Intelligent building data management system and method based on cloud computing

Abstract

The invention discloses an intelligent building data management system and method based on cloud computing, and relates to the technical field of cloud computing. Building construction geometric errors are accurately calculated by constructing standard and actual construction BIM models and mapping coordinate information, multiple sub-parameters of environmental data are collected and analyzed at the same time, actual and standard environmental errors are quantified, and the building construction geometric errors are accurately calculated. The data accuracy and reliability are greatly improved through error analysis of the system; an error curve slope is calculated to obtain a run-out value, a machine learning prediction error is combined, data accuracy is judged by comparing a prediction value with the run-out value, wrong data updating is effectively avoided, and a data management process is optimized; the data adding trend is predicted by using the auxiliary cache region data timestamp in combination with the time sequence prediction model, and early warning is performed in time when the abnormal trend occurs, so that the monitoring and processing capability of the intelligent building data is comprehensively improved, and an efficient and reliable solution is provided for intelligent building data management.

Description

Technical Field

[0001] The present invention relates to the technical field of cloud computing, and in particular to a cloud computing-based intelligent building data management system and method. Background Art

[0002] Intelligent building data management methods and systems are mainly used to efficiently collect, store, process and analyze various types of data generated during the operation of intelligent buildings, such as equipment operation data, environmental monitoring data and geometric building data of constructed parts, so as to achieve optimized control of building equipment, effective management of energy and rational use of space.

[0003] The existing publication number is CN117875711A, which is a method and system for intelligent building management based on big data. The method and system include an interactive interface unit, which has an interactive interface for connecting a centralized data processing unit and a communication collaboration platform. The interface is responsible for coordinating data flow and communication between the two units. The system adopts a multi-layer data processing architecture, including a data collection layer, a data integration layer and a data analysis layer. It collects data from multiple construction projects in real time and ensures the accuracy of the data through data quality management technology. At the data integration layer, data from different projects are integrated into a unified database to ensure that information from different projects and data sources can be accurately associated and integrated. At the data analysis layer, the integrated data is analyzed in many aspects. The multi-layer data processing architecture ensures that data from multiple construction projects can be collected, integrated and analyzed in many aspects in real time, providing comprehensive data analysis capabilities for project management.

[0004] While the aforementioned patent provides a data management solution for construction projects, it lacks error analysis between engineering entity detection data and environmental data, potentially leading to insufficient data accuracy and reliability. This lack of error analysis, in turn, impacts the accuracy of intelligent building data management. Summary of the Invention

[0005] The purpose of the present invention is to provide a cloud computing-based intelligent building data management system and method to solve the problems raised in the prior art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a cloud computing-based intelligent building data management method, the intelligent building data management method comprising the following steps: Step S1: construct a BIM model of the target building based on the building information parameterized database, obtain engineering entity detection data of the constructed part of the target building, and analyze and calculate the geometric error of the target building construction with reference to the BIM model; Step S1-1: The building information parameterized database is represented as a database table storing geometric space data, structural material data, and equipment system data. The data is collected during the design phase of the architectural design software, and during the construction phase, the data of the target building is obtained and stored using measuring instruments and testing equipment. The BIM model constructed based on the building information parameterized database is used as the standard BIM model; Step S1-2: Use the target building project entity detection data obtained through measuring instruments and detection equipment as the data source for BIM model construction to build an actual construction BIM model; Step S1-3: Construct a geometric space coordinate system and determine the benchmark, map the coordinate information of the standard BIM model and the coordinate information of the actual construction BIM model into the geometric space coordinate system, and use the coordinate difference calculated from the coordinate information as the geometric error of the target building construction; Calculate the error between the actual construction BIM model and the standard BIM model for a single coordinate using the following formula: ; Where d represents the error value of a single coordinate between the actual construction BIM model and the standard BIM model; the single coordinate of the standard BIM model is (x1, y1, z1); x1 represents the horizontal coordinate; y1 represents the vertical coordinate; z1 represents the vertical coordinate; the single coordinate of the actual construction BIM model is (x2, y2, z2); x2 represents the horizontal coordinate; y2 represents the vertical coordinate; z2 represents the vertical coordinate; The geometric error between the actual construction BIM model and the standard BIM model is obtained based on the error of each coordinate. The calculation formula is as follows: ; Where D represents the geometric error between the actual construction BIM model and the standard BIM model; d i It is represented as the error value of the i-th coordinate; n is represented as the number of coordinates; By calculating the errors between the actual construction BIM model and the standard BIM model, the differences between the two in single coordinates and overall geometry are clearly quantified. By calculating the single coordinate error values separately and then synthesizing the geometric error values, it can accurately reflect the deviation between the actual construction situation of the target building and the design standards, providing scientific, accurate and intuitive data basis for subsequent construction adjustments and quality assessments, thereby improving the quality and efficiency of construction.

