Engineering monitoring management method, system and equipment based on big data and storage medium

Abstract

The invention relates to the technical field of engineering management, and provides an engineering monitoring management method and system based on big data, and the method comprises the steps: carrying out the dividing and screening of a large amount of construction site historical data and historical risk data, and obtaining data groups corresponding to various historical risk events, identifying feature data and feature thresholds corresponding to the risk events by analyzing change features of the data, and establishing a risk event probability model corresponding to each risk event type according to each data value in the data set; according to the method, data of a project is monitored in real time, meanwhile, the data are input into a digital twin to monitor feature data, probability calculation is conducted through a model corresponding to the feature data when a data value exceeds a feature threshold value, project management and control are conducted according to the risk event occurrence probability, the management cost is reduced, the safety in the project construction process is improved, and the project construction efficiency is improved. And the overall monitoring management efficiency in the engineering process is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of project management, and in particular, to a project monitoring and management method, system, device, and storage medium based on big data. Background Art

[0002] In construction projects, it is necessary to prevent various risk events. Generally, only cameras are used to monitor the construction site in real time, but this requires managers to pay attention to the monitoring screen for a long time, or other sensors are used to monitor the data in the construction site. However, the types of data that need to be monitored in construction projects are numerous and the data volume is large, making it difficult to effectively process the data and identify the possible risk events that may be triggered, resulting in difficult project monitoring and management and low efficiency at present. Summary of the Invention

[0003] The present invention provides a project monitoring and management method based on big data, which is used to solve the problems of difficult project monitoring and management and low efficiency in the prior art.

[0004] The first aspect of the present invention provides a project monitoring and management method based on big data, including:

[0005] Obtain the historical data of the construction site and the historical risk event data, divide the historical data of the construction site according to the historical risk event time to obtain multiple risk-related construction site data groups; establish a digital twin of the construction site, locate it in the digital twin according to the source of the historical data of the construction site, and screen the historical data of the construction site in the risk-related construction site data groups based on the occurrence location of the historical risk event data;

[0006] Analyze the change characteristics of each data in the risk-related construction site data groups, identify the characteristic data that has an associated relationship with the occurrence of risk events, and obtain the characteristic thresholds corresponding to each characteristic data, and establish probability models for various types of risk events;

[0007] Obtain the real-time monitoring data of the project and input it into the digital twin of the construction site, monitor the characteristic data values. When there is characteristic data exceeding the corresponding characteristic threshold, calculate the occurrence probability of the current project risk event with the probability model of the risk event corresponding to the characteristic data, and then give a prompt and warning in the digital twin of the construction site.

[0008] Optionally, after establishing the probability models for various types of risk events, it specifically further includes:

[0009] The probability model of the risk event is specifically:

[0010] ;

[0011] Wherein, is the occurrence probability of the a-th type of risk event, is the number of data types in the risk-related construction site data group, is the influence coefficient of the nth type of construction site data on the occurrence of risk events, is the current data value of the nth type of construction site data, is the standard data value of the nth type of construction site data.

[0012] Optionally, the positioning in the digital twin is based on the source of the construction site historical data, and the construction site historical data in the risk-associated construction site data group is screened based on the occurrence location of the historical risk event data. Specifically:

[0013] A spatial coordinate system is established in the construction site digital twin. The first spatial coordinates of the sensors monitoring the construction site historical data in the construction site digital twin are identified, and the second spatial coordinates of the occurrence location of the historical risk event in the construction site digital twin are identified. The distance between the first spatial coordinates and the second spatial coordinates is calculated, and the construction site historical data corresponding to the first spatial coordinates with a distance greater than the preset distance threshold is excluded from the risk-associated construction site data group.

[0014] The second aspect of the present application provides a project monitoring and management system based on big data, including:

[0015] A big data processing module for obtaining construction site historical data and historical risk event data, dividing the construction site historical data according to the historical risk event time to obtain multiple risk-associated construction site data groups; establishing a construction site digital twin, positioning in the digital twin according to the source of the construction site historical data, and screening the construction site historical data in the risk-associated construction site data group based on the occurrence location of the historical risk event data;

[0016] A model construction module for analyzing the change characteristics of each data in the risk-associated construction site data group, identifying the characteristic data associated with the occurrence of risk events, obtaining the characteristic thresholds corresponding to each characteristic data, and establishing probability models for various types of risk events;

[0017] A monitoring and management module for obtaining project real-time monitoring data and inputting it into the construction site digital twin, monitoring the characteristic data values, and when there is characteristic data exceeding the corresponding characteristic threshold, calculating the occurrence probability of the current project risk event with the probability model of the risk event corresponding to the characteristic data, and giving a prompt and warning in the construction site digital twin.

