A construction site inspection method based on data processing

Abstract

The present invention discloses a construction site inspection method based on data processing, comprising the following steps: S1, obtaining the current inspection information of a PDA handheld terminal, and determining the operation and maintenance inspection attribute of the current inspection information; S2, traversing the current inspection information, correcting the erroneous text of the current inspection information, and obtaining valid inspection information; S3, marking the valid inspection information according to the operation inspection attribute. The present invention marks the important text in the valid inspection information, highlights the key points, facilitates users to quickly grasp the inspection information obtained by the PDA handheld terminal, and can effectively improve work efficiency.

Description

Technical Field

[0001] The invention belongs to the technical field of information processing, and in particular relates to a construction site inspection method based on data processing. Background Art

[0002] In modern construction site management, inspection work is crucial to ensure construction safety, quality and progress. Traditional site inspection methods mainly rely on manual recording and post-processing, which is not only inefficient but also prone to errors, making it difficult to achieve real-time monitoring and effective management of site conditions. With the rapid development of information technology, especially the widespread application of mobile smart terminals and data processing technology, new solutions have been provided for site inspection.

[0003] In recent years, PDA handheld terminals have been widely used in construction site inspections due to their portability, ease of operation, and powerful data processing capabilities. Through PDA handheld terminals, inspectors can record problems found during the inspection in real time, take photos to preserve evidence, and upload text information to the background management system to realize the digitization and instantaneity of inspection information. However, due to the complexity of the construction site environment and the differences in inspectors, inspection information is often lengthy and complex, and may contain a lot of unimportant information, resulting in a lack of focus on inspection information and difficulty in obtaining important information points.

[0004] In order to overcome the above problems and improve the efficiency and accuracy of construction site inspections, the industry has begun to explore construction site inspection methods based on data processing, which can quickly screen and annotate construction site inspection information. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a construction site inspection method based on data processing.

[0006] The technical solution of the present invention is: a construction site inspection method based on data processing comprises the following steps:

[0007] S1. Obtain the current inspection information of the PDA handheld terminal and determine the operation and maintenance inspection attributes of the current inspection information;

[0008] S2. Traverse the current inspection information, correct the erroneous text of the current inspection information, and obtain valid inspection information;

[0009] S3. According to the operation inspection attributes, the effective inspection information is highlighted.

[0010] Furthermore, S1 includes the following sub-steps:

[0011] S11, obtaining the current inspection information of the PDA handheld terminal, and extracting several keywords of each complete sentence in the current inspection information;

[0012] S12, determining the collaborative attribute of each keyword according to the context of the sentence in which each keyword is located;

[0013] S13, extracting a collaborative set of current inspection information according to the collaborative attribute of each keyword;

[0014] S14. Obtain the title of each existing inspection information in the database, and determine the operation and maintenance inspection attribute of the current inspection information in combination with the coordinated set of the current inspection information.

[0015] The beneficial effect of the above further scheme is: in the present invention, in S11, there are many methods for extracting keywords, such as unsupervised keyword extraction methods. After the inspection personnel generate the inspection information, it is necessary to match it with the existing information titles in the database, and comprehensively analyze to obtain the operation and maintenance inspection attributes that characterize the important content of the inspection information. The titles of the existing inspection information in the database are manually generated. The staff names the titles for the existing inspection information that has been highlighted. The titles can reflect the important information of the existing inspection information, and therefore can be used to participate in the generation of operation and maintenance inspection attributes of the current inspection information.

[0016] Furthermore, in S12, the collaborative attribute of the kth keyword in the hth sentence The calculation formula is:

[0017] ; In the formula, Represents the word vector of the kth keyword in the hth sentence, represents the word vector of the mth word in the h+1th sentence, represents the word vector of the nth word in the h-1th sentence, M represents the number of words contained in the h+1th sentence, N represents the number of words contained in the h-1th sentence, and c represents a constant. represents the number of times the kth keyword in the hth sentence appears in the h+1th sentence, It represents the number of times the kth keyword in the hth sentence appears in the h-1th sentence.

[0018] Further, S13 includes the following sub-steps:

[0019] S131, extracting a keyword with the largest synergy attribute and a keyword with the smallest synergy attribute as a super-influence keyword and a marginal-influence keyword, respectively;

[0020] S132, calculating the link value between the remaining keywords and the super-influence keywords, and calculating the irrelevant value between the remaining keywords and the marginal-influence keywords;

[0021] S133, adding the link value and irrelevant value of the remaining keywords and taking the reciprocal as the synergy value of the remaining keywords;

[0022] S134. The remaining keywords corresponding to the coordination values ​​greater than the average of all coordination values ​​are taken as the coordination set of the current inspection information.