[0007] Step S2: collect actual environmental data of the constructed part of the target building, and analyze the error between the actual environmental data of the target building and the standard environmental data based on the actual environmental data combined with the BIM model; construct a geometric error curve based on multiple sets of geometric error data of the target building, and construct an environmental data error curve based on multiple sets of environmental data error data of the target building; When collecting actual environmental data, the operating status of sensors and other equipment is recorded simultaneously. If data is found during periods of equipment failure, it is directly marked and removed from the dataset. Secondly, statistical methods such as the 3σ principle (three standard deviations) are used to calculate the mean and standard deviation of the data. Data that deviates from the mean by more than three standard deviations is considered abnormal data. Combined with information such as construction logs and equipment maintenance records, it is determined whether the cause is non-construction factors such as equipment failure or sudden external interference, such as temporary construction machinery blocking light. If confirmed, the error data is removed.

[0008] Step S2-1: Collecting actual environmental data of the constructed portion of the target building to construct an environmental data set, wherein the environmental data includes multiple sub-parameters, including lighting data, ventilation data, and temperature and humidity data; and obtaining ideal environmental data of the target building according to the parameter settings of the standard BIM model; Step S2-2: obtaining a uniformity index by dividing the minimum value of a sub-parameter of the environmental data by the average value of the corresponding sub-parameter; obtaining a quantization parameter by dividing the sub-parameter data of the actual collected environmental data by the corresponding sub-parameter of the ideal environmental data; and obtaining an actual value of the quantized sub-parameter by weighted fusion of the uniformity index and the quantization parameter; The actual value of the parameter after quantization is calculated based on the sub-parameter data of the actual collected environmental data using the following formula: ; Where N is the actual value of the sub-parameter quantized by weighted fusion of the uniformity index and the quantization parameter; p is the sub-parameter correction weight coefficient of the actual collected environmental data; n new Indicates the sub-parameters of the actual collected environmental data; n BIM It is represented as the corresponding sub-parameter of the ideal environmental data; q is represented as the weight coefficient of the uniformity index; n min Indicates the historical minimum value collected for the sub-parameter; n avg Expressed as the mean of the subparameters.

[0009] Step S2-3: Use the sub-parameter of the ideal environment data to subtract the actual value of the corresponding sub-parameter after quantization to obtain the error of the sub-parameter, and calculate the error of each sub-parameter through weighted fusion to obtain the error between the actual environment data and the standard environment data; Step S2-4: construct the x-axis with the time data as the horizontal coordinate and the y-axis with the error value as the vertical coordinate in the chronological order of the data collection time; construct a geometric error curve based on multiple sets of geometric error data of the target building, and construct an environmental data error curve based on multiple sets of environmental data error data of the target building.

[0010] By collecting, processing and calculating multiple sub-parameters of actual environmental data, the environmental data is compared and analyzed with the ideal data in the standard BIM model, the actual value and error of each sub-parameter are quantified, and the trend of error change over time is intuitively presented in the form of a curve, which can accurately reflect the difference between the actual environment of the target building and the standard environment.

[0011] Step S3, calculating the slopes of two adjacent groups of data points in the geometric error curve, and selecting the maximum slope as the geometric error jitter value; calculating the slopes of two adjacent groups of data points in the environmental data error curve, and selecting the maximum slope as the environmental data error jitter value; Calculate the slopes of the geometric error curve and the environmental data error curve: use the error value of the current data point minus the error value of the previous data point to obtain the difference, and then divide it by the difference between the time data of the current data point and the time data of the previous data point to obtain the slope; select the maximum value slope in the geometric error curve as the geometric error jitter value by comparing the size values; select the maximum value slope in the environmental data error curve as the environmental data error jitter value by comparing the size values.

[0012] By calculating the slopes of adjacent data points of the geometric error curve and the environmental data error curve and selecting the maximum value as the jitter value, the maximum variation range of the target building construction geometric error and environmental data error in the time series can be captured, and the severity of the error change can be intuitively reflected. This provides key quantitative indicators for evaluating the stability of building construction and fluctuations in environmental data, and helps to promptly discover abnormal changes in construction and environment.

