Sorting order distribution method and device, storage medium and electronic equipment

Abstract

The invention relates to a sorting order distribution method and device, a storage medium and electronic equipment, in particular to the technical field of intelligent warehousing, and the method comprises the steps that rule parameters corresponding to sorting order distribution rules are analyzed to obtain optimized values of the rule parameters, and the sorting order distribution rules can be used for sorting order distribution workstations; the sorting order distribution rule is updated according to the optimized value of the rule parameter; and then, according to the updated sorting order distribution rule, distributing the sorting order to the corresponding work station. According to the technical scheme, sorting order distribution is carried out based on the optimized rule parameters, so that a sorting order distribution work station is more reasonable, the situation that the sorting order distribution work station is unreasonable can be reduced, the processing efficiency of the sorting order can be improved, and then the sorting efficiency in a warehouse system can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent warehousing technology, and in particular to a picking list allocation method, device, storage medium and electronic device. Background Art

[0002] With the growing development of e-commerce, the technology of automatic cargo handling in warehousing logistics is becoming more and more mature. In the warehousing system, order processing is one of the main processes. After receiving the user's order, a picking list will be generated according to the order, and then the picking list will be assigned to the workstation for picking processing.

[0003] At present, the warehousing system receives a large number of orders, so in order to deal with the processing of the numerous picking orders generated, multiple workstations are deployed in the warehousing system. However, in the related art, there may be unreasonable allocation of picking orders to workstations, which affects the efficiency of picking order processing and further affects the picking efficiency in the warehousing system. Summary of the invention

[0004] In view of this, the present disclosure provides a picking order allocation method, device, storage medium and electronic device, the main purpose of which is to improve the current related technology that there is an unreasonable situation in which picking order allocation workstations affect the picking order processing efficiency and further affect the picking efficiency in the warehousing system.

[0005] In a first aspect, the present disclosure provides a picking list allocation method, comprising:

[0006] Analyzing rule parameters corresponding to a picking order allocation rule to obtain optimized values ​​of the rule parameters, wherein the picking order allocation rule is used for a picking order allocation workstation;

[0007] updating the picking list allocation rule according to the optimization value;

[0008] According to the updated picking list allocation rules, the picking list is allocated to the corresponding workstation.

[0009] Optionally, before analyzing the rule parameters corresponding to the picking order allocation rule to obtain the optimized values ​​of the rule parameters, the method further includes:

[0010] Based on the picking order to be assigned and the workstation information, configuring the constraint conditions and assignment guidance conditions corresponding to the picking order assignment rule;

[0011] The step of analyzing the rule parameters corresponding to the picking order allocation rule to obtain the optimized values ​​of the rule parameters includes:

[0012] The optimization value is obtained according to the degree to which the picking order allocation result satisfies the constraint conditions and the allocation guidance conditions.

[0013] Optionally, obtaining the optimization value according to the satisfaction degree of the picking order allocation result for the constraint condition and the allocation guide condition includes:

[0014] Scoring the picking order allocation results according to the satisfaction degree of the constraint conditions and allocation guidance conditions;

[0015] A target picking list with a score that meets preset conditions is obtained, and the optimization value is determined according to the conditional parameters corresponding to the allocation of the target picking list.

[0016] Optionally, scoring the picking order allocation result according to the satisfaction degree of the constraint condition and the allocation guide condition includes:

[0017] Use a preset tool to score the picking order allocation results according to the degree of satisfaction of the constraints and allocation guidance conditions, wherein the preset tool scores the allocation results of different batches of picking orders, and iteratively updates the scoring mechanism based on the picking order allocation results selected for each batch score.

[0018] Optionally, the method also includes: if the task volume processed by a workstation is saturated when a batch of picking orders is assigned to the workstation, the batch of picking orders will be cached, and when the task volume processed by the workstation is not saturated, at least one batch of picking orders accumulated and cached will be assigned to the workstation to update the scoring mechanism of the preset tool.

[0019] Optionally, the method also includes: if the allocation result of the picking list of the target batch does not meet the constraint content, selecting the target allocation result with the highest score from the allocation results of the picking list of the target batch to perform the picking list allocation workstation, so as to update the scoring mechanism of the preset tool.

[0020] Optionally, the method further includes:

[0021] A dynamic observation diagram is output, wherein the dynamic observation diagram is used to display the dynamic effect of allocating the picking orders to the corresponding workstations according to the updated picking order allocation rules.

[0022] Optionally, the method further includes:

[0023] Adjusting the constraint conditions and allocation guidance conditions corresponding to the picking order allocation rule;

[0024] According to the adjusted constraint conditions and allocation guide conditions, the picking order allocation rules are updated again;

[0025] According to the updated picking order allocation rules, the picking orders are allocated to the corresponding workstations.

[0026] Optionally, the dynamic observation graph includes picking tasks for multiple orders corresponding to picking waves, and a flow view of the picking tasks between processing flow nodes.

[0027] Optionally, creating the dynamic observation graph includes:

[0028] Obtain the start time and end time of the order entering each processing flow node, as well as the order type of the order;

[0029] The dynamic observation graph is generated based on the start time, the end time and the order type.

[0030] Optionally, the output dynamic observation graph includes:

[0031] If the duration of any order element's stay at a processing flow node is greater than or equal to a preset threshold, a corresponding alarm prompt will be issued in the dynamic observation graph.

[0032] Optionally, the playback speed of the dynamic observation graph is greater than the normal playback speed.

[0033] In a second aspect, the present disclosure provides a picking list allocating device, comprising:

[0034] an analysis module configured to analyze a rule parameter corresponding to a picking order allocation rule to obtain an optimized value of the rule parameter, wherein the picking order allocation rule is used for a picking order allocation workstation;

[0035] An updating module, configured to update the picking order allocation rule according to the optimization value;

[0036] The processing module is configured to allocate the picking orders to corresponding workstations according to the updated picking order allocation rules.

[0037] In a third aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the picking order allocation method described in the first aspect.

