Picking rechecking task management method, device and equipment, medium and product

Abstract

The embodiment of the invention discloses a picking rechecking task management method and device, equipment and a medium, and the method comprises the steps: obtaining picking task information and picker information corresponding to a picking task in an ongoing state, and the working state information of a rechecking table; performing information prediction according to the acquired information to obtain a residual picking time length, an average transportation time consumption of transporting the goods to each rechecking station, a first estimated time consumption of processing an uncompleted picking rechecking task by each rechecking station and a second estimated time consumption of completing a to-be-allocated picking rechecking task corresponding to the picking task by each rechecking station; and determining a target review station corresponding to each to-be-allocated order picking review task according to the predicted information by taking the shortest review completion estimation time of all the to-be-allocated order picking review tasks as a target task scheduling result so as to perform task scheduling management. According to the technical scheme of the embodiment of the invention, manual scheduling of the picking rechecking task can be replaced, the task scheduling cost is reduced, and the task scheduling efficiency and effect are improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of logistics management, and in particular to a picking review task management method, device, equipment, medium and product. Background Art

[0002] Before the goods are shipped out of the warehouse, the picking results need to be reviewed. The picking cart that has completed a picking task is parked at a location by the picker, and then the special picking task dispatcher dispatches the picking cart to a review table, and finally the picking reviewer reviews the goods in the picking cart for shipment.

[0003] However, in the process of implementing the present invention, it is found that there are at least the following technical problems in the prior art:

[0004] When the picking task dispatcher dispatches the picking review tasks corresponding to each picking cart, the factors considered are not comprehensive, and the overall capacity balance and efficiency of the picking review tasks cannot be taken into account. Moreover, the labor cost is high, and the negative impact of human factors in the dispatching process of picking review tasks cannot be avoided. Summary of the invention

[0005] The embodiments of the present invention provide a picking and review task management method, device, equipment, medium and product, which can replace manual scheduling of picking and review tasks, reduce task scheduling costs, quickly analyze multi-dimensional information to determine the scheduling plan for picking and review tasks, and improve task scheduling efficiency and effectiveness.

[0006] In a first aspect, an embodiment of the present invention provides a picking review task management method, the method comprising:

[0007] Obtain the picking task information and picker information corresponding to the picking task in the task-in-progress state, and obtain the working status information of each review station;

[0008] Information prediction is performed based on the picking task information, the picker information and the work status information to obtain the remaining picking time of the picking task, the average transportation time for transporting the goods corresponding to the picking task to each of the review stations, the first estimated time for each of the review stations to process unfinished picking review tasks and the second estimated time for each of the review stations to complete the to-be-assigned picking review tasks corresponding to the picking task;

[0009] The shortest estimated time for completing the review of all the picking review tasks to be assigned is taken as the target task scheduling result. According to the remaining picking time, the average transportation time, the first estimated time and the second estimated time, the target review station corresponding to each of the picking review tasks to be assigned is determined to complete the task scheduling management of the picking review tasks.

[0010] In a second aspect, an embodiment of the present invention provides a picking review task management device, the device comprising:

[0011] The task information acquisition module is used to obtain the picking task information and picker information corresponding to the picking task in the task-in-progress state, and obtain the working status information of each review station;

[0012] A task processing time prediction module is used to perform information prediction based on the picking task information, the picker information and the work status information to obtain the remaining picking time of the picking task, the average transportation time for transporting the goods corresponding to the picking task to each of the review stations, the first estimated time for each of the review stations to process unfinished picking and review tasks, and the second estimated time for each of the review stations to complete the picking and review tasks to be assigned corresponding to the picking tasks;

[0013] The task scheduling processing module is used to take the shortest estimated time for completing the review of all the picking review tasks to be assigned as the target task scheduling result, and determine the target review station corresponding to each of the picking review tasks to be assigned according to the remaining picking time, the average transportation time, the first estimated time and the second estimated time, so as to complete the task scheduling management of the picking review tasks.

[0014] In a third aspect, an embodiment of the present invention further provides a computer device, the computer device comprising:

[0015] one or more processors;

[0016] A memory for storing one or more programs;

[0017] When one or more programs are executed by one or more processors, the one or more processors implement the picking review task management method provided by any embodiment of the present invention.

[0018] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a picking review task management method as provided in any embodiment of the present invention.

[0019] In a fifth aspect, the embodiments of the present disclosure further provide a computer program product, including a computer program, which, when executed by a processor, implements the picking review task management method provided in any embodiment of the present invention.

