Data analysis methods, devices, equipment and media for infrastructure construction projects

By selecting effective indicators based on historical data and multiple machine learning algorithms in infrastructure construction projects, and using a vector autoregression model for data analysis, the problem of low accuracy in data analysis in existing technologies has been solved, enabling scientific risk prediction and timely early warning.

CN117875694BActive Publication Date: 2026-11-17ROAD & BRIDGE INT CO LTD +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202311694966.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-12-11
Publication Date
2026-11-17
Estimated Expiration
2043-12-11

AI Technical Summary

Technical Problem

In existing technologies, data analysis for infrastructure construction projects is affected by subjective human factors, resulting in low accuracy and an inability to scientifically predict and warn of risks.

Method used

We employ historical data to determine effective indicators, combine multiple machine learning algorithms, use genetic optimization algorithms and chi-square tests to screen descriptive indicators, and use vector autoregression models for data prediction and risk warning.

Benefits of technology

It improves the scientific rigor and accuracy of data analysis, enabling timely detection and early warning of risks in construction projects, and enhancing the credibility and accuracy of risk prediction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117875694B_ABST
    Figure CN117875694B_ABST
Patent Text Reader

Abstract

This application relates to a data analysis method, apparatus, equipment, and medium for infrastructure construction projects, applied in the field of construction project management analysis technology. The method includes: acquiring historical data and data to be measured, wherein the historical data is historical project data, and the data to be measured is the project data to be predicted; determining effective indicators based on the historical data, wherein the effective indicators are indicators related to project risks; determining descriptive indicators based on the effective indicators and multiple machine learning algorithms, wherein the descriptive indicators are indicators used to describe risky projects, and the risky projects are projects with existing risks; predicting the data to be measured based on the descriptive indicators to obtain prediction results; and providing risk warnings based on the prediction results. This application has the effect of accurately predicting and warning of project risks.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the technical field of construction project operation analysis, and in particular to a data analysis method, apparatus, equipment and medium for infrastructure construction projects. Background Technology

[0002] Infrastructure is the material basis for the production, operation, work and life of all enterprises, units and residents. It is the guarantee for the normal operation of the main urban facilities. With the continuous development of society, the requirements for infrastructure construction are also increasing. Accompanying this is the increasing number of projects and increasingly complex project data. In the process of project advancement, the analysis of project data is an essential process. Through the analysis of project data, existing risks can be identified in a timely manner.

[0003] Currently, the analysis of project data is usually done manually. Due to the influence of human subjective factors, the accuracy of data analysis is low, making it impossible to conduct scientific data analysis and thus impossible to accurately predict and warn of project risks. Summary of the Invention

[0004] In order to accurately predict and warn of risks in projects, this application provides a data analysis method, device, equipment and medium for infrastructure construction projects.

[0005] Firstly, this application provides a data analysis method for infrastructure construction projects, employing the following technical solution: A data analysis method for infrastructure construction projects includes: Acquire historical data and data to be tested, wherein the historical data is historical project data and the data to be tested is the project data to be predicted; Based on the historical data, effective indicators are determined, and these effective indicators are those related to the risks associated with the project. Based on the effective indicators and multiple machine learning algorithms, descriptive indicators are determined. These descriptive indicators are used to describe risky projects, and the risky projects are projects that are at risk. Based on the described indicators, the test data is predicted to obtain the prediction result; Risk warnings will be issued based on the prediction results.

[0006] By adopting the above technical solution, indicators related to project risks, i.e., effective indicators, are determined based on historical data. Based on the effective indicators and machine learning algorithms, indicators describing risky projects are determined, making the determination of descriptive indicators more scientific and reasonable. Based on these descriptive indicators, predictions are made on the data to be tested, and the prediction results are more accurate, enabling more timely detection of risks and early warning.

[0007] Optionally, determining effective indicators based on the historical data includes: Risk project data is determined based on the historical data, and the risk project data is the data of the risk project. Based on the risk project data, a first evaluation indicator is determined, wherein the first evaluation indicator is an indicator that the null value rate is less than a preset null value rate; The effective indicators are determined based on the first evaluation index.

