Association prediction system and method for construction part and construction procedure

Abstract

The invention provides a correlation prediction system for construction parts and construction procedures, and the system comprises a correlation prediction model building module which is used for building a correlation prediction model through employing an AdaBoost algorithm according to the historical correlation result of the data of all construction parts and construction procedures; and the correlation prediction module is used for inputting the data of the current construction part and the construction process into the correlation prediction model to obtain a correlation prediction result of the data of the current construction part and the construction process. The correlation prediction model uses the AdaBoost algorithm, a weak classifier can be added after a prediction result goes wrong once during use, the algorithm is continuously optimized in practical application, the performance and applicability of the technical scheme are improved, and the final prediction accuracy is higher and higher along with the increase of the use frequency of the correlation prediction model.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering project management, and in particular to a system and method for predicting the association between a construction site and a construction process. Background Art

[0002] There are many challenges in the current project management field, one of which is the association between construction parts and construction processes in the management system. Project managers need to associate construction parts with construction processes in the management system to keep track of the progress and details of the project and facilitate subsequent process quality inspections.

[0003] However, this process involves a lot of manual operations, which is time-consuming and prone to errors, and brings considerable pressure to project management. The traditional manual hooking method can no longer meet the needs of engineering project management. Summary of the invention

[0004] The purpose of the present invention is to provide a construction location and construction process association prediction system to address the defects of the prior art, including:

[0005] The module for establishing the association prediction model is used to establish the association prediction model using the AdaBoost algorithm based on the historical association results of the data of all construction locations and construction processes at the construction site;

[0006] The correlation prediction module is used to input the data of the current construction site and construction process into the correlation prediction model to obtain the correlation prediction results of the data of the current construction site and construction process.

[0007] Furthermore, it also includes:

[0008] The data collection module is used to collect the historical correlation results of the data of all construction locations and construction processes at the construction site, and pre-process the historical correlation results.

[0009] Furthermore, it also includes:

[0010] The prediction result correction module is used to judge the correctness of the associated prediction result. If the associated prediction result is judged to be wrong, the number of weak classifiers in the AdaBoost algorithm is increased by one for each error.

[0011] Furthermore, the data of the construction process includes process type, process complexity, and process inspection items;

[0012] The data of the construction site includes a label of the construction site;

[0013] The historical association result of the data of the construction location and the construction process is a combination of the data of the construction location and the construction process in history.

[0014] Furthermore, the specific method for preprocessing the historical association result is:

[0015] First, the construction sites and construction processes are classified according to the project type. On the premise that the construction sites and construction processes are of the same project type, the abnormal values ​​of the historical correlation results between the data of the construction sites and construction processes are eliminated. The specific formula is as follows:

[0016]

[0017] Where P ij The ratio of the number of times that construction site i is associated with construction process j to the total number of times that construction site i is associated with all construction process data, n ij is the number of times construction site i is associated with the data of construction process j, and M is the total number of times construction site i is associated with the data of all construction processes;

[0018] The proportion of the number of times the construction site i is associated with the construction process j to the total number of times the construction site i is associated with the data of all construction processes P ij The value of outliers is removed. If P ij <0.01, the correlation result between the data of construction location i and construction process j is an outlier.

[0019] Furthermore, in the association prediction model building module, the specific method of using the AdaBoost algorithm to build the association prediction model based on the historical association results of the construction site and construction process data is as follows:

[0020] The specific formula of the association prediction model established using the AdaBoost algorithm is as follows:

[0021]

[0022] Among them, h t (x) is the result of whether the construction location i and construction process j data are associated in the tth weak classifier in the AdaBoost algorithm, T is the number of weak classifiers in the AdaBoost algorithm, α t is the weight of the t-th weak classifier, H(x) is the association prediction result of the association prediction model, and x is the combination of the label of the current construction location i and the data of the construction process j;

[0023] If the prediction result H(x) of the association prediction model is greater than 0, it means that the data of the current construction location i and the construction process j can be associated;

[0024] If the prediction result H(x) of the association prediction model is less than 0, it means that the data of the current construction location i and the construction process j cannot be associated;

[0025] The result h of whether the construction location i and construction process j data are associated in the tth weak classifier in the AdaBoost algorithm t (x) Determined by:

[0026] Calculate the historical correlation ratio P of the combination x of the data of the current construction location i and the construction process j x ,

[0027]

[0028] n x is the historical association times of the combination x of the data of the current construction location i and the construction process j, M is the total historical association times of the current construction location i and the construction process, and the preset threshold δ is x >δ, then h t (x) The result is associated, otherwise it is not associated.

