Multi-target picking scheduling method, storage medium and electronic equipment

Abstract

The invention discloses a multi-target order picking scheduling method, a storage medium and electronic equipment. The method comprises the following steps: combining any two orders in a to-be-picked order pool to generate an order combination; calculating the similarity of order combinations; based on the similarity of the order combinations, screening out a plurality of order combinations as to-be-matched order combinations; recombining each order combination to be matched with other orders to generate a new order combination, calculating a multi-target decision value of the new order combination, and taking the new order combination with the maximum multi-target decision value as an optimal order combination; according to the technical scheme, the order combinations with similar paths are preferentially considered in the order combining process, the similarity and the damage degree of the order combinations are comprehensively considered, so that a well balanced order combining mode is achieved, negative influences on feasibility, efficiency or effect and the like of combining a plurality of orders due to the fact that a single attention is paid to the similarity are avoided, and the order combining efficiency is improved. Reasonable allocation and utilization of resources are facilitated, and reliable decision support is provided.

Description

Technical Field

[0001] The present application relates to the technical field of warehousing and logistics, and in particular to a multi-objective picking scheduling method, a storage medium and an electronic device. Background Art

[0002] With the rapid development of the e-commerce industry, the warehousing and logistics industry is facing the challenges of increasing order volume and increasing customer requirements for delivery timeliness. In warehousing operations, picking is a very critical link, and its efficiency directly affects the speed and cost of the entire logistics distribution. In the traditional picking model, a single-person single-order picking method is often adopted. In this way, the picker only handles one order at a time. Even if the order is small, it is necessary to run back and forth in the warehouse to find the location of each product, resulting in a lot of time wasted on walking distance and low picking efficiency.

[0003] In order to significantly improve the picking efficiency, it is urgent to explore the feasibility of multi-objective picking scheduling. The key points to improve customer service satisfaction, enhance the overall operation efficiency of the warehouse and reduce logistics costs are to merge the orders to be picked and minimize the total delay time of the orders. However, the current multi-objective picking scheduling scheme is usually limited to merging multiple orders with high current priority according to the similarity of the order paths to form an order combination with the "minimum distance" to maximize the picker dispatch rate (by reasonably allocating orders, so that the number of orders undertaken by the picker and the workload are close to the relative saturation state), thereby improving the picking efficiency. However, it lacks the consideration of the negative impact of the current merging behavior on the feasibility, efficiency or effect of merging multiple orders in the future from a global perspective. As a result, the currently calculated "minimum distance" order combination destroys the subsequent optimal order combination, so that the number of orders that can be merged and processed in the future is reduced, or the processing of subsequent orders becomes more complicated and costly. Summary of the invention

[0004] In view of the above problems, the present application provides a multi-objective picking scheduling method to solve the problem that the existing multi-objective picking scheduling is limited to merging orders based on the similarity of order paths and ignores the impact on subsequent orders.

[0005] To achieve the above object, the inventor provides a multi-objective picking scheduling method, which includes the following steps: Combine any two orders in the order pool to be picked to generate an order combination; Calculate the similarity of order combinations; Based on the similarity of the order combinations, several order combinations are screened out as order combinations to be matched; Each order combination to be matched is combined with other orders to generate a new order combination, and its multi-objective decision value is calculated. The new order combination with the maximum multi-objective decision value is taken as the optimal order combination.

[0006] Furthermore, the calculation of the similarity of the order combination is to calculate the similarity between two orders based on the path nodes of the picking paths of the orders.

[0007] Furthermore, the step of selecting a plurality of order combinations as order combinations to be matched based on the similarity of the order combinations includes arranging the order combinations according to their similarity, selecting the order combinations that are matched, and order combinations as the order combinations to be matched; among them, Is a positive integer.

[0008] Furthermore, the order combinations are arranged according to their similarity, and the first The steps of taking the order combinations to be matched include constructing the order combination similarity matrix, selecting the previous As the order combination to be matched.