[0018] Optionally, in the model construction module, after establishing the probability models for various types of risk events, it specifically further includes:

[0019] The probability model of the risk event is specifically:

[0020] ;

[0021] Among them, is the occurrence probability of the a - type risk event, is the number of data types in the risk - associated construction site data group, is the influence coefficient of the n - type construction site data on the occurrence of the risk event, is the current data value of the n - type construction site data, is the standard data value of the n - type construction site data.

[0022] Optionally, in the big data processing module, locate in the digital twin according to the source of the construction site historical data, and screen the construction site historical data in the risk - associated construction site data group based on the occurrence location of the historical risk event data. Specifically:

[0023] Establish a spatial coordinate system in the construction site digital twin, identify the first spatial coordinates of the sensors monitoring the construction site historical data in the construction site digital twin, identify the second spatial coordinates of the historical risk event occurrence location in the construction site digital twin, calculate the distance between the first spatial coordinates and the second spatial coordinates, and remove the construction site historical data corresponding to the first spatial coordinates with a distance greater than the preset distance threshold from the risk - associated construction site data group.

[0024] The third aspect of this application provides a device for an engineering monitoring and management method based on big data. The device includes a processor and a memory:

[0025] The memory is used to store program codes and transmit the program codes to the processor;

[0026] The processor is used to execute the engineering monitoring and management method based on big data according to any one of the instructions in the program codes in the first aspect of the present invention.

[0027] The fourth aspect of this application provides a computer - readable storage medium. The computer - readable storage medium is used to store program codes, and the program codes are used to execute the engineering monitoring and management method based on big data according to any one of the first aspect of the present invention.

[0028] From the above technical solutions, it can be seen that the present invention has the following advantages: classifying and screening a large amount of construction site historical data and historical risk data to obtain data groups corresponding to various historical risk events, analyzing the change characteristics of the data to identify characteristic data and characteristic thresholds corresponding to the risk events, and establishing a risk event probability model corresponding to each risk event type according to each data value in the data group; while real - time monitoring the data of the project, inputting the data into the digital twin to monitor the characteristic data, when the data value exceeds the characteristic threshold, calculating the probability with the model corresponding to the characteristic data, and controlling the project according to the occurrence probability of the risk event, reducing the management cost, increasing the safety during the engineering construction process, and improving the overall monitoring and management efficiency during the engineering process. Description of the Drawings

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0030] Figure 1 It is a flowchart of an engineering monitoring and management method based on big data;

[0031] Figure 2 It is a structural diagram of an engineering monitoring and management system based on big data. Detailed Implementation Manner

[0032] In order to make the invention objectives, features, and advantages of the present invention more obvious and understandable, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0033] The present invention provides an engineering monitoring and management method based on big data, which is used to solve the problem of difficult and inefficient engineering monitoring and management in the prior art.

[0034] Please refer to Figure 1 , Figure 1 It is the first flowchart of an engineering monitoring and management method based on big data provided by the embodiment of the present invention.

[0035] S100, obtain the historical data of the construction site and the historical risk event data, divide the historical data of the construction site according to the historical risk event time to obtain multiple risk-related construction site data groups; establish a digital twin of the construction site, locate it in the digital twin according to the source of the historical data of the construction site, and screen the historical data of the construction site in the risk-related construction site data groups based on the occurrence location of the historical risk event data;

