Data processing method and device applied to building informatization system
By receiving and preprocessing construction progress data in the building information system, using machine learning algorithms to identify key features and construct feature vectors, the problem of massive data processing in the building information system is solved, and accurate prediction and intelligent analysis of construction progress are achieved.
Patent Information
- Application Number
- CN202411540190.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-31
- Publication Date
- 2025-02-28
AI Technical Summary
How to efficiently and accurately process massive data from the building information system to predict construction progress.
By receiving real-time construction progress data from the construction project site, pre-processing and verification, using machine learning algorithms to automatically identify and extract key features, build feature vectors, and input the construction progress prediction model for prediction and visualization.
It realizes accurate prediction and intelligent analysis of construction progress of construction projects, improves the accuracy and efficiency of construction progress prediction, and provides strong decision-making support for construction project management.
Smart Images
Figure CN119539154A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of building information technology, and in particular to a data processing method and device applied to a building information system. Background Art
[0002] With the rapid development of information technology, building information systems have become an indispensable part of the modern construction industry. By integrating and applying information technology, the system achieves efficient and accurate management of the entire life cycle of construction projects. However, the core of the building information system lies in data processing. How to efficiently and accurately process massive data is the key to improving the system's ability to predict construction progress. Summary of the invention
[0003] The technical problem to be solved by the present invention is how to efficiently and accurately process the massive data of a building information system to predict the construction progress; in view of this, the present invention provides a data processing method and device applied to a building information system.
[0004] The technical solution adopted by the present invention is a data processing method applied to a building information system, comprising:
[0005] Step S1, the construction information system receives real-time construction progress data from the construction project site;
[0006] Step S2, preprocessing the construction progress data;
[0007] Step S3, using a machine learning algorithm to automatically identify and extract key features related to the construction progress of the building project in the construction progress data, and construct a feature vector;
[0008] Step S4, inputting the feature vector into the configured construction progress prediction model to predict the corresponding construction progress and perform visualization processing.
[0009] In one embodiment, the step S1 further includes a verification process, specifically including:
[0010] Checking whether the format of the progress data meets the predetermined standard;
[0011] Verifying the integrity of said progress data;
[0012] By comparing historical data with the progress data, the accuracy of the timestamp is verified and outliers caused by recording errors are eliminated.
[0013] In one embodiment, the step S1 further includes:
[0014] The architectural information system records the data that does not meet the requirements during the verification process and notifies the data source to make corrections or supplements.
[0015] In one embodiment, step S2 specifically includes:
[0016] The construction information system cleans the received construction progress data;
[0017] The construction information system standardizes the cleaned construction progress data.
[0018] In one embodiment, the method of automatically identifying and extracting key features related to the construction progress of the construction project from the construction progress data using a machine learning algorithm includes:
[0019] Use random forest or gradient boosted tree algorithms to automatically identify key features related to the construction progress of a building project, including: project size, complexity, construction team experience level, weather conditions, material availability, and equipment failure rate.
[0020] In one embodiment, constructing a feature vector includes:
[0021] Calculate the correlation coefficient between each key feature and the construction progress, and sort the key features according to the magnitude of the correlation coefficient;
[0022] The architectural information system selects the key features whose correlation coefficient is greater than a preset value to construct a feature vector.
[0023] In one embodiment, the method further comprises:
[0024] The construction information system uses machine learning or deep learning algorithms to train the construction progress prediction model.
[0025] Another aspect of the present invention further provides a data processing device for use in a building information system, comprising:
[0026] A collection unit configured to receive real-time construction progress data from a construction project site as a building information system;
[0027] A preprocessing unit configured to preprocess the construction progress data;
[0028] a feature extraction unit configured to automatically identify and extract key features related to the construction progress of the building project from the construction progress data using a machine learning algorithm, and construct a feature vector;
[0029] The prediction unit is configured to input the feature vector into a configured construction progress prediction model to predict the corresponding construction progress and perform visualization processing.
[0030] Another aspect of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the data processing method applied to a building information system as described in any one of the above items.
[0031] Another aspect of the present invention further provides a computer storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the data processing method applied to a building information system as described in any one of the above items are implemented.
