A packaging consumables recommendation method, device, equipment and storage medium
By converting and analyzing the consumables and order product data of e-commerce warehouses, combining packing algorithms and machine learning algorithms, the problem of inefficient selection of consumables in e-commerce warehouses is solved, more accurate consumable recommendations are achieved, and waste and costs are reduced .
Patent Information
- Application Number
- CN202210220417.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-03-08
- Publication Date
- 2024-12-27
- Estimated Expiration
- 2042-03-08
AI Technical Summary
In the e-commerce shopping environment, e-commerce warehouses have a wide variety of SKUs and large differences in the types, quantity, size and compression attributes of order products, resulting in inefficient selection of packaging consumables, which is prone to selection of wrong consumables and waste.
By obtaining consumables and order product data, converting them, using packing algorithms and machine learning algorithms, combining historical order consumable data, the most suitable packaging consumables collection is calculated to improve the accuracy of consumables recommendations.
It improves the efficiency of the packaging process, reduces consumable waste and logistics costs, and improves the accuracy of consumable recommendations.
Smart Images
Figure CN114581011B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of warehousing and logistics technology, and in particular to a packaging consumables recommendation method, device, equipment and storage medium. Background Art
[0002] In the e-commerce shopping environment, merchants receive shopping orders from customers all the time. These order information will flow to the warehouse system, and the warehouse system will pick, pack and ship out the goods according to the current inventory information and order requirements. There are many types of SKUs in e-commerce warehouses, and there are differences in the types, quantities, and compression properties of goods in each order. There are many combinations of order goods, and fewer orders for single items, which makes it very difficult to select the most suitable consumables for a single order. At present, e-commerce companies have formulated rules based on different logistics channels, using the quantity, size, category, and compression properties of goods to determine the consumables for each order. Packing employees query the rules based on the order situation to find the appropriate consumables. Experienced packers directly select the appropriate consumables based on the order situation.
[0003] Packaging is an essential part of warehousing business. Reasonable recommendation of packaging consumables can improve order fulfillment efficiency, reduce the processing costs caused by using the wrong consumables, and the additional logistics channel costs caused by improper selection of consumables (especially for cross-border e-commerce). In the process of selecting consumables, the primary goal can be to fit all the goods. If the consumable selected for the first time is too small, the consumable will be invalid. All the goods in the consumable need to be taken out and new consumables need to be selected and loaded again until all the goods are loaded into one consumable. In order to improve the work efficiency of packers, many e-commerce warehouses will formulate consumable selection rules based on the logistics channels, number of goods, number of goods in each category, product size, and compression properties of goods in the order. Employees with certain packaging experience will directly select suitable consumables based on experience. E-commerce warehouses have a wide variety of SKUs, a wide variety of SKU combinations in orders, different product attributes, and compressibility have a great impact on the selection of consumables, which has disadvantages such as low efficiency and high logistics costs.
[0004] Since the sizes of consumables in different logistics channels vary, the rules formulated vary to a certain extent. Shoes and other products are packaged in cardboard boxes and cannot be folded, which will be the primary consideration. Different orders are mainly based on the number of goods, which is generally used as a secondary judgment criterion. The size of the goods is mainly based on manual identification by the packer, and the size of the goods may directly affect the selection of consumables, and the compressibility of different goods varies greatly. Based on the above factors, rules and experience can cover most cases to select feasible consumables, but there are still cases of inefficiency, waste of consumables and wrong selection of consumables. If it is converted into a three-dimensional packing problem, combined with historical order consumables data, and full use of data-level information, such as the number of goods, size of goods, compressibility of goods, and category of goods, better consumables recommendations can be made. Summary of the invention
[0005] The present application provides a packaging consumables recommendation method, device, equipment and storage medium, which are used to solve the technical problem that the prior art easily leads to wrong selection of consumables, resulting in low efficiency and waste of consumables in the product packaging process.
[0006] The first aspect of the present application provides a packaging consumables recommendation method, comprising:
[0007] Obtain consumables data and order product data;
[0008] The consumables data and the order product data are converted respectively to obtain consumables conversion data and product conversion data;
[0009] Obtaining a first consumables set by calculating through a packing algorithm according to the consumables conversion data and the commodity conversion data;
[0010] Get historical order consumables data;
[0011] According to the historical order consumables data and the first consumables set, a second consumables set is calculated by a machine learning algorithm, and the second consumables set is used as the packaging consumables set for the current order.
