Electrical construction task intelligent management system and method

Abstract

The invention relates to the field of project intelligent management, and provides an electrical construction task intelligent management system and method, and the method comprises the steps: firstly obtaining the number of a target building, searching a corresponding building information model according to the number, then carrying out the deep building analysis of the target building based on the information model, so as to determine the construction task level, and at the same time, carrying out the construction task management of the target building. The working states and working information of constructors are collected and sorted to form a total set of constructors, the working information of the constructors in the to-be-distributed state in the total set is further analyzed to evaluate the skill levels of the constructors, and finally, the working states and working information of the constructors are analyzed. And according to the determined construction task level and the skill level of the to-be-allocated constructor, scientifically and reasonably allocating the construction task. In this way, reasonable configuration between construction tasks and constructors can be ensured, and then the overall construction efficiency and quality can be improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent project management, and more specifically, to an intelligent management system and method for electrical construction tasks. Background Art

[0002] Electrical construction involves the installation and commissioning of electrical systems inside buildings, a job that requires electricians to have superb skills. Any mistakes or negligence may cause serious safety accidents such as electrical fires and electric shocks. Therefore, when assigning electrical construction tasks, great caution and professionalism must be ensured.

[0003] Patent CN116485164B proposes a BIM-based electrical construction task allocation management system and method, which first obtains the building number and construction personnel status information and saves the building information model. Then, the construction difficulty of each floor is evaluated based on the model. At the same time, the ability level of the construction personnel is assessed. Finally, according to the analysis results of the first two, tasks are reasonably allocated according to specific rules, and the construction personnel are notified through mobile terminals.

[0004] The above patent classifies construction workers by comprehensively evaluating their engineer grades and experience, calculating the task priority value and comparing it with the preset threshold. However, the method in the patent mainly relies on fixed formulas and weight coefficients to obtain the task priority value. In actual work, there may be complex implicit correlations between engineer grades and work experience, and quantitative indicators are difficult to capture and reflect these nuances, thus affecting the accuracy of grade judgment. In addition, this method based on preset thresholds uses a unified standard to evaluate all construction workers, ignoring individual differences, which affects the reasonable allocation of work and may lead to resource mismatch, reducing overall work efficiency and safety.

[0005] Therefore, an intelligent management solution for electrical construction tasks is desired. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present application provides an intelligent management system and method for electrical construction tasks.

[0007] According to one aspect of the present application, a method for intelligent management of electrical construction tasks is provided, which includes: obtaining a building number of a target building; searching for a building information model corresponding to the target building according to the building number; performing a building analysis on the target building based on the building information model to obtain a construction task level of the building; obtaining the work status and work information of construction personnel to obtain a total set of construction personnel; analyzing the work information of construction personnel whose work status is a to-be-assigned state in the total set of construction personnel to obtain the skill level of the to-be-assigned construction personnel; allocating construction tasks to the construction personnel in the to-be-assigned state according to the construction task level and the skill level of the to-be-assigned construction personnel; wherein, analyzing the work information of construction personnel whose work status is a to-be-assigned state in the total set of construction personnel to obtain the skill level of the to-be-assigned construction personnel includes: Filter out construction personnel whose working status is to be assigned from the total set of construction personnel to obtain a set of construction personnel to be assigned; Extracting work information of construction personnel to be assigned from the set of construction personnel to be assigned, wherein the work information includes engineer grade information and work experience information; Encoding the engineer grade information and work experience information of the construction personnel to be assigned respectively to obtain the engineer grade coding feature of the construction personnel to be assigned and the work experience embedded coding feature of the construction personnel to be assigned; External dynamic memory semantic interaction is performed on the engineer grade coding features of the construction personnel to be assigned and the work experience embedded coding features of the construction personnel to be assigned to obtain a semantic interactive fusion representation of the multi-dimensional information of the construction personnel to be assigned, and based on the semantic interactive fusion representation of the multi-dimensional information of the construction personnel to be assigned, the skill level label of the construction personnel to be assigned is obtained.

[0008] According to another aspect of the present application, an intelligent management system for electrical construction tasks is provided, which is used to execute the intelligent management method for electrical construction tasks as described above, and includes: A construction personnel data screening module is used to screen out construction personnel whose working status is to be assigned from the total set of construction personnel to obtain a set of construction personnel to be assigned; A construction personnel work information extraction module is used to extract the work information of the construction personnel to be assigned from the construction personnel to be assigned set, wherein the work information includes engineer grade information and work experience information; A construction personnel work information encoding module is used to encode the engineer grade information and work experience information of the construction personnel to be assigned respectively to obtain the engineer grade encoding feature of the construction personnel to be assigned and the work experience embedded encoding feature of the construction personnel to be assigned; The construction personnel skill level label generation module is used to perform external dynamic memory semantic interaction on the engineer level coding features of the construction personnel to be assigned and the work experience embedded coding features of the construction personnel to be assigned to obtain the multi-dimensional information semantic interaction fusion representation of the construction personnel to be assigned, and obtain the skill level label of the construction personnel to be assigned based on the multi-dimensional information semantic interaction fusion representation of the construction personnel to be assigned.

[0009] This application has significant technical effects due to the adoption of the above technical solutions: The intelligent management system and method for electrical construction tasks provided by the present application first obtains the number of the target building, and searches for the corresponding building information model accordingly. Subsequently, based on the information model, an in-depth building analysis is performed on the target building to determine its construction task level. At the same time, the work status and work information of the construction personnel are collected and sorted to form a total set of construction personnel. For the construction personnel in the total set who are in the state of being assigned, their work information is further analyzed to evaluate their skill level. Finally, the construction tasks are scientifically and reasonably assigned according to the determined construction task level and the skill level of the construction personnel to be assigned. In this way, the reasonable configuration between construction tasks and construction personnel can be ensured, thereby improving the overall construction efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0011] Figure 1 It is a flow chart of the intelligent management method of electrical construction tasks according to an embodiment of the present application.

[0012] Figure 2 This is a flowchart of step S150 in the intelligent management method of electrical construction tasks according to an embodiment of the present application.

[0013] Figure 3 This is a flowchart of step S153 in the intelligent management method of electrical construction tasks according to an embodiment of the present application.

[0014] Figure 4 This is a flowchart of step S154 in the intelligent management method of electrical construction tasks according to an embodiment of the present application.

[0015] Figure 5 This is a system block diagram of an intelligent management system for electrical construction tasks according to an embodiment of the present application. DETAILED DESCRIPTION

[0016] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0017] Electrical construction is the installation and commissioning of the electrical system inside a building, which requires extremely high skills from construction workers. Any mistakes or negligence in operation may cause serious safety accidents, such as electrical fires or electric shocks. Therefore, when assigning electrical construction tasks, you must be extremely cautious to ensure that the assigned work is highly professional.

[0018] Patent CN116485164B proposes a BIM-based electrical construction task allocation management system and method, which first collects the building number and the status information of the construction personnel, and saves the building information model. Then, the construction difficulty of each floor is analyzed through the model, and the ability level of the construction personnel is evaluated. Finally, according to these analysis results, the reasonable allocation of tasks is achieved according to specific rules, and the tasks are notified to the construction personnel through mobile terminals.

[0019] In the above patent, the ability assessment of construction workers mainly relies on the comprehensive analysis of engineer grades and work experience, calculates the task priority value, and compares it with the preset threshold value to complete the grade division of construction workers. However, this method relies on fixed formulas and weight coefficients to calculate the task priority value. In actual work, there may be complex implicit associations between engineer grades and work experience. These associations are difficult to accurately reflect through quantitative indicators, which may lead to deviations in the results of grade assessment. In addition, this method uses a unified preset threshold to evaluate all construction workers, ignoring individual differences, which may cause unreasonable task allocation and resource mismatch, which will reduce overall work efficiency and construction safety.

