Method and system for pushing construction operation management and control knowledge based on power station construction unit

Abstract

The invention relates to a construction operation management and control knowledge pushing method and system based on a power station construction unit, and belongs to the technical field of power station construction management, and the method comprises the steps: receiving project information, and recognizing a task name and project basic information in the project information; performing semantic analysis on the task name, and generating an intelligent extension code of the current WBS entry according to an analysis result; associating an experience set, a standard specification term set, a risk point set and a construction period and cost data set for the current WBS entry; generating a project scene factor set according to the project basic information; according to the project scene factor set and the data set associated with the current WBS entry, generating a project forced check list and a risk special item check list, and generating a project main execution list after fusion; and associating a person in charge for the project main execution list according to the project organization structure, the block to which the intelligent extension code belongs and the skill keyword required by the current WBS entry. The method has the beneficial effects that the decision response speed is increased, and the project construction quality is improved.

Description

Technical Field

[0001] This application relates to the technical field of power plant construction management, and in particular to a method and system for knowledge dissemination for construction operation control based on power plant construction units. Background Technology

[0002] With the continuous growth of energy demand, power plant construction projects are increasing in number and scale. Power plant construction involves numerous complex stages and professional fields, including civil engineering, electrical equipment installation, and commissioning. The safety, compliance, and efficiency of the construction process are crucial to ensuring the stable operation of the power plant and energy supply. However, traditional power plant construction management methods are gradually revealing many shortcomings when dealing with complex and ever-changing project needs and risks, necessitating a more scientific and intelligent management solution to improve management efficiency.

[0003] Currently, power plant construction relies heavily on manual methods for creating project plans and task lists. First, project managers manually identify task names and basic information based on experience and project requirements, then categorize and organize them. Next, a responsible person and approximate timeline are assigned to each task, forming a preliminary construction plan. During construction, progress and quality are monitored through regular on-site inspections and meetings, with quality control and safety management implemented according to pre-established standards and specifications.

[0004] However, because task information and experience data are isolated, it is difficult for each construction node to obtain comprehensive and accurate standards, specifications, historical cases and risk data in real time. As a result, the decision-making process often relies on personal experience, the response speed is slow and it is prone to deviation, thus affecting the overall construction quality of the project. Summary of the Invention

[0005] To improve decision-making response speed and thus enhance project construction quality, this application provides a method and system for knowledge dissemination in construction operation management based on power plant construction units.

[0006] Firstly, this application provides a method for knowledge dissemination regarding construction operation management based on power plant construction units, employing the following technical solution: A method for knowledge dissemination in construction operation management based on power plant construction units includes: Receive project information and identify the task name and basic project information in the project information; Semantic analysis is performed on the task name, and based on the analysis results, a smart extended code for the current WBS entry is generated. The smart extended code includes a basic WBS code and a semantic extended tag. Associate the current WBS entries with experience sets, standard and specification clause sets, risk point sets, and schedule and cost datasets; Based on the basic information of the project, a set of project scenario factors is generated; Based on the project scenario factor set and the dataset associated with the current WBS entries, generate a mandatory project inspection checklist and a risk-specific inspection checklist; The risk-specific inspection checklist is merged with the project mandatory inspection checklist to generate the project master execution checklist; Based on the project's organizational structure, the section to which the intelligent extended code belongs, and the skill keywords required for the current WBS entry, the primary and alternative responsible persons are associated with the project's main execution list.

[0007] By adopting the above technical solutions, through semantic-driven WBS intelligent extended coding and dynamic association of multi-source data, the silos between task information and experience data are broken down. This allows each construction node to access standard specifications, historical cases, and risk databases in real time, improving the responsiveness of decision-making. The checklist generation mechanism based on project scenario factors integrates rigid standard requirements with flexible risk control. The resulting master execution checklist ensures industry compliance standards while dynamically adjusting control priorities based on project-specific factors, effectively reducing management blind spots caused by insufficient scenario adaptation. Intelligent responsibility allocation matches people with tasks, automatically associating responsible entities with organizational structure and required skill keywords, reducing the subjectivity of human assignment and enhancing team collaboration's fault tolerance through a backup mechanism. In summary, this solution, through the combination of data-driven and intelligent decision-making, effectively shortens the project preparation cycle, reduces human decision-making bias, and improves compliance and safety during construction through standardized checklists and dynamic risk management.

[0008] Optionally, the specific steps for associating the current WBS entry with the experience set, standard specification clause set, risk point set, and schedule and cost dataset include: Search the historical project database for historical similar WBS entries that match the intelligent extended code; If a match is found, the current WBS entry will automatically inherit the historical experience set, standard specification clause set, risk point set, and historical duration and cost dataset from the historically similar WBS entries. If no match is found, the general template library is called to generate an initial dataset, which is then pushed to the expert review library. After expert correction, an experience set, a standard specification clause set, a risk point set, and a schedule and cost dataset are generated and associated with the current WBS item.

