Construction whole process quality tracing method and system based on BIM and block chain

Abstract

The invention discloses a BIM and block chain-based construction whole process quality tracing method and system, and relates to the technical field of building construction quality management. In a material entering stage, material information is collected through the Internet of Things and is associated with a BIM component identifier, and an initial block is generated by using an intelligent contract; in the process execution stage, BIM 4D / 5D simulation data is associated with a construction log, and a Hash chain algorithm is adopted to generate a process block containing IPFS Hash; in the acceptance inspection stage, the consistency of detection results is verified through zero-knowledge proof, and a new block is generated; checking the block data through a consensus mechanism to obtain a complete data set; constructing a graph database index based on the BIM component tree, and generating a chain path graph; responding to a query request, traversing path diagram nodes, comparing hash values and outputting a tracing result; trusted communication, tamper-proof evidence storage and intelligent tracing of data in the whole construction process are achieved, and the accuracy and reliability of project quality management are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of construction quality management technology, specifically a method and system for tracing the quality of the entire construction process based on BIM and blockchain. Background Technology

[0002] In the construction industry, construction quality management has always been a crucial area, directly related to project safety, service life, and public trust. Ensuring controllable and traceable quality throughout the entire construction process has become one of the core needs for industry development. With the popularization of digital technology, the construction industry is gradually moving towards intelligent management, but existing methods still have significant shortcomings in solving quality traceability issues. Many traditional methods rely on paper records or scattered electronic ledgers, which are prone to information gaps during data storage and transmission, making it difficult to clarify the attribution of responsibility for key links. Especially in some less noticeable construction stages, problems are often concealed, making accountability extremely difficult.

[0003] The current solution is limited by a lack of holistic and coherent data management. Information cannot be effectively shared between different stages of the construction process, such as material arrival, work procedure execution, and acceptance inspection. This fragmented approach makes it difficult to trace quality issues back from their source to the end, especially when multiple parties are involved, where data authenticity and consistency are hard to guarantee. This information isolation further exacerbates the industry's difficulties in verifying the quality of concealed works, as these projects are difficult to inspect again once completed, and incomplete or unreliable records make subsequent accountability virtually impossible.

[0004] Focusing on the technical challenges, the biggest challenge in construction quality management lies in ensuring the reliability of data throughout the entire process and its close correlation across different stages. Data reliability is primarily reflected in the authenticity of records. Due to the lack of effective anti-tampering mechanisms, key information during construction may be modified, such as replacing a batch of material testing reports, leading to the failure to promptly detect potential quality issues in subsequent projects. Furthermore, when data reliability cannot be guaranteed, cross-stage correlation becomes even more difficult. Data from different stages cannot form a complete chain; for example, there is no direct correspondence between the video recordings of concealed works and the final acceptance results, often requiring significant time and manpower to find the root cause of problems. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for quality traceability throughout the entire construction process based on BIM and blockchain. By integrating BIM and blockchain technologies, a chain-like data structure is constructed to cover the entire lifecycle from material arrival to acceptance inspection, thus solving the core problems of fragmented construction quality data, low credibility, and difficulty in traceability.

[0006] The objective of this invention can be achieved through the following technical solutions: This application provides a method for quality traceability throughout the entire construction process based on BIM and blockchain, including the following steps: S1. During the material arrival stage, material information is collected through IoT devices, and the material information is associated with the component identifiers in the BIM model. The initial block containing timestamps, material hash values, and BIM component IDs is generated using blockchain smart contracts to construct an initial chain data structure based on BIM. S2. During the process execution phase, based on the initial chained data structure, the BIM4D / 5D construction simulation data is associated with the real-time construction log and personnel operation records. The hash value of the previous block is calculated using the hash chain algorithm and linked to the current data to generate a process block containing IPFS hash, forming a continuous record sequence. S3. During the acceptance and inspection phase, based on the continuous record sequence, a three-dimensional comparative inspection is performed using the BIM model. The consistency between the inspection results and historical data is verified using zero-knowledge proof technology. This triggers a smart contract to generate a new block containing the inspection results, which is then linked to the block of the previous process, forming a cross-linked extended chain. S4. Extract all block data from the cross-link extended chain, combine the component relationships of the BIM model, and use the blockchain consensus mechanism and smart contract to automatically verify the timestamp, identifier and hash value of each block to obtain a verified complete dataset. S5. Based on the complete dataset and BIM component tree, construct a graph database index, establish a connection path from material arrival to acceptance inspection, and generate a chain path diagram for cross-stage queries. S6. In response to the query request, the nodes of the chain path graph are traversed through the smart contract, the node hash value is compared with the on-chain storage value, and the corresponding BIM component data and construction records are output to obtain the traceability result. S7. Generate an encrypted backup of the traceability results, distribute it to distributed nodes via IPFS, and verify the consistency of the replicas using a hash chain algorithm to form a persistent traceability system.

[0007] This application provides a construction process quality traceability system based on BIM and blockchain, applied to a construction process quality traceability method based on BIM and blockchain, including: The material arrival management module is used to collect material information through IoT devices during the material arrival stage, associate the material information with the component identifier in the BIM model, and use blockchain smart contracts to generate an initial block containing timestamps, material hash values ​​and BIM component IDs to build an initial chain data structure based on BIM. The process execution management module is used to associate BIM 4D / 5D construction simulation data with real-time construction logs and personnel operation records according to the initial chain data structure during the process execution stage. It uses a hash chain algorithm to calculate the hash value of the previous block and link it with the current data to generate a process block containing IPFS hash, forming a continuous record sequence. The acceptance inspection management module is used to perform three-dimensional comparative inspection based on the continuous record sequence during the acceptance inspection stage, using the BIM model to verify the consistency between the inspection results and historical data through zero-knowledge proof technology, triggering the smart contract to generate a new block containing the inspection results, linking it to the previous process block, and forming a cross-link extension chain. The data verification and fusion module is used to extract all block data from the cross-link extended chain, combine the component relationships of the BIM model, and use the blockchain consensus mechanism and smart contracts to automatically verify the timestamp, identifier and hash value of each block to obtain a verified complete dataset. The traceability path construction module is used to build a graph database index based on the complete dataset and BIM component tree, establish a related path from material arrival to acceptance inspection, and generate a chain path diagram for cross-stage query. The traceability query execution module is used to respond to query requests, traverse the nodes of the chain path graph through smart contracts, compare the node hash value with the on-chain stored value, output the corresponding BIM component data and construction records, and obtain the traceability result. The intelligent analysis and prediction module is used to perform node embedding representation on the chain path graph based on graph neural network, train a similarity reasoning model, and intelligently recommend historical quality data and potential risk prediction of similar components. The data backup and persistence module is used to generate encrypted backups of the traceability results, distribute them to distributed nodes via IPFS, and verify the consistency of the replicas using a hash chain algorithm, thus forming a persistent storage traceability system.

