Engineering supervision big data analysis system and analysis method based on Internet of Things

Abstract

The invention discloses a project supervision big data analysis system and analysis method based on the Internet of Things, relates to the technical field of project data analysis, and solves the technical problem that the accuracy of an evaluation result of project risk evaluation is not high due to the fact that the progress of a project is not analyzed in the prior art. The method comprises the following steps: collecting project operation data and corresponding expected data of each project, preprocessing the project operation data, detecting abnormal values and missing values in the data, modifying and filling, classifying standard operation data, and encrypting and transporting to obtain classified operation data; setting a short-term progress coefficient and a long-term progress coefficient according to the expected quality and the project quality, and calculating a risk coefficient of the project by combining an expected progress and an expected cost in the classified operation data; comparing the risk coefficient with a preset risk threshold to obtain an evaluation result; and integrating the evaluation result and the engineering operation data to obtain integrated data, and generating a project analysis report based on the integrated data.

Description

Technical Field

[0001] The present invention belongs to the field of engineering data analysis and relates to Internet of Things technology, and specifically to an engineering supervision big data analysis system and analysis method based on the Internet of Things. Background Art

[0002] In recent years, with the acceleration of urbanization and the rapid development of infrastructure construction, the number of engineering projects has increased dramatically. This has not only brought huge economic opportunities, but also put forward higher requirements on the project management and data analysis capabilities of enterprises. Project management is also facing more and more challenges, including cost control, schedule management, quality assurance, etc.

[0003] The invention patent with application number CN114037314A discloses a method for dynamic analysis of project risks in information system engineering supervision. The invention obtains an evaluation model by collecting initialization data and inputting the initialization data into a program. The evaluation model evaluates the comfort data, prompts the user that the data is not completed, and configures a risk threshold for the user. The project is evaluated based on the risk threshold, and a heartbeat mechanism is determined for the user. The risk assessment model and the indicator benchmark threshold trigger conditions are configured, and the supervision measure result data are input. The program statistically analyzes the project risk and finally outputs an analysis report. When obtaining the user's risk coefficient, the invention does not analyze the progress of the current project. The difference between slow-progressing projects and fast-progressing projects may cause the obtained risk coefficient to be inaccurate.

[0004] The present invention provides an engineering supervision big data analysis system and analysis method based on the Internet of Things to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an engineering supervision big data analysis system and analysis method based on the Internet of Things, which are used to solve the technical problem that the prior art does not analyze the progress of the project, resulting in low accuracy of the evaluation results of the risk assessment of the project.

[0006] To achieve the above-mentioned purpose, the first aspect of the present invention provides an engineering supervision big data analysis system based on the Internet of Things, comprising: a data collection module, a data transmission module, a data analysis module and a data integration module;

[0007] Data collection module: used to collect engineering operation data and expected data of each project;

[0008] Data transmission module: used to pre-process the engineering operation data to obtain standard operation data, classify the standard operation data and encrypt and transmit it to the supervision platform to obtain classified operation data;

[0009] Data analysis module: used to combine classified operating data and expected data to obtain the risk coefficient of each project; evaluate each project based on the risk coefficient to obtain the evaluation results;

[0010] Data integration module: used to integrate the engineering operation data of each project according to time and evaluation results to obtain integrated data, and generate project analysis reports based on the integrated data.

[0011] Preferably, the preprocessing of the engineering operation data to obtain standard operation data includes:

[0012] Extracting engineering operation data; the engineering operation data includes project type, project progress, project cost and project quality; wherein the project type includes short-term projects and long-term projects;

[0013] The engineering operation data is cleaned, outliers and missing values ​​are detected in turn, and the missing values ​​and outliers are changed and filled, and the pre-processed engineering operation data is marked as standard operation data.

[0014] Preferably, the classifying of the standard operating data and encrypting and transmitting the same to the supervision platform to obtain the classified operating data includes:

[0015] Extract standard operating data;

[0016] The standard operating data is classified according to the project type to obtain short-term operating data and long-term operating data; the short-term operating data and long-term operating data are encrypted and transmitted to the supervision platform via the HTTPS protocol, and the short-term operating data is stored in the short-term node, and the long-term operating data is stored in the long-term node; the combination of the short-term operating data stored in the short-term node and the long-term operating data stored in the long-term node is marked as classified operating data.

