Engineering project data early warning method and device

Abstract

The invention relates to the technical field of engineering project data early warning, and discloses an engineering project data early warning method and device, and the method comprises the steps: obtaining various original project data of a target engineering project, carrying out the data cleaning of the various original project data, and obtaining the progress data of the target project, the fund data of the target project, and the contract data of the target project; respectively calculating project risk alarm values corresponding to the target project progress data, the target project fund data and the target project contract data; and performing risk early warning on target project data corresponding to the project risk warning value, and predicting a project risk prediction value corresponding to the target project data through a trained project risk early warning model. Therefore, the project data of various different types of the target engineering project can be predicted efficiently and accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering project data early warning, and in particular to an engineering project data early warning method and device. Background Art

[0002] Engineering project data refers to various information and values ​​generated in various stages of engineering project planning, design, construction, operation, etc. These data are crucial for the successful implementation, cost control, quality assurance and subsequent maintenance of the project.

[0003] Related technologies, traditional engineering project data management methods often rely on manual collection and processing of data. This method is not only inefficient, but also easily affected by human factors. The actual project progress is difficult to grasp in real time and accurately, which in turn affects the prediction results of the engineering project. Summary of the invention

[0004] In view of this, the present invention provides a project data early warning method and device to solve the problem that traditional project data management methods often rely on manual collection and processing of data, resulting in inaccurate and low efficiency in project data prediction.

[0005] In a first aspect, an embodiment of the present disclosure provides a project data early warning method, the method comprising:

[0006] Acquire various original project data of the target project, including original project schedule data, original project funding data and original project contract data;

[0007] Clean various original project data to obtain target project progress data, target project funding data and target project contract data;

[0008] Calculate the project risk warning values ​​corresponding to the target project progress data, target project funding data and target project contract data respectively;

[0009] Issue risk warning for target project data corresponding to the project risk warning value.

[0010] The disclosed embodiment obtains a variety of original project data of the target engineering project, including original project progress data, original project funding data, and original project contract data; performs data cleaning on the various original project data to obtain target project progress data, target project funding data, and target project contract data; calculates project risk warning values ​​corresponding to the target project progress data, target project funding data, and target project contract data, respectively; and performs risk warning on the target project data corresponding to the project risk warning value. Finally, the disclosed embodiment can efficiently and accurately predict various types of data of the engineering project.

[0011] In some optional implementations, data cleaning is performed on a plurality of original project data to obtain target project data from the plurality of original project data, including:

[0012] Determine the initial value of the data window according to the influencing factors of the data window;

[0013] Match the data set in the data window, and determine whether to adjust the size of the data window based on the matching result;

[0014] According to the step length calculation formula, determine the adjustment step length of the data window;

[0015] Perform word segmentation, similar word extraction, and conjunction extraction on the data window, assign the word segmentation weight value M1, the similar word weight value M2, and the conjunction weight value M3 in turn, and confirm whether the data is similar data;

[0016] After deduplication of similar data, target project data from a variety of original project data is obtained.

[0017] The embodiments of the present disclosure are helpful to ensure the accuracy of data by performing the above-mentioned specific data cleaning actions.

[0018] In some optional implementations, the disclosed embodiments provide a project data early warning method, which calculates the project risk warning value corresponding to the target project progress data by the following formula:

[0019]

[0020] Among them, R1 is the risk warning value of project progress overtime, P a is the actual progress value of the target project, P b Plan progress values ​​for target projects;

[0021] The project risk warning value corresponding to the target project funding data is calculated using the following formula;

[0022]

[0023] Among them, R2 is the risk warning value of excess project funds, C a is the cumulative expenditure value of project funds, C b Plan investment value for project funds;

[0024] The project risk warning value corresponding to the target project contract data is calculated using the following formula;

[0025]

[0026] Among them, R3 is the risk warning value of project contract funds, C d is the actual payment value of the project contract, Ce The contractually agreed payment value for the project.

[0027] The disclosed embodiment can accurately calculate the project risk warning value corresponding to the target project progress data, the project risk warning value corresponding to the target project funding data, and the project risk warning value corresponding to the target project contract data through the above method.

