In-warehouse productivity processing method and system, electronic equipment and storage medium

Abstract

The invention provides an in-warehouse productivity processing method and system, an electronic device and a storage medium, and the method comprises the steps: obtaining a current order quantity of a day in real time, and carrying out the preprocessing of the current order quantity, and obtaining a target current order quantity; constructing model features by using the target current order quantity, and inputting the model features into the productivity prediction model, so that the productivity prediction model predicts a productivity curve of the day by using the model features; wherein the productivity prediction model is obtained by training a to-be-trained productivity prediction model by using a historical order quantity; and according to the preset capacity and the capacity of each working hour on the capacity curve, planning the number of workers in each working hour. According to the invention, the employees in each working hour can be reasonably planned, so that the problems that the distribution operation cannot be completed and the distribution operation cannot be carried out on time due to the fact that the number of arranged employees is too small, or the employment cost is increased due to the fact that the number of arranged employees is too large, and the productivity is wasted due to the fact that the productivity is too low in the working hours are solved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and more specifically, to a warehouse productivity processing method, system, electronic equipment and storage medium. Background Art

[0002] With the development of the e-commerce market, e-commerce merchants need to arrange a certain number of distribution operators every day to perform corresponding distribution operations on site based on the orders received. The number of distribution operators arranged every day is generally determined by the warehouse manager based on historical operation conditions and past experience.

[0003] However, manually determining the number of sowing operators based on historical operation conditions and past experience cannot guarantee a reasonable arrangement of productivity. Too few sowing operators (workers) may be arranged, resulting in failure to complete the sowing operation and failure to deliver on time. Too many sowing operators (workers) may be arranged, which will increase labor costs and lead to too low working hour capacity, wasting productivity. Summary of the invention

[0004] In view of this, the present invention provides a method, system, electronic device and storage medium for processing productivity within a warehouse, so as to realize reasonable planning of the workers for each working hour, so as to avoid the situation where too few workers are arranged, resulting in the inability to complete the sowing operation and fail to deliver on time, or too many workers are arranged, resulting in increased labor costs, too low working hour capacity, and waste of productivity.

[0005] A first aspect of the present invention provides a method for processing productivity in a warehouse, the method comprising:

[0006] Acquire the current order volume of the day in real time, and pre-process the current order volume to obtain the target current order volume;

[0007] constructing a model feature using the target current order volume, and inputting the model feature into a capacity prediction model, so that the capacity prediction model predicts the capacity curve of the day using the model feature; wherein the capacity curve includes the capacity of each working hour in the day; and the capacity prediction model is obtained by training the capacity prediction model to be trained using the historical order volume;

[0008] The number of employees for each working hour is planned according to the preset capacity and the capacity of each working hour on the capacity curve; wherein the preset capacity is the capacity of one employee in one working hour.

[0009] Optionally, the method of training the capacity prediction model to be trained by using the historical order volume to obtain the capacity prediction model includes:

[0010] Get the historical order volume within a preset past time period;

[0011] Performing standardization and unification preprocessing on the historical order volume to obtain a standard historical order volume; wherein the standard historical order volume includes the standard historical order volume of each day in the preset past time period;

[0012] For the daily standard historical order volume in the preset past time period, construct features for the standard historical order volume using a polynomial regression function to obtain model training features;

[0013] The model training features are input into the capacity prediction model to be trained, so that the capacity prediction model to be trained uses the model training features to predict the predicted capacity curve of the corresponding date, and a corresponding loss function is constructed using the root mean square error function, the predicted capacity curve and the corresponding actual capacity curve, so as to use the loss function to adjust the parameters of the capacity prediction model to be trained until the capacity prediction model to be trained reaches convergence, thereby obtaining a capacity prediction model.

[0014] Optionally, before planning the number of employees for each working hour according to the preset capacity and the capacity of each working hour on the capacity curve, the method further includes:

[0015] Determine the highest peak working hours and the lowest peak working hours from the capacity curve; wherein the highest peak working hours are the working hours with the highest capacity, and the lowest peak working hours are the working hours with the lowest capacity;

[0016] Calculating a peak ratio based on the capacity of the highest peak working hour and the capacity of the lowest peak working hour;

[0017] If the peak ratio is greater than the preset peak ratio, the capacity of the peak working hour is subjected to peak shaving processing to remove the target capacity from the capacity of the peak working hour;

[0018] The removed target capacity is sequentially allocated to each target working hour until the peak ratio of the capacity of the highest peak working hour to the lowest peak working hour is not greater than the preset peak ratio, thereby obtaining a target capacity curve; wherein each target working hour includes the lowest peak working hour on the capacity curve, and the working hour that is after the lowest peak working hour and at the trough;

[0019] According to the preset capacity and the capacity of each working hour on the capacity curve, the number of employees for each working hour is planned, including:

[0020] The number of workers to be employed for each working hour is planned according to the preset capacity and the capacity for each working hour on the target capacity curve.