[0008] By adopting the above technical solution, the indicators are screened, and those with lower null values ​​are selected for subsequent processing, which improves the integrity of the data. The effective indicators determined based on the first evaluation indicator also have higher completeness, thereby improving the credibility of the data analysis.

[0009] Optionally, determining the effective indicator based on the first evaluation indicator includes: Determine the data type of the first evaluation index, wherein the data type includes continuous and discrete types; If the data type of the first evaluation index is continuous, then the risk threshold is determined based on the genetic optimization algorithm, and the risk threshold is the critical value at which the first evaluation index touches the risk item; The first probability is calculated based on the first formula, which includes: Wherein, P(risk item | indicator value falls within the risk range) is the first probability, the risk range is the range determined based on the risk threshold, and the indicator value is the value corresponding to the first evaluation indicator; Effective indicators are determined based on the first probability and the probability of risky items. The probability of risky items is the probability of the risky item among all items, and all items include the risky item and normal items.

[0010] By adopting the above technical solution, different analysis methods are selected according to the data type of the first evaluation indicator, which improves the accuracy of data analysis. If the data type of the first evaluation indicator is continuous, the risk threshold is determined according to the genetic optimization algorithm, and the indicators related to the risks of the project are determined according to the calculation of conditional probability, making the effective indicators more scientific and reasonable.

[0011] Optionally, after determining the data type of the first evaluation index, the method further includes: If the data type of the first evaluation indicator is discrete, the correlation between the first evaluation indicator and the risk project is determined based on the chi-square test. If the correlation is greater than the preset correlation, the first evaluation index is determined as the second evaluation index. The second evaluation index is an index whose data type is discrete and whose correlation with the risk project is higher than the preset correlation. The effective indicators are determined based on the second evaluation index.

[0012] By adopting the above technical solution, if the data type of the first evaluation indicator is discrete, the correlation between the first evaluation indicator and the risk item is determined based on the chi-square test, and the indicator with higher correlation is selected for subsequent analysis, thereby improving the accuracy of risk prediction.

[0013] Optionally, determining the effective indicator based on the second evaluation indicator includes: The second probability is calculated based on the second formula, which includes: Wherein, P (second evaluation index | risk item) is the second probability; The effective indicator is determined based on the second probability and the probability of the risky project.

[0014] By adopting the above technical solution, the conditional probability of the second evaluation index is calculated and compared with the probability of risk projects, so that the determined effective index has a higher correlation with the risk projects, and the descriptive index determined based on the effective index can better describe the risk projects.

[0015] Optionally, the step of determining the descriptive metrics based on the effective metrics and multiple machine learning algorithms includes: Multiple first descriptive indicators are determined based on multiple machine learning algorithms, the effective indicators, and the historical data, wherein the first descriptive indicators are the descriptive indicators calculated by the machine learning algorithms; The accuracy of each of the machine learning algorithms is calculated based on the confusion matrix and multiple first descriptive metrics. A predetermined number of machine learning algorithms with high accuracy are selected as high-quality algorithms; The descriptive metrics are determined based on the aforementioned high-quality algorithm.

[0016] By adopting the above technical solution, indicators that can better describe risky projects are selected based on machine learning algorithms, and the accuracy of each machine learning algorithm is calculated based on the confusion matrix. The machine learning algorithm with higher accuracy is selected as the high-quality algorithm, and the first descriptive indicator obtained by the high-quality algorithm is determined as the descriptive indicator, thereby improving the accuracy of the descriptive indicator. Based on the descriptive indicator, prediction accuracy is improved.

[0017] Optionally, the step of predicting the data to be tested based on the descriptive indicators to obtain prediction results includes: determining project attribute indicators based on the descriptive indicators, wherein the project attribute indicators are indicators related to project attributes. The risk project data is clustered based on the project attribute indicators to obtain at least one category, wherein the risk project data in each category have similar project attributes; A vector autoregressive model is trained based on at least one of the aforementioned categories and the corresponding risk project data; The trained vector autoregressive model is used to predict the test data to obtain the prediction results.

