construction units, construction units, supervision units, design units, and auditing units. Smart contracts are written based on the Solidity language and have the characteristics of automatic execution, non-tamperability, transparency and auditability.

[0021] Preferably, it also includes a risk assessment and early warning module, which establishes a risk assessment index system by combining historical data and real-time data, uses hierarchical analysis method, fuzzy comprehensive evaluation method and neural network method to comprehensively assess the risks of engineering projects, sets early warning thresholds of different levels according to the assessment results, and issues early warnings to relevant personnel via SMS, email, system pop-up window, mobile push and voice alarm when the risk index exceeds the threshold.

[0022] Preferably, it also includes an audit intelligent assistance module, including an audit knowledge base and an audit doubt automatic discovery unit. The audit knowledge base integrates knowledge resources of audit regulations, policies, standards, cases, and industry best practices, and uses knowledge graph technology to achieve knowledge association and retrieval;

[0023] The automatic discovery unit for audit doubts analyzes financial data and business data based on machine learning algorithms to identify abnormal capital flows, expense expenditures, engineering quantity calculations, and doubts in the execution of contract terms.

[0024] Preferably, it also includes a real-time monitoring and feedback module, which uses video surveillance and sensor data to conduct real-time monitoring of the project site, realizes visual management, and establishes a feedback mechanism to enable project participants to promptly feedback problems and suggestions. The system analyzes and processes the feedback information. Video surveillance uses high-definition cameras with intelligent analysis functions. The feedback mechanism supports anonymous feedback. The system classifies, screens and prioritizes feedback information to ensure that important issues are dealt with in a timely manner.

[0025] The present invention also provides an embedded full-coverage engineering project intelligent audit supervision method, which specifically includes the following steps:

[0026] S1. Data collection: collect environmental data and engineering structure data of the project site through the IoT sensor unit, obtain project progress, cost, contract execution, material procurement and use, and personnel working hours and attendance information from the project management system, financial system, contract management system, material management system, and human resource management system through the system docking unit, and digitize paper documents using the document digitization unit to extract key information and convert it into structured data;

[0027] S2, data storage, storing the collected data in a distributed database storage unit, using data partitioning, data backup and recovery strategies to ensure data security, and storing historical data in a data warehouse unit for archiving and management;

[0028] S3. Data analysis: Use the risk assessment model of the big data analysis unit to analyze the data on project progress, cost, quality, safety, and environment to predict project risks. Use the machine learning analysis unit to analyze project change data and supplier data to identify abnormal changes and evaluate supplier performance.

[0029] S4. Audit supervision: Based on the data analysis results, the key nodes of the project are monitored in real time through the full-process audit monitoring unit. During the monitoring process, audit doubts are automatically generated for matters that do not comply with the audit rules. Audit doubts are graded according to severity. The audit workflow management unit is used to assign audit tasks to auditors. Auditors conduct on-site audits or remote audits according to task requirements. Audit evidence and audit findings are recorded during the audit process. An audit report is generated after the audit is completed. The audit report is released after review and approval. Data and documents in the audit process are fully traceable and traceable.

[0030] S5. Responsibility definition and tracing: Blockchain technology is used to record the operations and decisions of project participants, and the responsibility definition rules are automatically executed through smart contracts. When problems occur, the responsible party is quickly located according to the responsibility ledger. The blockchain ledger data is synchronized to all participating nodes in real time, and the execution results of the smart contract are open, transparent and cannot be tampered with.

[0031] S6. Risk assessment and early warning. We build a risk assessment indicator system by combining historical data and real-time data, use a variety of analysis methods to calculate the project risk value, and issue early warning signals based on the preset early warning thresholds. The risk assessment indicator system is dynamically adjusted according to the project stage and industry characteristics, and the early warning threshold is dynamically optimized based on the risk assessment results and the actual project situation.

[0032] S7. Audit intelligent assistance: Auditors use the audit knowledge base to obtain relevant knowledge support and conduct in-depth audits based on clues provided by the automatic discovery unit of audit doubts. The audit knowledge base supports knowledge search and intelligent recommendation, and the analysis results of the automatic discovery unit of audit doubts are manually verified and confirmed.

[0033] S8. Real-time monitoring and feedback: Real-time monitoring of project site conditions through video surveillance and sensor data. Project participants submit questions and suggestions through feedback channels. The system processes and responds to feedback information in a timely manner. Video surveillance data is stored and played back in real time, and the results of feedback information processing are promptly notified to the submitter.