[0029] A method for predicting the association between a construction location and a construction process, comprising:

[0030] According to the historical correlation results of the data of construction sites and construction processes, the AdaBoost algorithm is used to establish a correlation prediction model;

[0031] The data of the current construction location and construction process are input into the association prediction model to obtain the association prediction results of the data of the current construction location and construction process.

[0032] Furthermore, it also includes:

[0033] The historical correlation results of the data of all construction locations and construction processes at the construction site are collected, and the historical correlation results are preprocessed.

[0034] Furthermore, it also includes:

[0035] The correctness of the association prediction result is judged. If the association prediction result is judged to be wrong, the number of weak classifiers in the AdaBoost algorithm is increased by one for each error.

[0036] A computer program product includes a computer program / instruction, wherein the computer program / instruction, when executed by a processor, implements the above-mentioned method for predicting the association between construction locations and construction procedures.

[0037] The beneficial effects of the present invention are:

[0038] 1. By predicting the construction sites and construction procedures through algorithms, intelligent management of the relationship between construction sites and construction procedures is realized, manual operations are reduced, management efficiency is improved, and the degree of standardization of the relationship is improved, which reduces the impact of human factors on project quality, improves the quality and reliability of project management, helps project managers make more scientific decisions, and improves the accuracy and reliability of project management.

[0039] 2. Since the association prediction model uses the AdaBoost algorithm, a weak classifier can be added after the prediction result is wrong once. The algorithm is continuously optimized in practical applications, which improves the performance and applicability of this technical solution. Ultimately, the prediction accuracy will become higher and higher as the number of times the association prediction model is used increases. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a system block diagram of the present invention. DETAILED DESCRIPTION

[0041] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0042] Example 1

[0043] refer to Figure 1 , a correlation prediction system between construction locations and construction processes, comprising:

[0044] The data collection module is used to collect the historical correlation results of the data of all construction locations and construction processes at the construction site, and pre-process the historical correlation results.

[0045] The module for establishing the association prediction model is used to establish the association prediction model using the AdaBoost algorithm based on the historical association results of the data of all construction locations and construction processes at the construction site;

[0046] The correlation prediction module is used to input the data of the current construction site and construction process into the correlation prediction model to obtain the correlation prediction results of the data of the current construction site and construction process.

[0047] The prediction result correction module is used to judge the correctness of the associated prediction result. If the associated prediction result is judged to be wrong, the number of weak classifiers in the AdaBoost algorithm is increased by one for each error.

[0048] (1) Collect unit projects, such as highway projects, railway projects, water transport projects, etc., divide the unit projects into sub-projects, and further divide the sub-projects into leaf nodes, which are the construction sites.

[0049] Collecting process library: Collecting common processes according to engineering categories. The data of construction processes include process type, process complexity, process inspection items, etc. The data of construction sites include labels of construction sites.

[0050] (2) The historical association result of the data of the construction location and the construction process is a combination of the data of the construction location and the construction process in history. For example, the combination: the construction location is steel structure and the process type is steel bar binding. Another example is the combination: the construction location is steel structure, the process type is steel bar binding and the process complexity is simple. The data form is {G, (A, B)}, where G indicates that the label of the construction location is steel structure, A indicates that the process type is steel bar binding, and B indicates that the process complexity is simple.

[0051] (3) The specific method for preprocessing the historical association results is:

[0052] Process invalid values ​​to ensure data quality, perform judgment and cleaning based on the valid status of the system's historical data, and only extract valid data;

[0053] The construction sites and construction processes are classified according to the project type. On the premise that the construction sites and construction processes are of the same project type, the abnormal values ​​of the historical correlation results between the data of the construction sites and construction processes are eliminated. The specific formula is as follows:

[0054]

[0055] Where P ij The ratio of the number of times that construction site i is associated with construction process j to the total number of times that construction site i is associated with all construction process data, n ij is the number of times construction site i is associated with the data of construction process j, and M is the total number of times construction site i is associated with the data of all construction processes;

[0056] The proportion of the number of times the construction site i is associated with the construction process j to the total number of times the construction site i is associated with the data of all construction processes P ij The value of outliers is removed. If P ij <0.01, the correlation result between the data of construction location i and construction process j is an outlier.