[0028] In some optional implementations, performing risk warning on target project data corresponding to the project risk warning value includes:

[0029] If the project risk warning value is greater than the preset threshold, a risk warning is issued for the target project data corresponding to the project risk warning value;

[0030] If the project risk warning value is less than or equal to the preset threshold, it is determined that the target project data corresponding to the project risk warning value is in a safe state.

[0031] The disclosed embodiment can timely determine whether target project data has risks through conditional judgment of specific project risk warning values, and issue risk warnings for target project data with risks.

[0032] In some optional implementations, the present disclosure provides a project data early warning method, further comprising:

[0033] Selecting part of the data from a variety of original project data as sample data, extracting a first data feature from the sample data, using the first data feature to train a project risk early warning model, generating a project risk prediction result corresponding to the sample data, and a loss function value between the first data feature and the project risk prediction result, wherein the loss function is used to update the project risk early warning model;

[0034] A second data feature is extracted from the target project data, and the second data feature is input into a project risk early warning model for prediction, so as to obtain a project risk prediction value of the target project data.

[0035] The disclosed embodiment predicts the project risk prediction value corresponding to the target project data through a trained project risk warning model, which is conducive to efficiently and accurately predicting various types of project data of the target engineering project.

[0036] In some optional implementations, the present disclosure provides a project data early warning method, further comprising:

[0037] Based on the project risk warning value and the project risk prediction value, risk warning information of the target project data is obtained, wherein the risk warning information is used to characterize the abnormal situation of the target project data;

[0038] Based on the risk warning information of the target project data, analyze the target project data to obtain the abnormal reasons for the abnormal project data;

[0039] Send project risk warning values, project risk prediction values ​​and abnormal reasons for project abnormal data to the target user end.

[0040] The disclosed embodiment further analyzes the abnormal causes of project abnormal data based on the project risk warning value and the project risk prediction value, and informs the target user, so that the target user can promptly know the risk status of the target project data and the abnormal causes of the project abnormal data, and formulate response measures in time.

[0041] In a second aspect, an embodiment of the present disclosure provides a project data early warning device, the device comprising:

[0042] A data acquisition module is used to acquire various original project data of a target engineering project, including original project schedule data, original project funding data, and original project contract data;

[0043] The data cleaning module is used to clean various original project data to obtain target project progress data, target project funding data and target project contract data;

[0044] A data calculation module, used to calculate the project risk warning values ​​corresponding to the target project progress data, the target project funding data and the target project contract data respectively;

[0045] The early warning execution module is used to issue risk warnings to target project data corresponding to project risk warning values.

[0046] In a third aspect, an embodiment of the present disclosure provides a computer device, including:

[0047] The memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the engineering project data early warning method of the first aspect or any corresponding implementation method thereof by executing the computer instructions.

[0048] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the engineering project data early warning method of the first aspect or any corresponding embodiment thereof.

[0049] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including computer instructions, which are used to enable a computer to execute the engineering project data early warning method of the above-mentioned first aspect or any corresponding implementation method thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 is a flow chart of a method for early warning of engineering project data according to an embodiment of the present invention;

[0052] Figure 2 is a flow chart of another engineering project data early warning method according to an embodiment of the present invention;

[0053] Figure 3 is a structural block diagram of an engineering project data early warning device according to an embodiment of the present invention;

[0054] Figure 4 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0056] According to an embodiment of the present invention, an embodiment of an engineering project data early warning method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0057] In this embodiment, a project data early warning method is provided, which can be used for computer devices such as mobile phones, mobile terminals, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 1 is a flow chart of a project data early warning method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0058] Step S101, obtaining a variety of original project data of a target engineering project, wherein the various original project data include: original project progress data, original project funding data and original project contract data.

[0059] Specifically, the various original project data may be multiple data sources involved in the project early warning system, for example, the original project progress data includes: actual project progress data, project planned progress data; the original project funding data includes: project funding cumulative expenditure data, project funding planned investment data; the original project contract data includes: project contract actual payment data, project contract agreed payment data. These various original project data in the embodiments of the present disclosure can be obtained through one or more methods in Word documents and / or PDF documents and / or Excel documents, and the various original project data mentioned above can be parsed from these documents.