[0009] By adopting the above technical solution, the system leverages the matching capabilities of intelligent extended coding to prioritize the use of similar case data in the historical project database. This enables the rapid reuse of experience sets, standards and specifications, risk points, and schedule and cost data. This process reduces repetitive work and enhances the reliability of decision-making through the accumulation and application of historical data. For new scenarios without directly matching historical data, the system automatically uses a general template library to generate a basic dataset. Simultaneously, an expert review mechanism is introduced for dynamic correction, ensuring both the standardization and timeliness of data generation while mitigating limitations in specific scenarios through the intervention of professional experience. This collaborative model of efficient machine matching combined with precise expert calibration ensures that each WBS item receives data support highly aligned with the actual project, avoiding the inefficiency and errors of traditional manual data association.

[0010] Optionally, the specific steps for generating the mandatory project checklist and the risk-specific checklist based on the project scenario factor set and the dataset associated with the current WBS entries include: Iterate through each clause in the set of standard and specification clauses, where each clause predefines the conditions under which it takes effect; Select the normative clauses that meet the scenario conditions of the current project scenario, and adjust the detection standards of the normative clauses according to the scenario factors in the project scenario factor set. Then, add the adjusted normative clauses to the project mandatory inspection list. Assess the probability of occurrence and impact of each risk point in the risk point set under the current project context, and calculate the corresponding risk value; Risk points with risk values ​​exceeding the risk threshold are identified, and preventive inspection items are associated with these risk points based on the experience set, and these items are added to the risk-specific inspection list.

[0011] By adopting the aforementioned technical solutions and leveraging the intelligent matching of standard and regulatory clauses with project scenario factors, and through predefined effective conditions screening and dynamic adjustment of testing standards, the mandatory inspection checklist can both strictly adhere to industry compliance requirements and achieve differentiated adaptation based on the specific scenario characteristics of projects. This avoids the redundancy or omissions of traditional fixed checklists in complex scenarios. Simultaneously, by combining experience sets to match preventative inspection measures for high-risk items, the risk-specific checklist can focus on key risk areas, forming a closed-loop management system of risk identification, impact assessment, and prevention and control. This checklist generation logic, which integrates rigid regulatory requirements with flexible risk prevention and control, not only improves the targeting and efficiency of inspection work but also reduces the probability of violations and risk events from the source through scenario-based adjustments and proactive preventative measures.

[0012] Optionally, the steps following the association of preferred and alternative responsible persons with the project master execution list may include: After the person in charge receives the inspection tasks from the main execution list, the tasks are broken down into weekly or daily plans based on the planned start date, planned end date, and the person in charge's current workload. The broken-down weekly or daily plans will be synchronized as schedule items to the responsible person's personal calendar or work platform.

[0013] By adopting the above technical solution, after the responsible person confirms receipt of the task, the system automatically and intelligently breaks it down based on the planned cycle and individual workload. The inspection tasks in the main execution list are refined into directly executable weekly or daily plans, avoiding task backlog or resource idleness. Through synchronization with personal calendars or work platforms, the broken-down plans are directly converted into the responsible person's schedule items, achieving the integration of control requirements with daily work. This mechanism not only eliminates intermediate links in task communication, ensuring accurate delivery of execution requirements, but also improves the feasibility of task execution through load adaptation and strengthens the rigid constraints of time management through schedule embedding. This transforms the control requirements for power plant construction from paper plans into action schedules, improving the timeliness and quality of task execution.

[0014] Optionally, the control method further includes: Generate a predicted timeline based on the actual progress reported by the responsible party; Calculate the deviation between the predicted and planned completion dates of the task based on the predicted and planned timelines; A tiered warning is triggered when the deviation value exceeds a set threshold.

[0015] By adopting the above technical solution, a predicted timeline is generated based on the actual progress data provided by the responsible parties. Through intelligent comparison with the planned timeline, the deviation from the task completion date is calculated. When the deviation exceeds a set threshold, a tiered early warning is automatically triggered, simultaneously notifying the responsible parties and higher-level managers, forming a rapid response channel between frontline execution and management levels. This effectively solves the problems of delayed progress information and untimely risk detection in traditional project management. Dynamic prediction provides forward-looking management decisions, and tiered early warnings ensure timely problem handling. Ultimately, while ensuring transparency in task execution, it enhances the ability to control project progress risks.

