Method, device, electronic device and storage medium for generating personnel dispatch information

Abstract

The present application provides a method, device, electronic device and computer-readable storage medium for generating personnel scheduling information. The method for generating personnel scheduling information includes: when new task data of a target type task is detected, obtaining information of current personnel in a target area, wherein the target area refers to an area where the target type task is performed; identifying action information of the current personnel; determining data of the first person who performs the target type task among the current personnel based on the action information; generating information of personnel to be scheduled based on the data of the first person and the new task data, wherein the information of the personnel to be scheduled is used to instruct the scheduling personnel to complete the new task corresponding to the new task data in the target area. In the present application, personnel allocation can be carried out in real time and accurately according to changes in the amount of tasks in the division of labor, thereby improving the overall work execution efficiency.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to a method, device, electronic device and computer-readable storage medium for generating personnel scheduling information. Background Art

[0002] With the refinement of the division of labor in the production process, there are more and more types of division of labor in a production process, which is accompanied by the problem of how to arrange the number of personnel for each division of labor (hereinafter referred to as personnel ratio).

[0003] In the traditional staffing method, the corresponding number of personnel are pre-assigned according to the amount of division of labor based on manual experience to improve the efficiency of the entire production process. For example, in a logistics transfer yard, a certain number of personnel will be pre-assigned to load and unload goods, and a certain number of personnel will be assigned to pull the unloaded goods to a specific area by trailer.

[0004] However, due to the lack of flexibility in the existing staffing allocation method, it is difficult to allocate staff in real time and accurately according to the changes in the amount of tasks in a certain division of labor; therefore, to a certain extent, it leads to the problem of low execution efficiency of the entire production process. Summary of the invention

[0005] The present application provides a method, device, electronic device and computer-readable storage medium for generating personnel scheduling information, aiming to solve the problem in the prior art that it is difficult to accurately and timely allocate personnel according to changes in the amount of tasks divided by labor, resulting in low work execution efficiency.

[0006] In a first aspect, the present application provides a method for generating personnel scheduling information, the method comprising:

[0007] When new task data of a target type task is detected, information of current personnel in a target area is obtained, wherein the target area refers to an area where the target type task is performed;

[0008] Identify action information of the current person;

[0009] Determine data of a first person among the current persons who performs a target type task according to the action information;

[0010] Information of personnel to be dispatched is generated according to the data of the first personnel and the new task data, wherein the information of personnel to be dispatched is used to instruct the dispatched personnel to complete the new task corresponding to the new task data in the target area.

[0011] In a possible implementation of the present application, generating information of the person to be scheduled according to the data of the first person and the new task data includes:

[0012] Generate data of a second person according to the data of the first person, wherein the second person refers to a person other than the first person;

[0013] Acquiring distance information between the second person and the target area;

[0014] The information of the personnel to be dispatched is generated according to the distance information and the new task data.

[0015] In a possible implementation of the present application, the generating of information of personnel to be dispatched according to the distance information and the new task data also includes:

[0016] Acquiring work efficiency data of the second person;

[0017] The step of generating information of personnel to be dispatched according to the distance information and the new task data includes:

[0018] Information of personnel to be dispatched is generated according to the work efficiency data, the distance information and the new task data.

[0019] In a possible implementation of the present application, the identifying the action information of the current person includes:

[0020] Acquire first wristband data of the current person in a first time period, wherein the first wristband data includes first nine-axis data and first quaternion data determined by the first nine-axis data;

[0021] The first bracelet data is input into a trained motion recognition model to call the trained motion recognition model to recognize the motion information of the current person according to the first bracelet data.

[0022] In a possible implementation of the present application, the inputting the first bracelet data into a trained motion recognition model to call the trained motion recognition model to identify the motion information of the current person according to the first bracelet data, further comprising:

[0023] Acquire second wristband data within a second time period, and action label data corresponding to the second wristband data, wherein the second wristband data includes second nine-axis data and second quaternion data determined by the second nine-axis data, and the action label data is used to indicate actual action information corresponding to the second wristband data;

[0024] According to the second bracelet data and the action label data, the model parameters of the preset action recognition model are updated to obtain a trained action recognition model.

[0025] In a possible implementation of the present application, updating the model parameters of the preset action recognition model according to the second bracelet data and the action label data to obtain the trained action recognition model includes:

[0026] Performing time series difference processing on the second bracelet data to obtain first time series difference data of the second bracelet data;

[0027] According to the first time series difference data, the second bracelet data and the action label data, the model parameters of the preset action recognition model are updated to obtain a trained action recognition model.

[0028] In a possible implementation of the present application, inputting the first bracelet data into a trained motion recognition model to call the trained motion recognition model to identify the motion information of the current person according to the first bracelet data includes:

[0029] Performing time series difference processing on the first bracelet data to obtain second time series difference data of the first bracelet data;

[0030] The second time series difference data and the first bracelet data are input into a trained motion recognition model to call the trained motion recognition model to identify the motion information of the current person according to the second time series difference data and the first bracelet data.

[0031] In a second aspect, the present application provides a device for generating personnel scheduling information, the device for generating personnel scheduling information comprising:

[0032] an acquisition unit, configured to acquire information of current personnel in a target area when new task data of a target type task is detected, wherein the target area refers to an area where the target type task is performed;

[0033] A motion recognition unit, used to recognize the motion information of the current person;

[0034] A determination unit, configured to determine data of a first person among the current persons who performs a target type task according to the action information;

[0035] A generating unit is used to generate information of personnel to be dispatched based on the data of the first personnel and the new task data, wherein the information of the personnel to be dispatched is used to instruct the dispatching personnel to complete the new task corresponding to the new task data in the target area.

[0036] In a possible implementation of the present application, the generating unit is further configured to:

[0037] Generate data of a second person according to the data of the first person, wherein the second person refers to a person other than the first person;

[0038] Acquiring distance information between the second person and the target area;

[0039] The information of the personnel to be dispatched is generated according to the distance information and the new task data.

