Project quality problem reason analysis method based on automatic acquisition of control statements
By automatically obtaining and analyzing control statements for project quality problems, the problem of low accuracy in the analysis of project quality causes in the existing technology is solved, and the cause of quality problems is quickly and accurately positioned, improving the efficiency and accuracy of construction quality management , especially for high-frequency issues, key supervision has been carried out.
Patent Information
- Application Number
- CN202411029363.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-12-06
AI Technical Summary
During the analysis of the causes of existing projects, the accuracy is not high, and it is difficult to find the causes of quality problems from the source of construction, making it difficult to provide effective technical solutions for optimization and supervision in construction quality management.
Using the method of analysis of the cause of engineering quality problems automatically obtained based on control statements, collect and convert the quality acceptance specification text of the project, use jieba word segmentation, destop words and regular expressions to extract keywords, form a control statement library, and analyze it through comparison Actual construction technical measures and standardized measures, refine the statement library, reduce the number of statements, and improve analysis efficiency and accuracy.
It has achieved rapid and accurate positioning of the causes of quality problems, improved the work efficiency and result accuracy of the analysis of causes of quality problems, and provided key prevention links and regulatory details for future engineering construction quality management, especially for high-frequency quality problems. Focus on strengthening supervision.
Smart Images

Figure CN119088958A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of building engineering construction quality research, and in particular relates to a method for analyzing causes of engineering quality problems automatically acquired based on control statements. Background Art
[0002] The quality issue of construction projects is an important topic in the current research and analysis of engineering accidents, and the quality management of construction projects can prevent the occurrence of quality accidents to a certain extent. Therefore, it is necessary to conduct in-depth research on the quality of construction projects.
[0003] The existing project quality cause analysis process is based on direct inference by experts reading quality reports. The conclusions drawn are wide-ranging and not very accurate. It is difficult to find the causes of quality problems from the source of construction, resulting in the inability to provide timely optimization references for technical solutions for other projects, making it difficult to ensure construction quality and unable to focus on strengthening supervision in future project construction quality management work. Summary of the invention
[0004] In order to solve the above problems, the present invention provides a method for analyzing the causes of engineering quality problems based on automatic acquisition of control statements, which solves the problem of low accuracy in analyzing the causes of engineering quality problems.
[0005] The present invention is implemented by the following scheme: a method for analyzing the causes of engineering quality problems based on automatic acquisition of control statements, the method comprising the following steps:
[0006] S1. Collect the text of project quality acceptance specifications and establish a set of project quality acceptance specifications;
[0007] S2, converting the acquired engineering project quality acceptance specification set into a format that can be processed by a computer;
[0008] S3, performing Jieba word segmentation, stop word removal and keyword extraction operations on the engineering project quality acceptance specification set after format conversion;
[0009] S4. Based on the acquired keywords and the engineering project quality acceptance specification set, regular expressions are used to extract and classify control statements, and a control statement library is formed;
[0010] S5. Select and analyze multiple samples of quality problem reports of actual engineering projects, and count the quality problems that need to be analyzed;
[0011] S6. Invite experts to select several control statements corresponding to the quality problems that need to be analyzed from the control statement library, and compare and analyze the construction technical measures of the engineering project quality acceptance specifications corresponding to the control statements with the actual construction technical measures corresponding to the quality problems that need to be analyzed, so as to find out the causes of the quality problems that need to be analyzed.
[0012] A further improvement of the method for analyzing the causes of engineering quality problems automatically acquired based on control statements of the present invention is that the quality problems that need to be analyzed are quality problems that occur with high frequency.
[0013] A further improvement of the method for analyzing the causes of engineering quality problems automatically acquired based on control statements of the present invention is that, when executing step S4, control statements are extracted and classified according to the sub-projects; when executing step S5, quality problems are classified according to the sub-projects; when executing step S6, a comparative analysis is performed between the construction technical measures of the engineering project quality acceptance specifications corresponding to the control statements and the actual construction technical measures corresponding to the quality problems that need to be analyzed according to the sub-projects.
