Building data intelligent sharing method and system based on function collaborative feedback

Abstract

The invention provides a building data intelligent sharing method and system based on function collaborative feedback. The method comprises the following steps: collecting management data; based on the management data, constructing and updating a digital twinborn body in the ship and ocean engineering construction process; on the basis of the digital twin, cross-department and / or cross-stage collaborative tasks are identified, and a corresponding data demand model is constructed for each collaborative task; and encoding the data demand model of the collaborative task and a predefined trigger condition into a smart contract, deploying the smart contract in a permitted block chain network formed by construction participant nodes, and when the digital twinborn judges that the trigger condition is met, automatically executing the smart contract to directionally share data specified by the data demand model among authorized nodes. According to the method, service system data and high-precision physical perception data are combined, and on-demand, automatic and tampering-free directional sharing is realized by using a block chain smart contract, so that an information island is thoroughly broken, and a credible data circulation channel is established.

Description

Technical Field

[0001] This application relates to the field of shipbuilding and marine engineering construction technology, and more specifically, to a method and system for intelligent sharing of construction data based on functional collaborative feedback. Background Technology

[0002] The construction of ships and marine engineering equipment (such as large container ships, liquefied natural gas carriers, and floating production storage and offloading (FPSO) units) is a typical complex product systems engineering project, characterized by long project cycles, numerous participants, complex processes, and resource intensity. Currently, this field faces multiple systemic technical challenges in data management and collaboration.

[0003] Under the current multi-organizational collaborative construction model, design institutes, general assembly ships, section yards, supporting suppliers, and ship inspection agencies all operate independent business information systems. These systems differ significantly in data structure, standards, and interfaces, creating information barriers that are difficult to break down.

[0004] More importantly, the construction process involves huge sums of money and significant safety responsibilities, and all parties have extremely high requirements for the authenticity, integrity, and immutability of the data. In the current centralized data management model, the storage and transfer of critical engineering data (such as material certification reports, non-destructive testing records, and process parameters) rely on the internal systems of specific participants, posing a risk of unilateral alteration or damage. When quality incidents or contractual disputes occur, it is difficult to objectively and efficiently trace the source, flow path, and related operational responsibilities of the problematic data, leading to difficulties in determining liability and high costs in dispute resolution.

[0005] At the same time, the physical construction site lacks real-time and accurate digital perception of its condition. Managers struggle to grasp crucial information such as the actual welding deformation of hull sections, the precise three-dimensional pose of large equipment, the real-time capacity load of the workshop, and the dynamic status of material inventory.

[0006] Existing technical solutions are mostly single-function, focusing on post-event recording and reporting, and are passive response tools. They lack the ability to perform virtual simulation and risk warning for critical operations such as hoisting and closure based on real-time data, and also fail to drive adaptive optimization of process rules through in-depth analysis of historical collaborative efficiency and resource consumption patterns. The operation and improvement of the entire system highly depend on the personal experience of managers, and a continuous self-improvement intelligent mechanism has not yet been established.

[0007] While technologies such as the Internet of Things (IoT) and big data have been applied in some aspects of shipbuilding, their application is largely limited to improving single functions, such as using sensors to monitor equipment status or using cloud platforms to centrally store documents. These solutions fail to take a systems engineering approach, deeply integrating next-generation information technologies with the core business processes of shipbuilding to build an integrated data collaboration system that covers the entire value chain of design, production, logistics, and quality management, and possesses intelligent sensing, reliable sharing, forward-looking decision-making, and closed-loop optimization capabilities. Therefore, developing an intelligent data sharing method and system that can systematically solve the aforementioned multi-dimensional challenges has become an urgent need to promote the digital, networked, and intelligent transformation and upgrading of the shipbuilding and marine engineering construction industry. Summary of the Invention

[0008] The present invention aims to overcome the shortcomings of the prior art and provide a construction data intelligent sharing method and system based on functional collaborative feedback to solve the problems of data isolation, poor flow and low reliability in various stages of ship construction in the prior art.

[0009] In a first aspect, the present invention provides a method for intelligent sharing of construction data based on functional collaborative feedback, characterized in that the method includes: Collect management data on design, production, logistics, and quality throughout the entire process of ship and marine engineering construction; Based on the management data, a digital twin of the ship and marine engineering construction process is constructed and updated, and the digital twin includes geometric, physical, rule and real-time status information; Based on the digital twin, identify collaborative tasks across departments and / or stages, and construct a corresponding data requirement model for each collaborative task; The data requirement model of the collaborative task and the predefined triggering conditions are encoded into a smart contract and deployed in a permissioned blockchain network composed of nodes of the construction participants. When the digital twin determines that the triggering conditions are met, the smart contract is automatically executed to share the data specified by the data requirement model in a targeted manner among authorized nodes. After data sharing and collaborative operations are completed, collect performance data reflecting the results of the operations and the consumption of resources. The effect data is analyzed using an artificial intelligence model to generate a quantitative evaluation result of the collaborative task; Based on the quantitative evaluation results and real-time feedback data obtained from the digital twin and the physical site, the parameters of the data requirement model, the triggering conditions of the smart contract, and the execution logic are dynamically optimized.

[0010] Preferably, the collection of management data on design, production, logistics, and quality throughout the entire process of ship and marine engineering construction includes: By acquiring electronic data such as designs, plans, orders, and documents from business information systems; Real-time monitoring of welding deformation and residual stress distribution data is achieved by embedding or attaching a distributed fiber optic sensor network to large segments and structural components. By integrating ultra-wideband, radio frequency identification, and visual recognition into a multimodal positioning system, the three-dimensional spatial coordinates and attitude data of high-value equipment and key components can be continuously tracked in indoor and outdoor environments.

[0011] Preferably, before the collaborative task is triggered, the digital twin performs a forward-looking simulation in the virtual space based on the currently shared data. The simulation includes process feasibility verification, physical space interference check, and critical path duration simulation. The digital twin transforms potential conflicts discovered in the simulation into structured early warning instructions and optimization suggestions, which are then pushed to relevant responsible party nodes through the smart contract to drive the pre-adjustment of the collaborative process.