[0038] In a fourth aspect, the present disclosure provides an electronic device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the picking order allocation method described in the first aspect when executing the computer program.

[0039] In a fifth aspect, the present disclosure provides a computer program product, including a computer program, which implements the picking order allocation method described in the first aspect when executed by a processor.

[0040] By means of the above technical scheme, the present disclosure provides a picking order allocation method, device, storage medium and electronic device. Compared with the current related technologies, the present disclosure can analyze the rule parameters corresponding to the picking order allocation rules to obtain the optimized values ​​of the rule parameters, wherein the picking order allocation rules can be used for the picking order allocation workstation; then the picking order allocation rules are updated according to the optimized values ​​of the rule parameters; and then the picking orders are allocated to the corresponding workstations according to the updated picking order allocation rules. By applying the technical scheme of the present disclosure, the picking orders are allocated based on the optimized rule parameters, so that the picking order allocation workstations are more reasonable, the situation of unreasonable picking order allocation workstations can be reduced, the processing efficiency of the picking orders can be improved, and the picking efficiency in the warehouse system can be improved.

[0041] The above description is only an overview of the technical solution of the present disclosure. In order to more clearly understand the technical means of the present disclosure, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the specific implementation methods of the present disclosure are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0043] 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Figure 1 A schematic diagram of a process of allocating a picking list provided by an embodiment of the present disclosure is shown;

[0045] Figure 2 A schematic diagram of a process of allocating a picking list provided by an embodiment of the present disclosure is shown;

[0046] Figure 3 A schematic diagram showing an example provided by an embodiment of the present disclosure;

[0047] Figure 4 A schematic diagram of a process of allocating a picking list provided by an embodiment of the present disclosure is shown;

[0048] Figure 5 A schematic diagram showing an example provided by an embodiment of the present disclosure;

[0049] Figure 6 A schematic structural diagram of a picking list allocating device provided by an embodiment of the present disclosure is shown;

[0050] Figure 7 A schematic structural diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0051] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0052] Many specific details are described in the following description to facilitate a full understanding of the present disclosure. However, the present disclosure can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present disclosure, so the present disclosure is not limited by the specific implementation disclosed below.

[0053] The terms used in one or more embodiments of the present disclosure are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present disclosure. The singular forms of "a", "said" and "the" used in one or more embodiments of the present disclosure and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of the present disclosure refers to and includes any or all possible combinations of one or more associated listed items.

[0054] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of the present disclosure, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of the present disclosure, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0055] In order to improve the problem that the current related technology has unreasonable distribution of picking orders to workstations, which affects the efficiency of picking order processing and further affects the picking efficiency in the warehousing system. The present disclosure provides a picking order distribution method, such as Figure 1 As shown, the method includes the following steps 101 to 103:

[0056] Step 101: Analyze the rule parameters corresponding to the picking order allocation rule to obtain the optimized values ​​of the rule parameters.

[0057] Among them, the picking list allocation rules may include an algorithm for allocating picking lists (or picking tasks, etc.) to workstations. The picking list allocation rules can be used to indicate how to execute the picking list allocation workstations. The picking list allocation rules can be customized in combination with actual conditions to meet the specific needs of different warehouse scenarios. Among them, the picking list can be generated according to the user's order, and the picking list records the information of the goods that need to be picked out from the warehouse for subsequent packaging and delivery processes. The workstation can be called a workbench, etc., which can pick the required goods according to the picking list and pack the picked goods.

[0058] In some examples, a warehouse system receives a large number of orders, so multiple workstations are deployed in the warehouse system to handle the processing of the many picking orders generated. Picking order allocation rules can be used to guide each picking order to allocate its corresponding workstation, thereby enabling batch processing of picking order tasks through multiple workstations.

[0059] In some examples, in order to reasonably allocate the picking orders to be allocated to the appropriate workstations, the picking order allocation rules may include allocation guidance conditions and constraints (i.e., rule constraints), wherein the allocation guidance conditions refer to a series of rules or standards used to guide the allocation of picking tasks when allocating picking orders, such as the picking distance is less than a certain threshold (making the picking distance corresponding to the picking order task as small as possible), the balance of workstation task volume and the utilization of processing capacity meet certain requirements (minimizing the overload of some workstations while other workstations are idle), etc. These conditions can be formulated based on business needs and warehouse operation strategies, with the aim of improving picking efficiency, reducing picking time and ensuring order accuracy. Constraints refer to regulations or restrictions that need to be followed when allocating picking orders, such as the maximum number of picking order tasks that each workstation can accommodate, the maximum number of queue shelves that each workstation can accommodate, and allocation based on order priority, etc., to ensure the feasibility and safety of the operation.

[0060] In some embodiments, the allocation guidance condition may indicate that when a solution is feasible or better, a reward score is required; the constraint condition may indicate that when a solution is not feasible or violates certain constraints, a penalty score is required. Warehouse implementation managers will configure a variety of picking strategies including task allocation in the application system in advance, from which allocation guidance conditions for guiding the allocation of picking orders and constraint conditions for constraining the allocation of picking orders that can be identified by the application program can be summarized and analyzed.

[0061] In the process of using picking order allocation rules to execute picking order allocation workstations, based on the allocation guidance conditions and constraints, heuristic algorithms and delayed acceptance algorithms can be used to arrange and combine the picking tasks to be processed with each workstation, and then compare each combination plan and update the corresponding score of each combination plan. In this way, a relatively suitable order allocation plan can be found within a fixed period of time to improve picking efficiency.

[0062] Among them, in the process of dynamically updating the scores of each allocation scheme, according to the pre-set constraints and allocation guidance conditions, the multiple allocation schemes of picking orders to each workstation are dynamically scored. If a picking order is allocated to a certain workstation and it meets the allocation guidance conditions, it will be given a positive score (reward score); if a picking order is allocated to a certain workstation and it does not fall within any of the constraints, it will be given a negative score (punitive score). Finally, within a fixed period of time, the allocation scheme with a higher score will be adopted as the picking order allocation scheme. For example, when an allocation scheme meets the guidance conditions, the score of this scheme is increased, making the picking task more inclined to be allocated to a certain workstation; when an allocation scheme violates a constraint condition, the score corresponding to this constraint is deducted from this scheme. Over a period of time, the picking tasks that have not yet been allocated will continue to participate in this scoring, and the score will change dynamically according to the workload of the current workstation, so as to seek a suitable allocation scheme.

