An engineering data processing method and related equipment based on generative artificial intelligence

Abstract

The present application provides an engineering data processing method and related equipment based on generative artificial intelligence, which relates to the field of electrical digital data processing technology. In this method, multiple historical engineering data of different engineering environments and design parameters are obtained, and engineering feature data is extracted after preprocessing, covering engineering scheme design parameters and engineering environment data. Then, an engineering data prediction model is constructed using a generative AI algorithm and annotated historical engineering data to simulate the distribution of real environment data, and then the target design parameters under the current engineering environment are obtained, and the target design parameters are input into the model together with the current engineering environment to obtain predicted values. The predicted values ​​are then compared with the actual observed values ​​to obtain comparison results, and finally the engineering data prediction model is evaluated and adjusted based on the comparison results. This method can improve the accuracy and reliability of engineering data processing.

Description

Technical Field

[0001] The present application relates to the technical field of electrical digital data processing, and in particular to an engineering data processing method and related equipment based on generative artificial intelligence. Background Art

[0002] In today's engineering field, whether it is construction engineering, mechanical engineering or electronic engineering, accurate data processing and prediction play a vital role in project planning, implementation and subsequent maintenance. As the scale and complexity of projects continue to increase, traditional empirical engineering data processing methods can no longer meet the needs. Engineering decisions need to be based on in-depth analysis and accurate prediction of various engineering data to reduce costs, improve project quality and ensure project safety.

[0003] Currently, much engineering data processing relies on traditional statistical analysis methods. After obtaining historical engineering data, engineers use statistical software to perform simple descriptive statistics on the data, calculating statistics such as the mean and standard deviation to understand the data's central tendency and dispersion. Correlation analysis is used to identify linear relationships between different variables in the engineering data, such as engineering design parameters and environmental parameters. When making predictions, linear regression models are often used. A regression equation is constructed based on the relationships between variables in the historical data. The relevant parameters of the current project are then substituted into the equation to produce a predicted value. To improve prediction accuracy, engineers strive to collect as much historical data as possible and filter it to remove any obvious outliers.

[0004] However, engineering data is often highly nonlinear and complex, and traditional linear regression models cannot accurately capture the complex relationships between data, so traditional methods find it difficult to accurately process and predict engineering data. Summary of the Invention

[0005] This application provides an engineering data processing method and related equipment based on generative artificial intelligence for accurately processing and predicting highly nonlinear and complex engineering data.

[0006] In the first aspect, the present application provides an engineering data processing method based on generative artificial intelligence, which is applied to a server, and the method includes: obtaining multiple historical engineering data with different design parameters under different engineering environments; after preprocessing the historical engineering data, performing feature extraction on the historical engineering data to obtain engineering feature data, and the engineering feature data includes at least engineering scheme design parameters and engineering environment data, and the engineering environment data refers to data related to the environment in which the engineering activities are located; combining the generative AI algorithm and the historical engineering data annotated with the engineering feature data to construct an engineering data prediction model, and the engineering data prediction model is used to simulate the data distribution under a real engineering environment; after obtaining the target design parameters under the current engineering environment, the target design parameters and the current engineering environment are input into the engineering data prediction model to obtain the current engineering data prediction value; comparing the current engineering data prediction value with the actual observation value to obtain a comparison result; evaluating the engineering data prediction model and adjusting it according to the comparison result.

[0007] By employing these technical solutions, we acquire historical engineering data from multiple projects with varying engineering environments and design parameters, providing a rich sample for subsequent analysis. Preprocessing and feature extraction generate engineering feature data, encompassing both engineering design parameters and engineering environment data, enabling precise extraction of key information. By combining generative AI algorithms with annotated historical engineering data to build a model, we leverage the algorithm's strengths to learn data characteristics and simulate the data distribution in real-world engineering environments. The model then inputs the target design parameters and environmental conditions of the current project into the predicted values. These values ​​are then compared with actual observed values ​​to evaluate and adjust the model, enabling dynamic optimization of engineering data, improving prediction accuracy and reliability, and providing a more scientific basis for engineering decision-making.

[0008] In combination with some embodiments of the first aspect, in some embodiments, after the step of constructing an engineering data prediction model by combining a generative AI algorithm and historical engineering data annotated with the engineering feature data, it also includes: receiving a text description input by the user, and identifying the target design parameters using natural language processing technology; identifying a first current engineering environment from the engineering environment image uploaded by the user using image recognition technology; determining a second current engineering environment through environmental sensors within a set area of ​​multiple engineering activities; and determining the final current engineering environment by combining the first current engineering environment and the second current engineering environment.

[0009] By adopting the above technical solution, the system receives user-entered text descriptions and uses natural language processing technology to identify target design parameters, making it easier for users to express their needs and improving interaction convenience. The system identifies the first current engineering environment from user-uploaded images and uses environmental sensors to determine the second current engineering environment. This multi-channel environmental information collection ensures comprehensive information. The two are combined to determine the final current engineering environment, integrating data from different sources to make the acquired current engineering environment data more accurate and authentic. This provides more realistic input for the engineering data prediction model, improving the model's adaptability to the current engineering situation and its prediction accuracy.

[0010] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining the final current engineering environment by combining the first current engineering environment and the second current engineering environment, it also includes: using geographic information system data to analyze the topography, geological structure and infrastructure distribution information in the preset area of ​​the current project area; after fusing the topography, geological structure, infrastructure distribution information and the final current engineering environment data, adjusting the final current engineering environment data.