[0020] Based on this, this application proposes an intelligent management method for electrical construction tasks. Figure 1 Flow chart of the intelligent management method of electrical construction tasks according to an embodiment of the present application. Figure 1As shown, the intelligent management method of electrical construction tasks according to the embodiment of the present application includes: S110, obtaining the building number of the target building; S120, searching for the building information model corresponding to the target building according to the building number; S130, performing a building analysis on the target building based on the building information model to obtain the construction task level of the building; S140, obtaining the work status and work information of the construction personnel to obtain the total set of construction personnel; S150, analyzing the work information of the construction personnel whose work status is to be assigned in the total set of construction personnel to obtain the skill level of the construction personnel to be assigned; S160, assigning construction tasks to the construction personnel in the to-be-assigned state according to the construction task level and the skill level of the construction personnel to be assigned.

[0021] In step S110, the building number of the target building is obtained. It should be understood that in an environment with numerous and complex construction projects, the building number is a unique identifier for each building, which can help to clearly and accurately distinguish different buildings. For example, in a large commercial complex project, there may be multiple commercial buildings, office buildings, and supporting facilities buildings. The building number can be used to quickly and accurately locate a specific target building to avoid confusion and misidentification.

[0022] In step S120, the building information model corresponding to the target building is searched according to the building number. It should be understood that the building information model (BIM) is a digital model containing rich building data, covering detailed information of the entire process of building design, construction, operation and maintenance. By searching the corresponding building information model according to the building number, various parameters of the target building can be fully obtained, including but not limited to the building structure, space layout, equipment system distribution, etc., which can provide detailed data support for subsequent construction task analysis and allocation.

[0023] In step S130, the target building is subjected to architectural analysis based on the building information model to obtain the construction task level of the building. It should be understood that the building information model contains various detailed information of the building. By analyzing it, various characteristics of the building can be converted into quantifiable indicators, thereby determining the difficulty level of the construction task. For example, information such as the number of building floors, floor area, total number of building equipment, and number of building equipment of different equipment types are closely related to the complexity and workload of the construction task. By comprehensively considering this information, the difficulty of the construction task can be accurately assessed, and then the construction task classification of the building can be achieved. Clear construction task levels are the key basis for the reasonable allocation of construction tasks. Construction tasks of different levels require construction personnel with different skill levels and experience to undertake. By accurately dividing the construction task levels, it can be ensured that the tasks are assigned to personnel with corresponding capabilities to improve the quality and efficiency of the completion of the construction tasks.

[0024] Conducting architectural analysis on target buildings based on the Building Information Model (BIM) to obtain the construction task level is a systematic and rigorous work. Its specific implementation process covers multiple key links, involving data collection, feature analysis, difficulty assessment, and dynamic adjustment. The following is a detailed description of its implementation process: First of all, comprehensive data collection and integration is the basis of the entire analysis work. At the start-up stage of the project, it is necessary to obtain a detailed BIM model of the target building, which should include information in various professional fields such as building structure, electrical system, water supply and drainage system, HVAC system, etc., to ensure a comprehensive understanding of the building. At the same time, related design documents, construction drawings, engineering specifications and other materials are also indispensable. These rich data sources are organically integrated with the BIM model to build a solid data foundation for subsequent in-depth building analysis. For example, in a comprehensive hospital project, the BIM model should not only present the architectural appearance and internal space layout of the hospital building, but also carefully display the electrical requirements of various medical equipment, special electrical configurations of wards and operating rooms, etc. The design documents clarify the design principles and technical requirements of the electrical system, the construction drawings give specific construction dimensions and location information, and the engineering specifications ensure that the entire electrical construction meets industry standards and safety specifications.

[0025] Next, the key building features closely related to the construction tasks are accurately extracted from the integrated BIM model. The number of floors in a building is an important consideration. More floors means that the pressure of vertical transportation during construction increases, such as the up and down transportation of building materials, construction equipment and personnel will be more frequent and complex, and the difficulty of construction coordination between different floors will also increase accordingly. The building area of ​​each floor should not be ignored. Large floors require more manpower and material resources, and the coverage is wider when installing electrical wiring and equipment, which requires higher requirements for construction technology and organizational management. Building height is also a key indicator affecting the difficulty of construction. High-rise buildings face problems such as the risk of high-altitude operations, the impact of wind loads on the installation of electrical equipment, and the challenges of long-distance transmission of power supply lines. In addition, the complexity of spatial layout is also an aspect that needs to be analyzed. Complex spatial layout may involve special-shaped structures and the interlacing of multiple functional areas, which will lead to more customized solutions for electrical wiring, and the selection and coordination of equipment installation locations will also be more difficult. Taking a large commercial shopping center as an example, its internal space layout is complex and diverse, with different types of shops, dining areas, entertainment venues, etc. The electrical requirements and equipment layout of each area are different, and they need to be carefully planned and designed according to the specific spatial layout.

[0026] After analyzing the overall characteristics of the building, it is necessary to dig deeper into the characteristics of the electrical system in the building. There are many types of electrical equipment, from common lighting fixtures, sockets, distribution boxes to complex elevator control systems, electrical parts of air-conditioning systems, and special electrical devices for various types of equipment. Different types of equipment have their own technical requirements and difficulty levels in installation, commissioning, and maintenance. The statistics of the number of equipment are also indispensable. A large number of electrical equipment means more connection points and wiring workload. For example, a large data center is densely populated with thousands of servers, UPS power supplies, precision air conditioners and other equipment. The complexity of its electrical system is much higher than that of an ordinary residence. The distribution density of equipment also affects the difficulty of construction. In equipment-intensive areas, such as distribution rooms and computer rooms, the construction space is limited, and more sophisticated construction processes and strict safety measures are required to ensure the accuracy of equipment installation and the reliability of electrical connections. At the same time, the degree of intelligence of the electrical system is also an important part of the evaluation. With the development of the intelligent trend of modern buildings, the application of intelligent lighting systems, building automation systems, etc. is becoming more and more extensive. The integration and commissioning of these intelligent systems require a higher level of technical support, which further increases the complexity of construction.

[0027] Based on the above-extracted building features and electrical system analysis results, constructing a quantitative assessment model for construction difficulty becomes a key step. For each factor affecting the construction difficulty, a corresponding weight is assigned according to its importance in actual construction. For example, the factor of high building height may be given a higher weight due to the high-altitude operation risks and construction technical difficulties it brings, while the installation difficulty of ordinary lighting fixtures is relatively low, and its weight is correspondingly smaller. By multiplying the quantitative value of each factor by its weight and accumulating them, the comprehensive difficulty score of the construction task is obtained. For example, the building height of a certain building is high, the weight is 0.3, and its quantitative value is 8 (assuming a full score of 10 points); there are many types of electrical equipment, the weight is 0.25, and the quantitative value is 7; the spatial layout complexity is general, the weight is 0.2, and the quantitative value is 6; the equipment distribution density is high, the weight is 0.15, and the quantitative value is 7; the degree of intelligence is medium, the weight is 0.1, and the quantitative value is 5. Then the comprehensive difficulty score = 0.3×8+0.25×7+0.2×6+0.15×7+0.1×5=6.95. According to the pre-set difficulty level classification standards, such as 0-3 points for a first-level task, 4-6 points for a second-level task, 7-9 points for a third-level task, and 9 points and above for a fourth-level task, the construction task level of the building can be determined as a third-level task.