[0040] In a possible implementation of the present application, before the step of generating information of the personnel to be dispatched according to the distance information and the new task data, the acquisition unit is further configured to:

[0041] Acquiring work efficiency data of the second person;

[0042] The generating unit is further specifically used for:

[0043] Information of personnel to be dispatched is generated according to the work efficiency data, the distance information and the new task data.

[0044] In a possible implementation of the present application, the action recognition unit is further configured to:

[0045] Acquire first wristband data of the current person in a first time period, wherein the first wristband data includes first nine-axis data and first quaternion data determined by the first nine-axis data;

[0046] The first bracelet data is input into a trained motion recognition model to call the trained motion recognition model to recognize the motion information of the current person according to the first bracelet data.

[0047] In a possible implementation of the present application, the device for generating the personnel scheduling information further includes a training unit, and the training unit is specifically used to:

[0048] Acquire second wristband data within a second time period, and action label data corresponding to the second wristband data, wherein the second wristband data includes second nine-axis data and second quaternion data determined by the second nine-axis data, and the action label data is used to indicate actual action information corresponding to the second wristband data;

[0049] According to the second bracelet data and the action label data, the model parameters of the preset action recognition model are updated to obtain a trained action recognition model.

[0050] In a possible implementation of the present application, the training unit is further configured to:

[0051] Performing time series difference processing on the second bracelet data to obtain first time series difference data of the second bracelet data;

[0052] According to the first time series difference data, the second bracelet data and the action label data, the model parameters of the preset action recognition model are updated to obtain a trained action recognition model.

[0053] In a possible implementation of the present application, the action recognition unit is further configured to:

[0054] Performing time series difference processing on the first bracelet data to obtain second time series difference data of the first bracelet data;

[0055] The second time series difference data and the first bracelet data are input into a trained motion recognition model to call the trained motion recognition model to identify the motion information of the current person according to the second time series difference data and the first bracelet data.

[0056] In a third aspect, the present application further provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program, and when the processor calls the computer program in the memory, the processor executes the steps in any one of the methods for generating personnel scheduling information provided in the present application.

[0057] In a fourth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is loaded by a processor to execute the steps in the method for generating personnel scheduling information.

[0058] When the new task data of the target type task is detected, the application obtains the information of the current personnel in the target area; identifies the action information of the current personnel; determines the data of the first personnel who is currently performing the same task as the target type task according to the action information of the current personnel; and generates the information of the personnel to be scheduled according to the data of the first personnel and the new task data of the target type task. On the one hand, since the action information of the current personnel in the target area can be identified and whether the current personnel are performing the same division of labor as the target type task can be analyzed, and then the information of the personnel to be scheduled can be generated, when the task volume of a certain division of labor changes, the personnel can be timely and accurately matched according to the change of the task volume of the division of labor, thereby improving the work execution efficiency of the new task corresponding to the new task data. On the other hand, since the personnel can be matched according to the change of the task volume of the division of labor in real time and accurately, it is avoided that when the task volume of a certain division of labor suddenly increases, the personnel equipped may not be able to complete the division of labor in a short time, affecting the execution of other divisions of labor, and then leading to the problem of low overall work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0060] Figure 1 This is a flow chart of a method for generating personnel scheduling information provided in an embodiment of the present application;

[0061] Figure 2 is a scene schematic diagram of a target area provided in an embodiment of the present application;

[0062] Figure 3 is a schematic diagram of an embodiment of step S20 provided in an embodiment of the present application;

[0063] Figure 4 is a schematic diagram of an embodiment of step S40 provided in an embodiment of the present application;

[0064] Figure 5 is another scene schematic diagram of the target area provided in the embodiment of the present application;

[0065] Figure 6 is a schematic diagram of a distribution scenario of a UWB position sensor provided in an embodiment of the present application;

[0066] Figure 7 It is a schematic diagram of the structure of an embodiment of a device for generating personnel scheduling information provided in an embodiment of the present application;

[0067] Figure 8 It is a schematic diagram of the structure of an embodiment of an electronic device provided in the embodiments of the present application. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0069] In the description of the embodiments of the present application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0070] In order to enable any person skilled in the art to implement and use the present application, the following description is provided. In the following description, details are listed for the purpose of explanation. It should be understood that those of ordinary skill in the art can recognize that the present application can also be implemented without using these specific details. In other examples, the known process will not be elaborated in detail to avoid unnecessary details that make the description of the present application embodiment obscure. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest range of principles and features disclosed in accordance with the embodiments of the present application.

[0071] The embodiment of the present application provides a method, device, electronic device and computer-readable storage medium for generating personnel scheduling information. The device for generating personnel scheduling information can be integrated in an electronic device, which can be a server or a terminal.

[0072] First of all, before introducing the embodiments of the present application, the relevant content about the application background of the embodiments of the present application is introduced.

[0073] In the traditional staffing method, the corresponding number of personnel are pre-assigned according to the amount of division of labor based on manual experience to improve the efficiency of the entire production process. For example, in a logistics transfer yard, a certain number of personnel will be pre-assigned to load and unload goods, and a certain number of personnel will be assigned to pull the unloaded goods to a specific area by trailer.

[0074] However, the existing staffing ratio lacks flexibility. In all production processes, each division of labor is closely interconnected. If the staffing ratio of a certain division of labor is unreasonable, it will affect the overall work efficiency of the entire production process.

[0075] For example, when the workload of a certain division of labor suddenly increases, the staff assigned to it may not be able to complete the division of labor in a short period of time, affecting the execution of other divisions of labor, resulting in low overall work efficiency. For another example, when the workload of a certain division of labor decreases, the staff assigned to it will appear redundant, and other divisions with larger workloads will have no staff available, resulting in low overall work efficiency.

[0076] Based on the above-mentioned defects in the existing related technologies, the embodiments of the present application provide a method for generating personnel scheduling information, which at least overcomes the defects in the existing related technologies to a certain extent.

