Project construction period prediction method and system based on Bayesian network

Abstract

The invention relates to the technical field of detection and identification of small targets in images in the power industry, and provides a project period prediction method based on a Bayesian network and related equipment. The method comprises the following steps: splitting an item to be predicted into a plurality of WBS items, and constructing a Bayesian network of each WBS item; according to the key attribute of each item of WBS, obtaining historical data of a completed project, and calculating conditional probabilities of each item of WBS in different construction periods; according to the key attribute of each item of WBS and the same key attribute of a corresponding item in historical data, calculating the linear correlation probability of each item of WBS in different construction periods; according to the conditional probability and the linear correlation probability of each item of WBS, calculating the joint probability of each item of WBS in different construction periods; and the construction period corresponding to the highest value in the joint probability of each WBS item is selected as the predicted construction period of the WBS item, and the predicted construction periods of all the WBS items are accumulated to obtain the predicted construction period of the project, so that the accuracy of construction period prediction is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of project management, and in particular, to a project duration prediction method and system based on a Bayesian network. Background Art

[0002] The statements in this section merely provide background technical information related to the present invention and do not necessarily constitute prior art.

[0003] In the field of project management, the Work Breakdown Structure (WBS), as the cornerstone of project planning, the accuracy of its duration prediction directly determines the resource allocation efficiency, cost control accuracy, and risk response ability.

[0004] The current industry-wide duration prediction technology system still remains in the primary stage with individual experience-driven as the core. The accuracy is affected by individual subjectivity, so the accuracy is low and it is difficult to adapt to changes. Its technical architecture has shown significant inadaptability to the increasingly complex project management requirements. Summary of the Invention

[0005] To solve the technical problems existing in the above background art, the present invention provides a project duration prediction method and system based on a Bayesian network. The present invention splits the project to be predicted into several WBS items, constructs a Bayesian network for each WBS item; matches the corresponding records from the historical database according to the key attributes of each WBS item to form conditional probabilities; performs a linear correlation analysis on each WBS item and the corresponding item in the known dataset; combines the conditional probabilities and the linear correlation results to obtain the predicted duration. The present invention can improve the accuracy of duration prediction by analyzing the relationship between the key attributes of WBS items and historical data and combining statistical principles.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] The first aspect of the present invention provides a project duration prediction method based on a Bayesian network.

[0008] A project duration prediction method based on a Bayesian network, comprising:

[0009] Splitting the project to be predicted into several WBS items, and constructing a Bayesian network for each WBS item;

[0010] According to the key attributes of each WBS item, obtaining the historical data of the completed projects, and calculating the conditional probabilities of each WBS item under different durations;

[0011] Calculating the linear correlation probability of each WBS item under different durations according to the same key attributes of the key attributes of each WBS item and the corresponding items in the historical data;

[0012] Calculate the joint probability of each WBS under different construction periods according to the conditional probability and linear correlation probability of each WBS;

[0013] Select the construction period corresponding to the highest value among the joint probabilities of each WBS as the predicted construction period of this WBS, and accumulate the predicted construction periods of all WBS items to obtain the predicted construction period of the project.

[0014] Furthermore, the key attributes of each WBS include: WBS name, investment scale, workload, and measurement unit.

[0015] Furthermore, the WBS name includes: foundation construction, main structure construction, and interior decoration.

[0016] Furthermore, the linear correlation probability is calculated using the Pearson correlation coefficient.

[0017] Furthermore, the historical data includes: WBS name, investment scale, workload, measurement unit, and the actual construction period completed by the project.

[0018] Furthermore, after obtaining the historical data, it also includes data cleaning and standardization processing of the historical data.

[0019] The second aspect of the present invention provides a project construction period prediction system based on a Bayesian network.

[0020] A project construction period prediction system based on a Bayesian network includes:

[0021] A Bayesian network construction module for splitting the project to be predicted into several WBS items and constructing the Bayesian network of each WBS;

[0022] A conditional probability calculation module for obtaining the historical data of the completed project according to the key attributes of each WBS and calculating the conditional probability of each WBS under different construction periods;

[0023] A linear correlation probability calculation module for calculating the linear correlation probability of each WBS under different construction periods according to the same key attributes of the key attributes of each WBS and the corresponding items in the historical data;

[0024] A joint probability calculation module for calculating the joint probability of each WBS under different construction periods according to the conditional probability and linear correlation probability of each WBS;

[0025] A construction period prediction module for selecting the construction period corresponding to the highest value among the joint probabilities of each WBS as the predicted construction period of this WBS, and accumulating the predicted construction periods of all WBS items to obtain the predicted construction period of the project.

[0026] The third aspect of the present invention provides a computer device, which includes:

[0027] a processor, adapted to execute a computer program;

[0028] a computer-readable storage medium in which a computer program is stored, and when the computer program is executed by the processor, the steps in the method for predicting project duration based on a Bayesian network as described in the first aspect above are implemented.