[0021] Optionally, the method further includes:

[0022] After a preset time interval, the total capacity of the day is calculated according to the capacity of each working hour on the capacity curve;

[0023] Determine the reference capacity based on the total capacity, total working hours, total order quantity and target order quantity of the day; wherein the target order quantity is the order quantity within a preset time interval;

[0024] The reference capacity is used to correct the capacity of each working hour after the preset time interval on the capacity curve, and the preset capacity and the corrected capacity of each working hour are used to re-plan the corrected number of employees for each working hour; wherein the number of employees is the number of sowing operators in the sowing operation scenario.

[0025] Optionally, the method further includes:

[0026] After a preset time interval has passed, obtaining the actual production capacity of each working hour within the preset time interval;

[0027] Determine the average labor efficiency for each working hour in the preset time interval according to the actual production capacity and the number of employees for each working hour in the preset time interval;

[0028] The average labor efficiency is used to adjust the number of workers employed in each working hour after the preset time interval on the capacity curve; wherein the number of workers employed is the number of sowing operators in the sowing operation scenario.

[0029] A second aspect of the present invention discloses a warehouse productivity processing system, the system comprising:

[0030] A current order volume acquisition unit is used to acquire the current order volume of the day in real time and pre-process the current order volume to obtain a target current order volume;

[0031] A capacity curve prediction unit is used to construct a model feature using the target current order volume, and input the model feature into a capacity prediction model, so that the capacity prediction model predicts the capacity curve of the day using the model feature; wherein the capacity curve includes the capacity of each working hour in the day; and the capacity prediction model is obtained by training the capacity prediction model to be trained by the training unit using the historical order volume;

[0032] The employee headcount planning unit is used to plan the employee headcount for each working hour according to a preset capacity and the capacity of each working hour on the capacity curve; wherein the preset capacity is the capacity of one employee in one working hour.

[0033] Optionally, the training unit includes:

[0034] A historical order volume acquisition unit, used to acquire the historical order volume within a preset past time period;

[0035] A preprocessing unit, configured to perform standardization and unification preprocessing on the historical order volume to obtain a standard historical order volume; wherein the standard historical order volume includes the standard historical order volume of each day in the preset past time period;

[0036] A feature construction unit, configured to construct features of the standard historical order volume for each day in the preset past time period using a polynomial regression function to obtain model training features;

[0037] The training subunit is used to input the model training features into the capacity prediction model to be trained, so that the capacity prediction model to be trained uses the model training features to predict the predicted capacity curve of the corresponding date, and uses the root mean square error function, the predicted capacity curve and the corresponding actual capacity curve to construct a corresponding loss function, so as to use the loss function to adjust the parameters of the capacity prediction model to be trained until the capacity prediction model to be trained reaches convergence, thereby obtaining the capacity prediction model.

[0038] Optionally, before executing the employment number planning unit, the system further includes:

[0039] A determination unit, configured to determine a peak working hour and a minimum peak working hour from the capacity curve; wherein the peak working hour is the working hour with the highest capacity, and the minimum peak working hour is the working hour with the lowest capacity;

[0040] A peak ratio calculation unit, used for calculating the peak ratio according to the capacity of the highest peak working hour and the capacity of the lowest peak working hour;

[0041] a peak shaving processing unit, configured to perform peak shaving processing on the capacity of the highest peak working hour if the peak ratio is greater than a preset peak ratio, so as to remove a target capacity from the capacity of the highest peak working hour;

[0042] an allocating unit, configured to allocate the removed target capacity to each target working hour in sequence, until the peak ratio of the capacity of the highest peak working hour to the lowest peak working hour is not greater than the preset peak ratio, so as to obtain a target capacity curve; wherein each target working hour includes the lowest peak working hour on the capacity curve, and a working hour that is after the lowest peak working hour and at a trough;

[0043] The employee headcount planning unit is further used to plan the employee headcount for each working hour according to the preset capacity and the capacity for each working hour on the target capacity curve.

[0044] The third aspect of the present invention discloses an electronic device, comprising: a processor and a memory, wherein the processor and the memory are connected via a communication bus; wherein the processor is used to call and execute a program stored in the memory; and the memory is used to store a program, wherein the program is used to implement the in-warehouse productivity processing method disclosed in the first aspect of the present invention.

[0045] A fourth aspect of the present invention discloses a computer-readable storage medium, in which computer-executable instructions are stored. The computer-executable instructions are used to execute the warehouse productivity processing method disclosed in the first aspect of the present invention.