[0020] The embodiments of the above invention have the following advantages or beneficial effects:

[0021] According to an embodiment of the present invention, picking task information and picker information corresponding to picking tasks in a task-in-progress state are obtained, and work status information of each review station is obtained; information prediction is performed based on the picking task information, picker information and work status information to obtain the remaining picking time of the picking task, the average transportation time for transporting the goods corresponding to the picking task to each review station, the first estimated time for each review station to handle unfinished picking review tasks, and the second estimated time for each review station to complete the to-be-assigned picking review tasks corresponding to the picking tasks; the shortest estimated time for completing the review of all to-be-assigned picking review tasks is taken as the target task scheduling result, and the target review station corresponding to each to-be-assigned picking review task is determined based on the remaining picking time, the average transportation time, the first estimated time and the second estimated time, so as to complete the task scheduling management of the picking review tasks. The technical solution of the embodiment of the present invention solves the problems of low efficiency in manual scheduling of picking and review tasks and low task scheduling benefits caused by incomplete information analysis. It can replace manual scheduling of picking and review tasks, reduce task scheduling costs, quickly analyze multi-dimensional information to determine the scheduling plan for picking and review tasks, and improve task scheduling efficiency and effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of a picking review task management method provided by an embodiment of the present invention;

[0023] Figure 2 It is a schematic diagram of a process for implementing the scheduling management of picking review tasks in the prior art provided by an embodiment of the present invention;

[0024] Figure 3 This is a comparison diagram of a picking review task management process provided by an embodiment of the present invention;

[0025] Figure 4 It is a flow chart of a picking review task management method provided by an embodiment of the present invention;

[0026] Figure 5 This is a schematic diagram of a picking review task management process provided by an embodiment of the present invention;

[0027] Figure 6 This is a flowchart of a picking review task management method provided by an embodiment of the present invention;

[0028] Figure 7 This is a schematic diagram of the effect of an application example of a picking review task management method provided by an embodiment of the present invention;

[0029] Figure 8 It is a structural schematic diagram of a picking review task management device provided by an embodiment of the present invention;

[0030] Fig. 9It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0032] Figure 1 This is a flowchart of a picking review task management method provided by an embodiment of the present invention. This embodiment can be applied to the outbound management scenario of goods transported by logistics when they are outbound, especially the situation of picking review for goods after picking is completed. The method can be executed by a picking review task management device, which can be implemented by software and / or hardware and integrated into a computer device with application development functions, such as a warehouse management system (Warehouse Management System, WMS).

[0033] The current warehouse outbound process mainly includes the warehouse receiving order transmission, order positioning, order assembly into picking task list, picking, review, packaging and outbound delivery, etc. Figure 2 As shown in the figure. Among them, the picking review process occurs after multiple pickers have picked the picking tasks corresponding to the waiting picking task orders they have received, and the picking carts loaded with goods are pushed to the exit of the picking storage area. The dispatcher in the warehouse pushes them to the relatively appropriate review station according to the busyness of each review station. Then the review station will combine the goods in the picking cart according to the order dimension and send them to the packaging and labeling behind for delivery.

[0034] In this process, after picking up the task order, the picker may park the picking cart randomly. During peak hours, many picking carts will be piled up and the scene will be particularly chaotic. Special dispatchers in the warehouse are required to manually push them to the review table, which increases labor costs and reduces production efficiency. Moreover, the dispatcher's push to the review table depends entirely on the current busyness of the review table, ignoring the different review efficiencies of different review tables and the different distances of the carts. It is impossible to quickly analyze multi-dimensional information to achieve global capacity balance and efficiency assurance. In the current outbound process, it is also impossible to avoid the fraud of dispatchers and reviewers in the warehouse, resulting in extremely unbalanced workload and accrual in the review link, which in turn leads to the loss of reviewers in disguise. It is unclear to hold pickers accountable for picking carts that are abnormal, and it is impossible to effectively restrain pickers.

[0035] In order to improve the current warehouse outbound work conditions, the technical solution of this embodiment is proposed to improve the workflow of the warehouse outbound work and improve the efficiency of goods outbound.

[0036] like Figure 1 As shown, the picking review task management method of this embodiment includes the following steps:

[0037] S110, obtaining picking task information and picker information corresponding to the picking task in the task-in-progress state, and obtaining the working status information of each review station.

[0038] The picking task may be a picking task corresponding to at least one order received in the warehouse management system. The target picking goods in a picking task may be determined after a plurality of orders are grouped.

[0039] The picking task in the task-in-progress state may be any picking task corresponding to a waiting-to-pick task list after being received by a picker. Each picking task in the task-in-progress state is bound to a corresponding picker.

[0040] The picking task information corresponding to the picking task in the task in progress state may be information related to the goods to be picked and affecting the time to complete the picking task, or information indicating the difficulty of the picking task. For example, the picking task information may be information such as the quantity, volume, weight, total weight, storage location distribution, number of aisles across shelves, and picking task type of the goods to be picked.

[0041] The picker information corresponding to the picking task in the ongoing state can be information describing the impact of the picking task completion time from the perspective of the picker, or feature information indicating the picking efficiency of the picker. For example, the picker information corresponds to the company age, position, and labor attributes.

[0042] The working status information of each review station represents the information that affects the time efficiency of the picking review task from the review station dimension, including information such as the business type, the reviewer's age and backlog status that represents the review efficiency of the review station.

[0043] The above-mentioned relevant information about the picking task in the task-in-progress status takes into account the impact on the efficiency of the picking review task from multiple dimensions, so as to consider from multiple dimensions how to schedule the corresponding monitoring review task after the picking task in the task-in-progress status is completed.

[0044] S120. Perform information prediction based on the picking task information, picker information and work status information to obtain the remaining picking time of the picking task, the average transportation time for transporting the goods corresponding to the picking task to each review station, the first estimated time for each review station to handle unfinished picking review tasks, and the second estimated time for each review station to complete the picking review tasks to be assigned corresponding to the picking tasks.