[0009] Furthermore, the step of combining each to-be-matched order combination with other orders to generate a new order combination, calculating its multi-objective decision value, and taking the new order combination with the maximum multi-objective decision value as the optimal order combination includes the following steps: Get the current batch picking order quantity ;in, is a positive integer, and >2; For each order combination to be matched, perform the following steps: Count the number of orders in the order combination to be matched ; like , then each order combination to be matched is combined with other orders to generate a new order combination; Calculate the similarity of new order combinations; Based on the similarity of the new order combinations, several new order combinations are screened out to calculate the destructiveness of the new order combinations; According to the corresponding similarity and damage degree in the new order combination, the multi-objective decision value of the new order combination is calculated; Based on the new order combination and multi-objective decision value, the top The new order combination is used as the order combination to be matched; repeat the above steps until ; The order combination with the maximum value of the multi-objective decision value is the optimal order combination.

[0010] Furthermore, in the step of calculating the destructiveness of the new order combination, The degree of destruction of the new order combination = the number of order combinations having the previously preset number of other orders / the total number of order combinations having the previously preset number.

[0011] Furthermore, in the step of calculating the multi-objective decision value of the new order combination according to the corresponding similarity and damage degree in the new order combination, the multi-objective decision value

[0012] in, Indicates similarity, Indicates the degree of destruction, Represents the weight coefficient of similarity, The weight coefficient representing the degree of damage.

[0013] Furthermore, the weight coefficient of the similarity and the weight coefficient of the destructiveness are obtained by converting the ratio of the mean, maximum or minimum value of the similarity to the destructiveness.

[0014] A storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the multi-objective picking scheduling method.

[0015] An electronic device comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the multi-objective picking scheduling method are implemented.

[0016] Different from the existing technology, the above technical solution calculates the similarity between different order combinations, screens out the order combinations to be matched, and provides a key basis for subsequent order merging decisions, so that order combinations with similar paths are given priority in the order merging process, thereby effectively reducing the walking distance of pickers in the warehouse, reducing time costs, and improving picking efficiency; then the order combination to be matched is combined with other orders again, and the multi-objective decision value is calculated, and the similarity and destructiveness of the order combination are comprehensively considered to achieve a well-balanced order combination method, avoiding the single focus on similarity and the negative impact on the feasibility, efficiency or effect of subsequently merging multiple orders, which helps to achieve the rational allocation and utilization of resources and provides reliable decision support.

[0017] The above-mentioned records related to the invention content are only an overview of the technical solution of the present application. In order to enable ordinary technicians in the field to more clearly understand the technical solution of the present application, and then implement it according to the text of the specification and the contents recorded in the drawings, and to make the above-mentioned purpose and other purposes, features and advantages of the present application easier to understand, the following is an explanation in combination with the specific implementation mode and drawings of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings are only used to illustrate the principles, implementation methods, applications, characteristics and effects of the specific embodiments of the present invention and other related contents, and shall not be considered as limiting the present application.

[0019] In the drawings of the specification: Figure 1 It is a flowchart of the multi-objective picking scheduling method described in a specific implementation method. DETAILED DESCRIPTION

[0020] In order to explain in detail the possible application scenarios, technical principles, specific schemes that can be implemented, and the purposes and effects that can be achieved, the following is a detailed description of the specific embodiments listed in conjunction with the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present application, and are therefore only used as examples, and cannot be used to limit the scope of protection of the present application.

[0021] Reference to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The term "embodiment" appearing in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or association with other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the various technical features mentioned in the embodiments can be combined in any way to form a corresponding implementable technical solution.

[0022] Unless otherwise defined, the technical terms used in this document have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms in this document is only for describing specific embodiments and is not intended to limit this application.

[0023] In the description of this application, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" logical relationship.

[0024] In the present application, terms such as “first” and “second” are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship of quantity, priority or sequence between these entities or operations.