[0063] In some embodiments, the rule parameters corresponding to the picking order allocation rule may be the rule parameters involved in the picking order allocation rule. For example, the rule parameters may be the condition parameters corresponding to the allocation guidance conditions and constraint conditions, such as the picking distance parameter, the balance of the workstation task volume, the maximum number of picking order tasks that each workstation can accommodate, etc. For the embodiments of the present disclosure, there are multiple optional ways to obtain the optimized values ​​of the rule parameters through analysis. As an optional way, the data of historical picking order allocation workstations may be collected, including the processing time, walking distance, queue length and other indicators of historical picking order tasks assigned to the workstations, and then the statistical analysis tools are used based on these historical data to identify the optimized values ​​of the rule parameters, such as which rule parameters can make the picking order allocation more reasonable and improve the picking efficiency, and then select the optimized values ​​of the rule parameters.

[0064] For example, collect the processing time of each picking order task at the workstation, the walking distance required for the automated equipment to complete the picking and the length of time waiting in line at the workstation, the workload of each workstation, the record of whether the picking task is successfully completed, and the rule parameters used when assigning these picking order tasks to the workstation. Based on these data, use statistical analysis tools to analyze the data, establish a mapping relationship between these indicators and the corresponding conditional parameters, calculate the statistics of these indicators (such as mean, median, standard deviation, etc.), and generate visual charts. By adjusting different rule parameters, observe the changes in the statistics of these indicators, so as to find the appropriate rule parameters so that the statistics of these indicators meet the requirements, and use the found rule parameters as the optimized values ​​of the rule parameters.

[0065] Step 102: Update the picking order allocation rules according to the optimized values ​​of the rule parameters.

[0066] In some embodiments, specific allocation guidance conditions and constraints can be determined according to the optimized values ​​of the rule parameters. For example, in addition to the rigidly specified condition contents, some flexible condition contents with optional range values ​​can be determined from the optional range values ​​according to the optimized values, thereby determining the flexible condition contents. Then, the rules for allocating the picking list to the workstations are re-formulated according to the re-determined allocation guidance conditions and constraints, that is, the picking list allocation rules are updated.

[0067] For example, the optional range of the picking order priority weight may be 1-10 (the higher the value, the higher the priority). The weight is used to consider the priority when allocating the picking order task. The higher the weight, the more likely the picking order task will be allocated first. According to the optimized value of the constraint parameter obtained in step 101, it is determined that the picking order priority weight of the urgent order is set to 10, and the picking order priority weight of the ordinary order is set to 5.

[0068] Step 103: Allocate the picking order to the corresponding workstation according to the updated picking order allocation rule.

[0069] For example, according to the picking order allocation rules before the update, in the same picking wave, picking order 1 for an urgent order can be assigned to a workstation only after picking order 2 for an ordinary order is assigned to a workstation. According to the updated picking order allocation rules, compared with the picking order priority weight of an ordinary order, the picking order priority weight of an urgent order is set higher, so picking order 2 for an ordinary order can be assigned to a workstation only after picking order 1 for an urgent order is assigned to a workstation.

[0070] In some embodiments, the current batch of picking orders is assigned to corresponding workstations according to the updated picking order allocation rules, and the rule parameters can be re-optimized according to the allocation effect of the current batch, and the picking order allocation rules can be updated again according to the re-optimized rule parameters, thereby guiding the next batch of picking order allocation, so that the rule parameters can be iteratively optimized and updated, thereby continuously optimizing the process of picking order allocation workstations.

[0071] Compared with the current related technologies, the disclosed embodiment can analyze the rule parameters corresponding to the picking order allocation rule to obtain the optimized value of the rule parameter, wherein the picking order allocation rule can be used for the picking order allocation workstation; then the picking order allocation rule is updated according to the optimized value of the rule parameter; and then the picking order is allocated to the corresponding workstation according to the updated picking order allocation rule. By applying the technical solution of the disclosed embodiment, the picking order is allocated based on the optimized rule parameters, so that the picking order allocation workstation is more reasonable, the situation of unreasonable picking order allocation workstation can be reduced, the processing efficiency of the picking order can be improved, and then the picking efficiency in the warehouse system can be improved.

[0072] Further, as Figure 1 An optional method of the embodiment, such as Figure 2 As shown, the method may include the following steps 201 to 204:

[0073] Step 201: Based on the picking order to be assigned and the workstation information, configure the constraint conditions and assignment guidance conditions corresponding to the picking order assignment rule.

[0074] In some embodiments, the corresponding warehouse scene information can be determined based on the number of picking orders to be assigned, the type of picking orders, the order information corresponding to the picking orders, the workstation location, the number of workstations, the type of workstations, the capacity of the workstations, etc., and the constraints and allocation guidance conditions corresponding to the picking order allocation rules can be configured according to the warehouse scene information. The constraints and allocation guidance conditions can make the allocation of picking orders to workstations more reasonable and balanced.

[0075] The disclosed embodiments can determine different warehouse scene information based on different picking orders to be assigned and workstation information, and then configure corresponding constraints and allocation guidance conditions according to different warehouse scene information. That is, different constraints and allocation guidance conditions are set according to different warehouse scenes, so that the allocation of picking orders according to the picking order allocation rules can better meet the needs of the warehouse scene and achieve more reasonable allocation in the warehouse scene.

[0076] For example, for orders with the same source order number, their corresponding picking orders will be assigned to workstation a, which will make workstation a relatively busy, while other workstations are relatively idle. The disclosed embodiment can adjust the corresponding constraint conditions and allocation guidance conditions for this situation, so that picking orders with the same source order number can also be assigned to other workstations for processing, making the allocation more balanced. By applying the solution of the disclosed embodiment, the picking order allocation workstation can be made more flexible and more adaptable to the needs of different warehouse scenarios.