[0013] Step S4: creating an intelligent building data cache, wherein the intelligent building data cache includes a main cache and a secondary cache; storing the engineering entity detection data of the target building in the main cache, and predicting the geometric error curve and the environmental data error curve using a machine learning prediction method, and judging the accuracy of the engineering entity detection data of the target building by combining the geometric error jitter value and the environmental data error jitter value; updating the database of the engineering entity detection data in the intelligent building data cache that meets the accuracy judgment; and storing the engineering entity detection data that does not meet the accuracy judgment in the secondary cache; Step S4-1, setting the size of the intelligent building data cache and initializing parameters through a configuration file, wherein the intelligent building data cache includes a primary cache and a secondary cache; Step S4-2: Input the data in the geometric error curve into the machine learning prediction method to predict the error of the next data point, and record the obtained predicted value as the geometric error prediction value; simultaneously process the environmental data error curve, and predict the environmental error value of the next data point as the environmental data error prediction value; The calculation formula used by the machine learning prediction method is as follows: ; Where Gt represents the error prediction value at the prediction time t; m represents the window value of the moving average; Gi represents the actual error value at the time i; Step S4-3: Remove the first slope value judgment in the target building geometric error curve and the environmental data error curve. When the number of data points is not 1, start to select the maximum slope. According to the geometric error runout value and the environmental data error runout value, the accuracy of the engineering entity detection data of the target building is judged as follows: When the calculated slope of the geometric error prediction value and the geometric error value of the current data point exceeds the geometric error jump value, it is determined that there is an abnormal error in the accuracy of the engineering entity detection data of the target building, and the database update is not satisfied. The engineering entity detection data in the current intelligent building data cache is stored in the secondary cache; When the slope calculation result of the environmental data error prediction value and the environmental data error value of the current data point exceeds the environmental data error jump value, it is judged that there is an abnormal error in the accuracy of the engineering entity detection data of the target building, and the database update is not satisfied. The engineering entity detection data in the current intelligent building data cache area is stored in the secondary cache area; When the slope calculated based on the geometric error prediction value does not exceed the geometric error jump value, and at the same time, the slope of the environmental data error prediction value does not exceed the environmental data error jump value, it is judged that there is no large error in the accuracy of the engineering entity detection data of the target building, and the database update is satisfied.

[0014] Through computational processing, data can be effectively smoothed and noise filtered to reasonably predict future errors and reduce prediction deviations; the predicted value is compared with the current data point to calculate the slope and compare it with the jump value to judge the data accuracy, and the data is stored in the secondary cache to avoid erroneous updates to the database. If it does not exceed the limit, it will be updated to ensure the reliability and timeliness of the database; the main and secondary cache areas are set to optimize the data management process, the main storage of pending data ensures continuous processing, and the secondary storage of questionable data is convenient for manual verification, which improves the overall efficiency and quality of intelligent building data management, reduces construction risks and resource waste, and provides strong guarantees for building construction and operation.

[0015] Step S5: Analyze and warn the construction of the target building based on the timestamp of the engineering entity detection data added to the secondary buffer area.

[0016] The error anomaly rate of the engineering entity detection data of the target building is determined by the timestamp of the engineering entity detection data added to the secondary buffer, and the trend of data addition in the secondary buffer is predicted based on the timestamp of the engineering entity detection data by a time series prediction model. When the predicted trend is an upward trend, an early warning signal is issued, and the upward trend is represented by the time interval of engineering entity detection data added to the secondary buffer being less than the time interval of the last addition; the engineering entity detection data in the secondary buffer is sent to the management personnel for manual judgment. After the manual judgment is completed, the database is updated according to the manual judgment result, the timestamp in the secondary buffer is stored and recorded, and the secondary buffer is initialized and set; The time series forecasting model is calculated using the following formula: ; Where, P t It is represented by the error anomaly rate of the target construction engineering entity detection data at time t; a is represented by the constant term; n is represented by the lag order involved in the autoregressive part; Y i Expressed as autoregressive coefficient; P t-i It is expressed as the error anomaly rate of the target construction engineering entity detection data at time ti; m is expressed as the lag order involved in the moving average part; R j Expressed as moving average coefficient; F t-j It is represented by other factor values related to engineering entity detection data at time tj; By combining a time-series prediction model with the timestamps of engineering entity inspection data, the error anomaly rate is accurately calculated. Taking into account factors such as the lag order and coefficient of the autoregressive component and the lag order and coefficient of the moving average component, the trend of data additions in the secondary buffer can be accurately predicted. Once an upward trend is detected, an early warning signal is quickly issued, prompting management personnel to intervene and make manual judgments in a timely manner. Subsequently, based on the judgment results, the database is updated, the timestamp is stored, and the secondary buffer is initialized. This continuously optimizes the data management process, improves the monitoring and processing capabilities of engineering entity inspection data anomalies, and ensures data accuracy during construction.