[0025] Without further limitations, in this application, the words "include", "comprises", "has" or other similar open-ended expressions used in sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those limited elements, but also other elements not explicitly listed, or also include elements inherent to such process, method or product.

[0026] Similar to the understanding in the Examination Guidelines, in this application, expressions such as "greater than", "less than", "exceed" and the like are understood to exclude the number itself; expressions such as "above", "below", "within" and the like are understood to include the number itself. In addition, in the description of the embodiments of this application, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups", "multiple times", etc., unless otherwise clearly and specifically limited.

[0027] In the description of the embodiments of the present application, space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present application or facilitating the reader's understanding, and do not indicate or imply that the referred device or component must have a specific position, a specific orientation, or be constructed or operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.

[0028] See also Figure 1As shown in the figure, a multi-objective picking scheduling method is applied in a warehousing and logistics environment. It aims to provide comprehensive and accurate information for order merging decisions based on comprehensive considerations of multiple related orders, thereby realizing efficient and intelligent picking operations. It mainly calculates the similarity between different order combinations, screens out order combinations to be matched, and provides a key basis for subsequent order merging decisions, so that order combinations with similar paths are given priority in the order merging process, thereby effectively reducing the walking distance of pickers in the warehouse, reducing time costs, and improving picking efficiency. The order combinations to be matched are combined again with other orders, and the multi-objective decision values ​​are calculated. The similarity and destructiveness of the order combinations are comprehensively considered to achieve a well-balanced order combination method, avoiding the single focus on similarity and the negative impact on the feasibility, efficiency or effect of the subsequent merging of multiple orders, which is helpful to realize the rational allocation and utilization of resources, provides reliable decision-making support, and makes order merging decisions more scientific and accurate, thereby effectively promoting the development of the warehousing and logistics industry towards intelligence and efficiency.

[0029] Combination Figure 1 The following provides an implementation of a multi-objective picking scheduling method, which includes the following steps: S1. Combine any two orders in the order pool to be picked to generate an order combination; S2, calculating the similarity of order combinations; S3. Based on the similarity of the order combinations, a number of order combinations are screened out as order combinations to be matched; S4. Combine each order combination to be matched with other orders again to generate a new order combination, and calculate its multi-objective decision value, and take the new order combination with the maximum multi-objective decision value as the optimal order combination.

[0030] The above-mentioned pool of orders to be picked refers to a collection of orders that have received order requests, entered the warehouse picking stage, and have not yet performed actual picking operations; the above-mentioned orders include but are not limited to order numbers, customer information, commodity lists (including commodity names, specifications, quantities, etc.), estimated delivery times, etc. Any two orders in the pool of orders to be picked are combined to generate order combinations. A nested loop can be used to traverse all orders in the order pool, where the outer loop selects the first order and the inner loop selects the second order, and the two orders are combined together. A nested loop is used to traverse all orders in the order pool, where the outer loop selects the first order and the inner loop selects the second order, and the two orders are combined together. To avoid repeated combinations (for example, the combination of order A and order B is the same as the combination of order B and order A), the inner loop starts from the next position of the current index of the outer loop, and the generated order combination is stored in the database for subsequent further analysis and processing; the above-mentioned generated order combination can be stored in a list or matrix format.

[0031] The similarity of the above order combination refers to the path similarity of the orders in the order combination. Each order has a specific picking path due to the storage of the goods in the order in the warehouse. By calculating the similarity of the order combination, the similarity of the order path in the order combination is obtained. If the path similarity of two order combinations is high, it means that there is a large overlap in their picking paths in the warehouse, which provides a key basis for the subsequent order combination decision, so that we can give priority to those order combinations with similar paths in the order combination process, thereby effectively reducing the walking distance of the pickers in the warehouse, reducing time costs, and improving picking efficiency. The similarity of the order combination can be calculated based on the similarity of the picking path direction, the similarity of the picking path nodes, etc. The following is further explained based on the similarity of the path nodes. The similarity of the order combination is calculated based on the path nodes of the order picking path. The similarity between the two orders is calculated, that is, the order path is abstracted as a node sequence, and the similarity is measured by comparing the overlap degree of the node set; specifically, the picking path of each order is represented as a node sequence, and the node can be a shelf, a cargo position, etc. in the warehouse. For example, the path of order A is , the path of order B is ; Find the intersection and union of two order path node sets. The intersection is , and the union is ; then the similarity for:

[0032] Among them, |A∩B| represents the number of path nodes in the intersection, and |A∪B| represents the number of path nodes in the union. For orders A and B, the similarity is 0.33.

[0033] Based on the similarity of order combinations, several order combinations are screened out as order combinations to be matched, which provides a key basis for subsequent order matching decisions, so that order combinations with similar paths are given priority in the order matching process. In some embodiments, a similarity threshold is pre-set, and the calculated similarity of order combinations is compared with the similarity threshold, and order combinations greater than the similarity threshold are used as order combinations to be matched. In some embodiments, order combinations are arranged according to their similarity; the order combinations with the highest order similarity are selected. order combinations as the order combinations to be matched; among them, is a positive integer; no matter what the specific numerical distribution of similarity is, a fixed number of order combinations can be selected as the order combinations to be matched according to actual needs, and the number of order combinations involved in subsequent processing can be accurately controlled, making the entire order processing process more stable and predictable. Specifically, an order combination similarity matrix can be constructed, and the calculated order combination similarities can be filled in accordingly. As the order combination to be matched. The order combination similarity matrix can display the similarity relationship between all order combinations in an intuitive table form. Through the matrix, you can quickly understand which order combinations have high similarity. The overall data structure is clear at a glance, which is convenient for comparing and sorting the similarities of various order combinations. Select the top order combinations according to the similarity. This screening method is simple and direct, and can accurately obtain the most similar order combinations.

[0034] The above-mentioned step of combining each order combination to be matched with other orders again to generate a new order combination, calculating its multi-objective decision value, and taking the new order combination with the maximum multi-objective decision value as the optimal order combination includes the following steps: Get the current batch picking order quantity ;in, is a positive integer, and >2; For each order combination to be matched, perform the following steps: Count the number of orders in the order combination to be matched ; like , then each order combination to be matched is combined with other orders to generate a new order combination; Calculate the similarity of new order combinations; Based on the similarity of the new order combinations, several new order combinations are screened out to calculate the destructiveness of the new order combinations; According to the corresponding similarity and damage degree in the new order combination, the multi-objective decision value of the new order combination is calculated; Based on the new order combination and the multi-objective decision value, several new order combinations are screened out as the order combinations to be matched; the above steps are repeated until ; The order combination with the maximum value of the multi-objective decision value is the optimal order combination.

[0035] The number of orders picked in the current batch mentioned above Refers to the number of orders currently undertaken by the picker. During the order consolidation process, the number of orders in the current batch of picking continues to play a guiding role so that the number of orders in the final order combination Equal to the number of orders currently undertaken by the picker, to maximize the picker dispatch rate. If the number of orders in the order combination to be matched is much lower than the number of orders in the current batch of picking , which means that you can continue to merge orders and combine each order combination to be matched with other orders.

[0036] The above calculation of the similarity of the new order combination is the same as the above calculation of the similarity of the order combination. The above calculation of the similarity of the new order combination can also be calculated based on the similarity of the picking path direction, the similarity of the picking path nodes, etc. The above calculation of the destructiveness of the new order combination based on the similarity of the new order combination is to give priority to those order combinations with similar paths in the subsequent continuous order merging process, thereby improving the picking efficiency. Similarly, in some embodiments, a similarity threshold is pre-set, the similarity of the calculated new order combination is compared with the similarity threshold, and the destructiveness is calculated for the new order combination greater than the similarity threshold. In some embodiments, the new order combinations are arranged according to the size of their similarity; the destructiveness is calculated for the first few new order combinations; regardless of the specific numerical distribution of the similarity, the number of order combinations participating in the subsequent processing can be accurately controlled, making the entire order processing process more stable and predictable.