[0016] Optionally, the method further includes: N days before the task expires, select the top K lessons learned from the associated lessons learned set that have the highest matching degree with the current execution status of the task. By combining the standard and specification clauses, a personalized knowledge package is generated and pushed to the responsible person's mobile device.

[0017] By adopting the above technical solution, during the critical window N days before the task's due date, the system automatically and intelligently selects the top K cases with the highest matching degree from the experience and lessons learned based on the current execution status. This, combined with a set of standard and regulatory clauses, forms a targeted knowledge package and pushes it to the responsible person's mobile device, creating a dual guarantee of risk warning and compliance guidance. This effectively solves the problems of delayed knowledge transfer and insufficient scenario adaptability in traditional projects. By proactively pushing knowledge, historical experience is transformed into real-time decision support, and mobile access ensures convenient knowledge acquisition. Ultimately, this allows responsible persons to quickly learn from past mistakes and clarify regulatory boundaries during critical stages of task execution, reducing the probability of repeating errors from the source.

[0018] Optionally, the method further includes: After the task is completed, the task completion status is sent by the person in charge via mobile device. The task completion status includes the actual status, actual time taken, difficulty rating and problem description. The actual time spent is compared with the planned duration to generate a deviation report. The root causes of the deviation are analyzed in conjunction with the difficulty rating and synchronized to the experience set. Extract key events from the problem description, label high-frequency problems according to the risk point set and standard specification clause set, and synchronize them to the risk point set.

[0019] By adopting the above technical solution, multi-dimensional data including actual status, time consumption, difficulty rating, and problem description is automatically collected after the task is completed. A deviation report is generated by comparing the actual time consumption with the planned schedule, and root cause analysis is performed in conjunction with the difficulty rating. This allows for the identification of different types of deviation root causes, such as insufficient capabilities, planning oversights, or external interference, ensuring the relevance of lessons learned. Simultaneously, by extracting key events from the problem descriptions and automatically tagging high-frequency problems with existing risk point sets and standard specifications, scattered problem descriptions are transformed into structured risk characteristic data. This effectively solves the problems of fragmented experience summarization and delayed knowledge accumulation in traditional projects. Standardized data collection templates ensure the completeness of experience, root cause analysis enhances the applicability of lessons learned, and tagging strengthens the reusability of knowledge. Thus, the execution process of each task becomes a source of updates for the system's knowledge base. As the project progresses, the coverage and accuracy of the experience set and risk point set are continuously optimized, forming a virtuous cycle of execution-summarization-optimization-re-execution.

[0020] Secondly, this application provides a system for knowledge dissemination in construction operation management based on power plant construction units, employing the following technical solution: A system for knowledge dissemination in construction operation management based on power plant construction units includes: The information receiving module is used to receive project information; The information recognition module is used to identify the task name and basic project information in the project information; The information processing module is used to perform semantic analysis on the task name and generate intelligent extended codes for the current WBS entry based on the analysis results. The intelligent extended codes include basic WBS codes and semantic extended tags, and are used to generate a set of project context factors based on the basic information of the project. The task generation module is used to associate experience sets, standard specification clause sets, risk point sets, and schedule and cost datasets for the current WBS entry. It is used to generate a mandatory project checklist and a risk-specific checklist based on the project scenario factor set and the dataset associated with the current WBS entry. It is used to merge the risk-specific checklist and the mandatory project checklist to generate the main project execution list. It is also used to associate the primary and alternative responsible persons for the main project execution list based on the project organizational structure, the section to which the intelligent extended code belongs, and the skill keywords required by the current WBS entry.

[0021] Thirdly, this application provides a computer device that adopts the following technical solution: A computer device includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method for knowledge push for construction operation management based on power plant construction units as described in the first aspect.

[0022] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in the first aspect, a method for knowledge dissemination for construction operation management based on power plant construction units.

[0023] In summary, this application includes at least one of the following beneficial technical effects: By leveraging semantically driven WBS intelligent extended coding and dynamic association with multi-source data, the silos between task information and experience data are broken down, enabling each construction node to access standard specifications, historical cases, and risk databases in real time, thus improving decision-making responsiveness. A checklist generation mechanism based on project scenario factors integrates rigid standard requirements with flexible risk control. The resulting master execution checklist ensures industry compliance standards while dynamically adjusting control priorities based on project-specific factors, effectively reducing management blind spots caused by insufficient scenario adaptation. Intelligent responsibility allocation matches people with tasks, automatically associating responsible parties with organizational structure and required skill keywords, reducing the subjectivity of human assignment and enhancing team collaboration's fault tolerance through a backup mechanism. In summary, this solution, through the combination of data-driven and intelligent decision-making, effectively shortens project preparation cycles, reduces human decision-making bias, and improves compliance and safety during construction through standardized checklists and dynamic risk management. Attached Figure Description