[0077] The executor of the method for generating personnel scheduling information in the embodiment of the present application may be a personnel scheduling information generating device provided in the embodiment of the present application, or a server device, a physical host or a user equipment (UE) and other different types of electronic devices integrated with the personnel scheduling information generating device, wherein the personnel scheduling information generating device may be implemented in hardware or software, and the UE may specifically be a terminal device such as a smart phone, a tablet computer, a laptop computer, a PDA, a desktop computer or a personal digital assistant (PDA).

[0078] The electronic device can adopt a working mode of independent operation or a working mode of a device cluster. By applying the method for generating personnel scheduling information provided in the embodiment of the present application, personnel allocation can be carried out in real time and accurately according to changes in the amount of tasks divided into different tasks, thereby improving the overall work execution efficiency.

[0079] Next, we will begin to introduce the method for generating personnel scheduling information provided in an embodiment of the present application. In the embodiment of the present application, an electronic device is used as the execution subject. For the sake of simplicity and ease of description, the execution subject will be omitted in the subsequent method embodiments.

[0080] Reference Figure 1 , Figure 1 A flowchart of a method for generating personnel scheduling information provided in an embodiment of the present application. It should be noted that although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here. The method for generating personnel scheduling information includes steps S10 to S40, wherein:

[0081] S10. When new task data of a target type task is detected, information of current personnel in the target area is obtained.

[0082] The target area refers to the area where the target type task is performed. The target area is set according to the actual business scenario. For example, the area where goods are loaded and unloaded in the logistics transfer yard is set as the target area. Figure 2 As shown, Figure 2 It is a scene schematic diagram of the target area provided in an embodiment of the present application.

[0083] Among them, the new task data of the target type task refers to the data of the specific division of labor task. There are many types of division of labor for target type tasks, which can be set according to the division of labor in specific scenarios. For example, in a logistics transfer station, the target type task can be a cargo unloading task, a cargo loading task, or a cargo marking task.

[0084] In an embodiment of the present application, relevant staff will wear devices that can collect motion data, such as bracelets, and UWB (Ultra Wide Band, wireless carrier communication technology) position sensors will be reasonably arranged in the target area. After the staff wearing the bracelet enters the target area, a communication connection will be established with the UWB position sensor in the target area. Therefore, the staff in the target area can be detected by the UWB position sensor.

[0085] For example, in a logistics transfer yard, when there is a new cargo unloading task, the UWB position sensor in the target area can detect the staff currently in the target area, and the information of the current personnel in the target area can be obtained.

[0086] It is understandable that the UWB position sensor mentioned here and later can also be replaced by other types of position sensors, as long as the type of position sensor can establish a communication connection with the wristband worn by the staff to detect the staff in the target area and obtain the data of the wristband worn by the staff. For example, the staff in the target area can also be detected through positioning in WSN (wireless sensor network).

[0087] S20: Identify the action information of the current person.

[0088] Among them, the action information refers to the action of the current personnel. The action information required for identification can be set according to specific needs and is not limited here. For example, in a logistics transfer yard, the action information of personnel in the loading and unloading area may include "loading and unloading goods", "resting", etc. For another example, in a logistics transfer yard, the action information of personnel in the loading and unloading area may include "loading and unloading goods", "trailer pulling goods", "resting", etc.

[0089] Step S20 can be implemented by an AI deep learning network. For example, after obtaining the information of the current person in the target area, the wristband data of the current person can be obtained through the wristband worn by the staff, and the motion recognition can be implemented by the deep learning motion recognition model.

[0090] For details, please refer to Figure 3 , Figure 3 This is a schematic diagram of an embodiment of step S20 provided in an embodiment of the present application, and “identifying the action information of the current person” may further include the following steps S21 to S22, wherein:

[0091] S21. Obtain first bracelet data of the current person in a first time period.

[0092] Among them, the bracelet data includes nine-axis data and quaternion data. The nine-axis data includes the data returned by the three-axis gyroscope, the data returned by the three-axis accelerometer, and the data returned by the three-axis magnetometer. Quaternion data refers to the posture data at each moment restored based on the data returned by the three-axis gyroscope, the data returned by the three-axis accelerometer, and the data returned by the three-axis magnetometer.

[0093] The first bracelet data includes first nine-axis data and first quaternion data determined by the first nine-axis data.

[0094] The first nine-axis data refers to the data returned by the three-axis gyroscope, the data returned by the three-axis accelerometer, and the data returned by the three-axis magnetometer collected in the first time period.

[0095] The first quaternion data refers to the posture data at each moment restored based on the data returned by the three-axis gyroscope, the data returned by the three-axis accelerometer, and the data returned by the three-axis magnetometer collected in the first time period.

[0096] Among them, the Madgwick algorithm can be used to calculate the quaternion data at each moment based on the nine-axis data.

[0097] The essence of the Madgwick algorithm is to weight the attitude calculated by the gyroscope at time t Attitude calculated together with the accelerometer and magnetic field meter So as to obtain the final posture The weighted formula is as follows.

[0098]

[0099] α1+α2=1, 0≤α1≤1, 0≤α2≤1

[0100] Among them, α1 is the weighting coefficient of the attitude calculated by the gyroscope, α2 is the weighting coefficient of the attitude calculated by the accelerometer and the magnetic field meter, and the sampling time interval is Δt.

[0101] In some embodiments, the staff can wear the bracelet on one hand. In some embodiments, the staff can also wear the bracelet on both hands. In this case, the first bracelet data includes the nine-axis data collected by the bracelets worn on the left and right hands, and the quaternion data determined by the nine-axis data collected by the bracelets worn on the left and right hands.

[0102] In the embodiment of the present application, the wristband worn by the staff is a wristband with an IMU (Inertial measurement unit, a device for measuring the three-axis attitude angle and acceleration of an object). The IMU may include a three-axis gyroscope, a three-axis accelerometer, and a three-axis magnetometer.