[0045] The remaining picking time of the picking task, the average transportation time for transporting the goods corresponding to the picking task to each review station, the first estimated time for each review station to handle the unfinished picking review tasks, and the second estimated time for each review station to complete the picking review tasks corresponding to the picking tasks are predicted respectively. The prediction can be made based on the information data that affects the corresponding time in the picking task information, picker information and work status information obtained in the previous step.

[0046] The specific duration prediction process can be calculated using the corresponding duration prediction model algorithm; it can also be matched with the corresponding information in the historical picking task practice process based on the corresponding information in the picking task information, picker information and work status information to determine the remaining picking time, average transportation time, first estimated time and second estimated time of the closest historical picking task as the corresponding prediction result.

[0047] The total time from a picking task to the completion of the corresponding picking review task includes the sum of the remaining picking time, the time to transport to the corresponding review station after the picking is completed, the time to wait for review after arriving at the review station, and the compounded time. Among them, the time to wait for review after arriving at the review station corresponds to the first estimated time for the review station to process the unfinished picking review task, and the compounded time corresponds to the second estimated time for the review station to complete the picking task corresponding to the to-be-assigned picking review task.

[0048] S130. Taking the shortest estimated time for completing the review of all picking review tasks to be assigned as the target task scheduling result, determine the target review station corresponding to each picking review task to be assigned according to the remaining picking time, the average transportation time, the first estimated time and the second estimated time, so as to complete the task scheduling management of the picking review tasks.

[0049] The task scheduling result with the shortest estimated completion time of all picking review tasks to be assigned takes into account the global picking review task scheduling efficiency.

[0050] The overall time consumption of each possible picking review task scheduling allocation scheme can be calculated according to the remaining picking time, the average transportation time consumption, the first estimated time consumption and the second estimated time consumption, and the scheme with the shortest overall time consumption can be used as the final target scheme.

[0051] Assume that there are currently 4 picking tasks corresponding to the picking review tasks, and there are 3 review stations in total. Each picking review task may be assigned to any one of the 3 review stations, so there are 3*3*3*3 corresponding assignable schemes. For each assignable scheme, the estimated time to complete the review of all the picking review tasks to be assigned can be calculated. Among them, the estimated time to complete the review of a picking review task to be assigned can be the corresponding remaining picking time, average transportation time, first estimated time and second estimated time calculation accumulation, the accumulation of the estimated time to complete the review of the picking review task to be assigned.

[0052] In the allocable solution with the shortest estimated time for completing the review of all the picking and review tasks to be allocated, the corresponding relationship between each picking and review task to be allocated and the review station is used as the final scheduling and allocation result of the picking and review tasks.

[0053] Furthermore, the identification information and / or location information of the target review station corresponding to each to-be-assigned picking and review task can be sent to the target handheld terminal determined according to the picker information. Thus, after the corresponding picker sees the target review station information, he or she can directly push the picking cart with the picked goods to the target review station. This process saves the role of the dispatcher and the dispatcher's decision-making thinking process. Replacing manual dispatching of picking and review tasks reduces labor costs, realizes the connection between picking and picking review, and improves the efficiency of task scheduling.

[0054] For example, please refer to Figure 3 Comparison of different task scheduling processes shown. In this embodiment, the overall solution is to change the traditional dispatcher who pushes the chaotic picking cart to the appropriate review station at the moment into a picker who can give full play to the initiative of the picker and push the order to the review station pushed by the algorithm. The picker can only pick up the next picking task after the order is pushed, otherwise the account cannot participate in picking. Compared with the original solution, the role of the dispatcher will be eliminated, saving labor costs, avoiding uneven distribution of review tasks and avoiding fraud, making the on-site review production scene from disorder to order, and optimizing the overall production time during the stage time.

[0055] The technical solution of this embodiment is to obtain the picking task information and picker information corresponding to the picking tasks in the task in progress state, and obtain the working status information of each review station; perform information prediction based on the picking task information, picker information and working status information to obtain the remaining picking time of the picking task, the average transportation time for transporting the goods corresponding to the picking task to each review station, the first estimated time for each review station to handle the unfinished picking review tasks, and the second estimated time for each review station to complete the to-be-assigned picking review tasks corresponding to the picking tasks; take the shortest estimated time for completing the review of all to-be-assigned picking review tasks as the target task scheduling result, determine the target review station corresponding to each to-be-assigned picking review task based on the remaining picking time, the average transportation time, the first estimated time and the second estimated time, so as to complete the task scheduling management of the picking review tasks. The technical solution of the embodiment of the present invention solves the problems of low efficiency in manual scheduling of picking and review tasks and low task scheduling benefits caused by incomplete information analysis. It can replace manual scheduling of picking and review tasks, reduce task scheduling costs, quickly analyze multi-dimensional information to determine the scheduling plan for picking and review tasks, and improve task scheduling efficiency and effectiveness.

[0056] Figure 4 This is a flowchart of a picking and reviewing task management method provided by an embodiment of the present invention. This embodiment and the picking and reviewing task management method in the above embodiment belong to the same inventive concept, and further describes the process of determining the task scheduling scheme. The method can be executed by a picking and reviewing task management device, which can be implemented by software and / or hardware and integrated into a computer device with application development function.