[0024] Figure 1 This is a first flowchart of an embodiment of the method of this application; Figure 2 This is a second flowchart of an embodiment of the method of this application; Figure 3 This is a third flowchart of an embodiment of the method of this application; Figure 4 This is the fourth flowchart of an embodiment of the method of this application. Detailed Implementation

[0025] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figures 1-4 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0026] The first embodiment of this application discloses a method for knowledge dissemination in construction operation management based on power plant construction units. (Refer to...) Figure 1 The method may include S110-S170: S110 receives project information and identifies the task name and basic project information in the project information; S120, perform semantic analysis on the task name, and generate intelligent extended coding for the current WBS entry based on the analysis results. The intelligent extended coding includes basic WBS coding and semantic extended tags. S130 is the current WBS item associated with the experience set, standard specification clause set, risk point set, and schedule and cost dataset; S140, Generate a set of project scenario factors based on the basic project information; S150, Based on the project scenario factor set and the dataset associated with the current WBS entries, generate a mandatory project checklist and a risk-specific checklist; S160 integrates the risk-specific inspection checklist with the project mandatory inspection checklist to generate the main project execution checklist; S170, based on the project's organizational structure, the section to which the intelligent extended code belongs, and the skill keywords required for the current WBS entry, associates the primary and secondary responsible persons for the project's main execution list.

[0027] Specifically, for steps S110-S120, the core task in the database construction phase is to establish a WBS-related knowledge base under unified coding rules. This is implemented by using the hierarchical work breakdown structure recommended by ISO or PMBOK as a foundation, combined with eight defined business segments such as coal-fired units, gas-fired (gas turbine) units, photovoltaic projects, onshore wind power, offshore wind power, substation engineering, transmission lines, and nuclear power engineering (State Power Investment Corporation, China General Nuclear Power Corporation), to design a five-level, twelve-bit basic WBS coding system: the first level is the project type (e.g., A represents a coal-fired unit); the second level is the functional section (e.g., A1 represents the boiler island); the third level is the professional category (e.g., A1-ME represents the mechanical part); the fourth level is the subsystem / equipment group (e.g., A1-ME-01 represents the coal feeder system); and the fifth level is the specific work item (e.g., A1-ME-01-001 represents coal feeder installation). This coding system not only meets the uniqueness requirement but also supports path resolution and hierarchical backtracking.

[0028] Natural language processing models such as BERT-BiLSTM-CRF are used to perform entity recognition and keyword extraction on task names in historical projects. For example, when inputting "main transformer placement and foundation grouting," the system automatically identifies three action-object combinations: "main transformer," "placement," and "grouting," and then maps them to generate a semantic extended tag set ["Electrical_Transformer", "Installation", "Grouting"], forming an intelligent extended coding structure of "basic coding + semantic tags." All raw data comes from ERP, PMIS, as-built documentation, and expert experience documents. After ETL cleaning, it is stored in the graph database Neo4j, enabling a network of relationships between WBS items and lessons learned, standards and specifications such as GB50231 and DL / T5161, risk points such as "not wearing a safety belt while working at height," schedule, and cost. A visual editing interface is also provided, allowing project managers to manually adjust relationships or add missing items.

[0029] S130, the specific steps for associating the current WBS entries with the experience set, standard specification clause set, risk point set, and schedule and cost dataset include: Search the historical project database for similar WBS entries that match the smart extended code; If a match is found, the current WBS entry will automatically inherit the historical experience set, standard specification clause set, risk point set, and historical duration and cost dataset from similar historical WBS entries. If no match is found, the general template library is called to generate an initial dataset, which is then pushed to the expert review library. After expert correction, an experience set, a standard specification clause set, a risk point set, and a schedule and cost dataset are generated and associated with the current WBS item.

[0030] Specifically, the selection phase involves automatically generating various execution lists applicable to the current project based on the established knowledge base. This is implemented by the system calling a similarity matching algorithm: comprehensively using cosine similarity to calculate semantic closeness between text descriptions, tree path matching to assess WBS coding hierarchy consistency, and Jaccard coefficients to compare semantic tag overlap rates, thereby retrieving the most similar reference project from the historical project database. For example, if a newly built 500MW offshore wind farm is highly consistent with a project in Zhoushan, Zhejiang three years prior in terms of installed capacity, turbine model, and construction window, the system determines it as a high-match case and automatically inherits the experience set, standard specifications, risk point set, and historical construction period and cost dataset from that historical project regarding key items such as "single pile driving deviation control" and "submarine cable laying meteorological window early warning."