[0011] By employing this technical solution, GIS data is used to analyze topography, geological structure, and infrastructure distribution, supplementing project environmental data from a macro-geographic perspective. This information is integrated with the final current project environmental data to comprehensively consider multiple factors. Adjustments to this integrated data optimize the environmental data, making it more accurately reflect the complex environmental conditions in which the project actually operates. This adjusted environmental data allows the project data prediction model to simulate the real-world project environment more comprehensively and accurately, thereby enhancing the scientific nature and reliability of the model's predictions.

[0012] In combination with some embodiments of the first aspect, in some embodiments, after the step of constructing an engineering data prediction model by combining a generative AI algorithm and historical engineering data annotated with the engineering feature data, it also includes: obtaining real-time data during the current engineering implementation process, which real-time data includes at least engineering progress and equipment operating status data; when the engineering progress is delayed or the equipment operating status data is abnormal, the parameters in the engineering data prediction model are adjusted according to preset rules based on the severity of the delay or abnormality.

[0013] By implementing this technical solution, real-time data, such as project progress and equipment operating status, is captured during project implementation, providing real-time insights into project progress. When project delays or equipment operating abnormalities occur, model parameters are adjusted according to pre-set rules, enabling timely corrections to the model based on changing conditions. Because project data is influenced by actual project conditions, these adjustments allow the model to better adapt to dynamic changes, maintain accurate predictions, and avoid disconnects between model predictions and actual conditions caused by unexpected project events.

[0014] In combination with some embodiments of the first aspect, in some embodiments, when the project progress is delayed or the equipment operation status data is abnormal, after the step of adjusting the parameters in the engineering data prediction model according to preset rules based on the severity of the delay or abnormal situation, it also includes: establishing an engineering data prediction model sharing platform for different engineering types based on the engineering type of the current project; when the engineering data prediction model is adjusted and optimized, uploading the adjusted model parameters and optimization experience to the sharing platform; after receiving the case viewing instruction sent by the user end, obtaining optimization cases similar to the current project from the sharing platform, and combining the characteristics of the current project to perform a second optimization on the current engineering data prediction model.

[0015] By implementing the above technical solution, a shared platform is established based on project type, providing a channel for data and experience exchange across different projects. After model adjustment and optimization, parameters and experience are uploaded to accumulate industry knowledge. When a user-side case review instruction is received, similar optimization cases are retrieved and the model is re-optimized based on the characteristics of the current project. This allows the model to learn from the successful experiences of other projects and further improve its own characteristics. This approach continuously improves model performance, enhances the accuracy and efficiency of project data prediction, and promotes the joint advancement of data prediction technology across the entire engineering industry.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of comparing the current engineering data predicted value with the actual observation value to obtain a comparison result, it also includes: if the comparison result shows that the error between the current engineering data predicted value and the actual observation value exceeds a preset error range, and the current engineering data predicted value is associated with a preset engineering safety key indicator, then the emergency response mechanism is automatically started; an alarm message is sent to the management end, and at the same time, virtual reality technology is used in combination with a hazard database to simulate suspected dangerous scenarios; and the suspected dangerous scenarios are sent to the management end for display.

[0017] By employing this technical solution, after comparing predicted values ​​with actual observed values, if the error exceeds a preset range and correlates with a critical safety indicator, an emergency response mechanism is automatically activated, enabling a rapid response to potential risks. Alerts are sent to management terminals, and virtual reality technology, combined with a hazard database, simulates suspected hazardous scenarios, enabling managers to intuitively and quickly understand potential hazards. The simulated scenarios are then displayed on the management terminal, providing a strong basis for timely and informed decision-making and enabling rapid and effective risk mitigation measures.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of sending an alarm message to the management end and simulating a suspected dangerous scene using virtual reality technology combined with a danger database, it also includes: using blockchain technology to record the alarm message and the suspected dangerous scene.

[0019] By adopting the above technical solutions, the tamper-proof and traceable characteristics of blockchain can ensure the authenticity and reliability of the data. These records can provide accurate original data for subsequent analysis of abnormal situations, making it easier to review the causes of accidents.

[0020] In a second aspect, the present application provides a server comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code comprising computer instructions, the one or more processors calling the computer instructions to cause the server to execute the method described in the first aspect and any possible implementation of the first aspect.

[0021] In a third aspect, the present application provides a computer-readable storage medium comprising instructions, which, when executed on a server, cause the server to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, the present application provides a computer program product, which, when executed on a server, enables the server to execute the method described in the first aspect and any possible implementation of the first aspect.

[0023] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0024] 1. Due to the adoption of technical means based on the collection, preprocessing and feature extraction of historical engineering data, combined with the generative AI algorithm to build a prediction model, and the target design parameters and environment of the current project are input into the model, and compared with the actual observation values ​​for evaluation and adjustment, it effectively solves the technical problems of inaccurate prediction of traditional engineering data and the inability to dynamically adjust to different engineering environments and changes in design parameters. It then achieves dynamic and accurate prediction of engineering data, providing a more scientific and reliable basis for engineering decision-making.

[0025] 2. By using the geographic information system to analyze the topography, geological structure and infrastructure distribution information of the project area and integrating and adjusting it with the current project environment data, the technical problem of incomplete and inaccurate consideration of project environment information in existing project data processing has been effectively solved, thereby achieving the technical effect of improving the simulation ability of the project data prediction model for complex environmental conditions and providing more comprehensive and accurate environmental data support for the planning and implementation of project construction.

