Personnel dynamic scheduling method based on biological characteristics of sorting personnel

Abstract

The invention discloses a personnel dynamic scheduling method based on biological characteristics of sorting personnel, which comprises the following steps of: acquiring data of individual biological characteristics of personnel in a logistics transit yard, preprocessing the acquired data, and constructing a biological characteristic vector; a human-machine-task three-element collaborative virtual mapping system is constructed, and predictive optimization and state-driven regulation and control of a scheduling strategy are realized; based on a current sorting task, personnel health, sorting priority and fatigue regulation and control as targets, a multi-objective function is designed to realize comprehensive optimization of dynamic scheduling; and based on the established multi-objective optimization model, a multi-objective evolutionary algorithm is applied to a multi-objective scheduling problem, and structure optimization and heuristic enhancement are carried out for a logistics scene. According to the invention, dynamic perception, intelligent optimization and closed-loop control of logistics sorting and scheduling are realized on the premise of considering operation efficiency improvement, personnel health guarantee and task response accuracy.

Description

Technical Field

[0001] The present invention relates to the field of logistics scheduling, and particularly to a dynamic scheduling method for personnel based on the biometric characteristics of sorting personnel. Background Art

[0002] With the rapid development of e-commerce logistics, the sorting operations in logistics transfer yards are facing the dual challenges of efficiency improvement and personnel safety guarantee. Traditional static scheduling methods, such as the fixed 8-hour shift system and the manual allocation method based on experience, are difficult to meet the requirements of modern logistics for flexible and intelligent management in practical applications. These methods often ignore the physiological states of sorting personnel, such as key biometric characteristics like fatigue degree and heart rate changes, which easily lead to unreasonable distribution of work intensity, resulting in overwork and even health risks. At the same time, their scheduling mechanisms lack flexibility and cannot be dynamically adjusted according to real-time task volumes and personnel states, leading to low resource allocation efficiency. In addition, the static algorithm parameters are fixed and lack the adaptability to complex scenarios such as peak periods and sudden absences. In recent years, with the rapid development of wearable devices (such as smart bracelets and smart work badges) and biometric sensor technologies, the biometric data of sorting personnel can be collected in real time, which provides a technical basis for constructing a human-centered and dynamically perceiving scheduling system. However, how to deeply integrate these high-frequency and multi-dimensional human physiological data with scheduling algorithms and achieve precise modeling and prediction of personnel states through a digital twin model, so as to realize dynamic scheduling that takes into account operation efficiency, personnel health, and task urgency, is still an important technical difficulty that needs to be urgently broken through. Summary of the Invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art and provide a dynamic scheduling method for personnel based on the biometric characteristics of sorting personnel. On the premise of taking into account the improvement of operation efficiency, personnel health guarantee, and task response accuracy, it realizes the dynamic perception, intelligent optimization, and closed-loop control of logistics sorting scheduling, and solves the problems of the lack of perception of physiological states and poor adaptability to complex environments in traditional static scheduling modes.

[0004] The purpose of the present invention is achieved through the following technical solutions: A dynamic scheduling method for personnel based on the biometric characteristics of sorting personnel, comprising the following steps: Collect data on the individual biometric characteristics of the staff in the logistics transfer yard, preprocess the collected data, and construct a biometric vector; Construct a virtual mapping system for the tripartite coordination of humans, machines, and tasks to achieve predictive optimization and state-driven regulation of scheduling strategies; Based on the current sorting tasks, personnel health, sorting priorities, and fatigue degree regulation as the goals, design a multi-objective function to achieve the comprehensive optimization of dynamic scheduling; Based on the established multi-objective optimization model, a multi-objective evolutionary algorithm is applied to the multi-objective shift scheduling problem, and structural optimization and heuristic enhancement are carried out for the logistics scenario.