[0060] Step S102, performing data cleaning on various original project data to obtain target project progress data, target project funding data and target project contract data.

[0061] In some optional implementations, the above step S102, performing data cleaning on a variety of original project data to obtain target project progress data, target project funding data and target project contract data, includes:

[0062] Step a1, determining the initial value of the data window according to the influencing factors of the data window.

[0063] Specifically, the data window refers to a time period or spatial range set for data collection and analysis, and the initial value is a preset value of the data window.

[0064] Step a2, matching the data set in the data window, and determining whether to adjust the size of the data window according to the matching result.

[0065] Specifically, suppose the data set in the data window is {E m , E m+1 , ..., E m+n}, the data set is the various original project data mentioned above, and each data in the data set is compared with E m Compare and calculate (E m , E m+1 ) has a similarity of Sim1; when compared to E m+n , if (E m , E m+n ) n >T1, then according to the comparison result Sim n Expand the data window; if (E m , E m+n ) n <T2, then according to the comparison result Sim nReduce the data window, where T1 is the minimum similarity threshold of the data window value and T2 is the maximum similarity threshold of the data window value.

[0066] Step a3: Determine the adjustment step size of the data window according to the step size calculation formula.

[0067] Specifically, determine the size of the data window, and calculate (E m , E m+n ) in the similarity of the mth and m+nth window values; and then further determine whether to increase the minimum similarity threshold of the window value.

[0068] Among them, the enlarged step size formula is expressed by the following formula:

[0069]

[0070] Among them, W1 is the number of steps of expansion, T1 is the minimum similarity threshold of the data window value, Sim(E m ,E m+n ) is the similarity of the data window value, W a is the step length.

[0071] Among them, the formula for reducing the step size is expressed by the following formula:

[0072]

[0073] Among them, W1 is the number of steps to reduce, T2 is the minimum similarity threshold of the data window value, Sim(E m ,E m+n ) is the similarity of the data window value, W a Step length

[0074] Step a4, perform word segmentation, similar word extraction, and conjunction extraction on the data window, assign the word segmentation weight value M1, the similar word weight value M2, and the conjunction weight value M3 in turn, and confirm whether the data is similar data.

[0075] Specifically, whether the data is similar is determined by the following formula:

[0076] Sim e (d1, d2) = M1*Sim M1 (d1,d2)+M1*Sim M2 (d1,d2)+M1*Sim M3 (d1,d2)

[0077] Among them, (d1, d2) are two different target project data, Sim e (d1, d2) are the similarity results corresponding to two different target project data.

[0078] Step a5, after removing duplicates from similar data, the target project data from the various original project data is obtained.

[0079] After executing the above steps a1 to a5, the embodiment of the present disclosure can achieve accurate cleaning of the above original project progress data, original project funding data and original project contract data, and thus obtain relatively accurate target project progress data, target project funding data and target project contract data.

[0080] Step S103, respectively calculating the project risk warning values ​​corresponding to the target project progress data, the target project funding data and the target project contract data.

[0081] In some optional implementations, the project risk warning value corresponding to the target project progress data is calculated by the following formula:

[0082]

[0083] Among them, R1 is the risk warning value of project progress overtime, P a is the actual progress value of the target project, P b Plan progress values ​​for target projects;

[0084] The project risk warning value corresponding to the target project funding data is calculated using the following formula;

[0085]

[0086] Among them, R2 is the risk warning value of excess project funds, C a is the cumulative expenditure value of project funds, C b Plan investment value for project funds;

[0087] The project risk warning value corresponding to the target project contract data is calculated using the following formula;

[0088]

[0089] Among them, R3 is the risk warning value of project contract funds, C d is the actual payment value of the project contract, C e The contractually agreed payment value for the project.

[0090] Step S104: issuing a risk warning for the target project data corresponding to the project risk warning value.

[0091] In some optional implementations, the above step S104, performing risk warning on the target project data corresponding to the project risk warning value, includes:

[0092] Step b1: If the project risk warning value is greater than a preset threshold, a risk warning is issued for the target project data corresponding to the project risk warning value.

[0093] Step b2: if the project risk warning value is less than or equal to the preset threshold, determine that the target project data corresponding to the project risk warning value is in a safe state.