[0077] Step 202: Obtain optimized values ​​of rule parameters corresponding to the picking order allocation rule according to the degree to which the picking order allocation result satisfies the constraint conditions and the allocation guidance conditions.

[0078] In some embodiments, when picking orders are allocated to workstations according to picking order allocation rules, corresponding picking order allocation results can be obtained. However, due to the complexity of the actual allocation, it is necessary to further determine whether these picking order allocation results meet the constraints and allocation guidance conditions, and then screen out the picking orders that best meet or relatively meet the constraints and allocation guidance conditions. The target condition parameters used in the allocation of the picking orders can be used to determine the optimized values ​​of the rule parameters.

[0079] In some embodiments, the constraints may include hard constraints and soft constraints; wherein hard constraints are rules or conditions that must be strictly followed. For example, hard constraints may include the number of workstations that can be assigned to a picking order task, the maximum number of picking order tasks that each workstation can accommodate, the maximum number of queued shelves that each workstation can accommodate, etc. Soft constraints are some preference or target conditions that are best met, but even if they are not met, they are acceptable. For example, picking order tasks with high priority are assigned to workstations first, picking order tasks are assigned to workstations with a small number of assigned tasks first, and shelves that hit the queue are assigned to the same workstation, etc.

[0080] The disclosed embodiment adds hard constraints and soft constraints to the constraint conditions of the picking list allocation rule. The hard constraints are used to ensure the effectiveness and feasibility of the solution, while the soft constraints are used to improve the quality and satisfaction of the solution. By reasonably defining and processing these two types of constraints, a solution that meets basic requirements and optimizes the target as much as possible can be designed.

[0081] In some examples, step 202 may specifically include: scoring the picking order allocation results according to the satisfaction degree of the constraint conditions and the allocation guide conditions; then obtaining the target picking order whose score meets the preset conditions, wherein the preset conditions may be preset according to actual needs, for example, when a picking order allocation result meets the allocation guide conditions, the score of the picking order is increased; when a picking order allocation result violates a hard constraint condition, the score corresponding to the constraint is deducted from the picking order; similarly, when a picking order allocation result violates a soft constraint, the score corresponding to the soft constraint is deducted from the picking order. Under this condition, the picking order with the highest score may be considered as the target picking order whose score meets the preset conditions, or the picking order with a score greater than a preset threshold may be considered as the target picking order whose score meets the preset conditions, etc. Then, the optimization value of the rule parameter may be determined according to the conditional parameters used corresponding to the allocation of the target picking order.

[0082] In some examples, the parameters corresponding to the soft constraints can be used to adjust the importance of the soft constraints. For example, by assigning different weights to different soft constraints, you can control which soft constraints are more important. This helps to find a balance between multiple competing objectives; it allows the importance of soft constraints to be adjusted according to actual conditions during the optimization process. For example, if a soft constraint is very important in the current situation, you can emphasize this by increasing its weight. In addition, when calculating the total cost of the solution, the soft constraint parameters can help determine the cost caused by violating the soft constraints. By properly setting and adjusting the soft constraint parameters, complex problems with multiple objectives and preferences can be effectively managed and optimized.

[0083] In some embodiments, the picking order allocation results are scored according to the degree of satisfaction of the constraints and allocation guidance conditions, which may specifically include: using a preset tool to score the picking order allocation results according to the degree of satisfaction of the constraints and allocation guidance conditions, wherein the preset tool scores the allocation results of different batches of picking orders, and iteratively updates the scoring mechanism based on the picking order allocation results selected for each batch score. The disclosed embodiment can obtain the optimized value of the rule parameters through the preset tool.

[0084] In some examples, for each batch of picking order allocation workstation processes, a preset tool can be used to score the picking order allocation results according to the degree of satisfaction of the constraints and allocation guidance conditions, and the scores of these picking order allocation results can be further outputted, and the operation and maintenance personnel of the preset tool can select from these scored picking order allocation results in combination with the actual allocation situation. The preset tool determines that its corresponding scoring method is more recognized based on the selected picking order allocation result, and clarifies the scale for measuring the degree of satisfaction of the constraints and allocation guidance conditions, so the scoring mechanism can be updated according to the scoring method. In the next batch of picking order allocation workstation processes, the preset tool can use the updated scoring mechanism to score the picking order allocation results, and the operation and maintenance personnel of the preset tool can select from these scored picking order allocation results in combination with the actual allocation situation again, and the preset tool determines that its corresponding scoring method is more recognized based on the selected picking order allocation result, so the scoring mechanism can be updated again according to the scoring method. Through this process, the scoring mechanism of the preset tool is iteratively updated. The preset tool has the ability of self-learning and continuously optimizes the scoring mechanism, so that the preset tool can more accurately find the optimal value of the rule parameters.

[0085] In some examples, the preset tool may be an OptaPlanner tool, a Google OR-Tools tool, a ChocoSolver tool, and the like.