[0028] Finally, based on the construction task level obtained through quantitative evaluation, combined with rich actual construction experience and strict industry standards, the construction task level of the target building is finally determined. This level will serve as the core basis for guiding the subsequent allocation of construction personnel, construction resource allocation, and construction schedule arrangement. During the construction process, dynamic monitoring and adjustment must be maintained. As the construction progresses, various actual changes may occur, such as design changes leading to adjustments to the electrical system layout, changes in construction conditions (such as complex geological conditions affecting the laying of underground electrical pipelines), etc. At this time, the BIM model and related data should be updated in a timely manner, the building analysis should be re-conducted, and the construction task level should be dynamically adjusted to ensure that the construction task allocation is always reasonable and efficient, thereby ensuring the smooth progress of the entire electrical construction project, improving construction quality and efficiency, and reducing construction risks.

[0029] In step S140, the work status and work information of the construction personnel are obtained to obtain the total set of construction personnel. It should be understood that the work status of the construction personnel (busy or to be assigned) directly affects whether they can undertake new construction tasks. Understanding this status can avoid assigning tasks to already busy construction personnel, resulting in task backlogs and delays, while ensuring that the construction personnel to be assigned can obtain appropriate work tasks in a timely manner, thereby improving the utilization rate and work efficiency of the construction personnel. The work information can reflect the experience accumulation and skill performance of the construction personnel in actual work. That is, by obtaining the work status of the construction personnel, the construction personnel to be assigned who can currently accept the new task assignment can be quickly screened out to form a set of construction personnel to be assigned, which can provide a personnel resource pool for subsequent task assignment; by obtaining the work information of the construction personnel, the skill level of the construction personnel can be deeply analyzed with the help of various indicators in the work information, and then the appropriate skill level (such as first-level construction personnel, second-level construction personnel or third-level construction personnel) can be determined for each construction personnel to be assigned, so as to accurately match the subsequent construction tasks of the corresponding level.

[0030] In step S150, the work information of the construction personnel whose work status is to be assigned in the total set of construction personnel is analyzed to obtain the skill level of the construction personnel to be assigned.

[0031] Accordingly, in analyzing the construction workers to be assigned in the total set of construction workers to obtain the skill levels of the construction workers to be assigned, the technical concept of the present application is to screen out the set of construction workers to be assigned from the total set of construction workers, and extract the work information (engineer grade information and work experience information) of the construction workers to be assigned therefrom, and use the data analysis and processing algorithm based on machine learning to embed the engineer grade information and work experience information respectively, so as to intelligently judge the skill level of the construction workers to be assigned based on the external dynamic semantic interaction representation between the engineer grade coding features of the construction workers to be assigned and the embedded coding features of the work experience of the construction workers to be assigned. In this way, the complex implicit relationship between the engineer grade information and the work experience information can be captured, rather than just a simple quantitative indicator. At the same time, the unique skills and experience of each construction worker can be identified, and personalized evaluation results can be provided, thereby realizing the intelligent evaluation of the skill level of the construction workers.

[0032] Figure 2 FIG. 1 is a flow chart of step S150 in the intelligent management method for electrical construction tasks according to an embodiment of the present application. Figure 2As shown, the step S150 includes: S151, screening out construction personnel whose working status is to be assigned from the total set of construction personnel to obtain a set of construction personnel to be assigned; S152, extracting work information of the construction personnel to be assigned from the set of construction personnel to be assigned, wherein the work information includes engineer grade information and work experience information; S153, respectively encoding the engineer grade information and work experience information of the construction personnel to be assigned to obtain engineer grade coding features of the construction personnel to be assigned and work experience embedded coding features of the construction personnel to be assigned; S154, performing external dynamic memory semantic interaction on the engineer grade coding features of the construction personnel to be assigned and the work experience embedded coding features of the construction personnel to be assigned to obtain a semantic interactive fusion representation of multi-dimensional information of the construction personnel to be assigned, and obtaining the skill grade label of the construction personnel to be assigned based on the semantic interactive fusion representation of the multi-dimensional information of the construction personnel to be assigned.

[0033] In step S151, the construction personnel whose working status is to be assigned are screened out from the total set of construction personnel to obtain a set of construction personnel to be assigned. It should be understood that in the entire total set of construction personnel, the working status of the construction personnel is different. Some are busy and cannot undertake new tasks, while others are in a state to be assigned and can be put into new work at any time. By screening out the construction personnel whose working status is to be assigned, it is possible to quickly and accurately determine the human resources currently available for task assignment, narrow the target range of task assignment, and improve the pertinence and efficiency of task assignment. In this way, by directly focusing on the construction personnel in the state to be assigned, the system can speed up the task assignment process, enable construction tasks to be issued in a timely manner, reduce construction waiting time, and help improve the operating efficiency of the entire electrical construction project. And it can ensure that construction personnel resources are reasonably utilized to avoid idleness or over-allocation of human resources.

[0034] In step S152, work information of the construction personnel to be assigned is extracted from the set of construction personnel to be assigned, and the work information includes engineer grade information and work experience information. In particular, the work experience information includes the total number of electrical construction, the total number of electrical maintenance, the success rate of electrical construction and the success rate of electrical maintenance. It should be understood that the engineer grade information (junior engineer, intermediate engineer and senior engineer) is a basic division of the professional qualifications of construction personnel, which can reflect the theoretical knowledge reserve and the initial level of professional skills of construction personnel in the field of electrical construction to a certain extent. Engineers of different grades have differences in the depth and breadth of education, training and professional knowledge, which can provide a basic framework for a more accurate assessment of their actual work ability in the future. The total number of electrical construction and the total number of electrical maintenance in the work experience information intuitively reflect the degree of participation of construction personnel in actual work and the amount of accumulated practical experience. The more projects involved, the more actual problems may be encountered and solved, which reflects their ability to deal with various construction scenarios and problems to a certain extent. The success rate of electrical construction and the success rate of electrical maintenance measure the work quality and stability of construction personnel from the perspective of work results. A high success rate indicates that the construction personnel were able to complete the task well in their past work and have strong problem-solving and operational skills. Otherwise, they may need to further improve their skills or be given appropriate attention and guidance in task allocation. In general, by extracting the work information of the construction personnel to be assigned, including the engineer level information and work experience information, a detailed and comprehensive capability profile can be constructed for each construction personnel to be assigned, which can clearly show their professional ability, practical experience and work quality level in the field of electrical construction, and thus help to more comprehensively and accurately evaluate the ability of each construction personnel to be assigned, thereby providing a scientific basis for more reasonable task allocation.

[0035] In step S153, the engineer grade information and work experience information of the construction personnel to be assigned are respectively coded to obtain the engineer grade coding features of the construction personnel to be assigned and the work experience embedded coding features of the construction personnel to be assigned. Specifically, Figure 3 FIG. 1 is a flowchart of step S153 in the method for intelligent management of electrical construction tasks according to an embodiment of the present application. Figure 3 As shown, the step S153 includes: S1531, performing one-hot encoding on the engineer grade information of the construction personnel to be assigned to obtain the engineer grade encoding vector of the construction personnel to be assigned as the engineer grade encoding feature of the construction personnel to be assigned; S1532, performing data integration and embedding encoding on the work experience information of the construction personnel to be assigned to obtain the work experience embedded encoding vector of the construction personnel to be assigned as the work experience embedded encoding feature of the construction personnel to be assigned.