[0094] Specifically, for example, for the target project progress data, when the project progress exceeds the preset threshold, the risk warning value is greater than the preset threshold, indicating that the current project progress risk is relatively high, and the target project progress data corresponding to the project risk warning value is subjected to risk warning. For example, when the risk warning value of the project progress exceeds the preset threshold, it indicates that the current project progress risk is relatively low, and the target project progress data is determined to be in a safe state. Similarly, for example, for the target project funding data, when the project funding exceeds the preset threshold, the risk warning value is greater than the preset threshold, indicating that the current project funding risk is relatively high, and the target project funding data corresponding to the project risk warning value is subjected to risk warning. For example, when the risk warning value of the project funding exceeds the preset threshold, it indicates that the current project funding risk is relatively low, and the target project funding data is determined to be in a safe state. Similarly, for the target project contract data, when the risk warning value of the project contract excess is greater than the preset threshold, it indicates that the current project contract risk is relatively high, and the target project contract data corresponding to the project risk warning value is subjected to risk warning. For example, when the risk warning value of the project contract funding is less than or equal to the preset threshold, it indicates that the current project contract risk is relatively low, and the target project contract data is determined to be in a safe state.

[0095] Therefore, the engineering project data early warning method in the disclosed embodiment obtains a variety of original project data of the target engineering project, and the various original project data include: original project progress data, original project funding data and original project contract data; performs data cleaning on the various original project data to obtain target project progress data, target project funding data and target project contract data; calculates the project risk warning values ​​corresponding to the target project progress data, target project funding data and target project contract data respectively; and performs risk warning on the target project data corresponding to the project risk warning value. Finally, the disclosed embodiment can efficiently and accurately predict various types of data of the engineering project.

[0096] In this embodiment, a project data early warning method is provided, which can be used for computer devices such as mobile phones, mobile terminals, tablet computers, desktop computers, portable notebooks, servers, etc. Figure 2 is a flow chart of a project data early warning method according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0097] Step S201, select part of the data from a variety of original project data as sample data, and extract the first data feature from the sample data, use the first data feature to train the project risk warning model, generate the project risk prediction result corresponding to the sample data, and the loss function value between the first data feature and the project risk prediction result, and the loss function is used to update the project risk warning model.

[0098] Specifically, the sample data is historical application data selected from a variety of original project data in an engineering project early warning scenario. The sample data is feature extracted by some feature extraction algorithms to obtain a first data feature. For example, the feature extraction algorithm may be a radial basis function neural network algorithm (RBF network algorithm) or a long short-term memory network (LSTM network algorithm), or a recurrent neural network (RNN network algorithm). When the feature extraction algorithm is an RBF network algorithm, the corresponding project risk early warning model is an RBF network model. When the feature extraction algorithm is an LSTM network algorithm, the corresponding project risk early warning model is an LSTM network model. When the feature extraction algorithm is an RNN network algorithm, the corresponding project risk early warning model is an RNN network model. The first data feature is used to train the project risk early warning model. In order to obtain the project risk prediction result corresponding to the sample data and the loss function value between the first data feature and the project risk prediction result, the loss function is used to update the project risk early warning model. The trained neural network model is conducive to accurately and efficiently predicting various types of project data of the target engineering project.

[0099] Specifically, in the embodiment of the present disclosure, the preferred project risk warning model is an LSTM network model. The LSTM network can learn long-term dependent information. The LSTM network model has good generalization when using training sequences of regular languages ​​and simple non-regular languages. The LSTM network model has shown certain capabilities and success in dealing with complex problems with long-term characteristics and has been widely used. The LSTM network model can learn long-term information, is suitable for processing time series data, and can easily extract abstract, high-level information or metrics from sequential data. It has internal feedback connections and can be used to classify, process and predict time series data. Each unit in the LSTM network model consists of three information flow regulators: a forget gate, an input gate and an output gate. After training, the input gate controls which inputs are important enough. The forget gate determines how long the state memory should be retained and how to add new information from the current input to the unit state, and the output gate determines how much memory is used to generate the output. Together, they allow the network to remember information from the past while discarding unnecessary information. It should be noted that, depending on the business scenario, the corresponding data features are also different, and the prediction model can be divided into a stationary type, a periodic type and a non-periodic type. The steady prediction model is a time series in which the mean and variance do not change systematically and the periodic changes are strictly eliminated. The periodic prediction model is a time series in which the mean and variance show periodic changes. The non-periodic prediction model is a time series in which the mean and variance do not change regularly. For example, taking the project progress data as an example, the general project progress data shows periodic changes with the weather conditions. When the weather is clear, the project progress will be fast and the risk of overtime will be small. When it is cloudy, the project progress will be relatively slow and the risk of overtime will be large. Therefore, the prediction model obtained by training the LSTM network model is a periodic prediction model.