[0018] By adopting the above technical solution, the risk project data is clustered, and a vector autoregressive model is trained according to the category, which makes the model have better generalization ability and the prediction based on the model has higher accuracy.

[0019] Secondly, this application provides a data analysis device for infrastructure construction projects, which adopts the following technical solution: A data analysis device for infrastructure construction projects, comprising: The data acquisition module is used to acquire historical data and data to be tested, wherein the historical data is historical project data and the data to be tested is the project data to be predicted; The first determining module is used to determine effective indicators based on the historical data, wherein the effective indicators are indicators related to the risks of the project. The second determining module is used to determine a descriptive indicator based on the effective indicator and multiple machine learning algorithms. The descriptive indicator is an indicator used to describe risky projects, and the risky project is a project that is at risk. The data prediction module is used to predict the data to be tested based on the descriptive index and obtain the prediction result; The risk warning module is used to issue risk warnings based on the prediction results.

[0020] By adopting the above technical solution, indicators related to project risks, i.e., effective indicators, are determined based on historical data. Based on the effective indicators and machine learning algorithms, indicators describing risky projects are determined, making the determination of descriptive indicators more scientific and reasonable. Based on these descriptive indicators, predictions are made on the data to be tested, and the prediction results are more accurate, enabling more timely detection of risks and early warning.

[0021] Thirdly, this application provides an electronic device that adopts the following technical solution: An electronic device includes a processor coupled to a memory; The memory stores a computer program that can be loaded by a processor and executed as a data analysis method for infrastructure construction projects according to any one of the first aspects.

[0022] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium storing a computer program capable of being loaded by a processor and executing the data analysis method for infrastructure construction projects as described in any of the first aspects. Attached Figure Description

[0023] Figure 1 This is a flowchart illustrating a data analysis method for infrastructure construction projects provided in an embodiment of this application.

[0024] Figure 2 This is a structural block diagram of a data analysis device 200 for an infrastructure construction project provided in an embodiment of this application.

[0025] Figure 3 This is a structural block diagram of the electronic device 300 provided in the embodiments of this application. Detailed Implementation

[0026] The present application will be further described in detail below with reference to the accompanying drawings.

[0027] This application provides a data analysis method for infrastructure construction projects. This data analysis method can be executed by an electronic device, which can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet computer, desktop computer, etc., but is not limited to these.

[0028] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0029] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0030] like Figure 1 As shown, a data analysis method for infrastructure construction projects is described below, with the main process flow as follows (steps S101 to S105): Step S101: Obtain historical data and data to be tested.

[0031] Historical data refers to historical project data, while data to be tested refers to project data to be predicted. Project leaders upload project data to the database in real time, so the database stores all project data. Historical project data and data to be predicted are retrieved from the database.

[0032] Step S102: Determine effective indicators based on historical data.

[0033] Among them, the effective indicators are those related to the risks of the project.

[0034] Specifically, determining effective indicators based on historical data includes: determining risk project data based on historical data, where risk project data refers to data of risk projects; determining a first evaluation indicator based on risk project data, where the first evaluation indicator is an indicator that the null value rate is less than a preset null value rate; and determining effective indicators based on the first evaluation indicator.

[0035] If a construction project experiences a profit margin lower than the target profit margin for three consecutive months during its execution, the project is considered to be at risk. Data from the three months preceding the risk is marked as risky project data. Data with this risk mark is retrieved from historical data and used as risky project data. Multiple sets of risky project data exist, each set representing a single project and a specific time point. Each set is described by multiple indicators, such as: measured output value rate, balance of accounts receivable and payable, project region, and project type. Statistical analysis is performed on each set of risky project data. Indicators with a blank value rate lower than a preset blank value rate are designated as the primary evaluation indicators. The preset blank value rate is manually set in advance and can be 3% or 2%, without specific limitations. Indicators related to the project's risk are selected from these primary evaluation indicators as valid indicators.