[0029] The fourth aspect of the present invention provides a computer-readable storage medium storing a computer program, which is adapted to be loaded and executed by a processor to implement the steps in the method for predicting project duration based on a Bayesian network as described in the first aspect above.

[0030] The fifth aspect of the present invention provides a computer program product or a computer program.

[0031] The present invention provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps in the method for predicting project duration based on a Bayesian network as described in the first aspect above.

[0032] Compared with the prior art, the beneficial effects of the present invention are:

[0033] The present invention provides a method and system for predicting project duration based on a Bayesian network, which splits a project to be predicted into several WBS items, constructs a Bayesian network for each WBS item; according to the key attributes of each WBS item, obtains the historical data of completed projects, and calculates the conditional probability of each WBS item at different durations; according to the key attributes of each WBS item and the same key attributes of the corresponding items in the historical data, calculates the linear correlation probability of each WBS item at different durations; according to the conditional probability and linear correlation probability of each WBS item, calculates the joint probability of each WBS item at different durations; selects the duration corresponding to the highest value in the joint probability of each WBS item as the predicted duration of this WBS item, and accumulates the predicted durations of all WBS items to obtain the predicted duration of the project. Through the scientific basis provided by the Bayesian network model, project managers can make more reasonable and reliable decisions, reduce the uncertainty brought by subjective judgment, and improve the accuracy of project duration prediction.

[0034] The present invention not only considers key attributes such as investment scale and workload, but also introduces data in more dimensions through linear correlation analysis, making the prediction results more comprehensive and reliable. In addition, the Bayesian network can be updated and optimized as new data is continuously added to improve the accuracy of project duration prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings forming a part of this specification are used to provide a further understanding of the present invention. The schematic embodiments and descriptions thereof of the present invention are used to explain the present invention and do not constitute an improper limitation to the present invention.

[0036] Figure 1 is a flowchart of a project duration prediction method based on a Bayesian network shown in an embodiment of the present invention;

[0037] Figure 2 is a basic structure diagram of a Bayesian network shown in an embodiment of the present invention;

[0038] Figure 3 is a structure diagram of a project duration prediction system based on a Bayesian network shown in an embodiment of the present invention;

[0039] Figure 4 is a structure diagram of a computer device shown in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0041] It should be noted that the following detailed descriptions are all illustrative and are intended to provide a further description of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0042] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0043] To facilitate the understanding of the technical solution of the present invention, some technical terms related to the present invention will be introduced below.

[0044] 1. Project management

[0045] Work Breakdown Structure (WBS): It is a process of decomposing a project into smaller and more manageable parts according to certain rules. Each WBS item represents a specific work package, which has a clear task description and deliverables.

[0046] Key Attribute Identification: For each WBS item, it is necessary to determine the key attributes that affect its completion time. These attributes may include, but are not limited to, investment scale, workload, required resources, construction difficulty, etc.

[0047] Utilization of Historical Data: The completion status of past similar projects provides valuable data references for new projects. By analyzing historical data, the impact patterns of different factors on the project duration can be discovered.

[0048] 2. Statistics

[0049] Conditional Probability: It refers to the probability of an event occurring given certain conditions. In project duration prediction, this may refer to the probability that a certain WBS item is completed within a specific time given a specific investment scale and workload.

[0050] Linear Correlation Analysis: It is used to evaluate whether there is a linear relationship between two variables and its strength. For example, the correlation degree between the investment scale and the project duration is measured by the Pearson's correlation coefficient.

[0051] Joint Probability: By combining the probability distributions under multiple conditions, the probability of satisfying multiple conditions simultaneously is calculated. This is a core concept in Bayesian networks, used to update the prior probability to obtain the posterior probability.

[0052] 3. Bayesian Network

[0053] Bayesian Network: It is a graphical model based on probability theory, used to represent a set of random variables and their conditional dependencies. It consists of nodes (representing random variables) and directed edges (representing direct dependencies).

[0054] Probability Inference: Probability inference through a Bayesian network allows updating beliefs about unobserved variables based on observed evidence. This inference method is particularly suitable for dealing with uncertainty problems.

[0055] Learning Process: A Bayesian network can automatically infer the network structure and parameters from data through learning algorithms, which enables it to adapt to new information and continuously optimize the prediction accuracy over time.

[0056] For this reason, this embodiment provides a project duration prediction method based on a Bayesian network, as Figure 1 shown, including:

[0057] Split the project to be predicted into several WBS items and construct the Bayesian network for each WBS item.

[0058] According to the key attributes of each WBS item, obtain the historical data of completed projects and calculate the conditional probabilities of each WBS item under different durations.

[0059] According to the key attributes of each WBS item and the same key attributes of the corresponding items in the historical data, calculate the linear correlation probabilities of each WBS item under different durations.

[0060] According to the conditional probabilities and linear correlation probabilities of each WBS item, calculate the joint probabilities of each WBS item under different durations.