[0100] Step S202: extracting a second data feature from the target project data, and inputting the second data feature into a project risk early warning model for prediction, thereby obtaining a project risk prediction value of the target project data.

[0101] Specifically, the target project data is the target project progress data, target project funding data and target project contract data after data cleaning processing, and some feature data representing the project progress, project funding and project contract are extracted from these target project data. The second data feature extraction method is the same as the first data feature extraction method, which will not be repeated here. Since the risk warning model has been pre-trained based on the sample data, the pre-trained project risk warning model can be directly used.

[0102] The disclosed embodiment executes the above steps S201-S202 to predict the project risk prediction value corresponding to the target project data through a pre-trained project risk warning model, which is conducive to efficiently and accurately predicting various types of project data of the target engineering project.

[0103] In some optional implementations, the engineering project data early warning method in the embodiment of the present disclosure further includes:

[0104] Step c1, based on the project risk warning value and the project risk prediction value, obtaining risk warning information of the target project data, wherein the risk warning information is used to characterize the abnormal situation of the target project data;

[0105] Step c2: Analyze the target project data based on the risk warning information of the target project data to obtain the abnormal reasons of the abnormal project data.

[0106] Specifically, the disclosed embodiment can combine the project risk warning value and the project risk prediction value of the target project data to obtain all the risk warning information of the target engineering project, and use the decision tree algorithm to classify and analyze all the risk warning information to obtain the abnormal reasons of the project abnormal data; the abnormal reasons of the project abnormal data are the root causes of the abnormal data, and there are many reasons for data abnormality. For example, the target project progress data is A, and the corresponding project risk warning value is R1. The reason for the generation of the project risk warning value may be weather reasons or arrears of employee wages, etc. These reasons are used as risk warning information related to the target project progress data; for example, the target project funding data is B, and the corresponding project risk warning value is R2. The reason for the generation of the project risk warning value may be too much purchase of engineering equipment or price increase of engineering land or price increase of purchased engineering materials, etc. These reasons are used as risk warning information related to the target project funding data. For example, the target project contract data is C, and the corresponding project risk warning value is R3. The reason for the generation of the project risk warning value may be the carelessness of the person issuing the contract or the lack of signatures of relevant personnel, etc. These reasons are used as risk warning information related to the target project contract data.

[0107] Therefore, in the disclosed embodiment, the decision tree is a decision analysis method that is based on the known probability of occurrence of various situations (various risk warning information) and is used to obtain the probability that the expected value of the net present value is greater than or equal to zero by constructing a decision tree, evaluate the data risk of the target project, and judge its feasibility. It is a graphical method that intuitively uses probability analysis. In machine learning, a decision tree is a prediction model that represents a mapping relationship between object attributes and object values. Here, the data anomaly is the object attribute, and the cause of the anomaly is the object value. The decision tree algorithm is used to obtain the mapping relationship between the data anomaly and the cause of the anomaly. Then determine the association between different risk anomaly causes. For example, if there is risk warning information D, risk warning information E and risk warning information F, the correlation between risk warning information D, risk warning information E and risk warning information F is obtained by the Apriori association mining algorithm and the FP-Growth frequent item set mining algorithm. If there is a correlation between risk warning information D, risk warning information E and risk warning information F, when one of the risk warning information is detected, risk warning information E and risk warning information F can be predicted. For example, if a timeout exception occurs in the target project progress data, risk warning information D is generated. At the same time, an overage exception occurs in the target project funding data, and risk warning information E is generated. Through the Apriori association mining algorithm and the FP-Growth frequent item set mining algorithm, it is obtained that the risk warning information D and the risk warning information E are associated. The risk warning information D and the risk warning information E generate an alarm strategy chain. When the risk warning information D is detected, the risk warning information E can be predicted according to the alarm strategy chain.

