Risk assessment method and device, computer equipment and storage medium

Abstract

The invention relates to a risk assessment method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a building information model of a target bridge; building data of the target bridge are collected, and the collected building data are obtained; wherein the building data at least comprises one of the following data: bridge architecture data, construction progress data, quality detection data and safety detection data; determining target building data corresponding to a target data identifier from the collected building data based on the target data identifier of the building information model and an association relationship between the data identifier and the building data; and performing data comparison on the target building data corresponding to the target data identifier and the reference data to generate risk assessment data. By adopting the method, potential risks in the construction process can be identified more accurately, dynamic and intelligent supervision of the whole period of target bridge construction is realized, and powerful data support and decision basis are provided for engineering safety and quality assurance.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a risk assessment method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] With the development of smart construction and digital infrastructure management technologies, Building Information Modeling (BIM) has become an important tool for the full lifecycle management of bridge projects. This technology can integrate multi-dimensional data from all stages of design, construction, and operation and maintenance, enabling visualized and information-based management. Its key feature is using a unified data model as a carrier to support collaborative operations and decision analysis within the project. Traditionally, risk assessment for bridge construction and operation phases typically relies on manual on-site inspections and comparisons with paper or discrete electronic documents. Managers must manually compare on-site data such as structural inspections and construction progress with design drawings or independent quality and safety standards, relying on experience to determine if deviations or potential hazards exist. However, this current manual-driven, document-discrete management approach suffers from significant problems such as difficulties in information integration, low comparison efficiency, and delayed risk response. Summary of the Invention

[0003] Therefore, it is necessary to provide a risk assessment method, apparatus, computer equipment, computer-readable storage medium, and computer program product to address the aforementioned technical problems.

[0004] Firstly, this application provides a risk assessment method. The method includes:

[0005] Obtain the architectural information model of the target bridge; wherein, the architectural information model includes various reference data of the target bridge and the corresponding target data identifier;

[0006] The construction data of the target bridge is collected to obtain the collected construction data; wherein, the construction data includes at least one of the following: bridge structure data, construction progress data, quality inspection data, and safety inspection data;

[0007] Based on the target data identifier of the building information model and the association between the data identifier and the building data, the target building data corresponding to the target data identifier is determined from the collected building data;

[0008] The target building data corresponding to the target data identifier and the reference data are compared to generate risk assessment data.

[0009] In one embodiment, determining the target building data corresponding to the target data identifier from the collected building data based on the target data identifier of the building information model and the association relationship between the data identifier and the building data includes:

[0010] Analyze the building data and the data identifier to determine the data characteristics corresponding to the building data;

[0011] Based on the data features, a data identifier corresponding to the data features is matched from the building information model;

[0012] Establish the association between the data identifier and the building data.

[0013] In one embodiment, the risk assessment data includes quality risk data; the generation of risk assessment data includes:

[0014] The quality inspection data is compared with preset quality parameters to obtain the comparison results;

[0015] Obtain historical quality inspection data for each component of the target bridge;

[0016] Based on the quality inspection data and the historical quality inspection data, determine the trend of change in the quality inspection data;

[0017] Based on the comparison results and the changing trend, the quality risk data is determined.

[0018] In one embodiment, the risk assessment data includes schedule anomaly data, and the generation of risk assessment data includes:

[0019] Obtain the estimated completion time for each sub-area in the building information model;

[0020] The construction progress data is compared with the estimated completion time, and the delayed progress is determined.

[0021] Based on the lagging progress, abnormal progress data is generated, and the estimated completion time is updated.

[0022] In one embodiment, generating risk assessment data includes:

[0023] The building data is compared with the corresponding reference data to determine the initial risk data;

[0024] The time series features of the building data are input into a preset anomaly model to obtain anomaly coefficients; wherein, the time series includes building data and corresponding time data; the anomaly model is used to determine the probability of anomalies occurring based on the time series features of the data;

[0025] Risk assessment data is generated based on the initial risk data and the anomaly coefficient.

[0026] In one embodiment, the reference data includes a reference threshold, and the method further includes:

[0027] Obtain the historical architectural data of the target bridge;

[0028] Based on the historical building data, determine the statistical distribution characteristics of each building data point;

[0029] The reference threshold is determined based on the statistical distribution characteristics.

[0030] Secondly, this application also provides a risk assessment device. The device includes:

[0031] The data acquisition module is used to acquire the building information model of the target bridge; wherein, the building information model includes various reference data of the target bridge and the corresponding target data identifier;

[0032] The data acquisition module is used to collect the construction data of the target bridge to obtain the collected construction data; wherein, the construction data includes at least one of the following: bridge structure data, construction progress data, quality inspection data, and safety inspection data;

[0033] The association establishment module is used to determine the target building data corresponding to the target data identifier from the collected building data based on the target data identifier of the building information model and the association relationship between the data identifier and the building data;

[0034] The data comparison module is used to compare the target building data corresponding to the target data identifier with the reference data to generate risk assessment data.