[0014] A further improvement of the method for automatically obtaining causes of engineering quality problems based on control statements of the present invention is that the regular expression is a re regular expression.
[0015] A further improvement of the method for analyzing the causes of engineering quality problems based on automatic acquisition of control statements of the present invention is that the extraction and classification of control statements according to sub-projects specifically includes the following steps:
[0016] Use re.findall to complete control statement extraction;
[0017] The control statements are classified and sorted according to the sub-projects, all the information in the engineering project quality acceptance specifications is screened, and the statements with low correlation with keywords are eliminated. On this basis, the control statements are classified into sub-projects.
[0018] A further improvement of the method for automatically obtaining causes of engineering quality problems based on control statements of the present invention is that the engineering project quality acceptance specification text includes the national standard unified standard for construction quality acceptance of building projects and the construction standard file of the building industry.
[0019] A further improvement of the method for analyzing the causes of engineering quality problems automatically acquired based on control statements of the present invention is that step S3 specifically includes the following steps:
[0020] S31. Generate word segmentation results using the Jieba Chinese word segmentation library to achieve accurate segmentation of sentences without redundant data;
[0021] S32. On the basis of the general stop word library, add words that are common in the construction field but have a low correlation with quality issues to form a stop word list; remove stop words according to the stop word list;
[0022] S33. Use keyword extraction method to extract keywords from the engineering project quality acceptance specification set.
[0023] A further improvement of the method for analyzing causes of engineering quality problems automatically acquired based on control statements of the present invention is that the keyword extraction method is a TF-IDF algorithm.
[0024] A further improvement of the method for automatically obtaining causes of engineering quality problems based on control statements of the present invention is that step S2 also includes the step of: manually deleting the information with accompanying English content during the process of converting the format of the engineering project quality acceptance specification set; the information with English content includes an English abstract and an English directory.
[0025] A further improvement of the method for analyzing the causes of engineering quality problems automatically acquired based on control statements of the present invention is that the format that can be processed secondary by the computer is a txt format.
[0026] Compared with the prior art, the present invention has the following beneficial effects:
[0027] The present invention uses re.findall to complete control statement extraction, and then uses the re regular expression to classify and sort the acquired control statements according to each sub-project, which can effectively reduce the number of statements in the control statement library, achieve the purpose of refining the statement library, and solve the problem that the existing engineering specifications cover a variety of sub-projects, the number of statements is large and the types are complicated; by comparing and analyzing the construction technical measures of the engineering project quality acceptance specification corresponding to the sub-project control statement and the actual construction technical measures corresponding to the sub-project quality problem that needs to be analyzed, the cause of the quality problem that needs to be analyzed is obtained, thereby further improving the work efficiency and result accuracy of the quality problem cause analysis, and achieving the purpose of quickly and accurately locating the cause of the quality problem; the reasons obtained by analysis are items that do not meet the requirements of the construction technical measures specification, which points out the key prevention links for the construction quality management of future projects, clarifies the details that need to be strengthened in the future construction quality management of projects, and focuses on strengthening the supervision of construction details for quality problems that occur frequently, and jointly improves the efficiency of project quality management from the two aspects of cause analysis and operation control. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] Figure 1 A schematic diagram of the quality problem cause analysis process of the present invention is shown.
[0029] Figure 2A schematic diagram of keyword extraction results according to an embodiment of the present invention is shown.
[0030] Figure 3 A schematic diagram showing the manifestation of the basement leakage problem described in an embodiment of the present invention is shown. DETAILED DESCRIPTION
[0031] In order to solve the problem of low accuracy in cause analysis of engineering quality problems, the present invention provides a method for automatically obtaining cause analysis of engineering quality problems based on control statements. The following is a further description of the method for automatically obtaining cause analysis of engineering quality problems based on control statements using a specific embodiment in combination with the accompanying drawings.