[0026] 3. Due to the adoption of a technical means of establishing an engineering data prediction model sharing platform based on the engineering type, uploading and sharing the optimized model parameters and experience, and re-optimizing the model in combination with the current engineering characteristics after receiving the user-side case viewing instructions, it effectively solves the technical problems of the difficulty in continuous optimization of a single engineering data prediction model and the inability to fully utilize the experience of similar cases in the industry, thereby achieving the technical effect of improving model performance, improving the accuracy and efficiency of engineering data prediction, and promoting the common progress of the engineering industry in data prediction technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a flow chart of an engineering data processing method based on generative artificial intelligence in an embodiment of the present application;

[0028] Figure 2 This is another flowchart of the engineering data processing method based on generative artificial intelligence in an embodiment of the present application;

[0029] Figure 3 This is a schematic diagram of the physical device structure of the server in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The terms used in the following examples of the present application are for the purpose of describing specific embodiments only and are not intended to limit the present application. As used in the specification and appended claims of the present application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to and encompasses any or all possible combinations of one or more of the listed items.

[0031] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0032] For ease of understanding, the following describes the process of the method provided by this implementation. Figure 1 , which is a flow chart of the engineering data processing method based on generative artificial intelligence in an embodiment of the present application.

[0033] S101, obtaining multiple historical engineering data with different design parameters under different engineering environments;

[0034] The server connects to various engineering databases. These databases may come from different engineering fields, such as industry-standard databases in the construction engineering field, which store detailed data on a large number of completed construction projects, including building design parameters (such as building structure type, building area, number of floors, etc.) and corresponding engineering environment data (such as the climate conditions, geological conditions, and surrounding environment of the project site); and internal enterprise databases in the mechanical engineering field, which contain design parameters of various mechanical equipment (such as the size, material, and transmission method of mechanical components) and their operating data under different working conditions.

[0035] The server connects to these databases using standardized data interface protocols and, according to pre-defined query rules, selects historical engineering data that meets the requirements. For example, to obtain bridge construction project data, the server sends a query to the relevant transportation engineering database, requesting design parameters (such as span, beam height, and pier type) for bridges of different structural types and in different regions over the past decade, as well as environmental data from the construction phase (such as earthquake intensity, wind speed, and river flow in the region).

[0036] S102: After preprocessing the historical engineering data, extract features from the historical engineering data to obtain engineering feature data, where the engineering feature data includes at least engineering scheme design parameters and engineering environment data, where the engineering environment data refers to data related to the environment in which the engineering activities take place;

[0037] After obtaining multiple historical engineering data with different design parameters in different engineering environments, the server needs to preprocess these data to improve data quality. The preprocessing at least includes data cleaning and data standardization.

[0038] After preprocessing, the server performs feature extraction. For engineering design parameters, taking bridge engineering as an example, the server uses analytical geometry and structural mechanics to extract geometric parameters such as bridge span, beam height, and pier spacing from digitized files of bridge design drawings. By reading the bill of materials and design specifications, the server obtains material parameters such as the bridge structure material type and strength grade. Using logical analysis, the server then analyzes functional parameters such as the bridge structure system (e.g., beam bridge, arch bridge, cable-stayed bridge), and construction techniques (e.g., cantilever casting, jacking, etc.).

[0039] Regarding the extraction of project environmental data, for meteorological data, the server establishes an interface with a meteorological data platform to obtain historical meteorological data for the project site, including temperature, humidity, wind speed, and precipitation. Data fusion technology is used to integrate multi-source meteorological data to improve data accuracy. For geological data, the server extracts data from digital documents of geological exploration reports, parsing the report text using natural language processing techniques to identify stratigraphic structure and geotechnical parameters (such as the elastic modulus and Poisson's ratio of the rock and soil). Geographic Information System (GIS) technology is used to obtain geological structural information about the project area, such as fault distribution and fold morphology. For surrounding environmental data, the server uses image recognition technology to analyze satellite or aerial imagery of the area surrounding the project to identify geographic features such as buildings, roads, and rivers. Web crawler technology is used to obtain data on the distribution of infrastructure surrounding the project, such as the location and size of substations and communication base stations, from relevant geographic information websites.

[0040] S103. Build an engineering data prediction model by combining a generative AI algorithm with historical engineering data annotated with the engineering feature data. The engineering data prediction model is used to simulate data distribution in a real engineering environment.

[0041] When building prediction models for engineering data, the server uses cutting-edge generative AI algorithms tailored to the characteristics of engineering data, such as a hybrid algorithm combining a variational autoencoder (VAE) and a generative adversarial network (GAN). This is because the complexity and nonlinearity of engineering data make it difficult for traditional algorithms to effectively capture its inherent patterns. This hybrid algorithm leverages the strengths of both approaches. VAEs learn the underlying distribution of data by encoding and decoding it, mapping engineering feature data into a low-dimensional space to extract key features, reducing data redundancy and enabling the model to focus on core information. GANs, through adversarial training of the generator and discriminator, generate data samples that more closely resemble the real-world data distribution, improving the model's generalization capabilities.

