Digital intelligence system applied to cooperative management and control of water-power engineering construction participating units

Abstract

The invention relates to the technical field of management and control systems, in particular to a digital intelligence system applied to collaborative management and control of water-power engineering construction participating units, which comprises a project data management module covering water-power engineering construction full life cycle management, extracting multi-source information data from various subsystems, and constructing a project view and a project management information base; the project risk analysis module is used for constructing an intelligent risk analysis model for risk analysis and generating a dynamic evaluation result, a graded early warning notification and an auxiliary decision scheme; the project collaborative management module is used for processing graded early warning notification and auxiliary decision-making schemes by using a multi-layer perceptron model, and generating finalizing service achievements and management process records; and the project document management module is used for performing compliance automatic checking and processing on the electronic documents needing to be archived, and dynamically updating and optimizing the project management information base. Through the closed-loop management and control system, the cooperative management and control efficiency of water-power engineering construction participation units is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of management and control systems, in particular to a digital and intelligent system applied to collaborative management and control of water and electricity engineering construction participating units. BACKGROUND

[0002] Currently, the administrative management and operation control activities of water and electricity wisdom engineering projects generally rely on multiple functionally dispersed information systems. For example, core management functions such as project planning, resource scheduling and cost control are usually executed in independent professional project software; and engineering design documents, administrative approval processes and daily office collaboration are scattered in various document management and general office automation tools. Each participating unit, including design, construction, supervision and equipment supply, often independently runs its internal management and control system, which makes it difficult for engineering data such as BIM three-dimensional building information model, GIS geographic information data, and emerging Internet of Things real-time sensing data to be effectively integrated and shared with core project management information and administrative process data. This widespread information island phenomenon makes it difficult for data to form a unified view that supports comprehensive management decision-making. Although there are some general industrial internet platform technologies on the market, they often have obvious shortcomings in terms of deep adaptation to the complex management scenarios specific to water and electricity engineering, support for collaborative management and control modes that enable efficient participation by multiple parties, and implementation of intelligent management applications based on domain knowledge.

[0003] Therefore, the main deficiency of the prior art in supporting water and electricity wisdom engineering to achieve its core management and control objectives is the lack of an industrial internet platform to achieve data-driven digital and intelligent collaborative management of water and electricity engineering, which results in unclear overall situational awareness of the project, delayed risk pre-control, poor multi-party collaboration, and low management decision-making efficiency, thereby severely restricting the improvement of the wisdom level and comprehensive benefits of the project.

[0004] Therefore, a digital and intelligent system applied to collaborative management and control of water and electricity engineering construction participating units is proposed. SUMMARY

[0005] The present application aims to provide a digital and intelligent system applied to collaborative management and control of water and electricity engineering construction participating units, which improves the collaborative management and control efficiency of water and electricity wisdom engineering through a closed-loop management and control system. The system includes a project data management module that extracts multi-source information data from the entire life cycle of water and electricity wisdom engineering and each subsystem of each wisdom engineering, and constructs a project view and a project management information database; a project risk analysis module that constructs an intelligent risk analysis model for risk analysis, generates dynamic evaluation results, graded early warning notifications and auxiliary decision-making schemes; a project collaborative management module that uses a multi-layer perception machine model to process graded early warning notifications and auxiliary decision-making schemes, and generates finalized business results and management process records; and a project document management module that optimizes the project management information database through knowledge extraction technology.

[0006] To achieve the above object, the present application provides the following technical solutions: A digital system applied to collaborative management and control of participating units in hydropower engineering construction, characterized in that it comprises: A project data management module that extracts multi-source information data from a hydropower smart engineering full life cycle and each subsystem of each smart engineering, and constructs a project view and a project management information base based on the multi-source information data; A project risk analysis module that constructs an intelligent risk analysis model to perform risk analysis on the project management information base and the project view, and generates dynamic evaluation results, hierarchical early warning notifications, and auxiliary decision-making schemes; A project collaborative management module that processes hierarchical early warning notifications and auxiliary decision-making schemes using a multi-layer perception model, calls the project management information base and the project view as execution support, and generates finalized business results and management process records; A project document management module that receives finalized business results and management process records, performs compliance automatic checking and processing on data to be archived, and feeds management experience, risk cases, and project information back to the project management information base through knowledge extraction technology to dynamically update and optimize the project management information base.

[0007] Preferably, the process of constructing the project view comprises: Integrating hydropower smart engineering-related engineering plan and actual progress data, cost accounting and contract performance data, and quality evaluation and safety control process data from each subsystem of each smart engineering; integrating various types of management process data, and performing multi-dimensional association and state mapping with engineering entity information contained in the BIM three-dimensional building information model corresponding to the hydropower smart engineering, to form a constructed project view containing time dimension, space dimension, engineering state, management progress, and key indicators.

[0008] Preferably, the project management information base is specifically a hydropower engineering professional knowledge graph that describes and stores the association relationships between engineering elements, management processes, resource allocation, contract terms, risk factors, and industry specification standards in a semantic way for advanced query and reasoning.

[0009] Preferably, the process of risk analysis by the intelligent risk analysis model comprises: Based on the integrated contract budget data, term agreement data, real-time progress and payment settlement data, engineering change and claim data obtained from the project management information base and the project view, a hybrid analysis method that combines hydropower industry contract management expert experience rules and machine learning algorithms is used to perform correlation analysis on multi-dimensional performance data and to perform hierarchical dynamic weight assignment on risk factors; and dynamic evaluation results of contract performance risk state in different dimensions, hierarchical early warning notifications, and auxiliary decision-making schemes are generated.

[0010] Preferably, the auxiliary decision-making scheme specifically represents outputting decision-making reference information containing multiple alternative countermeasures, and expected cost data, expected benefit evaluation data and comprehensive ranking consideration indicators corresponding to each alternative countermeasure for the identified specific risk.

[0011] Preferably, the process of processing the hierarchical early warning notice and the auxiliary decision-making scheme by using the multi-layer perception model comprises: according to the level and type of the hierarchical early warning notice and the historical similar risk disposal cases and management regulations of the hydropower engineering in the project management information base, using the multi-layer perception model trained based on the historical project success cases to dynamically adjust the preset risk response process and administrative approval process, the adjustment including optimization of process participant nodes, approval levels, processing time limit and required supporting material list; when determining the process participant nodes, further calling the participant unit responsibilities and personnel skill portrait data in the project management information base for intelligent recommendation of processing persons.

[0012] Preferably, the process of generating the final business results and management process records comprises: when processing the collaborative project management activities, engineering change approval and important scheme review, calling the electronic seal service at the key approval node to ensure the effectiveness of the digital signature of the final business results and the compliance of the approval process.