[0017] Preferably, the risk coefficient of each project obtained by combining the classified operating data and the expected data includes:

[0018] Extract classified operating data and expected data; the expected data includes the expected completion time, expected budget, and expected quality of each project;

[0019] Match the expected data corresponding to the short-term operating data and mark it as short-term expected data, match the expected data corresponding to the long-term operating data and mark it as long-term expected data;

[0020] According to the expected completion time in the short-term expected data and the current time, the short-term expected progress is obtained; according to the expected completion time in the long-term expected data and the current time, the long-term expected progress is obtained; according to the expected budget in the short-term expected data and the current time, the short-term cost is obtained; according to the expected budget in the long-term expected data and the current time, the long-term cost is obtained; according to the short-term expected progress, the short-term project progress, the long-term expected progress and the long-term project progress, the progress status of each project is obtained;

[0021] Set the short-term progress coefficient and the long-term progress coefficient according to the expected quality and project quality; mark the short-term progress coefficient as α and the long-term progress coefficient as β; mark the short-term expected progress as DYD, the project progress of the short-term project as DJD, the project cost of the short-term project as DCB, and the short-term cost as DXB; mark the long-term expected progress as CYD, the project progress of the long-term project as CJD, the project cost of the long-term project as CCB, and the long-term cost as CXB;

[0022] When the progress status of a short-term project is normal, the short-term risk factor DFS of the short-term project is calculated by the formula DFS = α × (DYD-DJD) × DCB / DXB; when the progress status of a short-term project is abnormal, the short-term risk factor DFS of the short-term project is calculated by the formula DFS = (DJD-DYD) / α × DCB / DXB;

[0023] When the progress status of a long-term project is normal, the long-term risk factor CFS of the long-term project is calculated by the formula CFS = β × (CYD-CJD) × CCB / CXB; when the progress status of a long-term project is abnormal, the long-term risk factor CFS of the long-term project is calculated by the formula CFS = (CJD-CYD) / β × CCB / CXB;

[0024] Label the short-term risk factor and the long-term risk factor as risk factors.

[0025] Preferably, obtaining the progress status of each project according to the short-term expected progress, the short-term project progress, the long-term expected progress and the long-term project progress includes:

[0026] Extract short-term expected progress, short-term project progress, long-term expected progress and long-term project progress;

[0027] Determine whether the progress of the short-term project is greater than or equal to the expected progress of the short-term project; if yes, mark the progress status of the corresponding short-term project as normal progress; if no, mark the progress status of the corresponding short-term project as abnormal progress;

[0028] Determine whether the progress of the long-term project is greater than or equal to the expected progress of the long-term project; if yes, mark the progress status of the corresponding long-term project as normal progress; if no, mark the progress status of the corresponding long-term project as abnormal progress.

[0029] Preferably, the short-term progress coefficient and the long-term progress coefficient are set according to the expected quality and the project quality, including:

[0030] Extract expected quality and project quality;

[0031] Determine whether the project quality is greater than or equal to the expected quality; if yes, mark the quality status of the corresponding project as normal; if no, mark the quality status of the corresponding project as abnormal;

[0032] When the quality status is normal, the expected quality of short-term projects is marked as DYL, and the project quality of short-term projects is marked as DZL; the expected quality of long-term projects is marked as CYL, and the project quality of long-term projects is marked as CZL;

[0033] The short-term progress coefficient α of the short-term project is calculated by the formula α=DYL / DZL; the long-term progress coefficient β of the long-term project is calculated by the formula β=CYL / CZL.

[0034] Preferably, the evaluation of each project based on the risk factor to obtain the evaluation result includes:

[0035] Extract risk factor;

[0036] Setting risk thresholds; the risk thresholds include short-term risk thresholds and long-term risk thresholds;

[0037] Determine whether the short-term risk coefficient is greater than the short-term risk threshold; if yes, mark the short-term assessment result of the corresponding short-term project as a risk project; if no, mark the short-term assessment result of the corresponding short-term project as a non-risk project;

[0038] Determine whether the long-term risk coefficient is greater than or equal to the long-term risk threshold; if yes, mark the long-term assessment result of the corresponding long-term project as a risk project; if no, mark the long-term assessment result of the corresponding long-term project as a non-risk project.

[0039] Preferably, the step of integrating the engineering operation data of each project according to the time and the evaluation results to obtain integrated data includes:

[0040] Count the evaluation results of all projects at the current time;

[0041] Construct a data table, integrate and compile statistics of the engineering operation data of each project in chronological order, and input the engineering operation data of each project and the corresponding expected data into the data table; mark the risk projects to obtain integrated data.