[0103] For example, the bracelet worn by the staff can be an LPMS-B2 bracelet. LPMS-B2 is an innovative, high-performance miniature wireless transmission attitude sensor. It uses Bluetooth technology to easily communicate with devices such as PCs and smart phones, and is used in robot and human motion measurement. A host system can connect multiple LPMS-B2s at the same time, with a maximum transmission rate of up to 400Hz. LPMS-B2 can achieve fast and accurate azimuth measurement through three different data of high-speed positioning in three-dimensional directions measured by MEMS sensors (three-axis gyroscopes, three-axis accelerometers and three-axis magnetometers) under zero drift. In the embodiment of the present application, the bracelet worn by the staff has not been improved, and some existing bracelets are mainly used to collect motion data; therefore, the specific structure and function of the bracelet in the embodiment of the present application can refer to the specific structure and function of the existing bracelet, which will not be repeated here.

[0104] The first time period may be set according to a specific business scenario, for example, it may be a preset time period before a time point at which new task data is detected, or a preset time period after a time point at which new task data is detected.

[0105] Specifically, for example, if new task data is detected at 8:00, the wristband data of the staff in the target area between 7:55 and 8:00 is obtained through the LPMS-B2 wristband as the first wristband data of the current person in the first time period. For another example, if new task data is detected at 8:00, the wristband data of the staff in the target area between 8:00 and 8:05 is obtained through the LPMS-B2 wristband as the first wristband data of the current person in the first time period.

[0106] S22: inputting the first bracelet data into a trained motion recognition model to call the trained motion recognition model to identify the motion information of the current person according to the first bracelet data.

[0107] Specifically, the trained action recognition model can be a convolutional neural network (CNN).

[0108] For example, in some embodiments, the trained action recognition model is composed of a backbone network and a fully connected layer. The backbone network is composed of two 5*1 convolutional layers, a 2*1 maximum pooling layer, and two 5*1 convolutional layers. The backbone network then outputs the corresponding action category through the fully connected layer. A random dropout is added to each pooling layer and fully connected layer to prevent overfitting of the model.

[0109] Specifically, first, the collected first nine-axis data and the calculated first quaternion data are normalized and input into the trained motion recognition model.

[0110] Then, after the first bracelet data is input into the trained motion recognition model, the trained motion recognition model will use the first bracelet data as input and input into the backbone network.

[0111] Furthermore, the data input is batch size N (batch_size: 4), number of channels C (channel: 1), data length H (imu_data_length: 40), sliding window length W (sliding_windows_length: 100). After passing through two 5*1 convolutional layers, the input is transformed and converted into (N, W, H, C). The input conversion allows the model to learn quaternion data within a certain period of time, making the recognition results of action information more accurate.

[0112] Finally, the data obtained through the backbone network is passed through the fully connected layer, and after passing through the fully connected layer, the action category corresponding to the first bracelet data is output (for example, whether the current person is in a loading state or a resting state within a certain time period), that is, the action information of the current person is output.

[0113] From the above content, it can be seen that the motion information of the current person is identified by calling the trained motion recognition model. Since the trained motion recognition model combines the first nine-axis data and the first quaternion data determined by the first nine-axis data, the motion information of the current person is more accurate.

[0114] In some embodiments of the present application, step S22 can specifically: perform time difference processing on the first bracelet data to obtain second time difference data of the first bracelet data; input the second time difference data and the first bracelet data into a trained motion recognition model to call the trained motion recognition model to identify the motion information of the current person according to the second time difference data and the first bracelet data.

[0115] For example, in some embodiments, the trained action recognition model consists of two branches, a backbone network branch and a sequential network branch, which then output the corresponding action category through a fully connected layer. A random dropout is added to each pooling layer and fully connected layer to prevent the model from overfitting.

[0116] The main network branch structure consists of two 5*1 convolutional layers, a 2*1 maximum pooling layer, and two 5*1 convolutional layers. The original first bracelet data is used as input.

[0117] The structure of the temporal network branch is the same as that of the main network branch, which is also composed of two 5*1 convolutional layers, one 2*1 maximum pooling layer, and two 5*1 convolutional layers. The difference is that in the temporal network branch, the original first bracelet data is processed by data difference to obtain the second temporal difference data as input; specifically, the data difference between time point T+1 and time T is used as the input of the temporal network branch.

[0118] Specifically, first, the collected first nine-axis data and the calculated first quaternion data are normalized and input into the trained motion recognition model.

[0119] Then, after the first bracelet data is input into the trained motion recognition model, the trained motion recognition model will use the original first bracelet data as input and input it into the backbone network branch. On the other hand, the first bracelet data at time point T+1 and the first bracelet data at time T are subjected to data difference processing, and the obtained second time series difference data is input into the time series network branch.

[0120] Finally, the data obtained through the backbone network branch and the timing network branch are passed through the fully connected layer. After passing through the fully connected layer, the action category corresponding to the first bracelet data is output (for example, whether the current person is in a loading state or a resting state within a certain time period), that is, the action information of the current person is output.

[0121] From the above content, it can be seen that by combining the original first bracelet data and the second time series difference data obtained after data difference processing on the first bracelet data for action recognition, the time series characteristics of the action can be extracted, thereby improving the accuracy of the action information.

[0122] In some embodiments of the present application, the action recognition model trained in step S22 is obtained through the following steps A1 to A2, wherein:

[0123] A1. Acquire second bracelet data within a second time period, and action tag data corresponding to the second bracelet data.

[0124] The second bracelet data includes second nine-axis data and second quaternion data determined by the second nine-axis data, and the action label data is used to indicate actual action information corresponding to the second bracelet data.

[0125] The second nine-axis data refers to the data returned by the three-axis gyroscope, the data returned by the three-axis accelerometer, and the data returned by the three-axis magnetometer collected in the second time period.

[0126] The second quaternion data refers to the posture data at each moment restored based on the data returned by the three-axis gyroscope, the data returned by the three-axis accelerometer, and the data returned by the three-axis magnetometer collected in the second time period. Similar to the above step S21, the second quaternion data at each moment can be calculated based on the second nine-axis data using the Madgwick algorithm.