[0032] See also Figure 1 to Figure 3 As shown, a method for analyzing the causes of engineering quality problems based on automatic acquisition of control statements comprises the following steps:
[0033] S1. Collect the texts of the quality acceptance specifications for the engineering project (in this embodiment, the selection of the quality acceptance specifications is mainly based on the concrete structure sub-projects, and finally a total of 35 relevant engineering specifications such as GB 50204-2015 "Concrete Structure Engineering Construction Quality Acceptance Specifications" are selected), and establish a set of quality acceptance specifications for the engineering project;
[0034] S2. Convert the acquired engineering project quality acceptance specification set into a txt format that can be processed by a computer. During the process, manually delete the information with English content; the English content information includes an English abstract and an English directory;
[0035] S3, performing Jieba word segmentation, stop word removal and keyword extraction operations on the converted engineering project quality acceptance specification set in sequence, specifically including the following steps:
[0036] S31. Generate word segmentation results using the Jieba Chinese word segmentation library to achieve accurate segmentation of sentences without redundant data;
[0037] S32. On the basis of common stop word libraries such as the stop word library of Harbin Institute of Technology, the stop word library of the Machine Learning Laboratory of Sichuan University, and the stop word list of Baidu, words that are commonly used in construction fields such as construction engineering, planning, and engineering general contracting but have a low correlation with quality issues are added to form a stop word list; and stop words are removed according to the stop word list;
[0038] S33, extracting keywords from the engineering project quality acceptance specification set using a keyword extraction method;
[0039] Use Python 3.7 to write the code for Jieba word segmentation, stop word removal and TF-IDF keyword extraction method; after running the program, it summarizes and extracts 5 document keywords: "concrete", "casting", "rebar", "construction", and "template". The code running results are shown in the attached Figure 2 As shown;
[0040] The specific calculation formula of the TF-IDF algorithm is:
[0041]
[0042]
[0043] TF-IDF=TF*IDF;
[0044] Among them, TF refers to term frequency, IDF refers to inverse document frequency;
[0045] S4. Based on the acquired keywords and the engineering project quality acceptance specification set, use the re regular expression to extract and classify control statements according to the sub-projects, and form a control statement library;
[0046] The extraction and classification of control statements according to the sub-projects specifically includes the following steps:
[0047] Use re.findall to complete control statement extraction;
[0048] Classify and sort out the control statements according to the sub-projects, conduct a preliminary screening of all the information in the project quality acceptance specifications, eliminate the statements with low correlation with the keywords, and classify the control statements into sub-projects on this basis;
[0049] In this embodiment, the control statements are classified according to the concrete structure sub-projects, and divided into 6 sub-projects: steel bar engineering, concrete engineering, formwork engineering, cast-in-place structure engineering, prestressed engineering, and prefabricated structure engineering; after the program is run and the results are sorted, a total of 398 quality control statements are extracted, including 83 steel bar engineering, 213 concrete engineering, 66 formwork engineering, 6 cast-in-place structure engineering, 17 prestressed engineering, and 13 prefabricated engineering. The classification results are shown in Table 1 below;
[0050] Table 1 Example of classification results of control statements for concrete structure construction engineering
[0051]
[0052] The control statements obtained after screening have the defects of too many and low precision. In order to further improve the accuracy of statement extraction, the document keywords are used for secondary extraction; taking concrete engineering as an example, the first extraction classification result obtained a total of 213 statements; based on this classification result, the remaining 4 keywords "casting", "rebar", "construction", and "formwork" are used for secondary extraction; after the program is run, the second classification result of concrete engineering obtains a total of 136 statements, which is 77 statements filtered out compared with the first extraction result, effectively improving the accuracy; and so on, the classification results of the remaining 5 sub-projects are extracted for secondary extraction, and a total of 241 statements are obtained;
[0053] S5. Select and analyze multiple samples of quality problem reports from actual engineering projects, and count the types of quality problems and their frequency of occurrence;