[0042] Preferably, generating a project analysis report based on the integrated data includes:

[0043] Input the integrated data into business intelligence tools to obtain preliminary analysis reports;

[0044] Mark the progress status and quality status of each project in the preliminary analysis report to obtain a project analysis report.

[0045] A second aspect of the present invention provides an engineering supervision big data analysis method based on the Internet of Things, comprising:

[0046] Step 1: Collect engineering operation data and expected data of each project;

[0047] Step 2: Preprocess the engineering operation data to obtain standard operation data, classify the standard operation data and encrypt and transmit it to the supervision platform to obtain classified operation data;

[0048] Step 3: Combine the classified operating data and expected data to obtain the risk coefficient of each project; evaluate each project based on the risk coefficient to obtain the evaluation results;

[0049] Step 4: Integrate the engineering operation data of each project according to the time and evaluation results to obtain integrated data, and generate a project analysis report based on the integrated data.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] 1. The present invention collects the engineering operation data and the corresponding expected data of each project, pre-processes the engineering operation data, detects abnormal values ​​and missing values ​​in the data and modifies and fills them, ensures the integrity of the data, and improves the accuracy of the data; classifies the standard operation data and encrypts and transports them to obtain classified operation data, improves the security of the data, and speeds up the efficiency and convenience of data retrieval; matches the expected data corresponding to the engineering operation data, and obtains the short-term expected progress and long-term expected progress according to the expected completion time and the current time, and obtains the short-term cost and long-term cost according to the expected budget in the expected data, so as to monitor the progress and financial status of the project in real time, ensure that the project proceeds as planned, and help identify potential risks and make preparations in advance. Preparation and planning make the data clearer and easier to understand; set short-term and long-term progress coefficients according to expected quality and project quality, and calculate the risk coefficient of the project in combination with the expected progress and expected cost, which helps to monitor the progress of the project in real time, evaluate the cost-effectiveness of the project, help control costs, and provide management with key information on project progress and cost status, helping them make correct decisions at an early stage; compare the risk coefficient with the preset risk threshold to obtain the evaluation result; integrate the evaluation result with the engineering operation data to obtain integrated data, generate a project analysis report based on the integrated data, help identify potential risks faced by the project, take corresponding preventive measures, and adjust the project plan in time to avoid delays.

[0052] 2. The present invention obtains the progress status of each project according to the short-term expected progress, the short-term project progress, the long-term expected progress and the long-term project progress, and sets the short-term progress coefficient and the long-term progress coefficient according to the expected quality and the project quality. The risk coefficient of the project is calculated based on the progress status and the progress coefficient. For projects with abnormal progress status, timely adjustments are made to speed up the progress to ensure the completion of the task. The risk coefficient is compared with the preset risk threshold to obtain the evaluation result of the project. If the evaluation result of the project is a risky project, the project needs to be adjusted and improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 The following is a flowchart of an embodiment of the present invention.

[0055] Figure 2 It is a system composition diagram of the present invention.

[0056] Figure 3 The figure is a complete flow chart for obtaining the progress status in one embodiment of the present invention. DETAILED DESCRIPTION

[0057] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] See also Figure 1-Figure 3 , the first aspect of the present invention provides an engineering supervision big data analysis system and analysis method based on the Internet of Things, including: a data collection module, a data transmission module, a data analysis module and a data integration module;

[0059] Data collection module: used to collect engineering operation data and expected data of each project.

[0060] Exemplarily, three construction projects being implemented by Company A are collected, namely Project 1, Project 2 and Project 3. Project 1 is a short-term project with a project progress of 50% completion in 2 months, a current project cost of 300,000 yuan, and an evaluation satisfaction score of 70 points for project quality. Project 2 is a long-term project with a project progress of 40% completion in 5 months, a current project cost of 500,000 yuan, and a project quality of 77 points. Project 3 is a short-term project with a project progress of 65% completion in 3 months, a current project cost of 400,000 yuan, and a project quality of 70 points. The expected data for Project 1 are an expected completion time of 5 months, an expected budget of 600,000 yuan, and an expected quality of 70 points. The expected data for Project 2 are an expected completion time of 12 months, an expected budget of 1 million yuan, and an expected quality of 70 points. The expected data for Project 3 are an expected completion time of 4 months, an expected budget of 600,000 yuan, and an expected quality of 70 points.