[0057] In practical applications, it is usually necessary to analyze the correlation between the concrete pouring processes of different parts (such as floors, columns, and walls) in large-scale construction projects. By collecting historical data, the correlation data of various categories of parts and processes are cleaned to ensure the reliability and accuracy of the data.

[0058] On the premise that the construction location and construction process are of the same type of project, calculating the data coverage rate on this basis can make the sample data more accurate. ij <0.01 indicates that the correlation occurred by chance and is most likely an outlier.

[0059] (4) In the association prediction model building module, the specific method of using the AdaBoost algorithm to build the association prediction model based on the historical association results of the construction location and construction process data is as follows:

[0060] The specific formula of the association prediction model established using the AdaBoost algorithm is as follows:

[0061]

[0062] Among them, h t (x) is the result of whether the construction location i and construction process j data are associated in the tth weak classifier in the AdaBoost algorithm, T is the number of weak classifiers in the AdaBoost algorithm, α t is the weight of the t-th weak classifier. The more times of association, the higher the accuracy, and the lower the weight of the current weak classifier. H(x) is the association prediction result of the association prediction model, and x is the combination of the label of the current construction site i and the data of the construction process j. sign(·): is a sign function that maps the positive and negative conditions of its parameters to +1 or -1. Here, it is used to map the result of the weighted sum to the result of the binary classification, +1 means attachment, and -1 means no attachment.

[0063] If the prediction result H(x) of the association prediction model is greater than 0, it means that the data of the current construction site i and the construction process j can be associated. If the prediction result H(x) of the association prediction model is less than 0, it means that the data of the current construction site i and the construction process j cannot be associated.

[0064] The result h of whether the construction location i and construction process j data are associated in the tth weak classifier in the AdaBoost algorithm t (x) Determined by:

[0065] Calculate the historical correlation ratio P of the combination x of the data of the current construction location i and the construction process j x ,

[0066]

[0067] n x is the historical association times of the combination x of the data of the current construction location i and the construction process j, M is the total historical association times of the current construction location i and the construction process, and the preset threshold δ is x >δ, then h t (x) The result is associated, otherwise it is not associated. x It can change with historical data, and the threshold δ can be adjusted according to actual conditions.

[0068] By using algorithms to predict the association between construction sites and construction processes, intelligent management of the association between construction sites and construction processes is achieved, manual operations are reduced, management efficiency is improved, and the degree of standardization of the association is increased, reducing the impact of human factors on project quality, improving the quality and reliability of project management, helping project managers make more scientific decisions, and improving the accuracy and reliability of project management.

[0069] (4) If in actual application, a construction site i completes the predicted associated standard process j, and the association is manually judged to be wrong, it is manually corrected, that is, the association is cancelled, and the number of corrections is counted. The number of weak classifiers T is increased according to the number of corrections. If the number of corrections is k, the number of k weak classifiers is increased to improve the accuracy of the associated prediction. If the predicted association is manually judged to be correct, the algorithm remains unchanged.

[0070] Since the AdaBoost algorithm is used, a weak classifier can be added each time an error occurs. The algorithm is continuously optimized in practical applications, which improves the performance and applicability of this technical solution, and ultimately the prediction accuracy will become higher and higher.

[0071] Example 2

[0072] A method for predicting the association between a construction location and a construction process, comprising:

[0073] The historical correlation results of the data of all construction locations and construction processes at the construction site are collected, and the historical correlation results are preprocessed.

[0074] According to the historical correlation results of the data of all construction sites and construction processes at the construction site, the AdaBoost algorithm is used to establish a correlation prediction model;

[0075] The data of the current construction location and construction process are input into the association prediction model to obtain the association prediction results of the data of the current construction location and construction process.

[0076] The correctness of the association prediction result is judged. If the association prediction result is judged to be wrong, the number of weak classifiers in the AdaBoost algorithm is increased by one for each error.

[0077] (1) Collect unit projects, such as highway projects, railway projects, water transport projects, etc., divide the unit projects into sub-projects, and further divide the sub-projects into leaf nodes, which are the construction sites.

[0078] Collecting process library: Collecting common processes according to engineering categories. The data of construction processes include process type, process complexity, process inspection items, etc. The data of construction sites include labels of construction sites.

[0079] (2) The historical association result of the data of the construction location and the construction process is a combination of the data of the construction location and the construction process in history. For example, the combination: the construction location is steel structure and the process type is steel bar binding. Another example is the combination: the construction location is steel structure, the process type is steel bar binding and the process complexity is simple. The data form is {G, (A, B)}, where G indicates that the label of the construction location is steel structure, A indicates that the process type is steel bar binding, and B indicates that the process complexity is simple.