[0036] Specifically, determining effective indicators based on a first evaluation index includes: determining the data type of the first evaluation index, which may include continuous or discrete types; if the data type of the first evaluation index is continuous, then determining a risk threshold based on a genetic optimization algorithm, where the risk threshold is the critical value at which the first evaluation index triggers a risk item; and calculating a first probability based on a first formula, which includes: Wherein, P(risk item | indicator value falls within the risk range) is the first probability, the risk range is the range determined based on the risk threshold, and the indicator value is the value corresponding to the first evaluation indicator; the effective indicator is determined based on the first probability and the probability of the risk item, the probability of the risk item is the probability of the risk item among all items, and all items include risk items and normal items.

[0037] In this embodiment, each first evaluation indicator corresponds to a data type. If the first evaluation indicator is a numerical indicator, then the data type of the first evaluation indicator is continuous. For example, the data types of the measured output value rate and the balance of the two funds are both continuous. If the first evaluation indicator is a categorical indicator, then the data type of the first evaluation indicator is discrete. For example, the data types of the project area and the project type are both discrete.

[0038] If the data type of the first evaluation indicator is continuous, then the critical value at which the data corresponding to the first evaluation indicator touches the risk project is calculated based on historical data and the genetic optimization algorithm. The genetic optimization algorithm can calculate the critical value, i.e., the risk threshold, for a single indicator among many construction projects. The first probability is calculated according to the above-mentioned conditional probability formula. The risk range is determined based on the business logic of the first evaluation indicator and the risk threshold. If the business logic of the first evaluation indicator is that the larger the better, for example, the business logic of the output value rate is that the larger the better, then the risk range is the range represented by the indicator value of the first evaluation indicator being less than the risk threshold. If the business logic of the first evaluation indicator is that the smaller the better, for example, the business logic of the contract asset balance is that the smaller the better, then the risk range is the range represented by the indicator value of the first evaluation indicator being greater than the risk threshold.

[0039] If the calculated first probability is greater than the probability of the risky project, then the first evaluation indicator is a valid indicator; otherwise, the first evaluation indicator is not a valid indicator.

[0040] Furthermore, after determining the data type of the first evaluation indicator, the method also includes: if the data type of the first evaluation indicator is discrete, then the correlation between the first evaluation indicator and the risk project is determined based on the chi-square test; if the correlation is greater than the preset correlation, then the first evaluation indicator is determined as the second evaluation indicator, the second evaluation indicator is an indicator with a discrete data type and a correlation with the risk project that is higher than the preset correlation; and effective indicators are determined based on the second evaluation indicator.

[0041] In this embodiment, if the data type of the first evaluation indicator is discrete, the correlation between the first evaluation indicator and the risk project is calculated using a chi-square test. For example, taking the first evaluation indicator as a bridge, the chi-square test is calculated as follows: Table 1. Statistics on Bridges and Risk Projects Chi-square test table Bridge project Non-bridge projects sum Normal Project a b a+b Risky projects c d c+d sum a+c b+d n Where n = a + b + c + d.

[0042] The formula for calculating the chi-square test is: p represents the correlation between the first evaluation indicator and the risk project. If p is greater than the preset correlation, that is, the first evaluation indicator is highly correlated with the risk project, then the first evaluation indicator is determined as the second evaluation indicator, and an effective indicator is determined based on the second evaluation indicator. The preset correlation is a pre-set value, which can be 0.05.

[0043] Specifically, determining effective indicators based on the second evaluation index includes: calculating the second probability based on the second formula, which includes: Wherein, P (second evaluation index | risk item) is the second probability; effective indicators are determined based on the second probability and the probability of risk items.

[0044] In this embodiment, the second probability is calculated using the second formula, and then compared with the probability of the risky project. If the second probability is greater than the probability of the risky project, the second evaluation index is determined to be an effective index; otherwise, the second evaluation index is not an effective index.

[0045] Step S103: Determine descriptive metrics based on effective metrics and multiple machine learning algorithms.

[0046] Among them, the descriptive indicators are those used to describe risky projects.