[0054] In this embodiment, 63 concrete structure construction project quality problem reports from 37 engineering units were selected as analysis samples, and a preliminary analysis of the quality problems existing in concrete structure construction projects was completed using statistical methods. The specific quality problems and frequency statistics are shown in Table 2 below:
[0055] Table 2 Summary and frequency statistics of quality problems in concrete structure construction projects
[0056] Question Category Number of questions Proportion Roof waterproofing leakage 37 7.31% Waterproof leakage of exterior walls, doors and windows 50 9.88% Basement waterproofing leakage 54 10.67% Waterproof leakage of floor and bathroom 41 8.10% Infill wall cracking 34 6.72% The masonry joints are not full 17 3.36% Cracks in concrete floors and ground 28 5.53% Wall plaster cracks 25 4.94% External wall insulation issues 4 0.79% Defects in concrete components 61 12.06% Steel bar position deviation, insufficient pad protection layer 36 7.11% Formwork reinforcement and cleaning 41 8.10% Structural column and masonry construction errors 29 5.73% Quality of coating works 16 3.16% Other quality issues 33 6.52%
[0057] Statistics show that leakage and crack problems account for as much as 56% of engineering quality problems. Leakage and crack problems will have a great impact on the later use function of the building. As a frequent project of engineering quality problems, continuous follow-up inspection is required to strengthen quality risk management. The basement is a typical concrete structure construction project. Common engineering quality problems in the basement are concentrated on leakage and cracks caused by cracks and joints in the concrete structure. Combined with the quality inspection report, the manifestations of basement leakage problems in multiple projects are summarized and sorted out, as shown in the attached figure. Figure 3 As shown;
[0058] S6. Invite technical experts in the industry to conduct interviews. The experts select several control statements of the sub-projects corresponding to the quality problems from the control statement library, and compare and analyze the construction technical measures of the project quality acceptance specifications corresponding to the control statements with the actual construction technical measures corresponding to the quality problems, and find out the reasons for the quality problems of the project, which are the items that do not meet the requirements of the construction technical measures specifications;
[0059] In this embodiment, taking the basement leakage problem as an example, combined with the established quality acceptance specification set, the reasons for the basement leakage problem caused by cracks in the concrete structure are discussed; 5 technical quality experts in the industry are invited to interview the basement leakage quality problem, including 1 chief engineer, 2 quality directors, and 2 technical leaders. According to the control statement library established above, the experts select several control statements that are most closely related to the basement leakage quality problem, and establish a correlation between the control statements and the reasons behind the quality appearance; according to the results of the expert interviews, the basement leakage quality problem may be caused by a total of 101 specific reasons, as shown in Table 3 below:
[0060] Table 3 Causes of basement leakage quality problems
[0061]
[0062] The results show that the occurrence of basement leakage quality problems is not caused by the non-compliance of the construction of a single sub-project, but the result of the combined effect of multiple sub-project factors; among them, "concrete engineering construction" has the most significant impact on basement leakage problems. From multiple angles such as concrete material production, transportation and pouring, on-site construction management, setting of post-construction joints, pouring and vibration maintenance, and winter construction, a total of 70 specific reasons were summarized.
[0063] The process and results of this study point out the key preventive links for the construction quality management of other basement structure projects.
[0064] The present invention automatically and quickly locks the quality specification control statements corresponding to the quality appearance problems, obtains the construction technical measures that do not meet the quality specifications through comparative analysis, and then analyzes the possible causes of quality problems. At the same time, it clarifies the details that need to be strengthened in the future engineering construction quality management work, and jointly improves the efficiency of engineering quality management from the two aspects of cause analysis and operation control.
[0065] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0066] The present invention is described in detail above in conjunction with the embodiments of the accompanying drawings. A person skilled in the art can make various variations of the present invention according to the above description. Therefore, certain details in the embodiments should not constitute a limitation of the present invention, and the scope of protection of the present invention shall be defined by the scope of the attached claims.