[0037] The above calculation of the destructive degree of the new order combination refers to the negative impact of adding other orders to a to-be-matched order combination on the subsequent order combination. Specifically, the destructive degree of the new order combination = the number of order combinations with the previously preset number of other orders / the total number of order combinations with the previously preset number.

[0038] The above target decision value is a quantitative indicator used to comprehensively evaluate the quality of order combinations. In the order combination, it is a value calculated based on the similarity and destructiveness of the order combination, integrating the information of different targets into a single value. The higher the value, the better the order combination is after considering all the targets. For example, when calculating the multi-target decision value of an order combination, if the similarity of an order combination is high and the destructiveness is low, then its multi-target decision value will be relatively large, indicating that the order combination is a more ideal solution after comprehensively considering factors such as similarity and destructiveness.

[0039] The above-mentioned step of calculating the multi-objective decision value of the new order combination according to the corresponding similarity and damage degree in the new order combination can be calculated by weighted sum method, hierarchical analysis method, ideal solution method (TOPSIS method), etc. In some embodiments, the multi-objective decision value

[0040] in, Indicates similarity, Indicates the degree of destruction, Represents the weight coefficient of similarity, The weight coefficient representing the degree of damage.

[0041] The weight coefficient of the similarity and the weight coefficient of the destructiveness are obtained by converting the ratio of the mean, maximum or minimum value of the similarity to the destructiveness.

[0042] The present application is further explained below by taking the ratio conversion based on the mean as an example.

[0043] Calculate the ratio of the mean similarity to the mean damage

[0044] The weight coefficient of similarity is

[0045] The weight coefficient of the degree of destruction is

[0046] The above-mentioned step of screening out several new order combinations as order combinations to be matched based on the multi-objective decision values ​​of the new order combinations provides a key basis for the subsequent order matching decision, so that order combinations with high multi-objective decision values ​​are given priority in the order matching process. Similarly, in some embodiments, a target decision threshold is pre-set, the target decision value of the calculated order combination is compared with the target decision threshold, and the order combination greater than the target decision threshold is used as the order combination to be matched. In some embodiments, the order combinations are arranged according to the size of their target decision values; the order combinations before the target decision threshold is selected are selected. order combinations as the order combinations to be matched; no matter what the specific numerical distribution of the target decision value is, a fixed number of order combinations can be selected as the order combinations to be matched according to actual needs, and the number of order combinations participating in subsequent processing can be accurately controlled, making the entire order processing process more stable and predictable.

[0047] To further illustrate the present application, a specific implementation of a multi-objective picking scheduling method is provided below. The number of current batch picking orders is 3, and an order combination similarity matrix is ​​constructed based on the orders in the order pool to be picked, as shown in Table 1.

[0048] Table 1 o1 o2 o3 o4 o5 o6 o7 o8 o9 o0 o1 1 0.69 0.28 0.85 0.3 0.18 0.92 0.72 0.69 0.80 o2 0.69 1 0.21 0.59 0.11 0.52 0.03 0.57 0.24 0.11 o3 0.28 0.21 1 0.49 0.24 0.54 0.61 0.6 0.15 0.02 o4 0.85 0.59 0.49 1 0.90 0.59 0.78 0.25 0.84 0.09 o5 0.3 0.11 0.24 0.90 1 0.7 0.18 0.36 0.47 0.22 o6 0.18 0.52 0.54 0.59 0.7 1 0.86 0.2 0.33 0.93 o7 0.92 0.03 0.61 0.78 0.18 0.86 1 0.34 0.41 0.76 o8 0.72 0.57 0.6 0.25 0.36 0.2 0.34 1 0.29 0.39 o9 0.69 0.24 0.15 0 84 0.47 0.33 0.41 0.28 1 0 o0 0.80 0.11 0.02 0.09 0.22 0.93 0.76 0.39 0 1 Among them, o0-o9 represent the numbers of different orders, so the order combination is arranged as follows (o6, o0), (o1, o7), (o4, o5), (o6, o7), (o9, o4), ...; Assumptions =3, then the first three order combinations are selected as the order combinations to be matched, that is, the order combinations to be matched are: (o6, o0), (o1, o7), (o4, o5); Based on the similarity of the new order combinations, several new order combinations are screened out, as follows: (o6, o0, o7), (o6, o0, o1), (o6, o0, o7) (o1, o7, o6), (o1, o7, o4), (o1, o7, o0) (o4, o5, o1), (o4, o5, o9), (o4, o5, o0).