[0005] The beneficial effects of the present invention are as follows: The present invention constructs a dynamic shift scheduling optimization system driven by multi-source biometrics for intelligent logistics transfer yards. By integrating high-frequency physiological data collected by wearable devices, digital twin modeling, and multi-objective evolutionary algorithms, the dynamic and intelligent nature of the shift scheduling strategy is comprehensively improved. Specifically, the present invention establishes a personnel state quantification model with key physiological indicators such as heart rate, fatigue level, and attention as core variables, revealing the internal coupling relationship between the physiological state of operators, work efficiency, and health risks. At the same time, digital twin technology is introduced to construct a virtual mapping system for ternary collaboration of "human-machine-task", realizing real-time mapping and prediction of the individual state of sorting personnel, and providing high-precision and feedbackable dynamic input for the scheduling system. In terms of scheduling optimization, the present invention proposes a multi-objective shift optimization model covering maximizing operation efficiency, minimizing health risks, task emergency response, and fatigue balance, and conducts structural optimization and adaptive enhancement based on the NSGA-II algorithm, proposing a two-dimensional matrix chromosome coding method to ensure the spatial continuity and time coordination of task allocation. By introducing an adaptive crossover and mutation strategy, the population diversity and local search ability of the algorithm are effectively improved, and the robustness and adaptability to complex scenarios such as peak periods and sudden absences are enhanced. On the premise of considering the improvement of operation efficiency, personnel health protection, and task response accuracy, the present invention realizes the dynamic perception, intelligent optimization, and closed-loop control of logistics sorting shift scheduling, breaking through the technical bottlenecks of the traditional static shift mode, such as the lack of physiological state perception and poor adaptability to complex environments, and providing a new theoretical basis and technical support for the field of intelligent logistics shift scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] Figure 1 It is a flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0007] The technical solutions of the present invention will be further described in detail below with reference to the drawings, but the protection scope of the present invention is not limited to the following.

[0008] This patent aims to solve the key technical problems existing in the current logistics sorting scheduling, specifically including: how to scientifically quantify the correlation between the biometric characteristics of sorting personnel and their operation efficiency, construct a mathematical model with physiological indicators such as heart rate and fatigue as core variables, and reveal the influence mechanism of individual physiological states on operation performance; how to construct a dynamic virtual mapping body of sorting personnel based on digital twin technology, and through integrating multi-source real-time data collected by wearable devices (such as heart rate, movement trajectory, working hours, etc.), achieve accurate modeling and dynamic simulation of individual states, thereby forming a "virtual-real linkage" system highly synchronized with real personnel, providing real-time and predictable digital support for scheduling strategies; on this basis, how to achieve dynamic scheduling driven by multiple objectives, while ensuring operation efficiency, taking into account personnel health, safety risks and task urgency, and completing the intelligent optimization of scheduling strategies.

[0009] As Figure 1 shown, a method for dynamic personnel scheduling based on the biometric characteristics of sorting personnel includes the following steps: Collect data on the individual biometric characteristics of logistics transfer yard staff, preprocess the collected data, and construct a biometric vector. For the data collection and quantification of the individual biometric characteristics of logistics transfer yard staff, we use intelligent work badges, intelligent bracelets, and eye trackers to collect the following biometric data in real time: heart rate , in beats per minute; body temperature , in degrees Celsius; movement amplitude , a standardized value calculated by an acceleration sensor, ranging from 0 to 1; fatigue , a standardized evaluation value based on physiological electromyogram signals, ranging from 0 to 1; line-of-sight tracking , a standardized concentration of attention determined by an eye tracker, ranging from 0 to 1.

[0010] For the fatigue quantification model, we combine electromyogram signals (EMG) and movement amplitude to construct a fatigue function: where is the weight. Based on the above definitions, we integrate the above biometric data into a biometric vector X .

[0011] Use a three-axis acceleration sensor to measure the acceleration and calculate the acceleration modulus: , represents the measured x at time t, y ,z Accelerations in three directions; Denote the acceleration magnitude at time t; Using minmax normalization: Wherein, Is the maximum acceleration magnitude in historical statistics, Is the acceleration magnitude collected when standing still; For the above collected data, perform data preprocessing: adopt the Kalman filter algorithm to denoise the heart rate , body temperature Time series data, and the formula is: Wherein, Is the observed value, that is, the heart rate Or body temperature , Is the value after filtering, Is the Kalman gain; the denoised heart rate Is denoted as , the denoised body temperature Is denoted as ; The constructed biometric vector is denoted as: X .