[0036] It should be noted that a large number of sensors will be set up in the construction site to monitor and obtain multi-source heterogeneous information data. For example, cameras are set up to take pictures of the construction site to obtain image data, sensors or induction probes are set up on protective facilities to obtain usage data to determine the usage situation and status of workers' protective equipment, weather data of the current area is obtained through networking to get data such as wind direction, and various progress data will be recorded during the construction process to know the construction status of each area of the building; various types of event data will also be recorded and monitored during the project process. Among them, risk events such as falling of high-altitude objects, falling of personnel, injury of personnel, and collision of mechanical equipment will record the time and location of occurrence. The location of occurrence of such risk events is generally recorded as the building area; after obtaining the historical risk event data of each item, a time period is divided according to the occurrence time point of the historical risk event. For example, the time period one hour before the event occurrence time point is used as the associated time period, and the historical construction site data within this time period is divided and regarded as the data related to this risk event. Each historical risk event can obtain a risk-associated construction site data group; the risk-associated construction site data group can be classified according to the specific type of risk event. Comparing the data groups of the same type with each other can further improve the accuracy of subsequent analysis;

[0037] In the construction site, a digital twin of the construction site can be established based on the building to be constructed and the real-time building state according to the 3D model, and the digital twin of the construction site can be updated in real time through the real-time data obtained by the construction site sensors; when a risk event occurs, it will be divided in the digital twin of the construction site according to the location recorded in the risk event to determine the twin body area where the occurrence location is located, and then identify and screen out which historical construction site data is monitored and obtained in this area. For example, when an object falling event occurs in area a on a certain floor A, the data of floors B and C and areas bc on floor A will be excluded from the corresponding risk-associated construction site data group. The change of the historical construction site data in these areas has no impact on the occurrence of the risk event, and because the source of each historical construction site data is each sensor, the historical construction site data collected by it can be screened according to the installation position of the sensor. Further, a spatial coordinate system can be constructed in the digital twin of the construction site to obtain the first coordinates of the installation of each sensor, and a corresponding second coordinate is set for the risk event. After calculating the Euclidean distance between the first coordinate and the second coordinate, the historical construction site data obtained by the sensor corresponding to the first coordinate greater than the threshold distance is excluded; and some data that is necessarily not related can also be screened out. For example, data such as personnel safety rope sensors and construction progress can be excluded from the risk-associated construction site data group in the case of mechanical equipment collision.

[0038] S200. Analyze the change characteristics of each data in the risk-associated construction site data group, identify the characteristic data that has an associated relationship with the occurrence of the risk event, and obtain the characteristic threshold corresponding to each characteristic data to establish probability models for various types of risk events;

[0039] It should be noted that after the data screening in the foregoing steps, the remaining data in the risk-associated construction site data group have certain inducing factors for the occurrence of risk events or have an impact on increasing the occurrence probability. Among the multiple groups of risk-associated construction site data groups corresponding to the same type of risk events, the historical data of each associated construction site may vary. For example, in multiple object falling risk events, the data associated with this type of risk event can be identified according to the similarity of the historical data of each construction site. For example, in these object falling risk events, the recorded weather data all have a certain degree of wind force level, the construction progress in the area where the event occurs is in the state of exterior wall laying, or there are a large number of people activities at the event location. By comparing the average value of the data in the data group with other data groups, the proportion of the difference in the average value of the data is greater than a certain set proportion threshold, and then the data change characteristics are identified. The data significantly associated with the object falling risk event is used as characteristic data, and the average value of the characteristic data in each risk-associated construction site data group is taken and empirically corrected to obtain a threshold. Since the data divided in the data group is the data of a time period, the characteristic data may change. Therefore, the averaging calculation method can also be used. The data of some construction sites can be set corresponding parameter values based on the status and stage for subsequent calculation;

[0040] The characteristic data of different types of risk events are different, and the significant correlation degrees of the characteristic data are also different. However, in the data groups of the same type of risk events, the same characteristic data will vary within a certain range. For example, in multiple object falling risk events, the weather wind force data, the construction progress in the area where the event occurs, and the personnel activity data corresponding to the construction site data groups are different. In a certain risk event, the number of personnel activities is small but the weather wind force is large, while in a certain risk event, the wind force is small, the number of personnel activities is also small, but the regional construction is in a slower progress. Moreover, there are also differences in the construction site data of other various non-characteristic data. Although it is not significantly associated with the risk, it also contains a certain risk impact. Therefore, we can establish a risk event probability model to reflect the comprehensive impact of all types of data on a certain type of risk event in the construction site.

