A building engineering management system and its management method

Abstract

This application relates to the technical field of project management. Specifically, it discloses a construction project management system and its management method. It uses data processing technology based on deep learning to semantically analyze the electronic materials of target laborers to extract the identity information characteristics of the laborers. At the same time, in combination with the pre-established construction requirement rules, by performing semantic query response encoding on the identity information of the laborers and a large number of construction requirement rules, the potential matching relationship between the laborers and the construction project is mined, so as to realize the intelligent evaluation of the suitability of the laborers. This application can more comprehensively and accurately evaluate whether the laborers meet the specific requirements of the construction project, and effectively avoid construction problems caused by insufficient skills or lack of experience of the laborers.

Description

Technical Field

[0001] This application relates to the technical field of project management, and more specifically, to a construction project management system and its management method. Background Art

[0002] In the field of construction projects, effectively managing the construction progress, personnel, and materials is the key to ensuring the smooth progress of the project. With the rapid development and technological progress of the construction industry, traditional manual management methods have gradually revealed problems such as low efficiency, untimely data processing, and difficulty in comprehensive monitoring. In response to this, the invention patent with the publication number CN118840072A proposes a management system for construction projects, which is provided with a project management module, a personnel information module, an engineering materials module, and a supervision module. It can not only supervise the progress of engineering projects, the construction conditions of construction personnel, the consumption of construction materials, and the construction environment status, but also realize the risk assessment of labor construction personnel to ensure that all personnel participating in the construction meet the construction requirements and ensure the smooth progress of the project.

[0003] However, the existing technology mainly judges whether laborers meet the requirements of construction projects by judging whether the identity documents of laborers are valid, checking whether laborers are within the legal working age, and confirming whether laborers are monitored persons, while ignoring important factors such as the professional skills, work experience, and suitability of laborers for specific construction projects. Therefore, in actual applications, there may be situations where laborers meet the basic identity requirements but are unable to effectively complete construction tasks due to insufficient skills or lack of experience, thus affecting the overall progress and quality of engineering projects.

[0004] Therefore, an optimized construction project management system and its management method are expected. Summary of the Invention

[0005] In order to solve the above technical problems, this application is proposed. The embodiments of this application provide a construction project management system and its management method, which use data processing technology based on deep learning to perform semantic analysis on the electronic materials of target laborers to extract the identity information characteristics of laborers. At the same time, combined with the pre-established construction requirement rules, by performing semantic query response encoding on the identity information of laborers and a large number of construction requirement rules, the potential matching relationship between laborers and construction projects is mined, so as to realize the intelligent evaluation of the suitability of laborers. In this way, it is possible to more comprehensively and accurately evaluate whether laborers meet the specific requirements of construction projects, and effectively avoid construction problems caused by insufficient skills or lack of experience of laborers.

[0006] Accordingly, according to one aspect of the present application, a construction project management system is provided, which includes: a central processing unit module for two-way data interaction with other modules; a storage module for storing various data information of construction projects; a control module for receiving user operation instructions through a connected touch screen to control and manage other modules; a project management module for recording and managing various information of the project; a personnel information module for judging and evaluating labor personnel information, creating files for them and conducting daily attendance management; an engineering materials module for collecting, classifying and managing material information required for construction; a supervision module for judging the suitability of the current environmental state for construction based on on-site construction environment data.

[0007] In the above construction project management system, the personnel information module includes:

[0008] A labor personnel information acquisition unit for acquiring electronic materials of target labor personnel;

[0009] A construction requirement rule acquisition unit for extracting a set of construction requirement rules from a construction project rule library;

[0010] An identity information structured coding unit for performing structured coding on the electronic materials to obtain a comprehensive structured coding vector of the target labor personnel identity information;

[0011] A construction requirement rule semantic understanding unit for extracting semantic features of each construction requirement rule in the set of construction requirement rules to obtain a set of construction requirement rule semantic embedding coding vectors;

[0012] A semantic search verification unit for performing identity-rule semantic search verification coding based on dynamic weight regulation on the comprehensive structured coding vector of the target labor personnel identity information and the set of construction requirement rule semantic embedding coding vectors to obtain an identity-construction rule semantic level query response coding vector;

[0013] A labor personnel suitability evaluation unit for determining whether the target labor personnel meet the requirements of the construction project based on the identity-construction rule semantic level query response coding vector.

[0014] According to another aspect of the present application, a construction project management method is provided, which includes:

[0015] Acquiring electronic materials of target labor personnel;

[0016] Extracting a set of construction requirement rules from a construction project rule library;

[0017] Performing structured coding on the electronic materials to obtain a comprehensive structured coding vector of the target labor personnel identity information;

[0018] Extract the semantic features of each construction requirement rule in the set of construction requirement rules to obtain a set of construction requirement rule semantic embedding coding vectors;

[0019] Perform identity-rule semantic search verification coding based on dynamic weight regulation on the comprehensive structured coding vector of the target laborer identity information and the set of construction requirement rule semantic embedding coding vectors to obtain an identity-construction rule semantic-level query response coding vector;

[0020] Based on the identity-construction rule semantic-level query response coding vector, determine whether the target laborer meets the requirements of the construction project.