[0061] Select the duration corresponding to the highest value in the joint probabilities of each WBS item as the predicted duration of this WBS item, and accumulate the predicted durations of all WBS items to obtain the predicted duration of the project.

[0062] Figure 2 The basic structure of the Bayesian network is shown, including the relationship between nodes and edges. Using a graphical method through the Bayesian network to describe the mutual relationship between data, it has clear semantics, is easy to understand, has simple calculations, high accuracy, and can predict the project duration quickly and efficiently. Based on the scientific basis provided by the Bayesian network, project managers can make more reasonable and reliable decisions, reducing the uncertainty brought by subjective judgment. Through the key attributes of each WBS item and the historical data of completed projects, calculate the conditional probabilities, linear correlation probabilities, and joint probabilities of each WBS item under different durations respectively. Select the duration corresponding to the highest value in the joint probabilities of each WBS item as the predicted duration of this WBS item to obtain the predicted duration of the project. The present invention can improve the accuracy of duration prediction, help to reasonably allocate project resources, avoid resource waste or shortage, and improve the overall efficiency of the project.

[0063] In one or more embodiments, the key attributes of the WBS item include: WBS name, investment scale, workload, and measurement unit.

[0064] Specifically, WBS name: the name of the specific work breakdown structure item of the project, such as "foundation pit design". Investment scale: the total investment amount of the project or WBS item, usually expressed in monetary units. Workload: the workload required to complete the WBS item, which can be time (such as person - days), quantity (such as cubic meters), etc. Measurement unit: the measurement unit of the workload, such as "cubic meters", "hours", "tons", etc.

[0065] In one or more embodiments, the historical data of completed projects may refer to the data of the above - mentioned key attributes collected from project plans, historical records, or other relevant documents.

[0066] In one or more embodiments, historical data is cleaned to remove incomplete or abnormal data points to ensure data quality; data from different units is standardized for subsequent querying and analysis.

[0067] Example: The data collected for a WBS item includes: WBS name: Foundation pit design; Investment scale: 200,000 yuan; Workload: 100 cubic meters; Unit of measurement: cubic meters.

[0068] In one or more embodiments, based on the key attributes of each WBS, historical data of completed projects is obtained, and the conditional probability of each WBS under different durations is calculated; the specific implementation process includes:

[0069] Collect relevant data of WBS items from completed projects, including but not limited to WBS name, investment scale, workload, unit of measurement, and actual completed duration, and then perform data cleaning. Store the cleaned data in the historical database for subsequent querying and analysis.

[0070] For the WBS item to be predicted, search for historical records with the same or similar attributes in the historical database according to its key attributes; count the number of occurrences of different durations in these historical records to form a frequency distribution; divide the frequency of each duration by the total number of records to obtain the probability of that duration occurring under the given conditions.

[0071] Based on historical data and statistical analysis, the present invention generates conditional probabilities by identifying the key attributes of WBS items and combining historical records, thereby providing more accurate duration predictions. The present invention not only considers key attributes such as investment scale and workload, but also introduces more dimensional data through linear correlation analysis, making the prediction results more comprehensive and reliable.

[0072] Example: Suppose there are the following records in the historical database:

[0073] WBS item: Foundation pit design, Investment scale: 200,000 yuan, Workload: 100 cubic meters, Unit of measurement: cubic meters, Duration: 20 days;

[0074] WBS item: Foundation pit design, Investment scale: 200,000 yuan, Workload: 100 cubic meters, Unit of measurement: cubic meters, Duration: 25 days;

[0075] WBS item: Foundation pit design, Investment scale: 200,000 yuan, Workload: 100 cubic meters, Unit of measurement: cubic meters, Duration: 30 days;

[0076] WBS item: Foundation pit design: Investment scale: 200,000 yuan, Workload: 100 cubic meters, Unit of measurement: cubic meters, Duration: 20 days;

[0077] WBS Item: Foundation Pit Design, Investment Scale: 200,000 yuan, Workload: 100 cubic meters, Measurement Unit: cubic meter, Construction Period: 20 days;

[0078] WBS Item: Foundation Pit Design: Investment Scale: 200,000 yuan, Workload: 100 cubic meters, Measurement Unit: cubic meter, Construction Period: 25 days;

[0079] WBS Item: Foundation Pit Design, Investment Scale: 200,000 yuan, Workload: 100 cubic meters, Measurement Unit: cubic meter, Construction Period: 30 days;

[0080] In this case, the probability of a 20-day construction period is 3 / 7 (about 0.43), the probability of a 25-day construction period is 2 / 7 (about 0.29), and the probability of a 30-day construction period is 2 / 7 (about 0.29).

[0081] In one or more embodiments, according to the key attributes of each WBS and the same key attributes of the corresponding items in the historical data, calculate the linear correlation probability of each WBS under different construction periods; the specific implementation process includes:

[0082] Determine the variables for linear correlation analysis, usually the key attributes (such as investment scale, workload, etc.) of the WBS item to be measured and the corresponding attributes in the historical records. To eliminate the influence of dimensions, the data can be standardized so that its mean is 0 and the standard deviation is 1.

