Engineering manpower informatization management scheduling method and system based on AI and big data

Abstract

The invention discloses an engineering manpower informatization management scheduling method and system based on AI and big data, and the method comprises the steps: inputting the basic information and working state information of engineering personnel through employing a deep learning-based personnel capability evaluation model, precisely evaluating the fitness scores of the personnel for different tasks in a data-driven manner, and improving the working efficiency of the engineering personnel. Subjective and one-sided evaluation of manual evaluation is avoided, a scientific basis is provided for task allocation, and task efficiency and quality are improved; meanwhile, a task scheduling optimization model based on reinforcement learning is adopted, fitness scores, tasks and environment information are input, an optimal allocation strategy is learned through interaction with the environment, intelligent decision making is achieved, the method is more suitable for complex scenes, and allocation rationality and effectiveness are improved; besides, an initial allocation scheme is optimized by combining engineering real-time requirements and resource constraints, re-evaluation and dynamic adjustment are performed, and an optimal allocation state is kept on the premise that conditions are met, so that engineering manpower management scheduling is flexible and efficient, and engineering uncertainty is better dealt with.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of engineering human information management scheduling, and particularly relates to an engineering human information management scheduling method and system based on AI and big data. BACKGROUND

[0002] In the field of engineering construction, reasonable human management scheduling is one of the key factors for the smooth progress and success of the project. With the continuous expansion of the engineering scale and the increasing complexity, the traditional human management scheduling method faces many challenges and has been difficult to meet the efficient and accurate management needs of modern engineering.

[0003] With the development of information technology, some engineering projects have begun to use simple information management systems to assist human management scheduling. These systems can usually only record and query personnel basic information and task information, and the function is relatively single. Although the efficiency of information management is improved to some extent, there is still a lack of scientific methods and intelligent support in personnel capability assessment and task allocation decision-making. At the same time, the system cannot dynamically adjust the personnel task allocation scheme according to the actual ability and working state of the personnel, and the real-time demand and environmental changes of the engineering. SUMMARY

[0004] Therefore, the present application provides an engineering human information management scheduling method and system based on AI and big data, which can effectively solve the defects of the prior art that lack scientific methods and intelligent support in personnel capability assessment and task allocation decision-making, and cannot dynamically adjust the personnel task allocation scheme.

[0005] The technical scheme of the present application is as follows:

[0006] The engineering human information management scheduling method based on AI and big data comprises:

[0007] Collecting basic information, working state information, engineering task information and engineering environment information of engineering personnel;

[0008] Inputting the basic information and working state information of the engineering personnel into a preset personnel capability assessment model based on deep learning to obtain adaptability scores of the personnel for different types of tasks;

[0009] Inputting the adaptability scores of the personnel for different types of tasks, the engineering task information and the engineering environment information into a preset task scheduling optimization model based on reinforcement learning to obtain an initial personnel task allocation scheme;

[0010] Optimizing the initial personnel task allocation scheme in combination with real-time demand and resource constraints of the engineering to obtain an optimal personnel task allocation scheme.

[0011] As a further optional solution of the AI and big data based engineering human information management scheduling method, the collection of the basic information, working state information, engineering task information and engineering environment information of the engineering personnel specifically includes:

[0012] The basic information of the engineering personnel is collected by the engineering management system interface, and the basic information includes personal identity information, educational background and work experience;

[0013] The working state information of the engineering personnel is collected by the intelligent wearable device in real time, and the working state information includes heart rate, motion steps and body surface temperature, and the collected heart rate, continuous working time and body activity intensity data are converted into body fatigue degree index;

[0014] The engineering task information is obtained by connecting with the engineering task management software, and the engineering task information includes task number, task target, task associated equipment and materials;

[0015] The engineering environment information is collected by using various sensors installed on the engineering site.

[0016] As a further optional solution of the AI and big data based engineering human information management scheduling method, the basic information and working state information of the engineering personnel are input into the preset personnel capability evaluation model based on deep learning, and the adaptability score of the personnel to different types of tasks is obtained, specifically including:

[0017] The personnel capability evaluation model based on deep learning is constructed in advance, and the personnel capability evaluation model based on deep learning adopts a multi-layer neural network structure, wherein the number of input layer nodes is determined according to the feature dimension of the basic information and working state information of the engineering personnel, and the output layer nodes correspond to the adaptability scores of different types of tasks;

[0018] The basic information and working state information of the engineering personnel are input into the preset personnel capability evaluation model based on deep learning, and the model outputs the adaptability scores of the engineering personnel to various types of tasks defined in advance.