[0049] Among them, the similarity of the new order combination is: (o6, o0, o7) = 1.79 (o6, o0, o1) = 1.73 (o6, o0, o7) = 1.49 (o1, o7, o6) = 1.78 (o1, o7, o4) = 1.77 (o1, o7, o0) = 1.72 (o4, o5, o1) = 1.75 (o4, o5, o9) = 1.74 (o4,o5,o0)=1.68.

[0050] Taking (o6, o0, o7) as an example, calculate the degree of destructiveness of the new order combination, that is, the proportion of the o7 order in the previous preset number of order combinations.

[0051] Assume that the preset number of order combinations is: (o6, o0), (o1, o7), (o4, o5), (o6, o7), (o9, o4); but (o6, o0, o7) = 2 / 5 (o6, o0, o1) = 1 / 5 (o6, o0, o7) = 2 / 5 (o1, o7, o6) = 2 / 5 (o1, o7, o4) = 2 / 5 (o1, o7, o0) = 1 / 5 (o4, o5, o1) = 1 / 5 (o4, o5, o9) = 1 / 5 (o4, o5, o0) = 2 / 5.

[0052] Subsequently, you only need to set the parameters to obtain the corresponding multi-objective decision values. The order combination with the largest objective decision value is the optimal order combination, which will not be elaborated here.

[0053] The processor described in the embodiments of the present application can be implemented by hardware, firmware, software or a combination thereof, and can use a circuit, a single or multiple application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), a digital signal processor (Digital Signal Processor, DSP), a digital signal processing device (Digital Signal Processing Device, DSPD), a programmable logic device (Programmable Logic Device, PLD), a field programmable gate array (Field Programmable Gate Array, FPGA), a central processing unit (Central Processing Unit, CPU), a controller, a microcontroller, at least one of a microprocessor, and also includes other physical, biological or chemical structures that can achieve similar or equivalent functions to the processors listed above, such as biological neurons, quantum computing units, DNA computing units, etc., so that the processor can execute some or all of the steps in the computer program or method involved in the various embodiments of the present application, or any combination of the steps mentioned therein.

[0054] The computer program involved in the embodiment can be stored in a computer device readable storage medium, which includes but is not limited to a disk, a tape, a magnetic card, a floppy disk, a flash memory, an optical disk, an optical card, a read-only memory (ROM), a random access memory (RAM), an erasable programmable ROM (EPROM) and an electrically erasable programmable ROM (EEPROM), etc., and also includes other biological, physical or chemical structures that can achieve the same or equivalent functions as the storage media listed above, such as DNA, RNA, protein and other units with information storage capabilities. In a specific embodiment, the storage medium involved can be one of the above-mentioned media types, or a combination of the above-mentioned media types. In different embodiments, the computer program involved in the embodiment can be stored in a single medium in a centralized manner, or it can be stored in multiple media in a distributed manner. The memory containing the computer device readable storage medium can be a non-volatile memory or a random access memory. These computer device readable storage media can be built into the device, or they can be connected to the device involved in the embodiment as an external device or a part of an external device. In some embodiments, a memory with a computer device readable storage medium is deployed locally; in other embodiments, a solution of deploying the memory away from the processor may also be adopted, such as a network attached memory accessed via an RF circuit or an external port and a communication network, wherein the communication network may be the Internet, one or more intranets, a local area network (LAN), a wide area network (WLAN), a storage area network (SAN), etc., or a suitable combination thereof, as long as the computer device can access the memory. In addition, the computer program involved in the embodiment may be stored in plaintext / ciphertext form, or may be designed as training data, which may be integrated and reorganized through model training and implicitly stored in the parameter state of a deep neural network or other machine learning model.