[0086] It should be noted that in the process of optimizing the scoring mechanism, different situations may be encountered. The embodiments of the present disclosure can achieve more appropriate and reasonable scoring mechanism optimization for different situations. For details, please refer to the following examples:

[0087] In some examples, if the workload of a workstation is saturated when a batch of picking orders is assigned to a workstation, the picking orders of this batch will be cached and will not be assigned to a workstation for the time being. This is because if a workstation is assigned at this time, no suitable picking order assignment result can be selected, which is not conducive to updating the scoring mechanism of the preset tool. Therefore, caching can be performed first, such as saving to a preset cache location. If the workload of a workstation is still saturated when the next batch of picking orders arrives, caching can continue. When the workload of a workstation is not saturated, at least one batch of picking orders that has been cached will be assigned to a workstation to update the scoring mechanism of the preset tool. For example, the preset tool is used to score the picking order allocation results according to the satisfaction degree of the constraints and allocation guidance conditions. The constraints may include hard constraints and soft constraints. The hard constraints may include that a picking order task can only be assigned to one workstation, the maximum number of picking order tasks that each workstation can accommodate, the maximum number of queued shelves that each workstation can accommodate, etc.; soft constraints may include that picking order tasks with high priority are assigned to workstations first, picking order tasks are assigned to workstations with a small number of assigned tasks first, and shelves in the queue are assigned to the same workstation, etc.; allocation guidance conditions may include that the picking distance is less than a certain threshold (making the picking distance corresponding to the picking order task as small as possible), the balance of workstation task volume and the utilization rate of processing capacity meet certain requirements (minimizing the overload of some workstations and the idleness of other workstations). Then, the operation and maintenance personnel of the preset tool select from these scored picking order allocation results based on the actual allocation situation. The preset tool determines that its corresponding scoring method is more recognized based on the selected picking order allocation result, and can update the scoring mechanism according to the scoring method.

[0088] In some examples, if the allocation result of the picking list of the target batch (such as a certain batch) is not ideal for satisfying the constraint conditions and the allocation guidance conditions, that is, the general scores are all below a certain threshold, then the target allocation result with the highest score is selected from the allocation results of the picking list of the target batch for the picking list allocation workstation to update the scoring mechanism of the preset tool. For example, in order for the preset tool to self-learn the scoring mechanism, the target allocation result with the highest score this time can be first selected for the picking list allocation workstation, so that the preset tool updates the scoring mechanism according to the scoring method corresponding to the target allocation result.

[0089] Step 203: Update the picking order allocation rule according to the optimized value of the rule parameter.

[0090] In some embodiments, the picking order allocation rules may be updated according to the rule parameters optimized by the above process.

[0091] Step 204: Allocate the picking order to the corresponding workstation according to the updated picking order allocation rule.

[0092] By applying the technical solution of the embodiment of the present disclosure, the picking orders are allocated based on the optimized rule parameters, so that the allocation of picking orders to workstations is more reasonable, the situation where the picking orders are allocated to workstations unreasonably can be reduced, the processing efficiency of picking orders can be improved, and the picking efficiency in the warehouse system can be improved.

[0093] Further, as Figure 1 or Figure 2 In an optional manner of the embodiment, a corresponding dynamic observation diagram may also be output, which may be used to show the effect of assigning the picking order to the corresponding workstation according to the updated picking order assignment rule. The dynamic observation diagram may include order elements of multiple orders corresponding to the picking wave, and a flow view of the order elements between the processing flow nodes.

[0094] Among them, the order element can be the element corresponding to the order displayed in the dynamic observation map, and its display style can be pre-set according to actual needs. For example, the picking list element can be a combination of a dot and at least one small dot, and the dot represents the order corresponding to the picking list, and the small dots represent the goods in the order.

[0095] The flow view of order elements being assigned to corresponding workstations can be used to represent the process of each picking order being dynamically assigned to a workstation. Operation and maintenance personnel can use this dynamic observation chart to intuitively understand the flow process of each picking order being assigned to a workstation, and then determine whether this allocation process is reasonable, such as whether there is any problem such as unbalanced workstation allocation.

[0096] In some embodiments, the dynamic observation graph may also include order elements before generating each picking order element, and a flow view of order elements between processing flow nodes. The processing flow nodes may also be referred to as flow nodes, state nodes, etc., and may specifically include waiting for scheduling, creating picking work, pre-allocating storage areas, wave formation, generating picking orders, allocating picking orders, picking in progress, and picking completed.

[0097] In this way, we can take orders as individuals and achieve dynamic visualization of the flow between processing nodes during the processing of each order, so that operation and maintenance personnel can intuitively understand the flow status of each order processing process. Figure 3 As shown in the figure, each point is equivalent to an order, and the processing flow nodes may include: waiting for scheduling, creating picking work, pre-allocating storage area, wave formation, generating picking orders, picking order allocation, picking in progress, picking completed, etc. According to the moving speed of the order, the processing time of the order at each processing flow node is determined, as well as the picking order allocation workbench (i.e. Figure 3 This helps operation and maintenance personnel to identify problems and perform corresponding maintenance.

[0098] In some embodiments, the process of creating a dynamic observation graph may include: first obtaining the target data in the order processing process, and then generating a dynamic observation graph based on the target data. The target data may include the start time and end time of the order entering each processing flow node, as well as the order type of the order, etc. The processing flow node may include: waiting for scheduling, creating picking work, pre-allocating warehouse areas, wave formation, generating picking orders, picking order allocation, picking in progress, picking completed, etc. In addition, it may also include subdivided status nodes involving the robot management system (RMS), such as calling a robot, a robot taking a shelf, a robot returning a shelf, etc., such as splitting the status node in picking into more subdivided status nodes involving RMS.

[0099] In some examples, the order may be a historical order, and analysis may be performed based on the processing status of the historical orders to achieve a dynamic visualization of the flow between processing flow nodes during the processing of each historical order, so that operation and maintenance personnel can intuitively understand the flow status of each historical order processing process, thereby discovering and solving problems to optimize the processing of current orders.

[0100] In some examples, the playback speed of the output dynamic observation graph is faster than the normal playback speed. Since the order life cycle goes through many processing flow nodes and the processing flow is slow, when processing historical orders, the playback speed can be increased in subsequent dynamic observation graphs (such as 50 times, 100 times, etc.) to more clearly discover problems.

[0101] In some examples, orders can also be real-time orders, and based on the processing status of real-time orders, a dynamic visualization effect of the flow between processing flow nodes during the processing of each real-time order can be achieved, which is convenient for operation and maintenance personnel to monitor the processing status of each real-time order in a timely manner.