[0057] like Figure 4 As shown, the picking review task management method of this embodiment includes the following steps:

[0058] S210: Acquire the picking task information and picker information corresponding to the picking task in the task-in-progress state, and acquire the working status information of each review station.

[0059] S220. Perform information prediction based on the picking task information, picker information and work status information to obtain the remaining picking time of the picking task, the average transportation time for transporting the goods corresponding to the picking task to each review station, the first estimated time for each review station to handle unfinished picking review tasks, and the second estimated time for each review station to complete the picking review tasks to be assigned corresponding to the picking tasks.

[0060] Specifically, when performing information prediction, the picking task information and the picker information can be input into the picking time prediction model for information prediction to obtain the remaining picking time of the picking task; the information related to the transportation time in the picking task information and the picker information can be input into the average transportation time prediction model to obtain the average transportation time for transporting the goods corresponding to the picking task to each review station; the work status information can be input into the backlog review task time prediction model to obtain the first estimated time for each review station to process the unfinished picking review tasks; the picking task information and the work status information can be input into the single review task time prediction model to obtain the second estimated time for each review station to complete the picking review tasks corresponding to the picking tasks.

[0061] Among them, the picking time prediction model, the average transportation time prediction model, the backlog review task time prediction model and / or the single review task time prediction model can be a machine learning model or a deep learning network. The picking time prediction model, the average transportation time prediction model, the backlog review task time prediction model and / or the single review task time prediction model can be based on the picking task information and picker information corresponding to the picking task corresponding to the historical picking task in the scheduling process, as well as the working status information of each review station, and the remaining picking time, average transportation time, first estimated time and second estimated time data determined by the picking review task corresponding to the historical picking task.

[0062] In an optional implementation, the process of training the picking time prediction model, the average transportation time prediction model, the backlog review task time prediction model and / or the single review task time prediction model may include the following steps:

[0063] First, the picking task information, picker information and time-consuming data of each link in the task scheduling process corresponding to each historical picking review task in the task scheduling process of the historical picking review task are obtained, and the working status information of each review station is obtained. Then, according to the picking task information, picker information, time-consuming data of each link in the task scheduling process and working status information, the model training samples of the picking time prediction model, the average transportation time prediction model, the backlog review task time prediction model and / or the single review task time prediction model are respectively constructed.

[0064] In the specific implementation, historical data can be bucketed from the dimensions of picking task orders, pickers, and review tables, and the features used for bucketing are prior experience inputs. For example, data that measures the difficulty of picking tasks: the total number of picked items in the task order, the number of cross-channels, the total weight, the order quantity, the type of task order, etc.; features that measure the efficiency of pickers: such as company age, position, and labor attributes; features that measure the review efficiency of the review table: business type, reviewer age, backlog, etc.; feature data that measures the difficulty of picking tasks: can be features that measure transportation time included in the picking task information, such as the degree of congestion in the storage area, the distribution of goods, etc. Based on the sample data obtained above, equations can be constructed in different data dimensions to describe the corresponding information. For example:

[0065] Picking task information: f(α i )=θ1(qtys)+θ2(weight)+θ3(taskType)+….

[0066] Picker information: g(β j )=σ1(age)+σ2(experience)+σ3(job)+….

[0067] Working status information of the review station: h(γ k )=δ1(busy)+δ2(age)+δ3(type)+….

[0068] Transportation time:

[0069] Among them, qtys represents quatity, the number of goods in each picking task, weight represents the weight of goods, taskType represents the task type, age represents age, experience represents company experience, job represents position, busy represents the busyness, which can be measured by the number of backlog review tasks, and group represents the business type grouping of review tasks.

[0070] Then, the pre-built models or equations can be trained through training samples to obtain corresponding picking time prediction models, average transportation time prediction models, backlog review task time prediction models and / or single review task time prediction models.

[0071] The models trained according to the sample data of the above dimensions can be expressed as follows:

[0072] Picking time prediction model: e ij =U(f(α i ),g(β j )), predict the remaining picking time of the current picker j for picking task i.

[0073] Average transportation time prediction model: cost(μ ik ), predict the average transportation time from picking cart i to review station k. The picking cart corresponds to the picking task.

[0074] Backlog review task time prediction model: busy k =V(h(γ k ))*busyQtys k , predict the time it takes to process the backlog at the review desk.

[0075] Single review task time prediction model: deal ik =W(f(α i ),h(γ k )), is used to predict the estimated time required for review station k to review the current task i.

[0076] S230, respectively calculating the estimated time required for each to-be-assigned picking and review task from completion of picking to assignment to each review station for review based on the remaining picking time, the average transportation time, the first estimated time, and the second estimated time.

[0077] See reference for the estimated time required for each pending picking and review task from completing the picking to assigning it to each review station. Figure 5 The process shown calculates the possible time it takes for the picking cart to reach each review station, including u i 、f i and e ij The sum of the three parts. i Corresponding to the sum of the remaining picking time and the average transportation time, f i Corresponding to the first estimated time, e ij Corresponding to the second estimated time.

[0078] S240: Calculate the estimated time to complete the review of all the to-be-assigned picking review tasks corresponding to each feasible task scheduling solution according to the estimated time-consuming result.