[0046] The present invention provides a method, system, electronic device and storage medium for processing productivity in a warehouse. The current order volume of the day can be obtained in real time, and the current order volume is preprocessed to obtain the target current order volume; and the target current order volume is used to construct a model feature, and the model feature is input into a capacity prediction model, so that the capacity prediction model uses the model feature to predict the capacity curve of the day; wherein the capacity curve includes the capacity of each working hour in the day; the capacity prediction model is obtained by training the capacity prediction model to be trained using the historical order volume; according to the preset capacity and the capacity of each working hour on the capacity curve, the number of employees for each working hour is planned; wherein the preset capacity is the capacity of one employee in one working hour. The technical solution provided by the present invention can predict the capacity of each working hour of the day according to the model features constructed using the current order volume by a pre-trained capacity prediction model, so as to reasonably plan the number of employees for each working hour according to the preset capacity and the capacity of each working hour on the capacity curve, thereby avoiding the problem that too few employees are arranged through manual planning, which will lead to the inability to complete the seeding operation and the inability to deliver on time, or too many employees are arranged, which will lead to an increase in labor costs, and also lead to too low working hour capacity and waste of productivity. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0048] Figure 1 A schematic diagram of a process flow of a method for processing in-warehouse productivity provided by an embodiment of the present invention;

[0049] Figure 2 A schematic diagram of the structure of a warehouse productivity processing system provided by an embodiment of the present invention;

[0050] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0053] It should be noted that the concepts such as "first" and "second" mentioned in the disclosure of the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0054] It should be noted that the modifications of "one" and "plurality" mentioned in the disclosure of the present invention are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0055] It should be noted that the collection, collection, update, analysis, processing, use, transmission, storage and other aspects of the merchant's order information involved in the technical solution of this disclosure are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken for the merchant's order information to prevent illegal access to the merchant's order information and maintain the security of the merchant's order information, network security and national security.

[0056] See also Figure 1 , shows a flow chart of a method for processing in-warehouse productivity provided by an embodiment of the present invention, and the method for processing in-warehouse productivity specifically includes the following steps:

[0057] S101: Acquire the current order volume of the day in real time, and pre-process the current order volume to obtain the target current order volume.

[0058] In the specific process of executing step S101, the current picking quantity and the current cross-docking quantity of the day can be obtained in real time, and the sum of the current picking quantity and the current cross-docking quantity is used as the current order quantity; the current order quantity is standardized and unified preprocessed using the StandardScaler function to obtain the standard target current order quantity.

[0059] S102: Construct model features using the target current order quantity.

[0060] In the specific process of executing step S102, after preprocessing the acquired current order quantity to obtain the target current order quantity, the model features that meet the input of the capacity prediction model can be constructed according to the obtained target current order quantity by using the polynomial regression function PolynomialFeatures.

[0061] S103: Inputting the model features into the capacity prediction model, so that the capacity prediction model predicts the capacity curve of the day by using the model features; wherein the capacity prediction model is obtained by training the capacity prediction model to be trained by the training unit by using the historical order volume.

[0062] Among them, the capacity curve includes the capacity for each working hour of the day.

[0063] In an embodiment of the present application, the capacity prediction model to be trained may be trained in advance using historical order quantities to obtain a capacity prediction model.

[0064] The capacity prediction model to be trained can be a Ridge regression algorithm, and accordingly, the capacity prediction model obtained by pre-training the capacity prediction model to be trained using the historical order volume is an explicit regression model. The selection of the capacity prediction model to be trained can be made according to the actual application, and the embodiment of the present application is not limited thereto.

[0065] Optionally, the capacity prediction model to be trained is trained using historical order volumes, and the process of obtaining the capacity prediction model can be specifically as follows: obtaining the historical order volumes within a preset past time period; using the StandardScaler function to standardize and unify the historical order volumes to obtain the standard historical order volumes; wherein the standard historical order volumes include the standard historical order volumes for each day within the preset past time period; using a polynomial regression function to construct features for the standard historical order volumes for each day within the preset past time period, and obtaining the model training features for each day within the preset past time period.

[0066] For the daily model training features within a preset past time period, the model training features corresponding to the day are input into the capacity prediction model to be trained, so that the model training features of the capacity prediction model to be trained on that day predict the capacity of each working hour on that day, and obtain a predicted capacity curve composed of the capacity of each working hour on that day, and use the root mean square error function, the predicted capacity curve of that day and the corresponding actual capacity curve to construct a corresponding loss function, and finally use the constructed loss function to adjust the parameters of the capacity prediction model to be trained until the capacity prediction model to be trained converges to obtain the capacity prediction model.

[0067] The actual capacity curve includes the actual capacity for each working hour on the corresponding date.

[0068] It should be noted that the historical picking volume and the historical cross-docking volume in a preset past time period can be obtained, and the sum of the historical picking volume and the historical cross-docking volume can be used as the historical order volume in the preset past time period. The historical order volume includes the historical order volume of each day in the preset past time period.

[0069] It should also be noted that the preset past time period may be the past three months, the past six months, the past year, etc. It may be set according to actual needs, and the embodiment of the present application is not limited thereto.