[0012] Preferably, in the permissioned blockchain network, the data access, writing, and contract execution permissions of each participating node are bound to its organizational role and function in the construction project; Each data sharing transaction driven by the smart contract has its entire chain of requests, authorizations, executions, and confirmations encrypted and generated into an immutable block, forming a data operation evidence storage and traceability chain.

[0013] Preferably, the step of using an artificial intelligence model to analyze the effect data and generate a quantitative evaluation result for the collaborative task includes: Calculate the coefficient for improving collaborative efficiency and the coefficient for reducing resource waste; The quantitative evaluation result is determined based on the collaborative efficiency improvement coefficient and the resource waste reduction coefficient. The collaborative efficiency improvement coefficient is used to quantify the time-consuming optimization effect, and the resource waste reduction coefficient is used to quantify the cost control effect.

[0014] Preferably, the formula for calculating the collaborative efficiency improvement coefficient is: in, The coefficient for improving collaborative efficiency. This refers to the average time taken to complete this collaborative task in similar or historical scenarios. This refers to the actual time taken to complete the collaborative task during the current execution process; The formula for calculating the resource waste reduction coefficient is as follows: in, To reduce the coefficient of resource waste, This refers to the standard quota budget cost determined based on the standard process library, time quotas, and bill of materials. This refers to the actual consumption cost collected in real time through an Internet of Things (IoT) system. This refers to the dynamic adjustment factor related to task complexity and environmental risk factors.

[0015] Preferably, the collaborative scenarios specifically implemented by the method include: During the design release phase, the digital twin performs manufacturability analysis based on real-time updated manufacturing capability data, and synchronizes the analysis results and modification suggestions to the design department node through the smart contract; During the material supply phase, the digital twin generates delivery requirements based on real-time construction progress and inventory prediction models, and automatically triggers the smart contract to issue delivery instructions containing time windows and geofences to the supplier nodes. In the closed-loop quality management, when a quality deviation is detected, a cross-departmental root cause analysis task is automatically initiated based on blockchain evidence storage, and the analysis conclusions and corrective measures are fed back to the source links of design, process or procurement through the optimized data requirement model.

[0016] Secondly, the present invention provides a construction data intelligent sharing system based on functional collaborative feedback, comprising: The data acquisition module is used to collect management data on design, production, logistics, and quality throughout the entire process of ship and marine engineering construction. A digital twin construction module is used to construct and update a digital twin of the ship and marine engineering construction process based on the management data. The digital twin includes geometric, physical, rule and real-time status information. A data requirement model building module is used to identify cross-departmental and / or cross-stage collaborative tasks based on the digital twin, and to build a corresponding data requirement model for each collaborative task. The data sharing module is used to encode the data requirement model of the collaborative task and the predefined triggering conditions into a smart contract and deploy it in a permissioned blockchain network composed of construction participant nodes. When the digital twin determines that the triggering conditions are met, the smart contract is automatically executed to share the data specified by the data requirement model in a targeted manner among authorized nodes. The effect data acquisition module is used to collect effect data reflecting the operation results and resource consumption after data sharing and collaborative operation are completed. The quantitative evaluation result generation module is used to analyze the effect data using an artificial intelligence model and generate a quantitative evaluation result for the collaborative task. The dynamic optimization module is used to dynamically optimize the parameters of the data requirement model, the triggering conditions of the smart contract, and the execution logic based on the quantitative evaluation results and real-time feedback data obtained from the digital twin and the physical site.

[0017] Thirdly, the present invention provides a readable medium including executable instructions, which, when executed by a processor of an electronic device, cause the electronic device to perform any of the methods described in the first aspect.

[0018] Fourthly, the present invention provides an electronic device including a processor and a memory storing execution instructions, wherein when the processor executes the execution instructions stored in the memory, the processor performs the method as described in any of the first aspects.

[0019] This invention provides a construction data intelligent sharing method and system based on functional collaborative feedback. By combining business system data with high-precision physical sensing data and utilizing blockchain smart contracts to achieve on-demand, automatic, and tamper-proof targeted sharing, it completely breaks down information silos and establishes a reliable data flow channel. The digital twin, as a precise mirror of the physical construction process, is not only used for status monitoring but also serves as a decision-making center for process simulation, conflict detection, and proactive early warning, transforming passive response into proactive optimization and significantly improving the accuracy and reliability of collaboration. The collaborative effect is quantitatively evaluated using an artificial intelligence model (such as efficiency improvement coefficient and resource waste reduction coefficient), and the evaluation results are fed back to the data demand model and smart contracts for dynamic optimization, forming an intelligent feedback loop of "perception-sharing-evaluation-optimization," enabling the system to continuously learn and self-improve. This invention closely integrates with the shipbuilding scenario, specifically addressing practical problems such as low efficiency, difficulty in collaboration, and serious resource waste through implementation in specific application scenarios (design collaboration, logistics collaboration, and quality traceability), demonstrating strong practicality and industrial application value.

[0020] The further effects of the aforementioned non-conventional preferred method will be explained below in conjunction with specific embodiments. Attached Figure Description

[0021] To more clearly illustrate the embodiments of the present invention or the existing technical solutions, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A schematic diagram of a construction data intelligent sharing method based on functional collaborative feedback provided in an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating a scenario application of a construction data intelligent sharing method based on functional collaborative feedback, provided by an embodiment of the present invention. Figure 3 A schematic diagram of another intelligent sharing method for construction data based on functional collaborative feedback provided in an embodiment of the present invention; Figure 4 A schematic diagram illustrating the composition of a construction data intelligent sharing system based on functional collaborative feedback, provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0024] The construction of ships and marine engineering equipment is a typical complex product systems engineering project, characterized by long project cycles, numerous participants, complex processes, and intensive resources. Currently, this field faces multiple systemic technical challenges in data management and collaboration.