[0008] The beneficial effects of this invention are as follows: To address the issues of fragmented information and ineffective data integration across different stages in traditional construction quality management, this invention constructs a full-lifecycle chain-like data structure based on BIM and blockchain. It collects incoming material information via IoT devices and associates it with BIM component identifiers, generating initial blocks using smart contracts. During the process execution stage, BIM 4D / 5D simulation data is linked with construction logs and personnel operation records, using a hash chain algorithm to generate a continuous record sequence. In the acceptance and inspection stage, zero-knowledge proof technology verifies the consistency between inspection results and historical data, generating new blocks. This achieves data integration from the material source to the acceptance result, solving the industry problem of difficulty in fully tracing quality issues caused by data dispersion and fragmented processes. To address the problems of data authenticity being difficult to guarantee, susceptibility to tampering, and difficulties in cross-stage correlation in traditional methods, this invention constructs a multi-layered anti-tampering mechanism and an intelligent verification system. It automatically verifies block timestamps and hash values ​​through a blockchain consensus mechanism to eliminate tampered data; it constructs a graph database index based on the BIM component relationship graph, generates a chained path graph, and integrates smart contracts to automatically traverse nodes and compare hash values ​​for accurate traceability; simultaneously, it introduces a graph neural network to train a similarity reasoning model to achieve intelligent prediction of quality risks; and it upgrades static traceability to proactive early warning, significantly improving the ability to discover quality problems and the efficiency of accountability in complex scenarios such as concealed works. To address the challenges of long-term data preservation and secure sharing, this invention constructs a persistent storage system based on IPFS and blockchain. The traceability results are encrypted and backed up before being uploaded to IPFS to obtain a unique content identifier. Copy data is retrieved in parallel from multiple distributed nodes, and a hash chain algorithm is used to verify data consistency. Verified copy data is anchored to the blockchain traceability record, and the identifier and verification hash value are written into the notarization block via a smart contract. Leveraging the distributed storage of IPFS and the immutability of blockchain, this ensures that data can be recovered and integrity verified even if some nodes are offline, providing a secure and reliable data foundation for the full lifecycle supervision of engineering quality. Attached Figure Description

[0009] To better understand and implement this application, the technical solution is described in detail below with reference to the accompanying drawings.

[0010] Figure 1 A flowchart illustrating a method for tracing the quality of the entire construction process based on BIM and blockchain, provided in Embodiment 1 of this application; Figure 2 A flowchart illustrating step S3 in a construction process quality traceability method based on BIM and blockchain provided in Embodiment 1 of this application; Figure 3 A flowchart illustrating step S5 in a construction process quality traceability method based on BIM and blockchain provided in Embodiment 1 of this application; Figure 4 This is a schematic diagram of a construction process quality traceability system based on BIM and blockchain, provided in Embodiment 2 of this application. Detailed Implementation

[0011] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, exemplary embodiments will be described in detail below, examples of which are illustrated in the accompanying drawings. In the following description, when referring to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0012] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used herein are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0013] The following detailed description of the specific implementation methods, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided in detail.

[0014] Example 1, please refer to Figures 1-3 This embodiment provides a method for quality traceability throughout the entire construction process based on BIM and blockchain, including the following steps: S1. During the material arrival stage, material information is collected through IoT devices and associated with the component identifiers in the BIM model. The initial block containing timestamps, material hash values ​​and BIM component IDs is generated using blockchain smart contracts to construct an initial chain data structure based on BIM.

[0015] BIM (Building Information Modeling) is a digital method for building information modeling applied to engineering design, construction, and management.

[0016] Further, step S1 specifically includes: The material information is collected in real time through IoT devices, including data on material source, specifications and batches, and the integrity of the material information is determined by integrity detection algorithm. The IoT devices include RFID readers, QR code scanning terminals, and sensor arrays. Multi-source data fusion technology ensures the accuracy and real-time nature of the collected data, while automatically marking and re-collecting abnormal data to provide a reliable foundation for subsequent correlation. The integrity detection algorithm, based on a combination of hash verification and field rule verification, performs null value detection, format verification, and logical consistency judgment on the collected material data. If data loss or anomalies are detected, a re-collection mechanism is triggered to ensure the integrity and reliability of data entering subsequent processes.

[0017] RFID (Radio Frequency Identification) is a wireless communication technology that uses radio signals to identify specific targets and read and write related data.

[0018] Based on the collected material information, the material information is matched with the component identifiers in the BIM model using pre-established mapping rules to obtain associated data pairs. The mapping rules are based on the semantic alignment of material type codes and BIM component classification standards. They achieve rapid association through a hash mapping table and use the oracle mechanism of smart contracts to verify the accuracy of the mapping, ensuring a unique correspondence between materials and components. The oracle mechanism obtains the comparison information between material standard codes and BIM component classifications from external trusted data sources. It ensures the accuracy and tamper resistance of the mapping rules through cross-verification of multiple data sources. The mapping results are stored in a temporary buffer in the form of key-value pairs for subsequent on-chain use.

[0019] For the associated data pairs, an initial block containing timestamps, material hash values, and BIM component IDs is generated using the blockchain smart contract mechanism. The hash value integrity of the block is then verified, and once the verification is successful, it is linked to the initial chain data structure based on BIM. The smart contract automatically executes the block generation logic. The timestamp is provided by the consensus nodes of the blockchain network and digitally signed. The material hash value is calculated using the SHA-256 algorithm to ensure the immutability and traceability of the block content. The smart contract contains preset trigger conditions. Block generation is automatically executed only after the material information passes the integrity verification and the mapping relationship verification is passed. The generated block is broadcast to all network nodes through the consensus mechanism. After confirmation, it is written into the distributed ledger to ensure the non-repudiation of the initial block and the consistency of the entire network.