[0047] Specifically, the descriptive metrics are determined based on effective metrics and multiple machine learning algorithms, including: determining multiple first descriptive metrics based on multiple machine learning algorithms, effective metrics, and historical data, wherein the first descriptive metrics are descriptive metrics calculated by machine learning algorithms; calculating the accuracy of each machine learning algorithm based on the confusion matrix and multiple first descriptive metrics; selecting a pre-set number of machine learning algorithms with high accuracy as high-quality algorithms; and determining descriptive metrics based on high-quality algorithms.

[0048] In this embodiment, effective indicators and corresponding historical data are calculated using multiple machine learning models to obtain multiple first descriptive indicators. Each machine learning model can obtain multiple first descriptive indicators to describe risky projects. Machine learning models include, but are not limited to, KNN classification algorithm (K Nearest Neighbors), Random Forest algorithm, Adaboost algorithm, Gradient Boosting Regression Tree algorithm, Support Vector Regression, Least Angle Regression algorithm, Decision Tree algorithm, Linear Regression algorithm, and Ridge Regression algorithm. The accuracy of the first descriptive indicators calculated by each machine learning algorithm is calculated using a confusion matrix. The machine learning algorithms are ranked from high to low according to their accuracy, and a preset number of machine learning algorithms with the highest accuracy are selected as high-quality algorithms. The multiple first descriptive indicators calculated by the high-quality algorithms are determined as descriptive indicators. The preset number can be 4 or 3, and is not specifically limited here.

[0049] Step S104: Make predictions based on descriptive indicators to obtain prediction results.

[0050] Specifically, the prediction of the test data based on descriptive indicators to obtain prediction results includes: determining project attribute indicators based on descriptive indicators, wherein the project attribute indicators are indicators related to project attributes; clustering the risk project data based on the project attribute indicators to obtain at least one category, wherein the risk project data in each category have similar project attributes; training a vector autoregressive model based on at least one category and the corresponding risk project data; and predicting the test data based on the trained vector autoregressive model to obtain prediction results.

[0051] In this embodiment, the project attribute database stores indicators related to project attributes. The indicators that exist in the project attribute database from the descriptive indicators are determined as project attribute indicators, that is, indicators related to project attributes are selected from the descriptive indicators, such as: project location, company to which the project belongs, and contract amount, etc. The risk project data is clustered according to the project attribute indicators by a hierarchical clustering algorithm, so that the risk project data in each category have similar project attributes. The vector autoregression model is trained based on at least one category and the corresponding risk project data. The trained vector autoregression model is used to predict the test data to obtain the prediction results. The prediction results include whether the test data has risks or not.

[0052] Step S105: Conduct risk warning based on prediction results.

[0053] If the prediction result indicates that the data to be tested is at risk, a risk warning will be issued so that relevant personnel can deal with the risk in a timely manner; if the prediction result indicates that the data to be tested is not at risk, no risk warning is required.

[0054] Figure 2 This is a structural block diagram of a data analysis device 200 for an infrastructure construction project provided in an embodiment of this application.

[0055] like Figure 2 As shown, the data analysis device 200 for infrastructure construction projects mainly includes: The data acquisition module 201 is used to acquire historical data and data to be tested. The historical data is historical project data, and the data to be tested is project data to be predicted. The first determination module 202 is used to determine effective indicators based on historical data. The effective indicators are those related to the risks of the project. The second determining module 203 is used to determine descriptive indicators based on effective indicators and multiple machine learning algorithms. The descriptive indicators are used to describe risky projects, and risky projects are projects that are at risk. The data prediction module 204 is used to predict the data to be tested based on descriptive indicators and obtain the prediction results. The risk warning module 205 is used to provide risk warnings based on the prediction results.

[0056] As an optional implementation of this embodiment, the first determining module 202 is further specifically used to determine effective indicators based on historical data, including: determining risk project data based on historical data, wherein the risk project data is data of risk projects; determining a first evaluation indicator based on the risk project data, wherein the first evaluation indicator is an indicator whose null value rate is less than a preset null value rate; and determining effective indicators based on the first evaluation indicator.