[0070] In the specific process of executing step S103, after constructing the model features using the target current order volume, the constructed model features can be input into a pre-trained capacity prediction model, so that the capacity prediction model predicts the capacity of each working hour on the day according to the input model features, and obtains a capacity curve composed of the capacity of each working hour on the day.

[0071] S104: Planning the number of workers for each working hour based on the preset capacity and the capacity for each working hour on the capacity curve.

[0072] In the embodiment of the present application, a corresponding preset capacity can be preset, wherein the preset capacity is the capacity of one worker in one working hour.

[0073] Furthermore, in the embodiment of the present application, the labor efficiency training samples corresponding to different groups of people can be used to train the labor efficiency prediction model to be trained, so as to obtain the labor efficiency prediction model. In order to input the employment information corresponding to the current employment into the pre-trained labor efficiency prediction model, the labor efficiency prediction model uses the employment information to predict, obtain the labor efficiency corresponding to the current employment, and set the corresponding preset capacity according to the currently predicted labor efficiency. Among them, the future production trend can be seen from the predicted labor efficiency.

[0074] It should be noted that different groups include middle-aged and elderly people, young women, young men, etc.

[0075] In the embodiment of the present application, the labor efficiency prediction model can predict that the labor efficiency of the young male group is greater than that of the young female group, and the labor efficiency of the young female group is greater than that of the middle-aged and elderly group. Therefore, when setting the corresponding preset capacity, the preset capacity setting of the middle-aged and elderly group or the young female group should be lower than the capacity of the group composed entirely of young males. In this way, humanized labor efficiency configuration can be made for different groups of people, ensuring that different groups of people in the warehouse have a reasonable labor efficiency ratio.

[0076] In the specific process of executing step S104, after obtaining the capacity curve for the day, the number of employees for each working hour can be planned according to the preset capacity and the capacity for each working hour on the capacity curve.

[0077] For example, the preset capacity is 100 pieces, that is, the capacity of one worker in one working hour is 100; if the predicted capacity of a certain working hour is 650, it can be determined that the number of workers required for that working hour is 7.

[0078] Furthermore, in an embodiment of the present application, before planning the number of employees for each working hour based on the preset capacity and the capacity for each working hour on the capacity curve, the highest peak working hour and the lowest peak working hour can also be determined from the obtained capacity curve, and the corresponding peak ratio can be calculated based on the capacity corresponding to the determined highest peak working hour and the capacity corresponding to the lowest peak working hour.

[0079] It is determined whether the calculated peak ratio is greater than the preset peak ratio; if the peak ratio is not greater than the preset peak ratio, the number of employees for each working hour can be planned directly based on the preset capacity and the capacity for each working hour on the capacity curve.

[0080] If the peak ratio is greater than the preset peak ratio, the capacity of the highest peak working hour can be peak-cut to remove the target capacity from the capacity of the highest peak working hour; and the removed target capacity is allocated to each target working hour in turn until the peak ratio of the capacity of the highest peak working hour to the peak ratio of the lowest peak working hour is no greater than the preset peak ratio, thereby obtaining a target capacity curve; wherein each target working hour includes the lowest peak working hour on the capacity curve and the working hour at the trough after the lowest peak working hour.

[0081] It should be noted that after subtracting the target capacity from the capacity of the highest peak working hour, the subtracted target capacity can be allocated to each target working hour in turn in a recursive manner until the peak ratio of the capacity of the highest peak working hour to the peak ratio of the lowest peak working hour is no greater than the preset peak ratio, so that the capacity of each working hour tends to be stable.

[0082] In some embodiments, the preset peak ratio may be 1.3, and may be set according to actual applications, which is not limited in the embodiments of the present application.

[0083] Further, in the embodiment of the present application, after planning the number of workers per working hour according to the preset capacity and the capacity of each working hour on the capacity curve, the warehouse manager can arrange the corresponding number of workers according to the planned number of workers per working hour so as to complete the corresponding output within the corresponding working hour. However, in actual work, the capacity of each worker may change, resulting in a certain difference between the capacity completed within the corresponding working hour and the predicted capacity.

[0084] Therefore, after a preset time interval, the current order volume of the day can be re-acquired. Since a part of the production capacity, that is, a part of the orders, has been completed within the preset time interval, the current order volume currently acquired is different from the order volume previously acquired. Therefore, according to the current order volume currently acquired, steps S101 to S103 can be re-executed to obtain a new capacity curve for the day, so as to re-plan the number of employees for each working hour according to the preset capacity and the capacity of each working hour on the new capacity curve. In this way, the capacity of each working hour previously predicted can be corrected, so that the capacity of subsequent working hours and the planned number of employees can be more accurate.

[0085] It should be noted that the preset time interval can be one working hour, that is, after one working hour, the current order volume of the day can be re-acquired. The specific setting of the preset time interval can be set according to the actual application, and the embodiment of the present application is not limited thereto.