[0083] For each key attribute, calculate the Pearson correlation coefficient between each WBS to be measured and the historical records. If the correlation coefficient is close to 1, it indicates a strong positive correlation; if it is close to -1, it indicates a strong negative correlation; if it is close to 0, it indicates no obvious linear relationship.

[0084] Among them, the Pearson correlation coefficient is an index to measure the strength of the linear relationship between two variables, and its value range is between -1 and 1. The formula is as follows:

[0085]

[0086] Among them, X i and Y i respectively represent the observed values of the two variables, respectively represent the respective averages of the two variables.

[0087] Example: Suppose the key attributes of the WBS item to be measured are an investment scale of 200,000 yuan and a workload of 100 cubic meters. Find the historical records with the same attributes from the historical database and calculate the Pearson correlation coefficient between each record and the WBS item to be measured. As shown in Table 1, assume that the calculation results show that a certain record has a high correlation with the investment scale of the WBS item to be measured (r = 0.8), but a low correlation with the workload (r = 0.2).

[0088] Table 1 Coefficient of correlation is divided into different intervals

[0089] Coefficient interval Interval range High correlation 0.8-1.0 Medium correlation 0.6-0.8 Low correlation 0.4-0.6 Weak correlation 0.2-0.4 Very weak correlation 0-0.2

[0090] In one or more embodiments, according to the conditional probability and linear correlation probability of each WBS, calculate the joint probability of each WBS under different construction periods; the specific implementation process includes:

[0091] Define event A as the occurrence of a specific construction period, and event B as the linear correlation between the WBS item to be measured and the historical record;

[0092] Use Bayes' formula to calculate the joint probability P(A,B) = P(B|A) × P(A).

[0093] Among them, P(A) represents the conditional probability, P(B|A) represents the linear correlation probability, and P(A,B) represents the joint probability.

[0094] Compare the joint probabilities P(A,B) under different construction periods, and select the construction period with the highest joint probability as the final prediction value.

[0095] In one or more embodiments, select the construction period corresponding to the highest value among the joint probabilities of each WBS as the predicted construction period of this WBS item, and accumulate the predicted construction periods of all WBS items to obtain the predicted construction period of the project; more accurate construction period prediction helps to reasonably allocate project resources, avoid resource waste or shortage, and improve the overall efficiency of the project. Based on the prediction results, the project team can better assess the risks of the project, formulate countermeasures in advance, and reduce the possibility of project delay.

[0096] Example:

[0097] Given the conditional probability P(A) and the linear correlation probability P(B|A):

[0098] Construction period of 20 days: P(A) = 0.43, P(B|A) = 0.8;

[0099] Construction period of 25 days: P(A) = 0.29, P(B|A) = 0.5;

[0100] Construction period of 30 days: P(A) = 0.29, P(B|A) = 0.3;

[0101] Calculate the joint probability:

[0102] Construction period of 20 days: P(A,B) = 0.43 × 0.8 = 0.344;

[0103] Construction period of 25 days: P(A,B) = 0.29 × 0.5 = 0.145;

[0104] Construction period is 30 days: P(A,B) = 0.29×0.3 = 0.087;

[0105] Select the construction period of 20 days with the highest joint probability as the final predicted value.

[0106] Through the above detailed steps, the construction period of the WBS item to be measured can be estimated more accurately, thereby improving the project management efficiency and decision-making quality. This method combines the statistical characteristics of historical data and the specific situation of the current WBS item, providing a more scientific and reasonable construction period prediction method.

[0107] Through the detailed construction period prediction of each WBS item in the present invention, project managers can achieve more refined project management and ensure that each link is completed on time. The prediction results can help the project team timely discover potential schedule deviations and take corresponding measures for adjustment to ensure the project progresses according to the plan. Accurate construction period prediction helps better control project costs and avoid cost overruns caused by construction period delays.

[0108] In addition, the present invention is not only applicable to the construction industry, but also can be applied to other fields that require construction period prediction, such as manufacturing, software development, infrastructure construction, etc.

[0109] With the accumulation of data and the development of technology, this method can continuously improve the prediction performance by adding new variables and improving algorithms, and has good scalability.

[0110] In order to verify the feasibility of the method provided by the present invention, in this embodiment, a commercial complex construction project is taken as an example to implement the method described in this embodiment.

[0111] Project name: A commercial complex construction project

[0112] WBS items: Foundation construction, main structure construction, and interior decoration;

[0113] The project construction period prediction method based on Bayesian network described in this embodiment specifically includes the following steps:

[0114] Step 1: Identify the key attributes of the WBS item, as shown in Table 2.