[0079] The picking review task is to dispatch the picking carts generated in the upstream picking link to the relevant review stations. Since the pre-allocation method is adopted, the time for the pickers to pick up the picking carts will be estimated in advance, so there will be a matching relationship between multiple picking carts and multiple review stations. The 0-1 integer programming model idea can be adopted, with the shortest estimated review completion time of all current task orders as the objective function, as follows:

[0080] Decision variables: x ik =0 or 1, indicating whether the picking review task corresponding to picking task i is reviewed by review station k.

[0081] Shadow variable: y ij=0or1, indicating whether picking task i is picked by picker j, which is a known variable.

[0082] Objective function:

[0083]

[0084] The constraints for solving the above objective function can be:

[0085]

[0086] S250. Determine the target review station corresponding to each to-be-assigned picking review task according to the correspondence between the to-be-assigned picking review tasks and the review stations in the task scheduling plan corresponding to the shortest time in the estimated review completion time.

[0087] The objective function is solved according to the above constraints. After the solution of the objective function is obtained, the target review station corresponding to each picking review task to be assigned can be determined.

[0088] The technical solution of this embodiment obtains the picking task information and picker information corresponding to the picking task in the task in progress state, and obtains the working status information of each review station; performs information prediction based on the picking task information, the picker information and the working status information as well as the pre-trained information prediction model to obtain the remaining picking time of the picking task, the average transportation time for transporting the goods corresponding to the picking task to each review station, the first estimated time for each review station to handle the unfinished picking review tasks, and the second estimated time for each review station to complete the picking review tasks corresponding to the picking tasks to be assigned Estimated time consumption; according to the remaining picking time, average transportation time consumption, first estimated time consumption and second estimated time consumption, respectively calculate the estimated time consumption results of each to-be-assigned picking and review task from the completion of picking to the assignment to each review station to complete the review; according to the estimated time consumption results, calculate the estimated time for completion of the review of all to-be-assigned picking and review tasks corresponding to each feasible task scheduling scheme; according to the correspondence between the to-be-assigned picking and review tasks and the review stations in the task scheduling scheme corresponding to the shortest time in the estimated time for completion of the review, determine the target review station corresponding to each to-be-assigned picking and review task. The technical solution of the embodiment of the present invention solves the problems of low efficiency in manually scheduling picking and review tasks and low task scheduling benefits due to incomplete information analysis. It can replace manual scheduling of picking and review tasks, reduce task scheduling costs, quickly analyze multi-dimensional information to determine the scheduling scheme for picking and review tasks, and improve task scheduling efficiency and effectiveness.

[0089] Figure 6This is a flowchart of a picking and reviewing task management method provided by an embodiment of the present invention. This embodiment and the picking and reviewing task management method in the above embodiment belong to the same inventive concept, and further illustrates the process of determining the picking and reviewing task scheduling allocation plan. The method can be executed by a picking and reviewing task management device, which can be implemented by software and / or hardware and integrated into a computer device with application development function.

[0090] like Figure 6 As shown, the picking review task management method of this embodiment includes the following steps:

[0091] S310, obtaining the picking task information and picker information corresponding to the picking task in the task-in-progress state, and obtaining the working status information of each review station.

[0092] S320. Input the picking task information and the picker information into the picking time prediction model for information prediction to obtain the remaining picking time of the picking task; input the information related to the transportation time in the picking task information and the picker information into the average transportation time prediction model to obtain the average transportation time for transporting the goods corresponding to the picking task to each review station; input the work status information into the backlog review task time prediction model to obtain the first estimated time for each review station to handle the unfinished picking review tasks; input the picking task information and the work status information into the single review task time prediction model to obtain the second estimated time for each review station to complete the picking review tasks corresponding to the picking tasks.

[0093] S330, based on the remaining picking time, the average transportation time, the first estimated time and the second estimated time, respectively calculate the estimated time results of each picking and review task to be assigned from the completion of picking to the completion of review at each review station.

[0094] S340, calculating the estimated time to complete the review of all the to-be-assigned picking review tasks corresponding to each feasible task scheduling scheme according to the estimated time-consuming result; and calculating the Gini coefficient of the busyness of each review station in each task scheduling scheme.

[0095] Among them, the Gini coefficient is used to indicate the difference in busyness of each review station. The smaller the Gini coefficient, the fairer the distribution of picking review tasks at each review station.

[0096] The process of calculating the Gini coefficient can be expressed as: k (∑ i∈I x ik *busy k ).

[0097] S350, conduct a comprehensive analysis on the estimated time to complete the review and the Gini coefficient, take the minimum value of the corresponding comprehensive analysis result as the target task scheduling result, and determine the target review station corresponding to each picking review task to be assigned.

[0098] In this embodiment, the objective function for determining the target review station corresponding to each to-be-assigned picking review task can be expressed as:

[0099]

[0100] The above function can be used for multi-objective planning. The first item is the shortest estimated time for the total task order, and the second item is the Gini coefficient of the busyness of each review station. The smaller the Gini coefficient, the more fair it is. i To balance the two objectives (trade-off), to achieve a balance between efficiency priority and fair assignment. The constraints of the multi-objective programming are the same as the constraints in the previous embodiment.

[0101] S360: Send the identification information and / or location information of the target review station to the target handheld terminal determined according to the picker information.