[0086] Furthermore, in the embodiment of the present application, the total capacity of the day can be calculated according to the capacity of each working hour on the capacity curve after a preset time interval; and the reference capacity can be determined according to the total capacity, total working hours, total order quantity and target order quantity of the day; and finally, the capacity of each working hour after the preset time interval on the capacity curve can be corrected by using the reference capacity, so as to re-plan the number of employees for each working hour after the preset time interval by using the preset capacity and the corrected capacity of each working hour. The target order quantity is the order quantity within the preset time interval.

[0087] It should be noted that by referring to the production capacity, it can be seen whether there is insufficient productivity in each working hour after the preset time interval; if so, corresponding adjustments can be made to avoid the situation where too few workers will lead to the inability to complete the sowing operation and delivery on time, or too many workers will lead to increased labor costs, too low working hour capacity, and waste of productivity.

[0088] It should also be noted that the number of employees refers to the number of sowing operators in the sowing operation scenario.

[0089] In some embodiments, the total capacity can be divided by the total working hours to obtain a first initial reference capacity, the total order quantity can be subtracted from the target order quantity to obtain the remaining order quantity, and the remaining order quantity can be divided by the remaining working hours to obtain the second initial reference capacity; the smaller value between the first initial reference capacity and the second initial reference capacity is taken as the reference capacity.

[0090] Furthermore, in an embodiment of the present application, after a preset time interval has passed, the actual production capacity for each working hour within the preset time interval can be obtained; based on the actual production capacity and the number of employees for each working hour within the preset time interval, the average labor efficiency for each working hour within the preset time interval can be determined; finally, the average labor efficiency can be used to adjust the number of employees for each working hour after the preset time interval on the production capacity curve.

[0091] The average labor efficiency can be the average productivity of each employee in a working hour. The actual productivity corresponding to a working hour can be divided by the corresponding number of employees to obtain the average labor efficiency per worker in that working hour.

[0092] It should also be noted that the number of employees refers to the number of sowing operators in the sowing operation scenario.

[0093] Specifically, the average labor efficiency can be compared with the preset capacity. If the average labor efficiency is greater than the preset capacity, it means that the current productivity is higher than the established level, that is, the subsequent working hours need to reduce a certain number of workers; if the average labor efficiency is less than the preset capacity, it means that the current productivity does not meet the standard, that is, the subsequent working hours need to increase a certain number of workers. Among them, the number of workers reduced = (actual capacity / preset capacity) - the actual number of workers, and the number of workers increased = the actual number of workers - (actual capacity / preset capacity).

[0094] In some embodiments, for each subsequent working hour, the predicted average labor efficiency for that working hour is calculated based on the productivity and the number of employees for that working hour. If the predicted average labor efficiency is less than the average labor efficiency, it means that the productivity of that working hour is low, and the corresponding number of employees can be increased based on the number of employees for that working hour; if the predicted average labor efficiency is greater than the average labor efficiency, it means that the productivity of that working hour is high, and the corresponding number of employees can be reduced based on the number of employees for that working hour.

[0095] For example, the preset time interval is one working hour, the actual production capacity of the working hour is 2000, and the number of employees for the working hour is 4. The average labor efficiency of the working hour is equal to 2000 divided by 4, which is 500. If the preset production capacity is 460, it can be determined that the average labor efficiency (500) is greater than the preset production capacity (460), indicating that the current productivity is higher than the established level, that is, the subsequent working hours need to reduce a certain number of employees, and then (2000 / 460)-actual number of employees (4) can be agreed to be 0.35, and it can be considered that one person needs to be reduced.

[0096] Furthermore, in an embodiment of the present application, after completing the production capacity for the day, the actual production capacity curve for the day can be obtained, and after calculating the peak ratio for the day based on the production capacity of the highest peak working hour and the production capacity of the lowest peak working hour in the actual production capacity curve for the day, the peak ratio for the day can be compared with the peak ratio for yesterday to analyze the problems existing on the day and yesterday. The larger the peak ratio, the more unstable the operating rhythm in the warehouse and the more balance is needed. The smaller the peak ratio, the more reasonable the operation in the warehouse and the stable production.

[0097] In an embodiment of the present application, a corresponding planned employment curve can also be generated based on the number of employees planned for each working hour of the day; a corresponding actual employment curve can be generated based on the actual number of employees for each working hour of the day; and a corresponding yesterday's employment curve can be generated based on the actual number of employees for each working hour of yesterday; by comparing the planned employment curve for the day, the actual employment curve and the yesterday's employment curve, it can be seen whether the actual work process is proceeding stably according to the predicted capacity curve. If there is a large difference, it is necessary to analyze it in combination with the actual working situation and make corresponding adjustments in a timely manner.