[0012] To realize the real-time perception, dynamic mapping and intelligent simulation of the operation status of sorting personnel in the logistics transfer yard, the present invention constructs a virtual mapping system of "human-machine-task" ternary collaboration to realize the predictive optimization of scheduling strategies and state-driven regulation. Specifically, each operator corresponds to a unique digital twin, and this twin is dynamically modeled by the following three types of information: (1) Static information layer: includes personnel ID, job type, maximum working duration, and health records, which are used to initialize the basic parameter constraints of the twin model; (2) Dynamic state layer: Real-time obtain the biometric vector X , transmit it to the digital twin of the staff, and based on the edge computing gateway, upload the data of the personnel digital twin to the digital twin system of the sorting machine in real time; (3) Simulation behavior layer: Construct a state professional model using the collected historical data and adopt a time series prediction model based on the LSTM network: First, according to the historical information, construct multiple groups of sample data. Each group of sample data contains the states of two adjacent time windows. After training the LSTM network with multiple groups of samples, obtain the trained LSTM network. Then, input the state of the current time window into the trained LSTM network to obtain the state of the next time window; the state refers to X at each moment ; Based on the historical state of the most recent time window, input it into the trained LSTM model to obtain the state information within the next time window; Sorting task information: Pre-define and clarify the sorting task details: the standing position of the sorting personnel, the number of sorted packages, and the status of the sorting machine; then establish a task process model for the sorting task, including the interaction between the sorting personnel and the sorting machine during the sorting process; connect the task information to the digital twin model of the sorting machine; The digital twin model of the sorting machine is based on the CAD model, kinematic and dynamic parameters of the actual equipment, establishes an accurate three-dimensional model of the equipment, and docks the physical equipment model with the data real-time update interface to achieve two-way mapping between the virtual environment and the physical equipment; the digital twin models of the sorting machine and the personnel and the task information all need to have interfaces for synchronous data communication; the digital twin model of the sorting machine is used to accurately evaluate the current sorting task information. By accessing the biological state data of the digital twin of the sorting personnel, obtain the sorting performance index, that is, the package return rate.

[0013] Construction of a multi-objective optimization model: Based on the current sorting task, personnel health, sorting priority, and fatigue control as objectives, design a multi-objective function to achieve the comprehensive optimization of dynamic scheduling; (1) Work efficiency objective Sorting efficiency It is defined as the number of packages that can be sorted per minute, which is related to the real-time fatigue degree and attention concentration of the sorting personnel , where , is the weight coefficient, satisfying .

[0014] (2) Personnel health objective Health risk index , where is the benchmark value of healthy heart rate and body temperature, is the threshold value of healthy heart rate and body temperature, is the weight.

[0015] (3) Task urgency objective Task urgency , where is the adjustment coefficient, is the remaining value of the current sorting task from the package departure time, is the time for each package from entering the sorting system to being sorted and transported by vehicle.

[0016] (4) Fatigue regulation target First, we define the fatigue balance degree , where n is the total number of sorting personnel in the current sorting shift, is the average fatigue degree, is the weight.

[0017] Based on the above goals, we construct a multi-objective optimization function: Among them, are their respective weight coefficients, which are dynamically adjusted by the Analytic Hierarchy Process (AHP), including: Construct a hierarchical structure model: Among them, the layout scheduling problem is divided into two-level architecture: (1) The goal layer realizes the optimal scheduling efficiency and the balance of personnel health; (2) The criterion layer includes four core optimization goals: , that is, the operation efficiency goal, represented by ; , that is, the health risk control goal, represented by ; , that is, the task urgency response goal, represented by ; , that is, the operation efficiency goal, represented by .

[0018] Based on the above four defined criteria, a pairwise comparison matrix is carried out, where represents the importance degree of criterion i relative to criterion j.