[0108] Step c3, sending the project risk warning value, project risk prediction value and abnormal reasons of the project abnormal data to the target user end.

[0109] Specifically, the project risk warning value, project risk prediction value and abnormal reasons of project abnormal data are sent to the target user end, so that the target user can timely learn the risk situation of the target project data and the abnormal reasons of the project abnormal data, and formulate response measures in time.

[0110] In the present embodiment, a project data early warning device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0111] This embodiment provides a project data early warning device, such as Figure 3 As shown, including:

[0112] The data acquisition module 301 is used to acquire various original project data of the target engineering project, wherein the various original project data include: original project progress data, original project funding data and original project contract data;

[0113] The data cleaning module 302 is used to clean various original project data to obtain target project progress data, target project funding data and target project contract data;

[0114] The data calculation module 303 is used to calculate the project risk warning values ​​corresponding to the target project progress data, the target project funding data and the target project contract data respectively;

[0115] The data warning module 304 is used to issue a risk warning to the target project data corresponding to the project risk warning value.

[0116] In some optional implementations, the data cleaning module 302 includes:

[0117] Determine the initial value of the data window according to the influencing factors of the data window;

[0118] Match the data set in the data window, and determine whether to adjust the size of the data window based on the matching result;

[0119] According to the step length calculation formula, determine the adjustment step length of the data window;

[0120] Perform word segmentation, similar word extraction, and conjunction extraction on the data window, assign the word segmentation weight value M1, the similar word weight value M2, and the conjunction weight value M3 in turn, and confirm whether the data is similar data;

[0121] After deduplication of similar data, target project data from a variety of original project data is obtained.

[0122] In some optional implementations, the disclosed embodiments provide a project data early warning device, which calculates the project risk warning value corresponding to the target project progress data by the following formula:

[0123]

[0124] Among them, R1 is the risk warning value of project progress overtime, P a is the actual progress value of the target project, P b Plan progress values ​​for target projects;

[0125] The project risk warning value corresponding to the target project funding data is calculated using the following formula;

[0126]

[0127] Among them, R2 is the risk warning value of excess project funds, Ca is the cumulative expenditure value of project funds, C b Plan investment value for project funds;

[0128] The project risk warning value corresponding to the target project contract data is calculated using the following formula;

[0129]

[0130] Among them, R3 is the risk warning value of project contract funds, C d is the actual payment value of the project contract, C e The contractually agreed payment value for the project.

[0131] In some optional implementations, the data warning module 304 includes:

[0132] The first execution submodule is used to issue a risk warning to the target project data corresponding to the project risk warning value if the project risk warning value is less than or equal to a preset threshold value;

[0133] The second execution submodule is used to determine that the target project data corresponding to the project risk warning value is in a safe state if the project risk warning value is less than or equal to a preset threshold.

[0134] In some optional implementations, the present disclosure provides an engineering project data early warning device, further comprising:

[0135] A data training module is used to select part of the data from a variety of original project data as sample data, extract a first data feature from the sample data, train a project risk early warning model using the first data feature, generate a project risk prediction result corresponding to the part of the data, and a loss function value between the first data feature and the project risk prediction result, and the loss function is used to update the project risk early warning model;

[0136] The feature prediction module is used to extract the second data feature from the target project data, and input the second data feature into the project risk early warning model for prediction to obtain the project risk prediction value of the target project data.

[0137] In some optional implementations, the present disclosure provides an engineering project data early warning device, further comprising:

[0138] An alarm information acquisition module is used to acquire risk alarm information of target project data based on the project risk alarm value and the project risk prediction value, wherein the risk alarm information is used to characterize abnormal conditions of the target project data;

[0139] The alarm information analysis module is used to analyze the target project data based on the risk alarm information of the target project data to obtain the abnormal reasons for the abnormal data of the project;

[0140] The alarm information sending module is used to send the project risk alarm value, project risk prediction value and the abnormal reason of the project abnormal data to the target user end.