[0061] Data transmission module: used to pre-process the engineering operation data to obtain standard operation data, classify the standard operation data and encrypt and transmit it to the supervision platform to obtain classified operation data.

[0062] Exemplarily, data cleaning is performed on the engineering operation data of three projects, and outliers and missing values ​​in the engineering operation data are detected. It is detected that there are no outliers and missing values ​​in the engineering operation data, and the preprocessed engineering operation data are marked as standard operation data.

[0063] In some other embodiments, when pre-processing the engineering operation data, abnormal values ​​or missing values ​​are detected. Since each project is indispensable to the supervision platform, it is necessary to manually change or fill in the abnormal values ​​or missing values ​​to ensure the integrity of the data.

[0064] The standard operating data is classified according to the project type. The engineering operating data of Project One and Project Three are classified into short-term operating data, and the engineering operating data of Project Two is classified into long-term operating data. The short-term operating data and long-term operating data are encrypted and transmitted to the supervision platform via the HTTPS protocol, and the short-term operating data is stored in the short-term node, and the long-term operating data is stored in the long-term node. The combination of short-term operating data stored in the short-term node and long-term operating data stored in the long-term node is marked as classified operating data.

[0065] Data analysis module: used to combine classified operating data and expected data to obtain the risk coefficient of each project; evaluate each project based on the risk coefficient to obtain the evaluation result.

[0066] Exemplarily, the expected data corresponding to Project One and Project Three are marked as short-term expected data, and the expected data corresponding to Project Two is marked as long-term expected data; based on the expected completion time of Project One and the current time, the short-term expected progress of Project One is 40%, based on the expected completion time of Project Two and the current time, the long-term expected progress of Project Two is 42%, and based on the expected completion time of Project Three and the current time, the short-term expected progress of Project Three is 75%; based on the expected budget of Project One and the current time, the short-term cost of Project One is 300,000, based on the expected budget of Project Two and the current time, the long-term cost of Project Two is 400,000, and based on the expected budget of Project Three and the current time, the short-term cost of Project Three is 390,000.

[0067] Determine whether the progress of the short-term project is greater than or equal to the expected progress of the short-term project. If the progress of Project 1 is less than the expected progress and the progress of Project 3 is greater than the expected progress, the progress status of Project 1 is abnormal progress and the progress status of Project 3 is normal progress. Determine whether the progress of the long-term project is greater than or equal to the expected progress of the long-term project. If the progress of Project 2 is greater than the expected progress, the progress status of Project 2 is normal.

[0068] Determine whether the project quality is greater than or equal to the expected quality. If the quality of Project 1, Project 2 and Project 3 is greater than or equal to the expected quality, then the quality status of Project 1, Project 2 and Project 3 is normal. The short-term progress coefficient α of the short-term project is calculated by the formula α=DYL / DZL, and the long-term progress coefficient β of the long-term project is calculated by the formula β=CYL / CZL to be 1.1.

[0069] It should be noted that if the quality status of the project is abnormal, its implementation needs to be suspended and the quality issues need to be rectified before it can be continued.

[0070] The progress status of Project 1 is abnormal progress, and the short-term risk factor DFS of Project 1 is calculated by the formula DFS = (DJD-DYD) / α×DCB / DXB = 10.0;

[0071] The progress status of Project 2 and Project 3 is normal progress. The short-term risk factor DFS of Project 3 is calculated by the formula DFS = α × (DYD-DJD) × DCB / DXB = 10.2;

[0072] The long-term risk factor of Project 2 is calculated using the formula CFS = β × (CYD-CJD) × CCB / CXB to obtain CFS = 14.4.

[0073] In this embodiment, the short-term risk threshold is set to 10, and the long-term risk threshold is 15; determine whether the short-term risk coefficient is greater than the short-term risk threshold, and determine that the short-term risk coefficient of project one is equal to the short-term risk threshold, and the short-term risk coefficient of project three is greater than the short-term risk threshold, then the short-term assessment result of project one is marked as a non-risk project, and the short-term assessment result of project three is marked as a risk project; determine whether the long-term risk coefficient is greater than or equal to the long-term risk threshold, and determine that the long-term risk coefficient of project two is less than the long-term risk threshold, then the long-term assessment result of project two is a non-risk project.