[0035] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the risk assessment method as described in any one of the embodiments of this disclosure.

[0036] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the risk assessment method as described in any one of the embodiments of this disclosure.

[0037] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the risk assessment method as described in any of the embodiments of this disclosure.

[0038] The aforementioned risk assessment methods, devices, computer equipment, storage media, and computer program products automatically correlate and compare collected on-site actual construction data (such as structural, progress, quality, and safety data) to generate risk assessments. A closed-loop digital management process is established: through standardized correlation operations based on data identification, multi-source heterogeneous data is effectively unified, solving the problem of information silos and laying the foundation for accurate assessment; furthermore, an automated continuous comparison mechanism replaces traditional manual sampling, significantly reducing safety risks caused by oversights and delays, and greatly improving the efficiency of risk monitoring; finally, the system generates structured risk assessment data, providing managers with objective and traceable decision-making basis, realizing a shift from experience-based judgment to data-driven scientific decision-making, and comprehensively improving the timeliness, accuracy, and systematic nature of bridge engineering risk management. Attached Figure Description

[0039] Figure 1 This is a diagram illustrating the application environment of the risk assessment method in one embodiment;

[0040] Figure 2 This is a flowchart illustrating a risk assessment method in one embodiment;

[0041] Figure 3 This is a flowchart illustrating the implementation of a risk assessment method in one embodiment;

[0042] Figure 4 This is a structural block diagram of a risk assessment device in one embodiment;

[0043] Figure 5 This is a real-time structural block diagram of the risk assessment device in one embodiment;

[0044] Figure 6 Here is a block diagram of a risk assessment system in one embodiment;

[0045] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0047] The risk assessment method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on a cloud or other network server. In this application environment, terminal 102 can be used to collect and upload the target bridge's construction data (including at least one of bridge structure, construction progress, quality inspection, and safety inspection data) to server 104. Server 104 is configured to execute the method in this embodiment: obtain a target bridge construction information model containing various reference data and their data identifiers; establish a structured association between the identifiers and the received construction data based on the data identifiers of the model; and then automatically compare and analyze the construction data corresponding to each identifier with the reference data to generate risk assessment data reflecting deviations or anomalies. After processing, server 104 can push the risk assessment data to relevant terminals 102 for alarms or archiving to support safety decision-making and control of bridge engineering. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0048] In one embodiment, such as Figure 2 As shown, a risk assessment method is provided, including the following steps:

[0049] Step S200: Obtain the building information model of the target bridge; wherein the building information model includes various reference data of the target bridge and the corresponding target data identifier.

[0050] The building information model (BIM) of the target bridge can be a multi-dimensional dataset generated during the bridge's design, construction, and operation. This model can include geometric structural information, as well as bridge-related physical properties, material parameters, construction plans, and quality and safety standards. This model enables digital management of the bridge's entire lifecycle and provides fundamental data support for subsequent risk assessments.

[0051] In one exemplary embodiment, the building information model (BIM) of the target bridge can be generated in various ways, such as by integrating design drawings, construction records, and operation and maintenance data using BIM software. This model not only reflects the bridge's static attributes but can also be dynamically updated to adapt to changes during actual construction or operation. In this way, the BIM becomes the core data carrier connecting the design, construction, and operation and maintenance phases, providing a comprehensive and accurate data foundation for risk assessment.

[0052] In one exemplary embodiment, the building information model (BIM) can be updated in real time to reflect the latest status of the target bridge at different stages. For example, during the construction phase, the model can integrate real-time collected construction progress data and quality inspection data; during the operation phase, the model can include safety monitoring data and historical maintenance records. Through this dynamic updating mechanism, the BIM can always maintain a high degree of consistency with the actual engineering status, thereby providing more reliable data support for risk assessment.

[0053] Step S202: Collect the construction data of the target bridge to obtain the collected construction data; wherein, the construction data includes at least one of the following: bridge structure data, construction progress data, quality inspection data, and safety inspection data.

[0054] The acquisition of structural data for the target bridge can be achieved through various methods. For example, sensor networks can be used to monitor the bridge's physical state in real time, acquiring structural data including stress, deformation, and vibration. Construction progress data can be collected using project management software or on-site recording tools to ensure accurate understanding of task completion at each stage. Quality inspection data, covering material properties, component dimensions, and installation accuracy, can be generated using quality testing equipment and standardized processes. Simultaneously, comprehensive safety inspection data can be generated through safety inspection systems or reports provided by professional testing institutions. The data acquisition process must ensure timeliness and accuracy to provide a reliable basis for subsequent risk assessments. Furthermore, the acquired data must undergo preliminary cleaning and formatting to ensure effective comparison with reference data in the building information model.

[0055] In one exemplary embodiment, the integration and processing of multi-source heterogeneous data can also be implemented. For example, for bridge structure data, sensor arrays deployed at key parts of the bridge can acquire parameters such as structural stress, strain, and vibration frequency in real time; for construction progress data, task status and completion percentage information can be automatically synchronized through the project management platform interface; the collection of quality inspection data can be combined with on-site testing equipment and laboratory analysis results to form a complete quality record chain; and safety inspection data relies on regular inspection reports and automated monitoring systems to ensure that safety hazards can be detected and recorded in a timely manner. After standardization, these data will provide a solid data foundation for subsequent risk assessment.