[0057] As an optional implementation of this embodiment, the first determining module 202 is further specifically used to determine an effective indicator based on a first evaluation indicator, including: determining the data type of the first evaluation indicator, the data type including continuous and discrete types; if the data type of the first evaluation indicator is continuous, then determining a risk threshold based on a genetic optimization algorithm, the risk threshold being the critical value at which the first evaluation indicator touches a risk item; calculating a first probability based on a first formula, the first formula including: Wherein, P(risk item | indicator value falls within the risk range) is the first probability, the risk range is the range determined based on the risk threshold, and the indicator value is the value corresponding to the first evaluation indicator; the effective indicator is determined based on the first probability and the probability of the risk item, the probability of the risk item is the probability of the risk item among all items, and all items include risk items and normal items.

[0058] As an optional implementation of this embodiment, the first determining module 202 is further configured to, after determining the data type of the first evaluation indicator, include: if the data type of the first evaluation indicator is discrete, then determine the correlation between the first evaluation indicator and the risk project based on the chi-square test; if the correlation is greater than a preset correlation, then determine the first evaluation indicator as a second evaluation indicator, wherein the second evaluation indicator is an indicator whose data type is discrete and whose correlation with the risk project is higher than the preset correlation; and determine an effective indicator based on the second evaluation indicator.

[0059] As an optional implementation of this embodiment, the first determining module 202 is further specifically used to determine an effective indicator based on a second evaluation index, including: calculating a second probability based on a second formula, the second formula including: Wherein, P (second evaluation index | risk item) is the second probability; effective indicators are determined based on the second probability and the probability of risk items.

[0060] As an optional implementation of this embodiment, the second determining module 203 is further specifically used to determine descriptive indicators based on effective indicators and multiple machine learning algorithms, including: determining multiple first descriptive indicators based on multiple machine learning algorithms, effective indicators and historical data, wherein the first descriptive indicators are descriptive indicators calculated by machine learning algorithms; calculating the accuracy of each machine learning algorithm based on the confusion matrix and multiple first descriptive indicators; selecting a preset number of machine learning algorithms with high accuracy as high-quality algorithms; and determining descriptive indicators based on high-quality algorithms.

[0061] As an optional implementation of this embodiment, the data prediction module 204 is further specifically used to predict the data to be tested based on descriptive indicators to obtain prediction results, including: determining project attribute indicators based on descriptive indicators, wherein the project attribute indicators are indicators related to project attributes; clustering the risk project data based on the project attribute indicators to obtain at least one category, wherein the risk project data in each category have similar project attributes; training a vector autoregressive model based on at least one category and the corresponding risk project data; and predicting the data to be tested based on the trained vector autoregressive model to obtain prediction results.

[0062] In one example, the module in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0063] For example, when modules in a device can be implemented via a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling programs. Alternatively, these modules can be integrated together as a system-on-a-chip (SOC).

[0064] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0065] Figure 3 This is a structural block diagram of an electronic device 300 provided in an embodiment of this application.

[0066] like Figure 3 As shown, the electronic device 300 includes a processor 301 and a memory 302, and may further include one or more of an information input / output (I / O) interface 303, a communication component 304, and a communication bus 305.

[0067] The processor 301 controls the overall operation of the electronic device 300 to complete all or part of the steps of the data analysis method for the aforementioned infrastructure construction project. The memory 302 stores various types of data to support the operation of the electronic device 300. This data may include, for example, instructions for any application or method operating on the electronic device 300, as well as application-related data. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as one or more of Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0068] I / O interface 303 provides an interface between processor 301 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 304 is used for wired or wireless communication between electronic device 300 and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 304 may include a Wi-Fi component, a Bluetooth component, and an NFC component.

[0069] The electronic device 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the data analysis method for infrastructure construction projects given in the above embodiments.

[0070] The communication bus 305 may include a path for transmitting information between the aforementioned components. The communication bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 305 can be divided into an address bus, a data bus, a control bus, etc.

[0071] Electronic device 300 may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers, and may also be servers.

[0072] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described data analysis method for infrastructure construction projects.