[0080] (3) The specific method for preprocessing the historical association results is:

[0081] Process invalid values ​​to ensure data quality, perform judgment and cleaning based on the valid status of the system's historical data, and only extract valid data;

[0082] The construction sites and construction processes are classified according to the project type. On the premise that the construction sites and construction processes are of the same project type, the abnormal values ​​of the historical correlation results between the data of the construction sites and construction processes are eliminated. The specific formula is as follows:

[0083]

[0084] Where P ij The ratio of the number of times that construction site i is associated with construction process j to the total number of times that construction site i is associated with all construction process data, n ij is the number of times construction site i is associated with the data of construction process j, and M is the total number of times construction site i is associated with the data of all construction processes;

[0085] The proportion of the number of times the construction site i is associated with the construction process j to the total number of times the construction site i is associated with the data of all construction processes P ij The value of outliers is removed. If P ij <0.01, the correlation result between the data of construction location i and construction process j is an outlier.

[0086] In practical applications, it is usually necessary to analyze the correlation between the concrete pouring processes of different parts (such as floors, columns, and walls) in large-scale construction projects. By collecting historical data, the correlation data of various categories of parts and processes are cleaned to ensure the reliability and accuracy of the data.

[0087] On the premise that the construction location and construction process are of the same type of project, calculating the data coverage rate on this basis can make the sample data more accurate. ij <0.01 indicates that the correlation occurred by chance and is most likely an outlier.

[0088] (4) The specific method of establishing the association prediction model using the AdaBoost algorithm based on the historical association results of the data of the construction location and the construction process is as follows:

[0089] The specific formula of the association prediction model established using the AdaBoost algorithm is as follows:

[0090]

[0091] Among them, h t (x) is the result of whether the construction location i and construction process j data are associated in the tth weak classifier in the AdaBoost algorithm, T is the number of weak classifiers in the AdaBoost algorithm, α t is the weight of the t-th weak classifier. The more times of association, the higher the accuracy, and the lower the weight of the current weak classifier. H(x) is the association prediction result of the association prediction model, and x is the combination of the label of the current construction site i and the data of the construction process j. sign(·): is a sign function that maps the positive and negative conditions of its parameters to +1 or -1. Here, it is used to map the result of the weighted sum to the result of the binary classification, +1 means attachment, and -1 means no attachment.

[0092] If the prediction result H(x) of the association prediction model is greater than 0, it means that the data of the current construction site i and the construction process j can be associated. If the prediction result H(x) of the association prediction model is less than 0, it means that the data of the current construction site i and the construction process j cannot be associated.

[0093] The result h of whether the construction location i and construction process j data are associated in the tth weak classifier in the AdaBoost algorithm t (x) Determined by:

[0094] Calculate the historical correlation ratio P of the combination x of the data of the current construction location i and the construction process j x ,

[0095]

[0096] n x is the historical association times of the combination x of the data of the current construction location i and the construction process j, M is the total historical association times of the current construction location i and the construction process, and the preset threshold δ is x >δ, then h t (x) The result is associated, otherwise it is not associated. x It can change with historical data, and the threshold δ can be adjusted according to actual conditions.

[0097] By using algorithms to predict the association between construction sites and construction processes, intelligent management of the association between construction sites and construction processes is achieved, manual operations are reduced, management efficiency is improved, and the degree of standardization of the association is increased, reducing the impact of human factors on project quality, improving the quality and reliability of project management, helping project managers make more scientific decisions, and improving the accuracy and reliability of project management.

[0098] (4) If in actual application, a construction site i completes the associated standard process j, and the association is manually judged to be wrong, it is manually corrected, that is, the association is cancelled, and the number of corrections is counted. The number of weak classifiers T is increased according to the number of corrections. If the number of corrections is k, the number of k weak classifiers is increased to improve the accuracy of the association prediction. If the predicted association is manually judged to be correct, the algorithm remains unchanged.

[0099] Since the AdaBoost algorithm is used, a weak classifier can be added each time an error occurs. The algorithm is continuously optimized in practical applications, which improves the performance and applicability of this technical solution, and ultimately the prediction accuracy will become higher and higher.

[0100] Example 3

[0101] A computer program product includes a computer program / instruction, and when the computer program / instruction is executed by a processor, the method for predicting the association between a construction location and a construction process in Example 2 is implemented.