[0013] Preferably, the process of performing compliance automatic checking and processing on the data to be archived comprises: intelligently constructing a context-adaptive compliance judgment benchmark according to the latest effective regulations, standards and management systems stored in the project management information base and dynamically associated with the current document business context, combining the engineering entity state and risk level information obtained from the project management information base; using natural language processing technology to perform deep semantic compliance review on the document content, and generating prompt information containing specific positioning, explainable analysis and correction guidance; feeding back the compliance problems identified in the checking and effective processing experience to the project management information base.

[0014] Preferably, the process of feeding back to the project management information base comprises: using natural language processing and knowledge engineering technology to actively identify and extract structured knowledge elements that can reflect effective management practices, risk control key points and decision optimization logic in the context of hydropower engineering from the final business results, management process records that have passed compliance checking, and associated compliance guidelines and correction suggestions; performing multi-dimensional semantic linking and explicit knowledge expression of the extracted structured knowledge elements with the existing engineering entities, business process nodes, regulation standard clauses in the project management information base, forming context-based experience knowledge units that can be understood and reasoned by computers and feeding back to the project management information base.

[0015] Preferably, the dynamic updating and optimization of the project management information base includes the learning and analysis of the contextualized experiential knowledge units, the dynamic updating and optimization of the early warning threshold settings in the intelligent risk analysis model and the recommended execution path of the management process of the project collaborative management module.

[0016] Compared with the prior art, the present application has the following beneficial effects: 1. The project data management module efficiently extracts and fuses multi-source information data in the whole life cycle of the hydropower project and each subsystem of the intelligent project, generates a unified project view and a structured project management information base, effectively breaks the data silos under the traditional management mode, and converts the originally scattered and difficult-to-use data into a management information base that can be understood, analyzed and supported for decision-making, ensuring that all subsequent digital and intelligent collaborative management activities can be based on comprehensive, accurate and real-time information, and truly realizing data-driven management.

[0017] 2. The intelligent risk analysis model can perform in-depth analysis and intelligent research and judgment on the complex engineering and management data obtained from the project management information base and the project view, significantly improving the risk perception lag and the lack of pre-control ability caused by insufficient data utilization in the prior art, and can more effectively dynamically quantify and accurately early warn the specific potential risks of the hydropower project, effectively supporting the intelligent management and scientific decision-making of risks in digital and intelligent collaborative management.

[0018] 3. The project collaborative management module can dynamically adjust and optimize the preset risk response process and administrative approval process according to the level and type of early warning notification, as well as historical similar risk disposal cases and management regulations, effectively solving the technical problems of low collaboration efficiency and slow response caused by complex cross-organization and cross-department collaborative work processes and poor information transmission in hydropower projects, ensuring the effectiveness of the collaborative results and the compliance of the process by integrating electronic signature services at key approval nodes, and realizing efficient, intelligent and standardized operation of cross-organization and cross-department collaborative project management activities in hydropower projects, which effectively promotes the landing of digital and intelligent collaborative management.

[0019] 4. The project document management module uses knowledge extraction technology to deeply process the final business results, management process records and associated compliance guidelines and correction suggestions generated by the system, effectively solving the technical problems of insufficient organizational learning ability caused by the difficulty of implicit knowledge of project management experience and risk cases in hydropower projects, and the cumbersome and error-prone management of traditional documents. The automatic verification improves the efficiency and quality of compliance management, and the active extraction of structured knowledge elements optimizes the project management information base, improving the knowledge accumulation, intelligent application and continuous self-evolution ability of digital and intelligent collaborative management of hydropower projects. BRIEF DESCRIPTION OF DRAWINGS

[0020] Fig. 1 A flowchart of a digital and intelligent system applied to collaborative management and control of participating units in a hydropower engineering construction is provided for an embodiment of the present application. Fig. 2 A flowchart of a dynamic weighting model is provided for an embodiment of the present application. Fig. 3 A flowchart of a project collaborative management module is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0022] Please refer to Figs. 1 to 3 The present application provides a digital and intelligent management and control system applied to a smart hydropower engineering, and the technical solutions are as follows: A company is engaged in the construction, operation and maintenance and management of water conservancy and hydropower engineering. In order to improve the management efficiency and intelligent control level in complex hydropower engineering projects, A company deploys a digital and intelligent system applied to collaborative management and control of participating units in a hydropower engineering construction on its industrial internet platform, and the specific system flowchart is as shown in Fig. 1 .

[0023] The project data management module extracts multi-source information data from the full life cycle of the smart hydropower engineering and each subsystem of each smart engineering, and constructs a project view and a project management information base based on the multi-source information data; For the hydropower smart engineering construction project of A company, the project data management module obtains a three-dimensional BIM model of the engineering from a BIM design system through a pre-set interface adapter, which contains main engineering structure information and key attributes; at the same time, extracts WBS (work breakdown structure), plan and actual progress data of the project from a project progress management software; obtains construction log abstracts of key processes, main resource input conditions and important problem feedback from a daily construction management system. In addition, the module also accesses the core design drawings and important technical disclosure files of this stage from a document management system. The extracted various data, such as BIM model data, P6 plan data, construction log text, drawing files, etc., are corrected by the ETL tool built-in the module for non-standard records, ensure that all progress data adopts a unified date format and percentage representation method, identify the process name, completion status and problem description from the construction log text, and then collect the processed data into the cloud platform data storage layer deployed by the system.

[0024] Further, after data integration, the project data management module is committed to generating an intuitive and information-rich project view. The core of the view is to associate and visually map the actual progress data reported by the construction unit, the key status information in the construction log, and the corresponding engineering entities in the BIM three-dimensional model (such as a specific pouring unit of the dam, a certain load-bearing column of the plant, or a certain excavation section of the tunnel). For example, the current completion percentage of a WBS task can be directly reflected on its corresponding BIM component, clearly displayed in the three-dimensional model through different colors and labels. A company's management personnel can access this project view through the unified front-end interface provided by the system cloud platform, which is based on three-dimensional models and integrates key progress indicators (such as planned and actual comparisons) and the current status of major processes, providing a comprehensive and intuitive understanding of the progress of the project's core construction phase. To achieve accurate association between construction progress data, log status, and other management information and the corresponding engineering entities in the BIM three-dimensional model, two complementary methods are used. The first method is to pre-set the corresponding WBS code in the attribute parameters of the component during the BIM model design phase, and the system can automatically establish a link between the P6 plan task and the BIM component based on this after importing the data. The second method, as a supplement to the pre-set coding method or when the pre-set coding is not available, provides a human-computer interaction mapping tool that allows users to select P6 tasks and corresponding BIM components on the interface to assist the system in completing the matching and designation between the two.