[0034] Technical effects and advantages of the present invention:

[0035] 1. By integrating IoT sensors, big data analysis, machine learning and other advanced technologies, intelligent audit supervision of the entire process of engineering projects from project establishment to settlement is realized. It can collect and analyze various data in the engineering construction process in real time, including environmental data, engineering structure data, project progress, cost, contract execution, etc., so as to accurately predict and evaluate project risks, which not only improves the accuracy and efficiency of audits, but also effectively prevents illegal operations and potential risks in engineering projects;

[0036] 2. The present invention uses blockchain technology to establish a responsibility account book for project participants, records every operation and decision in the project construction process, and realizes the automatic definition and execution of the responsibilities of all parties through smart contracts, so that the responsible party can be quickly located when problems arise, effectively solving the problems of unclear responsibility definition and difficult tracing in traditional engineering projects. At the same time, the immutability and transparency of blockchain technology also enhance the credibility and trustworthiness of project management;

[0037] 3. By introducing the audit intelligent assistance module, risk assessment and early warning module, and real-time monitoring and feedback module, the intelligence level and efficiency of audit work have been significantly improved. The audit knowledge base provides auditors with rich knowledge support, and the automatic discovery unit of audit doubts can automatically identify abnormal data and doubts based on machine learning algorithms, providing auditors with audit clues. In addition, the real-time monitoring and feedback module enables project participants to submit questions and suggestions in a timely manner, and the system can respond and process them quickly, thereby ensuring the smooth progress of the project and the timeliness of the audit work, which not only reduces the workload of auditors, but also improves the quality and efficiency of the audit work. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is the overall system diagram of the present invention.

[0039] Figure 2 It is a flow chart of the present invention.

[0040] The accompanying drawings are marked as follows: 10, data acquisition layer; 100, Internet of Things sensor unit; 101, system docking unit; 102, document digitization unit; 20, data storage layer; 200, distributed database storage unit; 201, data warehouse unit; 30, data analysis layer; 300, big data analysis unit; 301, machine learning analysis unit; 40, audit supervision layer; 400, full-process audit monitoring unit; 401, audit workflow management unit; 50, user interaction layer; 501, multi-terminal application unit; 502, visualization display unit; 60, responsibility definition and traceability module; 70, risk assessment and early warning module; 80, audit intelligent assistance module; 800, audit knowledge base; 801, automatic discovery unit of audit doubts; 90, real-time monitoring and feedback module. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] Embodiment 1,

[0043] As attached Figure 1 As shown, the present invention provides an embedded full-coverage engineering project intelligent audit supervision system, which specifically includes the following components:

[0044] Data collection layer 10

[0045] The IoT sensor unit 100 is used to deploy various sensors at the project site to collect environmental data and engineering structure data in real time during the construction process. The sensors include but are not limited to temperature sensors, pressure sensors, displacement sensors, humidity sensors, vibration sensors and image sensors. The data is transmitted to the data storage layer 20 through the wireless communication module.

[0046] The system docking unit 101 is connected with the project management system, financial system, contract management system, material management system and human resource management system through the data interface to obtain information on project progress, cost, contract execution, material procurement and use, and personnel working hours and attendance;

[0047] The document digitization unit 102 uses OCR and NLP to digitize paper documents, extract key information and convert it into structured data. Paper documents include engineering drawings, construction logs, acceptance reports, change notices, meeting minutes, and correspondence. The document digitization unit 102 has the functions of automatic classification, keyword extraction, and content summary generation;

[0048] Data storage layer 20

[0049] The distributed database storage unit 200 is used to store the collected massive data, and adopts data partitioning, data backup and recovery strategies to ensure data security and availability. The distributed database storage unit 200 supports horizontal expansion and can dynamically increase storage nodes according to the growth of data volume. The data partition strategy is divided according to data type and business module;

[0050] The data warehouse unit 201 is used to archive and manage historical data and provide data support for data analysis and mining.

[0051] Data analysis layer 30

[0052] The big data analysis unit 300 uses big data to perform real-time analysis and processing on the stored data, establishes a risk assessment model, and predicts project risks by analyzing multi-dimensional data on project progress, cost, quality, safety, and environment. The risk assessment model formula is: R = f(P, C, Q, S, E), where R represents project risk, P represents project progress, C represents cost, Q represents quality, S represents safety, E represents environment, and f represents risk assessment function;

[0053] The machine learning analysis unit 301 uses machine learning algorithms to analyze engineering change data, identify abnormal changes, evaluate supplier performance, and optimize procurement decisions. The machine learning algorithms include but are not limited to decision trees, neural networks, and support vector machines.