[0115] WBS name: Foundation construction, main structure construction, interior decoration; Investment scale: 5 million yuan (foundation construction), 10 million yuan (main structure construction), 8 million yuan (interior decoration); Workload: 2000 cubic meters (foundation construction), 5000 cubic meters (main structure construction), 1000 cubic meters (interior decoration); Measurement unit: cubic meters.

[0116] Table 2 Key attributes of each WBS item

[0117]

[0118]

[0119] Step 2: Generate conditional probability

[0120] Historical database construction: Collect historical data, including the WBS items of completed projects and their corresponding durations; Data cleaning: Remove incomplete or abnormal data points; Store the data in the historical database.

[0121] Query matching: Search for historical records in the historical database that have the same key attributes (WBS name, investment scale, workload, measurement unit).

[0122] Frequency statistics and probability calculation: Count the number of occurrences of different durations in these historical records to form a frequency distribution. Calculate the probability of each duration.

[0123] Example data:

[0124] (1) Foundation construction

[0125] The following records exist in the historical database:

[0126] WBS item: Foundation construction, investment scale: 5 million yuan, workload: 2000 cubic meters, measurement unit: cubic meter, previous task duration: 40 days, this task duration: 60 days;

[0127] WBS item: Foundation construction, investment scale: 5 million yuan, workload: 2000 cubic meters, measurement unit: cubic meter, previous task duration: 45 days, this task duration: 70 days;

[0128] WBS item: Foundation construction, investment scale: 5 million yuan, workload: 2000 cubic meters, measurement unit: cubic meter, previous task duration: 50 days, this task duration: 80 days;

[0129] WBS item: Foundation construction, investment scale: 5 million yuan, workload: 2000 cubic meters, measurement unit: cubic meter, previous task duration: 42 days, this task duration: 60 days;

[0130] WBS item: Foundation construction, investment scale: 5 million yuan, workload: 2000 cubic meters, measurement unit: cubic meter, previous task duration: 48 days, this task duration: 90 days;

[0131] WBS item: Foundation construction, investment scale: 5 million yuan, workload: 2000 cubic meters, measurement unit: cubic meter, previous task duration: 40 days, this task duration: 100 days;

[0132] WBS item: Foundation construction, investment scale: 5 million yuan, workload: 2,000 cubic meters, measurement unit: cubic meter, previous task duration: 52 days, this task duration: 70 days.

[0133] Conditional probability calculation:

[0134] Probability of a 60-day duration: 2 / 7 ≈ 0.29;

[0135] Probability of a 70-day duration: 2 / 7 ≈ 0.29;

[0136] Probability of an 80-day duration: 1 / 7 ≈ 0.14;

[0137] Probability of a 90-day duration: 1 / 7 ≈ 0.14;

[0138] Probability of a 100-day duration: 1 / 7 ≈ 0.14.

[0139] (2) Main structure construction

[0140] There are the following records in the historical database:

[0141] WBS item: Main structure construction, investment scale: 10 million yuan, workload: 5,000 cubic meters, measurement unit: cubic meter, previous task duration: 60 days, this task duration: 120 days;

[0142] WBS item: Main structure construction, investment scale: 10 million yuan, workload: 5,000 cubic meters, measurement unit: cubic meter, previous task duration: 70 days, this task duration: 150 days;

[0143] WBS item: Main structure construction, investment scale: 10 million yuan, workload: 5,000 cubic meters, measurement unit: cubic meter, previous task duration: 80 days, this task duration: 180 days;

[0144] WBS item: Main structure construction, investment scale: 10 million yuan, workload: 5,000 cubic meters, measurement unit: cubic meter, previous task duration: 65 days, this task duration: 120 days;

[0145] WBS item: Main structure construction, investment scale: 10 million yuan, workload: 5,000 cubic meters, measurement unit: cubic meter, previous task duration: 75 days, this task duration: 150 days;

[0146] WBS item: Main structure construction, investment scale: 10 million yuan, workload: 5,000 cubic meters, measurement unit: cubic meter, previous task duration: 85 days, this task duration: 180 days.

[0147] Conditional probability calculation:

[0148] Probability of a 120-day duration: 2 / 6 ≈ 0.33;

[0149] Probability of a 150-day construction period: 2 / 6 ≈ 0.33;

[0150] Probability of a 180-day construction period: 2 / 6 ≈ (0.33).

[0151] (3) Interior decoration

[0152] The following records are available in the historical database:

[0153] WBS item: Interior decoration, investment scale: 8 million yuan, workload: 1000 square meters, measurement unit: square meters, previous task duration: 90 days, this task duration: 100 days;

[0154] WBS item: Interior decoration, investment scale: 8 million yuan, workload: 1000 square meters, measurement unit: square meters, previous task duration: 100 days, this task duration: 110 days;

[0155] WBS item: Interior decoration, investment scale: 8 million yuan, workload: 1000 square meters, measurement unit: square meters, previous task duration: 95 days, this task duration: 100 days;

[0156] WBS item: Interior decoration, investment scale: 8 million yuan, workload: 1000 square meters, measurement unit: square meters, previous task duration: 105 days, this task duration: 110 days;

[0157] WBS item: Interior decoration, investment scale: 8 million yuan, workload: 1000 square meters, measurement unit: square meters, previous task duration: 90 days, this task duration: 100 days;

[0158] WBS item: Interior decoration, investment scale: 8 million yuan, workload: 1000 square meters, measurement unit: square meters, previous task duration: 110 days, this task duration: 110 days.