[0036] In step S1531, the engineer grade information of the construction personnel to be assigned is uniquely encoded to obtain the engineer grade coding vector of the construction personnel to be assigned as the engineer grade coding feature of the construction personnel to be assigned. Accordingly, considering that the engineer grade information is a categorical data (such as elementary, intermediate, and advanced) rather than numerical data, if integers are directly used to represent these categories, it may mislead the machine learning algorithm into thinking that there is a numerical relationship or order between these categories (for example, thinking that the advanced is twice the intermediate). Therefore, in order to be able to convert the category features into a series of binary variables while eliminating the inherent order or importance differences, in the technical solution of the present application, the engineer grade information of the construction personnel to be assigned is uniquely encoded to obtain the engineer grade coding vector of the construction personnel to be assigned. This can avoid such misunderstandings because it converts each category into an independent binary feature, which clearly indicates the existence or non-existence of the category.

[0037] Performing unique hot encoding on the engineer grade information of the construction personnel to be assigned to obtain the engineer grade encoding vector of the construction personnel to be assigned is an important data processing task. The specific implementation process involves the effective conversion and feature representation of the classified data. The following will explain in detail how it is implemented: First of all, clarifying the engineer grade classification system is a basic step. Comprehensively sort out the common engineer grade classification in the field of electrical construction. The grade classification may vary from company to company or project to project. Common basic grades include junior, intermediate, and senior. Some companies may also have more detailed levels such as assistant engineer and senior engineer.

[0038] Then, based on the determined level classification system, a unique hot coding mapping table is constructed. The coding rule setting determines the length of the binary coding vector according to the number of level categories. For example, three levels correspond to three-bit binary codes, and the junior engineer is coded as [1,0,0], the intermediate is [0,1,0], and the senior is [0,0,1]. This coding method ensures that only one element of each vector is 1, clearly distinguishes different levels, and avoids possible misleading of numerical coding. The constructed mapping table is stored in the project management system database for easy access at any time, and its maintainability is ensured. When the level system changes, it can be updated in time to ensure coding accuracy and consistency. For example, if a new level is introduced during the development of an enterprise, the mapping table needs to be adjusted accordingly.

[0039] Then, data collection and preprocessing are carried out. The engineer grade data of the construction personnel to be assigned are obtained from the construction personnel information management system. These data may be stored in a scattered manner and in different formats, and need to be integrated and cleaned. For example, correct input errors or unify non-standard formats to ensure that the data is accurate and complete. At the same time, the collected data is converted into a string format suitable for unique hot encoding processing. If the original is a digital code, it needs to be converted into a grade name string first to match the mapping table category.

[0040] Then perform the one-hot encoding operation. Use programming languages ​​(such as Python) and related data processing libraries (such as pandas, numpy) to write programs to implement the encoding function. The program reads the construction personnel grade information (in string form), finds the corresponding encoding vector in the mapping table and assigns it to the engineer grade encoding feature. For a large amount of personnel data to be assigned, batch processing is used to improve efficiency, read all data at one time, traverse each personnel grade information for encoding, and store the results in a new data structure (such as an array or data frame) for subsequent integration and analysis. For example, in large-scale electrical construction projects, facing a large number of construction personnel, batch encoding can quickly complete the conversion and provide data support for task allocation.

[0041] After the coding is completed, the coding results are verified and stored. Manual spot checks or automated test scripts are used to ensure that the coding is accurate. The coding results of some personnel are randomly selected and compared with the original grade information to check the consistency of the vector and mapping table rules to avoid missing or repeated coding. The verified coding vector is stored in the project database. When storing, attention should be paid to the data structure and format to ensure easy query, call and management, and facilitate association analysis.

[0042] In step S1532, the work experience information of the construction personnel to be assigned is data integrated and embedded coded to obtain the work experience embedded coding vector of the construction personnel to be assigned as the work experience embedded coding feature of the construction personnel to be assigned. Specifically, in an embodiment of the present application, the work experience information of the construction personnel to be assigned is data integrated and embedded coded to obtain the work experience embedded coding vector of the construction personnel to be assigned, including: integrating the work experience information of the construction personnel to be assigned according to the work experience sample dimension to obtain the work experience vector of the construction personnel to be assigned; and embedding the work experience vector of the construction personnel to be assigned using the work experience embedding matrix to obtain the work experience embedded coding vector of the construction personnel to be assigned.

[0043] It should be understood that there are mutual correlations and influences between different label information in the work experience information. For example, a high success rate of electrical construction may be associated with a large number of electrical construction times. Therefore, in order to make subsequent analysis and processing more efficient and accurate, in the technical solution of this application, the work experience information of the construction personnel to be assigned is integrated according to the work experience sample dimension to integrate the multi-dimensional work experience information into a unified representation, and obtain the work experience vector of the construction personnel to be assigned.

[0044] Then, considering that the work experience vector of the construction personnel to be assigned contains rich semantic meanings and the semantic associations between various work experience labels, in order to convert the original, possibly high-dimensional and sparse work experience data into a low-dimensional, dense and semantically rich representation, in the technical solution of the present application, the work experience vector of the construction personnel to be assigned is embedded and encoded using a work experience embedding matrix to map the high-dimensional work experience vector to a lower-dimensional space, and obtain the embedded coding vector of the work experience of the construction personnel to be assigned. In this way, not only the complexity of the data is reduced, but also the semantic associations between key semantic information and various experience information are retained, so as to better characterize the intrinsic connections and patterns between different work experience dimensions. In particular, the work experience embedding matrix is ​​constructed by collecting a large amount of work experience information about construction personnel.

[0045] In step S154, the engineer grade coding features of the construction personnel to be assigned and the work experience embedded coding features of the construction personnel to be assigned are subjected to external dynamic memory semantic interaction to obtain a multi-dimensional information semantic interaction fusion representation of the construction personnel to be assigned, and the skill grade label of the construction personnel to be assigned is obtained according to the multi-dimensional information semantic interaction fusion representation of the construction personnel to be assigned. Specifically, Figure 4 FIG. 1 is a flow chart of step S154 in the method for intelligent management of electrical construction tasks according to an embodiment of the present application. Figure 4 As shown, the step S154 includes: S1541, performing external dynamic memory semantic interaction on the engineer grade coding vector of the construction personnel to be assigned and the work experience embedded coding vector of the construction personnel to be assigned to obtain a semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned as the semantic interaction fusion representation of the multi-dimensional information of the construction personnel to be assigned; S1542, obtaining a detection result based on the semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned, and the detection result is used to represent the skill level label of the construction personnel to be assigned.

[0046] In step S1541, the engineer grade coding vector of the construction personnel to be assigned and the embedded coding vector of the work experience of the construction personnel to be assigned are subjected to external dynamic memory semantic interaction to obtain the semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned as the semantic interaction fusion representation of the multi-dimensional information of the construction personnel to be assigned. Specifically, in an embodiment of the present application, the step S1541 includes: performing fine-grained feature interaction on the engineer grade coding vector of the construction personnel to be assigned and the embedded coding vector of the work experience of the construction personnel to be assigned to obtain the engineer grade-work experience fine-grained interaction feature matrix; according to the engineer grade-work experience fine-grained interaction feature matrix, performing external attention interaction optimization on the engineer grade coding vector of the construction personnel to be assigned and the embedded coding vector of the work experience of the construction personnel to be assigned respectively to obtain the optimized engineer grade coding vector of the construction personnel to be assigned and the optimized embedded coding vector of the work experience of the construction personnel to be assigned; calculating the position point division between the optimized engineer grade coding vector of the construction personnel to be assigned and the optimized embedded coding vector of the work experience of the construction personnel to be assigned to obtain the semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned.