[0073] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0074] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0075] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. A method of data analysis for capital construction projects, characterized by, include: Acquire historical data and data to be tested, wherein the historical data is historical project data and the data to be tested is the project data to be predicted; Based on the historical data, effective indicators are determined, and these effective indicators are those related to the risks associated with the project. The determination of effective indicators based on the historical data includes: Risk project data is determined based on the historical data, and the risk project data is the data of the risk project. Based on the risk project data, a first evaluation indicator is determined, wherein the first evaluation indicator is an indicator that the null value rate is less than a preset null value rate; The effective indicators are determined based on the first evaluation index; The step of determining the effective indicator based on the first evaluation indicator includes: Determine the data type of the first evaluation index, wherein the data type includes continuous and discrete types; If the data type of the first evaluation index is continuous, then the risk threshold is determined based on the genetic optimization algorithm, and the risk threshold is the critical value at which the first evaluation index touches the risk item; The first probability is calculated based on the first formula, which includes: ; wherein, is the first probability, the risk interval is an interval determined based on the risk threshold, and the indicator value is a numerical value corresponding to the first evaluation indicator. Based on the first probability and the probability of risky items, an effective indicator is determined. The probability of risky items is the probability of the risky item among all items, and all items include the risky item and normal items. After determining the data type of the first evaluation index, the method further includes: If the data type of the first evaluation indicator is discrete, the correlation between the first evaluation indicator and the risk project is determined based on the chi-square test. If the correlation is greater than the preset correlation, the first evaluation index is determined as the second evaluation index. The second evaluation index is an index whose data type is discrete and whose correlation with the risk project is higher than the preset correlation. The effective indicators are determined based on the second evaluation index; The determination of the effective indicator based on the second evaluation indicator includes: The second probability is calculated based on the second formula, which includes: ; in, This is the second probability; The effective indicator is determined based on the second probability and the probability of the risky project. Based on the effective indicators and multiple machine learning algorithms, descriptive indicators are determined. These descriptive indicators are used to describe risky projects, and the risky projects are projects that are at risk. The process of determining descriptive metrics based on the effective metrics and multiple machine learning algorithms includes: Multiple first descriptive indicators are determined based on multiple machine learning algorithms, the effective indicators, and the historical data, wherein the first descriptive indicators are the descriptive indicators calculated by the machine learning algorithms; The accuracy of each of the machine learning algorithms is calculated based on the confusion matrix and multiple first descriptive metrics. A predetermined number of machine learning algorithms with high accuracy are selected as high-quality algorithms; The descriptive metrics are determined based on the aforementioned high-quality algorithm; Based on the described indicators, the test data is predicted to obtain the prediction result; Risk warnings will be issued based on the prediction results.

2. The method according to claim 1, characterized in that, The step of predicting the data to be tested based on the descriptive index to obtain the prediction result includes: Project attribute indicators are determined based on the descriptive indicators, and the project attribute indicators are indicators related to project attributes. The risk project data is clustered based on the project attribute indicators to obtain at least one category, wherein the risk project data in each category have similar project attributes; A vector autoregressive model is trained based on at least one of the aforementioned categories and the corresponding risk project data; The trained vector autoregressive model is used to predict the test data to obtain the prediction results.

3. A data analysis device for infrastructure construction projects, characterized in that, For implementing the method of claim 1, comprising: The data acquisition module is used to acquire historical data and data to be tested, wherein the historical data is historical project data and the data to be tested is the project data to be predicted; The first determining module is used to determine effective indicators based on the historical data, wherein the effective indicators are indicators related to the risks of the project. The second determining module is used to determine a descriptive indicator based on the effective indicator and multiple machine learning algorithms. The descriptive indicator is an indicator used to describe risky projects, and the risky project is a project that is at risk. The data prediction module is used to predict the data to be tested based on the descriptive index and obtain the prediction result; The risk warning module is used to issue risk warnings based on the prediction results.

4. An electronic device, characterized in that, Includes a processor, which is coupled to a memory; The processor is configured to execute a computer program stored in the memory, causing the electronic device to perform the method as described in any one of claims 1 to 2.

5. A computer-readable storage medium, characterized in that, It includes a computer program or instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1 to 2.

Citation Information

Patent Citations

  • Method and device for evaluating software project risks

    CN103208039A

  • Project risk prediction method and system based on project research and development process

    CN112465011A