[0159] Conditional probability calculation:

[0160] Probability of a 100-day construction period: 3 / 6 = 0.5;

[0161] Probability of an 110-day construction period: 3 / 6 = 0.5.

[0162] Step 3: Linear correlation analysis

[0163] Data preparation: Select variable: Previous task duration (X1).

[0164] Standardization: Standardize the data so that its mean is 0 and standard deviation is 1.

[0165] Pearson correlation coefficient calculation: Calculate the Pearson correlation coefficient between the WBS item to be measured and the previous task in the historical record under different construction periods.

[0166] Example data:

[0167] (1) Foundation construction

[0168] WBS item to be measured: Investment scale of 5 million yuan, workload of 2,000 cubic meters.

[0169] One record in the historical record: The previous task duration is 40 days, and the current task duration is 60 days.

[0170] Use Python or other statistical software to calculate the correlation coefficient.

[0171] Suppose the calculated Pearson correlation coefficient is 0.75, which indicates a strong positive correlation between the construction period of "Foundation construction" and the previous task's construction period.

[0172] (2) Main structure construction

[0173] WBS item to be measured: Investment scale of 10 million yuan, workload of 5,000 cubic meters.

[0174] One record in the historical record: The previous task duration is 60 days, and the current task duration is 120 days.

[0175] Use Python or other statistical software to calculate the correlation coefficient.

[0176] Suppose the calculated Pearson correlation coefficient is 0.85, which indicates a very strong positive correlation between the construction period of "Main structure construction" and the previous task's construction period.

[0177] (3) Interior decoration

[0178] WBS item to be measured: Investment scale of 8 million yuan, workload of 1,000 cubic meters.

[0179] One record in the historical record: The previous task duration is 90 days, and the current task duration is 100 days.

[0180] Use Python or other statistical software to calculate the correlation coefficient.

[0181] Suppose the calculated Pearson correlation coefficient is 0.65, which indicates a moderately strong positive correlation between the construction period of "Interior decoration" and the previous task's construction period.

[0182] Step 4: Application of Bayesian network

[0183] Define events:

[0184] Event A: The occurrence of a specific construction period.

[0185] Event B: The linear correlation between the WBS item to be measured and the previous task in the historical record under different construction periods.

[0186] Joint probability calculation: Using Bayes' formula P(A,B) = P(B|A) × P(A).

[0187] Example data:

[0188] (1) Foundation construction

[0189] Conditional probability P(A):

[0190] Construction period of 60 days: P(A) = 0.29;

[0191] Construction period of 70 days: P(A) = 0.29;

[0192] Construction period of 80 days: P(A) = 0.14;

[0193] Construction period of 90 days: P(A) = 0.14;

[0194] Construction period of 100 days: P(A) = 0.14;

[0195] Probability of linear correlation P(B|A):

[0196] Construction period of 60 days: P(B|A) = 0.75;

[0197] Construction period of 70 days: P(B|A) = 0.70;

[0198] Construction period of 80 days: P(B|A) = 0.65;

[0199] Construction period of 90 days: P(B|A) = 0.60;

[0200] Construction period of 100 days: P(B|A) = 0.75;

[0201] Joint probability calculation:

[0202] Construction period of 60 days: P(A,B) = 0.29 × 0.75 = 0.2175;

[0203] Construction period of 70 days: P(A,B) = 0.29 × 0.70 = 0.203;

[0204] Construction period of 80 days: P(A,B) = 0.14 × 0.65 = 0.091;

[0205] Construction period of 90 days: P(A,B) = 0.14 × 0.60 = 0.084;

[0206] Construction period of 60 days: P(A,B) = 0.14 × 0.75 = 0.105;

[0207] Final prediction: Select the construction period with the highest joint probability as the final predicted value.

[0208] In this example, the joint probability of a construction period of 60 days is the highest, so the predicted construction period is 60 days.

[0209] (2) Main structure construction

[0210] Conditional probability P(A):

[0211] Construction period of 120 days: P(A) = 0.33;

[0212] Construction period of 150 days: P(A) = 0.33;

[0213] Construction period of 180 days: P(A) = 0.33;

[0214] Linear correlation probability P(B|A):

[0215] Construction period of 120 days: P(B|A) = 0.85;

[0216] Construction period of 150 days: P(B|A) = 0.80;

[0217] Construction period of 180 days: P(B|A) = 0.75;

[0218] Joint probability calculation:

[0219] Construction period of 120 days: P(A,B) = 0.33 × 0.85 = 0.2805;

[0220] Construction period of 150 days: P(A,B) = 0.33 × 0.80 = 0.264;

[0221] Construction period of 180 days: P(A,B) = 0.33 × 0.75 = 0.2475;

[0222] Final prediction: Select the construction period with the highest joint probability as the final predicted value.