[0047] It should be understood that the engineer grade encoding vector provides the professional qualification information of the construction personnel, while the work experience embedding encoding vector reflects their performance and skill level in actual work. The combination of the two can provide a more complete personal ability portrait. For example, a senior engineer may have more successful experience in complex electrical construction tasks, while an intermediate engineer may perform well in specific types of maintenance tasks. Therefore, it can more accurately reflect the overall ability and adaptability of the construction personnel, thereby helping to match and find the most suitable task. In the technical solution of the present application, an external dynamic memory semantic interaction mechanism is introduced to process the engineer grade encoding vector of the construction personnel to be assigned and the work experience embedding encoding vector of the construction personnel to be assigned, so as to more accurately mine and characterize the fine-grained mutual influence and interaction between the two, thereby enhancing the richness and accuracy of the feature representation, and obtaining the semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned. In particular, additional professional domain knowledge or contextual information is used in the present application to adjust and optimize the feature representation. For example, external knowledge such as industry standards, best practices or special requirements of specific projects can be used to guide the feature interaction process, so that the final representation vector is closer to the needs of the actual application scenario.

[0048] Specifically, firstly, fine-grained feature interaction is performed on the engineer grade encoding vector of the construction personnel to be assigned and the work experience embedding encoding vector of the construction personnel to be assigned to obtain the engineer grade-work experience fine-grained interaction feature matrix. The above process can be expressed as: ;in, is the engineer grade coding vector of the construction personnel to be assigned, is the work experience embedding coding vector of the construction personnel to be assigned, for The transposed vector of is matrix multiplication, is the engineer level-work experience fine-grained interaction feature matrix.

[0049] It should be understood that by performing fine-grained feature interaction on the engineer grade encoding vector of the construction personnel to be assigned and the embedded encoding vector of the work experience of the construction personnel to be assigned, the fine-grained interactive information between the engineer grade encoding vector of the construction personnel to be assigned and the embedded encoding vector of the work experience of the construction personnel to be assigned can be captured. That is, the engineer grade-work experience fine-grained interactive feature matrix obtained by interaction allows the model to understand the correlation between the engineer grade information of the construction personnel to be assigned and the work experience information of the construction personnel to be assigned from a micro level.

[0050] Specifically, in an embodiment of the present application, according to the engineer grade-work experience fine-grained interactive feature matrix, the engineer grade encoding vector of the construction personnel to be assigned and the work experience embedding encoding vector of the construction personnel to be assigned are respectively subjected to external attention interaction optimization to obtain the optimized engineer grade encoding vector of the construction personnel to be assigned and the optimized work experience embedding encoding vector of the construction personnel to be assigned, including: performing external knowledge attention optimization on the engineer grade-work experience fine-grained interactive feature matrix to obtain the engineer grade-work experience external knowledge optimization fine-grained interactive feature matrix, and the process can be expressed as: ;in, is matrix multiplication, is the engineer level-work experience fine-grained interaction feature matrix, and They represent the learnable memory parameter matrix, for The transposed matrix of represents the normalization function, It is the engineer level-work experience external knowledge optimization fine-grained interaction feature matrix; The engineer grade encoding vector of the construction personnel to be assigned is linearly transformed to obtain an engineer grade query feature vector and an engineer grade value feature vector, and the engineer grade-work experience external knowledge optimization fine-grained interactive feature matrix is ​​used as a key matrix. The engineer grade query feature vector, the engineer grade value feature vector and the key matrix are modulated and optimized based on a converter to obtain the optimized engineer grade encoding vector of the construction personnel to be assigned. The process can be expressed as: ;in, is the engineer grade coding vector of the construction personnel to be assigned, is matrix multiplication, and are the engineer level query embedding matrix and the engineer level first bias vector respectively, is the engineer level query feature vector, and are the engineer level value embedding matrix and the engineer level second bias vector respectively, is the engineer grade value eigenvector, for The transposed matrix of yes Length, yes function, is the optimized engineer grade coding vector of the construction personnel to be assigned; The work experience embedding coding vector of the construction personnel to be assigned is linearly transformed to obtain a work experience query feature vector and a work experience value feature vector, and the engineer level-work experience external knowledge optimization fine-grained interactive feature matrix is ​​used as a key matrix. The work experience query feature vector, the work experience value feature vector and the key matrix are modulated and optimized based on the converter to obtain the optimized work experience embedding coding vector of the construction personnel to be assigned. The process can be expressed as: ;in, is the work experience embedding coding vector of the construction personnel to be assigned, is matrix multiplication, and are the work experience query embedding matrix and the work experience first bias vector, respectively. is the work experience query feature vector, and are the work experience value embedding matrix and the work experience second bias vector respectively, is the work experience value feature vector, for The transposed matrix of yes Length, yes function, It is the optimized embedding coding vector of the work experience of the construction personnel to be assigned.

[0051] It should be understood that by performing external knowledge attention optimization on the engineer grade-work experience fine-grained interactive feature matrix, external knowledge can be used to further optimize the engineer grade-work experience fine-grained interactive matrix. Specifically, in the implementation process of external knowledge attention optimization, the model's ability to understand knowledge in a specific field will be significantly enhanced. And by introducing the professional insights of domain experts, rich historical data and other relevant external knowledge, the model can break through the limitations of the original data and explore the potential connections between features in a broader knowledge field. Subsequently, the engineer grade encoding vector of the construction personnel to be assigned is linearly transformed to obtain the engineer grade query feature vector and the engineer grade value feature vector, and the engineer grade-work experience external knowledge optimization fine-grained interactive feature matrix is ​​used as the key matrix. The engineer grade query feature vector, the engineer grade value feature vector and the key matrix are modulated and optimized based on the converter to obtain the optimized construction personnel to be assigned engineer grade encoding vector. Here, the information exchange and integration between the internal and external knowledge of the feature vector is realized through the attention mechanism at the core of the converter structure, so as to ensure that the engineer grade encoding vector of the construction personnel to be assigned can benefit from the outside, thereby improving the quality of its feature expression. Similarly, the work experience embedding coding vector of the construction personnel to be assigned also undergoes the same processing flow, that is, linear transformation generates work experience query feature vector and work experience value feature vector, and performs modulation optimization based on the converter with the engineer grade-work experience external knowledge optimization fine-grained interactive feature matrix. In this way, the work experience embedding coding vector of the construction personnel to be assigned can also benefit from external knowledge, thereby improving the quality of its feature expression. It should be noted that when the engineer grade coding vector of the construction personnel to be assigned and the work experience embedding coding vector of the construction personnel to be assigned are subjected to external attention interaction optimization, the engineer grade-work experience external knowledge optimization fine-grained interactive feature matrix is ​​a common key matrix space, so that the optimized construction personnel engineer grade coding vector to be assigned and the optimized construction personnel work experience embedding coding vector to be assigned have relatively good alignment characteristics in high-dimensional space.

[0052] Finally, the optimized engineer grade coding vector of the construction personnel to be assigned and the optimized work experience embedding coding vector of the construction personnel to be assigned are divided by the position point to obtain the semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned. The above process can be expressed as: ;in, is the optimized engineer grade coding vector of the construction personnel to be assigned, is the optimized embedding coding vector of the work experience of the construction personnel to be assigned, It is the semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned.