[0041] S300. Obtain the real-time monitoring data of the project and input it into the construction site digital twin. Monitor the characteristic data value. When there is characteristic data exceeding the corresponding characteristic threshold, calculate the occurrence probability of the current project risk event with the risk event probability model corresponding to the characteristic data, and then give a prompt and warning in the construction site digital twin.

[0042] It should be noted that in engineering construction sites, sensors are set up to monitor various data in real time to ensure construction safety, efficiency, quality and compliance. The digital twin of the construction site established through the foregoing steps can reflect these monitored real-time engineering data in the digital twin for managers to view and control. While the data at various locations in the digital twin of the construction site changes in real time, it is not necessary to judge at any time using the risk event probability model. Instead, only the abnormal single-item data is monitored. When a certain piece of data is characteristic data and the monitored real-time data value reaches the characteristic threshold, the risk event probability model corresponding to the characteristic data will be used for identification and judgment, calculate the occurrence probability of the risk event, and can display different colors on the digital twin of the construction site according to the probability level. The color of the risk event probability occurrence area is displayed as green for low probability, yellow for medium probability, and red for high probability. The digital twin can be connected to the network for real-time alarm, and the monitored data and predicted probability data are stored in the cloud, automatically generating a risk probability report and pushing it to the managers.

[0043] In this embodiment, by dividing and screening a large amount of construction site historical data and historical risk data, data groups corresponding to various historical risk events are obtained, and through the analysis of the change characteristics of the data, the characteristic data and characteristic thresholds corresponding to the risk events are identified, and the risk event probability models corresponding to each risk event type are established according to each data value in the data group. While monitoring the engineering data in real time, the data is input into the digital twin to monitor the characteristic data. When the data value exceeds the characteristic threshold, the probability is calculated using the model corresponding to the characteristic data, and the engineering is controlled according to the occurrence probability of the risk event, reducing the management cost, increasing the safety during the engineering construction process, and improving the overall monitoring and management efficiency during the engineering process.

[0044] The above is the detailed description of the first embodiment of a method for engineering monitoring and management based on big data provided by this application. The following is the detailed description of the second embodiment of a method for engineering monitoring and management based on big data provided by this application.

[0045] In this embodiment, a method for engineering monitoring and management based on big data is further provided. After establishing the risk event probability models of various types in the foregoing step S200, it specifically further includes:

[0046] The risk event probability model is specifically:

[0047] ;

[0048] Among them, is the occurrence probability of the a-th type of risk event, is the number of data types in the risk-associated construction site data group, is the influence coefficient of the nth type of construction site data on the occurrence of risk events, is the current data value of the nth type of construction site data, is the standard data value of the nth type of construction site data;

[0049] It should be noted that the risk event probability model reflects the comprehensive influence of all types of data on a certain type of risk event. For example, for the probability of a falling risk event, workers not wearing safety protection equipment, the area where the workers are located being in an earlier progress with unenclosed walls, and strong wind in the weather will all increase the risk event probability. However, the weights of the triggering probabilities of different types of data are different. Therefore, the influence coefficients in the model are obtained by substituting the big data corresponding to different occurrences of the same type of risk event into the model. The sum of these coefficients is 1 to ensure that the event probability is less than 100%. The standard data value of the construction site data can be the historical maximum value of all such risk events. That is, when the current data value of a certain construction site reaches the historical maximum value, it is considered that the induced influence of this data on the risk event is the greatest.

[0050] Further, in the aforementioned step S100, the positioning in the digital twin based on the construction site historical data source and the screening of the construction site historical data in the risk-associated construction site data group based on the occurrence location of the historical risk event data are specifically as follows: Establish a spatial coordinate system in the construction site digital twin, identify the first spatial coordinates of the sensors monitoring each construction site historical data in the construction site digital twin, identify the second spatial coordinates of the historical risk event occurrence location in the construction site digital twin, calculate the distance between the first spatial coordinates and the second spatial coordinates, and remove the construction site historical data corresponding to the first spatial coordinates with a distance greater than the preset distance threshold from the risk-associated construction site data group;

[0051] It should be noted that the construction site of a construction project has a large space, and generally a large number of sensors need to be set up to perform complete data monitoring on the construction site. In the aforementioned steps, only the time range of the construction site historical data is screened after dividing the construction site historical data based on events. However, all the data that can be detected on the construction site are included in the risk-associated construction site data group. In fact, in terms of space, the state change of the location where many data are monitored will not affect the occurrence location of the risk event. Therefore, the construction site historical data can be removed according to the spatial distance to reduce the processing volume of subsequent steps and improve the processing efficiency; the distance threshold is set according to the type of risk event and the type of construction site historical data. The greater the influence of the construction site historical data on the risk event, or the farther the range it can affect, the greater the distance threshold, and it can be adjusted according to the empirical value.