[0021] Beneficial effects: Compared with the prior art, the construction project management system and its management method provided by the present application use deep learning-based data processing technology to semantically analyze the electronic materials of target laborers to extract the identity information features of the laborers. At the same time, in combination with the pre-established construction requirement rules, by performing semantic query response coding on the identity information of the laborers and a large number of construction requirement rules, the potential matching relationship between the laborers and the construction project is mined, so as to realize the intelligent evaluation of the adaptability of the laborers, and can more comprehensively and accurately evaluate whether the laborers meet the specific requirements of the construction project, effectively avoiding construction problems caused by insufficient skills or lack of experience of the laborers. Description of the Drawings

[0022] By describing the embodiments of the present application in more detail in conjunction with the drawings, the above and other objects, features and advantages of the present application will become more obvious. The drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification, and are used to explain the present application together with the embodiments of the present application, and do not constitute a limitation to the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0023] Figure 1 It is a block diagram of the personnel information module in the construction project management system according to an embodiment of the present application.

[0024] Figure 2 It is a schematic diagram of the data flow of the personnel information module in the construction project management system according to an embodiment of the present application.

[0025] Figure 3 It is a block diagram of the semantic search verification unit in the construction project management system according to an embodiment of the present application.

[0026] Figure 4 It is a block diagram of the feature contribution modeling and evaluation sub-unit in the construction project management system according to an embodiment of the present application.

[0027] Figure 5It is a flowchart of a construction project management method according to an embodiment of the present application. Detailed implementation manners

[0028] As shown in the present application and the claims, unless the context clearly indicates an exception, words such as "a", "an", "one", and / or "the" are not specifically singular and may also include plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0029] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0030] In the present application, flowcharts are used to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in order. On the contrary, as needed, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0031] Next, exemplary embodiments of the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described herein.

[0032] Figure 1 It is a block diagram of the personnel information module in the construction project management system according to an embodiment of the present application. Figure 2 It is a schematic diagram of data flow of the personnel information module in the construction project management system according to an embodiment of the present application. As Figure 1 and Figure 2As shown in the figure, the personnel information module 100 includes: a laborer information acquisition unit 110 for acquiring the electronic materials of the target laborer; a construction requirement rule acquisition unit 120 for extracting a set of construction requirement rules from the construction project rule base; an identity information structured encoding unit 130 for performing structured encoding on the electronic materials to obtain a comprehensive structured encoding vector of the target laborer's identity information; a construction requirement rule semantic understanding unit 140 for extracting the semantic features of each construction requirement rule in the set of construction requirement rules to obtain a set of construction requirement rule semantic embedding encoding vectors; a semantic search verification unit 150 for performing identity-rule semantic search verification encoding based on dynamic weight regulation on the comprehensive structured encoding vector of the target laborer's identity information and the set of construction requirement rule semantic embedding encoding vectors to obtain an identity-construction rule semantic-level query response encoding vector; and a laborer suitability evaluation unit 160 for determining whether the target laborer meets the requirements of the construction project based on the identity-construction rule semantic-level query response encoding vector.

[0033] In the above construction project management system, the laborer information acquisition unit 110 is used to acquire the electronic materials of the target laborer. In a specific example of the present application, the electronic materials include identity cards, special operation certificates, physical examination reports for the most recent three months, safety training certificates, and past project resumes. It should be understood that the identity card is the key certificate for confirming the identity of the laborer, and the information it contains, such as name, gender, date of birth, address, identity card number, etc., is the basis for establishing a personnel file and conducting personnel management. The special operation certificate proves that the laborer has the qualification and ability to engage in specific types of construction work, which is particularly important for construction projects involving high risks or special skills (such as welding, lifting, working at heights, etc.). By confirming the special operation certificate held by the laborer, the safe progress of special operations during construction can be ensured, and safety accidents and violations caused by unqualified personnel qualifications can be avoided. At the same time, the intensity of construction work is high and the environment is complex, which has certain requirements for the physical health of laborers. The physical examination indicators such as blood routine, urine routine, liver function, kidney function, electrocardiogram, and blood pressure detailed in the physical examination report can help managers understand the physical functions and health conditions of laborers. On the one hand, it can ensure that they have enough physical strength and energy to complete the work tasks, and on the other hand, it can prevent sudden diseases during work due to physical reasons, reducing the health risks and potential losses of the project. The safety training certificate indicates that the laborer has received the necessary safety education and training and has mastered basic safety knowledge and operation skills. Laborers holding safety training certificates are more likely to comply with safety regulations during construction, have safety awareness and emergency handling capabilities, which helps to reduce safety accidents at the construction site and ensure a safe construction environment for the project. The past project resume details information such as the construction projects the laborer has participated in, the positions held, work performance, skill levels, and evaluations and awards obtained, which can comprehensively reflect the work experience and ability level of the laborer, helps to evaluate whether they have the experience and ability to participate in the current project, and provides strong reference for personnel position allocation and project team formation. Based on this, the present application comprehensively collects information such as the basic situation, skill qualifications, physical condition, safety awareness, and work experience of the target laborer, provides comprehensive and accurate data support, and helps to avoid problems such as project delays and quality hazards caused by improper personnel selection.