[0074] Construct an initial data chart, enter the engineering operation data of Project 1, Project 2 and Project 3 into the initial data chart in chronological order, and also enter the corresponding expected data into the initial data chart as a comparison standard for the engineering operation data, and mark Project 3 as a risk project in the data chart.

[0075] Input the integrated data into PowerBI software to obtain a preliminary analysis report, mark the progress status of Project 1 as abnormal in the preliminary analysis report, and obtain a project analysis report.

[0076] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0077] Working principle of the present invention:

[0078] The present invention collects engineering operation data and expected data of each project, pre-processes the engineering operation data to obtain standard operation data, and classifies the standard operation data according to project types to obtain short-term operation data and long-term operation data; obtains short-term expected progress and long-term expected progress according to expected completion time; obtains short-term cost and long-term cost according to expected budget; obtains the progress status of each project based on short-term expected progress, short-term project progress, long-term expected progress and long-term project progress; sets short-term progress coefficient and long-term progress coefficient according to expected quality and project quality, calculates the risk coefficient of each project based on progress status, progress coefficient, expected progress and expected cost, compares the risk coefficient with a preset risk threshold to obtain the project evaluation result; statistically integrates the engineering operation data according to the evaluation result to obtain integrated data, and generates a project analysis report based on the integrated data.

[0079] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. The engineering supervision big data analysis system based on the Internet of Things is characterized by: include: Data collection module, data transmission module, data analysis module and data integration module; Data collection module: used to collect engineering operation data and expected data of each project; Data transmission module: used to pre-process the engineering operation data to obtain standard operation data, classify the standard operation data and encrypt and transmit it to the supervision platform to obtain classified operation data; Data analysis module: used to combine classified operating data and expected data to obtain the risk coefficient of each project; Evaluate each project based on the risk factor to obtain the evaluation results; Data integration module: used to integrate the engineering operation data of each project according to time and evaluation results to obtain integrated data, and generate project analysis reports based on the integrated data.

2. According to the Internet of Things-based engineering supervision big data analysis system according to claim 1, it is characterized in that: The preprocessing of the engineering operation data to obtain standard operation data includes: Extracting engineering operation data; the engineering operation data includes project type, project progress, project cost and project quality; wherein the project type includes short-term projects and long-term projects; The engineering operation data is cleaned, outliers and missing values ​​are detected in turn, and the missing values ​​and outliers are changed and filled, and the pre-processed engineering operation data is marked as standard operation data.

3. According to the Internet of Things-based engineering supervision big data analysis system of claim 1, it is characterized in that: The process of classifying the standard operating data and encrypting and transmitting the data to the supervision platform to obtain the classified operating data includes: Extract standard operating data; The standard operating data is classified according to the project type to obtain short-term operating data and long-term operating data; the short-term operating data and long-term operating data are encrypted and transmitted to the supervision platform via the HTTPS protocol, and the short-term operating data is stored in the short-term node, and the long-term operating data is stored in the long-term node; the combination of the short-term operating data stored in the short-term node and the long-term operating data stored in the long-term node is marked as classified operating data.

4. The engineering supervision big data analysis system based on the Internet of Things according to claim 1 is characterized in that: The risk factor of each project is obtained by combining the classified operating data and the expected data, including: Extract classified operating data and expected data; the expected data includes the expected completion time, expected budget, and expected quality of each project; Match the expected data corresponding to the short-term operating data and mark it as short-term expected data, match the expected data corresponding to the long-term operating data and mark it as long-term expected data; According to the expected completion time in the short-term expected data and the current time, the short-term expected progress is obtained; according to the expected completion time in the long-term expected data and the current time, the long-term expected progress is obtained; according to the expected budget in the short-term expected data and the current time, the short-term cost is obtained; according to the expected budget in the long-term expected data and the current time, the long-term cost is obtained; according to the short-term expected progress, the short-term project progress, the long-term expected progress and the long-term project progress, the progress status of each project is obtained; Set the short-term progress coefficient and the long-term progress coefficient according to the expected quality and project quality; mark the short-term progress coefficient as α and the long-term progress coefficient as β; mark the short-term expected progress as DYD, the project progress of the short-term project as DJD, the project cost of the short-term project as DCB, and the short-term cost as DXB; mark the long-term expected progress as CYD, the project progress of the long-term project as CJD, the project cost of the long-term project as CCB, and the long-term cost as CXB; When the progress status of a short-term project is normal, the short-term risk factor DFS of the short-term project is calculated by the formula DFS = α × (DYD-DJD) × DCB / DXB; when the progress status of a short-term project is abnormal, the short-term risk factor DFS of the short-term project is calculated by the formula DFS = (DJD-DYD) / α × DCB / DXB; When the progress status of a long-term project is normal, the long-term risk factor CFS of the long-term project is calculated by the formula CFS = β × (CYD-CJD) × CCB / CXB; when the progress status of a long-term project is abnormal, the long-term risk factor CFS of the long-term project is calculated by the formula CFS = (CJD-CYD) / β × CCB / CXB; Label the short-term risk factor and the long-term risk factor as risk factors.