[0052] The above is a detailed description of a big data-based engineering monitoring and management method provided in the first aspect of this application. Next is a detailed description of an embodiment of a big data-based engineering monitoring and management system provided in the second aspect of this application.

[0053] Please refer to Figure 2 , Figure 2 which is a structure diagram of an engineering monitoring and management system based on big data. This embodiment provides an engineering monitoring and management system based on big data, including:

[0054] A big data processing module 10, configured to obtain construction site historical data and historical risk event data, divide the construction site historical data according to the historical risk event time to obtain multiple risk-associated construction site data groups; establish a digital twin of the construction site, locate it in the digital twin according to the source of the construction site historical data, and screen the construction site historical data in the risk-associated construction site data groups based on the occurrence location of the historical risk event data;

[0055] A model construction module 20, configured to analyze the change characteristics of each data in the risk-associated construction site data groups, identify the characteristic data associated with the occurrence of risk events, obtain the characteristic thresholds corresponding to each characteristic data, and establish probability models for various types of risk events;

[0056] A monitoring and management module 30, configured to obtain real-time engineering monitoring data and input it into the digital twin of the construction site, monitor the characteristic data values, and when there is characteristic data exceeding the corresponding characteristic threshold, calculate the occurrence probability of the current engineering risk event with the probability model of the risk event corresponding to the characteristic data, and then give a prompt and warning in the digital twin of the construction site.

[0057] Further, in the model construction module 20, after establishing the probability models for various types of risk events, it specifically further includes:

[0058] The probability model of the risk event is specifically:

[0059] ;

[0060] Wherein, is the occurrence probability of the a-th type of risk event, is the number of data types in the risk-associated construction site data groups, is the influence coefficient of the n-th type of construction site data on the occurrence of risk events, is the current data value of the n-th type of construction site data, is the standard data value of the n-th type of construction site data.

[0061] Further, in the big data processing module 10, locating in the digital twin according to the source of the construction site historical data and screening the construction site historical data in the risk-associated construction site data groups based on the occurrence location of the historical risk event data is specifically:

[0062] Establish a spatial coordinate system in the construction site digital twin, identify the first spatial coordinates of the sensors monitoring the historical data of each construction site in the construction site digital twin, identify the second spatial coordinates of the occurrence locations of historical risk events in the construction site digital twin, calculate the distance between the first spatial coordinates and the second spatial coordinates, and remove the construction site historical data corresponding to the first spatial coordinates with a distance greater than the preset distance threshold from the risk-related construction site data group.

[0063] The third aspect of this application also provides an engineering monitoring and management method device based on big data, including a processor and a memory: wherein the memory is used to store program codes and transmit the program codes to the processor; the processor is used to execute the above-mentioned engineering monitoring and management method based on big data according to the instructions in the program codes.

[0064] The fourth aspect of this application provides a computer-readable storage medium, characterized in that the computer-readable storage medium is used to store program codes, and the program codes are used to execute the above-mentioned engineering monitoring and management method based on big data.

[0065] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0066] In the several embodiments provided by this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the displayed or discussed mutual coupling or direct coupling or communication connection can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be in electrical, mechanical, or other forms.