[0019] As a further optional solution of the AI and big data based engineering human information management scheduling method, the adaptability scores of the personnel to different types of tasks, the engineering task information and the engineering environment information are input into the preset task scheduling optimization model based on reinforcement learning, and the initial personnel task allocation plan is obtained, specifically including:

[0020] The task scheduling optimization model based on reinforcement learning is constructed, the state is defined as the combination of the current personnel state, task demand and environment information, the action is the personnel task allocation plan, and the reward function comprehensively considers the engineering progress, cost and quality;

[0021] The adaptability scores of the personnel to different types of tasks, engineering task information, and engineering environment information are input into the task scheduling optimization model based on reinforcement learning, and an initial personnel task allocation scheme is obtained through interaction with the environment.

[0022] As a further optional scheme of the AI and big data based engineering human information management scheduling method, the initial personnel task allocation scheme is optimized in combination with engineering real-time demand and resource constraint conditions to obtain an optimal personnel task allocation scheme, which specifically includes:

[0023] Real-time collection of engineering real-time demand information and resource constraint condition information;

[0024] Defining a chromosome coding mode of a genetic algorithm, the personnel task allocation scheme is coded as a chromosome, and each gene position represents an allocation relationship between a personnel and a task;

[0025] Initializing the population of the genetic algorithm, a plurality of initial chromosomes are randomly generated to represent different personnel task allocation schemes;

[0026] According to the engineering real-time demand information and the resource constraint condition information, the genetic algorithm is iterated, and after a plurality of iterations, when the preset maximum number of iterations is reached, the personnel task allocation scheme corresponding to the chromosome with the highest fitness is output as the optimized initial personnel task allocation scheme.

[0027] As a further optional scheme of the AI and big data based engineering human information management scheduling method, the method further includes:

[0028] The optimal personnel task allocation scheme is pushed to the relevant engineering personnel through the information management platform, and the task execution situation is monitored in real time, and the task scheduling strategy is dynamically adjusted according to the task execution feedback information.

[0029] An AI and big data based engineering human information management scheduling system, comprising:

[0030] An information collection module for collecting basic information, working state information, engineering task information, and engineering environment information of engineering personnel;

[0031] A personnel capability evaluation module for inputting the basic information and working state information of the engineering personnel into a preset personnel capability evaluation model based on deep learning to obtain adaptability scores of the personnel to different types of tasks;

[0032] A task allocation scheme generation module for inputting the adaptability scores of the personnel to different types of tasks, engineering task information, and engineering environment information into a preset task scheduling optimization model based on reinforcement learning to obtain an initial personnel task allocation scheme;

[0033] The task allocation optimization module is configured to optimize the initial personnel task allocation plan according to real-time engineering requirements and resource constraints to obtain an optimal personnel task allocation scheme.

[0034] As a further optional solution of the AI and big data based engineering human information management scheduling system, the system further comprises:

[0035] The dynamic adjustment module is configured to push the optimal personnel task allocation scheme to relevant engineering personnel through the information management platform, monitor the task execution in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information.

[0036] A computing device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of any one of the above AI and big data based engineering human information management scheduling methods when executing the computer program.

[0037] A computer readable storage medium, the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of any one of the above AI and big data based engineering human information management scheduling methods.