[0020] The system retrieves the stored initial block information from the chained data structure, cross-validates the timestamps and material information in the blocks to determine data consistency, and evaluates the traceability of the material information based on the verification results using a preset threshold rule to obtain a reliability determination.

[0021] The cross-validation is achieved by comparing the block timestamp with the local log time of the IoT device, the material production date, and other multi-source time information. The consistency judgment is based on the time deviation tolerance model. If the deviation exceeds the preset range, it is marked as a suspicious block. The threshold rule is dynamically adjusted according to the material type, supplier level, and historical traceability success rate. The reliability judgment result is output in the form of a score and recorded on the blockchain for evidence storage. At the same time, the collection frequency and range of the IoT device are automatically adjusted through smart contracts according to the judgment result. Low reliability materials trigger high-frequency collection and multi-sensor fusion verification, while high reliability materials appropriately reduce the collection density to optimize resource utilization, forming a closed-loop adaptive management mechanism.

[0022] Specifically, by using IoT devices to collect material information and linking it with BIM component identifiers during the material arrival phase, and combining this with blockchain smart contracts to generate initial blocks containing timestamps and hash values, the problem of easily tampered material data and low credibility of arrival information in traditional construction is solved, thus realizing credible storage and closed-loop adaptive management of material source data.

[0023] S2. Based on the initial chained data structure, during the process execution phase, the BIM 4D / 5D construction simulation data is associated with the real-time construction logs and personnel operation records. The hash chain algorithm is used to calculate the hash value of the previous block and link it to the current data. At the same time, the construction logs and operation records are stored in IPFS to generate process blocks containing IPFS hashes, forming a continuous record sequence.

[0024] IPFS (InterPlanetary File System) is an interplanetary file system that represents a peer-to-peer distributed file storage protocol.

[0025] Further, step S2 specifically includes: Acquire BIM 4D / 5D construction simulation data during the process execution phase, and simultaneously collect construction logs and personnel operation records in real time through IoT terminals. Perform spatiotemporal alignment and format standardization processing on multi-source data to generate a structured dataset to be uploaded to the blockchain. The spatiotemporal alignment is based on a unified time synchronization protocol, which calibrates the timeline of the BIM simulation data with the actual construction time collected by the IoT terminal at the millisecond level, ensuring that the simulation progress corresponds to the actual record under the same time reference. The format standardization process uses a predefined data template to uniformly convert the text descriptions in the construction log, the sensor data in the personnel operation records, and the parameter information in the BIM simulation data into JSON or Protobuf format, and adds a process identifier as a correlation key to form a dataset with a consistent structure, providing standardized input for subsequent on-chain processing.

[0026] JSON (JavaScript Object Notation) represents a simplified notation of JavaScript objects and is a lightweight data exchange format; Protobuf (Protocol Buffers) represents a protocol buffer and is a method for serializing structured data.

[0027] The hash value of the previous block is calculated using a hash chain algorithm as a link credential, and the structured dataset of the current process is combined with the previous hash value to construct a new block; if the amount of construction logs or personnel operation records exceeds a preset threshold, they are automatically stored in the IPFS distributed file system, and the returned IPFS hash value is obtained as a data index. The hash chain algorithm uses SHA-256 recursive calculation, taking the hash value of the previous block and the data content of the current block as input to generate a new block hash, ensuring that the order relationship between blocks cannot be tampered with. The data volume threshold is dynamically set according to the block size limit and network transmission efficiency. When the log or record data exceeds the threshold, the smart contract automatically triggers the IPFS storage process, storing the original data in shards on distributed nodes. The returned IPFS hash value is embedded in the block as a data index, which not only ensures the lightweight nature of on-chain data, but also achieves reliable storage and fast retrieval of large-capacity data through the IPFS content addressing mechanism.

[0028] The process simulation data, construction log summary, key personnel operation information, previous block hash value and IPFS hash value are packaged together to generate a process block. After calculating the current block hash value, they are linked to a chain data structure to form a continuous and tamper-proof sequence of construction process records.

[0029] The packaging process of the process blocks is automatically executed by smart contracts. The construction log summary and key personnel operation information are hash digests of the original data, which preserves data uniqueness and avoids on-chain storage redundancy. After the hash value of the current block is calculated, it is broadcast to the blockchain network through a consensus mechanism. Each consensus node verifies the integrity of the block content and the correctness of the hash chain. After confirmation, it is written into the distributed ledger. This mechanism ensures that the execution process of each process is cryptographically linked to the previous process. Any tampering with historical data will cause all subsequent block hashes to become invalid, thereby achieving transparent traceability and data trustworthiness throughout the construction process.

[0030] Specifically, by aligning BIM4D / 5D simulation data with construction logs and personnel operation records in time and space and associating them with hash chains during the process execution phase, and combining this with IPFS to achieve large-capacity data storage, the problem of fragmented process records and difficulty in forming a reliable association with preceding and subsequent stages in traditional construction is solved. This achieves continuous tamper-proof recording and lightweight reliable storage of process execution data.

[0031] S3. Based on the continuous recording sequence, the BIM model is used for three-dimensional comparison inspection during the acceptance inspection stage. The consistency between the inspection results and historical data is verified by zero-knowledge proof technology. If the verification is successful, the smart contract is triggered to generate a new block containing the inspection results, and the new blockchain is connected to the previous process block to form a cross-link extension chain.

[0032] Furthermore, step S3 specifically includes: S31. Obtain the 3D data of the BIM model during the acceptance inspection phase and the continuous record sequence generated in step S2. Use a 3D detection algorithm based on point cloud comparison to compare the BIM model with the actual construction results in real time and generate detection result data containing deviation values ​​and compliance indicators. The 3D detection algorithm acquires point cloud data from the construction site using a laser scanner or UAV photogrammetry system. After denoising, filtering, and registration, the data is automatically compared with the ideal geometric surface in the BIM model. The registration process uses an iterative nearest-point algorithm to align the point cloud with the model coordinate system. The difference analysis generates a deviation heatmap by calculating the shortest distance from each point cloud to the model surface and identifies areas exceeding the allowable error range of the design specifications as construction defects. The detection results are stored in a structured format, including a list of deviation values, defect location coordinates, compliance judgment marks, and detection timestamps, providing quantitative basis for subsequent on-chain verification.