[0102] In some examples, such as Figure 3 As shown, taking an order as an individual, the display form can be dots or other styles and shapes, etc., starting from the node waiting for scheduling, and sequentially going through the nodes of creating picking work, pre-allocating warehouse areas, and wave formation, the dynamic effect of the transformation can be displayed when reaching the node of generating a picking list. For example, taking the display style of the order element as dots as an example, when generating a picking list, the order dots are wrapped in a large circle to reflect their transformation process. After generating a picking list, it can be further transformed into other styles. For example, on the basis of the order dots, the order dots are connected with at least one smaller dot, and these smaller dots can represent the goods in the order. In this way, the order dots plus the connected smaller dots indicate that the order has been transformed into a picking list.

[0103] Furthermore, dots of different colors or styles may be displayed according to the type of order. The order types may include single item, multiple items, orders to the merchant, orders to the user, and some custom types. Figure 3 As shown, according to the start time and end time of the order entering each processing flow node, a smooth transition display of the dot flow is performed in chronological order, so as to achieve a dynamic observation diagram of the order flow between the processing flow nodes.

[0104] In some examples, if the length of time that any order element stays at a processing flow node is greater than or equal to a preset threshold, a corresponding alarm prompt is issued in the dynamic observation diagram to promptly remind the operation and maintenance personnel of abnormalities, thereby facilitating timely corresponding maintenance processing. For example, if the length of time that an order stays at a processing flow node exceeds a certain threshold, a corresponding alarm prompt is issued in the dynamic observation diagram. Among them, the preset threshold corresponding to each processing flow node may be different, and can be determined comprehensively based on the processing complexity of the processing flow node and combined with actual conditions.

[0105] In some examples, the dynamic observation graph also includes all the status nodes from order placement to distribution on the seed wall, as well as the flow view of order elements between processing flow nodes, so that immediate correction intervention can be carried out before the order distribution workstation. For example, if it is found in the dynamic observation graph that a large number of orders stay at a certain status node for a long time without moving down, then immediate human intervention can be carried out to check.

[0106] Furthermore, if the operation and maintenance personnel determine that the allocation of picking orders to workstations is unreasonable based on the dynamic observation graph, for example, some workstations are relatively concentrated with picking orders, while other workstations are relatively idle, the overall processing time increases, affecting the efficiency of picking order processing, thereby affecting the picking efficiency in the warehouse system. The picking order allocation rules can be adjusted accordingly, such as Figure 4 As shown, the method may include the following steps 301 to 304:

[0107] Step 301: Adjust the constraint conditions and allocation guidance conditions corresponding to the picking order allocation rules.

[0108] In some embodiments, the purpose of adjusting the constraint conditions and allocation guidance conditions may be to allocate picking orders to workstations more evenly, thereby reducing the situation where some workstations are relatively concentrated with picking orders while other workstations are relatively idle.

[0109] In some embodiments, the constraint conditions and allocation guide conditions corresponding to the picking list allocation rules may be adjusted according to the adjustment instructions of the operation and maintenance personnel. For example, the constraint conditions and allocation guide conditions may be adjusted to make the picking list allocation workstation more reasonable.

[0110] Step 302: Update the picking order allocation rules again according to the adjusted constraint conditions and allocation guidance conditions.

[0111] In some embodiments, the target rule parameters corresponding to the adjusted constraint conditions and the allocation guidance conditions may be determined according to the initially configured rule parameters. For example, the initially configured rule parameters may be default general rule parameters, or may be configured by the operation and maintenance personnel according to requirements.

[0112] In some embodiments, the initially configured rule parameters may be optimized, and the optimized rule parameters may be obtained as target rule parameters. Figure 1 or Figure 2 The optimization process shown in the corresponding embodiment is used to obtain optimized rule parameters. For example, the preset tool can be used to obtain the optimized value of the rule parameter as the target rule parameter corresponding to the adjusted constraint condition and allocation guide condition. Then, the target rule parameter is used in combination with the adjusted constraint condition and allocation guide condition to update the picking list allocation rule again.

[0113] Step 303: Allocate the picking order to the corresponding workstation according to the updated picking order allocation rule.

[0114] In some embodiments, a corresponding dynamic observation diagram may be output to show the effect of allocating the picking orders to the corresponding workstations according to the updated picking order allocation rules, so that the operation and maintenance personnel can intuitively understand through the dynamic observation diagram whether the adjusted constraint conditions and allocation guidance conditions have improved the unreasonable problem of allocating picking orders to workstations.

[0115] For example, based on the dynamic observation graph, behavioral conditions can be intervened in a timely manner to improve picking efficiency: if there is an uneven order distribution, such as picking tasks are concentrated in certain workstations or some workstations are more idle, the allocation guidance conditions and rule constraints can be dynamically adjusted; based on the adjusted rule guidance and constraint content, the scoring mechanism is dynamically updated. In this way, the results are displayed through the observation graph, and the allocation condition intervention learning is performed multiple times, which can make the picking task distribution more even, thereby achieving the purpose of improving picking efficiency.

[0116] In some embodiments, dynamic display diagrams before and after the constraint content is adjusted can be output for comparison, so that the operation and maintenance personnel can intuitively understand whether the adjusted constraint content has improved the problem of unreasonable allocation of picking orders to workstations, and whether it is necessary to further adjust the constraint content to further improve this unreasonable allocation problem. For example, before the adjustment, it can be observed through the corresponding dynamic display diagram that a part of the workstations are relatively concentratedly allocated picking orders, while another part of the workstations are relatively idle; according to this situation, the operation and maintenance personnel can adjust the allocation guidance conditions and rule constraints, such as adjusting hard constraints (such as adjusting the maximum number of picking order tasks that each workstation can accommodate, the maximum number of queue shelves that each workstation can accommodate, etc.) and soft constraint content (such as setting the priority weights of different types of picking orders, etc.). After the adjustment, it can be observed through the corresponding dynamic display diagram that this relative concentration of allocation has been significantly improved, and the allocation of picking orders to workstations is more balanced.