[0025] In the current multi-organizational collaborative construction model, design institutes, shipyards, section yards, supporting suppliers, and ship inspection agencies all operate independent business information systems. These systems differ significantly in data structure, standards, and interfaces, creating information barriers that are difficult to overcome. A design change or process adjustment often requires multiple rounds of manual communication and confirmation between organizations through traditional methods such as meetings and emails. This results in a long information flow chain, poor timeliness, and susceptibility to misunderstandings, frequently leading to design rework, production delays, and logistical setbacks, severely hindering the overall collaborative efficiency of the project.

[0026] More importantly, the construction process involves huge sums of money and significant safety responsibilities, and all parties have extremely high requirements for the authenticity, integrity, and immutability of the data. In the current centralized data management model, the storage and transfer of critical engineering data (such as material certification reports, non-destructive testing records, and process parameters) rely on the internal systems of specific participants, posing a risk of unilateral alteration or damage. When quality incidents or contractual disputes occur, it is difficult to objectively and efficiently trace the source, flow path, and related operational responsibilities of the problematic data, leading to difficulties in determining liability and high costs in dispute resolution.

[0027] Meanwhile, the physical construction site lacks real-time, accurate digital awareness of its status. Managers struggle to grasp crucial information such as actual welding deformation of hull sections, precise three-dimensional positioning of large equipment, real-time workshop capacity load, and material inventory dynamics. This lack of transparency leads to a severe disconnect between production planning and on-site execution, frequently resulting in unplanned shutdowns due to waiting for information, material shortages, or process conflicts. Overly conservative design or procurement strategies also lead to significant waste of materials and labor, leaving construction cost control in a perpetually rudimentary state.

[0028] Most existing technical solutions are single-function, focusing on post-event recording and reporting, and are passive response tools. They lack the ability to perform virtual simulation and risk warning for critical operations such as hoisting and closure based on real-time data, and also fail to drive adaptive optimization of process rules through in-depth analysis of historical collaborative efficiency and resource consumption patterns. The operation and improvement of the entire system highly depend on the personal experience of managers, and a continuous self-improvement intelligent mechanism has not yet been established.

[0029] While technologies such as the Internet of Things (IoT) and big data have been applied in some aspects of shipbuilding, their application is largely limited to improving single functions, such as using sensors to monitor equipment status or using cloud platforms to centrally store documents. These solutions fail to take a systems engineering approach, deeply integrating next-generation information technologies with the core business processes of shipbuilding to build an integrated data collaboration system that covers the entire value chain of design, production, logistics, and quality management, and possesses intelligent sensing, reliable sharing, forward-looking decision-making, and closed-loop optimization capabilities. Therefore, developing an intelligent data sharing method and system that can systematically solve the aforementioned multi-dimensional challenges has become an urgent need to promote the digital, networked, and intelligent transformation and upgrading of the shipbuilding and marine engineering construction industry.

[0030] In view of this, the present invention provides a method for intelligent sharing of construction data based on functional collaborative feedback. See also Figure 1 The image shows a specific embodiment of a construction data intelligent sharing method based on functional collaborative feedback provided by the present invention. In this embodiment, the construction data intelligent sharing method based on functional collaborative feedback includes:

[0031] Step 101: Collect management data on design, production, logistics, and quality throughout the entire process of ship and marine engineering construction; Specifically, this embodiment integrates advanced technologies such as digital twins, blockchain, artificial intelligence, and the Internet of Things to construct an intelligent collaborative system covering the entire process of shipbuilding and marine engineering construction. This step aims to comprehensively and in real-time acquire all types of data generated during construction activities. The data sources are mainly divided into two categories:

[0032] Business management data acquisition: Electronic data is automatically extracted from various business software such as design, planning, production, inventory, and quality control through dedicated data interfaces or system integration platforms. This electronic data constitutes the logical framework of construction activities and specifically includes: design data, such as 3D models, 2D drawings, and bills of materials; planning and order data, such as production schedules, purchase orders, and shipping notices; and process and quality data, such as process cards, inspection records, and non-conforming product reports.

[0033] Physical Site Status Data Acquisition: By deploying a high-precision sensor network on the construction site, the precise status of physical entities is perceived in real time, making the site transparent. Specifically, this includes: Structural Status Monitoring: During the welding of large segments, a distributed fiber optic sensor network is pre-embedded in key weld areas to monitor temperature changes, deformation, and residual stress distribution in real time. This data is crucial for assessing weld quality and predicting structural deformation. Asset Location and Attitude Tracking: In workshops, docks, and storage yards, a multimodal positioning system integrating ultra-wideband positioning, radio frequency identification, and video recognition is deployed. Positioning tags are installed on key assets such as gantry cranes, marine main engines, and large segments to achieve continuous tracking of the three-dimensional spatial coordinates, movement trajectories, and attitude tilt angles (attitude data) of high-value equipment and critical components. For example, during the dock assembly phase, the system can obtain the precise spatial location of the segments to be assembled, the real-time location and load of the cranes, and the distribution of other equipment within the dock, providing a realistic data foundation for virtual lifting simulations.

[0034] Step 102: Based on management data, construct and update a digital twin of the ship and marine engineering construction process. The digital twin includes geometric, physical, rule and real-time status information. Furthermore, based on the massive amount of management data collected in step 101, a "digital twin" corresponding one-to-one with the physical ship is constructed and continuously updated in the computing platform. This digital twin is not a static three-dimensional model, but a virtual image that integrates geometric shape, material physical properties, assembly process rules, and can reflect on-site sensor data (such as stress, position, and temperature) in real time.

[0035] The core function of the digital twin in this embodiment lies in synchronization and fusion. For example, when a segment in the physical world completes welding, its completed 3D point cloud data and stress data measured by fiber optic sensors are immediately updated to the corresponding component in the digital twin. Simultaneously, the production status of that segment in the business system changes from "in manufacturing" to "completed." Thus, the digital twin becomes a unified digital foundation connecting the information world and the physical world, and fusing business flows and state flows, providing a single, reliable source for global perception and intelligent decision-making.