[0017] Furthermore, a cloud computing-based intelligent building data management system includes a model error construction module, an environmental error analysis module, a runout value calculation module, a construction early warning processing module, and a data cache management module; The model error construction module is used to construct the target building BIM model and calculate the construction geometry error; the environmental error analysis module is used to collect actual environmental data and analyze the error with the standard data; the runout value calculation module is used to calculate the slope of adjacent data points in the error curve and select the maximum value; the construction early warning processing module is used to analyze and warn the construction according to the timestamp of the secondary buffer area data; the data cache management module is used to store the engineering entity detection data and determine its accuracy; The output end of the model error construction module is electrically connected to the input end of the environmental error analysis module; the output end of the environmental error analysis module is electrically connected to the input end of the jitter value calculation module; the output end of the jitter value calculation module is electrically connected to the input end of the construction early warning processing module; the output end of the construction early warning processing module is electrically connected to the input end of the data cache management module; The model error construction module includes a parameter library modeling unit and a coordinate error calculation unit; the parameter library modeling unit is used to collect building data to build a standard BIM model; the coordinate error calculation unit is used to map the standard and actual BIM model coordinates to calculate the geometric error; The environmental error analysis module includes an environmental data acquisition unit and an error curve generation unit; the environmental data acquisition unit is used to collect actual environmental data of the constructed part of the target building; the error curve generation unit is used to construct geometric and environmental error curves based on multiple sets of error data; The jitter value calculation module includes a geometric slope calculation unit and an environmental slope calculation unit; the geometric slope calculation unit is used to calculate the slope of adjacent data points of the geometric error curve and obtain the jitter value; the environmental slope calculation unit is used to calculate the slope of adjacent data points of the environmental data error curve and obtain the jitter value; The construction early warning processing module includes an abnormality rate analysis unit and an early warning handling unit; the abnormality rate analysis unit is used to determine the abnormality rate of engineering entity detection data errors based on timestamps; the early warning handling unit is used to predict data addition trends and perform early warning and manual handling operations; The data cache management module includes a data cache storage unit and an accuracy judgment unit; the data cache storage unit is used to store the target construction engineering entity detection data through the main cache area; the accuracy judgment unit is used to judge the data accuracy and process it in combination with the error jump value and the predicted value.

[0018] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention constructs a standard BIM model and an actual construction BIM model, mapping their coordinate information into a geometric space coordinate system to accurately calculate the geometric error of the target building construction. Simultaneously, multiple sub-parameters of actual environmental data are collected and analyzed to quantify the error between the actual environment and the standard environment. Compared to existing technologies, this invention effectively improves the accuracy and reliability of intelligent building data through systematic error analysis, providing scientific and accurate data support for subsequent construction adjustments and quality assessments.

[0019] 2. This method calculates the slopes of adjacent data points of the geometric error curve and the environmental data error curve to obtain the error jitter value, and then uses machine learning prediction methods to predict the error curve. The slope is calculated by comparing the predicted value with the current data point and then compared with the jitter value to determine the accuracy of the engineering entity inspection data. This method can promptly detect data anomalies, avoid updating the database with erroneous data, ensure the reliability and timeliness of data management, and optimize the data management process.

[0020] 3. This invention utilizes the timestamps of engineering entity inspection data in the secondary buffer, combined with a time series prediction model, to analyze and predict data addition trends. When an increasing trend in data error anomaly is predicted, a warning signal is promptly issued, and the data is sent to management personnel for manual evaluation. Based on the evaluation results, the database is updated, the timestamp is stored, and the secondary buffer is initialized. This process seamlessly integrates intelligent prediction with manual verification, continuously optimizes data management processes, and significantly enhances the ability to monitor and handle anomalies in engineering entity inspection data. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a flow chart of a cloud computing-based intelligent building data management method of the present invention; Figure 2 This is a structural diagram of a cloud computing-based intelligent building data management system of the present invention. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0023] Example 1: Figure 1 As shown, the present invention provides a technical solution, a cloud computing-based intelligent building data management method, the intelligent building data management method comprising the following steps: Step S1: construct a BIM model of the target building based on the building information parameterized database, obtain engineering entity detection data of the constructed part of the target building, and analyze and calculate the geometric error of the target building construction with reference to the BIM model; Step S1-1: The building information parameterized database is represented as a database table storing geometric space data, structural material data, and equipment system data. The data is collected during the design phase of the architectural design software, and during the construction phase, the data of the target building is obtained and stored using measuring instruments and testing equipment. The BIM model constructed based on the building information parameterized database is used as the standard BIM model; Step S1-2: Use the target building project entity detection data obtained through measuring instruments and detection equipment as the data source for BIM model construction to build an actual construction BIM model; Step S1-3: Construct a geometric space coordinate system and determine the benchmark, map the coordinate information of the standard BIM model and the coordinate information of the actual construction BIM model into the geometric space coordinate system, and use the coordinate difference calculated from the coordinate information as the geometric error of the target building construction.