[0042] When preparing annotated historical engineering data with engineering feature data, the server first deeply annotates the previously extracted engineering feature data. For engineering design parameters, the annotations not only include the specific values ​​of the parameters but also indicate the engineering subsystem to which they belong, the design standards and specifications, and the ideal range under different working conditions. For example, in bridge engineering, when annotating bridge spans, it is clearly stated that they are bridge superstructure design parameters based on the "General Specifications for the Design of Highway Bridges and Culverts," and reasonable value ranges for different types of bridge spans are given. For engineering environmental data, the annotations include the data collection time, location, accuracy, and degree of relevance to key aspects of the project. For example, meteorological data is annotated with the specific time of collection, accurate to the minute, the longitude and latitude coordinates of the collection location, and the measurement accuracy of the data, such as temperature, accurate to 0.1°C. The impact on the construction progress (such as how high temperatures affect the quality of concrete pouring and thus the construction progress) and the long-term stability of the project (such as the impact of strong winds on the stress of the bridge structure) are also explained.

[0043] During model training, the server utilizes powerful computing resources and adopts a distributed training strategy. Historical engineering data is divided into multiple subsets according to certain rules and assigned to multiple computing nodes for parallel training. The training tasks on each computing node are relatively independent, yet they collaborate through a parameter synchronization mechanism. For example, using a parameter server architecture, computing nodes regularly upload gradient information from the training process to the parameter server. The parameter server updates the model parameters based on this gradient information and distributes the updated parameters to the computing nodes, thereby accelerating the training process, improving training efficiency, and reducing training time. At the same time, the server also utilizes transfer learning technology to draw on the parameters and experience of previously trained models in other similar engineering fields. For example, some parameters and training experience related to structural mechanics analysis from a model that has been successfully applied in the construction engineering field are transferred to the bridge engineering data prediction model, accelerating model convergence and improving the model's training results, enabling it to more quickly and better simulate the data distribution in real engineering environments.

[0044] In some embodiments, as a project progresses, the server continuously acquires real-time data on the current project implementation process. This data covers at least project progress and equipment operating status. For project progress data, the server connects to the project management system to obtain real-time information such as the actual and planned completion times for each project phase, enabling accurate monitoring of the project's progress. In construction projects, the server can obtain progress data for various stages, such as foundation construction and main structure construction, from project management software. For equipment operating status data, the server connects to the monitoring systems of various types of engineering equipment to collect real-time operating parameters, such as speed, temperature, and vibration amplitude for mechanical equipment, and voltage and current for electrical equipment. This data provides a timely reflection of the equipment's operating status, helping staff identify potential problems in advance. When the server detects a delay in project progress or an anomaly in equipment operating status data, it adjusts the parameters of the project data prediction model based on pre-set rules and the severity of the delay or anomaly. The server pre-sets different delay and anomaly levels. In terms of project progress, a delay of less than 10% behind the planned schedule is considered minor, 10%-30% is considered moderate, and over 30% is considered severe. Regarding equipment operating status, abnormality levels are determined based on the degree to which key equipment parameters deviate from the normal range. For minor issues, the server may only fine-tune some minor parameters in the model, such as adjusting the efficiency parameters related to the equipment. For severe issues, however, the model structure or key parameters may be significantly adjusted, reassessing the impact of the equipment failure on the overall project progress and quality. Key parameters such as the relevant weight coefficients in the model will be adjusted accordingly to better align the model with the actual project situation and ensure the accuracy of the prediction.

[0045] To facilitate data and experience sharing between different projects, the server establishes a shared platform for engineering data prediction models based on the current project type. This platform stores valuable resources from various projects involved in the data prediction model optimization process. The shared platform for construction projects stores model optimization experiences for various building structures and scales. The shared platform for mechanical engineering projects focuses on operational data processing and model optimization for various types of mechanical equipment. This allows project teams working on the same or similar projects to share and access useful information on the platform, promoting technological advancement across the industry. After optimizing an engineering data prediction model, the server uploads the adjusted model parameters and optimization experience to the shared platform. This uploaded content becomes a valuable knowledge repository for the shared platform, providing a reference for other projects. When the server receives a case review request from the user, it selects optimization cases from the shared platform that are similar to the current project. By comparing the current project's characteristics, such as project scale, construction environment, and materials used, it performs a compatibility analysis on these selected cases. Based on these analysis results, the server performs a secondary optimization of the current engineering data prediction model. We may learn from the model structure adjustment methods in similar cases, or refer to their parameter optimization strategies to further improve the performance of the current model, so that it can more accurately predict engineering data and provide more reliable support for engineering decision-making.

[0046] S104: After obtaining the target design parameters under the current engineering environment, input the target design parameters and the current engineering environment into the engineering data prediction model to obtain the current engineering data prediction value;

[0047] The server primarily obtains target design parameters for the current project environment through various interactive methods. Firstly, the server provides a user-friendly interface, allowing users to enter target design parameters in either structured tables or free text. For structured table input, the server pre-sets parameter templates based on different project types. Users simply fill in specific values ​​according to the templates, and the server performs real-time format verification and data validity checks. For example, when entering architectural design parameters, the server sets reasonable value ranges for parameters such as building area and number of floors based on architectural design standards. If the user's input exceeds this range, the system immediately displays an error message and guides the user to correct the error. For free text input, the server utilizes natural language processing technology to first perform semantic analysis on the input text, extract key information, and then match and correlate it with a knowledge base of engineering parameters, converting the natural language description into precise design parameters. Furthermore, the server can also integrate with design software systems. Many engineering design tasks utilize specialized design software. The server has developed corresponding interface programs to enable data interaction with these design software. Once the designer completes the design in the software, the server automatically extracts the target design parameters from the software's database or files, ensuring parameter accuracy and consistency and avoiding errors that may arise from manual input.