[0054] Audit supervision layer 40

[0055] The whole process audit monitoring unit 400 audits and supervises the whole process of the project based on the analysis results, and conducts real-time monitoring of key nodes such as project approval, feasibility study, design, bidding, construction, completion acceptance and settlement to ensure that the project is implemented in accordance with specifications and standards;

[0056] The audit workflow management unit 401 is used to establish an audit workflow management system to realize the allocation, tracking and management of audit tasks, support multi-person collaborative auditing, allocate tasks according to the roles and permissions of auditors, and provide task progress tracking and reminder functions.

[0057] User Interaction Layer 50

[0058] Multi-terminal application unit 501 is used to develop web-terminal and mobile-terminal applications, providing convenient access portals for auditors, project managers, and corporate executives;

[0059] The visualization display unit 502 displays information on audit results, risk warnings, project progress, cost trends and quality indicators through a visualization interface, thereby achieving real-time sharing and interaction of information.

[0060] Specifically, in this embodiment, the engineering site data collected by the IoT sensor unit 100, the business system data acquired by the system docking unit 101, and the paper document data processed by the document digitization unit 102 are transmitted to the distributed database storage unit 200 of the data storage layer 20 through the network for storage. The data in the distributed database storage unit 200 will be extracted to the data warehouse unit 201 for archiving and further processing according to demand, and also provide data support for the big data analysis unit 300 and the machine learning analysis unit 301 of the data analysis layer 30;

[0061] The data results analyzed and processed by the big data analysis unit 300 and the machine learning analysis unit 301 are transmitted to the full-process audit monitoring unit 400 of the audit supervision layer 40 for real-time monitoring of key nodes of the engineering project. The audit doubts and task information generated by the full-process audit monitoring unit 400 during the monitoring process are transmitted to the audit workflow management unit 401, and the audit workflow management unit 401 assigns tasks according to the roles and permissions of the auditors.

[0062] The task execution status of the audit workflow management unit 401 and the data and document information generated during the audit process are fed back to the full-process audit monitoring unit 400 for monitoring and management, and are displayed to auditors, project managers, corporate executives and other users through the multi-terminal application unit 501 and the visualization display unit 502 of the user interaction layer 50. The specific usage environment is as follows:

[0063] During the construction process, the IoT sensor unit 100 continuously collects data such as temperature, pressure, displacement, etc. at the construction site, and the system docking unit 101 obtains the project progress update information in the project management system and the cost expenditure data in the financial system in real time. After these data enter the distributed database storage unit 200, the big data analysis unit 300 analyzes whether there are risks in the project based on the preset risk assessment model, combined with the project progress, cost, and environmental and structural data collected by the sensors. If risks are found, such as delayed project progress and cost overruns, the big data analysis unit 300 transmits the risk information to the full-process audit monitoring unit 400, which triggers the early warning mechanism and assigns the relevant audit tasks to the auditors through the audit workflow management unit 401;

[0064] During the execution of tasks, auditors can obtain task information and related data anytime and anywhere through the multi-terminal application unit 501, and use the visualization display unit 502 to view the overall situation of the project, including risk warnings, project progress trends, etc. At the same time, the audit knowledge base 800 in the audit intelligent auxiliary module 80 provides auditors with knowledge support such as laws and policies, and the audit doubt automatic discovery unit 801 analyzes financial data based on machine learning algorithms to provide auditors with clues to doubts. The audit evidence and problems recorded by auditors during the audit process are managed through the audit workflow management unit 401, and finally an audit report is generated. After the report is reviewed and approved, it is released through the user interaction layer 50 for relevant personnel to view and make reference for decision-making.

[0065] Embodiment 2,

[0066] As attached Figure 1 As shown, the embedded full-coverage engineering project intelligent audit supervision system of this embodiment, on the basis of embodiment 1, further includes a responsibility definition and traceability module 60, which uses blockchain technology to establish a responsibility account book for project participants, records every operation and decision in the project construction process, and realizes automatic definition and execution of the responsibilities of all parties through smart contracts. When problems arise, the responsible party can be quickly located. The blockchain technology adopts a consortium chain architecture. The participants include the construction unit, the construction unit, the supervision unit, the design unit, and the audit unit. The smart contract is written based on the Solidity language and has the characteristics of automatic execution, non-tamperability, transparency and auditability;

[0067] Specifically, the responsibility definition and tracing module 60 is connected to the data collection layer 10, and obtains on-site operation data related to responsibility definition from the IoT sensor unit 100, such as the use records of construction equipment, the time when personnel enter and leave the construction site, etc. These data can be used as auxiliary basis for determining responsibility, relying on the paper document data processed by the document digitization unit 102, such as the discussion records on responsibility allocation in the meeting minutes, the content related to responsibility changes in the change notice, etc., to provide written evidence support for responsibility definition;