[0025] By integrating BIM, progress, construction log, and other multi-source information data, and performing cleaning, unification, and key information extraction, a visual project view deeply associated with the BIM model is finally generated, effectively breaking the common data island phenomenon in hydropower projects. This significantly improves the accuracy, consistency, and real-time sharing level of project data, providing a key data foundation and unified cognitive platform for subsequent data-driven decision-making, intelligent analysis, and efficient multi-party collaborative management and control, which is an important prerequisite for realizing data-driven digital and intelligent collaborative management and control in hydropower projects.

[0026] Further, based on the project view and multi-source information data, a project management information library is constructed, which is specifically implemented as a hydropower engineering knowledge graph in A company's smart hydropower project. The knowledge graph aims to deeply integrate and associate key engineering elements and management information in the core construction phase of the project in a semantic manner, providing structured and networked data support for subsequent intelligent analysis and collaborative work.

[0027] Specifically, the construction of the knowledge graph relies first on the mapping between BIM components and WBS tasks, as defined in the project view, and core data extracted from various source systems and processed through ETL. For example, key engineering structural components in the BIM model (such as specific dam casting units, main beams and columns of powerhouses, and foundations for key equipment); WBS task items in the project schedule management software (including their planned attributes and logical relationships); metadata information about core design drawings and technical briefing documents; and key process progress descriptions and issue records extracted from construction log summaries—these data are defined as core entities in the knowledge graph. The project data management module then establishes relationships with clear business semantics between these core entities. For example, a WBS task node is connected to its corresponding specific engineering entity node in the 3D view through a precise BIM component relationship. This WBS task node, in turn, is connected to the construction log summary node, which records its daily progress, through a construction record relationship. If a specific issue is recorded in the construction log, the issue record node is associated with the relevant WBS task and BIM component to report the issue. The metadata nodes of a core design drawing are connected to the corresponding WBS tasks and BIM component nodes they describe or guide through design basis reference relationships. These relationships are established primarily based on the data mapping logic established in the project view and are ensured accurately through standardized methods such as matching the WBS codes in P6 with the WBS codes preset in the BIM component properties. The constructed knowledge graph is stored and managed on a cloud platform using graph database technology, facilitating efficient query and expansion.

[0028] The project management information database transforms the core project information originally scattered in different systems and views into an interconnected knowledge network, providing a key data foundation for the subsequent project risk analysis module to identify related risks and the project collaborative management module to drive context-aware workflows.

[0029] The project risk analysis module builds an intelligent risk analysis model to perform risk analysis on the project management information base and project views, generating dynamic assessment results, graded warning notifications, and auxiliary decision-making plans; The project risk analysis module retrieves and integrates multi-dimensional data related to contract performance from the project management information repository and the real-time updated project view. This data includes the contract budget estimate, detailed terms and conditions, real-time progress data for each relevant WBS task, payment settlement data, and records of engineering changes and claims generated during project execution. Because this data is semantically linked and structured within the knowledge graph, its consistency and integration are guaranteed.

[0030] Table 1 Example table of multi-dimensional data related to contract performance

[0031] Further, after acquiring and integrating the multi-dimensional data related to the specific contract performance in the knowledge graph, the intelligent risk analysis model immediately starts its risk analysis and evaluation process, the key of which is to use a hybrid analysis method that combines the experience rules of water and electricity industry contract management experts and machine learning algorithms. The method uses the semantic association capability of the knowledge graph to perform penetrating correlation analysis on complex performance data, and dynamically assigns weights to key risk factors based on the analysis results and context awareness.

[0032] Specifically, the processing flow of the hybrid analysis method first applies the pre-set rules derived from the experience of senior water and electricity contract management experts to the structured entities and their relationships in the knowledge graph through the expert rule engine. These rules can quickly identify contract performance conditions that match known high-risk patterns, such as a key payment node that does not match the previous engineering progress in the knowledge graph, and explicit penalties in the associated contract clauses. At the same time, to make up for the shortcomings of explicit rules in dealing with complex, unknown, and gradual risks, the process introduces a machine learning algorithm such as Gradient Boosting Decision Tree (GBDT). The GBDT model is pre-trained using historical project data within the platform (historical project data that has been structured and can be accessed in the knowledge graph), which can perform deep learning and pattern recognition on a wider and more multi-dimensional set of performance data features extracted from the current project knowledge graph (e.g., the frequency and average impact period of engineering changes in similar historical projects, the correlation between text features and processing results of claim events, the pattern of key resource price fluctuations and cost overruns, and the potential collaboration tension reflected in multi-party communication record metadata). In this way, the model can discover complex non-linear relationships, more hidden risk precursors, or emerging risk evolution trends that are difficult to capture through explicit rules, predict the probability of occurrence and potential impact of specific contract risks (such as major claim risks and key supplier default risks), and the output of the GBDT model, such as risk probability scores, abnormal pattern alerts, or key risk factor rankings, will serve as a powerful supplement to expert rule judgments, cross-validation, and an important basis for optimizing expert rule parameters. Finally, the expert rule engine output and the GBDT output are combined into a set to obtain preliminary risk results.

[0033] Furthermore, after obtaining preliminary risk results through the expert rule engine and GBDT machine learning model, the intelligent risk analysis model conducts a deep correlation analysis based on the hydropower project's professional knowledge graph. This step does not involve isolated, shallow assessments of identified risk points. Instead, it leverages the global, multi-dimensional semantic network unique to the knowledge graph to achieve penetrating insights into the inherent connections and complex transmission mechanisms between risks. This significantly differs from traditional risk assessment methods based on fragmented data sources and limited correlation models. Specifically, for each risk signal indicated by the preliminary risk identification results (e.g., a high-probability risk event output by the GBDT model, a contract clause warning triggered by an expert rule), the intelligent risk analysis model proactively traverses and reasoning through the knowledge graph, starting with the core entities associated with the signal (such as specific WBS tasks, contract clauses, BIM components, and supplier entities). It then follows pre-established structural connections (based on the inherent business logic of the hydropower project and mapped data) and semantic links dynamically discovered during analysis, performing a multi-path, multi-depth traversal and reasoning process. These semantic links span multiple dimensions, including the project's contract text, schedule network, cost breakdown structure, BIM 3D model, technical specifications, resource allocation, and interaction records among all parties involved in the project.