[0117] The specific implementation process of the embodiment of the present disclosure is further described below with reference to one example:

[0118] like Figure 5 As shown in Figure 2, the dynamic observation graphs before and after the allocation guidance conditions and rule constraints are adjusted are compared. Figure 5 In the figure, the left part is the dynamic observation diagram A before adjustment. According to the corresponding picking order allocation rules, the picking orders are allocated to the workstations, and an unbalanced allocation will occur. For example, it can be clearly observed that a large number of picking orders are relatively concentratedly allocated to the workbench corresponding to station 1, while the workbenches corresponding to stations 3 and 4 are allocated significantly fewer picking orders.

[0119] In order to improve the above problem, the operation and maintenance personnel can adjust the allocation guidance conditions and rule constraints corresponding to the picking order allocation rules, and further determine the target rule parameters corresponding to the adjusted allocation guidance conditions and rule constraints. When determining the target rule parameters, the OptaPlanner tool can be used to optimize the initially configured rule parameters, and the obtained optimized values ​​are used as the target rule parameters.

[0120] In some examples, the OptaPlanner tool scores the picking order allocation process according to the adjusted allocation guidance conditions and rule constraints and corresponding scoring rules, and obtains the rule parameters when the score meets the requirements as the optimization value, which may specifically be the optimized rule parameters.

[0121] According to the adjusted allocation guidance conditions and rule constraints and the optimized rule parameters, the picking list allocation rules are updated, and the picking lists are allocated to the corresponding workstations according to the updated picking list allocation rules. Accordingly, a dynamic observation graph B can be generated, that is, Figure 5 The right part of .

[0122] By comparing the dynamic observation graph A and the dynamic observation graph B, we can intuitively understand that the adjusted distribution is more balanced, such as Figure 5 As shown, from the comparison results, it can be seen that the workstations corresponding to station 1 are relatively concentrated in the left part, while the workstations of the four stations in the right part are more evenly distributed, indicating that the adjusted picking order allocation rule helps to improve the efficiency of picking order processing. In the next round of picking order allocation workstations, the adjusted picking order allocation rule can be used for picking order allocation.

[0123] In some examples, if by comparing the dynamic observation graph A and the dynamic observation graph B, it is found that the picking list allocation workstations are still not balanced, that is, they have not met expectations, the allocation guidance conditions and rule constraints can be adjusted again based on the picking list allocation in the dynamic observation graph B, and then the optimized rule parameters can be found through the OptaPlanner tool, and then the picking list allocation rules can be updated, and the corresponding comparison graph can be generated for observation. If it still has not met expectations, the optimization process can be continued until the appropriate picking list allocation rules are found to make the picking list allocation workstations more balanced.

[0124] By applying the solution provided by the embodiment of the present disclosure, the picking orders can be allocated to workstations more evenly, reducing the situation where some workstations are relatively concentrated with picking orders while other workstations are relatively idle. The optimized effect can also be dynamically visualized so that operation and maintenance personnel can intuitively understand the optimized effect.

[0125] Further, as Figures 1 to 5 In the specific implementation of the example shown, the present disclosure provides a picking list distribution device, such as Figure 6 As shown, the device includes: an analysis module 41, an update module 42, and a processing module 43.

[0126] An analysis module 41 is configured to analyze a rule parameter corresponding to a picking order allocation rule to obtain an optimized value of the rule parameter, wherein the picking order allocation rule is used for a picking order allocation workstation;

[0127] An updating module 42, configured to update the picking order allocation rule according to the optimization value;

[0128] The processing module 43 is configured to allocate the picking orders to corresponding workstations according to the updated picking order allocation rules.

[0129] In some embodiments, the processing module 43 is further configured to configure the constraint conditions and allocation guide conditions corresponding to the picking order allocation rule based on the picking order to be allocated and the workstation information;

[0130] Correspondingly, the analysis module 41 is specifically configured to obtain the optimization value according to the degree to which the picking order allocation result satisfies the constraint conditions and the allocation guide conditions.

[0131] In some embodiments, the analysis module 41 is further configured to score the picking order allocation results according to the degree of satisfaction of the constraint conditions and allocation guidance conditions; obtain the target picking order whose score meets the preset conditions, and determine the optimization value based on the conditional parameters used to allocate the target picking order.

[0132] In some embodiments, the analysis module 41 is specifically configured to use a preset tool to score the picking order allocation results according to the degree of satisfaction of the constraints and allocation guidance conditions, wherein the preset tool scores the allocation results of different batches of picking orders, and iteratively updates the scoring mechanism based on the picking order allocation results selected for each batch of scores.

[0133] In some embodiments, the processing module 43 is further configured to cache the batch of picking orders if the workload of the workstation is saturated when the picking orders for a batch are assigned to the workstation, and when the workload of the workstation is not saturated, assign at least one batch of picking orders that has been cached to the workstation to update the scoring mechanism of the preset tool.

[0134] In some embodiments, the processing module 43 is further configured to select the target allocation result with the highest score from the allocation results of the picking orders of the target batch to perform the picking order allocation workstation, so as to update the scoring mechanism of the preset tool.

[0135] In some embodiments, the processing module 43 is further configured to output a dynamic observation diagram, wherein the dynamic display diagram is used to display the dynamic effect of allocating the picking orders to the corresponding workstations according to the updated picking order allocation rules.

[0136] In some embodiments, the processing module 43 is further configured to adjust the constraints and allocation guidance conditions corresponding to the picking order allocation rules; the updating module 42 is further configured to update the picking order allocation rules again according to the adjusted constraints and allocation guidance conditions; the processing module 43 is further configured to allocate the picking orders to the corresponding workstations according to the again updated picking order allocation rules.

[0137] In some embodiments, the dynamic observation graph includes picking tasks for multiple orders corresponding to a picking wave, and a flow view of the picking tasks between processing flow nodes.

[0138] In some embodiments, the processing module 43 is also configured to obtain the start time and end time of the order entering each processing flow node, as well as the order type of the order; and generate the dynamic observation graph based on the start time, the end time and the order type.