[0012] This application first converts the consumables data and order product data instead of directly using the direct attributes of the consumables or products. This not only expands the scope of use but also improves the effect of the algorithm calculation. Then, the available first consumables set is calculated through the packing algorithm, and then the final recommended second consumables set is calculated through the machine learning algorithm, and the second consumables set is used as the packaging consumables set for the current order. The machine learning algorithm and the operations optimization algorithm are combined to select the available first consumables set according to the packing algorithm, i.e., the operations optimization algorithm, and obtain the final recommended second consumables set according to the machine learning algorithm. In addition, since the consumables data of historical orders are combined and the machine learning algorithm is used to replace the existing sorting process using consumables loading rate and consumables cost, the accuracy of consumables recommendation is greatly improved, thereby solving the technical problem that the prior art easily selects the wrong consumables, resulting in inefficiency and waste of consumables in the product packaging process.
[0013] Optionally, the obtaining the first consumables set by calculating through a packing algorithm according to the consumables conversion data and the commodity conversion data includes:
[0014] According to the consumable conversion data and the commodity conversion data, the loading rate of each consumable is calculated by using a maximal space algorithm to obtain a first consumable set.
[0015] Optionally, the obtaining a second consumables set by calculating the historical order consumables data and the first consumables set through a machine learning algorithm, and using the second consumables set as the packaging consumables set for the current order includes:
[0016] Building a learning model based on the historical order consumables data;
[0017] The first consumables set is input into the learning model to obtain a second consumables set, and the second consumables set is used as the packaging consumables set of the current order.
[0018] Optionally, the machine learning algorithm is a LightGBM algorithm.
[0019] Optionally, the converting the consumables data and the order product data respectively to obtain consumables conversion data and product conversion data includes:
[0020] Convert the consumables data according to the size of the consumables to obtain consumables conversion data;
[0021] The order product data is converted according to the material attributes of the product to obtain product conversion data.
[0022] Optionally, converting the consumable data according to the size of the consumable to obtain consumable conversion data includes:
[0023] The consumables data of the plane size is converted into consumables conversion data of the box size.
[0024] Optionally, converting the order product data according to the material attributes of the product to obtain product conversion data includes:
[0025] According to the compression rate of the product, the deformable product data is converted into compressed product conversion data.
[0026] A second aspect of the present application provides a packaging consumables recommendation device, comprising:
[0027] A first acquisition unit, used to acquire consumables data and order product data;
[0028] A conversion unit, used to convert the consumables data and the order commodity data respectively to obtain consumables conversion data and commodity conversion data;
[0029] A first calculation unit, configured to calculate a first consumables set by a packing algorithm according to the consumables conversion data and the commodity conversion data;
[0030] A second acquisition unit, used to acquire historical order consumables data;
[0031] The second calculation unit is used to calculate a second consumable set through a machine learning algorithm based on the historical order consumable data and the first consumable set, and use the second consumable set as the packaging consumable set of the current order.
[0032] A third aspect of the present application provides an electronic device, comprising a processor and a memory storing a computer program, wherein when the processor executes the computer program, the steps of the packaging consumables recommendation method as described in the first aspect are implemented.
[0033] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the packaging consumables recommendation method as described in the first aspect are implemented. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] Figure 1 A schematic diagram of a process for recommending packaging consumables provided in an embodiment of the present application;
[0035] Figure 2 A model block diagram of the packaging consumables recommendation method provided in an embodiment of the present application;
[0036] Figure 3 A schematic diagram of the structure of a packaging consumables recommendation device provided in an embodiment of the present application;
[0037] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0038] The embodiments of the present application provide a packaging consumables recommendation method, device, equipment and storage medium, which are used to solve the technical problem that the prior art easily leads to wrong selection of consumables, resulting in low efficiency and waste of consumables in the product packaging process.
[0039] In order to make the purpose, features, and advantages of the invention of this application more obvious and easy to understand, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the embodiments described below are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0040] See also Figure 1 and Figure 2 , the present application embodiment provides a packaging consumables recommendation method, comprising:
[0041] S101, obtaining consumables data and order product data.
[0042] S102 , respectively convert the consumables data and the order product data to obtain consumables conversion data and product conversion data.
[0043] After obtaining the consumables data and order product data, since directly using the obtained consumables data and order product data will affect the subsequent algorithm calculations, this embodiment needs to process the consumables data and order product data, and the processing standards include the type of consumables, size information, product size and product category, etc.