[0056] Step S204: Based on the target data identifier of the building information model and the association between the data identifier and the building data, determine the target building data corresponding to the target data identifier from the collected building data.

[0057] The process of establishing the association between data identifiers and building data can include parsing and matching operations on the building data. Specifically, the collected building data is first parsed to extract key features, such as data type, timestamps, or spatial location. Then, based on these features, the corresponding data identifier is searched in the Building Information Model (BIM). Through this matching mechanism, the actual collected building data can be mapped one-to-one with the reference data in the model, thus forming a structured association. This method not only improves the efficiency of data processing but also ensures the accuracy of subsequent comparative analysis. Furthermore, intelligent algorithms, such as rule-based reasoning or machine learning models, can be introduced to further enhance the accuracy and robustness of the matching.

[0058] Among them, the target data identifier is a structured label in the building information model that can be used to uniquely distinguish each reference data, such as hierarchical identifiers such as "main beam concrete strength - left span - mid-span" and "pier column reinforcement spacing - No. 3 pier - bottom layer". The relationship between the data identifier and the building data is established through preset mapping rules, which cover the binding logic between metadata such as data source (such as sensor number, test report number), data type (such as numerical, text, image) and collection timestamp and the identifier. In practice, the collected building data is first parsed to extract its data source identifier, data category, and time information. Then, the target data identifiers in the building information model are traversed and matched in the parsed building data according to preset mapping rules. For example, the concrete strength data collected by sensor number "SG-001" is matched to the identifier "main beam concrete strength - left span - mid-span". For the same identifier with multiple data sources (such as manual detection data and sensor monitoring data at the same location), the device will filter or merge the data according to the data priority strategy (such as real-time monitoring data taking precedence over periodic detection data) to finally determine the unique target building data corresponding to each target data identifier, forming a one-to-one correspondence between "identifier and data", providing structured input for subsequent comparative analysis.

[0059] In one exemplary embodiment, the process of establishing the association between data identifiers and building data can also include adaptability to complex scenarios. For example, when the target bridge involves data from multiple regions, stages, or types, matching efficiency can be optimized through hierarchical modeling. Specifically, the building information model is divided into several sub-regions or sub-modules, each corresponding to a specific functional unit or construction stage. Based on the spatial distribution or time-series characteristics of the collected building data, it is categorized into the corresponding sub-modules. Furthermore, the matching rules for data identifiers can be further refined to ensure efficient and accurate association construction even with large amounts of data or complex structures. In addition, an incremental matching mechanism can be designed, re-matching only newly added or changed data, thereby significantly reducing computational overhead and improving system response speed. This method not only meets the data management needs of large-scale engineering projects but also provides more flexible and reliable support for subsequent risk assessments.

[0060] Step S206: Compare the target building data corresponding to the target data identifier with the reference data to generate risk assessment data.

[0061] The process of generating risk assessment data can include multi-level analysis and comprehensive judgment. The associated building data can be compared item by item with its corresponding reference data to identify deviations or anomalies. For example, construction progress data can be compared with the estimated completion time to determine if there are any delays; quality inspection data can be compared with preset quality parameters to assess whether it meets standards. Furthermore, historical data can be combined for trend analysis to further uncover potential risk factors. For example, by analyzing the changing trends of quality inspection data, potential future quality problems can be predicted; long-term monitoring of safety inspection data can assess whether the safety status of a bridge is deteriorating. These analytical results will be integrated into structured risk assessment data to support subsequent decision-making and management.

[0062] In one exemplary embodiment, intelligent algorithms can also be introduced to improve the accuracy and efficiency of risk assessment. For example, machine learning models can be used to analyze the time-series characteristics of building data to predict the probability of anomalies. Specifically, the collected building data and its timestamps can be input into a pre-trained anomaly detection model to obtain an anomaly coefficient for each data point. These anomaly coefficients are then combined with the initial risk data to generate a more comprehensive and accurate risk assessment result. Furthermore, customized assessment strategies can be designed based on different risk types. For example, for schedule risks, the assessment results can be optimized by dynamically adjusting the estimated completion time; for quality risks, a comprehensive score can be obtained by combining multi-dimensional quality indicators. This approach not only improves the scientific rigor and reliability of risk assessment but also provides more operational guidance for project management.

[0063] The aforementioned risk assessment method automatically correlates and compares collected on-site construction data (such as structural, progress, quality, and safety data) to generate a risk assessment. A closed-loop digital management process is established: through standardized correlation operations based on data identification, multi-source heterogeneous data is effectively unified, solving the problem of information silos and laying the foundation for accurate assessment; furthermore, an automated continuous comparison mechanism replaces traditional manual sampling, significantly reducing safety risks caused by oversights and delays, and greatly improving the efficiency of risk monitoring; finally, the system generates structured risk assessment data, providing managers with objective and traceable decision-making basis, realizing a shift from experience-based judgment to data-driven scientific decision-making, and comprehensively improving the timeliness, accuracy, and systematic nature of bridge engineering risk management.