[0036] Step 103: Based on the digital twin, identify collaborative tasks across departments and / or stages, and build a corresponding data requirement model for each collaborative task; Furthermore, based on a real-time updated digital twin, the system automatically analyzes the construction process network, intelligently identifies key nodes that require multi-party collaboration to proceed smoothly, and defines them as collaborative tasks. For example, the system might identify the collaborative task of "installing pump room equipment," which involves multiple departments or stages, including the design team (providing equipment models and installation space), the materials supplier (providing equipment arrival information), the production workshop (providing the completion status of the compartment structure), and the hoisting team (providing crane resources). For each identified collaborative task, the system automatically or semi-automatically constructs a refined data requirement model. This data requirement model clarifies "who needs whom to provide what data, when, and what." Taking the aforementioned equipment installation as an example, its data requirement model might stipulate that three days before installation, the hoisting team needs to obtain the final 3D model and weight center of gravity data of the equipment from the design team, the estimated arrival time and precise dimensions of the equipment from the materials supplier, and the completed measured dimensions of the compartment opening from the production workshop.

[0037] Step 104: Encode the data requirement model of the collaborative task and the predefined trigger conditions into a smart contract and deploy it in a permissioned blockchain network composed of nodes of the construction participants. When the digital twin determines that the trigger conditions are met, the smart contract is automatically executed to share the data specified by the data requirement model in a targeted manner among authorized nodes. Furthermore, to automate and ensure the reliability of the data sharing process, this step combines the collaborative tasks and data requirement model defined in step 103 with preset execution conditions (such as "72 hours before installation") into an automatically running "smart contract." These smart contracts are deployed on a permissioned blockchain network maintained by all participants (such as shipowners, shipyards, design institutes, suppliers, and classification societies).

[0038] Each participant, acting as a node on the blockchain, has strictly limited access to and manipulation of data, commensurate with their role in the project. When the logic or progress judgment within the digital twin meets the triggering conditions of a smart contract (e.g., the virtual progress reaches 72 hours before device installation), the contract is automatically activated.

[0039] The contract execution process is completely transparent and uninterrupted. Data requests are sequentially sent to data providers (such as design institutes and materials departments). After the provider responds, the contract verifies the data format and digital signature. Once verification is successful, the encrypted data packet is automatically distributed to the designated requester (such as a hoisting team). Every step of the entire process—who requested what, when, what was requested, and what was provided—is fully recorded and packaged into encrypted blocks, permanently stored on the blockchain, forming immutable data and resolving issues of quality traceability and accountability.

[0040] Before a collaborative task is triggered, the digital twin conducts a forward-looking simulation in a virtual space based on the currently shared data. The simulation includes process feasibility verification, physical space interference checks, and critical path schedule simulation. The digital twin transforms potential conflicts discovered in the simulation into structured early warning instructions and optimization suggestions, and pushes them to relevant responsible party nodes through smart contracts to drive the pre-adjustment of the collaborative process.

[0041] Specifically, after the smart contract is triggered and data sharing is completed, but before physical collaborative operations are executed, the system does not simply transmit information, but initiates a crucial virtual pre-simulation phase. The digital twin performs a high-fidelity simulation of the collected data from various parties (such as design models, manufacturing precision data, equipment parameters, and resource status) in virtual space. This mainly includes: process feasibility verification, for example, for a complex curved surface segmented assembly, the digital twin simulates the entire welding sequence and fixture clamping process, calculates the deformation caused by heat input, and predicts whether the final profile accuracy required by the design can be achieved. If the simulation results show that the deformation will exceed the tolerance, it means that the existing process is not feasible. Physical space interference checks, for example, when simulating the hoisting of the main engine into the cabin, the digital twin makes the virtual crane carry the main engine model along a predetermined path and performs real-time collision detection with the digitized cabin structure. This detects in advance whether the boom will interfere with the superstructure, and whether the equipment will encounter pipes or other potential conflicts when rotating at the hatch. Critical path duration simulation uses a digital twin to dynamically extrapolate tasks on subsequent critical links, combining current progress, resource availability (such as the number of welders and crane availability), and process logic. It can simulate the impact of different decisions (such as prioritizing segment A or segment B) on the overall project duration, providing early warnings of potential delays. Once the simulation identifies any potential conflicts or risks, the digital twin will not simply output an alarm signal but will automatically generate a structured warning instruction and optimization suggestion report. This report will clearly indicate: what the problem is (e.g., "path interference"), where it occurs (3D coordinate positioning), why it occurs (e.g., "equipment model version does not match the cabin model"), and suggested solutions (e.g., "modify the hoisting path to scheme B" or "please have the designer confirm whether a certain pipeline can be temporarily disassembled"). More importantly, this report will be packaged into a new, high-priority smart contract instruction and automatically and targeted to the responsible nodes directly related to this risk. For example, an interference report will be pushed to the hoisting scheme engineer and on-site supervisor; a process feasibility issue report will be pushed to the process department and production workshop. This allows problems to be exposed and communicated to problem solvers before they actually occur, prompting all parties to make proactive adjustments and eliminating problems in the virtual world, thus avoiding high-cost rework and safety incidents in the physical world.

[0042] In a permissioned blockchain network, the data access, writing, and contract execution permissions of each participating node are bound to their organizational roles and functions in the construction project; every data sharing transaction driven by a smart contract has its entire chain record of request, authorization, execution, and confirmation encrypted and generates an immutable block, forming a data operation evidence storage and traceability chain.