[0034] Furthermore, the dynamic weight assignment of risk factors is achieved through a dynamic weighting model, the flow chart of which is as follows: Fig. 2As shown, the model receives three types of data, the first is the quantitative indicators of the preliminary risk results output by the expert rule engine and the GBDT model, such as the initial level of risk, the occurrence probability score or the confidence of abnormal patterns, the second is the output results of deep correlation analysis about the importance of risk factors in the knowledge graph, such as whether the factor is located at the intersection of multiple important influence paths, the breadth of the potential impact range of the factor; the third is the context information of the current project (such as project phase, major events that have recently occurred and their impact level) in the knowledge graph. Standardize the three types of data, then for the above three types of standardized input data, the model presets a corresponding lookup table for each type of input, which converts each type of standardized input value into its specific contribution score to the maximum weight. For example, the higher the correlation key degree score, the greater the key degree contribution score obtained by converting it through the lookup table. First, select the adjustment rule according to the contribution score of the initial risk result, divide the initial risk contribution level into low, medium and high levels through the preset warning threshold, when the initial risk contribution level is determined to be low, the contribution score of the initial risk result will be converted into weight according to the rule, the weight is a dynamic weight; when the initial risk contribution level is determined to be medium, the contribution score of the initial risk result will be converted into weight according to the rule, the contribution score of the correlation output result will be converted into an adjustment coefficient, the dynamic adjustment coefficient will be obtained by adding 0.5 to the adjustment coefficient, and the dynamic weight will be obtained by multiplying the weight and the dynamic adjustment coefficient; when the initial risk contribution level is determined to be high, the contribution score of the initial risk result will be converted into weight according to the rule, then the correlation analysis output result and the context adjustment contribution score will be converted into correlation coefficient and context coefficient respectively according to the exponential function, and the dynamic weight will be obtained by multiplying the correlation coefficient and the context coefficient with the weight; finally, normalize all dynamic weights to ensure that the sum of the coefficients is 1, and finally multiply the corresponding risk factor quantitative risk value to generate dynamic evaluation results, early warning signals representing the performance risk state of the contract in different dimensions from the contract clause level, specific bid level, project overall level to enterprise operation level. The dynamic evaluation results will be output in the form of a report for system operators to view.

[0035] The project risk analysis module relies on the knowledge graph for deep correlation and dynamic weighting, converting multi-source data into precise multi-level risk insights and early warnings. This directly enhances data-driven decision-making and intelligent analysis capabilities, providing key technical support for realizing digital and intelligent collaborative management and control of hydropower projects and overcoming the challenges of traditional management and control modes.

[0036] Further, after the intelligent risk analysis model completes dynamic assessment on a specific risk and issues a warning, the project risk analysis module immediately starts the generation process of the auxiliary decision-making scheme. For the specific risk that has been identified and assessed, the module retrieves the disposal experience of historical similar risk cases according to the characteristics recorded in the hydropower engineering knowledge graph (such as risk type, cause, and current project stage), matches the system with the standardized response strategy library for various common hydropower engineering risks. Through this retrieval and matching process, the system automatically filters or combines to generate several preliminary alternative measures.

[0037] Subsequently, for each alternative measure, the module will further call the relevant data stored in the knowledge graph (for example, project resource unit price, labor hour rate, historical cost and benefit records of similar measures, current project plan parameters and contract benchmarks, etc.) for quantitative analysis to generate the key reference information required for decision-making, including providing the expected cost data required for implementing each alternative measure; the expected benefit evaluation data that can be brought by the reduction or elimination of the current risk after implementation; the comprehensive sorting consideration index for comprehensive evaluation, such as the expected execution cycle of the measure, technical feasibility and implementation complexity, and potential secondary impact on other aspects of the project (such as quality and safety). Finally, the project risk analysis module integrates the structured information of these alternative measures and their corresponding quantitative evaluation data (expected cost, expected benefit, and comprehensive consideration index) into an auxiliary decision-making scheme, which is presented for reference by project managers.

[0038] The auxiliary decision-making scheme function automatically generates and quantitatively evaluates various risk response measures through knowledge graph data, converts hydropower engineering experience and data into clear and comparable decision-making references, improves the data-driven and intelligent level of risk disposal decision-making, provides scientific basis for managers to select the optimal strategy, thereby enhancing the collaborative control efficiency, helping to alleviate the problems of traditional subjective decision-making and untimely response, and improving the data-driven and digital collaborative control efficiency of hydropower engineering.

[0039] The project collaborative management module uses a multi-layer perception model to process the hierarchical warning notifications and auxiliary decision-making schemes, calls the project management information base and project view as execution support, and generates finalized business results and management process records. The process diagram of the project collaborative management module is shown in Fig. 3

[0040] ​When the project collaborative management module receives the early warning signals and auxiliary decision-making schemes generated by the project risk analysis module, the project collaborative management module first uses these information, combined with the historical similar risk disposal success cases and management procedures related to the hydropower project stored in the knowledge graph, to start the dynamic adjustment of the related administrative approval process. The adjustment process uses a multilayer perceptron neural network model with an embedding layer integrated for category features at its input end to make intelligent decisions. The embedding layer is mainly responsible for converting high-base category data such as risk level encoding, risk type identification, historical similar case classification labels, and specific management procedure indexes extracted from input features into low-dimensional, dense real number vector representations. These feature vectors processed by the embedding layer are then sent to the multiple fully connected hidden layers of the MLP along with other numerical input features (such as quantified risk impact assessment, project stage parameters) for nonlinear transformation and high-order feature learning. The MLP neural network model is trained in advance based on a large amount of historical project data, which includes the features of different risk events, the risk response adopted at the time, the specific parameters of the administrative approval process (including the participating nodes in the process, the approval level setting, the actual processing time limit, and the list of supporting materials submitted), and the final execution efficiency of the process and the actual effectiveness of risk disposal. In actual operation, when the project collaborative management module receives new graded early warning notifications and auxiliary decision-making schemes, the MLP neural network model takes the level and type of the current risk, the features of the historical similar risk disposal cases retrieved from the knowledge graph, and the key elements of the existing management procedures as inputs, and directly outputs an optimized combination of process parameters in this situation through the complex nonlinear mapping relationship between the learned inputs and the optimal process parameters. These optimized parameters specifically represent dynamic adjustment suggestions for the participating nodes, approval levels, processing time limits, and required supporting material lists in the pre-set process. When determining the specific handlers of each participating node in the process, the system further calls the skill profiles of key personnel and historical workload data stored in the knowledge graph about the responsibility scope of each participating unit, to achieve intelligent and more matched handler recommendations. Table 2 shows an example of intelligent handler recommendations. Through this intelligent handler recommendation mechanism, each collaborative task can be quickly and accurately assigned to the most suitable handler, thereby improving overall work efficiency and quality.