[0032] Compared with the prior art, the present invention has at least the following advantages:
[0033] The technical solution of the present invention, through the above-mentioned detailed steps and implementation methods, the construction information system uses machine learning algorithms to automatically identify key features related to the construction progress of construction projects, and constructs feature vectors or feature matrices, thereby realizing accurate prediction and intelligent analysis of the construction progress of construction projects. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] Figure 1 A schematic diagram of a data processing method applied to a building information system according to an embodiment of the present invention;
[0035] Figure 2 is another flow chart of a data processing method applied to a building information system according to an embodiment of the present invention;
[0036] Figure 3 A schematic diagram of a data processing method and device applied to a building information system according to an embodiment of the present invention;
[0037] Figure 4 The figure is a schematic diagram of the composition of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0038] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose, the present invention is described in detail below in conjunction with the accompanying drawings and preferred embodiments.
[0039] Unless otherwise defined, all terms (including technical terms and scientific terms) used in this article have the same meaning as commonly understood by ordinary technicians in the field to which this application belongs. It should also be understood that terms (such as terms defined in commonly used dictionaries) should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and will not be interpreted in an idealized or overly formal sense unless explicitly defined in this article.
[0040] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0041] The embodiment of the present invention, as Figure 1 As shown, a data processing method applied to a building information system comprises:
[0042] Step S1, the construction information system receives real-time construction progress data from the construction project site;
[0043] Step S2, preprocessing the construction progress data;
[0044] Step S3, using a machine learning algorithm to automatically identify and extract key features related to the construction progress of the building project in the construction progress data, and construct a feature vector;
[0045] Step S4, inputting the feature vector into the configured construction progress prediction model to predict the corresponding construction progress and perform visualization processing.
[0046] refer to Figure 2 , the method provided in this embodiment will be described in detail step by step below.
[0047] Step 1: Data reception and verification
[0048] Data reception: The construction information system receives real-time construction progress data from the construction project site through the network interface. These data are uploaded by on-site construction personnel or automated equipment, including the actual start and end time of each construction task, the amount of work completed, the input of construction personnel and equipment, etc. The construction information system is equipped with a high-performance network communication module to ensure that these data can be received stably and quickly even during data peak periods. For example, use a database query language (such as SQL) to extract real-time construction progress data from the construction project management database. Specific fields include: task ID, task name, planned start time, actual start time, planned end time, actual end time, amount of work, etc. Obtain historical construction progress data from historical project archives to ensure that the time span of the data is long enough to include various construction conditions and changes.
[0049] Data verification: The construction information system conducts strict verification on the received construction progress data. First, check whether the data format meets the predetermined standards, such as whether the timestamp is in a standard format and whether the engineering quantity is a numerical type. Secondly, verify the integrity of the data to ensure that there is no missing construction task information. Finally, by comparing historical data with actual data, verify the accuracy of the timestamp and exclude outliers caused by recording errors. For data that does not meet the requirements, the construction information system will record it and notify the data source to correct or supplement it. For example, use Python's Pandas library for data cleaning. For missing values, if the missing ratio is less than 5%, use the mean or median to fill it; if it is greater than 5%, consider deleting the feature or sample. Use timestamps to verify the temporal nature of the data to ensure that all records are arranged in chronological order and there are no duplicate timestamps.
[0050] Step 2: Data Preprocessing
[0051] Data cleaning: The architectural information system cleans the received construction progress data. First, statistical methods are used to identify and remove outliers, such as extremely early or late construction times due to recording errors. Second, for missing data, the architectural information system attempts to complete it through interpolation methods (such as linear interpolation, polynomial interpolation, etc.). If there are a lot of missing data, the architectural information system will also complete it based on pattern recognition of historical data, such as using historical data of the same construction stage to estimate the missing engineering quantities.
[0052] Data standardization: In order to facilitate subsequent analysis and processing, the architectural information system standardizes the cleaned construction progress data. First, all timestamps are converted to a unified time zone standard to ensure the consistency of time data. Secondly, all engineering quantities are converted to a unified unit of measurement to eliminate the errors caused by different units of measurement. Finally, for numerical features, the architectural information system normalizes or standardizes them so that they are distributed in the same numerical range to improve the training efficiency of subsequent machine learning models.