[0064] In one embodiment, determining the target building data corresponding to the target data identifier from the collected building data based on the target data identifier of the building information model and the association relationship between the data identifier and the building data includes:

[0065] Analyze the building data and the data identifier to determine the data characteristics corresponding to the building data;

[0066] Based on the data features, a data identifier corresponding to the data features is matched from the building information model.

[0067] Establish the association between the data identifier and the building data.

[0068] The process of parsing building data can include data classification and feature extraction. For example, building data can be divided into different categories based on its source and type, such as structural, progress, quality, and safety categories. Key features can be extracted from each category of data; these features can be time attributes, spatial attributes, or specific business attributes. This provides clear input conditions for subsequent matching operations. When matching data identifiers, various techniques can be used to improve matching accuracy. For example, fuzzy matching algorithms can be used to handle inconsistencies between data features and identifiers, ensuring reliable association even in the presence of noise or format differences. Furthermore, semantic analysis techniques can be combined to gain a deeper understanding of the meaning of data features, thereby finding the most suitable identifier in the building information model. This method not only improves the success rate of matching but also enhances the system's adaptability. After establishing associations, the association results can be verified to ensure their accuracy and completeness. For example, cross-checking can be used to compare the associated data with the original collected data to confirm whether there are any omissions or incorrect matches. If a problem is found, a correction mechanism is triggered, re-executing the parsing and matching steps until the association reaches the expected quality standard. This process ensures the reliability of data in subsequent risk assessment stages, providing a solid guarantee for the scientific nature of the overall process.

[0069] In one exemplary embodiment, the correction mechanism may include both automated feedback and manual intervention modes. In automated feedback mode, the system can automatically identify and correct matching errors based on preset rules or algorithms. For example, when it finds that the deviation between certain building data and reference data exceeds a reasonable range, the system will mark these data and attempt to re-parse and match them. If automated correction fails to resolve the issue, manual intervention mode is triggered, where professionals review and adjust the abnormal data. This dual-track correction mechanism not only improves the flexibility of data processing but also ensures the accuracy of correlations in complex scenarios. Furthermore, all operation records during the correction process are fully saved, forming a traceable log file for subsequent auditing and optimization. In this way, the system's self-improvement capability is continuously enhanced, providing a more stable and reliable data foundation for risk assessment.

[0070] In this embodiment, by parsing building data and establishing its association with data identifiers, the problem of integrating multi-source heterogeneous data can be effectively solved. This process not only improves the efficiency of data processing but also provides high-quality data support for subsequent risk assessment. Through the application of intelligent algorithms and semantic analysis technology, the system can achieve accurate matching in complex scenarios, ensuring the accuracy and completeness of the association relationships.

[0071] In one embodiment, the risk assessment data includes quality risk data; the generation of risk assessment data includes:

[0072] The quality test data is compared with preset quality parameters to obtain the comparison results.

[0073] Obtain historical quality inspection data for each component of the target bridge.

[0074] Based on the quality inspection data and the historical quality inspection data, the trend of the quality inspection data is determined.

[0075] Based on the comparison results and the changing trend, the quality risk data is determined.

[0076] The process of determining the quality risk data may include comparing the currently collected quality inspection data with preset quality parameters item by item, identifying non-compliant parts, and recording specific deviation values ​​or anomalies. These deviation values ​​can serve as preliminary risk indicators to measure the gap between the current quality status and the expected target. By analyzing historical quality inspection data, a quality change trend chart of each component of the target bridge is constructed. This trend chart can intuitively reflect the changing pattern of the quality status over time, such as whether there are signs of gradual deterioration or periodic fluctuations. Combining the comparison results and the change trend, the system can comprehensively assess the quality risk level of each component. For example, if the current data deviates from the standard and historical data shows continuous deterioration, the component may be marked as high-risk; conversely, if the current data meets the standard and the historical trend is stable, the risk level is low. In addition, a weight allocation mechanism can be introduced to adjust the priority of the risk assessment results according to the importance of different components in the overall bridge structure, thereby ensuring that the assessment results are more targeted and practical.

[0077] In one exemplary embodiment, machine learning models can also be used to dynamically optimize quality risk data. For example, by training a time series prediction model, the system can predict potential future quality problems based on historical quality inspection data and issue early warnings. Simultaneously, the model can continuously update its parameters based on newly collected data to adapt to the actual operating conditions of the target bridge. This approach not only improves the foresight of risk assessment but also enhances the system's adaptability, enabling it to maintain efficient operation in complex and ever-changing engineering environments. The final generated quality risk data will be presented in a structured format, including risk levels, specific anomalies, trend analysis results, and corresponding improvement suggestions, providing comprehensive support for subsequent decision-making.