[0041] Table 2 Example of intelligent handler recommendations

[0042] According to the risk level, historical success cases and regulations, the nodes, levels, time limits and materials of the risk response and approval process are dynamically optimized through a multi-layer perception model, and the intelligent recommendation processing personnel are combined with the knowledge graph to realize the process adaptation and precise resource matching based on data and intelligent algorithms, which significantly improves the efficiency, pertinence and decision quality of the risk response and administrative approval of hydropower projects.

[0043] When any of the above collaborative management activities and approval processes proceed to a pre-defined key approval node, such as the final confirmation, approval and issuance by key roles such as the project general manager, chief engineer, specific department supervisor or external supervision unit representative, the project collaborative management module will utilize the automatic calling platform to specify the third-party electronic signature service platform. At the node, the electronic documents to be approved (e.g. the completed engineering change order PDF file after all previous audits, the important construction scheme PDF version to be issued) will be pushed to the electronic signature service link, and the designated approver will be prompted to use his personal or unit digital certificate to perform electronic signature on the electronic document with legal effect under the support of the electronic signature service platform. After the electronic signature service platform completes the signature action, it will return the final business results with the effective digital signature of the approver to the collaborative management module of the system. In addition, the module will verify the validity of the signature, and when the signature is verified as valid, the signature information and signature time will be saved as an unalterable management process record in the approval process.

[0044] The electronic signature service integration fully digitizes the key approval link of hydropower projects, ensuring the legal effect of electronic signature of various final business results and the compliance and traceability of the approval process. Not only does it significantly improve the efficiency and convenience of multi-party collaborative approval, but more importantly, it provides highly reliable and unalterable digital credentials and process data for the digital and intelligent collaborative management system, strengthening the cornerstone of data-driven decision-making and serving as a key guarantee for realizing full-process closed-loop, standardized and intelligent management and control.

[0045] The project document management module receives the final business results and management process records, performs compliance automatic verification and processing on the data to be archived, and feeds back the management experience, risk cases and project information to the project management information database through knowledge extraction technology to dynamically update and optimize the project management information database.

[0046] When the project document management module receives the final business results generated by the project collaboration management module and the related management process records that need to be archived, in addition to performing standard authenticity, integrity, availability, and security four nature detection, the project document management module also starts a more in-depth and intelligent content compliance automatic checking and processing process. Specifically, first, the personalized and context-adaptive compliance judgment benchmark is intelligently constructed. For the current document to be checked, the module queries the project management information library, not only to retrieve the latest effective regulations, industry standards, company internal management systems and quality requirement details dynamically associated with the business context of the document, but also to combine the current state information and the latest risk level assessment results of the engineering entities related to the content of the scheme from the knowledge graph. According to the specific business context of the document, the most directly related clauses and requirements are intelligently selected from the general regulation standard knowledge base; further, according to the real-time state data and risk assessment results of the associated engineering entities, the specific risk level and engineering characteristic complexity of the document associated engineering entities are adjusted to dynamically adjust the strictness of the relevant compliance clauses; the general statements in the regulations and standards are converted into specific and quantifiable judgment standards for the current specific context; and the type list of the required supporting materials and the level of detail they should achieve are adaptively determined. Through the above fine adaptation process, the system finally constructs a context-adaptive compliance judgment benchmark for the current document to be checked.

[0047] After obtaining the highly customized and context-adaptive compliance judgment benchmark for the current document to be checked, the project document management module immediately uses natural language processing (NLP) technology to perform a deep semantic compliance review of the actual content of the document against the dynamically generated benchmark. The specific review process is that the NLP engine built into the system performs word segmentation, part-of-speech tagging, and syntax dependency analysis preprocessing on the input document text. Then, the engine will comprehensively use various NLP methods for analysis, accurately capture the key engineering elements mentioned in the document (such as equipment name, material specification, geological condition description), quantitative technical parameters, responsibility subject and time limit set, etc. information through named entity recognition (NER) technology; understand the logical relationships between these identified entities, the order of action execution and conditional dependencies through relationship extraction (RE) technology; further use semantic similarity calculation and text entailment judgment to accurately compare and verify the actual expression content in the document, the extracted key information and logical relationships with each specific, contextualized and quantified inspection standard in the compliance judgment benchmark generated in the previous step. This process focuses on understanding the true intent and integrity of the text, rather than simply performing keyword surface matching, to determine whether the document content substantially meets all the compliance requirements specified in the dynamic benchmark.

[0048] Further, if any deviation from the compliance judgment benchmark, information omission, internal logic contradiction, and potentially risky statement are identified by the NLP engine during this deep semantic compliance review process, the system will automatically determine these as potential risk points. For each identified risk point, the system will generate a structured prompt message containing three core parts: first, specific positioning information to clearly indicate the exact location of the risk point in the original document, such as accurately to chapter, paragraph, sentence, chart, and footnote number; second, explainability analysis, the system will briefly explain why this content is determined to be potentially non-compliant based on its judgment logic and associated compliance benchmark clauses, for example, which specific requirement of the compliance judgment benchmark is violated, which article of which standard is in conflict, and which specific risk situation of the current project is not fully considered; finally, revision guidance and suggestions, the system will provide preliminary and actionable modification suggestions, such as suggesting which missing information should be supplemented, which standard clauses should be referred to for revision, and which statements should be clarified and improved, so as to assist the document creator and reviewer in quickly locating the problem, understanding the reason, and efficiently completing the compliance modification of the document content.

[0049] By dynamically utilizing the regulations, standards, real-time project status, and risk levels in the knowledge graph, personalized and context-adaptive judgment benchmarks are constructed, and NLP technology is used for deep semantic review. This realizes the transformation of document compliance checking from manual dependence and static standards to intelligent automation and dynamic adaptation, greatly improving document quality and compliance review efficiency. Not only does it provide data-driven intelligent support for the standardized management of hydropower projects, reducing compliance risks, but also provides a high-quality and reliable information base for the effective operation of the overall digital and intelligent collaborative management system.

[0050] The system conducts a deep analysis of the text content of these documents and records that have passed the compliance check. In terms of NLP technology application, a pre-trained Transformer model is used for sequence labeling to achieve high-precision named entity recognition, accurately capturing key engineering objects, participant names, technical terms, risk description words, and core entities mentioned in the document; further, a bidirectional long short-term memory network model is used to identify and understand the complex logical relationships, action execution order, and conditional dependencies between the identified entities.