[0053] Step 3: Feature extraction and construction
[0054] Feature identification: In the feature extraction stage, the architectural information system uses machine learning algorithms (such as random forests, gradient boosting trees, etc.) to automatically identify key features related to the construction progress of the construction project. These features may include the scale of the project (such as building area, floor height, etc.), complexity (such as structural type, decoration level, etc.), experience level of the construction team (such as the average duration of historical construction projects, quality scores, etc.), weather conditions (such as temperature, humidity, wind speed, etc.), material supply (such as material arrival time, quantity, etc.), equipment failure rate (such as equipment maintenance records, failure frequency, etc.), etc.
[0055] To identify these features, the architectural information system first builds a feature recognition model based on historical construction progress data and domain knowledge. Then, through iterative training and optimization, the model gradually learns to identify the most relevant features of the construction progress from the raw data. During the training process, the architectural information system uses cross-validation to evaluate the generalization ability of the model and uses regularization techniques to prevent overfitting.
[0056] Feature construction: After identifying key features, the architectural information system further constructs feature vectors or feature matrices. These feature vectors will serve as the basis for subsequent intelligent analysis. When constructing feature vectors, the architectural information system considers the correlation, redundancy, and importance between features. For example, if two features are highly correlated (such as building area and floor height), the architectural information system may only retain one of them to avoid redundancy. At the same time, the architectural information system also uses feature selection techniques (such as principal component analysis, recursive feature elimination, etc.) to ensure that the constructed feature set is both comprehensive and representative.
[0057] Specifically, the architectural information system calculates the correlation coefficient between each feature and the target variable (i.e., construction progress) and sorts the features according to the size of the correlation coefficient. Then, the architectural information system selects features with higher correlation coefficients to construct feature vectors and removes features with lower correlation to reduce redundancy. In addition, the architectural information system uses feature selection technology to further screen features to improve the predictive performance of subsequent models.
[0058] One possible way is to implement step 3 by following the steps below:
[0059] 1. Feature identification and preliminary screening
[0060] Application of domain knowledge: Combined with the knowledge base of the construction domain, a preliminary list of features that may affect the construction progress is listed, including: project scale (building area, floor height), complexity (structural type, decoration level), experience level of the construction team (average construction period and quality score of historical construction projects), weather conditions (temperature, humidity, wind speed), material supply (material arrival time and quantity), equipment failure rate (equipment maintenance record, failure frequency), etc.
[0061] Feature extraction: Use Python’s Pandas library to extract preliminarily identified features from the preprocessed data. For example, the “task delay” feature can be extracted by calculating the difference between the actual start time and the planned start time.
[0062] Initial feature screening: Use statistical methods (such as chi-square test) to evaluate the correlation between features and construction progress. Set the significance level α to 0.05 and only retain features that are significantly correlated with construction progress.
[0063] 2. Machine learning model training and feature selection
[0064] Model selection: Gradient Boosting Tree (GBT) was selected as the machine learning model for feature selection because it performs well in handling classification and regression problems and can automatically handle interactions between features.
[0065] Model training: Use the GradientBoostingRegressor model in the Scikit-learn library for training. Set the learning rate (learning_rate) to 0.1, the maximum depth (max_depth) to 3, and the number of trees (n_estimators) to 100 to balance the complexity of the model and the risk of overfitting. Evaluate the model performance through K-fold cross validation (K=5) to ensure that the model has good generalization ability.
[0066] Feature selection: Use the feature importance evaluation function of the machine learning model to select the most important features. Set the threshold of feature importance to 0.05 and only keep features with importance higher than 0.05.
[0067] 3. In-depth analysis and construction of features
[0068] Feature relationship analysis: Use the correlation coefficient matrix to analyze the correlation between features. For highly correlated features (correlation coefficient greater than 0.8), consider retaining only one of them. Use principal component analysis (PCA) to identify redundancy between features. Select the first N principal components so that they can explain at least 95% of the data variance.