[0038] The beneficial effects of the present application are: by using the preset personnel capability evaluation model based on deep learning, the basic information and working state information of the engineering personnel are taken as input, so as to accurately evaluate the adaptability score of the personnel to different types of tasks. This data-driven evaluation method avoids the subjectivity and one-sidedness of manual evaluation, provides a scientific and objective basis for subsequent task allocation, ensures that the personnel can be allocated to tasks matching their capabilities, and improves the efficiency and quality of task completion. At the same time, the task scheduling optimization model based on reinforcement learning is adopted, the adaptability score of the personnel to different types of tasks, engineering task information and engineering environment information are taken as input, the reinforcement learning model learns the optimal task allocation strategy by continuously interacting with the simulated or actual engineering environment. During the interaction process, the model will take different actions according to different states, and obtain corresponding rewards or punishments according to the task completion effect. In this way, the model can automatically explore and optimize the task allocation scheme, comprehensively consider personnel capability, task demand, environmental conditions and other factors, and realize intelligent decision-making. Compared with traditional simple rules or manual decision-making, this intelligent decision-making method can better adapt to complex engineering scenarios, improve the rationality and effectiveness of task allocation. In addition, by combining the real-time demand of engineering and resource constraints, the initial personnel task allocation scheme is optimized, the feasibility and rationality of personnel task allocation are re-evaluated, the allocation scheme is dynamically adjusted, and the optimal personnel task allocation state is maintained under the premise of meeting the real-time demand of engineering and resource constraints. This dynamic adjustment capability makes the engineering human resource management and scheduling more flexible and efficient, and can better cope with various uncertainties in engineering. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0040] Fig. 1 The flowchart of the present application, an AI and big data based engineering human resource information management and scheduling method;

[0041] Fig. 2 The composition schematic diagram of the present application, an AI and big data based engineering human resource information management and scheduling system;

[0042] Fig. 3 The composition schematic diagram of the present application, a computing device. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present application will be clearly and completely described below. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0044] Reference Figs. 1 to 3 The AI and big data based engineering personnel informatization management and scheduling method comprises the following steps:

[0045] Basic information, working state information, engineering task information and engineering environment information of the engineering personnel are collected, specifically including the following aspects:

[0046] The basic information of the engineering personnel is collected by using an engineering management system interface, and the basic information includes personal identity information, educational background and work experience.

[0047] The working state information of the engineering personnel is collected in real time by using an intelligent wearable device, and the working state information includes heart rate, motion steps and body surface temperature, and the collected heart rate, continuous working time and body activity intensity data are converted into a body fatigue degree index.

[0048] The engineering task information is obtained by connecting with an engineering task management software, and the engineering task information includes task number, task target, and associated equipment and materials.

[0049] The engineering environment information is collected by using various sensors installed at the engineering site.

[0050] Specifically, the information is collected from multiple channels, covering personnel basic conditions (identity, educational background, work experience), real-time working state (heart rate, motion steps, body surface temperature and other physiological and activity data), task specific requirements (task number, target, associated equipment and materials) and engineering site environment parameters. The integration of such multi-dimensional information provides comprehensive and rich basic data for subsequent personnel capability assessment and task allocation, and avoids decision bias caused by information loss.

[0051] The basic information is collected by using an engineering management system interface, which ensures the accuracy and standardization of the personnel basic data; the working state information is collected in real time by using an intelligent wearable device, which can obtain the most real and timely personnel physiological and activity data; the task information is obtained by connecting with an engineering task management software, which ensures the accuracy and consistency of the task related data; and the environment information is collected by using sensors installed at the engineering site, which provides objective and accurate site environment data.

[0052] The smart wearable device collects information such as the heart rate, motion steps and body temperature of the engineering personnel in real time, realizes real-time dynamic monitoring of the working state of the personnel, the management personnel can understand the working intensity and physical condition of the personnel at any time, timely find abnormal conditions and take corresponding measures, and guarantee the physical health and working safety of the personnel; the collected heart rate, continuous working time and physical activity intensity data are converted into a physical fatigue degree index, so that the working fatigue state of the personnel is quantified, which provides a scientific basis for reasonably arranging working tasks and adjusting working rhythm, avoids the decrease of working efficiency and quality caused by excessive fatigue of the personnel, and also helps to prevent working accidents caused by fatigue;

[0053] The engineering task information is obtained through the connection with the engineering task management software, the timely acquisition and accurate transmission of the task related data are ensured, which enables the management personnel to clearly understand the specific requirements and associated resources of each task, provides detailed information support for reasonably allocating personnel and resources, and helps to improve the precision and efficiency of task execution; the engineering environment information is collected, the influence of the environment on the personnel working and task execution is considered, for example, different temperature, humidity and other environmental conditions may affect the working efficiency and physical state of the personnel, and the operation of the equipment, the consideration of these environmental factors can make the task allocation more in line with the actual situation, and improve the feasibility and success rate of task execution.