[0067] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0068] In addition, in each embodiment of the present invention, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0069] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0070] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An engineering monitoring and management method based on big data, characterized in that Including: Obtain the historical data of the construction site and the historical risk event data, divide the historical data of the construction site according to the time of historical risk events, and obtain multiple risk-associated construction site data groups; Establish a digital twin of the construction site, locate it in the digital twin according to the source of the historical data of the construction site, and screen the historical data of the construction site in the risk-associated construction site data groups based on the occurrence location of the historical risk event data; Analyze the change characteristics of each data in the risk-associated construction site data groups, identify the characteristic data that has an associated relationship with the occurrence of risk events, obtain the characteristic thresholds corresponding to each characteristic data, and establish probability models for various types of risk events; Obtain the real-time monitoring data of the project and input it into the digital twin of the construction site, monitor the characteristic data values. When there is characteristic data exceeding the corresponding characteristic threshold, calculate the occurrence probability of the current project risk event with the probability model of the risk event corresponding to the characteristic data, and then give a prompt and warning in the digital twin of the construction site.

2. The engineering monitoring and management method based on big data according to claim 1, wherein After establishing the probability models for various types of risk events, it specifically further includes: The probability model of the risk event is specifically: ； Among them, is the occurrence probability of the a-th type of risk event, is the number of data types in the risk-associated construction site data group, is the influence coefficient of the n-th type of construction site data on the occurrence of the risk event, is the current data value of the n-th type of construction site data, is the standard data value of the n-th type of construction site data.

3. The engineering monitoring and management method based on big data according to claim 1, characterized in that The positioning in the digital twin according to the source of the historical data of the construction site and screening the historical data of the construction site in the risk-associated construction site data groups based on the occurrence location of the historical risk event data is specifically: Establish a spatial coordinate system in the digital twin of the construction site, identify the first spatial coordinates of the sensors monitoring each piece of historical data of the construction site in the digital twin of the construction site, identify the second spatial coordinates of the occurrence location of the historical risk event in the digital twin of the construction site, calculate the distance between the first spatial coordinates and the second spatial coordinates, and remove the historical data of the construction site corresponding to the first spatial coordinates with a distance greater than the preset distance threshold from the risk-associated construction site data groups.

4. An engineering monitoring and management system based on big data, characterized in that, Including: A big data processing module, which is used to obtain the historical data of the construction site and the historical risk event data, divide the historical data of the construction site according to the time of historical risk events, and obtain multiple risk-associated construction site data groups; establish a digital twin of the construction site, locate it in the digital twin according to the source of the historical data of the construction site, and screen the historical data of the construction site in the risk-associated construction site data groups based on the occurrence location of the historical risk event data; A model construction module, which is used to analyze the change characteristics of each data in the risk-associated construction site data groups, identify the characteristic data that has an associated relationship with the occurrence of risk events, obtain the characteristic thresholds corresponding to each characteristic data, and establish probability models for various types of risk events; A monitoring and management module, which is used to obtain the real-time monitoring data of the project and input it into the digital twin of the construction site, monitor the characteristic data values. When there is characteristic data exceeding the corresponding characteristic threshold, calculate the occurrence probability of the current project risk event with the probability model of the risk event corresponding to the characteristic data, and then give a prompt and warning in the digital twin of the construction site.

5. An engineering monitoring and management system based on big data according to claim 4, characterized in that, In the model construction module, after establishing the probability models for various types of risk events, it specifically further includes: The probability model of the risk event is specifically: ； Among them, is the occurrence probability of the risk event of type a, is the number of data types in the risk-related construction site data group, is the influence coefficient of the nth type of construction site data on the occurrence of the risk event, is the current data value of the nth type of construction site data, is the standard data value of the nth type of construction site data.

6. An engineering monitoring and management system based on big data according to claim 4, characterized in that, In the big data processing module, the positioning in the digital twin according to the source of the historical data of the construction site and screening the historical data of the construction site in the risk-associated construction site data groups based on the occurrence location of the historical risk event data is specifically: Establish a spatial coordinate system in the construction site digital twin, identify the first spatial coordinates of the sensors that monitor the historical data of each construction site in the construction site digital twin, identify the second spatial coordinates of the occurrence locations of historical risk events in the construction site digital twin, calculate the distance between the first spatial coordinates and the second spatial coordinates, and remove the construction site historical data corresponding to the first spatial coordinates with a distance greater than the preset distance threshold from the risk-related construction site data group.

7. An engineering monitoring and management device based on big data, characterized in that, The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute a big data-based engineering monitoring and management method according to any one of claims 1-3 based on the instructions in the program code.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code, and the program code is used to execute a big data-based engineering monitoring and management method according to any one of claims 1-3.

Images