[0034] In the above construction project management system, the construction requirement rule acquisition unit 120 is configured to extract a set of construction requirement rules from a construction project rule library. Specifically, since different construction projects have different requirements and standards in terms of technology, safety, progress, etc. To accurately evaluate whether laborers meet the requirements of a specific construction project, this application extracts a set of construction requirement rules related to the current project from the construction project rule library. By matching and analyzing these construction requirement rules with the electronic materials of the target laborers, the adaptability of the laborers can be evaluated more precisely, ensuring that the selected personnel are capable of performing construction tasks, thereby improving the execution efficiency and quality of the project.

[0035] In the above construction project management system, the identity information structured encoding unit 130 is configured to perform structured encoding on the electronic materials to obtain a comprehensive structured encoding vector of the target laborer's identity information. In a specific example of this application, the identity information structured encoding unit 130 is further configured to: perform structured encoding on each piece of information in the electronic materials to obtain an identity information structured encoding vector, a special operation permit structured encoding vector, a physical examination report structured encoding vector, a safety training certificate structured encoding vector, and a past project resume structured encoding vector. It should be understood that this application takes into account that the original electronic materials of laborers, such as ID card information, certificate texts, physical examination data, etc., usually exist in an unstructured text format. Therefore, in order to convert the original text information into a structured data form recognizable by a computer for subsequent data processing and analysis, this application further performs structured encoding on each piece of information in the electronic materials. In the embodiments of this application, first, natural language processing technology is used to perform named entity recognition on text information such as ID card information, certificate texts, physical examination reports, and past project resumes to extract the key information of each piece of information. Then, a pre-trained word embedding model (such as the BERT model) is used to vectorize the extracted information of each piece of information, so as to map the information of each piece of information into a dense vector form in a high-dimensional semantic space by utilizing the rich language knowledge learned by the word embedding model during the pre-training process, thereby obtaining an identity information structured encoding vector, a special operation permit structured encoding vector, a physical examination report structured encoding vector, a safety training certificate structured encoding vector, and a past project resume structured encoding vector.

[0036] In a specific example of the present application, the identity information structured encoding unit 130 is further configured to: splice the identity information structured encoding vector, the special operation permit structured encoding vector, the physical examination report structured encoding vector, the safety training certificate structured encoding vector, and the past project resume structured encoding vector to obtain the target laborer identity information comprehensive structured encoding vector. Specifically, since the laborer profile information in a single dimension can only reflect certain characteristics of the laborer and cannot comprehensively reflect their comprehensive ability and adaptability. Therefore, the present application further splices the identity information structured encoding vector, the special operation permit structured encoding vector, the physical examination report structured encoding vector, the safety training certificate structured encoding vector, and the past project resume structured encoding vector to integrate multi-dimensional information and form a complete description of the laborer's characteristics, thereby obtaining the target laborer identity information comprehensive structured encoding vector, so as to facilitate a comprehensive and overall matching with the construction requirement rules and improve the accuracy and comprehensiveness of the matching.

[0037] In the above construction project management system, the construction requirement rule semantic understanding unit 140 is configured to extract the semantic features of each construction requirement rule in the set of construction requirement rules to obtain a set of construction requirement rule semantic embedding encoding vectors. It should be understood that construction requirement rules are generally presented in natural language text. In order to convert them into a computable and comparable vectorized form, the present application also uses a pre-trained word embedding model to perform semantic encoding on each construction requirement rule in the set of construction requirement rules to capture the key semantic information of each construction requirement rule and generate a set of construction requirement rule semantic embedding encoding vectors. Those of ordinary skill in the art should be aware that during the pre-training process of the word embedding model, by learning the co-occurrence relationship and context information of words in a large amount of text data, it can map natural language text descriptions into a continuous vector space, making the text information with similar semantics closer in the vector space. Thus, the semantic relevance and matching degree between the construction requirement rules and the laborer identity information can be measured based on the vector distance or similarity in the high-dimensional semantic space, providing strong support for subsequent personnel screening and adaptation analysis.