[0078] In this embodiment, potential quality risks can be comprehensively identified through multi-dimensional analysis of quality inspection data. Specifically, the currently collected quality inspection data is first compared item by item with preset quality parameters to determine whether there are any deviations or anomalies.

[0079] In one embodiment, the risk assessment data includes schedule anomaly data, and the generation of risk assessment data includes:

[0080] Obtain the estimated completion time for each sub-region in the building information model.

[0081] The construction progress data is compared with the estimated completion time, and the delayed progress is determined.

[0082] Based on the lagging progress, abnormal progress data is generated, and the estimated completion time is updated.

[0083] The process of generating progress anomaly data may include extracting the estimated completion time of each sub-region from the Building Information Model (BIM) to ensure the accuracy and consistency of the time data. Then, the actual collected construction progress data is compared with these estimated completion times one by one to identify the lagging sub-regions and their specific lag durations. Based on this, the system can classify each sub-region according to the severity of the lag, for example, into different levels such as slight lag, moderate lag, and severe lag. This classification mechanism helps managers quickly locate key problem areas and prioritize resource allocation for adjustments. Furthermore, the system can combine historical progress data to analyze lag trends and determine whether there is a risk of continued deterioration. If the progress of certain sub-regions is found to be consistently below target, a higher-level warning mechanism may be triggered, reminding relevant personnel to take emergency measures. When updating the estimated completion time, the system comprehensively considers the current actual progress, resource allocation, and external environmental factors, dynamically adjusting the timetable to ensure its rationality and feasibility. This method not only effectively addresses progress deviations but also provides a more scientific reference for subsequent construction plans, thereby improving the efficiency and flexibility of overall project management.

[0084] In one exemplary embodiment, intelligent algorithms can also be introduced to optimize the generation process of schedule anomaly data. For example, machine learning models can be used to perform time series analysis on construction progress data to predict potential future schedule deviations and formulate contingency strategies in advance. Specifically, the system can train a predictive model based on historical construction progress data and the current actual progress to assess the probability of completion for each sub-region within a specific future time period. If the prediction results indicate a high risk of lag in certain sub-regions, the system will automatically generate early warning information and suggest adjustments to resource allocation or optimization of the construction process. Furthermore, the model can also incorporate external environmental factors (such as weather conditions and supply chain status) for comprehensive analysis to further improve the accuracy of predictions. In this way, not only can early identification of schedule anomalies be achieved, but also more forward-looking decision support can be provided to managers, thereby significantly reducing the overall project risk caused by schedule deviations. The final generated schedule anomaly data will be presented in a clear, structured form, including lag levels, specific lag durations, trend prediction results, and corresponding optimization suggestions, providing comprehensive and actionable guidance for subsequent construction management.

[0085] In this embodiment, potential schedule risks can be accurately identified through multi-dimensional analysis of construction progress data. The system not only focuses on current delays but also combines historical data and future predictions to form a comprehensive evaluation perspective.

[0086] In one embodiment, generating risk assessment data includes:

[0087] The building data is compared with the corresponding reference data to determine the initial risk data.

[0088] The time series characteristics of the building data are input into a preset anomaly model to obtain anomaly coefficients; wherein, the time series includes building data and corresponding time data; the anomaly model is used to determine the probability of anomalies occurring based on the time series characteristics of the data.

[0089] Risk assessment data is generated based on the initial risk data and the anomaly coefficient.

[0090] The process of generating risk assessment data may include a comprehensive analysis of initial risk data and anomaly coefficients. The system dynamically adjusts the initial risk data based on the anomaly coefficient, thereby generating more accurate risk assessment results. For example, if the anomaly coefficient of a building data point is high, the system may increase its corresponding risk level and mark it as an object requiring close attention. Conversely, if the anomaly coefficient is low, its risk priority may be reduced, minimizing unnecessary resource investment. Furthermore, to improve the comprehensiveness of the assessment, the system can incorporate other relevant factors for supplementary analysis. For example, it can consider the spatial distribution characteristics of building data and the importance weights of related components, further refining the granularity of the risk assessment. This method not only enhances the scientific rigor and accuracy of the risk assessment but also enables more targeted risk management in complex engineering environments. The final risk assessment data will be presented in a multi-dimensional format, including risk level classification, anomaly point location, trend prediction, and optimization suggestions, providing managers with clear and practical decision support.

[0091] In one exemplary embodiment, real-time monitoring data can be further integrated to dynamically update risk assessment results. For example, the system can continuously collect the latest data from the construction site through a sensor network and compare it with historical data and reference standards to promptly identify changing trends in potential risks. This real-time capability not only improves the response speed of risk assessment but also provides more flexible decision support for project management. Furthermore, the system can introduce a multi-source verification mechanism to cross-verify key data points, avoiding misjudgments caused by errors from a single data source. When generating the final risk assessment data, the system comprehensively considers anomaly coefficients, initial risk levels, and real-time monitoring feedback to form a comprehensive and dynamic risk view. This approach enables managers to quickly locate high-risk areas in complex and ever-changing engineering environments and take targeted measures, thereby effectively reducing overall project risk. Simultaneously, all intermediate results and adjustment records during the assessment process are fully preserved, forming a traceable data chain and providing a solid foundation for subsequent auditing and optimization.