[0019] Suppose the dimension of the pairwise comparison matrix is n (in the present invention, n = 4), and its maximum eigenvalue is obtained by the eigenvalue decomposition method, which is used to measure the consistency degree of the comparison matrix. Calculate the consistency index and look up the table to obtain the random consistency index (the RI value is the empirical value proposed by Saaty, representing the expected consistency index under the completely random situation, and there are different values corresponding to matrices of different orders. In the current case of n = 4, RI = 0.9). Then calculate the consistency ratio . If , it is considered that the judgment matrix has good consistency and the weights are reasonable and reliable; otherwise, if , it is considered that there is a large deviation in the judgment matrix and the matrix structure needs to be corrected to improve the consistency.

[0020] Based on the established multi-objective optimization model, a multi-objective evolutionary algorithm is applied to the multi-objective scheduling problem, and structural optimization and heuristic enhancement are carried out for the logistics scenario.

[0021] Based on the above-established multi-objective optimization model, the present invention applies the classical multi-objective evolutionary algorithm NSGA-II to the multi-objective scheduling problem, and conducts structural optimization and heuristic enhancement for the logistics scenario. To ensure the spatial continuity and time controllability of task allocation, the following two-dimensional matrix structure is used to encode chromosomes to represent the scheduling scheme: C , where is the number of sorting areas, is the number of scheduling time periods, is the sorting personnel id for the i-th sorting area and the j-th scheduling time period. For the personnel set, each person cannot be assigned to multiple areas in the same time period. Each scheduling scheme is regarded as an individual, and all individuals constitute a population; To improve the population diversity and avoid premature convergence, the following adaptive probability adjustment formula is designed: Crossover probability : Mutation probability : where, is the fitness of the current individual (multi-objective weighted value, that is ; are the maximum and average fitness of the current population; is a small constant to prevent division by zero; are the upper and lower limits of the crossover probability, are the upper and lower limits of the mutation probability. The worse the individual (the lower the fitness), the higher the crossover probability to enhance exploration; the higher the mutation probability, the greater the possibility of mutation to jump out of the local optimum.

[0022] Implementation scheme of the multi-objective evolutionary algorithm NSGA-II: 1. Initialization stage 1.1 Encoding method: C , where is the number of sorting areas, is the number of scheduling time periods, is the sorting personnel id for the i-th sorting area and the j-th scheduling time period; according to the current personnel scheduling scheme used in the logistics transfer yard as the initial population . 1.2 Parameter setting: Maximum number of iterations , the size N of the population (how many different scheduling schemes) 2. Fitness Evaluation For each individual (scheduling scheme) in the population: 2.1 Calculate four objective functions: 2.2 Multi-objective fitness weighting: 3. Non-dominated sorting and crowding distance calculation 3.1 Non-dominated sorting: Divide the population into several levels (Front 1, Front 2, ...); Front 1: Completely non-dominated individuals; Front 2: Individuals dominated by Front 1 but not by others; And so on.

[0023] Meaning of domination: For A to dominate B, if and only if: A is not worse than B in all objectives; A is better than B in at least one objective.

[0024] A solution is called a non-dominated solution if no other solution dominates it.

[0025] NSGA-II tends to retain non-dominated solutions because they represent the most balanced and optimal combination of scheduling schemes among multiple objectives.

[0026] In NSGA-II: The first layer Front ( ): All non-dominated solutions; The second layer Front ( ): Individuals only dominated by the solutions in Front1; And so on.

[0027] 3.2 Crowding distance: Calculate the crowding distance according to the objective function values within the same Front; Individuals with a larger crowding distance are preferentially retained to ensure population diversity.

[0028] Crowdedness: In the same non-dominated layer (such as Front1), the objective values of different solutions may be close. To maintain diversity, we should give priority to retaining those solutions that are "sparsely distributed". NSGA-II uses "crowdedness" to measure the sparseness around a solution: a large crowdedness → the solution is more "isolated" → more likely to be retained; a small crowdedness → the solutions are "crowded together" → may be eliminated. Crowdedness ensures that different types of scheduling strategies can be retained, rather than only retaining one type of solution in a rush.