[0054] It should be noted that the collected heart rate, continuous working time and physical activity intensity data are converted into a physical fatigue degree index, and the specific formula is:

[0055] ;

[0056] Among them, is the fatigue degree value, is the heart rate variation coefficient, is the continuous working time, is the physical activity intensity, , , is a weight coefficient, which is determined according to historical data and expert experience).

[0057] The basic information and working state information of the engineering personnel are input into a preset personnel ability evaluation model based on deep learning, to obtain the adaptability score of the personnel to different types of tasks, specifically including:

[0058] The pre-constructed deep learning-based personnel capability evaluation model adopts a multi-layer neural network structure, wherein the number of input layer nodes is determined according to the feature dimensions of the basic information and the working state information of the engineers, the hidden layer adopts a suitable activation function and the number of neurons to realize effective feature extraction and nonlinear mapping, and the output layer nodes correspond to the fitness scores of different types of tasks;

[0059] The basic information and the working state information of the engineers are input into the pre-set deep learning-based personnel capability evaluation model, complex calculation and feature analysis are performed according to the input information, and finally the fitness scores of the engineers for various types of predefined tasks (such as mechanical operation tasks, electrical debugging tasks, and project management tasks) are output.

[0060] Specifically, based on the deep learning model, the basic information (such as identity information, educational background, work experience, etc.) and the working state information (such as heart rate, motion steps, body temperature, etc.) of the engineers are input as input, the deep learning model can automatically learn complex patterns and relationships from massive data, and through multi-layer neural network, the data is deeply analyzed and mined, so as to obtain the fitness scores of the personnel for different types of tasks. This data-driven evaluation method reduces the interference of human factors, and makes the evaluation results more scientific and objective.

[0061] The model adopts a multi-layer neural network structure, and the number of input layer nodes is determined according to the feature dimensions of the information, which means that the model can comprehensively consider the multi-dimensional features of the basic information and the working state information of the personnel, and fully evaluate the capability of the personnel. For example, not only the professional skills and work experience of the personnel are considered, but also the real-time working state is combined, so that the adaptability of the personnel to different tasks in the current state can be more accurately judged, and the limitation of single factor evaluation is avoided.

[0062] Through learning and training of a large amount of data, the deep learning model can capture the subtle relationship between personnel capability and task requirements. For different types of tasks, the model can accurately evaluate the fitness scores of the personnel for each task according to the comprehensive information of the personnel, which enables the management personnel to accurately allocate the personnel to the most suitable task according to the score results, improves the efficiency and quality of task completion. For example, for tasks requiring high-intensity physical labor, the model can combine the working state information (such as the degree of physical fatigue) and the basic information (such as age and physical condition) of the personnel to accurately evaluate whether the personnel are suitable for undertaking the task.

[0063] The ability and working state of each person are unique, and the scheme can conduct personalized ability evaluation for each engineer. The model outputs the specific adaptability score of different tasks according to the input information of the specific person, fully considers the differences between persons, and the personalized evaluation helps to tap the potential of each person, fully exert the advantages of personnel, and realize the optimal allocation of human resources.

[0064] The working state of the engineer is dynamically changed, such as the working intensity and the degree of physical fatigue, which will change with the working time and the environment. In the scheme, when the new working state information is input, the deep learning model can recalculate the adaptability score of the personnel to different tasks, which makes the evaluation result reflect the current ability state of the personnel in real time. The manager can adjust the personnel task allocation in time according to the latest score result, ensure that the personnel always work under the appropriate working load, and improve the safety and efficiency of the work. In the engineering implementation process, the type and requirement of the task may change. The personnel ability evaluation model based on deep learning can quickly adapt to the change, reevaluate the adaptability of the personnel to the changed task according to the new task information and personnel information, which helps the engineering team to adjust the human arrangement in time, flexibly cope with various task changes, and ensure the smooth progress of the engineering.

[0065] The adaptability score of the personnel to different types of tasks, the engineering task information and the engineering environment information are input into the preset task scheduling optimization model based on reinforcement learning to obtain an initial personnel task allocation plan, specifically including:

[0066] The task scheduling optimization model based on reinforcement learning is constructed, the state is defined as the combination of the current personnel state, the task demand and the environment information, the action is the personnel task allocation plan, and the reward function comprehensively considers the engineering progress, the cost and the quality.