[0043] Specifically, in the permissioned blockchain network, the permissions of each participant (node) are not general but finely configured based on their organizational role (such as "general contractor," "design subcontractor," or "specific equipment supplier") and specific functions. For example, a design institute node has the right to write and modify design model data but not the right to change the shipyard's quality inspection report; a classification society node has the right to access all relevant data for verification but typically has no right to modify any original data. This ensures data security and clear boundaries of responsibility from the source. Every data sharing transaction initiated by a smart contract has its entire lifecycle of key footprints fully recorded: Request: When and from which node did the smart contract request what data? Authorization: When did the requested party authorize the provision? Execution: When was the data encrypted and sent? Confirmation: When did the recipient confirm receipt and verification? This series of records, after being jointly verified by multiple nodes in the blockchain network, is packaged with a timestamp to form an encrypted, immutable data block and linked to previous blocks. Because all blocks are linked sequentially in chronological order, any final state or problem during the construction process (such as a quality defect in a component) can be traced back along the blockchain. It clearly shows who provided the design data for that component and when; who confirmed the manufacturing process data and when; and who signed the quality inspection report. This complete chain of data operation evidence storage and traceability makes it impossible to deny responsibility, greatly promotes honest cooperation among participants, and provides irrefutable evidence for future disputes.

[0044] Step 105: After data sharing and collaborative operation are completed, collect effect data reflecting the operation results and resource consumption. Furthermore, after data sharing drives actual collaborative operations (such as successful equipment installation), the system immediately initiates data collection for effect evaluation. Data collection not only records "success / failure" results but also focuses on collecting quantitative data reflecting process efficiency and resource consumption.

[0045] For example, for this equipment installation task, the system will collect: the total man-hours actually consumed during installation, the energy consumption of the crane during actual operation, the idle time caused by waiting for tools or coordination, and whether there was any rework. This data comes from feedback from IoT sensors (such as electricity meters), personnel attendance systems, and on-site inspection reports. This data objectively records the true cost and efficiency of this collaboration, providing factual basis for the next step of quantitative evaluation.

[0046] Step 106: Analyze the performance data using an artificial intelligence model to generate a quantitative evaluation result of the collaborative task; Furthermore, this step utilizes a pre-trained artificial intelligence model to deeply analyze the performance data collected in step 105, outputting objective and quantitative evaluation results. The core of the evaluation is to calculate two key indicators: the collaborative efficiency improvement coefficient and the resource waste reduction coefficient. The quantitative evaluation results are determined based on these two coefficients, whereby the collaborative efficiency improvement coefficient is used to quantify the time optimization effect, and the resource waste reduction coefficient is used to quantify the cost control effect.

[0047] The formula for calculating the collaborative efficiency improvement coefficient is: in, The coefficient for improving collaborative efficiency. This refers to the average time taken to complete this collaborative task in similar or historical scenarios. This refers to the actual time taken to complete the collaborative task during the current execution process; the collaborative efficiency improvement coefficient is used to measure the degree of optimization in terms of time. A positive value indicates improved efficiency; a negative value indicates decreased efficiency.

[0048] The formula for calculating the resource waste reduction coefficient is: in, To reduce the coefficient of resource waste, This refers to the standard quota budget cost determined based on the standard process library, time quotas, and bill of materials. This refers to the actual consumption cost collected in real time through an Internet of Things (IoT) system. This refers to a dynamic adjustment factor related to task complexity and environmental risk factors. The resource waste reduction coefficient measures the level of cost control. The dynamic adjustment factor takes into account the specific complexity and environmental factors of this task, making the assessment more equitable. Positive values ​​indicate cost savings, while negative values ​​indicate cost overruns.

[0049] The artificial intelligence model in this embodiment can employ a hybrid neural network, combining a time-series processing module (such as LSTM / Transformer) with a multimodal feature fusion module to simultaneously process time series, structured data, and spatial relationships. It is developed based on mainstream deep learning frameworks such as PyTorch or TensorFlow, supporting distributed training and service-oriented deployment. Training data and sample construction: Collect collaborative task records, resource consumption data, and quality reports from multiple completed shipbuilding projects. Use digital twins to generate simulation scenario data and expand the time-series samples through algorithms. Domain experts annotate historical tasks, providing benchmark values ​​for collaborative efficiency improvement coefficients and resource waste reduction coefficients, and annotating key influencing factors. Dynamically calibrate the calculation of the resource waste coefficient based on factors such as task complexity, environmental risk, and resource availability, making the evaluation fairer and more adaptable. Real-time calculation is performed using a small neural network. Input values ​​include task structure graph features, environmental sensor data, etc. Training process: Divided into three stages: pre-training (self-supervised learning), fine-tuning (supervised learning), and continuous learning (online incremental updates). Deployment method: Adopting an edge-cloud collaborative architecture, the lightweight model performs real-time inference locally at the shipyard, while the complete model undergoes periodic retraining and global optimization in the cloud.

[0050] The AI ​​model will combine the values, trends, and correlations of these two coefficients to generate an evaluation report. For example, the report might state: "The collaborative efficiency improved significantly by 15%, mainly due to sufficient information preparation reducing waiting time; however, the resource consumption coefficient only improved by 2%. Analysis revealed that the fine-tuning of the hoisting path increased fuel consumption, and it is recommended to optimize the simulation algorithm to provide a better path."

[0051] Step 107: Based on the quantitative evaluation results and real-time feedback data obtained from the digital twin and the physical site, dynamically optimize the parameters of the data requirement model, the triggering conditions of the smart contract, and the execution logic.

[0052] Furthermore, this step combines the quantitative evaluation results from step 106 with the continuously flowing real-time feedback data to dynamically optimize the system's operating rules. Optimization is automatic and continuous. If the evaluation finds that the timeliness of certain data (such as material arrival status) is insufficient, the system will automatically optimize the data requirement model, increasing the frequency of data provision from "daily" to "every four hours." If the evaluation finds that the triggering timing of smart contracts is consistently too late, the system will automatically optimize the contract triggering conditions, for example, adjusting "72 hours before installation" to "80 hours before installation," allowing more buffer time. If the AI ​​model's own judgment deviates from the actual benefits later, the system will use new data to optimize the AI ​​model's parameters, making its next evaluation more accurate.