[0023] Furthermore, in S132, the link value L between the remaining i-th keyword and the super influential keyword i1 The calculation formula is:

[0024] ; In the formula, SAME i represents the collaborative attributes of the remaining i-th keywords, Indicates the collaborative attributes of super-influential keywords, a i Represents the word vector of the remaining i-th keyword;

[0025] In S132, the irrelevant value L between the remaining i-th keywords and the marginal impact keywords i2 The calculation formula is:

[0026] ; In the formula, Indicates the collaborative properties of marginally influential keywords.

[0027] Further, S14 includes the following sub-steps:

[0028] S141, calculating the text similarity between the collaborative set of current inspection information and the titles of each existing inspection information in the database;

[0029] S142, removing stop words from the title with the highest text similarity, and generating reference information;

[0030] S143. Use the reference information and the collaborative set as operation and maintenance inspection attributes of the current inspection information.

[0031] Furthermore, in S3, the contents in the effective inspection information that have the same attributes as the operation and maintenance inspection are highlighted.

[0032] The beneficial effect of the above further scheme is: in the present invention, the operation and maintenance inspection attributes include many words, such as {network, speeding, trajectory, heat map}, then the words "network", "speeding", "trajectory" and "heat map" in the effective inspection information are highlighted (for example, marked in red) to complete the marking.

[0033] The beneficial effects of the present invention are:

[0034] (1) In the construction site inspection method, the current inspection information generated by the PDA handheld terminal after the work is completed is combined with the title of the existing inspection information in the database to generate the operation and maintenance inspection attributes of the current inspection information; the operation and maintenance inspection attributes contain many key contents of the current inspection information and can be used for key marking;

[0035] (2) In the construction site inspection method, the erroneous text of the current inspection information is also corrected to ensure the accuracy of the inspection information and obtain valid inspection information;

[0036] (3) In this construction site inspection method, important text in the effective inspection information is marked according to the operation and maintenance inspection attributes to highlight the key points, which makes it easier for users to quickly grasp the inspection information obtained by the PDA handheld terminal. This can effectively improve the efficiency of understanding the construction site situation and is of great significance for improving the construction site management level and ensuring the construction quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The flowchart of the construction site inspection method based on data processing. DETAILED DESCRIPTION

[0038] The embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0039] like Figure 1 As shown, the present invention provides a construction site inspection method based on data processing, comprising the following steps:

[0040] S1. Obtain the current inspection information of the PDA handheld terminal and determine the operation and maintenance inspection attributes of the current inspection information;

[0041] S2. Traverse the current inspection information, correct the erroneous text of the current inspection information, and obtain valid inspection information;

[0042] S3. According to the operation inspection attributes, the effective inspection information is highlighted.

[0043] In this embodiment of the present invention, S1 includes the following sub-steps:

[0044] S11, obtaining the current inspection information of the PDA handheld terminal, and extracting several keywords of each complete sentence in the current inspection information;

[0045] S12, determining the collaborative attribute of each keyword according to the context of the sentence in which each keyword is located;

[0046] S13, extracting a collaborative set of current inspection information according to the collaborative attribute of each keyword;

[0047] S14. Obtain the title of each existing inspection information in the database, and determine the operation and maintenance inspection attribute of the current inspection information in combination with the coordinated set of the current inspection information.

[0048] In the present invention, in S11, there are many methods for extracting keywords, such as unsupervised keyword extraction methods. After the inspection personnel generate the inspection information, it is necessary to match it with the existing information titles in the database, and comprehensively analyze to obtain the operation and maintenance inspection attributes that characterize the important content of the inspection information. The titles of the existing inspection information in the database are manually generated. The staff names the titles for the existing inspection information that has been highlighted. The titles can reflect the important information of the existing inspection information, and therefore can be used to participate in the generation of the operation and maintenance inspection attributes of the current inspection information.

[0049] In the embodiment of the present invention, in S12, the collaborative attribute of the kth keyword in the hth sentence The calculation formula is:

[0050] ; In the formula, Represents the word vector of the kth keyword in the hth sentence, represents the word vector of the mth word in the h+1th sentence, represents the word vector of the nth word in the h-1th sentence, M represents the number of words contained in the h+1th sentence, N represents the number of words contained in the h-1th sentence, and c represents a constant. represents the number of times the kth keyword in the hth sentence appears in the h+1th sentence, It represents the number of times the kth keyword in the hth sentence appears in the h-1th sentence.