[0044] S103: Obtain a first consumables set by calculating through a packing algorithm according to the consumables conversion data and the commodity conversion data.
[0045] The first available consumables set is calculated by a packing algorithm, namely, an operations optimization algorithm. It should be noted that this is a preliminarily screened consumables set, and is not a final recommended consumables set.
[0046] S104, obtaining historical order consumables data.
[0047] It should be noted that the historical order data, that is, the historical packaging data of the goods, is the input data of the machine learning algorithm in this embodiment. Similarly, the first consumables set calculated by the packing algorithm is also the input data of the machine learning algorithm.
[0048] S105. According to the historical order consumables data and the first consumables set, a second consumables set is calculated by a machine learning algorithm, and the second consumables set is used as the packaging consumables set of the current order.
[0049] After calculating the first set of consumables through the operations optimization algorithm, namely the packing algorithm, it is combined with the historical order consumables and the final recommended second set of consumables is calculated through the machine learning algorithm. This allows consumables with a higher loading rate to be selected to improve product packaging efficiency while reducing logistics costs.
[0050] Further, S103 is specifically:
[0051] According to the consumables conversion data and the commodity conversion data, the loading rate of each consumable is calculated by using the maximal space algorithm to obtain a first consumables set.
[0052] It should be noted that the following is a data model provided by this implementation. The goal of this mathematical model is to find a consumables set that can hold all the goods of the target order from all optional consumables, and select one or more consumables sets with a relatively high loading rate.
[0053] The mathematical model is as follows:
[0054] The item g∈G in the order has its corresponding length (l g)、Width(w g ), high (h g ), quantity (n g ) and quality (v g ), and obtain the compression rate (α g ). For the consumables data m∈M of a logistics channel, consumables can be divided into boxes and bags, length (l m )Width(w m )High(h m ), and the bag has a height of 0 and will be converted to a box later, and the mass (v m ). The cost of consumables is low, so they are not considered here.
[0055] Decision variable y m : Whether to use consumables m, y m ∈(0,1);
[0056] Objective function:
[0057] Maximize the material loading rate:
[0058]
[0059] Among them, vg = lg × wg × hg × αg, v m = l m × m ×h m ;
[0060] Constraints:
[0061] Only one consumable can be selected for packing.
[0062] The volume of the product cannot be larger than the volume of the consumables:
[0063] In the actual packaging process, some other constraints need to be considered, such as:
[0064] Each product must meet the actual consumables that can be loaded (such as maximum size constraints);
[0065] Some products cannot be deformed (e.g. sweaters can be bent, but shoe boxes cannot);
[0066] The products loaded with consumables cannot overlap in three-dimensional space;
[0067] In actual use, the above model cannot be used due to its excessive complexity, and a heuristic method will be used to process it, such as the maximal space method.
[0068] The specific process of the maximal space algorithm is as follows:
[0069] 1. Initialize parameters. Initialize the consumable size (convert bags to boxes), the product size of the order, and the loading rate data, and convert them into consumable space and product space representation respectively;
[0070] 2. Select maxiaml space. In the available space of consumables, select the maximum available space;
[0071] 3. Select the goods to be loaded. According to the given evaluation method (such as maximizing volume utilization), find the best goods to be loaded;
[0072] 4. Load the goods into the space. Load the goods into the maximal space, cut the original space, and put the unused space into the available space sequence of consumables. The spaces can overlap;
[0073] 5. Determine whether the algorithm is finished. If all the items of the order have been loaded, or there is no free space, go directly to step 6. Otherwise, repeat the process of 2-4;
[0074] 6. Output the packing result of the consumables. If all the goods in the order can be packed, output the loading rate, otherwise output that the consumables cannot be loaded.
[0075] The available first consumables set and the corresponding loading rate of each consumable are calculated according to the maxiaml space algorithm. The prior art usually sorts the loading rate and consumables cost, etc., to filter out the final recommended consumables result, but the final recommended consumables result is still not accurate enough and is prone to waste consumables.
[0076] Further, S105 includes:
[0077] S501, building a learning model based on historical order consumables data;
[0078] S502: Input the first consumables set into the learning model to obtain a second consumables set, and use the second consumables set as the packaging consumables set for the current order.
[0079] It should be noted that the first consumables set calculated by the packing algorithm is combined with the historical order consumables data, and the machine learning algorithm is used to calculate the probability of each consumable being adopted, so as to obtain the final recommended second consumables set, improve the accuracy of consumables recommendation, and then improve the efficiency of the packaging process, and avoid wasting consumables. First, it is necessary to build a learning model based on the historical order consumables data, and then input the product data of the current order. The available consumables set of the current order is the first consumables set. The features included include: consumable size, consumable channel, number of order items, product size and category, and compression rate.