[0127] The second time period can be set according to the specific action scene.

[0128] For example, in order to enable the trained motion recognition model to recognize motion information in a loading state and a resting state, the wristband data of the staff during the period of time in the loading state can be collected as the second wristband data, and the wristband data of the staff during the period of time in the loading state can be collected as the second wristband data.

[0129] A2. Update the model parameters of the preset action recognition model according to the second bracelet data and the action label data to obtain a trained action recognition model.

[0130] For example, corresponding to the trained motion recognition model, the preset motion recognition model is composed of a backbone network and a connection layer. The backbone network is composed of two 5*1 convolutional layers, a 2*1 maximum pooling layer, and two 5*1 convolutional layers. The feature data obtained after the second bracelet data passes through the backbone network is fitted through the fully connected layer.

[0131] Specifically, firstly, the Kaiming initialization method is used to initialize the model parameters.

[0132] Then, the collected second nine-axis data and the calculated second quaternion data are normalized and input into a preset motion recognition model.

[0133] After the second bracelet data is input into the preset motion recognition model, the preset motion recognition model will use the second bracelet data as input and input it into the backbone network. The feature data obtained after the second bracelet data passes through the backbone network will pass through the fully connected layer.

[0134] Finally, based on the fully connected layer, the actual action information corresponding to the action label data of the second bracelet data and the feature data obtained after the second bracelet data passes through the backbone network are fitted to determine the relationship between the bracelet data and the action information. That is, the model parameters of the preset action recognition model can be updated to obtain a trained action recognition model. At this point, the trained action recognition model can be used to identify the corresponding action information according to the bracelet data.

[0135] From the above content, it can be seen that by pre-collecting the second bracelet data corresponding to the action and training the preset action recognition model, the trained action recognition model can accurately remember the characteristics of the bracelet data corresponding to each action, so that the trained action recognition model can accurately and quickly fit and identify the action information of the current person according to the first bracelet data.

[0136] In some embodiments of the present application, step A2 may specifically include: performing time difference processing on the second bracelet data to obtain first time difference data of the second bracelet data; updating the model parameters of the preset action recognition model according to the first time difference data, the second bracelet data and the action label data to obtain a trained action recognition model.

[0137] For example, corresponding to the trained motion recognition model, the preset motion recognition model consists of two branches, the backbone network branch and the timing network branch. The second bracelet data passes through the backbone network branch and the timing network branch respectively, and then passes through the fully connected layer for fitting.

[0138] The main network branch structure consists of two 5*1 convolutional layers, a 2*1 maximum pooling layer, and two 5*1 convolutional layers. The original second bracelet data is used as input.

[0139] The structure of the temporal network branch is the same as that of the main network branch, which is also composed of two 5*1 convolutional layers, one 2*1 maximum pooling layer, and two 5*1 convolutional layers. The difference is that in the temporal network branch, the original second bracelet data is processed by data difference to obtain the first temporal difference data as input. Specifically, the first temporal difference data obtained by the data difference between time point T+1 and time T is used as the input of the temporal network branch.

[0140] Specifically, firstly, the Kaiming initialization method is used to initialize the model parameters.

[0141] Then, the collected second nine-axis data and the calculated second quaternion data are normalized and input into a preset motion recognition model.

[0142] After the second bracelet data is input into the preset motion recognition model, the preset motion recognition model, on the one hand, uses the original second bracelet data as input and inputs it into the backbone network branch. On the other hand, data difference processing is performed on the second bracelet data at time point T+1 and the second bracelet data at time T, and the obtained first time series difference data is input into the time series network branch.

[0143] Finally, the feature data obtained from the backbone network branch and the timing network branch are passed through the fully connected layer.

[0144] Based on the fully connected layer, fitting is performed according to the actual action information corresponding to the action label data of the second bracelet data, and the feature data obtained after the second bracelet data passes through the backbone network branch and the first time series difference data passes through the time series network branch to determine the relationship between the bracelet data, the time series difference data of the bracelet data and the action information. That is, the model parameters of the preset action recognition model can be updated to obtain a trained action recognition model. At this point, the trained action recognition model can be used to identify the corresponding action information according to the bracelet data.

[0145] From the above content, it can be seen that the preset action recognition model is trained through the relationship between the bracelet data, the time series difference data of the bracelet data and the action information, so that the trained action recognition model can accurately remember the comprehensive features such as the bracelet data and the time series difference data of the bracelet data corresponding to each action, so that the trained action recognition model can recognize more comprehensive action features, and then can accurately and quickly fit and identify the action information of the current person according to the first bracelet data.

[0146] S30. Determine data of the first person who performs a target type task among the current persons according to the action information.

[0147] The first person refers to a person among the current persons in the target area who is currently performing a task of the same type as the target task.

[0148] In some embodiments, first, the current person's currently executed task is determined based on the current person's action information. Then, it is detected whether the current person's currently executed task is the same as the target type task. If they are the same, the current person is taken as the first person, so that the data of the first person can be obtained.

[0149] For example, in a logistics transfer yard, if the new task data of the target type task is detected as data for loading and unloading goods, then the target type task is a loading and unloading task. Through step S20, the action recognition of the current personnel in the target area is performed to determine that the action information of personnel 1, personnel 2, personnel 3, personnel 4, and personnel 5 are "in loading and unloading state", "in resting state", "in resting state", "in loading and unloading state", and "in resting state", respectively. According to the action information determined in step S20, it can be determined that the current tasks performed by personnel 1 and personnel 4 are loading and unloading tasks, and personnel 1 and personnel 4 can be regarded as the first personnel.

[0150] S40: Generate information of personnel to be dispatched according to the data of the first personnel and the new task data.

[0151] The information of the personnel to be dispatched is used to instruct the dispatching personnel to complete the new task corresponding to the new task data in the target area.