[0033] S32. Use zero-knowledge proof technology to verify the consistency between the test result data and the historical data in the continuous record sequence, and prove the logical consistency between the test result and the previous process record without disclosing the specific data content; if the verification is successful, trigger the automatic execution of the preset smart contract to generate a new block data containing the test report hash, verification certificate and timestamp based on the test result; Furthermore, zero-knowledge proof technology is used to verify the consistency between the test result data and historical data in the continuous recording sequence. This includes: taking key indicators (such as deviation values ​​and defect numbers) in the test result data and material data and construction logs of the corresponding processes in the continuous recording sequence as input, and using zk-SNARKs or zk-STARKs algorithms to generate mathematical proofs. These proofs can confirm to the verification contract on the blockchain that there is a pre-defined logical consistency relationship between the test results and previous process records without disclosing any original data content (for example, proving that the current deviation value conforms to the theoretical error range corresponding to the material batch). The verification contract verifies the proof, and once it passes, the test result is deemed credible, and the smart contract is triggered to generate a new block containing the verification certificate, thereby achieving a credible association of data across stages while ensuring data privacy.

[0034] The verification process is automatically executed by a verification contract on the blockchain, and the verification certificate serves as the output of the proof. The smart contract has preset trigger conditions and is automatically executed only after the zero-knowledge proof verification is successful and the test result meets the basic format requirements. The generated test report hash is calculated using SHA-256, and the verification certificate contains the digital signature of the proof generator, ensuring the authenticity of the test result and the credibility of the verification process.

[0035] S33. Link the newly generated block to the block of the previous process through the hash chain algorithm to form an extended blockchain bar across stages, ensuring a reliable association between the acceptance inspection data and the construction process records.

[0036] The new block is permanently stored after consensus is reached on the blockchain network. The consensus process adopts a practical Byzantine fault-tolerant algorithm or an authoritative proof mechanism, in which multiple consensus nodes jointly confirm the block content, zero-knowledge proof verification results, and timestamps. After confirmation, the new block is added to the main chain, and its hash value forms an irreversible chain association with the previous process block. Any tampering with the data of the previous process or the acceptance and inspection data will cause the hash of all subsequent blocks to become invalid. Through this mechanism, a closed-loop traceability and anti-tampering supervision of the entire life cycle from material entry, process execution to acceptance inspection is realized, ensuring the credibility of the project quality data throughout the entire process.

[0037] Furthermore, after step S33, the method also includes: spatiotemporally associating the defect data in the detection results with the 4D / 5D schedule and cost information of the BIM model, automatically generating defect rectification tasks through smart contracts, and pushing them to the relevant responsible parties; The spatiotemporal correlation is based on matching the defect location coordinates with the component spatial information in the BIM model, binding the defect with the specific component and the current construction stage. At the same time, it combines 4D progress data to determine the time node of the defect occurrence and combines 5D cost data to estimate the resources required for rectification. The smart contract automatically generates a rectification task sheet according to the defect type and severity level, including rectification requirements, responsible persons, deadlines and budget constraints, and pushes it to the mobile terminals of the construction party, the supervision party and the owner through the blockchain event mechanism. After the rectification is completed, the relevant parties upload the rectification acceptance data, triggering a new round of testing and verification, forming a closed-loop management to ensure that all defects are traceable and handled in a closed loop.

[0038] Specifically, by introducing point cloud comparison detection and zero-knowledge proof technology during the acceptance inspection stage, the consistency verification of the inspection results with historical data is carried out and a new blockchain is generated and connected to the process chain. At the same time, after the defect data is associated with BIM 4D / 5D information, rectification tasks are automatically generated. This solves the problems of difficulty in verifying the quality of hidden works, disconnect between inspection data and construction process, and inability to trace the rectification of problems in a closed loop. It realizes credible verification in the acceptance stage and closed-loop management of defect rectification.

[0039] S4. Extract all block data from the cross-link extended chain, combine the component relationships of the BIM model, and use the blockchain consensus mechanism and smart contracts to automatically verify the timestamp, identifier and hash value of each block to obtain a verified complete dataset.

[0040] Furthermore, step S4 specifically includes: All block data are extracted from the cross-link extension chain to form the original block set; at the same time, the component hierarchy and topology in the BIM model are analyzed to generate a component relationship map with component ID as the node, providing a correlation benchmark for subsequent data verification; The extraction of the original block set is achieved by calling the RPC interface of the blockchain node or synchronizing local ledger data. A paginated retrieval mechanism is adopted to ensure that all data is fully obtained in large-scale block scenarios, and the blocks are decoded and restored to structured fields. The parsing of the BIM model is based on industrial basic class standards. The component elements and their attributes in the model are traversed to extract component ID, name, type, parent-child relationship and spatial location information. The association edges between components are stored using a graph database or in-memory graph structure to form a component relationship graph that supports fast traversal. Each node in the graph contains the static attributes of the component, and the edges identify the composition relationship or spatial adjacency relationship between components.

[0041] Based on the rules of the blockchain consensus mechanism, the timestamp sequence in the original block set is logically consistent to ensure that the block generation order and the timestamp increment relationship meet the consensus requirements. After the verification is successful, the smart contract is triggered to automatically execute the identifier comparison and hash value recalculation, matching the currently calculated hash value with the original hash value stored in the block, and removing tampered or abnormal blocks. The timestamp sequence verification adopts the time window rules agreed upon by the consensus mechanism. For example, it checks whether the timestamp of each block is strictly greater than the previous block and does not exceed the current system time plus the maximum allowable deviation. For networks using Practical Byzantine Fault Tolerance consensus, it is also necessary to verify whether the timestamp is aligned with the proposal time of the consensus node cluster. After the verification is passed, the smart contract traverses each block, extracts the BIM component ID and compares it with the component ID whitelist in the component relationship graph to ensure that all referenced component IDs exist in the model. At the same time, the hash value in the block header is recalculated, and the calculation result is compared bit by bit with the hash value stored in the block. If they are inconsistent, the block is marked as tampered and removed from the original set to ensure that the blocks participating in subsequent fusion are all trusted data that have been verified by consensus and history.

[0042] The valid block data with successful hash value matching is integrated with the component relationship graph. By associating information such as process, material, and acceptance with BIM components one by one through component ID, a complete dataset that has been verified by consensus and smart contract is formed, providing a reliable foundation for the trustworthy traceability and data analysis of the subsequent construction process.