[0053] The optimized rules and models will be immediately applied to the next round of similar collaborative tasks. This cycle continues, constantly driving the collaborative construction process towards greater efficiency and leaner execution, ultimately achieving the core goal of cost reduction and efficiency improvement.

[0054] As can be seen from the above technical solutions, the beneficial effects of this embodiment are as follows: by combining business system data with high-precision physical sensing data and utilizing blockchain smart contracts to achieve on-demand, automatic, and tamper-proof targeted sharing, information silos are completely broken down, and a reliable data flow channel is established. The digital twin, as a precise mirror of the physical construction process, is not only used for status monitoring but also serves as a decision-making center for process simulation, conflict detection, and proactive early warning, transforming passive response into proactive optimization and significantly improving the accuracy and reliability of collaboration. The collaborative effect is quantitatively evaluated using artificial intelligence models (such as efficiency improvement coefficients and resource waste reduction coefficients), and the evaluation results are fed back to the data demand model and smart contracts for dynamic optimization, forming an intelligent feedback loop of "perception-sharing-evaluation-optimization," enabling the system to continuously learn and self-improve. This invention closely integrates with the shipbuilding scenario, and through the implementation of specific application scenarios (design collaboration, logistics collaboration, quality traceability), it specifically solves practical problems such as low efficiency, difficulty in collaboration, and serious resource waste, possessing strong practicality and industrial application value.

[0055] Figure 1 The embodiments shown are merely basic examples of the method of the present invention. Other preferred embodiments of the method can be obtained by making certain optimizations and extensions based on them.

[0056] like Figure 3 The image shows another specific embodiment of the intelligent sharing method for construction data based on functional collaborative feedback according to the present invention. This embodiment further describes the method based on the foregoing embodiments, and includes the following steps:

[0057] Step 301: During the design release phase, the digital twin performs manufacturability analysis based on real-time updated manufacturing capability data, and synchronizes the analysis results and modification suggestions to the design department node through smart contracts. This embodiment provides a specific application of the method of Embodiment 1 in a "design-manufacturing" collaborative scenario. Figure 2 This paper demonstrates the specific application scenarios of the method of this invention in three typical collaborative scenarios in shipbuilding and marine engineering construction. The implementation steps for each scenario are explained in detail below with reference to the accompanying drawings.

[0058] Specifically, this step addresses the connection between the "design" and "production" stages, implementing a collaborative scenario for manufacturability analysis. When the design department completes the detailed design of a component and is ready for release, the system automatically triggers the collaborative process.

[0059] The specific process is as follows: The digital twin actively accesses real-time updated workshop manufacturing capability data. This data includes the maximum machining accuracy of currently available processing equipment, the tool library list of CNC machine tools, the mold status of large forming equipment (such as plate rolling machines and hydraulic presses), and the in-process workload of each workstation. Based on this, the digital twin performs automated manufacturability analysis on the design model in a virtual environment, simulating its processing and assembly processes to check for excessively complex surfaces, excessively small bending radii, or unreasonable assembly gaps that cannot be achieved with existing equipment. In this embodiment, manufacturability analysis refers to the process of evaluating whether a product design scheme can be produced economically, efficiently, and with high quality under specific manufacturing conditions through simulation and other means during the design phase. Manufacturing capability data is a set of data reflecting the real-time status and limit parameters of resources such as equipment, processes, and personnel on the production site.

[0060] For example, in the design, there is a curved section of the hull whose curvature exceeds the processing limits of the roller bending machine molds currently available in the workshop. The simulation analysis using a digital twin immediately identifies this "unmanufacturable" risk. Subsequently, the system automatically generates a structured analysis report, which includes problem location, risk description, and specific modification suggestions (such as adjusting the radius of curvature or recommending alternative splicing processes). This report is not sent via traditional email, but is encoded into a smart contract and automatically and purposefully "pushed" or "synchronized" to the business system nodes of the design department. Design engineers can receive this alert directly in their CAD workstations, enabling them to optimize the design before drawings are issued, thus preventing subsequent process changes, cost increases, and schedule delays from the outset.

[0061] Step 302: During the material supply phase, the digital twin generates delivery requirements based on the real-time construction progress and inventory prediction model, and automatically triggers the smart contract to issue delivery instructions containing time windows and geofences to the supplier nodes. Specifically, in this embodiment, real-time construction progress refers to data reflecting the actual completion of physical construction, acquired in real time through IoT sensors (such as visual recognition and RFID) and the production reporting system. The inventory forecasting model is a model built based on time series analysis and machine learning algorithms, used to predict future material demand to optimize inventory levels. This step focuses on the dynamic coordination of the "production" and "logistics" links to achieve just-in-time delivery. During the material supply phase, the system no longer relies on a fixed, long-term, unchanging supply plan, but rather dynamically adjusts according to the actual construction progress.

[0062] The specific process is as follows: The digital twin continuously integrates real-time construction progress data from the production site (such as the percentage of segment welding completion and the outfitting progress of compartments), and combines it with historical consumption data and future plans to perform rolling calculations through a built-in inventory forecasting model. This model can predict the demand and timing of specific materials (such as welding materials, pipe fittings, and cables) for specific workstations at specific future points in time.

[0063] For example, when a predictive model determines that a specific type of cable will be laid in a section of the dock in 36 hours, and the current on-site inventory is insufficient, the digital twin automatically generates a precise delivery request instruction. This instruction is immediately converted into a smart contract and automatically triggered. The contract sends a delivery instruction to the designated cable supplier node. The instruction includes not only the material type and quantity, but more importantly, a clear delivery time window (e.g., "delivery within 32-34 hours") and geofencing information (i.e., a precise delivery area defined on a digital map, such as "Material Temporary Storage Area B on the East Side of Dock 3"). Upon receiving this instruction, the supplier's logistics system can arrange a precise transportation plan. This ensures that materials are delivered to the required location at the required time, significantly reducing on-site material accumulation, shortages, and waste from secondary handling.