[0038] In the above construction project management system, the semantic search and verification unit 150 is used to perform identity-rule semantic search and verification coding with dynamic weight regulation on the set of the comprehensive structured coding vector of the target laborer identity information and the semantic embedding coding vector of the construction requirement rules to obtain an identity-construction rule semantic-level query response coding vector. Specifically, the semantic query response coding is further performed on the set of the comprehensive structured coding vector of the target laborer identity information and the semantic embedding coding vector of the construction requirement rules to capture the association and matching relationship between the target laborer and the construction requirement rules. Specifically, to improve the accuracy and efficiency of the matching, the present application proposes an identity-rule semantic search and verification coding method based on dynamic weight regulation. First, the semantic feature dynamic response relationship between the target laborer identity information and each construction requirement rule is captured by means of semantic anchoring. Then, based on the adaptive splicing mechanism, the importance weights of the semantic interaction information in different dimensions in the global context are adaptively learned to generate a set of weighted codings, and the local fine-grained interaction features between the comprehensive information of the target laborer and each construction requirement rule are correlated and fused to generate a highly correlated semantic matching representation between the target laborer and the construction requirement rules, that is, the identity-construction rule semantic-level query response coding vector. Among them, Figure 3 is a block diagram of the semantic search and verification unit in the construction project management system according to an embodiment of the present application. As Figure 3 shown, the semantic search and verification unit 150 includes: a semantic response anchoring coding sub-unit 151, which is used to perform semantic response anchoring coding on each semantic embedding coding vector of the construction requirement rules in the set of the comprehensive structured coding vector of the target laborer identity information and the semantic embedding coding vector of the construction requirement rules to obtain a set of identity-construction rule semantic response anchoring coding matrices; a feature contribution modeling and evaluation sub-unit 152, which is used to perform feature contribution modeling and evaluation on each identity-construction rule semantic response anchoring coding matrix in the set of the identity-construction rule semantic response anchoring coding matrices to obtain a set of identity-construction rule decision anchor adaptive splicing weight factors; a feature fusion sub-unit 153, which is used to fuse the set of the identity-construction rule semantic response anchoring coding matrices based on the set of the identity-construction rule decision anchor adaptive splicing weight factors to obtain the identity-construction rule semantic-level query response coding vector.

[0039] Specifically, in a specific example of the present application, the semantic response anchoring encoding subunit 151 is configured to: perform deep implicit feature extraction based on fully connected encoding on the comprehensive structured encoding vector of the target laborer identity information to obtain a deep implicit encoding vector of the semantic features of the target laborer identity information; perform deep implicit feature extraction based on fully connected encoding on each construction requirement rule semantic embedding encoding vector in the set of construction requirement rule semantic embedding encoding vectors to obtain a set of deep implicit encoding vectors of the semantic features of the construction requirement rules, which is expressed by the formula:

[0040]

[0041] Wherein, represents the set of construction requirement rule semantic embedding encoding vectors, 、 、 and respectively represent the 1st, 2nd, th, and th construction requirement rule semantic embedding encoding vectors in the set of construction requirement rule semantic embedding encoding vectors, is the number of vectors in the set of construction requirement rule semantic embedding encoding vectors, represents the semantic feature weight matrix of the identity information, represents the semantic feature weight matrix of the construction rule, represents the semantic feature bias term of the identity information, represents the semantic feature bias term of the construction rule, represents the comprehensive structured encoding vector of the target laborer identity information, represents the activation function, represents the deep implicit encoding vector of the semantic features of the target laborer identity information, represents the corresponding deep implicit encoding vector of the semantic features of the construction requirement rule.

[0042] Specifically, in order to enhance the semantic expression ability of the target laborer identity information and the construction requirement rules, the present application first performs deep implicit feature extraction based on fully connected encoding on the comprehensive structured encoding vector of the target laborer identity information and each construction requirement rule semantic embedding encoding vector respectively, so as to learn the global non-linear interaction relationship inside the original features through the non-linear mapping of the fully connected neural network, generate a deeper semantic feature representation, and obtain a deep implicit encoding vector of the semantic features of the target laborer identity information and a set of deep implicit encoding vectors of the semantic features of the construction requirement rules.

[0043] Specifically, in a specific example of the present application, the semantic response anchoring encoding subunit 151 is further configured to: respectively input each construction requirement rule semantic feature depth implicit encoding vector in the set of the target laborer identity information semantic feature depth implicit encoding vector and the construction requirement rule semantic feature depth implicit encoding vector into the semantic response decision anchoring component to obtain a set of identity-construction rule semantic response anchoring encoding matrices, which is expressed by the formula:

[0044]

[0045] Wherein, represents the transpose of the vector, represents the vector multiplication, represents the feature scale scaling factor, represents and the identity-construction rule semantic response anchoring encoding matrix between.

[0046] Specifically, further perform semantic interaction encoding between the target laborer identity information semantic feature depth implicit encoding vector and each construction requirement rule semantic feature depth implicit encoding vector through the semantic response decision anchoring component, and calculate the outer product between vectors to capture the semantic association response relationship between the target laborer identity information and each construction requirement rule, so as to generate a set of identity-construction rule semantic response anchoring encoding matrices.

[0047] Figure 4 It is a block diagram of the feature contribution modeling and evaluation subunit in the construction project management system according to an embodiment of the present application. As Figure 4 shown, the feature contribution modeling and evaluation subunit 152 includes: a decision anchor adaptive splicing factor calculation secondary subunit 1521, configured to determine the decision anchor adaptive splicing factor of each identity-construction rule semantic response anchoring encoding matrix based on the feature distribution of each identity-construction rule semantic response anchoring encoding matrix in the set of identity-construction rule semantic response anchoring encoding matrices to obtain a set of identity-construction rule decision anchor adaptive splicing factors; a weighting secondary subunit 1522, configured to perform weighting processing on the set of identity-construction rule decision anchor adaptive splicing factors based on the Softmax function to obtain a set of identity-construction rule decision anchor adaptive splicing weight factors.