[0043] The fusion process uses the component ID as the primary key, appending data such as material arrival records, construction logs, and acceptance inspection reports stored in the effective blocks to the attribute list of the corresponding component node in chronological order, forming a full lifecycle data chain at the component level. The fused data is persisted in the form of a graph database. In addition to the original BIM attributes, each component node is associated with multiple event nodes. The event nodes maintain a temporal relationship through a hash chain, and the event nodes store IPFS hashes to point to the original large file. This complete dataset supports quick retrieval of all historical data by component ID and achieves reliable traceability from the source of materials to the acceptance result through a graph traversal algorithm.

[0044] Specifically, by extracting cross-stage blockchain data and integrating it with the BIM component relationship graph, and using consensus mechanisms and smart contracts to automatically verify timestamps, identifiers, and hash values ​​to eliminate tampered data, the problem of fragmented and inconsistent data across stages and difficulty in ensuring authenticity has been solved. This has resulted in a trustworthy and complete dataset centered on components, providing a reliable data foundation for full lifecycle traceability.

[0045] S5. Based on the complete dataset and BIM component tree, construct a graph database index, establish the associated path from material arrival to acceptance inspection, and generate a chain path diagram for cross-stage queries.

[0046] Furthermore, step S5 specifically includes: S51. Extract structured records of each stage, such as material arrival, process execution, and acceptance inspection, from the complete dataset. At the same time, parse the hierarchical relationship of the BIM component tree, process each record into nodes according to its component ID and timestamp to form initial business node information, and mark the location distribution of nodes in the whole process. The extraction of structured records is achieved by traversing the complete dataset, filtering by three event types: material arrival, process execution, and acceptance inspection. Each record contains a component ID, timestamp, data hash value, and event type identifier. Node processing converts each record into an independent node in the graph database. Node attributes include event type, occurrence time, data summary, and a pointer to the original block. Simultaneously, the node is attached to the corresponding component in the BIM component tree based on the component ID. The location distribution labeling is based on the standardized phase division of the construction process, labeling material arrival nodes as Phase 1, process execution nodes as Phase 2, and acceptance inspection nodes as Phase 3, and recording the node's sequence number within its respective phase to provide a temporal basis for subsequent path construction.

[0047] S52. Based on the initial business node information, the node-edge model of the graph database is used to construct the entire process association path from material arrival to acceptance inspection. The physical relationship between components and the logical relationship of business data are transformed into edges in the graph database through preset mapping rules, generating a preliminary chain path framework. In the node-edge model, nodes include two types: component nodes and event nodes. Component nodes come from the BIM component tree, and event nodes come from the business nodes generated in step S51. The mapping rules include two types of edge generation logic: one type is "composition edges" based on the parent-child relationship of components, which connect component nodes at different levels; the other type is "time sequence edges" based on the same component ID and time sequence, which connect material arrival, process execution, and acceptance inspection event nodes under the same component, forming a vertical traceability path from arrival to acceptance. The preliminary path framework uses the component tree as the skeleton and the event chain as the network, completes storage through the batch write interface of the graph database, and establishes bidirectional indexes between nodes to support forward and reverse queries.

[0048] S53. For cross-stage query scenarios, the initial path framework is indexed and optimized. By analyzing the connection frequency and query hotspots between nodes, the index structure is dynamically adjusted to improve the traversal efficiency of key paths. The paths are then layered according to preset priority thresholds to determine the query support capabilities of each level of path. The index construction employs a combination of label and attribute indexes from graph databases. B+ tree indexes are built for frequently queried fields such as component ID, event type, and timestamps. Bidirectional pointers are also used to accelerate traversal of edges between nodes. Connection frequency analysis involves periodically scanning query logs to identify hot paths and frequently associated node pairs. Path results for high-frequency query paths are pre-calculated and cached. Priority thresholds are set based on the importance of project management. For example, paths related to main structural components are set to high priority, while decorative and finishing components are set to ordinary priority. During hierarchical processing, high-priority paths are stored on high-speed storage media and have denser indexes built, while ordinary priority paths use standard indexing strategies to ensure real-time response capabilities for critical business queries.

[0049] S54. Combine the layered path structure to generate a visual chain path graph, mark key nodes and paths, and integrate graph database traversal algorithms to achieve fast cross-stage query of the entire process. At the same time, dynamically update index information based on query response results to ensure the real-time and optimal nature of path query.

[0050] The chain-like path diagram uses a BIM component tree as its background, displaying event nodes in chronological order below the corresponding components in a flowchart format. Key nodes are marked with special colors and accompanied by data summary pop-ups, while critical paths are connected by bold lines. The graph database integrates traversal algorithms including depth-first search for complete tracing and breadth-first search for range queries. The query interface supports filtering returned path results by component ID based on time range or event type. The dynamic update mechanism records the response time after each query. If the query response for a certain path exceeds a preset threshold, it automatically triggers index reconstruction or cache preheating, while simultaneously feeding back hot path information to the index optimization module, forming an adaptive adjustment of the index strategy to ensure continuously optimal query performance over long-term operation.

[0051] By embedding nodes into a chain-like path graph using graph neural networks and training a similarity reasoning model, static traceability data is transformed into a dynamic knowledge graph with deep learning and reasoning capabilities. By aggregating multidimensional features of component nodes and their associated event nodes, such as quality indicators, temporal relationships, and material properties, a low-dimensional embedding vector is generated for each component. This enables efficient retrieval of similar components. When the features of the current component are input, the model can quickly return the most similar components in history, along with their quality data, defect records, and rectification measures, assisting construction managers in predicting potential quality risks of the current component. Simultaneously, the model supports anomaly detection. If the embedding vector of a new component deviates significantly from the historical distribution of normal components, an early warning is triggered, and enhanced inspection is recommended. This significantly improves the foresight, accuracy, and intelligence of quality control, achieving a leap from passive traceability to proactive prevention.