[0102] The contents not described in detail in this specification belong to the prior art known to those skilled in the art. It should be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0103] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes 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 a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0104] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit its protection scope. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that after reading the present invention, those skilled in the art can still make various changes, modifications or equivalent substitutions to the specific implementation methods of the invention, but these changes, modifications or equivalent substitutions are all within the protection scope of the pending claims of the invention.

Claims

1. A system for predicting the association between construction sites and construction processes, characterized in that: include: The module for establishing the association prediction model is used to establish the association prediction model using the AdaBoost algorithm based on the historical association results of all construction sites and construction process data at the construction site; The correlation prediction module is used to input the current construction location and construction process data into the correlation prediction model to obtain the correlation prediction results of the current construction location and construction process data.

2. The construction location and construction process correlation prediction system according to claim 1, characterized in that: Also includes: The data collection module is used to collect the historical correlation results of all construction locations and construction process data at the construction site, and pre-process the historical correlation results.

3. The construction location and construction process correlation prediction system according to claim 1, characterized in that: Also includes: The prediction result correction module is used to judge the correctness of the associated prediction result. If the associated prediction result is judged to be wrong, the number of weak classifiers in the AdaBoost algorithm is increased by one for each error.

4. The construction location and construction process correlation prediction system according to claim 1, characterized in that: The data of the construction process includes process type, process complexity, and process inspection items; The data of the construction site includes a label of the construction site; The historical association result of the data of the construction location and the construction process is a combination of the data of the construction location and the construction process in history.

5. The construction location and construction process correlation prediction system according to claim 2, characterized in that: The specific method for preprocessing the historical association results is: First, the construction sites and construction processes are classified according to the project type. On the premise that the construction sites and construction processes are of the same project type, the abnormal values ​​of the historical correlation results between the data of the construction sites and construction processes are eliminated. The specific formula is as follows: Where P ij The ratio of the number of times that construction site i is associated with construction process j to the total number of times that construction site i is associated with all construction process data, n ij is the number of times construction site i is associated with the data of construction process j, and M is the total number of times construction site i is associated with the data of all construction processes; The proportion of the number of times the construction site i is associated with the construction process j to the total number of times the construction site i is associated with the data of all construction processes P ij The value of outliers is removed. If P ij <set value, the correlation result between the data of construction location i and construction process j is an abnormal value.

6. The construction location and construction process correlation prediction system according to claim 1, characterized in that: In the association prediction model establishment module, the specific method of establishing the association prediction model using the AdaBoost algorithm based on the historical association results of the construction location and construction process data is as follows: Among them, h t (x) is the result of whether the construction location i and construction process j data are associated in the tth weak classifier in the AdaBoost algorithm, T is the number of weak classifiers in the AdaBoost algorithm, α t is the weight of the t-th weak classifier, H(x) is the association prediction result of the association prediction model, and x is the combination of the current construction location i and construction process j data; If the prediction result H(x) of the association prediction model is greater than 0, it means that the data of the current construction location i and the construction process j can be associated; If the prediction result H(x) of the association prediction model is less than 0, it means that the data of the current construction location i and the construction process j cannot be associated; The result h of whether the construction location i and construction process j data are associated in the tth weak classifier in the AdaBoost algorithm t (x) Determined by: Calculate the historical correlation ratio P of the combination x of the data of the current construction location i and the construction process j x , n x is the historical association times of the combination x of the data of the current construction location i and the construction process j, M is the total historical association times of the current construction location i and the construction process, and the preset threshold δ is x >δ, then h t (x) The result is associated, otherwise it is not associated.

7. A method for predicting the association between construction locations and construction procedures, characterized in that: include: According to the historical correlation results of the data of construction sites and construction processes, the AdaBoost algorithm is used to establish a correlation prediction model; The data of the current construction location and construction process are input into the association prediction model to obtain the association prediction results of the data of the current construction location and construction process.

8. The method for predicting the association between construction locations and construction procedures according to claim 7, characterized in that: Also includes: The historical correlation results of the data of all construction locations and construction processes at the construction site are collected, and the historical correlation results are preprocessed.

9. The method for predicting the association between construction locations and construction processes according to claim 7, characterized in that: Also includes: The correctness of the association prediction result is judged. If the association prediction result is judged to be wrong, the number of weak classifiers in the AdaBoost algorithm is increased by one for each error.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method for predicting the association between the construction location and the construction process described in any one of claims 7 to 9 is implemented.

Images