[0031] If no matching item is found, the default configuration package in the general template library will be used. This template is divided into 8 project categories, with each category containing no fewer than 500 standardized entries and default parameters. For example, gas turbine unit tasks will load relevant content from the "DL / T 5194 Gas Turbine Installation Code" by default. The entry will then be pushed to the expert review database, where it will be reviewed and corrected online by a three-level review mechanism (engineer → chief engineer → chief engineer). After closed-loop confirmation, the first version of the dedicated dataset will be generated and fed back into the historical knowledge base.

[0032] Reference Figure 2 S150, the specific steps for generating the project mandatory checklist and risk-specific checklist based on the project scenario factor set and the dataset associated with the current WBS entries include S210-S240: S210, iterate through each clause in the standard specification clause set, and each clause predefines the conditions under which it takes effect; S220: Select the normative clauses that meet the scenario conditions of the current project scenario, and adjust the testing standards of the normative clauses according to the scenario factors in the project scenario factor set. The adjusted normative clauses are then added to the project mandatory inspection list. S230, assess the probability of occurrence and impact of each risk point in the risk point set in the current project context, and calculate the corresponding risk value; S240: Filter out risk points whose risk values ​​exceed the risk threshold, and associate preventive inspection items with the risk points based on the experience set, and add them to the risk-specific inspection list.

[0033] Specifically, for step S140, after receiving the basic project information, the system automatically derives a set of scenario variables affecting decision-making based on this information. These factors are divided into static attributes, such as the region being within the coverage area of ​​the Southern Power Grid and the climate being subtropical monsoon, and dynamic conditions, such as the contract type being DBB (Design-Tender-Build) and the owner's special requirement for "zero-defect handover." The system has a built-in scenario factor knowledge graph, where each node represents an environmental characteristic, and edge relationships define the strength of its association with other specifications or risks. For example, "high temperature and high humidity areas" will increase the risk weight of "extended concrete curing period," while "foreign-controlled projects" will trigger stricter HSE audit clauses.

[0034] The system then iterates through every clause in the standard specification collection. Each specification has its effective conditions marked upon entry into the database. For example, a welding process standard may specify: "Applicable only to Q355 and above steel + ambient temperature > 5℃ + relative humidity < 80%". The system matches the current project scenario factors against these prerequisites one by one to filter out the applicable clauses.

[0035] In addition, the system supports dynamic adjustment of testing standards based on scenario factors. For example, when performing steel structure welding in "severely cold winter regions," the original specification requires a preheating temperature of 100℃. However, the system, combining local weather forecasts and historical low-temperature data, intelligently raises the temperature to 120℃ and notes the reason: "The lowest temperature in the past three years reached -28℃, posing a risk of cold cracking." All the selected and optimized clauses form a mandatory inspection checklist for the project.

[0036] Simultaneously, the system conducts quantitative analysis on inherited or newly created risk point sets. Each risk point includes the probability of occurrence P (derived from historical data based on a Bayesian network), the degree of impact I (scored across four dimensions: safety, schedule, quality, and cost), and mitigation measures M. The system calculates the risk value using the formula R=P×I and sets three threshold levels: low (<15), medium (15-30), and high (>30). For example, in the Guangdong sea area project, "short offshore operation window" has P=0.7, I=25, and a score of 17.5, placing it in the medium-risk range. The system then searches for relevant preventative measures from the experience set, such as "applying for navigation warnings in advance" and "establishing a backup vessel and equipment resource pool," and converts these into specific preventative inspection items added to the risk-specific inspection checklist. For high-risk items, the system also suggests increasing the inspection frequency or introducing third-party supervision.

[0037] The system employs a priority fusion algorithm: mandatory inspection items are placed at the top by default, risk-specific inspection items are inserted in order of risk level, and multiple inspections under the same task are automatically merged and displayed. For example, under "Wind Turbine Lifting Operation", multiple items such as "Non-destructive Testing of Welds (Mandatory)", "Meteorological Warning Response Verification (Risk)", and "Review of Special Operation Personnel's Certification Status (Dual Attribute)" will be integrated to form a clearly structured and clearly defined task package, i.e., the main execution list of the project.

[0038] In S170, the steps following the association of the preferred and alternative responsible persons with the project master execution list also include: After the person in charge receives the inspection tasks from the main execution list, the tasks are broken down into weekly or daily plans based on the planned start date, planned end date, and the person in charge's current workload. The broken-down weekly or daily plans will be synchronized as schedule items to the responsible person's personal calendar or work platform.