[0098] In actual application, the predicted average quantity can also be calculated based on the predicted total production capacity and the total working hours of the day; then, the corresponding example graphs can be generated and displayed based on the predicted average quantity of the day, the quantity of pieces to be broadcasted per working hour, the actual broadcast quantity per working hour of the day, and the predicted average broadcast quantity, so that relevant technical personnel can intuitively understand the corresponding situation through the displayed example graphs; among which, the quantity of pieces to be broadcasted per working hour is the production capacity corresponding to each working hour, the production capacity of the working hours before the current time is the actual production capacity, and the production capacity of the working hours after the current time is the dynamically corrected predicted production capacity; the actual broadcast quantity is the production capacity for each working hour of the day predicted for the first time.

[0099] The present invention provides a method for processing productivity in a warehouse, which can obtain the current order volume of the day in real time, and pre-process the current order volume to obtain the target current order volume; and construct model features using the target current order volume, and input the model features into the capacity prediction model, so that the capacity prediction model predicts the capacity curve of the day using the model features; wherein the capacity curve includes the capacity of each working hour on the day; the capacity prediction model is obtained by training the capacity prediction model to be trained using the historical order volume; according to the preset capacity and the capacity of each working hour on the capacity curve, the number of employees for each working hour is planned; wherein the preset capacity is the capacity of one employee in one working hour. The technical solution provided by the present invention can predict the capacity of each working hour of the day according to the model features constructed using the current order volume by the pre-trained capacity prediction model, so as to reasonably plan the number of employees for each working hour according to the preset capacity and the capacity of each working hour on the capacity curve, thereby avoiding the problem that too few employees are arranged through manual planning, which will lead to the inability to complete the seeding operation and fail to deliver on time, or too many employees are arranged, which will lead to increased labor costs, and will also lead to too low working hour capacity and waste of productivity.

[0100] Based on the in-warehouse productivity processing method disclosed in the embodiment of the present invention, the embodiment of the present invention also discloses a in-warehouse productivity processing system, such as Figure 2 As shown, the warehouse productivity processing system includes:

[0101] The current order quantity acquisition unit 21 is used to acquire the current order quantity of the day in real time and pre-process the current order quantity to obtain the target current order quantity;

[0102] The capacity curve prediction unit 22 is used to construct a model feature using the target current order volume, and input the model feature into the capacity prediction model, so that the capacity prediction model predicts the capacity curve of the day using the model feature; wherein the capacity curve includes the capacity of each working hour in the day; the capacity prediction model is obtained by the training unit using the historical order volume to train the capacity prediction model to be trained;

[0103] The employee number planning sheet 23 is used to plan the number of employees for each working hour according to the preset capacity and the capacity for each working hour on the capacity curve; wherein the preset capacity is the capacity of one employee in one working hour.

[0104] The specific principles and execution processes of each unit in the in-warehouse productivity processing system disclosed in the above embodiment of the present invention are the same as the in-warehouse productivity processing method disclosed in the above embodiment of the present invention. Please refer to the corresponding parts of the in-warehouse productivity processing method disclosed in the above embodiment of the present invention, and will not be repeated here.

[0105] The present invention provides a warehouse productivity processing system, which can obtain the current order volume of the day in real time, and pre-process the current order volume to obtain the target current order volume; and construct model features using the target current order volume, and input the model features into the capacity prediction model, so that the capacity prediction model uses the model features to predict the capacity curve of the day; wherein the capacity curve includes the capacity of each working hour in the day; the capacity prediction model is obtained by training the capacity prediction model to be trained using the historical order volume; according to the preset capacity and the capacity of each working hour on the capacity curve, the number of employees for each working hour is planned; wherein the preset capacity is the capacity of one employee in one working hour. The technical solution provided by the present invention can predict the capacity of each working hour of the day according to the model features constructed using the current order volume through the pre-trained capacity prediction model, so as to reasonably plan the number of employees for each working hour according to the preset capacity and the capacity of each working hour on the capacity curve, thereby avoiding the problem that too few employees are arranged through manual planning, which will lead to the inability to complete the seeding operation and the inability to deliver on time, or too many employees are arranged, which will lead to an increase in labor costs, and also lead to too low working hour capacity and waste of productivity.

[0106] Optional training modules include:

[0107] A historical order volume acquisition unit, used to acquire the historical order volume within a preset past time period;

[0108] A preprocessing unit is used to perform standardization and unification preprocessing on the historical order volume to obtain a standard historical order volume; wherein the standard historical order volume includes the standard historical order volume of each day in a preset past time period;

[0109] A feature construction unit is used to construct features of the standard historical order volume for each day in a preset past time period using a polynomial regression function to obtain model training features;

[0110] The training subunit is used to input the model training features into the capacity prediction model to be trained, so that the capacity prediction model to be trained can use the model training features to predict the predicted capacity curve of the corresponding date, and use the root mean square error function, the predicted capacity curve and the corresponding actual capacity curve to construct a corresponding loss function, so as to use the loss function to adjust the parameters of the capacity prediction model to be trained until the capacity prediction model to be trained reaches convergence, thereby obtaining the capacity prediction model.