[0024] In specific implementation, taking a commercial complex project as an example, architects use professional design software to collect data from the building information parametric database during the design phase, such as geometric spatial data such as building dimensions and structural beam and column dimensions. During the construction phase, measuring instruments such as total stations and laser scanners are used to obtain actual on-site data. The principle is to integrate data from the design and construction phases to construct a BIM model, which serves as a reference for construction standards. By comparing the model constructed with actual construction data, geometric errors are calculated, which forms the basis for subsequent data management. It is important to ensure that data collection is comprehensive and accurate, and measuring instruments must be regularly calibrated to ensure the accuracy and reliability of the BIM model.

[0025] Step S2: collect actual environmental data of the constructed part of the target building, and analyze the error between the actual environmental data of the target building and the standard environmental data based on the actual environmental data combined with the BIM model; construct a geometric error curve based on multiple sets of geometric error data of the target building, and construct an environmental data error curve based on multiple sets of environmental data error data of the target building; Step S2-1: Collecting actual environmental data of the constructed portion of the target building to construct an environmental data set, wherein the environmental data includes multiple sub-parameters, including lighting data, ventilation data, and temperature and humidity data; and obtaining ideal environmental data of the target building according to the parameter settings of the standard BIM model; Step S2-2: obtaining a uniformity index by dividing the minimum value of a sub-parameter of the environmental data by the average value of the corresponding sub-parameter; obtaining a quantization parameter by dividing the sub-parameter data of the actual collected environmental data by the corresponding sub-parameter of the ideal environmental data; and obtaining an actual value of the quantized sub-parameter by weighted fusion of the uniformity index and the quantization parameter; Step S2-3: Use the sub-parameter of the ideal environment data to subtract the actual value of the corresponding sub-parameter after quantization to obtain the error of the sub-parameter, and calculate the error of each sub-parameter through weighted fusion to obtain the error between the actual environment data and the standard environment data; Step S2-4: construct the x-axis with the time data as the horizontal coordinate and the y-axis with the error value as the vertical coordinate in the chronological order of the data collection time; construct a geometric error curve based on multiple sets of geometric error data of the target building, and construct an environmental data error curve based on multiple sets of environmental data error data of the target building.

[0026] During the actual environmental data collection phase, illuminance sensors, anemometers, temperature and humidity sensors, and other equipment are used to collect data on lighting, ventilation, temperature, and humidity in the constructed areas. The principle is to compare actual environmental data with the ideal environmental data set by the standard BIM model, using a weighted fusion of uniformity index and quantitative parameters to obtain the actual value. The error is then calculated to understand the difference between the actual building environment and the ideal state. It is important to note that sensors should be arranged appropriately to ensure that the data reflects the overall environmental conditions, and the collection frequency should be moderate to avoid data redundancy or insufficiency.

[0027] Step S3, calculating the slopes of two adjacent groups of data points in the geometric error curve, and selecting the maximum slope as the geometric error jitter value; calculating the slopes of two adjacent groups of data points in the environmental data error curve, and selecting the maximum slope as the environmental data error jitter value; Calculate the slopes of the geometric error curve and the environmental data error curve: use the error value of the current data point minus the error value of the previous data point to obtain the difference, and then divide it by the difference between the time data of the current data point and the time data of the previous data point to obtain the slope; select the maximum value slope in the geometric error curve as the geometric error jitter value by comparing the size values; select the maximum value slope in the environmental data error curve as the environmental data error jitter value by comparing the size values.

[0028] In practice, when calculating the slopes of the geometric error curve and the environmental data error curve, the rate of change of the error values of adjacent data points over time is analyzed, and the maximum slope value is selected as the jitter value to represent the severity of the error change. The principle is to use mathematical calculations to reflect data fluctuations and provide a basis for subsequent judgment of data accuracy. It is important to ensure the accuracy of the data sequence during the calculation process to avoid calculation errors caused by data disorganization.