[0064] Step 303: In the closed-loop quality management, when a quality deviation is detected, a cross-departmental root cause analysis task is automatically initiated based on blockchain evidence storage, and the analysis conclusions and corrective measures are fed back to the source links of design, process or procurement through the optimized data requirement model.

[0065] Specifically, this step is implemented throughout the entire production process, aiming to achieve root cause analysis and preventative improvement of quality issues. When a quality deviation is detected at any inspection point (such as incoming inspection, in-process inspection, or final inspection), the system initiates an automated root cause analysis process.

[0066] The specific process is as follows: After a quality alarm is triggered, the system immediately utilizes the immutable evidence stored on the blockchain to automatically trace the entire chain of data related to the defective part or process. This includes: the version of the design drawings for the part, the batch and certificate of conformity of the materials used, the parameter setting records of the processing equipment, the qualifications and working time of the operators, and even the original data of the upstream suppliers. Based on this reliable data, the system automatically initiates a cross-departmental root cause analysis task and uses data analysis tools to assist in locating the root cause.

[0067] For example, quality inspection revealed that the surface finish of the sealing surfaces of a batch of marine valves did not meet standards. After tracing blockchain records, the system discovered that this batch of valves all used a specific batch of blanks from supplier A, and the processing records showed that the cutting parameters of machine tool B had experienced abnormal fluctuations during a certain period. The analysis automatically pointed to the combined effect of "uneven hardness of the blank material" and "machine tool parameter drift." Subsequently, the system did not simply generate a report, but encapsulated this conclusion along with corrective measures (such as "conducting a full inspection of this batch of blanks from supplier A" and "performing preventative maintenance and calibration of machine tool B"). Most importantly, this information was automatically fed back to the source stages through a data demand model that had been optimized based on historical feedback: material issues were fed back to the purchasing department to adjust supplier evaluations; process equipment issues were fed back to the process department to update work instructions; and if design selection was involved, it was fed back to the design department. In this way, the experience from a single quality incident was systematically transformed into organizational knowledge to prevent similar problems from recurring, achieving a closed loop of continuous quality improvement.

[0068] As can be seen from the above technical solutions, the beneficial effects of this embodiment are as follows: This invention constructs a full-chain collaborative solution covering the pre-, mid-, and post-production stages, targeting the design source, logistics process, and production quality closed loop. Through digital twin simulation early warning, automatic execution of smart contracts, and reliable traceability of blockchain, it achieves a fundamental shift from passive response to proactive prevention, from static planning to dynamic adaptation, and from post-event accountability to source improvement. Together, these factors systematically improve the first-time success rate, resource utilization rate, and quality robustness of the construction process, promoting a comprehensive upgrade of shipbuilding models towards digitalization, intelligence, and lean manufacturing.

[0069] This invention also provides a construction data intelligent sharing system based on functional collaborative feedback. See also Figure 4 The image shows a specific embodiment of a construction data intelligent sharing system based on functional collaborative feedback provided by the present invention. This embodiment of the system is used to execute... Figures 1-3 The physical apparatus of the method. Its technical solution is essentially the same as the embodiments described above, and the corresponding descriptions in the embodiments above also apply to this embodiment. The system includes:

[0070] The management data acquisition module 401 is configured to collect management data on design, production, logistics and quality throughout the entire process of ship and marine engineering construction. Digital twin building module 402 is configured to build and update a digital twin of the ship and marine engineering construction process based on management data. The digital twin includes geometric, physical, rule and real-time status information. The data requirements model building module 403 is configured to identify collaborative tasks across departments and / or phases based on digital twins and to build a corresponding data requirements model for each collaborative task. The data sharing module 404 is configured to encode the data requirement model of the collaborative task and the predefined triggering conditions into a smart contract and deploy it in a permissioned blockchain network composed of nodes of the construction participants. When the digital twin determines that the triggering conditions are met, the smart contract is automatically executed to share the data specified by the data requirement model in a targeted manner among authorized nodes. The effect data acquisition module 405 is configured to collect effect data reflecting the operation results and resource consumption after data sharing and driving collaborative operations are completed. The quantitative evaluation result generation module 406 is configured to analyze the effect data using an artificial intelligence model and generate a quantitative evaluation result for the collaborative task. The dynamic optimization module 407 is configured to dynamically optimize the parameters of the data requirement model, the triggering conditions of the smart contract, and the execution logic based on the quantitative evaluation results and real-time feedback data obtained from the digital twin and the physical site.

[0071] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include main memory, such as high-speed random-access memory (RAM), or it may also include non-volatile memory, such as at least one disk storage device. Of course, the electronic device may also include other hardware required for other services.

[0072] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. Buses can be categorized as address buses, data buses, and other types. For ease of representation, Figure 5 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0073] Memory is used to store instructions for execution. Specifically, instructions for execution are computer programs that can be executed. Memory can include main memory and non-volatile memory, and it provides the processor with execution instructions and data.

[0074] In one possible implementation, the processor reads the corresponding execution instructions from non-volatile memory into main memory and then executes them. Alternatively, it may obtain the corresponding execution instructions from other devices to form a construction data intelligent sharing device based on functional collaborative feedback at the logical level. The processor executes the execution instructions stored in the memory to implement the construction data intelligent sharing method based on functional collaborative feedback provided in any embodiment of the present invention.

[0075] The above is as described in the present invention. Figure 4 The method for constructing an intelligent data sharing system based on functional collaborative feedback, as provided in the illustrated embodiment, can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed through integrated logic circuits in the processor's hardware or through software instructions. 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, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor.

[0076] The steps of the method disclosed in the embodiments of this invention can be directly manifested as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0077] This invention also proposes a readable medium storing execution instructions. When these instructions are executed by a processor of an electronic device, the device can perform a construction data intelligent sharing method based on functional collaborative feedback provided in any embodiment of this invention, specifically for executing, as... Figure 1 , Figure 3 The method shown.

[0078] The electronic devices in the foregoing embodiments may be computers.