[0052] Furthermore, after step S54, the method further includes: performing node embedding representation on the chain path graph based on graph neural network, training a similarity reasoning model, and using it to intelligently recommend historical quality data and predict potential risks of similar components; The graph neural network employs a GraphSAGE or GCN architecture, taking component nodes and their associated event nodes as input. It generates a low-dimensional embedding vector for each component by aggregating features from neighboring nodes. The embedding vector preserves the component's quality characteristics, temporal relationships, and material properties throughout the construction process. The trained model is used for similar component retrieval: when the feature vector of the current component is input, the model quickly returns several historically most similar components, along with their quality data, defect records, and rectification measures, assisting construction managers in predicting potential quality risks for the current component. Simultaneously, the model supports anomaly detection; when the embedding vector of a new component deviates significantly from the historical distribution of normal components, an early warning is triggered, and enhanced inspection is recommended. This mechanism, through the deep learning and reasoning capabilities of the graph neural network, upgrades the static traceability path graph into a dynamic knowledge graph with intelligent analysis and prediction capabilities, further improving the foresight and accuracy of quality control.

[0053] Specifically, by combining the complete dataset with the BIM component tree, a chain path diagram from material arrival to acceptance inspection is constructed using a graph database, and a graph neural network is introduced to achieve intelligent risk prediction. This solves the problems of poor data correlation, low query efficiency and lack of proactive early warning capabilities in traditional traceability, and realizes the visualization and rapid query of cross-stage data and intelligent prediction of quality risks.

[0054] S6. In response to the query request, the nodes of the chain path graph are traversed through the smart contract, and the node hash value is compared with the on-chain stored value. If they match, the corresponding BIM component data and construction records are output to obtain the traceability result.

[0055] Furthermore, step S6 specifically includes: Receive traceability query requests, parse the target component identifier in the request, locate the corresponding starting node in the chain path graph, and trigger the smart contract to automatically start the traversal verification process. The query request is encapsulated in JSON-RPC format and includes parameters such as the target component identifier, query time range, and required data type. After the smart contract is parsed, the corresponding node in the chain path graph is quickly located through the component ID index. At the same time, the caller's identity and permissions are verified, and only authorized users can trigger the traversal process to prevent unauthorized data access.

[0056] JSON-RPC (JSON Remote Procedure Call) is a lightweight remote procedure call protocol based on JSON, which uses JSON format for data encoding.

[0057] Based on the association relationship in the chain path graph, the smart contract uses a depth-first search algorithm to traverse all related nodes from the starting node, obtains the hash value stored in each node, and compares it with the corresponding hash value stored on the blockchain in real time to verify the consistency of the data. The depth-first search algorithm is implemented in the smart contract through recursive calls. However, to avoid gas limitations, an iterative approach combined with a stack structure is used to simulate recursion. During the traversal, visited nodes are recorded to prevent loops. The hash value stored in each node is written during the generation in steps S2 and S3. During comparison, the original hash value corresponding to the node is read from the blockchain world state. If it matches, it is marked as a trusted node; otherwise, it is recorded as a tampered node and further traversal of that branch is terminated.

[0058] For nodes whose hash values ​​match, the smart contract automatically extracts the BIM component attribute data and construction process records associated with that node, summarizes and generates a complete component traceability result, and returns it to the querying party through the blockchain network to ensure the transparency and immutability of the traceability process.

[0059] The extraction process is handled according to the node type: component nodes directly return the static attributes in the BIM model, while event nodes obtain the original construction logs or inspection reports from distributed storage through IPFS hashes and perform summary verification on the returned data; the summary results are generated in a structured document format, with the digital signature and timestamp of the smart contract attached to ensure the authenticity and verifiability of the traceability results, and the returned data is transmitted to the querying party through an encrypted channel to prevent man-in-the-middle theft.

[0060] Specifically, by automatically traversing the chain path graph and comparing node hash values ​​in real time through smart contracts, the problem of data authenticity not being guaranteed and the query process being opaque in traditional traceability queries is solved, and verifiable and tamper-proof component-level precise traceability is achieved.

[0061] S7. Generate encrypted backups of the traceability results, distribute them to distributed nodes via IPFS, and use a hash chain algorithm to verify the consistency of the replicas, forming a persistent traceability system.

[0062] Furthermore, step S7 specifically includes: The traceability result data generated in step S6 is used as the original dataset. The original data is encrypted using the national cryptographic SM4 or AES-256 symmetric encryption algorithm to generate an encrypted backup data packet. The encrypted backup data packet is uploaded to the IPFS distributed storage network to obtain the returned unique content identifier (CID) and record the mapping relationship between the CID and the traceability task ID. The encryption process employs a dynamic key derivation mechanism. During each backup, a random key is generated by the hardware security module. The encryption key is then generated using a key derivation function combined with the traceability task ID and the current timestamp, ensuring that different backups use different keys. The encrypted data packet is appended with an initialization vector and key version information. When uploaded to IPFS, the data is fragmented and stored across multiple storage nodes using a distributed hash table. The returned CID is a multi-hash value based on the data content, possessing content addressing and collision prevention characteristics. The mapping relationship between the CID and the traceability task ID is written to the off-chain database, while the hash value is anchored to the blockchain via a smart contract for rapid data location during subsequent verification.

[0063] Based on the CID, the storage replica data set is obtained in parallel from multiple distributed nodes of the IPFS network. The hash chain algorithm is used to perform block-by-block hash calculation on the replica set to generate the current consistent hash value. The hash value is compared with the preset base hash value to verify the consistency between each replica and with the original data, ensuring the data integrity and tamper resistance of the distributed storage. The parallel acquisition process involves the IPFS client concurrently requesting multiple nodes, prioritizing nodes with fast response times and high reputations to return data blocks, and using erasure coding technology to reconstruct missing or corrupted data blocks. The hash chain algorithm divides the data into fixed-size blocks, calculates the SHA-256 hash value of each data block sequentially, and uses the hash value of the previous data block as input for the hash calculation of the next block, ultimately generating a chain root hash as the current consistent hash value. The preset baseline hash value is the chain root hash calculated when the original data is uploaded, stored in the blockchain notarization, and if it matches during comparison, it proves that all copies are complete and have not been tampered with.

[0064] The verified copy data set and its CID association information are anchored to the traceability records on the blockchain. The CID and consistency verification hash value are written into the evidence storage block through smart contracts, forming a persistent and verifiable distributed traceability system, realizing the long-term secure storage and globally trusted access of traceability results.