[0029] Step S4: creating an intelligent building data cache, wherein the intelligent building data cache includes a main cache and a secondary cache; storing the engineering entity detection data of the target building in the main cache, and predicting the geometric error curve and the environmental data error curve using a machine learning prediction method, and judging the accuracy of the engineering entity detection data of the target building by combining the geometric error jitter value and the environmental data error jitter value; updating the database of the engineering entity detection data in the intelligent building data cache that meets the accuracy judgment; and storing the engineering entity detection data that does not meet the accuracy judgment in the secondary cache; Step S4-1, setting the size of the intelligent building data cache and initializing parameters through a configuration file, wherein the intelligent building data cache includes a primary cache and a secondary cache; Step S4-2: Input the data in the geometric error curve into the machine learning prediction method to predict the error of the next data point, and record the obtained predicted value as the geometric error prediction value; simultaneously process the environmental data error curve, and predict the environmental error value of the next data point as the environmental data error prediction value; Step S4-3: Remove the first slope value judgment in the target building geometric error curve and the environmental data error curve. When the number of data points is not 1, start to select the maximum slope. According to the geometric error runout value and the environmental data error runout value, the accuracy of the engineering entity detection data of the target building is judged as follows: When the calculated slope of the geometric error prediction value and the geometric error value of the current data point exceeds the geometric error jump value, it is determined that there is an abnormal error in the accuracy of the engineering entity detection data of the target building, and the database update is not satisfied. The engineering entity detection data in the current intelligent building data cache is stored in the secondary cache; When the slope calculation result of the environmental data error prediction value and the environmental data error value of the current data point exceeds the environmental data error jump value, it is judged that there is an abnormal error in the accuracy of the engineering entity detection data of the target building, and the database update is not satisfied. The engineering entity detection data in the current intelligent building data cache area is stored in the secondary cache area; When the slope calculated based on the geometric error prediction value does not exceed the geometric error jump value, and at the same time, the slope of the environmental data error prediction value does not exceed the environmental data error jump value, it is judged that there is no large error in the accuracy of the engineering entity detection data of the target building, and the database update is satisfied.

[0030] In practical implementation, the intelligent building data cache is set up to store data in the main cache, using machine learning prediction methods to predict error curves and assessing data accuracy based on error fluctuations. The principle is to use machine learning algorithms to identify patterns in data for prediction, combined with set thresholds to determine data reliability, enabling data screening and updating. It is important to note that the cache size should be appropriately set based on data volume to avoid data overflow and resource waste.

[0031] Step S5: Analyze and warn the construction of the target building based on the timestamp of the engineering entity detection data added to the secondary buffer area.

[0032] The error anomaly rate of the engineering entity detection data of the target building is judged by the timestamp of the engineering entity detection data added to the secondary buffer, and the trend of data added to the secondary buffer is predicted according to the timestamp of the engineering entity detection data through the time series prediction model. When the slope K of the predicted trend is greater than 1, an early warning signal is issued; the engineering entity detection data in the secondary buffer is sent to the management personnel for manual judgment. After the manual judgment is completed, the database is updated according to the manual judgment result, the timestamp in the secondary buffer is stored and recorded, and the secondary buffer is initialized.

[0033] In practice, this system analyzes and issues warnings based on the timestamps of engineering entity inspection data in the secondary cache. By calculating the error anomaly rate and predicting trends in the data, warnings are issued when the trend increases. This system utilizes time series analysis combined with manual judgment to perform secondary data processing to ensure database quality.

[0034] Example 2, as Figure 2 As shown, the present invention provides an intelligent building data management system based on cloud computing, which includes a model error construction module, an environmental error analysis module, a runout value calculation module, a construction early warning processing module and a data cache management module; The model error construction module is used to construct the target building BIM model and calculate the construction geometry error; the environmental error analysis module is used to collect actual environmental data and analyze the error with the standard data; the runout value calculation module is used to calculate the slope of adjacent data points in the error curve and select the maximum value; the construction early warning processing module is used to analyze and warn the construction according to the timestamp of the secondary buffer area data; the data cache management module is used to store the engineering entity detection data and determine its accuracy; The output end of the model error construction module is electrically connected to the input end of the environmental error analysis module; the output end of the environmental error analysis module is electrically connected to the input end of the jitter value calculation module; the output end of the jitter value calculation module is electrically connected to the input end of the construction early warning processing module; the output end of the construction early warning processing module is electrically connected to the input end of the data cache management module; The model error construction module includes a parameter library modeling unit and a coordinate error calculation unit; the parameter library modeling unit is used to collect building data to build a standard BIM model; the coordinate error calculation unit is used to map the standard and actual BIM model coordinates to calculate the geometric error; The environmental error analysis module includes an environmental data acquisition unit and an error curve generation unit; the environmental data acquisition unit is used to collect actual environmental data of the constructed part of the target building; the error curve generation unit is used to construct geometric and environmental error curves based on multiple sets of error data; The jitter value calculation module includes a geometric slope calculation unit and an environmental slope calculation unit; the geometric slope calculation unit is used to calculate the slope of adjacent data points of the geometric error curve and obtain the jitter value; the environmental slope calculation unit is used to calculate the slope of adjacent data points of the environmental data error curve and obtain the jitter value; The construction early warning processing module includes an abnormality rate analysis unit and an early warning handling unit; the abnormality rate analysis unit is used to determine the abnormality rate of engineering entity detection data errors based on timestamps; the early warning handling unit is used to predict data addition trends and perform early warning and manual handling operations; The data cache management module includes a data cache storage unit and an accuracy judgment unit; the data cache storage unit is used to store the target construction engineering entity detection data through the main cache area; the accuracy judgment unit is used to judge the data accuracy and process it in combination with the error jump value and the predicted value.