[0139] In some embodiments, the processing module 43 is further configured to issue a corresponding alarm in the dynamic observation graph if the residence time of any order element in the processing flow node is greater than or equal to a preset threshold.

[0140] In some embodiments, the playback speed of the output dynamic observation graph is greater than the normal playback speed.

[0141] It should be noted that for other corresponding descriptions of the functional units involved in the picking list distribution device provided in the embodiment of the present disclosure, reference can be made to Figures 1 to 5 The corresponding description in will not be repeated here.

[0142] Based on the above Figures 1 to 5 The example shown in the figure, accordingly, the embodiment of the present disclosure also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned Figures 1 to 5 Example method shown.

[0143] Based on the above Figures 1 to 5 The example shown, accordingly, the embodiment of the present disclosure also provides a computer program product, including a computer program, which implements the above-mentioned Figures 1 to 5 Example method shown.

[0144] Based on this understanding, the technical solution of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of various implementation scenarios of the present disclosure.

[0145] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0146] Figure 7A schematic block diagram of an example electronic device 1000 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0147] like Figure 7 As shown, the device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 1002 or a computer program loaded from a storage unit 1008 to a RAM (Random Access Memory) 1003. In the RAM 1003, various programs and data required for the operation of the device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An I / O (Input / Output) interface 1005 is also connected to the bus 1004.

[0148] A number of components in the device 1000 are connected to the I / O interface 1005, including: an input unit 1006, such as a keyboard, a mouse, etc.; an output unit 1007, such as various types of displays, speakers, etc.; a storage unit 1008, such as a disk, an optical disk, etc.; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1009 allows the device 1000 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0149] The computing unit 1001 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 1001 performs the various methods and processes described above, such as a control method for a robot. For example, in some embodiments, the control method for a robot may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to execute the aforementioned robot control method in any other appropriate manner (eg, by means of firmware).

[0150] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor that may be a dedicated or general-purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0151] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0152] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0153] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0154] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0155] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0156] It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0157] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0158] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A picking list allocation method, characterized in that: include: Analyzing rule parameters corresponding to a picking order allocation rule to obtain optimized values ​​of the rule parameters, wherein the picking order allocation rule is used for a picking order allocation workstation; updating the picking list allocation rule according to the optimization value; According to the updated picking list allocation rules, the picking list is allocated to the corresponding workstation.

2. The method according to claim 1, characterized in that Before analyzing the rule parameters corresponding to the picking order allocation rule to obtain the optimized values ​​of the rule parameters, the method further includes: Based on the picking order to be assigned and the workstation information, configuring the constraint conditions and assignment guidance conditions corresponding to the picking order assignment rule; The step of analyzing the rule parameters corresponding to the picking order allocation rule to obtain the optimized values ​​of the rule parameters includes: The optimization value is obtained according to the degree to which the picking order allocation result satisfies the constraint conditions and the allocation guidance conditions.

3. The method according to claim 2, characterized in that According to the satisfaction degree of the picking list allocation result for the constraint condition and the allocation guide condition, the optimization value is obtained, including: Scoring the picking order allocation results according to the satisfaction degree of the constraint conditions and allocation guidance conditions; A target picking list with a score that meets preset conditions is obtained, and the optimization value is determined according to the conditional parameters corresponding to the allocation of the target picking list.

4. The method according to claim 3, characterized in that The step of scoring the picking order allocation result according to the satisfaction degree of the constraint conditions and the allocation guide conditions includes: Use a preset tool to score the picking order allocation results according to the degree of satisfaction of the constraints and allocation guidance conditions, wherein the preset tool scores the allocation results of different batches of picking orders, and iteratively updates the scoring mechanism based on the picking order allocation results selected for each batch score.

5. The method according to claim 4, characterized in that The method further comprises: If the task volume processed by a workstation is saturated when a batch of picking orders is assigned to a workstation, the batch of picking orders will be cached. When the task volume processed by the workstation is not saturated, at least one batch of picking orders accumulated and cached will be assigned to the workstation to update the scoring mechanism of the preset tool.

6. The method according to claim 4, characterized in that The method further comprises: The target allocation result with the highest score is selected from the allocation results of the picking orders of the target batch to perform the picking order allocation workstation, so as to update the scoring mechanism of the preset tool.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: A dynamic observation graph is output, wherein the dynamic display graph is used to display the dynamic effect of allocating the picking orders to the corresponding workstations according to the updated picking order allocation rules.

8. The method according to claim 7, characterized in that The method further comprises: Adjusting the constraint conditions and allocation guidance conditions corresponding to the picking order allocation rule; According to the adjusted constraint conditions and allocation guide conditions, the picking order allocation rules are updated again; According to the updated picking order allocation rules, the picking orders are allocated to the corresponding workstations.

9. The method according to claim 7, characterized in that: The dynamic observation graph includes picking tasks of multiple orders corresponding to picking waves, and a flow view of the picking tasks between processing flow nodes.

10. The method according to claim 9, characterized in that Creating the dynamic observation graph includes: Obtain the start time and end time of the order entering each processing flow node, as well as the order type of the order; The dynamic observation graph is generated based on the start time, the end time and the order type.

11. The method according to claim 9, characterized in that The output dynamic observation graph includes: If the duration of any order element's stay at a processing flow node is greater than or equal to a preset threshold, a corresponding alarm prompt will be issued in the dynamic observation graph.

12. The method according to any one of claims 8 to 11, characterized in that The playback speed of the dynamic observation graph is greater than the normal playback speed.

13. A picking list distribution device, characterized in that: include: an analysis module configured to analyze a rule parameter corresponding to a picking order allocation rule to obtain an optimized value of the rule parameter, wherein the picking order allocation rule is used for a picking order allocation workstation; An updating module, configured to update the picking order allocation rule according to the optimization value; The processing module is configured to allocate the picking orders to corresponding workstations according to the updated picking order allocation rules.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 12 is implemented.

15. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 12 is implemented.

16. A computer program product comprising a computer program, characterized in that The computer program implements the method according to any one of claims 1 to 12 when executed by a processor.

Images