[0141] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0142] The engineering project data early warning device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0143] An embodiment of the present invention further provides a computer device having the above-mentioned engineering project data early warning device.

[0144] See also Figure 4 , Figure 4 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 4 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 A processor 10 is taken as an example.

[0145] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0146] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0147] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0148] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0149] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0150] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0151] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0152] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A project data early warning method, characterized in that: The method comprises: Acquire a variety of original project data of the target engineering project, wherein the various original project data include: original project progress data, original project funding data, and original project contract data; Cleaning the various original project data to obtain target project progress data, target project funding data, and target project contract data; Respectively calculating the project risk warning values ​​corresponding to the target project progress data, the target project funding data, and the target project contract data; A risk warning is issued for the target project data corresponding to the project risk warning value.

2. The method according to claim 1, characterized in that Performing data cleaning on the multiple original project data to obtain target project data from the multiple original project data includes: Determine the initial value of the data window according to the influencing factors of the data window; Match the data set in the data window, and determine whether to adjust the size of the data window based on the matching result; According to the step length calculation formula, determine the adjustment step length of the data window; Perform word segmentation, similar word extraction, and conjunction extraction on the data window, assign the word segmentation weight value M1, the similar word weight value M2, and the conjunction weight value M3 in turn, and confirm whether the data is similar data; After deduplication of similar data, target project data among the multiple original project data is obtained.

3. The method according to claim 1, characterized in that The project risk warning value corresponding to the target project progress data is calculated by the following formula; Among them, R1 is the risk warning value of project progress overtime, P a is the actual progress value of the target project, P b Plan progress values ​​for target projects; The project risk warning value corresponding to the target project funding data is calculated by the following formula; Among them, R2 is the risk warning value of excess project funds, C a is the cumulative expenditure value of project funds, C b Plan investment value for project funds; The project risk warning value corresponding to the target project contract data is calculated by the following formula; Among them, R3 is the risk warning value of project contract funds, C d is the actual payment value of the project contract, C e The contractually agreed payment value for the project.

4. The method according to claim 1 or 3, characterized in that: Perform risk warning on the target project data corresponding to the project risk warning value, including: If the project risk warning value is greater than a preset threshold, a risk warning is issued for the target project data corresponding to the project risk warning value; If the project risk warning value is less than or equal to a preset threshold, it is determined that the target project data corresponding to the project risk warning value is in a safe state.

5. The method according to claim 1, characterized in that Also includes: Selecting part of the data from the multiple original project data as sample data, extracting a first data feature from the sample data, using the first data feature to train a project risk early warning model, generating a project risk prediction result corresponding to the part of the data, and a loss function value between the first data feature and the project risk prediction result, wherein the loss function is used to update the project risk early warning model; A second data feature is extracted from the target project data, and the second data feature is input into the project risk early warning model for prediction to obtain a project risk prediction value of the target project data.

6. The method according to claim 5, characterized in that Also includes: Based on the project risk warning value and the project risk prediction value, obtaining risk warning information of the target project data, wherein the risk warning information is used to characterize an abnormal situation of the target project data; Based on the risk warning information of the target project data, the target project data is analyzed to obtain the abnormal reasons of the abnormal project data; The project risk warning value, the project risk prediction value and the abnormal reason of the project abnormal data are sent to the target user terminal.

7. An engineering project data early warning device, characterized in that: The device comprises: A data acquisition module is used to acquire a variety of original project data of a target engineering project, wherein the various original project data include: original project progress data, original project funding data and original project contract data; A data cleaning module, used to clean the various original project data to obtain target project progress data, target project funding data and target project contract data; A data calculation module, used to respectively calculate the project risk warning values ​​corresponding to the target project progress data, the target project funding data and the target project contract data; The early warning execution module is used to issue a risk early warning to the target project data corresponding to the project risk warning value.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the engineering project data early warning method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the engineering project data early warning method according to any one of claims 1 to 6.

10. A computer program product, characterized in that It comprises computer instructions, and the computer instructions are used to enable a computer to execute the engineering project data early warning method according to any one of claims 1 to 6.

Images