[0223] In this example, the joint probability of a construction period of 120 days is the highest, so the predicted construction period is 120 days.

[0224] (3) Interior decoration

[0225] Conditional probability P(A):

[0226] Construction period of 100 days: P(A) = 0.5;

[0227] Construction period of 110 days: P(A) = 0.5;

[0228] Linear correlation probability P(B|A):

[0229] Construction period is 100 days: P(B|A) = 0.65;

[0230] Construction period is 110 days: P(B|A) = 0.60;

[0231] Joint probability calculation:

[0232] Construction period is 100 days: P(A,B) = 0.5×0.65 = 0.325;

[0233] Construction period is 110 days: P(A,B) = 0.5×0.60 = 0.30;

[0234] Final prediction: Select the construction period with the highest joint probability as the final prediction value.

[0235] In this example, the joint probability of a construction period of 100 days is the highest, so the predicted construction period is 100 days.

[0236] Through the above steps, the present invention successfully uses the Bayesian network model to predict the construction periods of the three WBS items of "foundation construction", "main structure construction", and "interior decoration". This method combines the statistical characteristics of historical data and the specific situation of the current WBS item, providing a more scientific and reasonable construction period prediction method. This method can be widely applied to various engineering projects to improve the efficiency of project management and the quality of decision-making.

[0237] In the construction industry, the construction period prediction based on the Bayesian network model can help project managers better plan the project schedule, reasonably allocate resources, and timely adjust the plan to cope with unforeseen risks.

[0238] For software development projects, such a method is equally applicable. By analyzing factors such as module complexity and team size, the completion time of each stage can be predicted, thereby improving the efficiency of project management.

[0239] In the manufacturing industry or any other industry involving complex processes, this method can also be used to estimate the production cycle or service delivery time.

[0240] The above combination Figure 1 The project construction period prediction method based on the Bayesian network provided by the embodiments of the present invention has been introduced in detail. Next, the project construction period prediction system based on the Bayesian network provided by the embodiments of the present invention will be introduced in conjunction with the accompanying drawings.

[0241] Figure 3 is a schematic structural diagram of the project construction period prediction system based on the Bayesian network shown in the embodiments of the present invention. Referring to Figure 3 , the system described in the present invention includes:

[0242] A Bayesian network construction module, which is used to split the project to be predicted into several WBS items and construct a Bayesian network for each WBS item;

[0243] A conditional probability calculation module, which is used to obtain the historical data of the completed projects according to the key attributes of each WBS item and calculate the conditional probability of each WBS item under different construction periods;

[0244] A linear correlation probability calculation module, which is used to calculate the linear correlation probability of each WBS item under different construction periods according to the key attributes of each WBS item and the same key attributes of the corresponding items in the historical data;

[0245] A joint probability calculation module, which is used to calculate the joint probability of each WBS item under different construction periods according to the conditional probability and the linear correlation probability of each WBS item;

[0246] A construction period prediction module, which is used to select the construction period corresponding to the highest value in the joint probability of each WBS item as the predicted construction period of this WBS item, and accumulate the predicted construction periods of all WBS items to obtain the predicted construction period of the project.

[0247] In some embodiments, the key attributes of each WBS item include: WBS name, investment scale, workload, and measurement unit.

[0248] In some embodiments, the WBS name includes: foundation construction, main structure construction, and interior decoration.

[0249] In some embodiments, the linear correlation probability is calculated using the Pearson correlation coefficient.

[0250] In some embodiments, the historical data includes: WBS name, investment scale, workload, measurement unit, and the actual construction period of the project completed.

[0251] In some embodiments, after obtaining the historical data, it further includes data cleaning and standardization processing of the historical data.

[0252] The present invention promotes the application of data analysis technology in project management and promotes the technological innovation and development in the field of project management. By continuously optimizing the Bayesian network, more advanced technologies and methods, such as machine learning, deep learning, etc., can be introduced to further improve the prediction performance.

[0253] The prediction result based on data of the present invention improves the transparency of project information, which helps all parties to better understand and accept the prediction result. Project team members can communicate and collaborate more effectively according to the prediction result to jointly ensure the realization of project goals.

[0254] The present invention improves the accuracy of project duration prediction, helps the project to be delivered on time, and improves customer satisfaction. A reasonable project duration arrangement can ensure the quality and safety of the project, further enhancing customer trust and satisfaction.