[0092] In this embodiment, by combining the time-series characteristics of building data with anomaly models, the accuracy of risk assessment can be significantly improved. The system not only focuses on static risk indicators but also identifies potential abnormal trends by dynamically analyzing the changing patterns in the time series.

[0093] In one embodiment, the reference data includes a reference threshold, and the method further includes:

[0094] Obtain the historical architectural data of the target bridge.

[0095] Based on the historical building data, the statistical distribution characteristics of each building data point are determined.

[0096] The reference threshold is determined based on the statistical distribution characteristics.

[0097] The process of determining the reference threshold can include in-depth analysis of historical building data to ensure its scientific validity and rationality. The system can also clean and organize the historical building data of the target bridge, removing outliers or noisy data to obtain a more accurate base dataset. By modeling the statistical distribution characteristics of this data, such as calculating key indicators like mean, variance, and standard deviation, a clear understanding of the overall data distribution pattern is formed. Based on this, the system can automatically calculate the reference threshold for each building data point according to preset confidence intervals or specific algorithms. For example, when using a Gaussian distribution model, the threshold range can be determined by adding or subtracting a certain number of standard deviations from the mean; while for non-normally distributed data, quantiles or other statistical methods may be used to determine a reasonable threshold. This method not only reflects the true characteristics of historical data but also adapts to personalized needs in different scenarios. Furthermore, the system can also combine expert experience or industry standards to verify and adjust the automatically generated reference thresholds to further improve its applicability.

[0098] In one exemplary embodiment, a dynamic update mechanism can be introduced, enabling the reference thresholds to automatically adjust as new data is continuously input. For example, the system can periodically collect the latest building data and integrate it with historical data to recalculate statistical distribution characteristics, thereby generating reference thresholds that better reflect the current situation. This dynamic adjustment not only enhances the system's adaptability but also maintains the scientific validity and effectiveness of the evaluation criteria over long-term operation. Furthermore, to ensure the reliability of the reference thresholds, the system can also implement multi-level verification processes. For instance, after automatically generating new reference thresholds, they can be verified through comparative analysis and simulation testing to confirm their rationality in practical application scenarios. If certain thresholds deviate from expectations, a manual review process is triggered for further calibration by professionals. This approach ensures the accuracy of the reference thresholds and provides more robust data support for risk assessment in complex engineering environments. In this way, the system can continuously optimize evaluation criteria under constantly changing conditions, laying a solid foundation for subsequent risk identification and management.

[0099] In this embodiment, through in-depth mining and analysis of historical building data, the system can dynamically generate reference thresholds that adapt to the needs of different scenarios. This method not only improves the scientific rigor of threshold setting but also provides a more accurate benchmark for risk assessment.

[0100] In one exemplary embodiment, the risk assessment method can be as follows: Figure 3 The implementation shown may specifically include:

[0101] Step S300: Collect thread data of the steel bridge. Specifically, data can be collected periodically by sensor terminals, detection equipment, and mobile terminals at the construction site, and uploaded with timestamps.

[0102] Step S302: Data access and processing. Specifically, data can be transmitted to the cloud server via a network gateway, and the data access module performs parsing, verification, outlier removal, and format conversion.

[0103] Step S304, BIM model data fusion. Specifically, the system can match sensor data with corresponding component information based on the unique identifier (GUID) of the components in the BIM model to establish a "component-data" mapping relationship.

[0104] Step S306: Visualization and Early Warning. Specifically, the system can compare real-time progress with planned progress and calculate deviations; perform threshold judgment and trend analysis on monitoring data; and trigger early warnings or generate reports according to set rules.

[0105] Step S308: Data closure and traceability. The processing results can be pushed to the front-end display layer via API, and the component status colors in the BIM model are updated in real time: normal (green), delayed (yellow), and abnormal (red). At the same time, warning information and suggested measures pop up on the right side of the interface.

[0106] Step S310: Generate a construction supervision report. Management personnel can confirm, record, and rectify early warning issues through the client. The rectification results are then fed back into the database, forming a closed-loop management system.

[0107] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0108] Based on the same inventive concept, this application also provides a risk assessment apparatus for implementing the risk assessment method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more risk assessment apparatus embodiments provided below can be found in the limitations of the risk assessment method described above, and will not be repeated here.

[0109] In one embodiment, such as Figure 4 As shown, a risk assessment device 400 is provided, including: a data acquisition module 401, a data collection module 403, a correlation establishment module 405, and a data comparison module 407, wherein:

[0110] The data acquisition module is used to acquire the building information model of the target bridge; wherein, the building information model includes various reference data of the target bridge and the corresponding target data identifier;

[0111] The data acquisition module is used to collect the construction data of the target bridge to obtain the collected construction data; wherein, the construction data includes at least one of the following: bridge structure data, construction progress data, quality inspection data, and safety inspection data;

[0112] The association establishment module is used to determine the target building data corresponding to the target data identifier from the collected building data based on the target data identifier of the building information model and the association relationship between the data identifier and the building data;

[0113] The data comparison module is used to compare the target building data corresponding to the target data identifier with the reference data to generate risk assessment data.