[0111] Optionally, before executing the employment number planning unit, the warehouse productivity processing system provided by the embodiment of the present invention further includes:

[0112] A determination unit, used to determine the highest peak working hours and the lowest peak working hours from the capacity curve; wherein the highest peak working hours are the working hours with the highest capacity, and the lowest peak working hours are the working hours with the lowest capacity;

[0113] A peak ratio calculation unit, used for calculating the peak ratio according to the capacity of the highest peak working hour and the capacity of the lowest peak working hour;

[0114] A peak shaving processing unit, configured to perform peak shaving processing on the capacity of the peak working hour if the peak ratio is greater than a preset peak ratio, so as to remove the target capacity from the capacity of the peak working hour;

[0115] an allocation unit, configured to allocate the removed target capacity to each target working hour in sequence, until the peak ratio of the capacity of the highest peak working hour to the capacity of the lowest peak working hour is not greater than a preset peak ratio, thereby obtaining a target capacity curve; wherein each target working hour includes the lowest peak working hour on the capacity curve, and the working hour that is after the lowest peak working hour and at a trough;

[0116] The employee headcount planning unit is also used to plan the number of employees for each working hour based on the preset capacity and the capacity for each working hour on the target capacity curve.

[0117] Optionally, the warehouse productivity processing system provided by the embodiment of the present invention further includes:

[0118] A total capacity calculation unit, used for calculating the total capacity of the day according to the capacity of each working hour on the capacity curve after a preset time interval;

[0119] A reference capacity determination unit is used to determine the reference capacity according to the total capacity, total working hours, total order quantity and target order quantity of the day; wherein the target order quantity is the order quantity within a preset time interval;

[0120] The re-planning unit is used to correct the capacity of each working hour after a preset time interval on the capacity curve by using the reference capacity, and to re-plan the corrected number of employees for each working hour by using the preset capacity and the corrected capacity of each working hour; wherein the number of employees refers to the number of sowing operators in the sowing operation scenario.

[0121] Optionally, the warehouse productivity processing system provided by the embodiment of the present invention further includes:

[0122] An actual capacity acquisition unit, used for acquiring the actual capacity of each working hour within a preset time interval after a preset time interval has passed;

[0123] An average labor efficiency determination unit, used to determine the average labor efficiency of each working hour in a preset time interval according to the actual production capacity and the number of employees in each working hour in the preset time interval;

[0124] The adjustment unit is used to adjust the number of workers employed in each working hour after a preset time interval on the capacity curve by using the average labor efficiency; wherein the number of workers employed is the number of sowing operators in the sowing operation scenario.

[0125] The present application embodiment provides an electronic device, such as Figure 3 As shown, the electronic device includes a processor 301 and a memory 302, the memory 302 is used to store program codes and data for in-warehouse productivity processing, and the processor 301 is used to call the program instructions in the memory to execute the steps shown in the in-warehouse productivity processing method in the above embodiment.

[0126] An embodiment of the present application provides a storage medium, which includes a storage program, wherein when the program is running, the device where the storage medium is located is controlled to execute the warehouse productivity processing method shown in the above embodiment.

[0127] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, in which the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0128] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0129] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0130] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for processing productivity in a warehouse, characterized in that: The method comprises: Acquire the current order volume of the day in real time, and pre-process the current order volume to obtain the target current order volume; constructing a model feature using the target current order volume, and inputting the model feature into a capacity prediction model, so that the capacity prediction model predicts the capacity curve of the day using the model feature; wherein the capacity curve includes the capacity of each working hour in the day; and the capacity prediction model is obtained by training the capacity prediction model to be trained using the historical order volume; The number of employees for each working hour is planned according to the preset capacity and the capacity of each working hour on the capacity curve; wherein the preset capacity is the capacity of one employee in one working hour.

2. The method according to claim 1, characterized in that: The method of training the capacity prediction model to be trained by using the historical order volume to obtain the capacity prediction model includes: Get the historical order volume within a preset past time period; Performing standardization and unification preprocessing on the historical order volume to obtain a standard historical order volume; wherein the standard historical order volume includes the standard historical order volume of each day in the preset past time period; For the daily standard historical order volume in the preset past time period, a polynomial regression function is used to construct features of the standard historical order volume to obtain model training features; The model training features are input into the capacity prediction model to be trained, so that the capacity prediction model to be trained uses the model training features to predict the predicted capacity curve of the corresponding date, and a corresponding loss function is constructed using the root mean square error function, the predicted capacity curve and the corresponding actual capacity curve, so as to use the loss function to adjust the parameters of the capacity prediction model to be trained until the capacity prediction model to be trained reaches convergence, thereby obtaining a capacity prediction model.