[0048] In a specific example of the present application, the decision anchor adaptive splicing factor calculation secondary subunit 1521 is used to: calculate the decision anchor adaptive splicing factor of each identity-construction rule semantic response anchor encoding matrix based on the statistical eigenvalue of each identity-construction rule semantic response anchor encoding matrix in the set of identity-construction rule semantic response anchor encoding matrices, so as to obtain the set of identity-construction rule decision anchor adaptive splicing factors. The statistical eigenvalues include the maximum eigenvalue, eigenvalue variance, eigenvalue mean, and the number of eigenvalues. More specifically, taking the sum of the eigenvalue variance and the drift coefficient of the identity-construction rule semantic response anchor encoding matrix as the numerator, and calculating the square of the difference between the maximum eigenvalue and the eigenvalue mean of the identity-construction rule semantic response anchor encoding matrix multiplied by the number of its eigenvalues, plus the drift coefficient and twice the eigenvalue variance as the denominator, to obtain the identity-construction rule decision anchor adaptive splicing factor. Wherein, the drift coefficient is used to smooth the fluctuation of the eigenvalue distribution of the identity-construction rule semantic response anchor encoding matrix, and is expressed by the formula:

[0049]

[0050] Wherein, represents the number of elements of the calculation matrix, represents the difference amplification coefficient, that is, the number of eigenvalues of the identity-construction rule semantic response anchor encoding matrix, represents the eigenvalue variance of the identity-construction rule semantic response anchor encoding matrix, represents the drift coefficient of the identity-construction rule semantic response anchor encoding matrix, represents the eigenvalue mean of the identity-construction rule semantic response anchor encoding matrix, is the maximum value function, represents the corresponding identity-construction rule decision anchor adaptive splicing factor.

[0051] Specifically, in order to more accurately measure the importance of semantic interaction information in different dimensions, the present application introduces an adaptive weight allocation mechanism, which calculates its decision anchor adaptive splicing factor by learning the eigenvalue distribution of each identity-construction rule semantic response anchor encoding matrix, and generates a set of identity-construction rule decision anchor adaptive splicing factors. Here, the identity-construction rule decision anchor adaptive splicing factor is used to reflect the dominance of semantic interaction information in different dimensions in the global context, and is the weight basis for subsequent feature fusion.

[0052] Particularly, in a preferred example of the present application, for the drift coefficient , for the state transition of the eigenvalue set distribution of the identity-construction rule semantic response anchored coding matrix from a state where the mean integrity is weakly interpretable to a state where the maximum locality is strongly interpretable, the present application enhances the global dominance basis of the identity-construction rule semantic response anchored coding matrix by introducing the weak-to-strong interpretable generalization of the drift coefficient This is expressed by the formula:

[0053]

[0054] where is the intermediate transition representation value of the characteristic distribution equilibrium state of the identity-construction rule semantic response anchored coding matrix, is the matrix the th eigenvalue, is the natural constant.

[0055] Specifically, taking as the intermediate state transition representation from weak interpretability to strong interpretability, for each eigenvalue of the identity-construction rule semantic response anchored coding matrix, taking it as the importance score of the identity-construction rule semantic response anchored coding matrix for the global smooth state transition, to perform global control of the importance score weight for the intermediate state transition relative to the global state transition, so as to achieve the interpretable generalization inference of the weight basis of the identity-construction rule decision anchor adaptive splicing factor.

[0056] More specifically, the weighted secondary subunit 1522 is expressed by the formula:

[0057]

[0058] where represents the normalization exponential function, represents the identity-construction rule decision anchor adaptive splicing weight factor of the matrix .

[0059] Specifically, perform weighted processing on the set of the identity-construction rule decision anchor adaptive splicing factors based on the Softmax function, that is, use the Softmax function to normalize the set of the identity-construction rule decision anchor adaptive splicing factors into a weight set with probability distribution properties, and through the characteristics of the exponential function, further amplify the significant differences between each identity-construction rule semantic response anchored coding matrix to enhance the distribution discrimination ability of features.

[0060] Specifically, the feature fusion subunit 153 is expressed by the formula:

[0061]

[0062] Among them, represents the identity-construction rule semantic response anchor encoding fusion matrix, represents the feature shape reshaping function, represents the identity-construction rule semantic-level query response encoding vector.

[0063] Specifically, based on the generated weight distribution, the set of the identity-construction rule semantic response anchor encoding matrices is weighted and fused to fuse semantic interaction information of different dimensions, and through feature shape reshaping, it is restored to a vector form to generate the final identity-construction rule semantic-level query response encoding vector. In this way, the identity-construction rule semantic-level query response encoding vector, as the core basis for subsequent personnel screening and adaptation analysis, not only contains comprehensive semantic matching information between the target laborer and the construction requirement rules, but also emphasizes the importance of key semantic interaction information through the adaptive weight regulation mechanism, thereby improving the accuracy and efficiency of the matching.