[0069] Feature construction: Based on the results of feature relationship analysis, construct new feature combinations. For example, multiply "project scale" and "complexity" to get a new feature "comprehensive difficulty". Generate new features using methods such as polynomial feature expansion. For example, perform a secondary expansion on the "task delay" feature to get the "task delay^2" feature.
[0070] Feature validation and optimization: Verify the improvement of prediction performance of newly constructed features through model training. Use cross-validation to evaluate the improvement of model accuracy by new features. Use feature selection techniques to further optimize the feature set. For example, use the recursive feature elimination (RFE) method to gradually remove the features that contribute the least to model performance.
[0071] 4. Construction of eigenvector or eigenmatrix
[0072] Feature vectorization: Convert the selected features into numeric vectors. For categorical features, use one-hot encoding or label encoding for conversion; for numeric features, directly retain their numeric representation.
[0073] Feature matrix construction: Combine multiple feature vectors into a feature matrix. Each row represents a sample (such as a construction task), and each column represents a feature (such as "project size", "task delay", etc.).
[0074] Optimization and storage of feature matrix: Use sparse matrix storage technology to optimize the storage of feature matrix. For the classification feature matrix after one-hot encoding, since most of its elements are 0, it can be stored in sparse matrix format to save space. The optimized feature matrix is stored on the server for subsequent intelligent analysis and decision support. It can be stored in a distributed file system (such as HDFS) or a database (such as HBase).
[0075] Step 4: Intelligent analysis and decision support
[0076] Model training and optimization: The architectural information system uses machine learning or deep learning algorithms (such as support vector machines, neural networks, etc.) to train construction progress prediction models. These models are trained based on the extracted feature vectors, with the goal of accurately predicting the future construction progress of the building project. During the training process, the architectural information system uses cross-validation to evaluate the generalization ability of the model and uses regularization techniques to prevent overfitting. At the same time, the architectural information system also improves the prediction performance of the model through iterative training and optimization, such as adjusting model parameters and optimizing loss functions.
[0077] Real-time analysis and early warning: The trained construction progress prediction model is applied to real-time data analysis. The architectural information system continuously receives new construction progress data and uses the model to make real-time predictions. By comparing the real-time prediction results with the planned progress, the architectural information system can detect construction progress delays and trigger early warning mechanisms in a timely manner. For example, if the prediction results show that a construction task will be delayed, the architectural information system will send an early warning message to the management personnel and provide possible explanations and recommended measures (such as adding construction personnel, adjusting the construction plan, etc.).
[0078] Results evaluation and feedback: In order to continuously improve the performance of the construction progress prediction model, the architectural information system evaluates and provides feedback on the prediction results. The evaluation includes indicators such as prediction accuracy, recall rate, and F1 score. The architectural information system compares these indicators with the actual construction progress data to evaluate the prediction performance of the model. At the same time, the architectural information system also collects user feedback and usage experience to further optimize system functions and user interfaces. Based on the evaluation results and user feedback, the architectural information system automatically adjusts model parameters or retrains the model to improve performance.
[0079] Result output: The architectural information system outputs the processed and analyzed construction progress forecast results in a structured form to relevant users or systems. The output results may include forecast reports, delay analysis reports, decision support recommendations, etc. In order to ensure the accuracy and readability of the results, the architectural information system strictly reviews and formats the output results. For example, the forecast report will list in detail the forecast start and end time of each construction task, the estimated amount of work, and other information, and present it in the form of tables or charts.
[0080] Visual display: In order to improve the user experience and understanding ability, the architectural information system also provides a visual display function. The construction progress forecast results and key indicators of the construction project are intuitively displayed in the form of charts, dashboards, etc. Users can customize the display content and layout as needed to better understand the project construction progress status and make decision analysis. For example, users can choose to view the progress forecast curve chart of different construction stages, or compare the difference between the actual progress and the planned progress. The visual display function enables users to understand the construction progress forecast results more intuitively and make more effective decisions based on these results.