[0068] Connected to the data storage layer 20, the recorded project participants' responsibility ledger data is stored in the distributed database storage unit 200 to ensure data security and traceability. At the same time, the data warehouse unit 201 is used to archive and manage historical responsibility data for subsequent query and analysis;

[0069] It is connected with the audit supervision layer 40 to provide the basis for responsibility definition for the whole process audit monitoring unit 400. When an abnormal situation is monitored, the relevant responsible parties can be quickly determined based on the responsibility account book. For example, in the monitoring of construction progress delays, if it is found that it is caused by a certain construction team, the responsibility of the team and relevant managers can be traced back through the responsibility account book. The audit workflow management unit 401 refers to the responsibility definition results in the process of allocating audit tasks and managing audits, and clarifies the audit focus and responsibility scope. For example, for complex audit matters involving multiple responsibilities, the audit information that each participant should provide and the scope of the audit to be accepted are determined based on the responsibility definition;

[0070] It is connected to the user interaction layer 50 and displays the responsibility definition results and responsibility ledger information to relevant personnel through the multi-terminal application unit 501, so that all parties can check their own and other participants' responsibility status at any time. For example, project managers can check the responsibility fulfillment of each construction team at different construction stages on the mobile terminal. The visualization display unit 502 can display the relevant information of responsibility definition in the form of charts or processes, such as a responsibility allocation matrix, which intuitively presents the responsibility relationship of each participant in each link of the project.

[0071] The risk assessment and early warning module 70 combines historical data and real-time data to establish a risk assessment index system, uses the analytic hierarchy process, fuzzy comprehensive evaluation method and neural network method to comprehensively assess the risks of the project, sets early warning thresholds of different levels according to the assessment results, and issues early warnings to relevant personnel through SMS, email, system pop-up window, mobile terminal push, and voice alarm when the risk index exceeds the threshold;

[0072] Specifically, the risk assessment and early warning module 70 is connected to the data collection layer 10, and receives in real time the environmental data and engineering structure data collected by the IoT sensor unit 100, as well as the project progress, cost, contract execution and other data obtained by the system docking unit 101, as the basic data source for risk assessment, and uses the document data such as the change notice processed by the document digitization unit 102 to analyze the risks that may be caused by engineering changes, such as the cost increase and progress delay risks caused by the changes;

[0073] Connected to the data storage layer 20, historical project data is obtained from the distributed database storage unit 200 for building a risk assessment indicator system and training a risk assessment model. For example, by analyzing the cost overruns of similar projects in the past, indicators and thresholds for cost risk assessment are determined, and intermediate data and final results in the risk assessment process are stored in the distributed database storage unit 200 for subsequent analysis and tracing. At the same time, the data warehouse unit 201 stores historical risk assessment data for risk trend analysis and model optimization;

[0074] Connected to the data analysis layer 30, and working in coordination with the big data analysis unit 300, the multi-dimensional data analysis results provided by the big data analysis unit 300 are important inputs for risk assessment. For example, the correlation analysis results of the big data analysis unit 300 on the project progress and cost help the risk assessment and early warning module 70 to more accurately assess the overall risk status of the project. The analysis results of the machine learning analysis unit 301 on the project change and supplier data provide the risk assessment and early warning module 70 with information on the project change risk and supplier-related risks, enriching the dimensions of risk assessment.

[0075] Connected to the audit supervision layer 40, based on the risk assessment results, it provides risk warning information to the full-process audit monitoring unit 400 and triggers the corresponding audit monitoring process. For example, when the risk assessment shows that the quality risk of a project is high, the full-process audit monitoring unit 400 will strengthen the monitoring of the quality-related links of the project, and the audit workflow management unit 401 will adjust the priority and allocation strategy of the audit task based on the risk warning information. For example, for high-risk projects, experienced auditors are given priority and the audit frequency is increased;

[0076] It is connected to the user interaction layer 50 and pushes risk warning information to relevant personnel through the multi-terminal application unit 501 to ensure that relevant personnel can receive risk warnings in a timely manner. For example, after the project manager receives a warning notification about the project progress risk on the mobile terminal, he can take timely measures to adjust the progress plan. The visualization unit 502 displays the risk assessment results in the form of intuitive charts, such as risk heat maps that show the risk levels of different areas or links of the project, helping users to quickly understand the overall risk distribution of the project.