[0152] Specifically, the amount of tasks to be performed is determined based on the detected new task data of the target type task. The number of personnel to be scheduled is determined based on the data of the first personnel and the amount of tasks to be performed. The information of the personnel to be scheduled is generated by combining the number of personnel to be scheduled and at least one of the information of the location, work efficiency, and priority of the currently executed tasks of the dispatchable personnel (such as personnel in a resting state, personnel whose priority of currently executing tasks is lower than that of the target type task).

[0153] From the above, it can be seen that when new task data of a target type task is detected, the information of the current personnel in the target area is obtained; the action information of the current personnel is identified; according to the action information of the current personnel, the data of the first personnel who is currently performing the same task as the target type task is determined; according to the data of the first personnel and the new task data of the target type task, the information of the personnel to be scheduled is generated. On the one hand, since the action information of the current personnel in the target area can be identified and whether the current personnel is performing the same division of labor as the target type task can be analyzed, and then the information of the personnel to be scheduled can be generated, when the task volume of a certain division of labor changes, the personnel can be allocated in a timely and accurate manner according to the change in the task volume of the division of labor, thereby improving the work execution efficiency of the new task corresponding to the new task data. On the other hand, since the personnel can be allocated in real time and accurately according to the change in the task volume of the division of labor, it is avoided that when the task volume of a certain division of labor suddenly increases, the personnel equipped may not be able to complete the division of labor in a short time, affecting the execution of other divisions of labor, and thus leading to the problem of low overall work efficiency.

[0154] In some embodiments of the present application, step S40 includes the following steps S41 to S43, please refer to Figure 4 , Figure 4 is a schematic diagram of an embodiment of step S40 provided in the embodiments of the present application.

[0155] S41. Determine data of a second person according to the data of the first person.

[0156] Among them, the second person refers to a person other than the first person, that is, a dispatchable person. Specifically, in some embodiments, the second person refers to a person other than the first person in the target area. In some embodiments, the second person refers to a person other than the first person in a preset range area including the target area. In some embodiments, the second person refers to a person other than the first person among the people recorded by the system.

[0157] Please refer to Figure 5 , Figure 5 It is another scene schematic diagram of the target area provided in the embodiment of the present application. Figure 3In the figure, the logistics transfer yard is represented, where area 1 represents the area for loading and unloading goods, and area 2 represents the area for sorting goods. If the new task data of the target type task is detected as data for sorting goods, area 2 can be used as the target area. If the new task data of the target type task is detected as data for loading and unloading goods, area 1 can be used as the target area.

[0158] The following combination Figure 5 , take the target type task as loading and unloading goods, and area 1 as the target area as an example.

[0159] For example, in some embodiments, the second person refers to a person other than the first person in the target area. The current persons in area 1 (i.e., the target area) are F, G, H, and I. Through motion recognition, it is determined that the current tasks performed by G and H are loading and unloading tasks (i.e., G and H are determined to be the first persons), and the data of the second person is determined to be F and I.

[0160] For another example, in some embodiments, the second person refers to a person other than the first person in the preset range area including the target area. The current persons in area 1 (i.e., the target area) are F, G, H, and I. Through motion recognition, it is determined that the current tasks performed by G and H are loading and unloading tasks (i.e., G and H are determined to be the first persons). If the preset range area including the target area refers to the entire transfer yard, the data of the second person is determined to be A, B, C, D, E, F, and I. If the preset range area including the target area refers to area 1 and area 2, the data of the second person is determined to be A, B, C, F, and I.

[0161] S42: Obtain distance information between the second person and the target area.

[0162] In some embodiments, UWB position sensors will be reasonably arranged within a preset area (such as a logistics transfer site) and a target area, and staff within the preset area will wear wristbands so that the UWB position sensor can establish a communication connection with the wristband to detect the staff's location information.

[0163] Specifically, the position information of the second person is detected by the UWB position sensor, and then the distance information between the second person and the target area is determined according to the position information of the target area and the position information of the second person.

[0164] For example, taking the target type task as loading and unloading cargo, the area where cargo is loaded and unloaded is taken as the target area.

[0165] Please refer to Figure 6 , Figure 6 It is a schematic diagram of the distribution scenario of the UWB position sensor provided in the embodiment of the present application. Figure 6In the figure, area 1 represents the area for loading and unloading goods (i.e., the target area), area 2 represents the goods sorting area, and area 3 represents other areas. UWB position sensor 1 can establish a communication connection with the wristband in area 1, thereby detecting the information of the staff in area 1; similarly, UWB position sensor 2 can detect the information of the staff in area 2, and UWB position sensor 3 can detect the information of the staff in area 3.

[0166] For example, if the UWB position sensor 2 detects that the second person is in area 2, the distance between area 1 and area 2 (such as the distance between the center point of area 1 and the center point of area 2) can be used as the distance between the second person and the target area, and the distance information between the second person and the target area can be obtained.

[0167] For another example, if the UWB position sensor 3 detects that the second person is in area 3, the distance between area 1 and area 3 (such as the distance between the center point of area 1 and the center point of area 3) can be used as the distance between the second person and the target area, and the distance information between the second person and the target area can be obtained.

[0168] S43. Generate information of personnel to be dispatched according to the distance information and the new task data.

[0169] Specifically, in some embodiments, first, the amount of tasks to be performed is determined based on the detected new task data of the target type task. And the number of personnel to be scheduled is determined based on the data of the first person and the amount of tasks to be performed. Then, based on the distance information between the second person and the target area, the data of the second person whose distance to the target area is closest is obtained from the data of the second person as the information of the personnel to be scheduled, until the number of personnel to be scheduled is met.

[0170] From the above content, it can be seen that by determining the data of the second person who can be dispatched based on the data of the first person, and obtaining the distance information between the second person and the target area, the data of the person who is relatively close to the target area can be obtained from the data of the second person who can be dispatched, as the information of the person to be dispatched. Since the person who is relatively close to the target area can be put into execution of the new task corresponding to the new task data relatively quickly, the work execution efficiency of the division of labor tasks can be improved, thereby improving the overall work efficiency.