[0081] Data encryption and transmission security: During the entire construction progress data processing process, the architectural information system strictly abides by the principles of data security and privacy protection. For sensitive data (such as personal information of construction personnel, specific location of equipment, etc.), the architectural information system uses encryption technology for storage and transmission to ensure data security. The encryption algorithm can choose mature encryption technologies such as AES and RSA to ensure that the data is not stolen or tampered with during transmission and storage. At the same time, the architectural information system also establishes secure and reliable communication protocols (such as HTTPS, SSL / TLS, etc.) with data sources and users to prevent data leakage and tampering.
[0082] Access control and authority management: The architectural information system establishes a complete access control and authority management mechanism. Only authenticated and authorized users can access relevant construction progress data and analysis results. The architectural information system assigns different access rights according to the user's role and responsibilities to ensure the compliance use and privacy protection of data. For example, ordinary users may only be able to view the overall construction progress forecast results and reports, while administrators can access more detailed raw data and model parameters and other information. The access control and authority management mechanism ensures that only authorized users can access sensitive data and analysis results through user authentication, role assignment, and authority setting, preventing data leakage and abuse.
[0083] In summary, the embodiment of the present invention uses the above detailed steps and implementation methods, and the architectural information system uses a machine learning algorithm to automatically identify key features related to the construction progress of the construction project, and constructs a feature vector or feature matrix, thereby realizing accurate prediction and intelligent analysis of the construction progress of the construction project. The implementation of this technical solution not only improves the accuracy and efficiency of the construction progress prediction, but also provides powerful decision-making support for construction project management. By comprehensively using technical means such as data preprocessing, machine learning, feature selection and optimization, combined with professional knowledge in the field of construction, the technical solution can effectively identify key factors affecting the construction progress, such as project scale, complexity, construction team experience level, etc., and make accurate predictions and analyses based on these factors. At the same time, the technical solution also pays attention to data security and privacy protection, encrypts and stores sensitive feature data and transmits it, and establishes a role-based access control mechanism to ensure the legal use and privacy protection of feature data. The implementation of this technical solution has brought significant benefits to construction project management, not only improving the controllability and predictability of the construction progress, but also providing project managers with more comprehensive and accurate construction progress information, which helps them make timely adjustments and optimization decisions, and further improves the management level and efficiency of construction projects. Therefore, this technical solution has broad application prospects and promotion value in the field of construction project management.
[0084] The second embodiment of the present invention corresponds to the first embodiment, and can be referred to Figure 3 This embodiment introduces a data processing method and device applied to a building information system, including the following components:
[0085] A collection unit configured to receive real-time construction progress data from a construction project site as a building information system;
[0086] A preprocessing unit configured to preprocess the construction progress data;
[0087] a feature extraction unit configured to automatically identify and extract key features related to the construction progress of the building project from the construction progress data using a machine learning algorithm, and construct a feature vector;
[0088] The prediction unit is configured to input the feature vector into a configured construction progress prediction model to predict the corresponding construction progress and perform visualization processing.
[0089] In this embodiment, the acquisition unit is further used for verification processing, which specifically includes:
[0090] Checking whether the format of the progress data meets the predetermined standard;
[0091] Verifying the integrity of the progress data;
[0092] By comparing historical data with the progress data, the accuracy of the timestamp is verified and outliers caused by recording errors are eliminated.
[0093] In this embodiment, the acquisition unit is further configured as follows:
[0094] The architectural information system records the data that does not meet the requirements during the verification process and notifies the data source to make corrections or supplements.
[0095] In this embodiment, the preprocessing unit is further configured as follows:
[0096] The construction information system cleans the received construction progress data;
[0097] The construction information system standardizes the cleaned construction progress data.
[0098] In this embodiment, the feature extraction unit is configured as follows:
[0099] Use random forest or gradient boosted tree algorithms to automatically identify key features related to the construction progress of a building project, including: project size, complexity, construction team experience level, weather conditions, material availability, and equipment failure rate.
[0100] In this embodiment, constructing the feature vector includes:
[0101] Calculate the correlation coefficient between each key feature and the construction progress, and sort the key features according to the magnitude of the correlation coefficient;
[0102] The architectural information system selects the key features whose correlation coefficient is greater than a preset value to construct a feature vector.