[0051] Further, after obtaining the complex logical relationships, the execution order of actions and conditional dependencies by using the NLP technology, the system will use the knowledge engineering method for subsequent structured extraction, semantic alignment and verification. The system will refer to the pre-constructed and detailed hydropower engineering ontology, which defines various concepts, entity attributes, standard relationship types in hydropower engineering, and several knowledge graph patterns customized for specific knowledge types, uses SPARQL queries to assist verification and reasoning of existing information in the knowledge graph, and according to the hydropower engineering ontology and knowledge graph patterns, actively identifies and integrates standardized and structured knowledge elements that can clearly reflect effective management practices, risk control key points and decision optimization logic in specific scenarios of hydropower engineering. For example, from a risk disposal report, the system can structurally extract the core knowledge that for X type risk, in Y project phase, Z measures are adopted, and the final risk level is reduced from A to B.

[0052] Further, these knowledge elements extracted by NLP and refined and structured by KE method will be accurately integrated and enriched into the project management information library through multi-dimensional semantic linking and explicit knowledge expression mechanism. Specifically, the system will establish a link with clear semantic types in accordance with the established pattern of the knowledge graph and the definition of the hydropower engineering ontology between each newly extracted structured knowledge element and the various engineering entities, corresponding business process nodes and cited regulatory standard clauses that already exist in the knowledge graph, for example, creating a new experience knowledge node, for each previously extracted structured knowledge element, connecting it with related entities through "applied to", "solved" and "optimized" relationship types, and creating a core instance node representing this experience in the knowledge graph, i.e. a contextualized experience knowledge unit. Inside this newly created unit instance, the key components of the experience will be stored in the form of structured attributes according to the pre-defined knowledge graph pattern, including clear context description, adopted management practices and technical measures, and final implementation effect and experience lessons. In addition, in order to ensure the contextualization of the experience knowledge unit and its availability in the knowledge graph, the system will use the associated information obtained in the NLP and KE stages to establish rich and clear multi-dimensional links between the newly created contextualized experience knowledge unit instance and a large number of existing engineering entities, process nodes and specification clauses in the knowledge graph that are closely related to its context.

[0053] By using natural language processing and knowledge engineering technology, the valuable and implicit management experience, risk control points and decision logic in project documents and records are intelligently converted into structured situational experience knowledge units in the knowledge graph that can be calculated, reasoned and reused. The automatic sedimentation, explicitness and deep correlation of project knowledge are realized, greatly improving the value density and availability of data. It not only provides high-quality experience data and knowledge base for more accurate data-driven decision-making, continuous optimization of risk analysis models (such as weights and thresholds) and intelligent recommendation of collaborative process paths in hydropower projects, but also is a key enabling link for building a learning organization and realizing the iterative upgrade and deepening of overall digital collaborative management capabilities.

[0054] After continuously enriching situational experience knowledge units in the project management information base, further learning and analysis procedures are performed on these accumulated situational experience knowledge units. The learning and analysis process aims to extract rules and knowledge from historical experience that can be used to improve system performance. Specifically, the system comprehensively uses specific data mining and machine learning techniques to deeply analyze the structured information contained in these situational experience knowledge units. The system uses the Apriori association analysis algorithm to process the feature data in the experience units, calculates the support and confidence of different situation, measures and effectiveness combinations in historical records, and discovers hidden strong association rules with statistical significance, which helps to reveal effective management practice patterns and the evolution and response rules of specific risks. The system uses case-based reasoning (CBR) logic combined with support vector machines (SVM) for performance evaluation and pattern recognition, uses the similarity matching mechanism of CBR to retrieve a set of historical cases highly similar to the current analysis focus in the project situation from a large number of experience units; then, the management measures and technical scheme features in these retrieved similar cases and their corresponding actual effectiveness are used as training to build, train and optimize the SVM supervised learning model. These trained and optimized models can then predictively evaluate the expected effectiveness of different management measures or technical schemes in a specific situation, quantitatively sort the effectiveness of historical decisions, and thus assist the system in identifying the optimal practice patterns and potential process optimization opportunities under specific conditions.

[0055] Further, the system conducts in-depth statistical learning and pattern analysis on the accuracy of historical early warning events and the actual development severity level of their corresponding risk events. The system uses receiver operating characteristic curve analysis to dynamically adjust the quantitative threshold for triggering early warning of different risk levels. This optimization aims to continuously improve the accuracy of risk warning, reduce false positives and false negatives, and ensure that the warning signal can most effectively guide management actions. In terms of optimization of the project collaboration management module, the system is also empowered based on the learning and analysis results of the situational experience knowledge units accumulated in the knowledge graph. These experience units record the actual execution data of various risk response processes and administrative approval processes in history, including the specific triggering context at the time, the actual participant nodes and approval level configuration in the process, the processing time of each link, the effectiveness and completeness of the submitted supporting material list, and the final execution effectiveness. The system uses process mining Alpha algorithm to automatically identify efficient process patterns, common bottleneck links, and best practice elements from these rich historical process execution data. These process optimization insights extracted through process mining and case-based reasoning (CBR) analysis are then used to optimize the recommended execution path for specific management processes. The specific implementation of this optimization is to directly adjust the internal model parameters and the tendency and weight configuration of the recommended logic of the machine learning model (multilayer perceptron MLP) for dynamic adjustment of the process. When similar project situations or specific types of management processes need to be started in the future, a knowledge base that continuously learns and evolves from successful and failed experiences can be used to recommend a process execution scheme that includes a more reasonable combination of process participant roles, a more streamlined and efficient approval level structure, more accurate estimated processing time, and more targeted requirements for supporting materials, thereby continuously improving the efficiency and effectiveness of collaborative work.

[0056] Through intelligent learning and analysis of historical experience units, dynamic self-optimization of risk warning thresholds and collaborative process paths is achieved. This closed-loop learning mechanism enables the system to continuously improve the accuracy of early warning and process efficiency, significantly enhancing the intelligence and adaptability of hydropower engineering risk response and collaborative work, and providing a core driving force for deepening digitalized collaborative management.

[0057] By constructing an integrated BIM project view and professional knowledge graph, breaking down data silos, and achieving deep integration and sharing of information, a solid foundation is laid for data-driven. Its hybrid intelligent risk analysis model and auxiliary decision-making function significantly improve the risk prediction capability and the intelligent level of decision-making. At the same time, the dynamic collaborative process driven by machine learning, intelligent personnel recommendation based on knowledge graph, and electronic signature application greatly enhance the efficiency of multi-party collaboration and the standardization and agility of management and control. In addition, the system's intelligent compliance verification and knowledge extraction mechanism, combined with the learning analysis of situational experience knowledge units, realizes the dynamic self-optimization of risk warning thresholds and collaborative process recommendation paths, ultimately forming a data-driven, intelligent evolution, and efficient collaborative management and control loop, which comprehensively improves the digital management and control efficiency of hydropower projects and effectively addresses the bottlenecks of traditional modes.