[0053] It should be understood that by dividing the optimized engineer grade coding vector of the construction personnel to be assigned and the optimized work experience embedding coding vector of the construction personnel to be assigned by position, a semantic interactive fusion representation vector of the multi-dimensional information of the construction personnel to be assigned that integrates the original engineer grade coding vector of the construction personnel to be assigned and the work experience embedding coding vector information of the construction personnel to be assigned can be obtained. This vector can well reflect the interactive relationship between the work experience information of the construction personnel to be assigned and the engineer grade information of the construction personnel to be assigned.

[0054] In step S1542, according to the semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned, a detection result is obtained, and the detection result is used to represent the skill level label of the construction personnel to be assigned. Specifically, in the embodiment of the present application, the step S1542 includes: passing the semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned through a skill level detector based on a classifier to obtain the detection result. That is, the semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned obtained by external dynamic interaction using the engineer level coding vector of the construction personnel to be assigned and the work experience embedding coding vector of the construction personnel to be assigned is classified and processed, so as to intelligently judge the skill level of the construction personnel to be assigned. Specifically, a classifier is a machine learning model whose main function is to classify the input data into different predefined categories according to its characteristics. In this method, the classifier is trained based on a large number of sample data of construction personnel with marked skill levels (such as first-level construction personnel, second-level construction personnel, and third-level construction personnel) to learn the work information feature patterns of construction personnel of different skill levels in these samples. When the new semantic interaction fusion representation vector of multi-dimensional information of the construction personnel to be assigned is input into the trained classifier, the classifier outputs the skill level category of the construction personnel to be assigned based on the information contained in this vector. The obtained detection result represents the skill level of the construction personnel to be assigned in the entire construction team, which is the key basis for the subsequent matching of construction tasks with construction personnel. In particular, in a specific embodiment of the present application, the semantic interaction fusion representation vector of multi-dimensional information of the construction personnel to be assigned is passed through a skill level detector based on a classifier to obtain the detection result, including: using the fully connected layer of the classifier to fully connect the semantic interaction fusion representation vector of multi-dimensional information of the construction personnel to be assigned to obtain a fully connected encoded classification feature vector of the semantic interaction fusion of multi-dimensional information of the construction personnel to be assigned; inputting the semantic interaction fusion fully connected encoded classification feature vector of multi-dimensional information of the construction personnel to be assigned into the Softmax classification function of the classifier to obtain the detection result.

[0055] Here, considering that the engineer grade encoding vector of the construction personnel to be assigned and the work experience embedding encoding vector of the construction personnel to be assigned respectively represent the unique hot encoding features of the engineer grade information and the embedded encoding features of the work experience information of the construction personnel to be assigned, when performing fine-grained feature interaction based on external knowledge modulation, due to the external knowledge modulation differences caused by the different encoding mode feature differences corresponding to heterogeneous data, the semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned will have a probabilistic convergence and divergence based on different feature interactions, thereby affecting the accuracy of the detection results obtained by the skill level detector based on the classifier.

[0056] Preferably, the semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned is passed through a classifier-based skill level detector to obtain a detection result, which includes: Determine the median eigenvalue, the maximum eigenvalue and the minimum eigenvalue in the semantic interactive fusion representation vector of the multi-dimensional information of the construction personnel to be assigned, and divide the median eigenvalue by the difference between the maximum eigenvalue and the minimum eigenvalue to obtain the semantic interactive fusion distribution probability value of the multi-dimensional information of the construction personnel to be assigned. This process can be expressed as: ;in, and represent the median eigenvalue, the maximum eigenvalue and the minimum eigenvalue in the semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned, respectively. Indicates the semantic interaction fusion distribution probability value of the multi-dimensional information of the construction personnel to be assigned; The semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned is normalized to the maximum value to obtain the semantic interaction fusion probability feature vector of the multi-dimensional information of the construction personnel to be assigned ; The power function of each eigenvalue of the semantic interaction fusion probability feature vector of the multi-dimensional information of the construction personnel to be assigned is calculated with one minus the distribution probability value of the semantic interaction fusion of the multi-dimensional information of the construction personnel to be assigned as an exponent to obtain the first semantic interaction fusion convergence feature vector of the multi-dimensional information of the construction personnel to be assigned. The process can be expressed as: ;in, represents the semantic interaction fusion probability feature vector of the multi-dimensional information of the construction personnel to be assigned, represents the probability value of semantic interaction fusion distribution of multi-dimensional information of the construction personnel to be assigned, It means point multiplication by position. Indicates one minus Calculate for index The power function of each eigenvalue of Represents the semantic interaction fusion convergence feature vector of the multi-dimensional information of the first construction personnel to be assigned; The power function of each eigenvalue of the point difference eigenvector between the unit eigenvector and the eigenvector of the semantic interaction fusion probability of the multi-dimensional information of the construction personnel to be assigned is calculated with the distribution probability value of the semantic interaction fusion of the multi-dimensional information of the construction personnel to be assigned as an exponent to obtain the second semantic interaction fusion convergence eigenvector of the multi-dimensional information of the construction personnel to be assigned. The process can be expressed as: ;in, represents the unit eigenvector, represents the semantic interaction fusion probability feature vector of the multi-dimensional information of the construction personnel to be assigned, represents the probability value of semantic interaction fusion distribution of multi-dimensional information of the construction personnel to be assigned, and They represent point-by-point subtraction and point-by-point multiplication, respectively. Indicates Calculate for index Point reduction The power function of each eigenvalue in the obtained eigenvector is Represents the semantic interaction fusion convergence feature vector of the multi-dimensional information of the second construction personnel to be assigned; The semantic interaction fusion probability feature vector of the multi-dimensional information of the construction personnel to be assigned is multiplied by the difference between one minus the semantic interaction fusion distribution probability value of the multi-dimensional information of the construction personnel to be assigned to obtain the first semantic interaction fusion limited feature vector of the multi-dimensional information of the construction personnel to be assigned. This process can be expressed as: ;in, represents the semantic interaction fusion probability feature vector of the multi-dimensional information of the construction personnel to be assigned, represents the probability value of semantic interaction fusion distribution of multi-dimensional information of the construction personnel to be assigned, It means point multiplication by position. Represents a semantic interaction fusion limited feature vector of the multi-dimensional information of the first construction personnel to be assigned; The point difference feature vector is multiplied by the semantic interaction fusion distribution probability value of the multi-dimensional information of the construction personnel to be assigned to obtain the second semantic interaction fusion limited feature vector of the multi-dimensional information of the construction personnel to be assigned. The process can be expressed as: ;in, represents the unit eigenvector, represents the semantic interaction fusion probability feature vector of the multi-dimensional information of the construction personnel to be assigned, represents the probability value of semantic interaction fusion distribution of multi-dimensional information of the construction personnel to be assigned, and They represent point-by-point subtraction and point-by-point multiplication, respectively. Represents the second multi-dimensional information semantic interaction fusion limited feature vector of the construction personnel to be assigned; After dot-multiplying the first semantic interaction fusion convergence feature vector of the multi-dimensional information of the construction personnel to be assigned with the second semantic interaction fusion convergence feature vector of the multi-dimensional information of the construction personnel to be assigned, the optimized semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned is obtained by dot-multiplying the first semantic interaction fusion limiting feature vector of the multi-dimensional information of the construction personnel to be assigned and the second semantic interaction fusion limiting feature vector of the multi-dimensional information of the construction personnel to be assigned. This process can be expressed as: in, represents the semantic interaction fusion convergence feature vector of the multi-dimensional information of the first construction personnel to be assigned, represents the semantic interaction fusion convergence feature vector of the second multi-dimensional information of the construction personnel to be assigned, represents the semantic interaction fusion limited feature vector of the multi-dimensional information of the first construction personnel to be assigned, represents the semantic interaction fusion limited feature vector of the multi-dimensional information of the second construction personnel to be assigned, and They represent point-by-point multiplication and point-by-point addition, respectively. A semantic interactive fusion representation vector representing the optimized multi-dimensional information of the construction personnel to be assigned; The optimized semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned is passed through the classifier-based skill level detector to obtain the detection result.