[0077] Audit Intelligent Assistance Module 80

[0078] Audit Knowledge Base 800 integrates knowledge resources of audit regulations, policies, standards, cases, and industry best practices, and uses knowledge graph technology to achieve knowledge association and retrieval;

[0079] The automatic discovery unit 801 of audit doubts analyzes financial data and business data based on machine learning algorithms to identify abnormal fund flows, expense expenditures, engineering quantity calculations, and doubts about the execution of contract terms;

[0080] Specifically, the audit intelligent assistance module 80 is connected to the data collection layer 10, and uses the financial and business document data processed by the document digitization unit 102, such as account details, contract documents, etc., as the basic data for the construction of the audit knowledge base 800 and the automatic discovery of audit doubts. For example, information such as contract terms and amounts are extracted from the contract documents to enrich the content of the audit knowledge base 800 and provide a comparison basis for the automatic discovery of audit doubts;

[0081] Connected to the data storage layer 20, the knowledge resources in the audit knowledge base 800 are stored in the distributed database storage unit 200, which is convenient for calling and updating at any time. At the same time, the data warehouse unit 201 stores historical audit cases and related knowledge data, providing data support for the optimization of the knowledge base and the construction of the knowledge graph. The automatic discovery unit 801 of audit doubts obtains financial data and business data from the distributed database storage unit 200 for analysis, such as the capital flow data obtained from the financial system for detecting abnormal capital flow;

[0082] Connected to the data analysis layer 30, the audit doubt automatic discovery unit 801 performs data mining and analysis based on the algorithm and model of the machine learning analysis unit 301, for example, clustering analysis of financial data is performed using machine learning algorithms to discover abnormal data patterns. The overall project data provided by the big data analysis unit 300 provides background information for the audit intelligent assistance module 80, helping auditors to better understand the project status and be more targeted when using the audit knowledge base 800 and analyzing doubts;

[0083] Connected to the audit supervision layer 40, the audit doubt automatic discovery unit 801 transmits the discovered doubt information to the full-process audit monitoring unit 400. The full-process audit monitoring unit 400 adjusts the monitoring focus and strategy according to the doubt situation. For example, when a supplier's contract execution is found to have doubts, the monitoring of the supplier's related business is strengthened. The audit workflow management unit 401 optimizes the audit task allocation and audit process based on the knowledge support and doubt clues provided by the audit intelligent auxiliary module 80. For example, according to the regulatory requirements in the audit knowledge base 800, the audit steps and key inspection contents of specific audit matters are determined;

[0084] Connected to the user interaction layer 50, auditors access the audit knowledge base 800 through the multi-terminal application unit 501 to obtain the required knowledge resources to assist in the audit work. For example, during an on-site audit, they can query relevant laws and regulations and cases through the mobile terminal to determine the nature of the problems found in the audit and the basis for handling them. The visualization unit 502 can display the distribution and importance of audit doubts, helping auditors and project managers to intuitively understand the key areas of the audit. It can also display the knowledge association map in the audit knowledge base 800, making it convenient for users to explore knowledge resources.

[0085] Real-time monitoring and feedback module 90 uses video surveillance and sensor data to monitor the project site in real time, realize visual management, and establish a feedback mechanism so that project participants can promptly feedback problems and suggestions. The system analyzes and processes the feedback information. Video surveillance uses high-definition cameras with intelligent analysis functions. The feedback mechanism supports anonymous feedback. The system classifies, filters and prioritizes feedback information to ensure that important issues are handled in a timely manner.

[0086] Specifically, the real-time monitoring and feedback module 90 is connected to the data acquisition layer 10, and relies on various sensor data of the Internet of Things sensor unit 100, such as temperature and humidity sensor data for monitoring whether the construction site environment meets the construction requirements, and vibration sensor data for monitoring the operating status of large equipment, etc., to achieve real-time data collection of the project site, and provide a data basis for visual management and problem discovery. The video image data collected by the video surveillance system is an important source of monitoring information, which complements the sensor data and reflects the actual situation of the project site. For example, through video surveillance, the illegal operation of personnel at the construction site can be discovered, and at the same time, combined with the sensor data, it can be judged whether the behavior has an impact on the safety of the engineering structure;

[0087] Connected to the data storage layer 20, the video surveillance data and sensor data are stored in the distributed database storage unit 200 for subsequent playback and data analysis. For example, when an engineering accident occurs, the video and sensor data of the accident period can be retrieved to analyze the cause of the accident. The data warehouse unit 201 stores historical monitoring data for analyzing the changing trend of the project site conditions, such as long-term monitoring of environmental data in a certain area to analyze the potential impact of environmental changes on the project;

[0088] Connected with the audit supervision layer 40, it provides the full-process audit monitoring unit 400 with real-time project site conditions, assisting auditors in remote monitoring and judgment. For example, auditors can monitor the use of materials on the construction site by viewing real-time video monitoring and sensor data to prevent waste and theft. The audit workflow management unit 401 adjusts audit tasks and plans based on feedback information. For example, after receiving feedback from project participants on construction process issues, arrange auditors to conduct special audits on the cost and quality related to the process;