[0058] Example Two: B Company is a hydropower investment and operation company responsible for managing and operating multiple large and medium-sized hydropower stations in the river basin, including some old power stations that have been in operation for many years and newly built intelligent power stations. With the aging of generating units, difficulties in experience inheritance of technical personnel, and increasingly stringent safety and environmental protection regulatory requirements, B Company faces increasingly severe challenges in ensuring the safe, efficient, and economic operation of power stations. Therefore, B Company introduces a digital system for collaborative management and control of participating units in hydropower engineering construction provided by the present application.

[0059] In the operation and maintenance management of B Company, the core task of the project data management module is changed to the integration of data throughout the operation and maintenance cycle of each power station and the comprehensive perception of asset health status. Through the interface adapter, the module efficiently integrates real-time operation parameters from SCADA systems, state data such as vibration and oil temperature from online monitoring systems (CMS), work orders and historical maintenance records from equipment maintenance management systems (CMMS), manual inspection and periodic test reports, equipment accounts and technical specifications in BIM models and digital asset information databases, and other multi-source information data.

[0060] After cleaning, conversion, and semantic processing, these data are used to construct an operation period knowledge graph centered on hydropower station equipment assets. At the same time, the system generates a multi-dimensional, visual project view of power station health status and operation performance for operation and maintenance management. The view takes the digital twin model of the power station as the navigation basis and dynamically displays the main operation parameters, health scores, warning status, maintenance history of each key equipment, and related operation and maintenance document links, providing the operation and maintenance management team of B Company with an intuitive and comprehensive understanding of the overall asset status of the power station group.

[0061] Multi-dimensional data related to equipment health, operating conditions, maintenance history, external environment, etc. are retrieved from the operational period knowledge graph and real-time project view. Then, a hybrid analysis method that combines the experience rules of hydropower equipment operation and maintenance experts and machine learning algorithms is used for processing. For example, the expert rule base contains a large number of diagnostic logic for typical fault modes of specific equipment (such as hydro-generator units, main transformers, high-voltage switchgear, etc.). For example, if the temperature of a certain phase winding of the generator exceeds X degrees continuously, and the vibration value Y abnormally increases, it is determined as Z type fault risk, with high level. At the same time, the machine learning algorithm learns the pattern from a large amount of historical operation and monitoring data to identify those progressive equipment performance degradation trends or early fault features that are difficult to define by simple rules, and to predict the probability of occurrence of a specific fault or the remaining useful life (RUL).

[0062] Deep correlation analysis can help analyze how changes in the inflow of an upstream reservoir affect the operating conditions of the unit, and then correlate to the wear rate of the key components of the unit, and finally evaluate its impact on the unit overhaul cycle and the potential risk of power generation loss. The dynamic weight assignment of risk factors ensures that the contribution of various risk factors to the overall risk assessment can be adaptively adjusted under different operating modes, different seasons, and different equipment aging stages.

[0063] Finally, the module generates multi-level operational risk state quantitative assessment data and hierarchical early warning signals for B Company from the key equipment component level, single unit level, entire hydropower station level, and even the basin cascade hydropower station group operation level. When the health status of a certain equipment deteriorates, the predicted fault probability exceeds the threshold, or a certain operation indicator shows a major risk, the system will immediately send an early warning notice to the control center, power station operation and maintenance department, and relevant management personnel of B Company, and start the generation of auxiliary decision-making schemes. The auxiliary decision-making scheme here will provide various response measures such as "immediately arrange for inspection or precision diagnosis", "adjust the operation mode to reduce the risk", "plan ahead for maintenance and prepare spare parts", and "start emergency response plan", etc. for specific equipment fault warning or operation risk, with comprehensive evaluation information such as expected cost, expected benefit, urgency of implementation, and resource demand, to assist B Company in making the best operation and maintenance decision. After receiving the above operation risk warning and auxiliary decision-making scheme, the project collaboration management module will drive B Company and the necessary external collaboration units to efficiently execute the operation and maintenance related collaborative work processes.

[0064] When receiving the early warning of "certain key unit bearing vibration exceeds the standard, and there is a risk of major failure within 1 week" and the recommended decision-making scheme of "immediately arrange for precise diagnosis and prepare for emergency repair plan", the system will adjust the preset "equipment failure diagnosis and emergency repair process" dynamically according to the level and type of the early warning, and refer to the historical successful disposal cases and existing equipment maintenance management procedures of B Company in the knowledge graph. This adjustment may include automatically compressing some non-core approval links and improving the process priority according to the emergency level of the risk; intelligently recommending the optimal diagnosis execution team and necessary external experts according to the current task load, personnel skill portrait, and the available state of the required diagnosis equipment recorded in the knowledge graph; and dynamically generating a preliminary list of required supporting materials to assist in diagnosis according to the preliminary characteristics of the failure. When handling these operation coordination processes, the system will call and integrate the unified electronic signature service platform of B Company at key approval or confirmation nodes. The relevant responsible person completes the electronic signature by using his digital certificate through the system, ensuring the compliance, authenticity, and traceability of the operation decision and execution records. All process records, approval opinions, electronic signature information, and final operation reports of the collaborative work will be saved as the final business achievements and management process records.

[0065] The project document management module is responsible for receiving and managing various types of final business achievements and management process records generated in the above-mentioned collaborative operation processes. The project document management module first conducts intelligent content compliance automatic verification on these document materials. The system dynamically builds personalized and context-adaptive compliance judgment criteria according to the latest laws and regulations related to power station operation and maintenance, industry standards, B Company's internal operation and maintenance management system and equipment operation SOP stored in the knowledge graph, combined with the real-time state and risk level information of the current operating equipment. Then, the NLP technology is used to conduct deep semantic compliance review on the document content, identify potential violations of operation records, non-standard data reporting, missing safety measures description, and other issues, and generate prompt information containing specific positioning, explanation, and correction suggestions.

[0066] Further, the project document management module uses knowledge extraction technology to actively identify and extract structured knowledge elements reflecting effective management practices, key failure diagnosis logic, efficient emergency disposal plans, and equipment performance optimization techniques in the field of hydropower station operation and maintenance from these compliance-verified operation documents. These extracted operation experience knowledge elements will be transformed into contextualized experience knowledge units and linked to the corresponding equipment entities, fault codes, operation process nodes, and related regulation clauses in the knowledge graph, thereby continuously enriching and optimizing the operation professional knowledge graph of B Company.