[0171] In addition to scheduling personnel based on the distance between the personnel and the target area, personnel scheduling can also be further performed based on the personnel's work efficiency to further improve the work execution efficiency of the new task corresponding to the new task data. To this end, in some embodiments of the present application, "generating information about the personnel to be scheduled based on the distance information and the new task data" also includes: obtaining the work efficiency data of the second personnel. "Generating information about the personnel to be scheduled based on the distance information and the new task data" can further include: generating information about the personnel to be scheduled based on the work efficiency data, the distance information and the new task data.

[0172] Specifically, first, the amount of tasks to be performed is determined based on the detected new task data of the target type task. The number of personnel to be scheduled is determined based on the data of the first personnel and the amount of tasks to be performed. Then, the data of personnel with relatively high work efficiency and relatively close distance to the target area is obtained from the data of the second personnel until the number of personnel to be scheduled is met, which is used as the information of the personnel to be scheduled.

[0173] From the above content, it can be seen that by combining the work efficiency data of the second person and the distance information from the target area to generate the information of the person to be dispatched, the work execution efficiency of the new task corresponding to the new task data can be improved.

[0174] In order to better implement the method for generating personnel scheduling information in the embodiment of the present application, based on the method for generating personnel scheduling information, the embodiment of the present application also provides a device for generating personnel scheduling information, such as Figure 7 As shown, it is a schematic diagram of the structure of an embodiment of a device for generating personnel scheduling information in an embodiment of the present application. The device 700 for generating personnel scheduling information includes:

[0175] An acquisition unit 701 is used to acquire information of current personnel in a target area when new task data of a target type task is detected, wherein the target area refers to an area where the target type task is performed;

[0176] The action recognition unit 702 is used to recognize the action information of the current person;

[0177] A determination unit 703 is used to determine data of a first person who performs a target type task among the current persons according to the action information;

[0178] The generating unit 704 is used to generate information of personnel to be dispatched according to the data of the first personnel and the new task data, wherein the information of the personnel to be dispatched is used to instruct the dispatching personnel to complete the new task corresponding to the new task data in the target area.

[0179] In a possible implementation of the present application, the generating unit 704 is further configured to:

[0180] Generate data of a second person according to the data of the first person, wherein the second person refers to a person other than the first person;

[0181] Acquiring distance information between the second person and the target area;

[0182] The information of the personnel to be dispatched is generated according to the distance information and the new task data.

[0183] In a possible implementation of the present application, before the step of generating information of personnel to be dispatched according to the distance information and the new task data, the acquiring unit 701 is further specifically configured to:

[0184] Acquiring work efficiency data of the second person;

[0185] The generating unit 704 is further specifically configured to:

[0186] Information of personnel to be dispatched is generated according to the work efficiency data, the distance information and the new task data.

[0187] In a possible implementation of the present application, the action recognition unit 702 is further configured to:

[0188] Acquire first wristband data of the current person in a first time period, wherein the first wristband data includes first nine-axis data and first quaternion data determined by the first nine-axis data;

[0189] The first bracelet data is input into a trained motion recognition model to call the trained motion recognition model to recognize the motion information of the current person according to the first bracelet data.

[0190] In a possible implementation of the present application, the device for generating the personnel scheduling information further includes a training unit (not shown in the figure), and the training unit is specifically used to:

[0191] Acquire second wristband data within a second time period, and action label data corresponding to the second wristband data, wherein the second wristband data includes second nine-axis data and second quaternion data determined by the second nine-axis data, and the action label data is used to indicate actual action information corresponding to the second wristband data;

[0192] According to the second bracelet data and the action label data, the model parameters of the preset action recognition model are updated to obtain a trained action recognition model.

[0193] In a possible implementation of the present application, the training unit is further configured to:

[0194] Performing time series difference processing on the second bracelet data to obtain first time series difference data of the second bracelet data;

[0195] According to the first time series difference data, the second bracelet data and the action label data, the model parameters of the preset action recognition model are updated to obtain a trained action recognition model.

[0196] In a possible implementation of the present application, the action recognition unit 702 is further configured to:

[0197] Performing time series difference processing on the first bracelet data to obtain second time series difference data of the first bracelet data;

[0198] The second time series difference data and the first bracelet data are input into a trained motion recognition model to call the trained motion recognition model to identify the motion information of the current person according to the second time series difference data and the first bracelet data.

[0199] In specific implementation, the above units can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units can refer to the previous method embodiments, which will not be repeated here.

[0200] Since the personnel scheduling information generating device can execute the present application as follows Figures 1 to 6 Corresponding to the steps in the method for generating personnel scheduling information in any embodiment, therefore, the present application can be implemented as follows Figures 1 to 6 The beneficial effects that can be achieved by the method for generating personnel scheduling information in any embodiment are detailed in the previous description and will not be repeated here.

[0201] In addition, in order to better implement the method for generating personnel scheduling information in the embodiment of the present application, based on the method for generating personnel scheduling information, the embodiment of the present application also provides an electronic device, referring to Figure 8 , Figure 8 A schematic diagram of the structure of an electronic device according to an embodiment of the present application is shown. Specifically, the electronic device provided by the embodiment of the present application includes a processor 801, and the processor 801 is used to execute the computer program stored in the memory 802 to implement the following Figures 1 to 6 Corresponding to the steps of the method for generating personnel scheduling information in any embodiment; or, the processor 801 is used to execute the computer program stored in the memory 802 to implement the following Figure 7 The functions of each unit in the corresponding embodiment.

[0202] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 802, and executed by the processor 801 to complete the embodiment of the present application. One or more modules / units may be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.

[0203] The electronic device may include, but is not limited to, a processor 801 and a memory 802. Those skilled in the art will appreciate that the illustration is merely an example of an electronic device and does not constitute a limitation on the electronic device, and may include more or fewer components than those shown in the illustration, or may combine certain components, or different components, for example, the electronic device may also include input and output devices, network access devices, buses, etc., and the processor 801, memory 802, input and output devices, and network access devices, etc., are connected via a bus.