[0057] That is, by taking the cross entropy form power series of the distribution analysis probability of the semantic interactive fusion representation vector of the multi-dimensional information of the construction personnel to be assigned as the probability distribution convergence limit, the regression probability convergence approximation is performed on the basis of the combination of the feature set distribution and the probability density distribution of the semantic interactive fusion representation vector of the multi-dimensional information of the construction personnel to be assigned, so as to avoid the fatal potential divergence of the semantic interactive fusion representation vector of the multi-dimensional information of the construction personnel to be assigned under the premise of conservative convergence control, further use the probability distribution cross entropy of the semantic interactive fusion representation vector of the multi-dimensional information of the construction personnel to be assigned as the objective function to guide the limited recovery strategy, so as to achieve the common agility of the convergence of the probability convergence and divergence of the feature set of the semantic interactive fusion representation vector of the multi-dimensional information of the construction personnel to be assigned to the probability density distribution space, and improve the accuracy of the detection result obtained by the classifier-based skill level detector of the semantic interactive fusion representation vector of the multi-dimensional information of the construction personnel to be assigned.

[0058] In summary, step S150 is clearly explained, and it uses a data analysis and processing algorithm based on machine learning to embed and encode the engineer grade information and work experience information of the construction personnel to be assigned, respectively, so as to intelligently judge the skill level of the construction personnel to be assigned based on the external dynamic semantic interaction representation between the engineer grade coding features of the construction personnel to be assigned and the embedded coding features of the work experience of the construction personnel to be assigned. In this way, the complex implicit relationship between the engineer grade information and the work experience information can be captured, rather than just a simple quantitative indicator. At the same time, it can identify the unique skills and experience of each construction worker, provide personalized evaluation results, and thus realize the intelligent evaluation of the skill level of the construction workers.

[0059] In step S160, construction tasks are assigned to the construction personnel in the to-be-assigned state according to the construction task level and the skill level of the construction personnel to be assigned. It should be understood that the construction task level reflects the difficulty and complexity of the building construction task, while the skill level of the construction personnel to be assigned reflects the professional ability and experience level of the construction personnel. By matching the two, it can be ensured that each construction task is assigned to a construction personnel with corresponding capabilities, so that the task difficulty is adapted to the personnel skills, thereby improving the quality and success rate of the completion of the construction task. For example, a high-difficulty three-level construction task is assigned to a three-level construction personnel with a higher skill level. They are more likely to complete the task smoothly with their rich experience and professional skills, avoiding construction errors or delays due to insufficient personnel capabilities. Accurately matching tasks and personnel can also effectively reduce safety risks during the construction process. Construction personnel work within their capabilities, which can reduce the possibility of safety accidents such as electrical fires and electric shocks caused by improper operation. In addition, due to the reasonable task allocation, the construction progress can be effectively guaranteed, avoiding construction delays caused by unreasonable task allocation, and ensuring that the entire electrical construction project is completed on time.

[0060] In summary, the intelligent management method of electrical construction tasks based on the embodiment of the present application is explained, which first obtains the number of the target building and searches for the corresponding building information model accordingly. Subsequently, an in-depth building analysis is performed on the target building based on the information model to determine its construction task level. At the same time, the work status and work information of the construction personnel are collected and sorted to form a total set of construction personnel. For the construction personnel in the total set who are in a waiting state, their work information is further analyzed to evaluate their skill level. Finally, the construction tasks are scientifically and reasonably allocated based on the determined construction task level and the skill level of the construction personnel to be allocated. In this way, the reasonable allocation between construction tasks and construction personnel can be ensured, thereby improving the overall construction efficiency and quality.

[0061] In an embodiment of the present application, an intelligent management system for electrical construction tasks is also provided, which is used to execute the intelligent management method for electrical construction tasks as described above. Figure 5 : is a system block diagram of the intelligent management system for electrical construction tasks according to an embodiment of the present application. Figure 5 As shown, according to the embodiment of the present application, the intelligent management system 100 for electrical construction tasks includes: a construction personnel data screening module 110, which is used to screen out construction personnel whose working status is to be assigned from the total set of construction personnel to obtain a set of construction personnel to be assigned; a construction personnel work information extraction module 120, which is used to extract work information of construction personnel to be assigned from the set of construction personnel to be assigned, wherein the work information includes engineer grade information and work experience information; a construction personnel work information encoding module 130, which is used to encode the engineer grade information and work experience information of the construction personnel to be assigned respectively to obtain the engineer grade coding features of the construction personnel to be assigned and the work experience embedded coding features of the construction personnel to be assigned; a construction personnel skill level label generation module 140, which is used to perform external dynamic memory semantic interaction on the engineer grade coding features of the construction personnel to be assigned and the work experience embedded coding features of the construction personnel to be assigned to obtain a semantic interaction fusion representation of multi-dimensional information of the construction personnel to be assigned, and obtain the skill level label of the construction personnel to be assigned based on the semantic interaction fusion representation of the multi-dimensional information of the construction personnel to be assigned.

[0062] Here, those skilled in the art will appreciate that the specific functions and operations of the various units and modules in the above-mentioned electrical construction task intelligent management system 100 have been described in detail above. Figures 1 to 4 The invention has been introduced in detail in the description of the intelligent management method of electrical construction tasks, and therefore, its repeated description will be omitted.

[0063] In summary, the intelligent management system 100 for electrical construction tasks based on the embodiment of the present application is explained, which first obtains the number of the target building, and searches for the corresponding building information model accordingly, and then conducts an in-depth building analysis of the target building based on the information model to determine its construction task level. At the same time, the work status and work information of the construction personnel are collected and sorted to form a total set of construction personnel. For the construction personnel in the total set who are in the state of being assigned, their work information is further analyzed to evaluate their skill level. Finally, the construction tasks are scientifically and reasonably assigned according to the determined construction task level and the skill level of the construction personnel to be assigned. In this way, the reasonable configuration between construction tasks and construction personnel can be ensured, thereby improving the overall construction efficiency and quality.

Claims

1. An intelligent management method for electrical construction tasks, comprising: Get the building number of the target building; Searching for a building information model corresponding to the target building according to the building number; Performing architectural analysis on the target building based on the building information model to obtain a construction task level of the building; Acquire the work status and work information of the construction personnel to obtain the total set of construction personnel; analyze the work information of the construction personnel whose work status is to be assigned in the total set of construction personnel to obtain the skill level of the construction personnel to be assigned; assign construction tasks to the construction personnel in the to-be-assigned state according to the construction task level and the skill level of the construction personnel to be assigned; characterized in that the work information of the construction personnel whose work status is to be assigned in the total set of construction personnel to obtain the skill level of the construction personnel to be assigned includes: Filter out construction personnel whose working status is to be assigned from the total set of construction personnel to obtain a set of construction personnel to be assigned; Extracting work information of construction personnel to be assigned from the set of construction personnel to be assigned, wherein the work information includes engineer grade information and work experience information; Encoding the engineer grade information and work experience information of the construction personnel to be assigned respectively to obtain the engineer grade coding feature of the construction personnel to be assigned and the work experience embedded coding feature of the construction personnel to be assigned; External dynamic memory semantic interaction is performed on the engineer grade coding features of the construction personnel to be assigned and the work experience embedded coding features of the construction personnel to be assigned to obtain a semantic interactive fusion representation of the multi-dimensional information of the construction personnel to be assigned, and based on the semantic interactive fusion representation of the multi-dimensional information of the construction personnel to be assigned, the skill level label of the construction personnel to be assigned is obtained.