[0067] The adaptability score of the personnel to different types of tasks, the engineering task information and the engineering environment information are input into the task scheduling optimization model based on reinforcement learning, and the initial personnel task allocation plan is obtained through the interaction learning with the environment.

[0068] Specifically, the reinforcement learning model has the ability of autonomous learning and decision-making. By defining the state as the combination of the current personnel state, task demand and environmental information, and the action as the personnel task allocation scheme, and by comprehensively considering factors such as engineering progress, cost and quality to design the reward function, the model can automatically explore and optimize the task allocation strategy in complex engineering scenarios. Compared with the traditional decision-making method which relies on artificial experience or simple rules, this intelligent decision-making can more comprehensively and deeply analyze the mutual relationship between various factors, so as to make a more scientific and reasonable task allocation scheme. This scheme realizes the automation of task allocation decision-making. Once the model is trained, it can quickly output the initial personnel task allocation scheme after inputting the relevant information, greatly reducing the time and effort required for manual decision-making, improving the decision-making efficiency, and enabling the engineering team to respond to task demands and changes more timely.

[0069] The model comprehensively considers the adaptability score of personnel to different types of tasks, engineering task information and engineering environment information, and can more accurately match personnel with tasks. For example, according to the adaptability of personnel to specific task types, combined with the urgency, difficulty and on-site environmental conditions of the task, personnel can be reasonably arranged to perform corresponding tasks, ensuring that the ability of personnel matches the requirements of the task and improving the efficiency and quality of task completion. The situation of the engineering site is constantly changing, and task demands and environmental conditions may change at any time. The reinforcement learning model learns through interaction with the environment and can perceive these changes in real time and dynamically adjust the task allocation scheme. When there are emergency task insertions, personnel state changes or environmental factor changes, the model can quickly re-evaluate and optimize the allocation scheme to ensure that the task allocation always adapts to the actual needs of the project.

[0070] During the task allocation process, the model will consider engineering cost and resource utilization efficiency, optimize the task allocation scheme, reasonably arrange personnel's work tasks and time, avoid personnel idleness or overwork, and fully utilize equipment and other resources to achieve reasonable allocation of human resources and other resources, and reduce engineering cost. With engineering progress, cost and quality as the reward function factors, the model generates an allocation scheme that optimizes the overall benefit of the project. On the premise of ensuring that the task is completed on time, the task quality is improved as much as possible, and the cost is controlled, thereby maximizing the benefit of the project and improving the comprehensive competitiveness of the engineering project.

[0071] The initial personnel task allocation scheme is optimized in combination with real-time demand and resource constraint conditions to obtain an optimal personnel task allocation scheme, which specifically includes:

[0072] Real-time demand information is collected in real time, such as the type of emergency task, the deadline, the task quality standard required by the customer, etc. At the same time, resource constraint condition information is collected, including the number of available personnel, skill level, available equipment, operating status, etc.

[0073] Define the chromosome encoding method of genetic algorithm, encode the personnel task allocation scheme as a chromosome, and each gene position represents the allocation relationship between a person and a task, for example, use real number encoding, and the value of the gene position represents the priority or matching degree of the person performing the task;

[0074] Initialize the population of the genetic algorithm, randomly generate multiple initial chromosomes representing different personnel task allocation schemes, and ensure that the initial population has a certain diversity to increase the possibility of searching for the optimal solution;

[0075] Design a fitness function that takes into account real-time engineering requirements and resource constraints, for example, the fitness function can include task completion time indicators (prioritize completing urgent tasks), resource utilization indicators (balance personnel workload, high equipment usage efficiency), task quality indicators (meet customer special requirements), etc. Calculate the fitness value of each chromosome, the higher the fitness value, the better the personnel task allocation scheme;

[0076] Perform iterative operations of the genetic algorithm based on real-time engineering requirement information and resource constraint condition information, including selection, crossover and mutation, specifically:

[0077] Selection operation: select chromosomes with higher fitness values into the next generation according to the fitness values, which can use methods such as roulette wheel selection, tournament selection, etc., while combining resource constraints to ensure that the selected chromosomes are feasible in terms of resource utilization;

[0078] Crossover operation: exchange genes of selected chromosomes to generate new chromosomes, and check whether the newly generated chromosomes meet the real-time engineering requirements and resource constraints during the crossover process. If not, adjust or re-cross them;

[0079] Mutation operation: change the gene positions on the chromosome with a certain probability to increase the diversity of the population. Similarly, the mutated chromosomes need to meet the relevant conditions.