[0114] In one embodiment, such as Figure 5 As shown, another risk assessment device 500 is provided, including: a data acquisition module 501, a data transmission and access module 503, a data processing and analysis module 505, a visual monitoring and interaction module 507, and a system management and access control module 509, wherein:

[0115] Data Acquisition Module (Front-end Layer): The main execution components include on-site sensors, mobile terminals, and drone inspection systems. Key functions include collecting structural status data (such as stress, strain, displacement, and temperature); collecting construction progress data (component installation status, process completion status, etc.); collecting quality inspection data (weld inspection, coating thickness inspection, etc.); and collecting safety monitoring data (personnel positioning, environmental monitoring, etc.). Data generation formats: sensor data (JSON format), inspection reports (PDF / Excel), image and video data (JPG / MP4), etc. Data output: data is uploaded to the server-side data access module via IoT gateways or mobile terminals.

[0116] Data transmission and access module: The execution entity includes a cloud server or on-site edge computing nodes. Its main functions include receiving data streams from different devices; standardizing the format of raw data, synchronizing timestamps, and removing anomalies; and storing the data in a unified BIM database (based on the IFC standard). The processing flow includes data uploading from the data acquisition terminal; data verification and conversion by the access module; storage in the database; and generation of callable data interfaces for upper-layer modules to use.

[0117] Data Processing and Analysis Module (Core Algorithm Layer): The execution entity includes the server (cloud platform). Key functions include: Model Data Fusion Algorithm: mapping construction monitoring data to corresponding BIM components; Schedule Deviation Calculation Algorithm: calculating the deviation value ΔP based on planned and real-time progress; Quality Status Assessment Algorithm: assessing component health status by comparing monitoring parameter thresholds with historical data; Risk Warning Model: judging abnormal trends using rule engines or machine learning methods. An example of the algorithm principle is as follows: Assuming the actual installation time of component i is ti, and the planned installation time is Ti, then the schedule deviation is: ΔP = ti - Ti / Ti; when ΔP > α (set threshold), the system automatically generates a schedule deviation warning. For quality monitoring data Qi, if three consecutive sample values ​​deviate from the standard value Qs by more than a set proportion, a quality anomaly warning is triggered. Data Output: Generating a structural status assessment report, schedule deviation analysis results, and risk warning information, and pushing them to the visualization and monitoring module.

[0118] Visualized Monitoring and Interaction Module (Client Layer): The implementation entities include management terminals (PC, tablet, or mobile app). Key functions include dynamically displaying the real-time status of the construction site using a BIM 3D model; annotating component progress, quality, and risk information in the model using colors, symbols, and animations; allowing users to select components to view detailed monitoring data, historical curves, and inspection records; and providing an interface for early warning information push and decision support. Data Flow: Data is obtained from the server interface → loaded into the BIM front-end engine (such as Unity, Revit API, or WebGL) → real-time rendering and display on the user interface.

[0119] System Management and Access Control Module: The execution entities include the server and management terminal. Functions include user authentication and hierarchical access control; log recording, operation tracing, and data backup; and providing multi-role collaboration interfaces (owners, supervisors, and construction units share the same data view).

[0120] In an exemplary embodiment, the data processing sequence and execution logic can be as follows: Real-time data acquisition stage: Sensors and mobile terminals periodically collect on-site data → upload to the cloud access module; Data standardization and fusion stage: The access module performs data parsing → cleaning → storage in a unified database; Model mapping and analysis stage: The server calls the BIM component library → performs data matching → calculates progress / quality deviations → generates a risk assessment; Visualization stage: The client calls the visualization interface from the server → binds the monitoring results to the model → renders and displays the real-time construction status; Intelligent early warning and feedback stage: When an anomaly is detected, the system automatically triggers an early warning → sends a message to the terminals of supervisors and management personnel → allows remote confirmation and processing. Application scenario description: During the bridge main beam hoisting construction stage, the system links stress sensors with the BIM model in real time. When the hoisting stress or deviation exceeds the limit, the system marks the corresponding component in red in the 3D model and issues an early warning. Welding quality inspection stage: UAVs and infrared camera equipment collect appearance and temperature distribution images, and ultrasonic flaw detectors are used to detect internal defects in the weld. After the quality inspection results are uploaded, they are automatically associated with the corresponding components. If there are unqualified items in the inspection report, they are marked in yellow warning status in the model in real time. Overall progress monitoring phase: The system automatically calculates the progress deviation curve based on daily construction logs and displays areas of different completion levels in the model using gradient colors, enabling intuitive monitoring. Output results and technical effects: The final system outputs the following deliverables: a 3D visualized construction monitoring interface; a construction progress deviation and risk analysis report; a structural safety and quality monitoring report; and intelligent early warning information and decision-making suggestions.