[0089] It is connected to the user interaction layer 50 and realizes the feedback submission of project participants and the viewing of monitoring information by relevant personnel through the multi-terminal application unit 501. For example, construction personnel can submit feedback on safety hazards found on site on the mobile terminal, and the project manager can view the real-time monitoring video and feedback processing status on the Web terminal. The visualization display unit 502 displays the monitoring data in the form of real-time video streams, charts, etc., so that users can intuitively understand the status of the project site. At the same time, the processing progress and results of the feedback information are visualized to improve information transparency.

[0090] Embodiment 3,

[0091] As attached Figure 2 As shown, the embodiment of the present invention also provides an embedded full-coverage engineering project intelligent audit supervision method, which specifically includes the following steps:

[0092] S1. Data collection: collect environmental data and engineering structure data of the project site through the Internet of Things sensor unit 100, obtain project progress, cost, contract execution, material procurement and use, and personnel working hours and attendance information from the project management system, financial system, contract management system, material management system, and human resource management system through the system docking unit 101, and digitize paper documents using the document digitization unit 102 to extract key information and convert it into structured data;

[0093] S2, data storage, storing the collected data in the distributed database storage unit 200, using data partitioning, data backup and recovery strategies to ensure data security, and storing historical data in the data warehouse unit 201 for archiving and management;

[0094] S3, data analysis, using the risk assessment model of the big data analysis unit 300 to analyze the data of project progress, cost, quality, safety, and environment to predict project risks, and using the machine learning analysis unit 301 to analyze the project change data and supplier data to identify abnormal changes and evaluate supplier performance;

[0095] S4. Audit supervision: Based on the data analysis results, the key nodes of the project are monitored in real time through the full-process audit monitoring unit 400. During the monitoring process, audit doubts are automatically generated for matters that do not comply with the audit rules. The audit doubts are graded according to the severity. The audit tasks are assigned to auditors using the audit workflow management unit 401. Auditors conduct on-site audits or remote audits according to the task requirements. Audit evidence and audit findings are recorded during the audit process. An audit report is generated after the audit is completed. The audit report is released after review and approval. The data and documents in the audit process are fully traceable and traceable.

[0096] S5. Responsibility definition and tracing: Blockchain technology is used to record the operations and decisions of project participants, and the responsibility definition rules are automatically executed through smart contracts. When problems occur, the responsible party is quickly located according to the responsibility ledger. The blockchain ledger data is synchronized to all participating nodes in real time, and the execution results of the smart contract are open, transparent and cannot be tampered with.

[0097] S6. Risk assessment and early warning. We build a risk assessment indicator system by combining historical data and real-time data, use a variety of analysis methods to calculate the project risk value, and issue early warning signals based on the preset early warning thresholds. The risk assessment indicator system is dynamically adjusted according to the project stage and industry characteristics, and the early warning threshold is dynamically optimized based on the risk assessment results and the actual project situation.

[0098] S7, audit intelligent assistance, the auditor uses the audit knowledge base 800 to obtain relevant knowledge support, and conducts in-depth audits based on the clues provided by the audit doubt automatic discovery unit 801. The audit knowledge base 800 supports knowledge search and intelligent recommendation, and the analysis results of the audit doubt automatic discovery unit 801 are manually verified and confirmed;

[0099] S8. Real-time monitoring and feedback: Real-time monitoring of project site conditions through video surveillance and sensor data. Project participants submit questions and suggestions through feedback channels. The system processes and responds to feedback information in a timely manner. Video surveillance data is stored and played back in real time, and the results of feedback information processing are promptly notified to the submitter.

[0100] The principle of the present invention is as follows:

[0101] The present invention collects the on-site environment and structure data of the engineering project, obtains relevant information from multiple systems, processes paper documents, and transmits various types of data to the distributed database storage unit 200 and the data warehouse unit 201 of the data storage layer 20 for storage and management through the Internet of Things sensor unit 100, the system docking unit 101 and the document digitization unit 102 of the data collection layer 10;

[0102] The big data analysis unit 300 and the machine learning analysis unit 301 of the data analysis layer 30 use risk assessment models and machine learning algorithms to analyze and predict project risks, identify abnormal changes, and evaluate supplier performance based on stored data;

[0103] The whole process audit monitoring unit 400 and the audit workflow management unit 401 of the audit supervision layer 40 monitor the key nodes of the whole process of the engineering project in real time according to the analysis results and distribute and manage audit tasks;