[0048] Acquiring current engineering environment data also involves a multi-channel integration approach. In addition to acquiring data from user-uploaded images and environmental sensors, as mentioned above, the server also connects to professional environmental monitoring platforms. For example, for meteorological environmental data, the server establishes a data connection with the meteorological department's official monitoring platform to obtain high-precision, high-frequency meteorological data in real time, including temperature, humidity, wind speed, wind direction, and air pressure. For geological environmental data, the server connects to the database of geological exploration agencies to obtain the latest geological exploration report data, including stratigraphic structure, geotechnical parameters, and geological structure information.

[0049] After obtaining complete target design parameters and current project environment data, the server inputs this data into the established project data prediction model. During this input process, the server preprocesses the data, such as normalization, mapping data of varying magnitudes and units to specific intervals to improve the efficiency and stability of model training and prediction. After receiving the data, the model performs predictions on the current project data based on the patterns and rules learned during training. The model outputs predictions in various forms, including continuous values ​​(such as stress and strain values ​​of project structures and project cost estimates) and discrete categories (such as potential failure types and project quality levels). The server further processes and displays the prediction results based on the type of prediction and actual application requirements.

[0050] S105: Compare the predicted value of the current engineering data with the actual observed value to obtain a comparison result;

[0051] First, the server develops specialized data comparison strategies for different types of engineering data. For numerical data, such as the stress and strain values ​​of engineering structures and the physical properties of engineering materials, the server uses a combination of absolute and relative error calculations. Absolute error intuitively reflects the magnitude of the difference between the predicted value and the actual observed value, while relative error reflects the proportion of this difference to the actual observed value, providing a more comprehensive assessment of prediction accuracy.

[0052] For non-numeric data, such as engineering failure types and engineering quality grades, the server evaluates it using metrics such as classification accuracy, recall, and F1 value. Classification accuracy measures the proportion of correctly predicted samples relative to the total number of samples; recall focuses on the proportion of samples that actually belong to a certain category and are correctly predicted; and F1 value is the harmonic mean of accuracy and recall, providing a more balanced reflection of the model's performance on classification tasks. The server compares the predicted results with the observed classification labels one by one, and then calculates the values ​​of each metric.

[0053] During the data comparison process, the server also considers the time series characteristics of the data. Project data often exhibits temporal correlation, and changes in data at different time points reflect the dynamic development of the project. Therefore, the server uses time series analysis methods to compare the temporal trends of the predicted and observed values. By calculating statistics such as the autocorrelation function and partial autocorrelation function of the time series, the server can determine whether the predicted values ​​accurately capture the changing trends of the actual data. If the actual observed values ​​exhibit seasonal fluctuations and the predicted values ​​fail to reflect this trend, even if the error at a single time point is small, the overall prediction effect will be unsatisfactory.

[0054] In some embodiments, when a deviation between predicted and observed values ​​occurs and involves critical safety indicators, a series of measures are triggered to address potential risks. Specifically, during the monitoring and analysis of project data, the server continuously compares the predicted values ​​of the current project data with the actual observed values. If the comparison results indicate that the difference between the two exceeds a pre-defined error range and the predicted value correlates with a preset critical safety indicator for the project, the system immediately and automatically activates an emergency response mechanism. These critical safety indicators may include structural stress limits in construction projects and the load-bearing capacity of key components in mechanical equipment. During construction, if the predicted structural stress value exceeds the error range of the actual observed value and approaches or exceeds the designed safety limit, the activation conditions are met. Once the emergency response mechanism is activated, the server sends an alert to the management end to draw their attention. This alert contains detailed risk information, such as the specific project location, the critical safety indicators involved, and the discrepancy, allowing management to quickly understand the severity and overall situation of the problem. Furthermore, the server utilizes virtual reality (VR) technology in conjunction with a hazard database to simulate suspected hazardous scenarios. The hazard database stores detailed data and simulation models of dangerous situations that may be encountered in various projects, covering chain reactions caused by fire, collapse, and equipment failure. Through VR technology, these data are converted into realistic three-dimensional scenes to show the development process of potential hazards and the possible consequences. In order to ensure the authenticity, reliability and traceability of the data, the server uses blockchain technology to record this information after sending alarm information and suspected dangerous scenes to the management end. Blockchain is a distributed ledger technology with the characteristics of being tamper-proof and traceable. The server stores the content of the alarm information, sending time, receiving object, and simulation data and key parameters of suspected dangerous scenes in encrypted form on multiple nodes of the blockchain. This recording method prevents the data from being maliciously tampered with, and any access and modification to the data will leave traces. In the subsequent investigation or review of the accident, relevant personnel can accurately obtain the alarm and simulation scene data at the time through the blockchain, clearly understand the situation when the incident occurred, and analyze the cause of the accident.

[0055] S106: Evaluate and adjust the engineering data prediction model based on the comparison results.

[0056] Based on the comparison results obtained in S105, the server conducts a comprehensive evaluation of the engineering data prediction model from multiple perspectives. First, from the perspective of error metrics, the server sets different error thresholds. If the absolute error or relative error exceeds the pre-set threshold, it indicates that the model has a significant deviation in predicting this portion of the data. For classified data, if the classification accuracy, recall rate, or F1 value falls below the set standard, it also indicates that the model's classification performance needs improvement. The server determines the severity of the model's deviation based on the degree of deviation from these metrics.