[0102] The identification information and / or location information of the target verification station corresponding to each to-be-assigned picking and verification task is sent to the target handheld terminal determined according to the picker information. As a result, after the corresponding picker sees the target verification station information, he or she can directly push the picking cart with the finished goods to the target verification station. This process saves the role of the dispatcher and the dispatcher's decision-making thinking process. It replaces manual dispatching of picking and verification tasks, reduces labor costs, realizes the connection between picking and picking verification, and improves the efficiency of task scheduling.

[0103] The technical solution of this embodiment is to obtain the picking task information and picker information corresponding to the picking task in the task in progress state, and obtain the working status information of each review station; input the picking task information and picker information into the picking time prediction model for information prediction, and obtain the remaining picking time of the picking task; input the information associated with the transportation time in the picking task information and picker information into the average transportation time prediction model, and obtain the average transportation time for transporting the goods corresponding to the picking task to each review station; input the working status information into the backlog review task time prediction model, and obtain the first estimated time for each review station to handle the unfinished picking review tasks; input the picking task information and working status information into the single review task time prediction model, and obtain the time corresponding to each review station completing the picking task. The second estimated time for the assigned picking and review tasks; calculate the estimated time for each assigned picking and review task from completing picking to being assigned to each review station to complete the review based on the remaining picking time, the average transportation time, the first estimated time and the second estimated time; calculate the estimated time for completing the review of all the assigned picking and review tasks corresponding to each feasible task scheduling scheme based on the estimated time results; and calculate the Gini coefficient of the busyness of each review station in each task scheduling scheme; conduct a comprehensive analysis of the estimated time for completing the review and the Gini coefficient, and take the minimum value of the corresponding comprehensive analysis result as the target task scheduling result to determine the target review station corresponding to each assigned picking and review task; send the identification information and / or location information of the target review station to the target handheld terminal determined according to the picker information. The technical solution of the embodiment of the present invention solves the problems of low efficiency of manually scheduling picking and reviewing tasks and low task scheduling benefits caused by incomplete information analysis. It can be based on the efficiency and fairness optimal constraint dispatching algorithm of batch picking and reviewing tasks, so that its in-warehouse review can achieve global efficiency improvement on the basis of taking fairness into account. Figure 7 The application example of a picking review task management method is shown in the figure, which shows that after using the solution of the embodiment of the present invention, the total review time is reduced from 14.4h to 12.1h, and the number of review stations in a single warehouse is reduced from 5.3 to 6.6. In addition, without the intervention of the dispatcher, the average labor cost saved in one year is: 2.3h*365*25 (hourly wage)*750 (number of small and medium-sized warehouses) + the efficiency value of the review process 0.7 (average number of dispatchers)*8500 (monthly salary)*12*750 (number of small and medium-sized warehouses). The dispatcher labor cost is saved ≈ 6929w. In addition, there are potential benefits such as reduced staff turnover and increased equipment utilization.

[0104] Figure 8A structural schematic diagram of a picking and review task management device provided in an embodiment of the present invention. This embodiment can be applied to the outbound management scenario of goods in logistics transportation when they are outbound, especially the situation of picking review for goods after picking is completed. The picking and review task management device can be implemented by software and / or hardware and integrated in a computer terminal device with application development function.

[0105] like Figure 8 As shown, the picking review task management device includes: a task information acquisition module 410, a task processing time prediction module 420 and a task scheduling processing module 430.

[0106] Among them, the task information acquisition module 410 is used to obtain the picking task information and picker information corresponding to the picking task in the task in progress state, and obtain the working status information of each review station; the task processing time prediction module 420 is used to perform information prediction based on the picking task information, picker information and working status information, and obtain the remaining picking time of the picking task, the average transportation time for transporting the goods corresponding to the picking task to each review station, the first estimated time for each review station to process the unfinished picking review tasks, and the second estimated time for each review station to complete the picking review tasks to be assigned corresponding to the picking tasks; the task scheduling processing module 430 is used to take the shortest estimated time for completing the review of all picking review tasks to be assigned as the target task scheduling result, and determine the target review station corresponding to each picking review task to be assigned according to the remaining picking time, the average transportation time, the first estimated time and the second estimated time, so as to complete the task scheduling management of the picking review tasks.

[0107] The technical solution of this embodiment is to obtain the picking task information and picker information corresponding to the picking tasks in the task in progress state, and obtain the working status information of each review station; perform information prediction based on the picking task information, picker information and working status information to obtain the remaining picking time of the picking task, the average transportation time for transporting the goods corresponding to the picking task to each review station, the first estimated time for each review station to handle the unfinished picking review tasks, and the second estimated time for each review station to complete the to-be-assigned picking review tasks corresponding to the picking tasks; take the shortest estimated time for completing the review of all to-be-assigned picking review tasks as the target task scheduling result, determine the target review station corresponding to each to-be-assigned picking review task based on the remaining picking time, the average transportation time, the first estimated time and the second estimated time, so as to complete the task scheduling management of the picking review tasks. The technical solution of the embodiment of the present invention solves the problems of low efficiency in manual scheduling of picking and review tasks and low task scheduling benefits caused by incomplete information analysis. It can replace manual scheduling of picking and review tasks, reduce task scheduling costs, quickly analyze multi-dimensional information to determine the scheduling plan for picking and review tasks, and improve task scheduling efficiency and effectiveness.