[0029] Calculation scheme: For the k-th objective function , the crowdedness of individual i is: where , is the value of the adjacent individual of individual i in the k-th objective dimension. , are the maximum and minimum values of this objective function.

[0030] 4. Selection operation: Select parent individuals from the current population using the binary tournament method, that is, randomly select two individuals from the population and compare their non-dominated ranks (Front): the lower rank is preferred; if the ranks are the same, see which one has a larger crowdedness, and the one with the larger crowdedness is preferred. Select the better individual as the "parent" to participate in crossover and mutation.

[0031] 5. Crossover and mutation Crossover: Use the defined adaptive crossover probability , perform segment crossover on the time periods or regions of two parent chromosomes, and maintain the legality of the individuals (no repeated allocation).

[0032] Mutation: Use the defined adaptive mutation probability , randomly select a position in the matrix and replace it with other unallocated personnel in the same time period to ensure that the constraints are satisfied.

[0033] 6. Merging Merge the current population P t with the offspring population Q t to form R t , perform non-dominated sorting on R t , and select N individuals from the first several Fronts to form the next generation P t +1: Give priority to selecting those with a lower rank and a higher crowdedness.

[0034] 7. Termination and output If the maximum number of iterations is reached Or if the convergence condition is met, terminate and output the final scheduling measurement plan. The optimal individual plan finally output by the above multi-objective evolutionary algorithm (NSGA-II). In point 5, the optimization objectives are constructed, and in point 7, the representation method (chromosome) of the scheduling plan is defined. Under the constraints of these objective functions, the multi-objective evolutionary algorithm (NSGA-II) searches for the optimal scheduling plan and finally outputs a two-dimensional matrix. C , where: Rows, sorting areas: Each row represents different predefined sorting areas in the logistics transfer yard. Columns, scheduling time periods: Each column represents a scheduling period, in one-hour units. Content of each cell in the matrix: Sorting personnel ID.

[0035] Comprehensive meaning of scheduling measurement: 1. Personnel allocation: Specifically reflected in the arrangement of sorting personnel in each area during each time period, ensuring that there is no overlap of personnel and meeting the requirements of area tasks. 2. Task volume allocation: Through the expected sorting task volume, the scheduling system not only determines who goes to which area at what time, but also estimates the number of sorting tasks that the person should complete during the corresponding time period, and then uses it for subsequent operation monitoring and closed-loop feedback control. 3. Basis for dynamic adjustment: As the final output, this scheduling matrix is generated by a multi-objective optimization algorithm (such as NSGA-II) and can be dynamically adjusted according to real-time data to achieve maximum operation efficiency, minimum health risks, timely response to task emergencies, and balanced personnel fatigue.

[0036] The above is the preferred implementation manner of the present invention. It should be understood that the present invention is not limited to the form disclosed herein, should not be regarded as excluding other embodiments, but can be used in other combinations, modifications, and environments, and can be changed within the scope of the concept described herein through the above teachings or the technology or knowledge in related fields. And the changes and alterations made by those skilled in the art that do not depart from the spirit and scope of the present invention shall fall within the protection scope of the appended claims of the present invention.

Claims

1. A dynamic scheduling method for sorting personnel based on biological characteristics of sorting personnel, characterized by: The following steps are involved: Collect individual biometric data of logistics transfer station staff, pre-process the collected data, and construct biometric vectors; Build a virtual mapping system for the collaboration of humans, machines, and tasks to achieve predictive optimization of scheduling strategies and state-driven regulation; Based on the current sorting task, personnel health, sorting priority and fatigue control as goals, a multi-objective function is designed to achieve comprehensive optimization of dynamic scheduling; Based on the established multi-objective optimization model, the multi-objective evolutionary algorithm is applied to the multi-objective scheduling problem, and structural optimization and heuristic enhancement are performed for logistics scenarios.