[0057] Secondly, the server analyzes the model's performance under different engineering environments and design parameter combinations. By comparing large amounts of historical and current engineering data in groups, the server examines the model's prediction accuracy under specific environmental conditions (such as high temperature, high humidity, and strong seismic zones) or within specific design parameter ranges (such as long-span bridge design and super-high-rise building design). If the model performs poorly in certain specific situations, it indicates that the model is not adaptable to these special conditions and requires targeted optimization.

[0058] During the model adjustment phase, the server will adopt different adjustment strategies based on the evaluation results. If the prediction deviation is caused by improper model parameter settings, the server will use an optimization algorithm to readjust the model parameters. For example, the stochastic gradient descent algorithm is used to iteratively update the model parameters based on the backpropagation of the error, optimizing the model towards reducing the error. During the adjustment process, the server continuously monitors changes in error indicators and stops parameter adjustment when the error converges to a certain level or reaches the set optimization target. In addition, the server continues to collect new engineering data and regularly retrains the model. As engineering practice accumulates, new data will contain more information and changing trends. The server will merge the new data with historical data and re-perform data preprocessing, feature extraction, and model training to enable the model to adapt to the dynamic changes in engineering data and maintain good predictive performance.

[0059] In the embodiments of this application, a series of technical means are adopted, including acquiring historical engineering data from multiple sources, meticulously preprocessing and extracting features from the data, building models with cutting-edge generative AI algorithms, collecting current engineering data from multiple channels for prediction, and dynamically optimizing the model based on the comparison results. This allows the full exploitation of the potential value and complex relationships in engineering data. This effectively addresses the problems of low prediction accuracy, difficulty adapting to dynamic changes in the engineering environment and design parameters, limited in-depth mining of engineering environment information, and lack of industry experience sharing in model optimization, which exist in traditional engineering data processing methods. This allows for accurate and dynamic processing and prediction of engineering data, improving the quality and safety of engineering construction.

[0060] After combining the above content, the following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the engineering data processing method based on generative artificial intelligence in an embodiment of the present application.

[0061] S201, receiving a text description input by a user, and identifying target design parameters using natural language processing technology;

[0062] The server first builds a natural language processing (NLP) system that integrates multiple advanced NLP technologies. The server pre-processes the text input by the user, applying lexical analysis techniques and word segmentation algorithms to break the text into individual words or tokens.

[0063] During the semantic understanding phase, the server employs a deep learning-based semantic understanding model. This model is pre-trained on large-scale text data and acquires rich linguistic knowledge and semantic representations. The server inputs the preprocessed text into these models, which perform in-depth analysis of the semantic relationships between words in the text to understand the text's intent and key information. To more accurately identify target design parameters, the server builds and maintains a specialized engineering domain terminology knowledge base. This knowledge base covers specialized terminology for various engineering types, parameter names and definitions, possible value ranges, and other information. During the recognition process, the server matches and correlates the key information output by the semantic understanding model with the terminology knowledge base.

[0064] S202, identifying a first current engineering environment from an engineering environment image uploaded by a user using image recognition technology;

[0065] The server preprocesses user-uploaded images, including image denoising and normalization, to improve image quality and consistency and facilitate subsequent feature extraction. During feature extraction, the server uses a pretrained CNN model, which has been trained on large-scale image datasets and is capable of learning rich image feature representations. The server inputs the preprocessed engineering environment image into the pretrained model, which uses convolution operations to extract low-level features such as edges, texture, and color. Then, through a combination of multi-layer networks, it extracts higher-level, more abstract features that can represent various engineering environment elements in the image.

[0066] To accurately identify specific elements in the engineering environment, the server built an engineering environment element classifier. This classifier, trained on a large amount of labeled engineering environment image data, can identify common engineering environment elements such as buildings, terrain, vegetation, roads, and water bodies. The server inputs the features extracted by the CNN model into the classifier, which analyzes and determines the features and outputs the engineering environment element category corresponding to each area in the image.

[0067] The server then uses object detection algorithms to locate and identify specific engineering environment objects in the image. These algorithms can quickly detect the location and category of objects in the image, allowing the server to accurately identify key engineering environment objects in the image, such as large equipment at the construction site and surrounding special buildings.

[0068] S203, determining a second current engineering environment through a plurality of environmental sensors within the engineering activity setting area;

[0069] The server establishes stable and reliable communication links with multiple environmental sensors within the designated engineering activity area. These sensors may include meteorological sensors (such as temperature, humidity, wind speed, and air pressure), geological sensors (such as seismic sensors, soil moisture, and geotechnical pressure), and environmental monitoring sensors (such as noise, air quality, and water quality). The server uses standardized communication protocols to exchange data with the sensors, ensuring stable and efficient data transmission. The server also synchronizes data from different sensor types to ensure that all data has the same time base, facilitating subsequent comprehensive analysis.

[0070] The server utilizes data fusion technology to fuse different types of data collected by multiple sensors. Using a weighted average method, the server assigns different weights to each sensor's data based on its accuracy and reliability, and then calculates the weighted average as the fusion result. For complex environmental parameters, the server employs more advanced data fusion algorithms, such as the Kalman filter, which establishes a state-space model to optimally estimate the data from multiple sensors, resulting in more accurate and comprehensive data on the current project environment.