[0121] Each module in the aforementioned risk assessment device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0122] In one embodiment, such as Figure 6 As shown, a risk assessment system is provided, including: a data acquisition layer, a data transmission layer, a data processing layer, a visualization and monitoring layer, and a system management layer, wherein:

[0123] Data Acquisition Layer: This layer consists of various acquisition terminals installed on the construction site, including: structural monitoring sensors for stress, strain, and displacement; environmental monitoring sensors (temperature, humidity, wind speed, etc.); mobile terminals (such as tablets or mobile apps used by construction workers); and drone inspection systems. This layer is responsible for real-time acquisition of multi-source data from the construction site and performing preliminary encoding processing.

[0124] Data transmission layer: This layer includes IoT gateways, wireless network modules, and data communication protocol interfaces (MQTT, HTTP, WebSocket, etc.). Its main function is to securely and stably transmit the data generated by the acquisition layer to cloud servers or edge computing nodes.

[0125] Data Processing Layer: Deployed on a cloud server, it includes the following sub-modules: Data Parsing and Cleaning Module: standardizes data formats and removes anomalies; Data Fusion Module: matches monitoring data with BIM model component IDs; Analysis and Early Warning Module: calculates and assesses risks related to construction progress, quality, and safety; Data Storage Module: stores the processing results in a unified database and establishes a data indexing interface.

[0126] Visualized Supervision Layer: This layer consists of client applications, including PC, web, and mobile versions. It utilizes a BIM 3D engine (such as Unity, Revit API, or WebGL) for real-time rendering and display, enabling 3D interaction, component status annotation, progress playback, and other functions.

[0127] System management layer: Includes modules for user authentication, access control, logging, and decision support, used for system security and operation and maintenance management.

[0128] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a risk assessment method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0129] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0130] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0131] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0132] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0133] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A risk assessment method, characterized in that, The method includes: Obtain the architectural information model of the target bridge; wherein, the architectural information model includes various reference data of the target bridge and the corresponding target data identifier; The construction data of the target bridge is collected to obtain the collected construction data; wherein, the construction data includes at least one of the following: bridge structure data, construction progress data, quality inspection data, and safety inspection data; Based on the target data identifier of the building information model and the association between the data identifier and the building data, the target building data corresponding to the target data identifier is determined from the collected building data; The target building data corresponding to the target data identifier and the reference data are compared to generate risk assessment data.

2. The method according to claim 1, characterized in that, The determination of the target building data corresponding to the target data identifier from the collected building data, based on the target data identifier of the building information model and the association relationship between the data identifier and the building data, includes: Analyze the building data and the data identifier to determine the data characteristics corresponding to the building data; Based on the data features, a data identifier corresponding to the data features is matched from the building information model; Establish the association between the data identifier and the building data.

3. The method according to claim 1, characterized in that, The risk assessment data includes quality risk data; The generated risk assessment data includes: The quality inspection data is compared with preset quality parameters to obtain the comparison results; Obtain historical quality inspection data for each component of the target bridge; Based on the quality inspection data and the historical quality inspection data, determine the trend of change in the quality inspection data; Based on the comparison results and the changing trend, the quality risk data is determined.

4. The method according to claim 1, characterized in that, The risk assessment data includes progress anomaly data, and the generation of risk assessment data includes: Obtain the estimated completion time for each sub-area in the building information model; The construction progress data is compared with the estimated completion time, and the delayed progress is determined. Based on the lagging progress, abnormal progress data is generated, and the estimated completion time is updated.

5. The method according to claim 1, characterized in that, The generated risk assessment data includes: The building data is compared with the corresponding reference data to determine the initial risk data; The time series features of the building data are input into a preset anomaly model to obtain anomaly coefficients; wherein, the time series includes building data and corresponding time data; the anomaly model is used to determine the probability of anomalies occurring based on the time series features of the data; Risk assessment data is generated based on the initial risk data and the anomaly coefficient.

6. The method according to claim 1, characterized in that, The reference data includes a reference threshold, and the method further includes: Obtain the historical architectural data of the target bridge; Based on the historical building data, determine the statistical distribution characteristics of each building data point; The reference threshold is determined based on the statistical distribution characteristics.

7. A risk assessment device, characterized in that, The device includes: The data acquisition module is used to acquire the building information model of the target bridge; wherein, the building information model includes various reference data of the target bridge and the corresponding target data identifier; The data acquisition module is used to collect the construction data of the target bridge to obtain the collected construction data; wherein, the construction data includes at least one of the following: bridge structure data, construction progress data, quality inspection data, and safety inspection data; The association establishment module is used to determine the target building data corresponding to the target data identifier from the collected building data based on the target data identifier of the building information model and the association relationship between the data identifier and the building data; The data comparison module is used to compare the target building data corresponding to the target data identifier with the reference data to generate risk assessment data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images