[0065] The anchoring process involves calling a smart contract to package the CID, consistency verification hash value, verification timestamp, and verification node signature into a transaction, which is then written into the immutable blockchain ledger after consensus is reached. Simultaneously, the smart contract triggers an event listener to notify relevant participants to update the trusted data index in their local cache. The persistent traceability system relies on IPFS's globally distributed storage and the immutability of the blockchain. Even if some storage nodes are offline, data can still be recovered through the remaining nodes, and data integrity can be verified at any time through on-chain hash values, achieving permanent preservation of traceability results and high availability access globally.

[0066] Specifically, by encrypting and backing up the traceability results and distributing them to IPFS distributed nodes, and using a hash chain algorithm to verify the consistency of the copies and anchoring them to the blockchain for storage, the problems of easy loss, tampering and difficulty in global trusted access of traceability data in long-term storage are solved, and persistent secure storage and high availability verification of traceability results are achieved.

[0067] Example 2, please refer to Figure 4 This embodiment provides a construction process quality traceability system based on BIM and blockchain, applied to a construction process quality traceability method based on BIM and blockchain, including: The material arrival management module is used to collect material information through IoT devices during the material arrival stage, associate the material information with the component identifier in the BIM model, and use blockchain smart contracts to generate an initial block containing timestamps, material hash values ​​and BIM component IDs to build an initial chain data structure based on BIM. The process execution management module is used to associate BIM 4D / 5D construction simulation data with real-time construction logs and personnel operation records according to the initial chain data structure during the process execution stage. It uses a hash chain algorithm to calculate the hash value of the previous block and link it with the current data to generate a process block containing IPFS hash, forming a continuous record sequence. The acceptance inspection management module is used to perform three-dimensional comparative inspection based on the continuous record sequence during the acceptance inspection stage, using the BIM model to verify the consistency between the inspection results and historical data through zero-knowledge proof technology, triggering the smart contract to generate a new block containing the inspection results, linking it to the previous process block, and forming a cross-link extension chain. The data verification and fusion module is used to extract all block data from the cross-link extended chain, combine the component relationships of the BIM model, and use the blockchain consensus mechanism and smart contracts to automatically verify the timestamp, identifier and hash value of each block to obtain a verified complete dataset. The traceability path construction module is used to build a graph database index based on the complete dataset and BIM component tree, establish a related path from material arrival to acceptance inspection, and generate a chain path diagram for cross-stage query. The traceability query execution module is used to respond to query requests, traverse the nodes of the chain path graph through smart contracts, compare the node hash value with the on-chain stored value, output the corresponding BIM component data and construction records, and obtain the traceability result. The intelligent analysis and prediction module is used to perform node embedding representation on the chain path graph based on graph neural network, train a similarity reasoning model, and intelligently recommend historical quality data and potential risk prediction of similar components. The data backup and persistence module is used to generate encrypted backups of the traceability results, distribute them to distributed nodes via IPFS, and verify the consistency of the replicas using a hash chain algorithm, thus forming a persistent storage traceability system.

[0068] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any brief modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for quality traceability throughout the entire construction process based on BIM and blockchain, characterized in that: Includes the following steps: S1. During the material arrival stage, material information is collected through IoT devices, and the material information is associated with the component identifiers in the BIM model. The initial block containing timestamps, material hash values, and BIM component IDs is generated using blockchain smart contracts to construct an initial chain data structure based on BIM. S2. During the process execution phase, based on the initial chained data structure, the BIM 4D / 5D construction simulation data is associated with the real-time construction log and personnel operation records. The hash value of the previous block is calculated using the hash chain algorithm and linked to the current data to generate a process block containing IPFS hash, forming a continuous record sequence. S3. During the acceptance and inspection phase, based on the continuous record sequence, a three-dimensional comparative inspection is performed using the BIM model. The consistency between the inspection results and historical data is verified using zero-knowledge proof technology. This triggers a smart contract to generate a new block containing the inspection results, which is then linked to the block of the previous process, forming a cross-linked extended chain. S4. Extract all block data from the cross-link extended chain, combine the component relationships of the BIM model, and use the blockchain consensus mechanism and smart contract to automatically verify the timestamp, identifier and hash value of each block to obtain a verified complete dataset. S5. Based on the complete dataset and BIM component tree, construct a graph database index, establish a related path from material arrival to acceptance inspection, and generate a chain path diagram for cross-stage queries. S6. In response to the query request, the nodes of the chain path graph are traversed through the smart contract, the node hash value is compared with the on-chain storage value, and the corresponding BIM component data and construction records are output to obtain the traceability result. S7. Generate an encrypted backup of the traceability results, distribute it to distributed nodes via IPFS, and verify the consistency of the replicas using a hash chain algorithm to form a persistent traceability system.

2. The method for quality traceability throughout the construction process based on BIM and blockchain as described in claim 1, characterized in that: Step S1 specifically includes: The material information is collected in real time through IoT devices, including data on material source, specifications and batches, and the integrity of the material information is determined by integrity detection algorithm. Based on the collected material information, the material information is matched with the component identifiers in the BIM model using pre-established mapping rules to obtain associated data pairs; For the associated data pairs, an initial block containing timestamps, material hash values, and BIM component IDs is generated using the blockchain smart contract mechanism. The hash value integrity of the block is then verified, and once the verification is successful, it is linked to the initial chain data structure based on BIM. The system retrieves the stored initial block information from the chained data structure, cross-validates the timestamps and material information in the blocks to determine data consistency, and evaluates the material information based on the verification results using a preset threshold rule to obtain a reliability determination.

3. The method for quality traceability throughout the construction process based on BIM and blockchain as described in claim 1, characterized in that: Step S2 specifically includes: Acquire BIM 4D / 5D construction simulation data, collect construction logs and personnel operation records in real time through IoT terminals, perform spatiotemporal alignment and format standardization processing on multi-source data, and generate a structured dataset to be uploaded to the blockchain; The hash chain algorithm is used to calculate the hash value of the previous block. The structured dataset of the current process is combined with the previous hash value to construct a new block. When the data volume exceeds the preset threshold, it is automatically stored in IPFS and the IPFS hash value is obtained. The process simulation data, construction log summary, key personnel operation information, previous block hash value and IPFS hash value are packaged to generate process blocks. After calculating the current block hash value, they are linked to a chain data structure to form a continuous sequence of construction process records.