[0039] Specifically, in the responsibility definition phase, it is necessary to complete the task responsibility assignment and plan embedding, realizing the transformation from macro-level list to micro-level execution. The system first connects to the enterprise's organizational structure management system to obtain the role permissions, skills, expertise, and qualification information of each functional department, participating unit, and its personnel. For example, an electrical installation engineer named Zhang has a high-voltage electrician's certificate, is familiar with the IEC61850 communication protocol, and has led two photovoltaic substation projects. His skill tags are ["HV_Electrical", "IEC61850", "Substation_Project"]. After the project master execution list is generated, the system uses a combination of rule engines such as Drools and recommendation algorithms such as collaborative filtering to match the primary and secondary responsible persons for each WBS entry. The matching logic includes: basic rules such as "substation commissioning tasks must be undertaken by certified relay protection personnel", and advanced rules such as "tasks involving offshore construction should be assigned to those with tidal operation experience".

[0040] In addition, the system will also consider the current workload of the person in charge. For example, by reading the number of pending items in the OA system, the weight of ongoing tasks, and the historical completion efficiency curve, the system can predict the workload saturation for the next two weeks and avoid over-allocation.

[0041] Once the person in charge confirms receipt of the task, the system immediately triggers a plan breakdown mechanism: based on the task's planned start and end times, complexity (preliminarily judged by difficulty rating), and the person in charge's average daily effective working hours (usually set at 6 hours), the system breaks it down into weekly or daily plans. For example, a "GIS equipment withstand voltage test" originally scheduled to be completed in 5 days is broken down by the system into five sub-steps: "test preparation → wiring inspection → voltage boost test → data analysis → report preparation," which are scheduled to be executed each morning from Wednesday to Friday of the following week. The system also automatically generates to-do items and synchronizes them to the person in charge's schedule module, such as WeChat Work / DingTalk / self-developed mobile app.

[0042] Reference Figure 3 Furthermore, the method also includes S310-S330: S310, Generate a predicted timeline based on the actual progress reported by the person in charge; S320, calculate the deviation between the predicted completion date and the planned completion date of the task based on the predicted time axis and the planned time axis; S330 triggers a tiered warning when the deviation value exceeds the set threshold.

[0043] Specifically, during the execution phase, the core is to achieve intelligent push notifications and process-oriented guidance, thereby improving the compliance awareness and operational accuracy of frontline personnel. Based on the actual progress reported regularly by responsible personnel, such as "30% complete" or "2 days delayed due to weather," the system combines the remaining workload and resource allocation trends to generate a dynamic forecast curve using Earned Value Management (EVM) and Monte Carlo simulation technology. This curve is compared with the original plan, automatically generating a deviation report. For example, if foundation treatment work originally planned for 20 days is now predicted to take 25 days, the deviation reaches +25%, exceeding the preset 15% warning line.

[0044] If the deviation exceeds the limit, the system will activate a three-level response mechanism: a yellow alert reminds the responsible person to strengthen control; an orange alert notifies their immediate supervisor to intervene and coordinate; and a red alert is sent directly to the project director and copied to the company's operations center. The alert information includes a preliminary assessment of the root cause, such as "material supply delays account for 60% of the delay," a predicted scope of impact, such as the potential for a 7-day delay in downstream processes, and recommended actions, such as initiating a backup supplier process.

[0045] Furthermore, the method also includes: N days before the task expires, select the top K lessons learned from the associated lessons learned set that have the highest matching degree with the current execution status of the task. By combining the standard and specification clauses, a personalized knowledge package is generated and pushed to the responsible person's mobile device.

[0046] Specifically, N days before the task's completion (usually N=7), the system retrieves the top K records (usually K=3) most relevant to the current task status from the lessons learned set. Matching criteria include multi-dimensional features such as task type, geographical environment, seasonal factors, and equipment model used. For example, when a blade installation task at a northern wind farm in winter is nearing its end, the system might send the following notifications: "In 2022, the Inner Mongolia project experienced a slippage accident involving the lifting equipment due to frost; it is recommended to start the de-icing procedure 4 hours in advance," and "When nighttime temperatures drop below -20℃, the hydraulic system responds slowly; it is advisable to schedule daytime work."

[0047] The system integrates the aforementioned push notifications with currently valid standard and regulatory provisions, packaging them into lightweight knowledge cards. For example, a card titled "Precautions for the Final Stage of Wind Turbine Installation" includes: ① Standards for re-inspecting the torque of the last bolt (from GB / T XXXX); ② Review of historical accident cases from the same period; ③ List of emergency contacts for sudden weather changes; ④ QR code for self-inspection checklist. This knowledge package is delivered to the responsible person via APP pop-ups, SMS reminders, or voice broadcasts.