[0071] S204, determining a final current engineering environment by combining the first current engineering environment and the second current engineering environment;

[0072] The server utilizes data fusion technology to combine the first and second current project environments. During the data fusion process, the server employs a weighted fusion algorithm. Different weights are assigned to the first and second current project environment data based on the data's accuracy, reliability, and relevance to project decisions. For data closely related to project safety and critical decision-making, such as geological conditions and the location of large equipment, sensor data with higher accuracy and reliability in these areas is given a higher weight. For macro-environmental features, such as the general layout of surrounding buildings, image recognition data may be more advantageous, and its weighting is increased accordingly. The two types of data are integrated through methods such as weighted averaging and weighted fusion. For example, for terrain data of a specific area, image recognition provides general terrain contour information, while sensors provide local terrain elevation data. The server then fuses these two data types based on weighting to produce a more accurate description of the terrain.

[0073] S205. Analyze the topography, geological structure, and infrastructure distribution information within the preset area of ​​the current project area using geographic information system data;

[0074] The server first connects to a professional Geographic Information System (GIS) database, which stores high-resolution topographic data, detailed geological structure information, and comprehensive infrastructure distribution data. To obtain this topographic information, the server utilizes GIS's spatial analysis capabilities to process the Digital Elevation Model (DEM) data for the project area. By calculating parameters such as slope, aspect, and terrain relief, it accurately analyzes the changing characteristics of the terrain. Using contour generation technology, it visually displays the terrain's height and depth, providing foundational topographic information for project planning.

[0075] For geological structure information, the server extracts geological layer data from a GIS database, including information on stratum distribution, fault orientation, and fold morphology. Using geological modeling techniques, a three-dimensional geological model is constructed, visually presenting the spatial distribution characteristics of geological structures. The server also incorporates geomechanical principles to conduct a preliminary assessment of the stability of geological structures and analyze the potential impacts of different geological structures on engineering construction, such as the potential for earthquake risks near faults and the potential impact of unstable strata on the stability of building foundations.

[0076] When obtaining information about infrastructure distribution within a pre-defined area, the server uses GIS's network analysis and spatial query capabilities to retrieve various types of infrastructure within the area, such as roads, bridges, hydropower facilities, and communication base stations. For road facilities, the server analyzes parameters such as road grade, width, and traffic capacity to assess their impact on the transportation of construction materials and the flow of personnel. For hydropower facilities, the server obtains information such as their location, capacity, and supply range to determine whether they can meet the water and electricity needs during the project's construction and operation. For communication base stations, the server determines their coverage and signal strength to ensure smooth communication at the project site.

[0077] The server leverages GIS's buffer analysis capabilities to create buffer zones of varying radii, centered around the project construction area, and analyzes the density and importance of infrastructure within these zones. Infrastructure close to the project and with significant impact, such as nearby substations and water pipelines, is highlighted and analyzed, providing detailed infrastructure information for subsequent project planning and environmental data integration.

[0078] S206: After integrating the topography, the geological structure, the infrastructure distribution information and the final current engineering environment data, adjusting the final current engineering environment data.

[0079] The server uses data assimilation technology to deeply integrate topographical information, geological structure, and infrastructure distribution with the final current project environment data. When integrating topographical data, the server integrates terrain parameters (such as slope and aspect) obtained from GIS with the terrain-related information in the first and second current project environment data. Through spatial interpolation and data matching, the accuracy and completeness of the terrain data are improved. For geological structure data, the server combines stratigraphic information and fault data from the geological model with geological sensor data from the project site to correct and improve the geological environment data, ensuring that the geological data accurately reflects the actual geological conditions of the project area.

[0080] When integrating infrastructure distribution information, the server correlates the location and attributes of various infrastructure types with surrounding environmental elements in the project environment data. Road information is combined with project transportation route planning to optimize transportation plans based on road capacity and project material transportation needs. Hydropower facility information is matched with the project's hydropower supply needs to assess whether existing hydropower facilities can meet project needs and, if any, develop appropriate solutions.

[0081] After the data fusion is completed, the server adjusts the final current engineering environment data after fusion according to the actual needs and characteristics of the project. For the construction phase, the server focuses on data related to construction safety and progress. Adjust the layout plan of the construction site according to the topographic data to avoid setting up important construction facilities in areas with complex or unstable terrain; optimize the foundation construction plan based on the geological structure data, and strengthen foundation reinforcement measures for areas with poor geological conditions. For the project operation phase, the server adjusts the focus of the environmental data according to the infrastructure distribution data and the functional requirements of the project. If the project is a large commercial building, the server will focus on analyzing the impact of surrounding transportation facilities and public service facilities on the project operation, and make corresponding adjustments to the environmental data based on the analysis results to provide more targeted data support for project operation management.

[0082] The server will also continuously monitor changes in the project environment. When changes are found in the topography, infrastructure, etc., the corresponding data will be updated in a timely manner, and the data will be re-integrated and adjusted to ensure that the final current project environment data can always accurately reflect the actual environmental conditions of the project.

[0083] In the embodiments of this application, due to the use of technical means such as natural language processing, image recognition, sensor data fusion, geographic information system analysis, and deep fusion and dynamic adjustment of multi-source data, it is possible to obtain more comprehensive, accurate, and realistic current engineering environment data, and provide high-quality input data for the engineering data prediction model, while improving the model's adaptability to complex environments and the reliability of predictions. This effectively solves the problems of incomplete and inaccurate environmental data acquisition in traditional engineering data processing, poor quality of model input data, difficulty in comprehensively considering the complex geographical environment surrounding the project, and inability to dynamically optimize environmental data according to the actual needs of the project, thereby improving the accuracy and reliability of engineering data prediction.