2. According to claim 1, a method for dynamic scheduling of personnel based on the biological characteristics of sorting personnel, characterized in that: The data collection and quantification of individual biometric characteristics of logistics transfer site staff includes: The following biometric data of staff members are collected in real time: Heart rate , the unit is times / minute; body temperature , the unit is Celsius; Range of motion , a normalized value calculated by the acceleration sensor, ranging from 0 to 1, is calculated as follows: The acceleration modulus is calculated by measuring the acceleration sign using the three-axis acceleration sensor: , Indicates the measured value at time t x , y , z Acceleration in three directions; represents the acceleration modulus at time t; Using minmax normalization: in, is the historical statistical maximum acceleration modulus, is the acceleration modulus value collected when standing still; Fatigue , a standardized evaluation value based on physiological electromyographic signals, ranging from 0 to 1; The calculation combines the electromyographic signal and the movement amplitude , construct the fatigue function: in, is the weight; The electrical signal generated by the muscles during activity is collected by wearable patch electrodes attached to the skin on the surface of the muscles. The weak potential changes generated by muscle contraction are detected through the skin. The action frequency refers to the peak value detection of the envelope in the action state: each muscle contraction usually forms an obvious peak on the envelope. The action frequency is calculated by counting the number of peaks that appear within a certain period of time. ; The base frequency is the preset frequency: 1 time / 15 seconds; Gaze Tracking , the standardized focus of attention determined by an eye tracker, ranging from 0 to 1.

3. According to claim 2, a method for dynamic scheduling of personnel based on the biological characteristics of sorting personnel is characterized by: The preprocessing of the collected data includes: Using Kalman filter algorithm to analyze heart rate ,body temperature The time series data is denoised using the formula: in, is the observed value, i.e., heart rate or body temperature , is the filtered value, is the Kalman gain; the heart rate after denoising Recorded as , body temperature after denoising Recorded as ; The constructed biometric vector is recorded as: X 。 4. According to claim 1, a method for dynamic scheduling of personnel based on the biological characteristics of sorting personnel, characterized in that: The construction of a virtual mapping system for the ternary coordination of man, machine and task to achieve predictive optimization and state-driven regulation of scheduling strategies includes: Each operator has a unique digital twin, which is dynamically modeled by the following three types of information: (1) Static information layer: contains personnel ID, job type, maximum working time, and health records, which are used to initialize the basic parameter constraints of the twin model; (2) Dynamic state layer: real-time acquisition of biometric feature vector X , transmitted to the digital twin of the staff, and uploaded the data of the staff digital twin to the digital twin system of the sorting machine in real time based on the edge computing gateway; (3) Simulation behavior layer: Constructing a state professional model Using the collected historical data, a time series prediction model based on the LSTM network is adopted: First, multiple groups of sample data are constructed based on historical information. Each group of sample data contains the state of two adjacent time windows. After training the LSTM network with multiple groups of samples, a trained LSTM network is obtained. Then, the state of the current time window is input into the trained LSTM network to obtain the state of the next time window. The state refers to the X at each moment. ; Based on the historical state of the most recent time window, input it into the trained LSTM model to obtain the state information in the next time window; Sorting task information: predefine and clarify the sorting task details: sorting personnel position, number of sorted packages, and sorting machine status; then establish a task process model for the sorting task, including the interaction between the sorting personnel and the sorting machine in the sorting process; connect the task information to the sorting machine digital twin model; The digital twin model of the sorting machine establishes an accurate three-dimensional model of the equipment based on the CAD model, kinematic and dynamic parameters of the actual equipment, and connects the physical equipment model with the real-time data update interface to achieve two-way mapping between the virtual environment and the physical equipment. The digital twin models and task information of the sorting machine and personnel need to have interfaces for synchronous data communication. The digital twin model of the sorting machine is used to accurately evaluate the current sorting task information, and by accessing the biological status data of the digital twin of the sorting personnel, the sorting performance indicators, namely the package return rate, are obtained.