[0255] According to an embodiment of the present invention, the project duration prediction system based on a Bayesian network can correspond to the execution of the method described in the embodiments of the present invention, and the above and other operations and / or functions of each module of the project duration prediction system based on a Bayesian network are respectively for implementing Figure 1 the corresponding processes of each method in, and for the sake of brevity, they will not be elaborated here.

[0256] See Figure 4 the structural diagram of the computer device shown in. The computer device includes a processor, a communication interface, and a computer-readable storage medium. Among them, the processor, the communication interface, and the computer-readable storage medium can be connected through a bus or other means. Among them, the communication interface is used to receive and send data. The computer-readable storage medium can be stored in the memory of the computer device. The computer-readable storage medium is used to store a computer program, and the computer program includes program instructions. The processor is used to execute the program instructions stored in the computer-readable storage medium. The processor (or CPU (Central Processing Unit, central processor)) is the computing core and control core of the computer device, and is adapted to implement one or more instructions, specifically adapted to load and execute one or more instructions to implement the corresponding steps in the embodiments of the project duration prediction method based on a Bayesian network.

[0257] This embodiment provides a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in the computer device and is used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and, of course, the extended storage medium supported by the computer device. The computer-readable storage medium provides a storage space, and this storage space stores the processing system of the computer device.

[0258] And, one or more instructions suitable for being loaded and executed by the processor are also stored in this storage space. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory; optionally, it can also be at least one computer-readable storage medium located far from the aforementioned processor.

[0259] In one embodiment, one or more instructions are stored in the computer-readable storage medium; the one or more instructions stored in the computer-readable storage medium are loaded and executed by a processor to implement the corresponding steps in the above-mentioned embodiment of the project duration prediction method based on the Bayesian network.

[0260] This embodiment provides a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the corresponding steps in the above-mentioned embodiment of the project duration prediction method based on the Bayesian network.

[0261] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories and optical memories, etc.) containing computer-usable program code.

[0262] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0263] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0264] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, and thus the instructions executed on the computer or other programmable apparatus provide steps for realizing the functions specified in one process or multiple processes and / or blocks Figure 1 one process or multiple processes and / or blocks Figure 1 steps for realizing the functions specified in one block or multiple blocks.

[0265] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above various methods. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0266] The foregoing are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A project duration prediction method based on Bayesian network, characterized in that Including: Split the project to be predicted into several WBS items, and construct the Bayesian network for each WBS item; According to the key attributes of each WBS item, obtain the historical data of the completed projects, and calculate the conditional probability of each WBS item under different construction periods; According to the key attributes of each WBS item and the same key attributes of the corresponding items in the historical data, calculate the linear correlation probability of each WBS item under different construction periods; According to the conditional probability and linear correlation probability of each WBS item, calculate the joint probability of each WBS item under different construction periods; Select the construction period corresponding to the highest value in the joint probability of each WBS item as the predicted construction period of this WBS item, and accumulate the predicted construction periods of all WBS items to obtain the predicted construction period of the project.

2. The project duration prediction method based on Bayesian network according to claim 1, wherein The key attributes of each WBS item include: WBS name, investment scale, workload, and measurement unit.

3. The project duration prediction method based on Bayesian network according to claim 2, characterized in that, The WBS name includes: foundation construction, main structure construction, and interior decoration.

4. The project duration prediction method based on Bayesian network according to claim 1, characterized in that, The linear correlation probability is calculated using the Pearson correlation coefficient.

5. The project duration prediction method based on Bayesian network according to claim 1, characterized in that, The historical data includes: WBS name, investment scale, workload, measurement unit, and the actual construction period of the project.

6. The project duration prediction method based on Bayesian network according to claim 1, characterized in that After obtaining the historical data, it also includes data cleaning and standardization processing of the historical data.

7. The project duration prediction system based on Bayesian network is characterized by: Including: A Bayesian network construction module, which is used to split the project to be predicted into several WBS items and construct the Bayesian network for each WBS item; A conditional probability calculation module, which is used to obtain the historical data of the completed projects according to the key attributes of each WBS item and calculate the conditional probability of each WBS item under different construction periods; A linear correlation probability calculation module, which is used to calculate the linear correlation probability of each WBS item under different construction periods according to the key attributes of each WBS item and the same key attributes of the corresponding items in the historical data; A joint probability calculation module, which is used to calculate the joint probability of each WBS item under different construction periods according to the conditional probability and linear correlation probability of each WBS item; A construction period prediction module, which is used to select the construction period corresponding to the highest value in the joint probability of each WBS item as the predicted construction period of this WBS item, and accumulate the predicted construction periods of all WBS items to obtain the predicted construction period of the project.

8. A computer device, characterized in that a processor, suitable for executing a computer program; a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by the processor, it implements the steps in the method for predicting the project construction period based on the Bayesian network according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded and executed by the processor to implement the steps in the method for predicting the project construction period based on the Bayesian network according to any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program, and when the computer program is executed by the processor, it implements the steps in the method for predicting the project construction period based on the Bayesian network according to any one of claims 1-6.

Images