5. According to the Internet of Things-based engineering supervision big data analysis system of claim 4, it is characterized in that: The progress status of each project is obtained according to the short-term expected progress, the short-term project progress, the long-term expected progress and the long-term project progress, including: Extract short-term expected progress, short-term project progress, long-term expected progress and long-term project progress; Determine whether the progress of the short-term project is greater than or equal to the expected progress of the short-term project; if yes, mark the progress status of the corresponding short-term project as normal progress; if no, mark the progress status of the corresponding short-term project as abnormal progress; Determine whether the progress of the long-term project is greater than or equal to the expected progress of the long-term project; if yes, mark the progress status of the corresponding long-term project as normal progress; if no, mark the progress status of the corresponding long-term project as abnormal progress.

6. The engineering supervision big data analysis system based on the Internet of Things according to claim 4 is characterized in that: The short-term progress factor and the long-term progress factor are set according to the expected quality and project quality, including: Extract expected quality and project quality; Determine whether the project quality is greater than or equal to the expected quality; if yes, mark the quality status of the corresponding project as normal; if no, mark the quality status of the corresponding project as abnormal; When the quality status is normal, the expected quality of short-term projects is marked as DYL, and the project quality of short-term projects is marked as DZL; the expected quality of long-term projects is marked as CYL, and the project quality of long-term projects is marked as CZL; The short-term progress coefficient α of the short-term project is calculated by the formula α=DYL / DZL; the long-term progress coefficient β of the long-term project is calculated by the formula β=CYL / CZL.

7. The engineering supervision big data analysis system based on the Internet of Things according to claim 1 is characterized in that: The evaluation results obtained by evaluating each project based on the risk factor include: Extract risk factor; Setting risk thresholds; the risk thresholds include short-term risk thresholds and long-term risk thresholds; Determine whether the short-term risk coefficient is greater than the short-term risk threshold; if yes, mark the short-term assessment result of the corresponding short-term project as a risk project; if no, mark the short-term assessment result of the corresponding short-term project as a non-risk project; Determine whether the long-term risk coefficient is greater than or equal to the long-term risk threshold; if yes, mark the long-term assessment result of the corresponding long-term project as a risk project; if no, mark the long-term assessment result of the corresponding long-term project as a non-risk project.

8. The engineering supervision big data analysis system based on the Internet of Things according to claim 1 is characterized in that: The engineering operation data of each project is integrated according to the time and evaluation results to obtain integrated data, including: Count the evaluation results of all projects at the current time; Construct a data table, integrate and compile statistics of the engineering operation data of each project in chronological order, and input the engineering operation data of each project and the corresponding expected data into the data table; mark the risk projects to obtain integrated data.

9. The engineering supervision big data analysis system based on the Internet of Things according to claim 1 is characterized in that: The project analysis report generated based on the integrated data includes: Input the integrated data into business intelligence tools to obtain preliminary analysis reports; Mark the progress status and quality status of each project in the preliminary analysis report to obtain a project analysis report.

10. A method for analyzing engineering supervision big data based on the Internet of Things, used to run the engineering supervision big data analysis system based on the Internet of Things according to any one of claims 1 to 9, characterized in that: include: Step 1: Collect engineering operation data and expected data of each project; Step 2: Preprocess the engineering operation data to obtain standard operation data, classify the standard operation data and encrypt and transmit it to the supervision platform to obtain classified operation data; Step 3: Combine classified operating data and expected data to obtain the risk coefficient of each project; Evaluate each project based on the risk factor to obtain the evaluation results; Step 4: Integrate the engineering operation data of each project according to the time and evaluation results to obtain integrated data, and generate a project analysis report based on the integrated data.

Images