2. The intelligent management method for electrical construction tasks according to claim 1, characterized in that: The work experience information includes the total number of electrical constructions, the total number of electrical maintenances, the success rate of electrical constructions and the success rate of electrical maintenances.

3. The intelligent management method for electrical construction tasks according to claim 2 is characterized in that: The engineer grade information and work experience information of the construction personnel to be assigned are respectively encoded to obtain the engineer grade encoding features of the construction personnel to be assigned and the work experience embedded encoding features of the construction personnel to be assigned, including: Performing one-hot encoding on the engineer grade information of the construction personnel to be assigned to obtain an engineer grade encoding vector of the construction personnel to be assigned as the engineer grade encoding feature of the construction personnel to be assigned; Data integration and embedding coding are performed on the work experience information of the construction personnel to be assigned to obtain an embedding coding vector of the work experience of the construction personnel to be assigned as an embedding coding feature of the work experience of the construction personnel to be assigned.

4. The intelligent management method for electrical construction tasks according to claim 3 is characterized in that: The work experience information of the construction personnel to be assigned is integrated and embedded in the code to obtain an embedded coding vector of the work experience of the construction personnel to be assigned, including: Integrate the work experience information of the construction personnel to be assigned according to the work experience sample dimension to obtain a work experience vector of the construction personnel to be assigned; The work experience embedding matrix is ​​used to embed the work experience vector of the construction personnel to be assigned to obtain the work experience embedding coding vector of the construction personnel to be assigned.

5. The intelligent management method for electrical construction tasks according to claim 4 is characterized in that: Performing external dynamic memory semantic interaction on the engineer grade coding features of the construction personnel to be assigned and the work experience embedding coding features of the construction personnel to be assigned to obtain a multi-dimensional information semantic interaction fusion representation of the construction personnel to be assigned, and obtaining a skill grade label of the construction personnel to be assigned based on the multi-dimensional information semantic interaction fusion representation of the construction personnel to be assigned, including: Performing external dynamic memory semantic interaction on the engineer grade coding vector of the construction personnel to be assigned and the work experience embedding coding vector of the construction personnel to be assigned to obtain a semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned as the semantic interaction fusion representation of the multi-dimensional information of the construction personnel to be assigned; A detection result is obtained according to the semantic interactive fusion representation vector of the multi-dimensional information of the construction personnel to be assigned, and the detection result is used to represent the skill level label of the construction personnel to be assigned.

6. The intelligent management method for electrical construction tasks according to claim 5, characterized in that: The external dynamic memory semantic interaction is performed on the engineer grade coding vector of the construction personnel to be assigned and the work experience embedding coding vector of the construction personnel to be assigned to obtain a semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned, including: Performing fine-grained feature interaction on the engineer grade encoding vector of the construction personnel to be assigned and the work experience embedding encoding vector of the construction personnel to be assigned to obtain an engineer grade-work experience fine-grained interaction feature matrix; According to the engineer grade-work experience fine-grained interactive feature matrix, external attention interaction optimization is performed on the engineer grade encoding vector of the construction personnel to be assigned and the work experience embedding encoding vector of the construction personnel to be assigned, respectively, to obtain an optimized engineer grade encoding vector of the construction personnel to be assigned and an optimized work experience embedding encoding vector of the construction personnel to be assigned; The optimized engineer grade coding vector of the construction personnel to be assigned and the optimized work experience embedding coding vector of the construction personnel to be assigned are calculated and divided by the position points to obtain the semantic interactive fusion representation vector of the multi-dimensional information of the construction personnel to be assigned.

7. The intelligent management method for electrical construction tasks according to claim 6, characterized in that: According to the engineer grade-work experience fine-grained interactive feature matrix, external attention interaction optimization is performed on the engineer grade encoding vector of the construction personnel to be assigned and the work experience embedding encoding vector of the construction personnel to be assigned to obtain an optimized engineer grade encoding vector of the construction personnel to be assigned and an optimized work experience embedding encoding vector of the construction personnel to be assigned, including: Performing external knowledge attention optimization on the engineer level-work experience fine-grained interactive feature matrix to obtain an engineer level-work experience external knowledge optimized fine-grained interactive feature matrix; Performing a linear transformation on the engineer grade coding vector of the construction personnel to be assigned to obtain an engineer grade query feature vector and an engineer grade value feature vector, and using the engineer grade-work experience external knowledge optimized fine-grained interactive feature matrix as a key matrix, performing converter-based modulation optimization on the engineer grade query feature vector, the engineer grade value feature vector and the key matrix to obtain the optimized engineer grade coding vector of the construction personnel to be assigned; The work experience embedding coding vector of the construction personnel to be assigned is linearly transformed to obtain a work experience query feature vector and a work experience value feature vector, and the engineer level-work experience external knowledge optimized fine-grained interaction feature matrix is ​​used as a key matrix. The work experience query feature vector, the work experience value feature vector and the key matrix are modulated and optimized based on the converter to obtain the optimized work experience embedding coding vector of the construction personnel to be assigned.

8. The intelligent management method for electrical construction tasks according to claim 7, characterized in that: Obtaining a detection result according to the semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned, including: passing the semantic interaction fusion representation vector of the multi-dimensional information of the construction personnel to be assigned through a classifier-based skill level detector to obtain the detection result.

9. An intelligent management system for electrical construction tasks, used to execute the intelligent management method for electrical construction tasks as claimed in claim 1, characterized in that: The electrical construction task intelligent management system includes: A construction personnel data screening module is used to screen out construction personnel whose working status is to be assigned from the total set of construction personnel to obtain a set of construction personnel to be assigned; A construction personnel work information extraction module is used to extract the work information of the construction personnel to be assigned from the construction personnel to be assigned set, wherein the work information includes engineer grade information and work experience information; A construction personnel work information encoding module is used to encode the engineer grade information and work experience information of the construction personnel to be assigned respectively to obtain the engineer grade encoding feature of the construction personnel to be assigned and the work experience embedded encoding feature of the construction personnel to be assigned; The construction personnel skill level label generation module is used to perform external dynamic memory semantic interaction on the engineer level coding features of the construction personnel to be assigned and the work experience embedded coding features of the construction personnel to be assigned to obtain the multi-dimensional information semantic interaction fusion representation of the construction personnel to be assigned, and obtain the skill level label of the construction personnel to be assigned based on the multi-dimensional information semantic interaction fusion representation of the construction personnel to be assigned.

10. The intelligent management system for electrical construction tasks according to claim 9, characterized in that: The construction personnel work information encoding module is used to: Performing one-hot encoding on the engineer grade information of the construction personnel to be assigned to obtain an engineer grade encoding vector of the construction personnel to be assigned as the engineer grade encoding feature of the construction personnel to be assigned; Data integration and embedding coding are performed on the work experience information of the construction personnel to be assigned to obtain an embedding coding vector of the work experience of the construction personnel to be assigned as an embedding coding feature of the work experience of the construction personnel to be assigned.

Images