[0079] Those skilled in the art will understand that embodiments of the present invention can be provided as methods or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or a combination of software and hardware.

[0080] The various embodiments in this invention are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the apparatus embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0081] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0082] The above are merely embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A method for intelligent sharing of construction data based on functional collaborative feedback, characterized in that, The method includes: Collect management data on design, production, logistics, and quality throughout the entire process of ship and marine engineering construction; Based on the management data, a digital twin of the ship and marine engineering construction process is constructed and updated, and the digital twin includes geometric, physical, rule and real-time status information; Based on the digital twin, identify collaborative tasks across departments and / or stages, and construct a corresponding data requirement model for each collaborative task; The data requirement model of the collaborative task and the predefined triggering conditions are encoded into a smart contract and deployed in a permissioned blockchain network composed of nodes of the construction participants. When the digital twin determines that the triggering conditions are met, the smart contract is automatically executed to share the data specified by the data requirement model in a targeted manner among authorized nodes. After data sharing and collaborative operations are completed, collect performance data reflecting the results of the operations and the consumption of resources. The effect data is analyzed using an artificial intelligence model to generate a quantitative evaluation result of the collaborative task; Based on the quantitative evaluation results and real-time feedback data obtained from the digital twin and the physical site, the parameters of the data requirement model, the triggering conditions of the smart contract, and the execution logic are dynamically optimized.

2. The method according to claim 1, characterized in that, The collected data on design, production, logistics, and quality management throughout the entire shipbuilding and marine engineering process includes: By acquiring electronic data such as designs, plans, orders, and documents from business information systems; Real-time monitoring of welding deformation and residual stress distribution data is achieved by embedding or attaching a distributed fiber optic sensor network to large segments and structural components. By integrating ultra-wideband, radio frequency identification, and visual recognition into a multimodal positioning system, the three-dimensional spatial coordinates and attitude data of high-value equipment and key components can be continuously tracked in indoor and outdoor environments.

3. The method according to claim 1, characterized in that, Before the collaborative task is triggered, the digital twin performs a forward-looking simulation in the virtual space based on the currently shared data. The simulation includes process feasibility verification, physical space interference check, and critical path schedule simulation. The digital twin transforms potential conflicts discovered in the simulation into structured early warning instructions and optimization suggestions, which are then pushed to relevant responsible party nodes through the smart contract to drive the pre-adjustment of the collaborative process.

4. The method according to claim 1, characterized in that, In the permissioned blockchain network, the data access, writing, and contract execution permissions of each participating node are bound to its organizational role and function in the construction project; Each data sharing transaction driven by the smart contract has its entire chain of requests, authorizations, executions, and confirmations encrypted and generated into an immutable block, forming a data operation evidence storage and traceability chain.

5. The method according to claim 1, characterized in that, The step of using an artificial intelligence model to analyze the effect data and generate a quantitative evaluation result for the collaborative task includes: Calculate the coefficient for improving collaborative efficiency and the coefficient for reducing resource waste; The quantitative evaluation result is determined based on the collaborative efficiency improvement coefficient and the resource waste reduction coefficient. The collaborative efficiency improvement coefficient is used to quantify the time-consuming optimization effect, and the resource waste reduction coefficient is used to quantify the cost control effect.

6. The method according to claim 5, characterized in that, The formula for calculating the collaborative efficiency improvement coefficient is as follows: in, The coefficient for improving collaborative efficiency. This refers to the average time taken to complete this collaborative task in similar or historical scenarios. This refers to the actual time taken to complete the collaborative task during the current execution process; The formula for calculating the resource waste reduction coefficient is as follows: in, To reduce the coefficient of resource waste, This refers to the standard quota budget cost determined based on the standard process library, time quotas, and bill of materials. This refers to the actual consumption cost collected in real time through an Internet of Things (IoT) system. This refers to the dynamic adjustment factor related to task complexity and environmental risk factors.

7. The method according to claim 1, characterized in that, The specific collaborative scenarios implemented by the method include: During the design release phase, the digital twin performs manufacturability analysis based on real-time updated manufacturing capability data, and synchronizes the analysis results and modification suggestions to the design department node through the smart contract; During the material supply phase, the digital twin generates delivery requirements based on real-time construction progress and inventory prediction models, and automatically triggers the smart contract to issue delivery instructions containing time windows and geofences to the supplier nodes. In the closed-loop quality management, when a quality deviation is detected, a cross-departmental root cause analysis task is automatically initiated based on blockchain evidence storage, and the analysis conclusions and corrective measures are fed back to the source links of design, process or procurement through the optimized data requirement model.

8. A construction data intelligent sharing system based on functional collaborative feedback, characterized in that, include: The data acquisition module is used to collect management data on design, production, logistics, and quality throughout the entire process of ship and marine engineering construction. A digital twin construction module is used to construct and update a digital twin of the ship and marine engineering construction process based on the management data. The digital twin includes geometric, physical, rule and real-time status information. A data requirement model building module is used to identify cross-departmental and / or cross-stage collaborative tasks based on the digital twin, and to build a corresponding data requirement model for each collaborative task. The data sharing module is used to encode the data requirement model of the collaborative task and the predefined triggering conditions into a smart contract and deploy it in a permissioned blockchain network composed of construction participant nodes. When the digital twin determines that the triggering conditions are met, the smart contract is automatically executed to share the data specified by the data requirement model in a targeted manner among authorized nodes. The effect data acquisition module is used to collect effect data reflecting the operation results and resource consumption after data sharing and collaborative operation are completed. The quantitative evaluation result generation module is used to analyze the effect data using an artificial intelligence model and generate a quantitative evaluation result for the collaborative task. The dynamic optimization module is used to dynamically optimize the parameters of the data requirement model, the triggering conditions of the smart contract, and the execution logic based on the quantitative evaluation results and real-time feedback data obtained from the digital twin and the physical site.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method of any one of claims 1 to 7.

10. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1 to 7.

Images