[0064] In the above construction project management system, the laborer adaptability evaluation unit 160 is used to determine whether the target laborer meets the construction project requirements based on the identity-construction rule semantic-level query response encoding vector. In a specific example of the present application, the laborer adaptability evaluation unit 160 is used to: input the identity-construction rule semantic-level query response encoding vector into the intelligent decision module based on the classifier to obtain an intelligent decision result, and the intelligent decision result is used to represent whether the target laborer meets the construction project requirements. Specifically, the fully connected layer of the intelligent decision module is used to perform fully connected encoding on the identity-construction rule semantic-level query response encoding vector to obtain the identity-construction rule semantic-level query response fully connected encoding vector; input the identity-construction rule semantic-level query response fully connected encoding vector into the Softmax classification function of the intelligent decision module to obtain the probability values of the identity-construction rule semantic-level query response encoding vector belonging to each classification label, where the classification labels include that the target laborer meets the construction project requirements and that the target laborer does not meet the construction project requirements; determine the classification label corresponding to the largest of the probability values as the decision result. Here, the intelligent decision module based on the classifier is based on the neural network architecture, and through multi-layer feature perception of the identity-construction rule semantic-level query response encoding vector, it learns the semantic matching relationship between the target laborer and the construction requirement rules contained in the identity-construction rule semantic-level query response encoding vector, and performs intelligent decision processing based on this, and outputs an intelligent decision result on whether the target laborer meets the construction project requirements.

[0065] In the technical solution of this application, considering that the set of the comprehensive structured coding vectors of the target laborer identity information and the set of the semantic embedded coding vectors of the construction requirement rules respectively represent the set of the semantic coding features of the target laborer information and the set of the semantic coding features of the construction requirement rules, when aligning for semantic-level feature dynamic query adaptive response splicing, the semantic feature dimensions of each semantic embedded coding vector of the construction requirement rules in the set of the comprehensive structured coding vectors of the target laborer identity information and the semantic feature coding differences among the semantic embedded coding vectors of the construction requirement rules in the set of the semantic embedded coding vectors of the construction requirement rules will cause cross-sample semantic difference imbalance and insufficient intra-sample semantic consistency in the obtained identity-construction rule semantic-level query response coding vector, resulting in cross-domain dynamic matching differences. Therefore, it is desired to improve the detailed semantic aggregation response expression effect of the identity-construction rule semantic-level query response coding vector.

[0066] In a preferred example, inputting the identity-construction rule semantic-level query response coding vector into the intelligent decision-making module based on the classifier to obtain the intelligent decision result includes:

[0067] Based on the eigenvalue information of each position of the identity-construction rule semantic-level query response coding vector, constructing a first identity-construction rule semantic-level query response semantic evolution intensity index and a second identity-construction rule semantic-level query response semantic evolution intensity index, expressed as:

[0068]

[0069] Wherein, represents the identity-construction rule semantic-level query response coding vector, represents the th eigenvalue of the identity-construction rule semantic-level query response coding vector, represents the total number of eigenvalues of the identity-construction rule semantic-level query response coding vector, represents the first identity-construction rule semantic-level query response semantic evolution intensity index, represents the second identity-construction rule semantic-level query response semantic evolution intensity index;

[0070] Extract the number of eigenvalues of the identity-construction rule semantic-level query response encoding vector, and perform low-order phase reconstruction on the eigenvalues at each position in the identity-construction rule semantic-level query response encoding vector based on the number of eigenvalues, the first identity-construction rule semantic-level query response semantic evolution intensity index, and the second identity-construction rule semantic-level query response semantic evolution intensity index to obtain the first identity-construction rule semantic-level query response phase reconstruction vector, expressed as:

[0071]

[0072] where represents dot product by position, represents subtraction by position, represents the reciprocal of the vector by position, represents the first identity-construction rule semantic-level query response phase reconstruction vector;

[0073] Based on the number of eigenvalues, the first identity-construction rule semantic-level query response semantic evolution intensity index, and the second identity-construction rule semantic-level query response semantic evolution intensity index, perform high-order phase reconstruction on the eigenvalues at each position in the identity-construction rule semantic-level query response encoding vector to obtain the second identity-construction rule semantic-level query response phase reconstruction vector, expressed as:

[0074]

[0075] where represents the second identity-construction rule semantic-level query response phase reconstruction vector;

[0076] Perform linear dynamic fusion on the first identity-construction rule semantic-level query response phase reconstruction vector and the second identity-construction rule semantic-level query response phase reconstruction vector to obtain an optimized identity-construction rule semantic-level query response encoding vector;

[0077] Input the optimized identity-construction rule semantic-level query response encoding vector into an intelligent decision-making module based on a classifier to obtain an intelligent decision result.

[0078] Here, the identity-construction rule semantic-level query response encoding vector, denoted as The optimization is expressed as:

[0079]

[0080] where and represent weight hyperparameters, represents vector addition, Represents an optimized identity-construction rule semantic-level query response encoding vector.