5. According to claim 1, a method for dynamic scheduling of personnel based on the biological characteristics of sorting personnel, characterized in that: The multi-objective function is designed based on the current sorting task, personnel health, sorting priority and fatigue control as the objectives, including: The design goals are as follows: (1) Work efficiency target, using sorting efficiency Characterization: Sorting efficiency It is defined as the number of parcels that can be sorted per minute, and the real-time fatigue and concentration of the sorting personnel. The current sorting status of the sorting machine is affected by the type of sorting task and the current operating status of the sorting machine equipment; The sorting efficiency is denoted as ,in , , is the weight coefficient, satisfying ; The real-time parcel return rate output by the digital twin model of the sorter combined with the biometric status data of the sorting personnel is equal to the number of super-circle pieces divided by the total number of pieces; (2) Personnel health goals, using health risk index Characterization: Health Risk Index ,in is the baseline value of healthy heart rate and body temperature. are the thresholds for healthy heart rate and body temperature, is the weight; (3) Task urgency goal, using task urgency Characterization: Task urgency ,in is the adjustment factor, is the remaining time between the current sorting task and the package departure time. The time for each package from entering the sorting system to being sorted and shipped; (4) Fatigue control target, using fatigue balance Characterization: Defining fatigue balance , where n is the total number of sorters in the current sorting shift, is the average fatigue level, is the weight; represents the fatigue degree of the i-th sorter; Combining work efficiency goals, personnel health goals, task urgency goals, and fatigue control goals, a function for constructing a multi-objective optimization model is constructed: in, are their respective weight coefficients.

6. The method for dynamic scheduling of personnel based on the biological characteristics of sorting personnel according to claim 1, characterized in that: In the process of realizing the comprehensive optimization of dynamic scheduling, dynamic adjustment is made through the hierarchical analysis method, including: A1. Construct a hierarchical model: The typesetting scheduling problem is divided into two layers: (1) The target layer achieves the optimal balance between scheduling efficiency and personnel health; (2) Criteria layer, including four core optimization objectives: , that is, the operating efficiency target, express; , that is, the health risk control target, express; , that is, the task urgency response target, express; , that is, the operating efficiency target, express; A2. Based on the above four defined optimization objectives, a pairwise comparison matrix is ​​performed. ,in Indicates the importance of criterion i relative to criterion j; in, / , i=1,2,3,4; j=1,2,3,4; where, Customize the settings based on experience. When i=j, ; A3. Assume that the dimension of the pairwise comparison matrix is ​​n. Since the value range of i and j is an integer from 1 to 4, n=4. The maximum eigenvalue of the comparison matrix is ​​obtained by the eigenvalue decomposition method. , used to measure the consistency of the comparison matrix; Calculate consistency index , calculate the consistency ratio , where RI is the consistency index. When dimension n=4, RI=0.

9. , then the judgment matrix is ​​considered to have good consistency and the weights are reliable and reasonable; on the contrary, if , it is considered that the judgment matrix has a large deviation and is revised , to improve consistency.

7. The method for dynamic scheduling of personnel based on the biological characteristics of sorting personnel according to claim 1, characterized in that: Based on the established multi-objective optimization model, the multi-objective evolutionary algorithm NSGA-II is applied to the multi-objective scheduling problem, and structural optimization and heuristic enhancement are performed for logistics scenarios, including: In order to ensure the spatial continuity and temporal controllability of task allocation, a two-dimensional matrix structure is used to encode chromosomes and represent the scheduling scheme: C ,in is the number of sorting areas, is the number of scheduling time periods, is the sorting personnel id of the i-th sorting area and the j-th scheduling time period; for Personnel gathering: each person cannot be assigned to multiple areas at the same time; Take each scheduling scheme as an individual, and all individuals constitute the population; In order to improve population diversity and avoid premature convergence, the following adaptive probability adjustment formula is designed: Crossover probability : Mutation probability : in, is the fitness of the current individual, using multi-objective weighted values, namely ; is the maximum and average fitness of the current population; a trace constant to prevent division by zero; are the upper and lower limits of the crossover probability, are the upper and lower limits of the mutation probability; The multi-objective evolutionary algorithm NSGA-II is applied to the multi-objective scheduling problem to solve and output the final scheduling measurement solution. C .

Images