[0048] Reference Figure 4 Furthermore, the method also includes S410-S430: S410, after the task is completed, receive the task completion status sent by the person in charge's mobile terminal. The task completion status includes the actual status, actual time taken, difficulty rating and problem description. S420 compares the actual time spent with the planned duration to generate a deviation report, analyzes the root causes of the deviations in conjunction with the difficulty rating, and synchronizes them to the experience set; S430 extracts key events from the problem description, labels high-frequency problems based on the risk point set and standard specification clause set, and synchronizes them to the risk point set.

[0049] Specifically, in the feedback phase, after the task is completed, the person in charge must submit a complete execution report on the mobile device, covering the actual status (completed / paused / cancelled), the actual time taken, the subjective difficulty rating (1~5 stars), and the problem description (free text).

[0050] The system then activates a dual analysis mechanism: on the one hand, it compares the actual construction period with the planned construction period and calculates the deviation rate. If the deviation rate exceeds a preset threshold such as +20%, it triggers a three-level warning (yellow alert → orange warning → red emergency) and notifies the project manager to intervene and investigate. On the other hand, it conducts root cause analysis based on the difficulty rating. If most of the high difficulty ratings are concentrated in the "high steel structure welding rework rate" category, the system speculates that it may be related to insufficient welder qualifications or improper process parameters, and writes the conclusion into the experience set for reference in subsequent projects.

[0051] For the problem description text, the system uses NLP technology for event extraction and cluster analysis. For example, it identifies common expressions such as "bolts not tightened properly" and "grounding resistance exceeds the standard" in batches. It uses LDA topic model to extract high-frequency problem topics and compares them with the existing risk point set. If a new problem is found that is not covered by the existing risk library, such as "the positioning accuracy of the floating crane is affected by ocean currents", a new risk entry is created and assigned an initial probability of occurrence and impact level. If the frequency of an existing entry increases significantly, its risk level is increased and a higher intensity of preventive measures is triggered.

[0052] Finally, all updated lessons learned, revised risk lists, and optimized specification references will be stored back in the WBS database, becoming input resources for the next project planning.

[0053] Based on the above method embodiments, the second embodiment of this application discloses a system for knowledge dissemination of construction operation management based on power plant construction units. The system for knowledge dissemination of construction operation management based on power plant construction units in this embodiment can implement any of the above-described methods for knowledge dissemination of construction operation management based on power plant construction units, and the specific working process of each module in the system can be referred to the corresponding process in the above method embodiments.

[0054] For ease of understanding, an example is as follows: A system for knowledge dissemination in construction operation management based on power plant construction units includes: The information receiving module is used to receive project information; The information recognition module is used to identify task names and basic project information in project information; The information processing module is used to perform semantic analysis on task names and generate intelligent extended codes for the current WBS entry based on the analysis results. The intelligent extended codes include basic WBS codes and semantic extended tags, as well as a set of project context factors to generate based on basic project information. The task generation module is used to associate experience sets, standard specification clause sets, risk point sets, and schedule and cost datasets for the current WBS entries. It is used to generate mandatory project checklists and risk-specific checklists based on the project scenario factor set and the datasets associated with the current WBS entries. It is used to merge the risk-specific checklists and mandatory project checklists to generate the main project execution list. It is also used to associate the primary and alternative responsible persons for the main project execution list based on the project organizational structure, the section to which the intelligent extended code belongs, and the skill keywords required by the current WBS entries.

[0055] The third embodiment of this application provides a computer device, which may include a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement a method for knowledge push of construction operation management based on power plant construction units.

[0056] The memory can communicate with the processor via a communication bus, which can be an address bus, a data bus, a control bus, etc.

[0057] Additionally, the memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device.

[0058] Furthermore, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0059] The fourth embodiment of this application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as a method for pushing construction operation control knowledge based on power plant construction units.

[0060] The computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device; the program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0061] It should be noted that the computer device and storage medium in this application embodiment are respectively electronic devices and storage media for applying the above-described method for knowledge push of construction operation management based on power plant construction units. Therefore, all embodiments of the above-described method for knowledge push of construction operation management based on power plant construction units are applicable to the computer device and storage medium, and can achieve the same or similar beneficial effects. For the computer device / storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple; relevant details can be found in the descriptions of the method embodiments.

[0062] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0063] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A method for knowledge dissemination in construction operation management based on power plant construction units, characterized in that, include: Receive project information and identify the task name and basic project information in the project information; Semantic analysis is performed on the task name, and based on the analysis results, a smart extended code for the current WBS entry is generated. The smart extended code includes a basic WBS code and a semantic extended tag. Associate the current WBS entries with experience sets, standard and specification clause sets, risk point sets, and schedule and cost datasets; Based on the basic information of the project, a set of project scenario factors is generated; Based on the project scenario factor set and the dataset associated with the current WBS entries, generate a mandatory project inspection checklist and a risk-specific inspection checklist; The risk-specific inspection checklist is merged with the project mandatory inspection checklist to generate the project master execution checklist; Based on the project's organizational structure, the section to which the intelligent extended code belongs, and the skill keywords required for the current WBS entry, the primary and alternative responsible persons are associated with the project's main execution list.