[0081] Correspondingly, in the preferred example, the difference comparison of the attribute parameters of each position of the identity-construction rule semantic-level query response encoding vector with respect to the feature set of the vector as a whole is used to construct a semantic evolution intensity index, and the modulation paradigm generated by the difference comparison is used to implement the mimicry phase mapping related to the position. Furthermore, based on the multi-dimensional tensor equalization framework, through the displacement transformation operation under the stacked alternating architecture, the fusion enhancement strategy driven by the phase-sensitive mechanism can expand the axial perception range along the feature aggregation direction, so as to effectively enhance the recognition efficiency of the aggregation representation of the identity-construction rule semantic-level query response feature vector for detailed semantic changes, thereby improving the perception effect of the aggregation semantics of the identity-construction rule semantic-level query response encoding vector for detailed semantic changes, so as to improve the expression effect of the identity-construction rule semantic-level query response encoding vector, and improving the accuracy of the intelligent decision result obtained by passing it through the intelligent decision module based on the classifier.

[0082] In summary, the construction project management system based on the embodiments of the present application is clarified. It uses data processing technology based on deep learning to perform semantic analysis on the electronic materials of target laborers to extract the identity information characteristics of the laborers. At the same time, in combination with the pre-established construction requirement rules, by performing semantic query response encoding on the identity information of the laborers and a large number of construction requirement rules, the potential matching relationship between the laborers and the construction projects is mined, so as to realize the intelligent evaluation of the adaptability of the laborers. In this way, it is possible to more comprehensively and accurately evaluate whether the laborers meet the specific requirements of the construction project, and effectively avoid construction problems caused by insufficient skills or lack of experience of the laborers.

[0083] Furthermore, a construction project management method is also provided.

[0084] Figure 5 Is a flowchart of the construction project management method according to the embodiments of the present application. As Figure 5As shown, the construction project management method includes the steps of: S1, obtaining the electronic materials of the target laborers; S2, extracting the set of construction requirement rules from the construction project rule library; S3, performing structured encoding on the electronic materials to obtain the comprehensive structured encoding vector of the target laborer identity information; S4, extracting the semantic features of each construction requirement rule in the set of construction requirement rules to obtain the set of construction requirement rule semantic embedding encoding vectors; S5, performing identity-rule semantic search verification encoding based on dynamic weight regulation on the comprehensive structured encoding vector of the target laborer identity information and the set of construction requirement rule semantic embedding encoding vectors to obtain the identity-construction rule semantic level query response encoding vector; S6, determining whether the target laborer meets the construction project requirements based on the identity-construction rule semantic level query response encoding vector.

[0085] The basic principles of the present invention have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, advantages, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, advantages, effects, etc. are essential for each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and easy understanding, rather than limitations. The above details do not limit the present invention to necessarily adopt the above specific details to implement.

[0086] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiments described above are only illustrative. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0087] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to cover all changes within the meaning and scope of the equivalent elements of the claims in the present invention. Any associated drawing marks in the claims should not be regarded as limiting the claims involved.

[0088] In addition, it is obvious that the term "comprising" does not exclude other units or steps, and the singular does not exclude the plural. A plurality of units stated in the system claims can also be implemented by one unit through software or hardware.