[0080] After multiple iterations, when the maximum number of iterations is reached, output the personnel task allocation scheme corresponding to the chromosome with the highest fitness value as the optimized initial personnel task allocation scheme.

[0081] In some embodiments, the method further comprises:

[0082] Push the optimal personnel task allocation scheme to relevant engineering personnel through the information management platform, and monitor the task execution in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information.

[0083] Specifically, with the help of the information management platform, the optimal personnel task allocation scheme can be quickly and accurately pushed to the relevant engineering personnel. Compared with the traditional manual notification method, the information transmission time is greatly shortened, the distortion and delay of information in the transmission process are avoided, and the engineering personnel can understand their task arrangement in a timely and clear manner, providing a guarantee for the smooth development of the task.

[0084] Real-time monitoring of task execution, management personnel can understand the progress of the task, whether it encounters problems, etc. information, through the information management platform, the task execution state can be displayed in the form of intuitive charts, data, etc. to make the management personnel have a clear grasp of the engineering progress, so as to discover potential delay risks in time and take corresponding measures; in addition to progress monitoring, the quality and compliance of task execution can also be supervised, for example, through the platform to record the key data and operation steps in the task execution process, to ensure that the engineering personnel complete the task according to the specified standards and processes, to ensure the engineering quality and reduce the quality problems caused by human error or illegal operation.

[0085] An engineering human information management and scheduling system based on AI and big data, comprising:

[0086] An information collection module for collecting basic information, working state information, engineering task information and engineering environment information of engineering personnel;

[0087] A personnel capability assessment module for inputting the basic information and working state information of the engineering personnel into a pre-set personnel capability assessment model based on deep learning to obtain the adaptability score of the personnel to different types of tasks;

[0088] A task allocation preliminary plan generation module for inputting the adaptability score of the personnel to different types of tasks, engineering task information and engineering environment information into a pre-set task scheduling optimization model based on reinforcement learning to obtain an initial personnel task allocation plan;

[0089] A task allocation optimization module for optimizing the initial personnel task allocation plan in combination with real-time engineering demand and resource constraints to obtain an optimal personnel task allocation scheme.

[0090] In some embodiments, the system further comprises:

[0091] A dynamic adjustment module for pushing the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform and real-time monitoring of the task execution, and dynamically adjusting the task scheduling strategy according to the task execution feedback information.

[0092] A kind of computing device, including memory, processor and computer program stored in the memory and can be run on the processor, when the processor executes the computer program, the steps of any one of the above described AI and big data based engineering human information management scheduling method are implemented.

[0093] A computer readable storage medium, the storage medium is stored with computer program, when the computer program is executed by processor, the steps of any one of the above described AI and big data based engineering human information management scheduling method are implemented.