[0108] In an optional implementation, the task scheduling processing module 430 is specifically used to:

[0109] According to the remaining picking time, average transportation time, first estimated time and second estimated time, the estimated time of each picking and review task to be assigned from the completion of picking to the completion of review at each review station is calculated respectively;

[0110] Calculate the estimated time to complete the review of all the picking review tasks to be assigned corresponding to each feasible task scheduling solution based on the estimated time consumption results;

[0111] According to the correspondence between the to-be-assigned picking review tasks and the review stations in the task scheduling plan corresponding to the shortest time in the estimated review completion time, the target review station corresponding to each to-be-assigned picking review task is determined.

[0112] In an optional implementation, the task scheduling processing module 430 may also be specifically used for:

[0113] Calculate the Gini coefficient of the busyness of each review station in each task scheduling plan;

[0114] The target task scheduling result is the one with the smallest comprehensive analysis result corresponding to the Gini coefficient and the estimated time for completing the review, and the target review station corresponding to each picking review task to be assigned is determined.

[0115] In an optional implementation, the picking review task management device further includes a task scheduling management information sending module, which is used to:

[0116] The identification information and / or location information of the target review station is sent to the target handheld terminal determined according to the picker information.

[0117] In an optional implementation, the task processing duration prediction module 420 is specifically used to:

[0118] Input the picking task information and the picker information into the picking time prediction model to perform information prediction and obtain the remaining picking time of the picking task;

[0119] Input the information related to the transportation time in the picking task information and the picker information into the average transportation time prediction model to obtain the average transportation time for transporting the goods corresponding to the picking task to each review station;

[0120] Input the work status information into the backlog review task time consumption prediction model to obtain the first estimated time consumption for each review station to process the unfinished picking review task;

[0121] The picking task information and the work status information are input into a single review task time consumption prediction model to obtain a second estimated time consumption for each review station to complete the picking task and the corresponding picking review task to be assigned.

[0122] In an optional implementation, the picking review task management device further includes a model training module, which is used to:

[0123] The picking time prediction model, the average transportation time prediction model, the backlog review task time prediction model and / or the single review task time prediction model are trained. The training process includes the following steps:

[0124] Obtain the picking task information, picker information and time-consuming data of each link in the task scheduling process corresponding to each historical picking review task, and obtain the working status information of each review station;

[0125] According to the picking task information, picker information, time-consuming data of each link in the task scheduling and allocation process, and work status information, model training samples of the picking time prediction model, the average transportation time prediction model, the backlog review task time prediction model, and / or the single review task time prediction model are respectively constructed;

[0126] Model training is performed based on the model training samples to obtain a picking time prediction model, an average transportation time prediction model, a backlog review task time prediction model and / or a single review task time prediction model.

[0127] The picking and reviewing task management device provided in the embodiment of the present invention can execute the picking and reviewing task management method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0128] Fig. 9 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Fig. 9 A block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention is shown. Fig. 9 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention. The computer device 12 can be any terminal device with computing capabilities, such as an intelligent controller and server, a mobile phone and other terminal devices.

[0129] like Fig. 9 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0130] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0131] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0132] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Fig. 9 not shown, usually called a "hard drive"). Although Fig. 9 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0133] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0134] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with the other modules of the computer device 12 via the bus 18. It should be understood that although Fig. 9 Not shown, other hardware and / or software modules may be used in conjunction with computer device 12, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0135] The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, for example, implementing the picking review task management method provided in the embodiment of the present invention, which includes:

[0136] Obtain the picking task information and picker information corresponding to the picking task in the task-in-progress state, and obtain the working status information of each review station;

[0137] Information prediction is performed based on the picking task information, picker information and work status information to obtain the remaining picking time of the picking task, the average transportation time required to transport the goods corresponding to the picking task to each review station, the first estimated time required for each review station to handle unfinished picking review tasks, and the second estimated time required for each review station to complete the picking review tasks to be assigned corresponding to the picking tasks;

[0138] The target task scheduling result is to take the shortest estimated time to complete the review of all picking review tasks to be assigned. According to the remaining picking time, average transportation time, first estimated time and second estimated time, the target review station corresponding to each picking review task to be assigned is determined to complete the task scheduling management of the picking review tasks.

[0139] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the picking review task management method provided by any embodiment of the present invention is implemented. The method includes:

[0140] Obtain the picking task information and picker information corresponding to the picking task in the task-in-progress state, and obtain the working status information of each review station;

[0141] Information prediction is performed based on the picking task information, picker information and work status information to obtain the remaining picking time of the picking task, the average transportation time required to transport the goods corresponding to the picking task to each review station, the first estimated time required for each review station to handle unfinished picking review tasks, and the second estimated time required for each review station to complete the picking review tasks to be assigned corresponding to the picking tasks;

[0142] The target task scheduling result is to take the shortest estimated time to complete the review of all picking review tasks to be assigned. According to the remaining picking time, average transportation time, first estimated time and second estimated time, the target review station corresponding to each picking review task to be assigned is determined to complete the task scheduling management of the picking review tasks.