[0035] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A cloud computing-based intelligent building data management method, characterized by: The intelligent building data management method comprises the following steps: Step S1: construct a BIM model of the target building based on the building information parameterized database, obtain engineering entity detection data of the constructed part of the target building, and analyze and calculate the geometric error of the target building construction with reference to the BIM model; Step S2: collect actual environmental data of the constructed part of the target building, and analyze the error between the actual environmental data of the target building and the standard environmental data based on the actual environmental data combined with the BIM model; construct a geometric error curve based on multiple sets of geometric error data of the target building, and construct an environmental data error curve based on multiple sets of environmental data error data of the target building; Step S3, calculating the slopes of two adjacent groups of data points in the geometric error curve, and selecting the maximum slope as the geometric error jitter value; calculating the slopes of two adjacent groups of data points in the environmental data error curve, and selecting the maximum slope as the environmental data error jitter value; Step S4: creating an intelligent building data cache, wherein the intelligent building data cache includes a main cache and a secondary cache; storing the engineering entity detection data of the target building in the main cache, and predicting the geometric error curve and the environmental data error curve using a machine learning prediction method, and judging the accuracy of the engineering entity detection data of the target building by combining the geometric error jitter value and the environmental data error jitter value; updating the database of the engineering entity detection data in the intelligent building data cache that meets the accuracy judgment; and storing the engineering entity detection data that does not meet the accuracy judgment in the secondary cache; Step S5: Analyze and warn the construction of the target building based on the timestamp of the engineering entity detection data added to the secondary buffer area.

2. The cloud computing-based intelligent building data management method according to claim 1, characterized in that: The specific steps of step S1 are as follows: Step S1-1: The building information parameterized database is represented as a database table storing geometric space data, structural material data, and equipment system data. The data is collected during the design phase of the architectural design software, and during the construction phase, the data of the target building is obtained and stored using measuring instruments and testing equipment. The BIM model constructed based on the building information parameterized database is used as the standard BIM model; Step S1-2: Use the target building project entity detection data obtained through measuring instruments and detection equipment as the data source for BIM model construction to build an actual construction BIM model; Step S1-3: Construct a geometric space coordinate system and determine the benchmark, map the coordinate information of the standard BIM model and the coordinate information of the actual construction BIM model into the geometric space coordinate system, and use the coordinate difference calculated from the coordinate information as the geometric error of the target building construction.

3. The cloud computing-based intelligent building data management method according to claim 2, characterized in that: The specific steps of step S2 are as follows: Step S2-1: Collecting actual environmental data of the constructed portion of the target building to construct an environmental data set, wherein the environmental data includes multiple sub-parameters, including lighting data, ventilation data, and temperature and humidity data; and obtaining ideal environmental data of the target building according to the parameter settings of the standard BIM model; Step S2-2: obtain a uniformity index by dividing the minimum value of the sub-parameter of the environmental data by the average value of the corresponding sub-parameter; obtain a quantization parameter by dividing the sub-parameter data of the actual collected environmental data by the corresponding sub-parameter of the ideal environmental data; and obtain the actual value of the quantized sub-parameter by weighted fusion of the uniformity index and the quantization parameter.

4. The cloud computing-based intelligent building data management method according to claim 3, characterized in that: In step S2, it also includes: Step S2-3: Use the sub-parameter of the ideal environment data to subtract the actual value of the corresponding sub-parameter after quantization to obtain the error of the sub-parameter, and calculate the error of each sub-parameter through weighted fusion to obtain the error between the actual environment data and the standard environment data; Step S2-4: construct the x-axis with the time data as the horizontal coordinate and the y-axis with the error value as the vertical coordinate in the chronological order of the data collection time; construct a geometric error curve based on multiple sets of geometric error data of the target building, and construct an environmental data error curve based on multiple sets of environmental data error data of the target building.

5. The cloud computing-based intelligent building data management method according to claim 4, characterized in that: In step S3, the slopes of the geometric error curve and the environmental data error curve are calculated: the difference obtained by subtracting the error value of the previous data point from the error value of the current data point is divided by the difference between the time data of the current data point and the time data of the previous data point to obtain the slope; the maximum value slope in the geometric error curve is selected as the geometric error jitter value by comparing the size values; the maximum value slope in the environmental data error curve is selected as the environmental data error jitter value by comparing the size values.