[0094] The above only is the preferred embodiment of the present application, and does not use to limit the present application, any modification, equivalent replacement, improvement etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. An AI and big data-based engineering human resource informatization management and scheduling method, characterized by, The method comprises the following steps: Collecting basic information, working state information, engineering task information and engineering environment information of engineering personnel; Inputting the basic information and working state information of the engineering personnel into a preset personnel capability evaluation model based on deep learning to obtain adaptability scores of the personnel for different types of tasks; Inputting the adaptability scores of the personnel for different types of tasks, the engineering task information and the engineering environment information into a preset task scheduling optimization model based on reinforcement learning to obtain an initial personnel task allocation plan; Optimizing the initial personnel task allocation plan in combination with real-time demand and resource constraint conditions of the engineering to obtain an optimal personnel task allocation scheme. 2.The AI and big data-based engineering human resource informatization management and scheduling method of claim 1, wherein, The collection of the basic information, working state information, engineering task information and engineering environment information of the engineering personnel specifically comprises: Collecting the basic information of the engineering personnel by using an engineering management system interface, wherein the basic information comprises personal identity information, educational background and work experience; Collecting the working state information of the engineering personnel in real time by using an intelligent wearable device, wherein the working state information comprises heart rate, motion steps and body surface temperature, and the collected heart rate, continuous working time and body activity intensity data are converted into a body fatigue degree index; Obtaining the engineering task information by interfacing with an engineering task management software, wherein the engineering task information comprises task number, task target, task-associated equipment and materials; Collecting the engineering environment information by using various sensors installed at the engineering site. 3.The AI and big data-based engineering human resource informatization management and scheduling method of claim 2, wherein, The inputting of the basic information and working state information of the engineering personnel into the preset personnel capability evaluation model based on deep learning to obtain the adaptability scores of the personnel for different types of tasks specifically comprises: Pre-constructing a personnel capability evaluation model based on deep learning, wherein the personnel capability evaluation model based on deep learning adopts a multi-layer neural network structure, the number of nodes of an input layer is determined according to the feature dimension of the basic information and working state information of the engineering personnel, and the nodes of an output layer correspond to adaptability scores of different types of tasks; Inputting the basic information and working state information of the engineering personnel into the preset personnel capability evaluation model based on deep learning, and the model outputs adaptability scores of the engineering personnel for various types of tasks defined in advance. 4.The AI and big data-based engineering human resource informatization management and scheduling method of claim 3, wherein, The inputting of the adaptability scores of the personnel for different types of tasks, the engineering task information and the engineering environment information into the preset task scheduling optimization model based on reinforcement learning to obtain the initial personnel task allocation plan specifically comprises: Constructing a task scheduling optimization model based on reinforcement learning, defining a state as a combination of current personnel state, task demand and environment information, defining an action as a personnel task allocation scheme, and comprehensively considering engineering progress, cost and quality in a reward function; Inputting the adaptability scores of the personnel for different types of tasks, the engineering task information and the engineering environment information into the task scheduling optimization model based on reinforcement learning, and obtaining the initial personnel task allocation scheme through interaction learning with the environment. 5.The AI and big data-based engineering human resource informatization management and scheduling method of claim 4, wherein, The optimization of the initial personnel task allocation plan in combination with real-time demand and resource constraint conditions of the engineering to obtain the optimal personnel task allocation scheme specifically comprises: Collecting real-time demand information and resource constraint condition information of the engineering in real time; The chromosome coding mode of the genetic algorithm is defined, and a personnel task allocation scheme is coded as a chromosome, each gene position representing a personnel-task allocation relationship; The population of the genetic algorithm is initialized, and multiple initial chromosomes are randomly generated, representing different personnel task allocation schemes; According to the real-time demand information and resource constraint condition information of the project, the genetic algorithm is iterated, and after multiple iterations, when the preset maximum iteration number is reached, the personnel task allocation scheme corresponding to the chromosome with the highest fitness is output as the optimized initial personnel task allocation scheme. 6.The AI and big data-based engineering human resource informatization management and scheduling method of claim 5, wherein, The method further comprises: The optimal personnel task allocation scheme is pushed to the relevant engineering personnel through the information management platform, and the task execution situation is monitored in real time, and the task scheduling strategy is dynamically adjusted according to the task execution feedback information.

7. An AI and big data-based engineering human resource informatization management and scheduling system, characterized by It includes: The information collection module is used to collect the basic information, working state information, engineering task information and engineering environment information of the engineering personnel; The personnel capability evaluation module is used to input the basic information and working state information of the engineering personnel into a preset personnel capability evaluation model based on deep learning to obtain the adaptability scores of the personnel to different types of tasks; The task allocation preliminary plan generation module is used to input the adaptability scores of the personnel to different types of tasks, engineering task information and engineering environment information into a preset task scheduling optimization model based on reinforcement learning to obtain an initial personnel task allocation plan; The task allocation optimization module is used to optimize the initial personnel task allocation plan in combination with the real-time demand and resource constraint conditions of the project to obtain an optimal personnel task allocation scheme. 8.The AI and big data-based engineering human resource informatization management and scheduling system according to claim 7, characterized in that, The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information.

9. A computing device, comprising: The system further comprises:

10. A computer-readable storage medium, characterized in that, The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment module is used to push the optimal personnel task allocation scheme to the relevant engineering personnel through the information management platform, and monitor the task execution situation in real time, and dynamically adjust the task scheduling strategy according to the task execution feedback information. The system further comprises: The dynamic adjustment

Images