4. The method for quality traceability throughout the construction process based on BIM and blockchain as described in claim 1, characterized in that: Step S3 specifically includes: S31. Obtain the 3D data and continuous recording sequence of the BIM model during the acceptance and inspection phase, and use a 3D detection algorithm based on point cloud comparison to compare the BIM model with the actual construction results in real time, and generate detection result data including deviation values ​​and compliance indicators. S32. Use zero-knowledge proof technology to verify the consistency between the test result data and the historical data in the continuous record sequence, and verify the logical consistency between the test result and the previous process record; if the verification is successful, trigger the automatic execution of the preset smart contract, and generate a new block data containing the test report hash, verification certificate and timestamp according to the test result; S33. Link the generated new block to the block of the previous process through the hash chain algorithm to form an extended blockchain chain across stages.

5. A method for quality traceability throughout the entire construction process based on BIM and blockchain as described in claim 1, characterized in that: Step S4 specifically includes: Extract all block data from the cross-link extension chain to form the original block set; at the same time, analyze the component hierarchy and topology in the BIM model to generate a component relationship map with component ID as the node; Based on the rules of the blockchain consensus mechanism, the timestamp sequence in the original block set is logically consistent. After the verification is successful, the smart contract is triggered to automatically execute the identifier comparison and hash value recalculation, and the currently calculated hash value is matched with the original hash value stored in the block, and the tampered or abnormal blocks are removed. The valid block data with successful hash value matching is integrated with the component relationship graph. The process, materials, and acceptance information are associated with BIM components one by one through the component ID, forming a complete dataset that has been verified by consensus and smart contracts.

6. The method for quality traceability throughout the construction process based on BIM and blockchain as described in claim 1, characterized in that: Step S5 specifically includes: S51. Extract structured records of material arrival, process execution, and acceptance inspection from the complete dataset. At the same time, parse the hierarchical relationship of the BIM component tree and process each record into nodes according to its component ID and timestamp to form initial business node information. S52. Based on the initial business node information, the node-edge model of the graph database is used to construct the entire process association path from material arrival to acceptance inspection. The physical relationship between components and the logical relationship of business data are transformed into edges in the graph database through preset mapping rules, generating a preliminary chain path framework. S53. For cross-stage query scenarios, the initial path framework is indexed and optimized. By analyzing the connection frequency and query hotspots between nodes, the index structure is dynamically adjusted to improve the traversal efficiency of key paths, and the paths are layered according to the preset priority threshold. S54. Combine the layered path structure to generate a visual chain path graph, mark key nodes and paths, integrate graph database traversal algorithms, query cross-stages related to the entire process, and dynamically update index information based on query response results.

7. A method for quality traceability throughout the construction process based on BIM and blockchain as described in claim 6, characterized in that: After step S54, the method further includes: performing node embedding representation on the chain path graph based on graph neural network, training a similarity reasoning model, and using it to intelligently recommend historical quality data and predict potential risks of similar components.

8. A method for quality traceability throughout the construction process based on BIM and blockchain as described in claim 1, characterized in that: Step S6 specifically includes: Receive traceability query requests, parse the target component identifier in the request, locate the corresponding starting node in the chain path graph, and trigger the smart contract to automatically start the traversal verification process. Based on the association relationship in the chain path graph, the smart contract uses a depth-first search algorithm to traverse all related nodes from the starting node, obtains the hash value stored in each node, and compares it with the corresponding hash value stored on the blockchain in real time. For nodes whose hash values ​​match, the smart contract automatically extracts the BIM component attribute data and construction process records associated with that node, summarizes and generates a complete component traceability result, and returns it to the querying party through the blockchain network.

9. A method for quality traceability throughout the construction process based on BIM and blockchain as described in claim 1, characterized in that: Step S7 specifically includes: The traceability result data is used as the original dataset. The original data is encrypted using a symmetric encryption algorithm to generate an encrypted backup data package. The encrypted backup data package is then uploaded to the IPFS distributed storage network to obtain the returned unique content identifier. Based on the content identifier, the stored replica data set is obtained in parallel from multiple distributed nodes of the IPFS network. The hash chain algorithm is used to perform block-by-block hash calculation on the replica set to generate the current consistent hash value, and the consistency between each replica and with the original data is verified. The verified copy data set and its content identifier association information are anchored to the traceability record on the blockchain, and the content identifier and consistency verification hash value are written into the evidence storage block through a smart contract.

10. A construction process quality traceability system based on BIM and blockchain, applied to the construction process quality traceability method based on BIM and blockchain as described in any one of claims 1-9, characterized in that: include: The material arrival management module is used to collect material information through IoT devices during the material arrival stage, associate the material information with the component identifier in the BIM model, and use blockchain smart contracts to generate an initial block containing timestamps, material hash values ​​and BIM component IDs to build an initial chain data structure based on BIM. The process execution management module is used to associate BIM 4D / 5D construction simulation data with real-time construction logs and personnel operation records according to the initial chain data structure during the process execution stage. It uses a hash chain algorithm to calculate the hash value of the previous block and link it with the current data to generate a process block containing IPFS hash, forming a continuous record sequence. The acceptance inspection management module is used to perform three-dimensional comparative inspection based on the continuous record sequence during the acceptance inspection stage, using the BIM model to verify the consistency between the inspection results and historical data through zero-knowledge proof technology, triggering the smart contract to generate a new block containing the inspection results, linking it to the previous process block, and forming a cross-link extension chain. The data verification and fusion module is used to extract all block data from the cross-link extended chain, combine the component relationships of the BIM model, and use the blockchain consensus mechanism and smart contracts to automatically verify the timestamp, identifier and hash value of each block to obtain a verified complete dataset. The traceability path construction module is used to build a graph database index based on the complete dataset and BIM component tree, establish a related path from material arrival to acceptance inspection, and generate a chain path diagram for cross-stage query. The traceability query execution module is used to respond to query requests, traverse the nodes of the chain path graph through smart contracts, compare the node hash value with the on-chain stored value, output the corresponding BIM component data and construction records, and obtain the traceability result; The intelligent analysis and prediction module is used to perform node embedding representation on the chain path graph based on graph neural network, train the similarity reasoning model, and intelligently recommend historical quality data and potential risk prediction of similar components. The data backup and persistence module is used to generate encrypted backups of the traceability results, distribute them to distributed nodes via IPFS, and verify the consistency of the replicas using a hash chain algorithm, thus forming a persistent storage traceability system.

Images