[0051] In the embodiment of the present invention, S13 includes the following sub-steps:

[0052] S131, extracting a keyword with the largest synergy attribute and a keyword with the smallest synergy attribute as a super-influence keyword and a marginal-influence keyword, respectively;

[0053] S132, calculating the link value between the remaining keywords and the super-influence keywords, and calculating the irrelevant value between the remaining keywords and the marginal-influence keywords;

[0054] S133, adding the link value and irrelevant value of the remaining keywords and taking the reciprocal as the synergy value of the remaining keywords;

[0055] S134. The remaining keywords corresponding to the coordination values ​​greater than the average of all coordination values ​​are taken as the coordination set of the current inspection information.

[0056] In the embodiment of the present invention, in S132, the link value L between the remaining i-th keyword and the super-influential keyword i1 The calculation formula is:

[0057] ; In the formula, SAME irepresents the collaborative attributes of the remaining i-th keywords, Indicates the collaborative attributes of super-influential keywords, a i Represents the word vector of the remaining i-th keyword;

[0058] In S132, the irrelevant value L between the remaining i-th keywords and the marginal impact keywords i2 The calculation formula is:

[0059] ; In the formula, Indicates the collaborative properties of marginally influential keywords.

[0060] In this embodiment of the present invention, S14 includes the following sub-steps:

[0061] S141, calculating the text similarity between the collaborative set of current inspection information and the titles of each existing inspection information in the database;

[0062] S142, removing stop words from the title with the highest text similarity, and generating reference information;

[0063] S143. Use the reference information and the collaborative set as operation and maintenance inspection attributes of the current inspection information.

[0064] In the embodiment of the present invention, in S3, the content in the valid inspection information that is the same as the operation and maintenance inspection attribute is highlighted.

[0065] In the present invention, the operation and maintenance inspection attributes include many words, such as {network, speeding, trajectory, heat map}, and the words "network", "speeding", "trajectory" and "heat map" in the effective inspection information are highlighted (for example, marked in red) to complete the marking.

[0066] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. A construction site inspection method based on data processing, characterized in that: The following steps are involved: S1. Obtain the current inspection information of the PDA handheld terminal and determine the operation and maintenance inspection attributes of the current inspection information; S2. Traverse the current inspection information, correct the erroneous text of the current inspection information, and obtain valid inspection information; S3. According to the operation inspection attributes, the effective inspection information is marked; The S1 comprises the following sub-steps: S11, obtaining the current inspection information of the PDA handheld terminal, and extracting several keywords of each complete sentence in the current inspection information; S12, determining the collaborative attribute of each keyword according to the context of the sentence in which each keyword is located; S13, extracting a collaborative set of current inspection information according to the collaborative attribute of each keyword; S14, obtaining the title of each existing inspection information in the database, and determining the operation and maintenance inspection attribute of the current inspection information in combination with the collaborative set of the current inspection information; In S12, the collaborative attribute of the kth keyword in the hth sentence The calculation formula is: ; In the formula, Represents the word vector of the kth keyword in the hth sentence, represents the word vector of the mth word in the h+1th sentence, represents the word vector of the nth word in the h-1th sentence, M represents the number of words contained in the h+1th sentence, N represents the number of words contained in the h-1th sentence, and c represents a constant. represents the number of times the kth keyword in the hth sentence appears in the h+1th sentence, Indicates the number of times the kth keyword in the hth sentence appears in the h-1th sentence; The S13 includes the following sub-steps: S131, extracting a keyword with the largest synergy attribute and a keyword with the smallest synergy attribute as a super-influence keyword and a marginal-influence keyword, respectively; S132, calculating the link value between the remaining keywords and the super-influence keywords, and calculating the irrelevant value between the remaining keywords and the marginal-influence keywords; S133, adding the link value and irrelevant value of the remaining keywords and taking the reciprocal as the synergy value of the remaining keywords; S134, taking the remaining keywords corresponding to the synergy values ​​greater than the average of all synergy values ​​as the synergy set of the current inspection information; In S132, the link value L between the remaining i-th keyword and the super influential keyword i1 The calculation formula is: ; In the formula, SAME i represents the collaborative attributes of the remaining i-th keywords, Indicates the collaborative attributes of super-influential keywords, a i Represents the word vector of the remaining i-th keyword; In S132, the irrelevant value L between the remaining i-th keyword and the marginal impact keyword i2 The calculation formula is: ; In the formula, Indicates the collaborative properties of marginally influential keywords; The S14 comprises the following sub-steps: S141, calculating the text similarity between the collaborative set of current inspection information and the titles of each existing inspection information in the database; S142, removing stop words from the title with the highest text similarity, and generating reference information; S143. Use the reference information and the collaborative set as operation and maintenance inspection attributes of the current inspection information.

2. The construction site inspection method based on data processing according to claim 1, characterized in that: In S3, the contents in the valid inspection information that are the same as the operation and maintenance inspection attributes are highlighted.

Images