Claims
1. A method for analyzing the causes of engineering quality problems based on automatic acquisition of control statements, characterized in that: The method comprises the following steps: S1. Collect the text of project quality acceptance specifications and establish a set of project quality acceptance specifications; S2, converting the acquired engineering project quality acceptance specification set into a format that can be processed by a computer; S3, performing Jieba word segmentation, stop word removal and keyword extraction operations on the engineering project quality acceptance specification set after format conversion; S4. Based on the acquired keywords and the engineering project quality acceptance specification set, regular expressions are used to extract and classify control statements, and a control statement library is formed; S5. Select and analyze multiple samples of quality problem reports of actual engineering projects, and count the quality problems that need to be analyzed; S6. Invite experts to select several control statements corresponding to the quality problems that need to be analyzed from the control statement library, and compare and analyze the construction technical measures of the engineering project quality acceptance specifications corresponding to the control statements with the actual construction technical measures corresponding to the quality problems that need to be analyzed, so as to find out the causes of the quality problems that need to be analyzed.
2. The method for analyzing the causes of engineering quality problems based on automatic acquisition of control statements according to claim 1 is characterized in that: The quality problems that need to be analyzed are quality problems that occur frequently.
3. The method for analyzing the causes of engineering quality problems based on automatic acquisition of control statements according to claim 1 is characterized in that: When executing step S4, control statements are extracted and classified according to the sub-projects; when executing step S5, quality problems are classified according to the sub-projects; when executing step S6, construction technical measures of the project quality acceptance specifications corresponding to the control statements and actual construction technical measures corresponding to the quality problems that need to be analyzed are compared and analyzed according to the sub-projects.
4. The method for analyzing the causes of engineering quality problems based on automatic acquisition of control statements according to claim 3 is characterized in that: The regular expression is a re regular expression.
5. The method for analyzing the causes of engineering quality problems based on automatic acquisition of control statements according to claim 4 is characterized in that: The extraction and classification of control statements according to the sub-projects specifically includes the following steps: Use re.findall to complete control statement extraction; The control statements are classified and sorted according to the sub-projects, all the information in the engineering project quality acceptance specifications is screened, and the statements with low correlation with keywords are eliminated. On this basis, the control statements are classified into sub-projects.
6. The method for analyzing the causes of engineering quality problems based on automatic acquisition of control statements according to claim 1 is characterized in that: The engineering project quality acceptance specification text includes the national standard unified standard for construction quality acceptance of construction projects and the construction industry construction standard documents.
7. The method for analyzing the causes of engineering quality problems based on automatic acquisition of control statements according to claim 1 is characterized in that: The step S3 specifically comprises the following steps: S31. Generate word segmentation results using the Jieba Chinese word segmentation library to achieve accurate segmentation of sentences without redundant data; S32. On the basis of the general stop word library, add words that are common in the construction field but have a low correlation with quality issues to form a stop word list; remove stop words according to the stop word list; S33. Use keyword extraction method to extract keywords from the engineering project quality acceptance specification set.
8. The method for analyzing the causes of engineering quality problems based on automatic acquisition of control statements according to claim 7 is characterized in that: The keyword extraction method is the TF-IDF algorithm.
9. The method for analyzing the causes of engineering quality problems based on automatic acquisition of control statements according to claim 1, characterized in that: The step S2 also includes the step of: manually deleting the information with English content during the process of converting the format of the engineering project quality acceptance specification set; the information with English content includes an English abstract and an English directory.
10. The method for analyzing the causes of engineering quality problems based on automatic acquisition of control statements according to claim 1, characterized in that: The format that can be processed by the computer is txt format.
Citation Information
Patent Citations
Construction project supervision information management method and system
CN110322147A
Intelligent generation method and system for engineering construction scheme compilation basis
CN115982329A
Standardized acceptance method and terminal for residential distribution project
CN116629786A
KR20230160596A