2. The method for knowledge dissemination in construction operation management based on power plant construction units according to claim 1, characterized in that, The specific steps for associating the current WBS entries with the experience set, standard specification clause set, risk point set, and schedule and cost dataset include: Search the historical project database for historical similar WBS entries that match the intelligent extended code; If a match is found, the current WBS entry will automatically inherit the historical experience set, standard specification clause set, risk point set, and historical duration and cost dataset from the historically similar WBS entries. If no match is found, the general template library is called to generate an initial dataset, which is then pushed to the expert review library. After expert correction, an experience set, a standard specification clause set, a risk point set, and a schedule and cost dataset are generated and associated with the current WBS item.

3. The method for knowledge dissemination in construction operation management based on power plant construction units according to claim 1, characterized in that, The specific steps for generating the mandatory project checklist and risk-specific checklist based on the project scenario factor set and the dataset associated with the current WBS entries include: Iterate through each clause in the set of standard and specification clauses, where each clause predefines the conditions under which it takes effect; Select the normative clauses that meet the scenario conditions of the current project scenario, and adjust the detection standards of the normative clauses according to the scenario factors in the project scenario factor set. Then, add the adjusted normative clauses to the project mandatory inspection list. Assess the probability of occurrence and impact of each risk point in the risk point set under the current project context, and calculate the corresponding risk value; Risk points with risk values ​​exceeding the risk threshold are identified, and preventive inspection items are associated with these risk points based on the experience set, and these items are added to the risk-specific inspection list.

4. The method for knowledge dissemination in construction operation management based on power plant construction units according to claim 1, characterized in that, The steps following associating the primary and alternative responsible persons with the project's master execution list also include: After the person in charge receives the inspection tasks from the main execution list, the tasks are broken down into weekly or daily plans based on the planned start date, planned end date, and the person in charge's current workload. The broken-down weekly or daily plans will be synchronized as schedule items to the responsible person's personal calendar or work platform.

5. The method for knowledge dissemination in construction operation management based on power plant construction units according to claim 4, characterized in that, The control method also includes: Generate a predicted timeline based on the actual progress reported by the responsible party; Calculate the deviation between the predicted and planned completion dates of the task based on the predicted and planned timelines; A tiered warning is triggered when the deviation value exceeds a set threshold.

6. The method for knowledge dissemination in construction operation management based on power plant construction units according to claim 5, characterized in that, The control method also includes: N days before the task expires, select the top K lessons learned from the associated lessons learned set that have the highest matching degree with the current execution status of the task. By combining the standard and specification clauses, a personalized knowledge package is generated and pushed to the responsible person's mobile device.

7. The method for knowledge dissemination in construction operation management based on power plant construction units according to claim 6, characterized in that, The control method also includes: After the task is completed, the task completion status is sent by the person in charge via mobile device. The task completion status includes the actual status, actual time taken, difficulty rating and problem description. The actual time spent is compared with the planned duration to generate a deviation report. The root causes of the deviation are analyzed in conjunction with the difficulty rating and synchronized to the experience set. Extract key events from the problem description, label high-frequency problems according to the risk point set and standard specification clause set, and synchronize them to the risk point set.

8. A system for knowledge dissemination in construction operation management based on power plant construction units, characterized in that, Implementing the control method applicable to power plant construction operations as described in any one of claims 1 to 7, comprising: The information receiving module is used to receive project information; The information recognition module is used to identify the task name and basic project information in the project information; The information processing module is used to perform semantic analysis on the task name and generate intelligent extended codes for the current WBS entry based on the analysis results. The intelligent extended codes include basic WBS codes and semantic extended tags, and are used to generate a set of project context factors based on the basic information of the project. The task generation module is used to associate experience sets, standard specification clause sets, risk point sets, and schedule and cost datasets for the current WBS entry. It is used to generate a mandatory project checklist and a risk-specific checklist based on the project scenario factor set and the dataset associated with the current WBS entry. It is used to merge the risk-specific checklist and the mandatory project checklist to generate the main project execution list. It is also used to associate the primary and alternative responsible persons for the main project execution list based on the project organizational structure, the section to which the intelligent extended code belongs, and the skill keywords required by the current WBS entry.

9. A computer device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for knowledge push for construction operation management based on power plant construction units as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program stores a method for knowledge push for construction operation management based on power plant construction units, as described in any one of claims 1 to 7, which can be loaded by a processor and executed.

Images