3. The method according to claim 1, characterized in that Before planning the number of employees for each working hour according to the preset capacity and the capacity of each working hour on the capacity curve, the method further includes: Determine the highest peak working hours and the lowest peak working hours from the capacity curve; wherein the highest peak working hours are the working hours with the highest capacity, and the lowest peak working hours are the working hours with the lowest capacity; Calculating a peak ratio based on the capacity of the highest peak working hour and the capacity of the lowest peak working hour; If the peak ratio is greater than the preset peak ratio, the capacity of the peak working hour is subjected to peak shaving processing to remove the target capacity from the capacity of the peak working hour; The removed target capacity is sequentially allocated to each target working hour until the peak ratio of the capacity of the highest peak working hour to the lowest peak working hour is not greater than the preset peak ratio, thereby obtaining a target capacity curve; wherein each target working hour includes the lowest peak working hour on the capacity curve, and the working hour that is after the lowest peak working hour and at the trough; According to the preset capacity and the capacity of each working hour on the capacity curve, the number of employees for each working hour is planned, including: The number of workers to be employed for each working hour is planned according to the preset capacity and the capacity for each working hour on the target capacity curve.

4. The method according to claim 1, characterized in that The method further comprises: After a preset time interval, the total capacity of the day is calculated according to the capacity of each working hour on the capacity curve; Determine the reference capacity based on the total capacity, total working hours, total order quantity and target order quantity of the day; wherein the target order quantity is the order quantity within a preset time interval; The reference capacity is used to correct the capacity of each working hour after the preset time interval on the capacity curve, and the preset capacity and the corrected capacity of each working hour are used to re-plan the corrected number of employees for each working hour; wherein the number of employees is the number of sowing operators in the sowing operation scenario.

5. The method according to claim 1, characterized in that The method further comprises: After a preset time interval has passed, obtaining the actual production capacity of each working hour within the preset time interval; Determine the average labor efficiency for each working hour in the preset time interval according to the actual production capacity and the number of employees for each working hour in the preset time interval; The average labor efficiency is used to adjust the number of workers employed in each working hour after the preset time interval on the capacity curve; wherein the number of workers employed is the number of sowing operators in the sowing operation scenario.

6. A warehouse productivity processing system, characterized in that: The system comprises: A current order volume acquisition unit is used to acquire the current order volume of the day in real time and pre-process the current order volume to obtain a target current order volume; A capacity curve prediction unit is used to construct a model feature using the target current order volume, and input the model feature into a capacity prediction model, so that the capacity prediction model predicts the capacity curve of the day using the model feature; wherein the capacity curve includes the capacity of each working hour in the day; and the capacity prediction model is obtained by training the capacity prediction model to be trained by the training unit using the historical order volume; The employee headcount planning unit is used to plan the employee headcount for each working hour according to a preset capacity and the capacity of each working hour on the capacity curve; wherein the preset capacity is the capacity of one employee in one working hour.

7. The system according to claim 6, characterized in that The training unit comprises: A historical order volume acquisition unit, used to acquire the historical order volume within a preset past time period; A preprocessing unit, configured to perform standardization and unification preprocessing on the historical order volume to obtain a standard historical order volume; wherein the standard historical order volume includes the standard historical order volume of each day in the preset past time period; A feature construction unit, configured to construct features of the standard historical order volume for each day in the preset past time period using a polynomial regression function to obtain model training features; The training subunit is used to input the model training features into the capacity prediction model to be trained, so that the capacity prediction model to be trained uses the model training features to predict the predicted capacity curve of the corresponding date, and uses the root mean square error function, the predicted capacity curve and the corresponding actual capacity curve to construct a corresponding loss function, so as to use the loss function to adjust the parameters of the capacity prediction model to be trained until the capacity prediction model to be trained reaches convergence, thereby obtaining the capacity prediction model.

8. The system according to claim 6, characterized in that Before executing the employment number planning unit, the system further includes: A determination unit, configured to determine a peak working hour and a minimum peak working hour from the capacity curve; wherein the peak working hour is the working hour with the highest capacity, and the minimum peak working hour is the working hour with the lowest capacity; A peak ratio calculation unit, used for calculating the peak ratio according to the capacity of the highest peak working hour and the capacity of the lowest peak working hour; a peak shaving processing unit, configured to perform peak shaving processing on the capacity of the highest peak working hour if the peak ratio is greater than a preset peak ratio, so as to remove a target capacity from the capacity of the highest peak working hour; an allocating unit, configured to allocate the removed target capacity to each target working hour in sequence, until the peak ratio of the capacity of the highest peak working hour to the lowest peak working hour is not greater than the preset peak ratio, so as to obtain a target capacity curve; wherein each target working hour includes the lowest peak working hour on the capacity curve, and a working hour that is after the lowest peak working hour and at a trough; The employee headcount planning unit is further used to plan the employee headcount for each working hour according to the preset capacity and the capacity for each working hour on the target capacity curve.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the processor and the memory are connected via a communication bus; wherein the processor is used to call and execute a program stored in the memory; The memory is used to store a program, and the program is used to implement the warehouse productivity processing method as described in any one of claims 1-5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to execute the warehouse productivity processing method as described in any one of claims 1-5.

Images