[0143] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0144] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0145] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0146] Computer program code for performing the operation of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0147] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0148] The embodiments of the present disclosure also provide a computer program product, including a computer program, which, when executed by a processor, implements the picking review task management method provided in any embodiment of the present disclosure.

[0149] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code for the disclosed operation, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0150] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A picking review task management method, characterized in that: include: Obtain the picking task information and picker information corresponding to the picking task in the task-in-progress state, and obtain the working status information of each review station; Perform information prediction based on the picking task information, the picker information and the work status information to obtain the remaining picking time of the picking task, the average transportation time for transporting the goods corresponding to the picking task to each of the review stations, the first estimated time for each of the review stations to process unfinished picking review tasks and the second estimated time for each of the review stations to complete the picking review tasks to be assigned corresponding to the picking task; The shortest estimated time for completing the review of all the picking review tasks to be assigned is taken as the target task scheduling result. According to the remaining picking time, the average transportation time, the first estimated time and the second estimated time, the target review station corresponding to each of the picking review tasks to be assigned is determined to complete the task scheduling management of the picking review tasks.

2. The method according to claim 1, characterized in that The shortest estimated time for completing the review of all the to-be-assigned picking review tasks is used as the target task scheduling result, and the target review station corresponding to each to-be-assigned picking review task is determined according to the remaining picking time, the average transportation time, the first estimated time, and the second estimated time, including: Calculate the estimated time for each of the to-be-assigned picking and review tasks from the completion of picking to the assignment to each of the review stations for review based on the remaining picking time, the average transportation time, the first estimated time, and the second estimated time; Calculate the estimated time to complete the review of all the to-be-assigned picking review tasks corresponding to each feasible task scheduling solution according to the estimated time-consuming result; According to the correspondence between the to-be-assigned picking and reviewing tasks and the reviewing stations in the task scheduling scheme corresponding to the shortest time in the estimated review completion time, the target reviewing station corresponding to each to-be-assigned picking and reviewing task is determined.

3. The method according to claim 2, characterized in that The method further comprises: Calculating the Gini coefficient of the busyness of each of the review stations in each of the task scheduling schemes; The target task scheduling result is determined by taking the minimum value of the comprehensive analysis result corresponding to the Gini coefficient and the estimated time for completing the review as the target task scheduling result, and determining the target review station corresponding to each of the picking review tasks to be assigned.

4. The method according to claim 1, characterized in that: The method further comprises: The identification information and / or location information of the target review station is sent to the target handheld terminal determined according to the picker information.

5. The method according to any one of claims 1 to 4, characterized in that: The information prediction is performed based on the picking task information, the picker information and the work status information to obtain the remaining picking time of the picking task, the average transportation time for transporting the goods corresponding to the picking task to each of the review stations, the first estimated time for each of the review stations to process unfinished picking review tasks and the second estimated time for each of the review stations to complete the to-be-assigned picking review tasks corresponding to the picking task, including: Inputting the picking task information and the picker information into a picking time prediction model to perform information prediction, thereby obtaining the remaining picking time of the picking task; Inputting the information related to the transportation time in the picking task information and the picker information into the average transportation time prediction model to obtain the average transportation time for transporting the goods corresponding to the picking task to each of the review stations; Inputting the work status information into a time-consuming prediction model for backlog review tasks to obtain a first estimated time consuming for each review station to process an unfinished picking review task; The picking task information and the work status information are input into a single review task time-consuming prediction model to obtain a second estimated time consuming for each review station to complete the to-be-assigned picking review task corresponding to the picking task.

6. The method according to claim 5, characterized in that The process of training the picking time prediction model, the average transportation time prediction model, the backlog review task time prediction model and / or the single review task time prediction model includes: Obtain the picking task information, picker information and time-consuming data of each link in the task scheduling process corresponding to each historical picking review task, and obtain the working status information of each review station; According to the picking task information, the picker information, the time-consuming data of each link in the task scheduling and allocation process, and the work status information, respectively construct model training samples of the picking time prediction model, the average transportation time prediction model, the backlog review task time prediction model, and / or the single review task time prediction model; Model training is performed based on the model training samples to obtain the picking time prediction model, the average transportation time prediction model, the backlog review task time prediction model and / or the single review task time prediction model.

7. A picking review task management device, characterized in that: include: The task information acquisition module is used to obtain the picking task information and picker information corresponding to the picking task in the task-in-progress state, and obtain the working status information of each review station; A task processing time prediction module is used to perform information prediction based on the picking task information, the picker information and the work status information to obtain the remaining picking time of the picking task, the average transportation time for transporting the goods corresponding to the picking task to each of the review stations, the first estimated time for each of the review stations to process unfinished picking review tasks and the second estimated time for each of the review stations to complete the picking review tasks to be assigned corresponding to the picking tasks; The task scheduling processing module is used to take the shortest estimated time for completing the review of all the picking review tasks to be assigned as the target task scheduling result, and determine the target review station corresponding to each of the picking review tasks to be assigned according to the remaining picking time, the average transportation time, the first estimated time and the second estimated time, so as to complete the task scheduling management of the picking review tasks.

8. A computer device, characterized in that: The computer device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the picking review task management method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the picking review task management method as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the picking review task management method according to any one of claims 1 to 6.

Images