[0204] The processor 801 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0205] The memory 802 can be used to store computer programs and / or modules. The processor 801 implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 802 and calling the data stored in the memory 802. The memory 802 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the electronic device (such as audio data, video data, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0206] A person skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described personnel scheduling information generation device, electronic device and its corresponding unit can refer to the following. Figures 1 to 6 The description of the method for generating personnel scheduling information in any embodiment will not be repeated here in detail.

[0207] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0208] To this end, an embodiment of the present application provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the present application as follows: Figures 1 to 6 For the steps in the method for generating personnel scheduling information in any embodiment, the specific operations can be referred to as follows: Figures 1 to 6 The description of the method for generating personnel scheduling information in any embodiment will not be repeated here.

[0209] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0210] Due to the instructions stored in the computer-readable storage medium, the present application can be executed. Figures 1 to 6 Corresponding to the steps in the method for generating personnel scheduling information in any embodiment, therefore, the present application can be implemented as follows Figures 1 to 6The beneficial effects that can be achieved by the method for generating personnel scheduling information in any embodiment are detailed in the previous description and will not be repeated here.

[0211] The above is a detailed introduction to a method, device, electronic device and computer-readable storage medium for generating personnel scheduling information provided in an embodiment of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and scope of application. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for generating personnel scheduling information, characterized in that: The method comprises: When new task data of a target type task is detected, information of current personnel in a target area is obtained, wherein the new task data of the target type task includes data of specific division of labor tasks; the target area refers to an area where the target type task is performed; Using the trained motion recognition model to identify the motion information of the current person according to the wristband data of the current person; wherein the wristband data includes nine-axis data and quaternion data determined by the nine-axis data; the trained motion recognition model is obtained by training a preset motion recognition model; Determine data of a first person among the current persons who performs a target type task according to the action information; Information of personnel to be dispatched is generated according to the data of the first personnel and the new task data, wherein the information of personnel to be dispatched is used to instruct the dispatched personnel to complete the new task corresponding to the new task data in the target area.

2. The method for generating personnel scheduling information according to claim 1, characterized in that: The step of generating information of the personnel to be dispatched according to the data of the first personnel and the new task data includes: Generate data of a second person according to the data of the first person, wherein the second person refers to a person other than the first person; Acquiring distance information between the second person and the target area; The information of the personnel to be dispatched is generated according to the distance information and the new task data.

3. The method for generating personnel scheduling information according to claim 2, characterized in that: The step of generating information of personnel to be dispatched according to the distance information and the new task data also includes: Acquiring work efficiency data of the second person; The step of generating information of personnel to be dispatched according to the distance information and the new task data includes: Information of personnel to be dispatched is generated according to the work efficiency data, the distance information and the new task data.

4. The method for generating personnel scheduling information according to claim 1, characterized in that: The step of using the trained action recognition model to identify the action information of the current person according to the wristband data of the current person includes: Acquire first wristband data of the current person in a first time period, wherein the current person wears a wristband for collecting nine-axis data, a position sensor is provided in the target area, and the position sensor is used to establish a communication connection with the wristband worn by the person in the target area, and the first wristband data includes first nine-axis data and first quaternion data determined by the first nine-axis data; The first bracelet data is input into a trained motion recognition model to call the trained motion recognition model to recognize the motion information of the current person according to the first bracelet data.

5. The method for generating personnel dispatch information according to claim 4, characterized in that: The step of inputting the first bracelet data into a trained motion recognition model to call the trained motion recognition model to recognize the motion information of the current person according to the first bracelet data further includes: Acquire second wristband data within a second time period, and action label data corresponding to the second wristband data, wherein the second wristband data includes second nine-axis data and second quaternion data determined by the second nine-axis data, and the action label data is used to indicate actual action information corresponding to the second wristband data; According to the second bracelet data and the action label data, the model parameters of the preset action recognition model are updated to obtain a trained action recognition model.

6. The method for generating personnel scheduling information according to claim 5, characterized in that: The method of updating the model parameters of the preset action recognition model according to the second bracelet data and the action label data to obtain a trained action recognition model includes: Performing time series difference processing on the second bracelet data to obtain first time series difference data of the second bracelet data; According to the first time series difference data, the second bracelet data and the action label data, the model parameters of the preset action recognition model are updated to obtain a trained action recognition model.

7. The method for generating personnel dispatch information according to claim 6, characterized in that: The step of inputting the first bracelet data into a trained motion recognition model to call the trained motion recognition model to recognize the motion information of the current person according to the first bracelet data includes: Performing time series difference processing on the first bracelet data to obtain second time series difference data of the first bracelet data; The second time series difference data and the first bracelet data are input into a trained motion recognition model to call the trained motion recognition model to identify the motion information of the current person according to the second time series difference data and the first bracelet data.

8. A device for generating personnel scheduling information, characterized in that: The personnel dispatch information generating device comprises: an acquisition unit, configured to acquire information of current personnel in a target area when new task data of a target type task is detected, wherein the new task data of the target type task includes data of specific division of labor tasks; and the target area refers to an area where the target type task is performed; An action recognition unit, used to recognize the action information of the current person according to the wristband data of the current person using a trained action recognition model; A determination unit, configured to determine data of a first person among the current persons who performs a target type task according to the action information; wherein the wristband data includes nine-axis data and quaternion data determined by the nine-axis data; and the trained action recognition model is obtained by training a preset action recognition model; A generating unit is used to generate information of personnel to be dispatched based on the data of the first personnel and the new task data, wherein the information of the personnel to be dispatched is used to instruct the dispatching personnel to complete the new task corresponding to the new task data in the target area.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the method for generating personnel scheduling information according to any one of claims 1 to 7 is executed.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in the method for generating personnel scheduling information as described in any one of claims 1 to 7.

Images