[0055] Finally, it should be noted that although the above embodiments have been described in the specification and drawings of this application, this does not limit the scope of patent protection of this application. All technical solutions generated by replacing or modifying equivalent structures or equivalent processes based on the essential concept of this application using the contents recorded in the specification and drawings of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, are included in the scope of patent protection of this application.

Claims

1. A multi-objective picking scheduling method, characterized in that: The following steps are involved: Combine any two orders in the order pool to be picked to generate an order combination; Calculate the similarity of order combinations; Based on the similarity of the order combinations, several order combinations are screened out as order combinations to be matched; Combine each order combination to be matched with other orders to generate a new order combination, and calculate its multi-objective decision value. The new order combination with the maximum multi-objective decision value is taken as the optimal order combination. The step of combining each order combination to be matched with other orders again to generate a new order combination, calculating its multi-objective decision value, and taking the new order combination with the maximum multi-objective decision value as the optimal order combination includes the following steps: Get the current batch picking order quantity ;in, is a positive integer, and >2; For each order combination to be matched, perform the following steps: Count the number of orders in the order combination to be matched ; like , then each order combination to be matched is combined with other orders to generate a new order combination; Calculate the similarity of new order combinations; Based on the similarity of the new order combinations, several new order combinations are screened out to calculate the destructiveness of the new order combinations; According to the corresponding similarity and damage degree in the new order combination, the multi-objective decision value of the new order combination is calculated; Based on the new order combination and multi-objective decision value, the top The new order combination is used as the order combination to be matched; repeat the above steps until ; The order combination with the maximum value of the multi-objective decision value is the optimal order combination.

2. The multi-objective picking scheduling method according to claim 1, characterized in that: The calculation of the similarity of the order combination is to calculate the similarity between two orders according to the path nodes of the picking paths of the orders.

3. The multi-objective picking scheduling method according to claim 1, characterized in that: The step of selecting a plurality of order combinations as order combinations to be matched based on the similarity of the order combinations includes arranging the order combinations according to their similarity, selecting the first order combinations as the order combinations to be matched; among them, Is a positive integer.

4. The multi-objective picking scheduling method according to claim 3 is characterized in that: The order combinations are arranged according to their similarity, and the first The steps of taking the order combinations to be matched include constructing the order combination similarity matrix, selecting the previous As the order combination to be matched.

5. The multi-objective picking scheduling method according to claim 1, characterized in that: In the step of calculating the destructiveness of the new order combination, The degree of destruction of the new order combination = the number of order combinations having the previously preset number of other orders / the total number of order combinations having the previously preset number.

6. The multi-objective picking scheduling method according to claim 1, characterized in that: In the step of calculating the multi-objective decision value of the new order combination according to the corresponding similarity and damage degree in the new order combination, the multi-objective decision value ； in, Indicates similarity, Indicates the degree of destruction, Represents the weight coefficient of similarity, The weight coefficient representing the degree of damage.

7. The multi-objective picking scheduling method according to claim 6, characterized in that: The weight coefficient of the similarity and the weight coefficient of the destructiveness are obtained by converting the ratio of the mean, maximum or minimum value of the similarity to the destructiveness.

8. A storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the multi-objective picking scheduling method according to any one of claims 1 to 7 are implemented.

9. An electronic device, characterized in that It includes a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the multi-objective picking scheduling method according to any one of claims 1 to 7 are implemented.

Images