[0104] The multi-terminal application unit 501 and the visual display unit 502 of the user interaction layer 50 provide access portals and display various project information for relevant personnel;

[0105] At the same time, there is a responsibility definition and traceability module 60 that uses blockchain technology to record operational decisions and smart contracts to define execution responsibilities. The risk assessment and early warning module 70 builds an indicator system to assess risks and issue early warnings. The knowledge base and suspicious point discovery unit of the audit intelligent assistance module 80 assist in auditing. The real-time monitoring and feedback module 90 uses video surveillance and sensors to monitor the site and process feedback information. All modules and steps work together to achieve intelligent, comprehensive and efficient audit supervision of engineering projects, ensuring the smooth advancement and standardized execution of projects.

[0106] In summary, the present invention realizes intelligent audit supervision of the entire process of the engineering project, improves audit efficiency and accuracy, and reduces audit risks. At the same time, through the application of the responsibility definition and tracing module 60, the risk assessment and early warning module 70, the audit intelligent assistance module 80 and the real-time monitoring and feedback module 90, the management level and decision-making efficiency of the engineering project are further improved.

[0107] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. Embedded full coverage engineering project intelligent audit supervision system, characterized by: Specifically, it includes the following components: The data collection layer (10) includes an Internet of Things sensor unit (100) for deploying various sensors at the project site to collect environmental data and engineering structure data in real time during the construction process. The sensors include but are not limited to temperature sensors, pressure sensors, displacement sensors, humidity sensors, vibration sensors and image sensors. The data is transmitted to the data storage layer (20) via a wireless communication module. The system docking unit (101) is connected with the project management system, financial system, contract management system, material management system and human resource management system through a data interface to obtain information on project progress, cost, contract execution, material procurement and use, and personnel working hours and attendance; A document digitization unit (102) uses OCR and NLP to digitize paper documents, extract key information and convert it into structured data. The paper documents include engineering drawings, construction logs, acceptance reports, change notices, meeting minutes, and correspondence. The document digitization unit (102) has the functions of automatic classification, keyword extraction, and content summary generation. The data storage layer (20) includes a distributed database storage unit (200) for storing the collected mass data, and adopts data partitioning, data backup and recovery strategies to ensure the security and availability of the data. The distributed database storage unit (200) supports horizontal expansion and can dynamically increase storage nodes according to the growth of data volume. The data partition strategy is divided according to data type and business module; A data warehouse unit (201) is used to archive and manage historical data and provide data support for data analysis and mining; The data analysis layer (30) includes a big data analysis unit (300), which uses big data to perform real-time analysis and processing on stored data, establishes a risk assessment model, and predicts project risks by analyzing multi-dimensional data on project progress, cost, quality, safety, and environment. The risk assessment model formula is: R=f(P, C, Q, S, E), where R represents project risk, P represents project progress, C represents cost, Q represents quality, S represents safety, E represents environment, and f represents risk assessment function; A machine learning analysis unit (301) uses a machine learning algorithm to analyze engineering change data, identify abnormal changes, evaluate supplier performance, and optimize procurement decisions. The machine learning algorithm includes but is not limited to a decision tree, a neural network, and a support vector machine; The audit supervision layer (40) includes a full-process audit monitoring unit (400), which conducts audit supervision on the entire process of the project based on the analysis results, and conducts real-time monitoring of key nodes such as project approval, feasibility study, design, bidding, construction, completion acceptance and settlement to ensure that the project is implemented in accordance with specifications and standards; The audit workflow management unit (401) is used to establish an audit workflow management system, realize the allocation, tracking and management of audit tasks, support multi-person collaborative auditing, allocate tasks according to the roles and permissions of auditors, and provide task progress tracking and reminder functions; The user interaction layer (50) includes a multi-terminal application unit (501) for developing web-terminal and mobile-terminal applications to provide a convenient access portal for auditors, project managers, and corporate executives; The visualization display unit (502) displays audit results, risk warnings, project progress, cost trends and quality indicators through a visualization interface, thereby achieving real-time information sharing and interaction.

2. The embedded full-coverage engineering project intelligent audit supervision system according to claim 1 is characterized by: It also includes a responsibility definition and traceability module (60), which uses blockchain technology to establish a responsibility ledger for project participants, records every operation and decision in the project construction process, and automatically defines and executes the responsibilities of all parties through smart contracts. When problems arise, the responsible party can be quickly located. Blockchain technology adopts a consortium chain architecture, and the participants include construction units, construction units, supervision units, design units, and audit units. Smart contracts are written based on the Solidity language and have the characteristics of automatic execution, non-tamperability, transparency and auditability.