[0089] Finally, it should be noted that the above description has been given for purposes of illustration and description. In addition, the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A construction project management system, comprising: The central processing unit module is used for two-way data interaction with other modules; Storage module, used to store various data information of construction projects; The control module is used to receive user operation instructions through the connected touch screen to control and manage other modules; the project management module is used to record and manage various project information; The personnel information module is used to judge and evaluate the information of labor personnel, create files for them and conduct daily attendance management; the engineering material module is used to collect, classify and manage the material information required for construction; The supervision module is used to determine the degree to which the current environmental state is suitable for construction based on the construction site environmental data, and is characterized in that the personnel information module includes: A labor personnel information acquisition unit is used to acquire the electronic information of target labor personnel; A construction requirement rule acquisition unit, used to extract a set of construction requirement rules from a construction project rule library; An identity information structured coding unit, used for performing structured coding on the electronic data to obtain a comprehensive structured coding vector of the identity information of the target service personnel; A construction requirement rule semantic understanding unit, used for extracting semantic features of each construction requirement rule in the set of construction requirement rules to obtain a set of construction requirement rule semantic embedding coding vectors; A semantic search verification unit, used for performing identity-rule semantic search verification coding based on dynamic weight regulation on the set of the target labor personnel identity information comprehensive structured coding vector and the construction requirement rule semantic embedded coding vector to obtain an identity-construction rule semantic level query response coding vector; A labor suitability assessment unit, used to determine whether the target labor meets the requirements of the construction project based on the identity-construction rule semantic level query response encoding vector; The semantic search verification unit includes: The semantic response anchor coding subunit is used to perform semantic response anchor coding on the target labor personnel identity information comprehensive structured coding vector and each construction requirement rule semantic embedding coding vector in the set of the construction requirement rule semantic embedding coding vector to obtain a set of identity-construction rule semantic response anchor coding matrices; A feature contribution modeling evaluation subunit, used for performing feature contribution modeling evaluation on each identity-construction rule semantic response anchor coding matrix in the set of identity-construction rule semantic response anchor coding matrices to obtain a set of identity-construction rule decision anchor adaptive splicing weight factors; A feature fusion subunit, configured to fuse the set of identity-construction rule semantic response anchor encoding matrices based on the set of identity-construction rule decision anchor adaptive splicing weight factors to obtain the identity-construction rule semantic level query response encoding vector; The semantic response anchor encoding subunit is used to: Performing deep implicit feature extraction based on fully connected coding on the comprehensive structured coding vector of the target labor personnel's identity information to obtain a deep implicit coding vector of semantic features of the target labor personnel's identity information; Performing deep implicit feature extraction based on fully connected coding on each construction requirement rule semantic embedding coding vector in the set of construction requirement rule semantic embedding coding vectors to obtain a set of construction requirement rule semantic feature deep implicit coding vectors; Inputting each construction requirement rule semantic feature deep implicit coding vector in the set of the target labor personnel identity information semantic feature deep implicit coding vector and the construction requirement rule semantic feature deep implicit coding vector into the semantic response decision anchoring component to obtain a set of the identity-construction rule semantic response anchor coding matrices; The feature contribution modeling evaluation subunit includes: A decision anchor adaptive splicing factor calculation secondary subunit is used to determine the decision anchor adaptive splicing factor of each identity-construction rule semantic response anchor coding matrix in the set of identity-construction rule semantic response anchor coding matrices based on the feature distribution of each identity-construction rule semantic response anchor coding matrix to obtain a set of identity-construction rule decision anchor adaptive splicing factors; A weighted secondary subunit, used for performing a weighted processing based on a Softmax function on the set of identity-construction rule decision anchor adaptive splicing factors to obtain a set of identity-construction rule decision anchor adaptive splicing weight factors; The decision anchor adaptive splicing factor calculation secondary subunit is used to: The sum of the feature variance and the drift coefficient of the identity-construction rule semantic response anchor coding matrix is ​​used as the numerator, and the square of the difference between the maximum eigenvalue and the feature mean of the identity-construction rule semantic response anchor coding matrix is ​​multiplied by the number of its eigenvalues, and then the drift coefficient and twice the feature variance are added as the denominator to obtain the identity-construction rule decision anchor adaptive splicing factor, wherein the drift coefficient is used to smooth the feature distribution fluctuations of the identity-construction rule semantic response anchor coding matrix.

2. The construction project management system according to claim 1, characterized in that: The electronic data include identity card, special operation operation certificate, physical examination report within the last three months, safety training certificate and past project history.

3. The construction project management system according to claim 2, characterized in that: The identity information structured encoding unit is used to: Performing structured coding on each item of the electronic data to obtain a structured coding vector of identity information, a structured coding vector of a characteristic operation certificate, a structured coding vector of a physical examination report, a structured coding vector of a safety training certificate, and a structured coding vector of past project resumes; The identity information structured coding vector, the characteristic operation certificate structured coding vector, the physical examination report structured coding vector, the safety training certificate structured coding vector and the past project resume structured coding vector are spliced ​​to obtain a comprehensive structured coding vector of the target labor personnel's identity information.

4. The construction project management system according to claim 3, characterized in that: The decision anchor adaptive splicing factor calculation secondary subunit is used to: Based on the statistical eigenvalues ​​of each identity-construction rule semantic response anchor coding matrix in the set of identity-construction rule semantic response anchor coding matrices, the decision anchor adaptive splicing factors of each identity-construction rule semantic response anchor coding matrix are calculated to obtain the set of identity-construction rule decision anchor adaptive splicing factors, and the statistical eigenvalues ​​include the maximum eigenvalue, eigenvariance, eigenmean and eigenvalue number.

5. The construction project management system according to claim 4, characterized in that: The labor suitability assessment unit is used to: The identity-construction rule semantic level query response encoding vector is input into a classifier-based intelligent decision module to obtain an intelligent decision result, and the intelligent decision result is used to indicate whether the target labor personnel meet the requirements of the construction project.

6. A construction project management method, executed by the construction project management system according to any one of claims 1 to 5, characterized in that: include: Obtain the electronic data of target labor personnel; Extracting a set of construction requirement rules from a construction project rule base; Performing structured coding on the electronic data to obtain a comprehensive structured coding vector of the target labor personnel's identity information; Extracting semantic features of each construction requirement rule in the set of construction requirement rules to obtain a set of semantic embedding coding vectors of construction requirement rules; Performing identity-rule semantic search verification coding based on dynamic weight regulation on the set of the target labor personnel identity information comprehensive structured coding vector and the construction requirement rule semantic embedded coding vector to obtain an identity-construction rule semantic level query response coding vector; Based on the identity-construction rule semantic level query response encoding vector, it is determined whether the target labor personnel meet the requirements of the construction project.

Images