[0103] In this embodiment, the device is further configured as follows:
[0104] The construction information system uses machine learning or deep learning algorithms to train the construction progress prediction model.
[0105] A third embodiment of the present invention is an electronic device, such as Figure 4 As shown, it can be understood as a physical device, including a processor and a memory storing instructions executable by the processor. When the instructions are executed by the processor, the following operations are performed:
[0106] Step S1, the construction information system receives real-time construction progress data from the construction project site;
[0107] Step S2, preprocessing the construction progress data;
[0108] Step S3, using a machine learning algorithm to automatically identify and extract key features related to the construction progress of the building project in the construction progress data, and construct a feature vector;
[0109] Step S4, inputting the feature vector into the configured construction progress prediction model to predict the corresponding construction progress and perform visualization processing.
[0110] The fourth embodiment of the present invention, the process of the data processing method applied to the building information system of this embodiment is the same as that of the first, second or third embodiment, the difference is that in terms of engineering implementation, this embodiment can be implemented by means of software plus a necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the method of the present invention can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for a device to execute the method described in the embodiment of the present invention.
[0111] Through the description of the specific implementation methods, a deeper and more specific understanding of the technical means and effects adopted by the present invention to achieve the predetermined purpose should be obtained. However, the accompanying drawings are only for reference and illustration purposes and are not intended to limit the present invention.
Claims
1. A data processing method applied to a building information system, characterized in that: include: Step S1, the construction information system receives real-time construction progress data from the construction project site; Step S2, preprocessing the construction progress data; Step S3, using a machine learning algorithm to automatically identify and extract key features related to the construction progress of the building project in the construction progress data, and construct a feature vector; Step S4, inputting the feature vector into the configured construction progress prediction model to predict the corresponding construction progress and perform visualization processing.
2. The data processing method applied to the building information system according to claim 1, characterized in that: The step S1 also includes a verification process, which specifically includes: Checking whether the format of the progress data meets the predetermined standard; Verifying the integrity of said progress data; By comparing historical data with the progress data, the accuracy of the timestamp is verified and outliers caused by recording errors are eliminated.
3. The data processing method applied to the building information system according to claim 2 is characterized in that: The step S1 further comprises: The architectural information system records the data that does not meet the requirements during the verification process and notifies the data source to make corrections or supplements.
4. The data processing method applied to the building information system according to claim 1 is characterized in that: The step S2 specifically includes: The construction information system cleans the received construction progress data; The construction information system standardizes the cleaned construction progress data.
5. The data processing method applied to the building information system according to claim 1 is characterized in that: The method of automatically identifying and extracting key features related to the construction progress of the construction project from the construction progress data using a machine learning algorithm includes: Use random forest or gradient boosted tree algorithms to automatically identify key features related to the construction progress of a building project, including: project size, complexity, construction team experience level, weather conditions, material availability, and equipment failure rate.
6. The data processing method applied to the building information system according to claim 5, characterized in that: The constructing of the feature vector comprises: Calculate the correlation coefficient between each key feature and the construction progress, and sort the key features according to the magnitude of the correlation coefficient; The architectural information system selects the key features whose correlation coefficient is greater than a preset value to construct a feature vector.
7. The data processing method applied to the building information system according to claim 1, characterized in that: The method further comprises: The construction information system uses machine learning or deep learning algorithms to train the construction progress prediction model.
8. A data processing device applied to a building information system, characterized in that: include: A collection unit configured to receive real-time construction progress data from a construction project site as a building information system; A preprocessing unit configured to preprocess the construction progress data; a feature extraction unit configured to automatically identify and extract key features related to the construction progress of the building project from the construction progress data using a machine learning algorithm, and construct a feature vector; The prediction unit is configured to input the feature vector into a configured construction progress prediction model to predict the corresponding construction progress and perform visualization processing.
9. An electronic device, characterized in that: The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the data processing method applied to the building information system as described in any one of claims 1 to 7 are implemented.
10. A computer storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the data processing method applied to a building information system as claimed in any one of claims 1 to 7.