[0084] The following describes the server in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of a server in an embodiment of the present application.

[0085] It should be noted that Figure 3 The structure of the server shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0086] like Figure 3 As shown, the server includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes, such as the methods described in the above embodiments, based on programs stored in a read-only memory (ROM) 302 or programs loaded from a storage unit 308 into a random access memory (RAM) 303. RAM 303 also stores various programs and data required for system operation. CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0087] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, push button switches, and the like; an output section 307 including a liquid crystal display (LCD), an audio output device, indicator lights, and the like; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 310 as needed, so that computer programs read from the removable media can be installed in the storage section 308 as needed.

[0088] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for executing the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 309 and / or installed from removable media 311. When executed by the central processing unit (CPU) 301, the computer program performs the various functions defined in the present invention.

[0089] It should be noted that specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0090] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings.

[0091] Specifically, the server of this embodiment includes a processor and a memory, and a computer program is stored in the memory. When the computer program is executed by the processor, the engineering data processing method based on generative artificial intelligence provided by the above embodiment is implemented.

[0092] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the server described in the above embodiments, or may exist independently and not incorporated into the server. The storage medium carries one or more computer programs, which, when executed by a processor of the server, enable the server to implement the engineering data processing method based on generative artificial intelligence as provided in the above embodiments.

[0093] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0094] As used in the above embodiments, the term “when” may be interpreted to mean “if” or “after” or “in response to determining that” or “in response to detecting that”, depending on the context. Similarly, the phrases “upon determining that” or “if (stated condition or event) is detected” may be interpreted to mean “if determining that” or “in response to determining that” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0095] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for processing engineering data based on generative artificial intelligence, applied to a server, characterized in that: The method comprises: Acquire multiple historical engineering data with different design parameters under different engineering environments; After preprocessing the historical engineering data, feature extraction is performed on the historical engineering data to obtain engineering feature data, wherein the engineering feature data at least includes engineering scheme design parameters and engineering environment data, wherein the engineering environment data refers to data related to the environment in which the engineering activities are located; Building an engineering data prediction model by combining a generative AI algorithm with historical engineering data annotated with the engineering feature data, wherein the engineering data prediction model is used to simulate data distribution in a real engineering environment; After obtaining target design parameters under the current engineering environment, the target design parameters and the current engineering environment are input into the engineering data prediction model to obtain current engineering data prediction values; Comparing the predicted value of the current engineering data with the actual observed value to obtain a comparison result; Evaluate the engineering data prediction model and make adjustments based on the comparison results; After the step of building an engineering data prediction model by combining the generative AI algorithm and the historical engineering data annotated with the engineering feature data, the following steps are further included: Acquire real-time data during the current project implementation process, the real-time data including at least project progress and equipment operating status data; When the project progress is delayed or the equipment operation status data is abnormal, the parameters in the project data prediction model are adjusted according to the severity of the delay or abnormality according to preset rules; When the project progress is delayed or the equipment operation status data is abnormal, after the step of adjusting the parameters in the project data prediction model according to the preset rules based on the severity of the delay or abnormality, the method further includes: Establish a sharing platform for engineering data prediction models of different engineering types based on the engineering type of the current project; After the engineering data prediction model is adjusted and optimized, the adjusted model parameters and optimization experience are uploaded to the sharing platform; After receiving the case viewing instruction from the user end, obtaining optimization cases similar to the current project from the sharing platform, and combining the characteristics of the current project to perform a secondary optimization on the current project data prediction model; After the step of comparing the predicted value of the current engineering data with the actual observed value to obtain a comparison result, the method further includes: If the comparison result shows that the error between the current engineering data predicted value and the actual observed value exceeds the preset error range, and the current engineering data predicted value is associated with the preset engineering safety key indicator, the emergency response mechanism is automatically activated; Send alarm information to the management end, and use virtual reality technology combined with the danger database to simulate suspected dangerous scenes; The suspected dangerous scene is sent to the management terminal for display.

2. The method according to claim 1, characterized in that After the step of combining the generative AI algorithm and the historical engineering data annotated with the engineering feature data to build an engineering data prediction model, the method further includes: Receive the text description input by the user and identify the target design parameters using natural language processing technology; Identifying a first current engineering environment from an engineering environment image uploaded by a user using image recognition technology; determining a second current engineering environment through a plurality of environmental sensors within a set area of ​​the engineering activity; A final current engineering environment is determined by combining the first current engineering environment and the second current engineering environment.

3. The method according to claim 2, characterized in that After the step of determining a final current engineering environment by combining the first current engineering environment and the second current engineering environment, the method further includes: Use geographic information system data to analyze the topography, geological structure, and infrastructure distribution information within the project area; After the topography, the geological structure, the infrastructure distribution information and the final current engineering environment data are integrated, the final current engineering environment data is adjusted.

4. The method according to claim 1, wherein After sending an alarm message to the management end and simulating suspected dangerous scenarios using virtual reality technology combined with a hazard database, the following steps are also included: Blockchain technology is used to record the alarm information and the suspected dangerous scene.

5. A server, characterized in that: The server includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the server to execute the method according to any one of claims 1 to 4.

6. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a server, the server is caused to execute the method according to any one of claims 1 to 4.

7. A computer program product, characterized in that When the computer program product is run on a server, the server is caused to perform the method according to any one of claims 1 to 4.

Images