3. The embedded full-coverage engineering project intelligent audit supervision system according to claim 1 is characterized by: It also includes a risk assessment and early warning module (70), which combines historical data and real-time data to establish a risk assessment index system, uses hierarchical analysis method, fuzzy comprehensive evaluation method and neural network method to comprehensively assess the risks of the engineering project, sets early warning thresholds of different levels according to the assessment results, and issues early warnings to relevant personnel via SMS, email, system pop-up window, mobile terminal push, and voice alarm when the risk index exceeds the threshold.

4. The embedded full-coverage engineering project intelligent audit supervision system according to claim 1 is characterized by: It also includes an audit intelligent assistance module (80), including an audit knowledge base (800) and an audit doubt automatic discovery unit (801), wherein the audit knowledge base (800) integrates knowledge resources of audit regulations, policies, standards, cases, and industry best practices, and utilizes knowledge graph technology to achieve knowledge association and retrieval; The automatic discovery unit (801) of audit doubts analyzes financial data and business data based on machine learning algorithms to identify abnormal fund flows, expense expenditures, engineering quantity calculations, and doubts in the execution of contract terms.

5. The embedded full-coverage engineering project intelligent audit supervision system according to claim 1 is characterized by: It also includes a real-time monitoring and feedback module (90), which uses video monitoring and sensor data to monitor the project site in real time, realizes visual management, and establishes a feedback mechanism to allow project participants to promptly feedback problems and suggestions. The system analyzes and processes the feedback information. The video monitoring uses a high-definition camera with intelligent analysis function. The feedback mechanism supports anonymous feedback. The system classifies, screens and prioritizes the feedback information to ensure that important issues are handled in a timely manner.

6. The embedded full-coverage engineering project intelligent audit supervision system according to claim 1 is characterized by: The present invention also provides an embedded full-coverage engineering project intelligent audit supervision method, which specifically includes the following steps: S1, data collection, collecting environmental data and engineering structure data of the engineering project site through the Internet of Things sensor unit (100), obtaining information on project progress, cost, contract execution, material procurement and use, and personnel working hours and attendance from the project management system, financial system, contract management system, material management system, and human resource management system through the system docking unit (101), and digitizing paper documents using the document digitization unit (102), extracting key information and converting it into structured data; S2, data storage, storing the collected data in a distributed database storage unit (200), using data partitioning, data backup and recovery strategies to ensure data security, and storing historical data in a data warehouse unit (201) for archiving and management; S3, data analysis, using the risk assessment model of the big data analysis unit (300) to analyze the data of project progress, cost, quality, safety, and environment to predict project risks, and using the machine learning analysis unit (301) to analyze the project change data and supplier data to identify abnormal changes and evaluate supplier performance; S4. Audit supervision: Based on the data analysis results, the key nodes of the project are monitored in real time through the full-process audit monitoring unit (400). During the monitoring process, audit doubts are automatically generated for matters that do not comply with the audit rules. The audit doubts are graded according to the severity. The audit tasks are assigned to auditors using the audit workflow management unit (401). Auditors conduct on-site audits or remote audits according to the task requirements. Audit evidence and audit findings are recorded during the audit process. An audit report is generated after the audit is completed. The audit report is released after review and approval. Data and documents in the audit process are fully traceable and traceable. S5. Responsibility definition and tracing: Blockchain technology is used to record the operations and decisions of project participants, and the responsibility definition rules are automatically executed through smart contracts. When problems occur, the responsible party is quickly located according to the responsibility ledger. The blockchain ledger data is synchronized to all participating nodes in real time, and the execution results of the smart contract are open, transparent and cannot be tampered with. S6. Risk assessment and early warning. We build a risk assessment indicator system by combining historical data and real-time data, use a variety of analysis methods to calculate the project risk value, and issue early warning signals based on the preset early warning thresholds. The risk assessment indicator system is dynamically adjusted according to the project stage and industry characteristics, and the early warning threshold is dynamically optimized based on the risk assessment results and the actual project situation. S7, audit intelligent assistance, the auditor uses the audit knowledge base (800) to obtain relevant knowledge support, and conducts in-depth audits through clues provided by the audit doubt automatic discovery unit (801). The audit knowledge base (800) supports knowledge search and intelligent recommendation, and the analysis results of the audit doubt automatic discovery unit (801) are manually verified and confirmed; S8. Real-time monitoring and feedback: Real-time monitoring of project site conditions through video surveillance and sensor data. Project participants submit questions and suggestions through feedback channels. The system processes and responds to feedback information in a timely manner. Video surveillance data is stored and played back in real time, and the results of feedback information processing are promptly notified to the submitter.

Images