[0067] Finally, these accumulated contextualized experience knowledge units will optimize the intelligent capabilities of the system. For example, through the learning analysis of a large number of successful and failed fault diagnosis and maintenance case experiences, the system can dynamically optimize the parameters and feature weights of the machine learning model for equipment fault prediction in the intelligent risk analysis module, improving the accuracy of fault early warning; at the same time, it can also optimize the setting of the early warning threshold, making it more suitable for the characteristics of different equipment in different life stages. For the project collaboration management module, the system can optimize the recommended execution path and resource allocation suggestion for specific operation and maintenance tasks by analyzing the execution data of historical efficient operation and maintenance processes, so that the overall operation and maintenance management system of B Company can form a virtuous cycle of continuous learning, self-evolution and performance improvement based on data and knowledge. At the same time, all important operation and maintenance documents and records will also generate electronic archive packages according to regulations, supporting the long-term knowledge management and compliance audit needs of B Company.

[0068] While embodiments of the present application have been shown and described with reference to particular embodiments thereof, it will be understood by those skilled in the art that various changes in form and details can be made therein without departing from the spirit and scope of the application. The scope of the application is defined by the appended claims and their equivalents.

Claims

1. A digital intelligence system for collaborative management and control of construction units involved in hydropower project construction, characterized by: include: The project data management module extracts multi-source information data from the entire life cycle of hydropower smart projects and their subsystems, and builds a project view and project management information database based on this multi-source information data; The project risk analysis module builds an intelligent risk analysis model to perform risk analysis on the project management information database and project views, generating dynamic assessment results, graded warning notifications, and auxiliary decision-making plans; The project collaborative management module uses a multi-layer perceptron model to process hierarchical warning notifications and auxiliary decision-making plans, calls the project management information library and project views as execution support, and generates finalized business results and management process records; The project document management module receives finalized business results and management process records, and performs automated compliance verification and processing on the data to be archived; Through knowledge extraction technology, management experience, risk cases and project information are fed back to the project management information database, and the project management information database is dynamically updated and optimized.

2. The digital intelligent system for collaborative management and control of construction units involved in hydropower project construction according to claim 1 is characterized in that: The process of constructing a project view includes: Integrate engineering plans and actual progress data, cost accounting and contract performance data, and quality inspection and safety control process data related to hydropower smart projects from various subsystems of various smart projects; integrate various types of management process data, and conduct multi-dimensional association and status mapping with the engineering entity information contained in the BIM three-dimensional building information model corresponding to the hydropower smart project, to form a construction project view that includes time dimension, space dimension, engineering status, management progress and key indicators.

3. The digital intelligent system for collaborative management and control of construction units involved in hydropower project construction according to claim 1 is characterized in that: The project management information database is specifically a hydropower engineering professional knowledge graph. The knowledge graph describes and stores the relationship between engineering elements, management processes, resource allocation, contract terms, risk factors and industry specifications and standards in a semantic way, which is used for advanced query and reasoning.

4. The digital intelligent system for collaborative management and control of construction units involved in hydropower project construction according to claim 1 is characterized in that: The risk analysis process performed by the intelligent risk analysis model includes: Based on the integrated contract budget data, terms and conditions data, real-time progress and payment settlement data, engineering change and claim data obtained from the project management information database and project view, a hybrid analysis method that integrates the experience rules of contract management experts in the hydropower industry and machine learning algorithms is used to conduct correlation analysis on multi-dimensional performance data and assign layered dynamic weights to risk factors; dynamic assessment results of the performance risk status of the contract in different dimensions, graded early warning notifications and auxiliary decision-making plans are generated.

5. The digital intelligent system for collaborative management and control of construction units involved in hydropower project construction according to claim 4 is characterized in that: The decision support program specifically outputs a variety of alternative response measures for identified specific risks, as well as decision reference information including expected cost data, expected benefit evaluation data and comprehensive ranking consideration indicators corresponding to each alternative response measure.

6. The digital intelligent system for collaborative management and control of construction units involved in hydropower project construction according to claim 1 is characterized in that: The process of using the multi-layer perceptron model to process hierarchical early warning notifications and auxiliary decision-making plans includes: based on the level and type of the hierarchical early warning notifications and the historical similar risk handling cases and management procedures of hydropower projects contained in the project management information database, using the multi-layer perceptron model trained based on historical project success cases to dynamically adjust the preset risk response process and administrative approval process. The adjustment includes optimizing the process participation nodes, approval levels, processing time limits and the list of required supporting materials; when determining the process participation nodes, further calling the responsibilities of the participating units and personnel skills portrait data in the project management information database for intelligent recommendation of processing personnel.

7. The digital intelligent system for collaborative management and control of construction units involved in hydropower project construction according to claim 1 is characterized in that: The process of generating finalized business results and management process records includes calling the electronic signature service at key approval nodes when handling collaborative project management activities, engineering change approval and important plan review to ensure the validity of the digital signature of the finalized business results and the compliance of the approval process.

8. The digital intelligence system for collaborative management and control of construction units involved in hydropower project construction according to claim 1 is characterized in that: The process of automated compliance verification and processing of data to be archived includes: intelligently constructing a context-adaptive compliance judgment benchmark based on the latest valid laws, standards and management systems stored in the project management information library and dynamically associated with the current document business context, combined with the engineering entity status and risk level information obtained from the project management information library; using natural language processing technology to conduct a deep semantic compliance review of the document content, and at the same time generating prompt information containing specific positioning, explainability analysis and correction guidance, and feeding back the compliance issues identified in the verification and effective handling experience to the project management information library.

9. The digital intelligent system for collaborative management and control of construction units involved in hydropower project construction according to claim 1 is characterized in that: The process of feeding back to the project management information database includes: using natural language processing and knowledge engineering technology to actively identify and extract structured knowledge elements that can reflect effective management practices, risk control key points and decision-making optimization logic in the hydropower project scenario from the finalized business results that have passed compliance verification, management process records and related compliance guidelines and correction suggestions; the extracted structured knowledge elements are multi-dimensionally semantically linked and explicitly expressed with the existing engineering entities, business process nodes, and regulatory standard clauses in the project management information database to form contextualized experience knowledge units that can be understood and reasoned by computers and fed back to the project management information database.

10. The digital intelligent system for collaborative management and control of construction units involved in hydropower project construction according to claim 1 is characterized in that: The dynamic update and optimization of the project management information library includes the ability to learn and analyze contextualized experience knowledge units, dynamically update and optimize the warning threshold settings used in the intelligent risk analysis model and the recommended execution path of the management process of the project collaborative management module.

Images