6. The cloud computing-based intelligent building data management method according to claim 5, characterized in that: The specific steps of step S4 are as follows: Step S4-1, setting the size of the intelligent building data cache area and initializing parameters through a configuration file, wherein the intelligent building data cache area includes a primary cache area and a secondary cache area; Step S4-2: input the data in the geometric error curve into the machine learning prediction method to perform error prediction for the next data point, and the obtained prediction value is recorded as the geometric error prediction value; The environmental data error curve is processed simultaneously, and the environmental error value of the next data point is predicted and recorded as the environmental data error prediction value; Step S4-3: Remove the first slope value judgment in the target building geometric error curve and the environmental data error curve. When the number of data points is not 1, start to select the maximum slope. According to the geometric error runout value and the environmental data error runout value, the accuracy of the engineering entity detection data of the target building is judged as follows: When the calculated slope of the geometric error prediction value and the geometric error value of the current data point exceeds the geometric error jump value, it is determined that there is an abnormal error in the accuracy of the engineering entity detection data of the target building, and the database update is not satisfied. The engineering entity detection data in the current intelligent building data cache is stored in the secondary cache; When the slope calculation result of the environmental data error prediction value and the environmental data error value of the current data point exceeds the environmental data error jump value, it is judged that there is an abnormal error in the accuracy of the engineering entity detection data of the target building, and the database update is not satisfied. The engineering entity detection data in the current intelligent building data cache area is stored in the secondary cache area; When the slope calculated based on the geometric error prediction value does not exceed the geometric error jump value, and at the same time, the slope of the environmental data error prediction value does not exceed the environmental data error jump value, it is judged that there is no large error in the accuracy of the engineering entity detection data of the target building, and the database update is satisfied.

7. The cloud computing-based intelligent building data management method according to claim 6, characterized in that: In step S5, the error anomaly rate of the engineering entity detection data of the target building is judged by the timestamp of the engineering entity detection data added to the secondary buffer, and the trend of data addition in the secondary buffer is predicted according to the timestamp of the engineering entity detection data through the time series prediction model. When the predicted trend is an upward trend, an early warning signal is issued, and the upward trend is represented by the time interval of the engineering entity detection data added in the secondary buffer being less than the time interval of the last addition; the engineering entity detection data in the secondary buffer is sent to the management personnel for manual judgment. After the manual judgment is completed, the database is updated according to the manual judgment result, the timestamp in the secondary buffer is stored and recorded, and the secondary buffer is initialized.

8. A cloud computing-based intelligent building data management system, applied to the cloud computing-based intelligent building data management method according to any one of claims 1 to 7, characterized in that: The intelligent building data management system includes a model error construction module, an environmental error analysis module, a runout value calculation module, a construction early warning processing module and a data cache management module; The model error construction module is used to construct the target building BIM model and calculate the construction geometry error; the environmental error analysis module is used to collect actual environmental data and analyze the error with the standard data; the runout value calculation module is used to calculate the slope of adjacent data points in the error curve and select the maximum value; the construction early warning processing module is used to analyze and warn the construction according to the timestamp of the secondary buffer area data; the data cache management module is used to store the engineering entity detection data and determine its accuracy; The output end of the model error construction module is electrically connected to the input end of the environmental error analysis module; the output end of the environmental error analysis module is electrically connected to the input end of the jitter value calculation module; the output end of the jitter value calculation module is electrically connected to the input end of the construction early warning processing module; the output end of the construction early warning processing module is electrically connected to the input end of the data cache management module.

9. The cloud computing-based intelligent building data management system according to claim 8, characterized in that: The model error construction module includes a parameter library modeling unit and a coordinate error calculation unit; the parameter library modeling unit is used to collect building data to build a standard BIM model; the coordinate error calculation unit is used to map the standard and actual BIM model coordinates to calculate the geometric error; The environmental error analysis module includes an environmental data acquisition unit and an error curve generation unit; The environmental data acquisition unit is used to collect actual environmental data of the constructed part of the target building; the error curve generation unit is used to construct geometric and environmental error curves based on multiple sets of error data; The jitter value calculation module includes a geometric slope calculation unit and an environmental slope calculation unit; the geometric slope calculation unit is used to calculate the slope of adjacent data points of the geometric error curve and obtain the jitter value; the environmental slope calculation unit is used to calculate the slope of adjacent data points of the environmental data error curve and obtain the jitter value.

10. The cloud computing-based intelligent building data management system according to claim 8, characterized in that: The construction early warning processing module includes an abnormality rate analysis unit and an early warning handling unit; the abnormality rate analysis unit is used to determine the abnormality rate of engineering entity detection data errors based on timestamps; the early warning handling unit is used to predict data addition trends and perform early warning and manual handling operations; The data cache management module includes a data cache storage unit and an accuracy judgment unit; the data cache storage unit is used to store the target construction engineering entity detection data through the main cache area; the accuracy judgment unit is used to judge the data accuracy and process it in combination with the error jump value and the predicted value.

Images