[0080] It should be noted that the machine learning algorithm used in this embodiment may be the LightGBM algorithm.
[0081] Further, S102 includes:
[0082] S201, converting the consumables data according to the size of the consumables to obtain consumables conversion data;
[0083] S202: Convert the order product data according to the material attributes of the product to obtain product conversion data.
[0084] Furthermore, S201 is specifically:
[0085] Convert the consumables data of the plane size into the consumables data of the box size.
[0086] It should be noted that since the consumables adopt the box packing algorithm, all bag-type consumables must be converted to boxes before they can be used in subsequent solutions. Here, a rule is designed to convert the size of the bag in the consumables into the size of the box.
[0087] For box consumables, convert the two dimensions lg and wg in the bag into three dimensions l n g 、w n g and h n .
[0088]
[0089] l n g = l g -h n g ;
[0090] w n g =w g -h n g .
[0091] Further, S202 is specifically:
[0092] According to the compression rate of the product, the deformable product data is converted into compressed product conversion data.
[0093] It should be noted that the goods can be divided into deformable goods and non-deformable goods, and the packing algorithm can only be used for non-deformable goods. In this embodiment, only the deformable goods need to be converted. According to the compression rate of the goods, the deformable goods are converted into compressed goods. The deformable goods are converted into corresponding cuboids. In the packing process, all non-deformable goods will be packed first; and the specific size of the deformable goods will be determined in the packing process in combination with the actual size of the space used to finally determine its actual size after compression.
[0094] This embodiment first converts the consumables data and order product data, instead of directly using the direct attributes of the consumables or products, which not only expands the scope of use but also improves the effect of algorithm calculation. Then, the available first consumables set is calculated through the packing algorithm, and then the final recommended second consumables set is calculated through the machine learning algorithm, and the second consumables set is used as the packaging consumables set for the current order. The machine learning algorithm and the operations optimization algorithm are combined, and the available first consumables set is selected according to the packing algorithm, i.e., the operations optimization algorithm, and the final recommended second consumables set is obtained according to the machine learning algorithm. In addition, since the historical order consumables data is combined and the machine learning algorithm is used to replace the existing sorting process using consumables loading rate and consumables cost, the accuracy of consumables recommendation is greatly improved, thereby solving the technical problem that the prior art is prone to wrong selection of consumables, resulting in low efficiency and waste of consumables in the product packaging process.
[0095] The above is a detailed description of an embodiment of a packaging consumables recommendation method provided in the present application. The following is a detailed description of an embodiment of a packaging consumables recommendation device provided in the present application. The packaging consumables recommendation device described below and the packaging consumables recommendation method described above can be referenced to each other.
[0096] See also Figure 3 , an embodiment of the present application provides a packaging consumables recommendation device, comprising:
[0097] The first acquisition unit 201 is used to acquire consumable material data and order product data.
[0098] The conversion unit 202 is used to convert the consumables data and the order commodity data respectively to obtain consumables conversion data and commodity conversion data.
[0099] The first calculation unit 203 is used to calculate and obtain a first consumables set through a packing algorithm according to the consumables conversion data and the commodity conversion data.
[0100] The second acquisition unit 204 is used to acquire historical order consumables data.
[0101] The second calculation unit 205 is used to calculate the second consumables set through a machine learning algorithm according to the historical order consumables data and the first consumables set, and use the second consumables set as the packaging consumables set of the current order.
[0102] Further, the first calculation unit 203 is specifically used for:
[0103] According to the consumables conversion data and the commodity conversion data, the loading rate of each consumable is calculated by using the maximal space algorithm to obtain a first consumables set.
[0104] Further, the second calculation unit 205 includes:
[0105] A subunit is constructed to build a learning model based on historical order consumables data.
[0106] The input subunit is used to input the first consumables set into the learning model to obtain the second consumables set, and use the second consumables set as the packaging consumables set of the current order.
[0107] It should be noted that the machine learning algorithm used in this embodiment may be the LightGBM algorithm.
[0108] Further, the conversion unit 202 includes:
[0109] The first conversion subunit is used to convert the consumables data according to the size of the consumables to obtain consumables conversion data.
[0110] The second conversion subunit is used to convert the order product data according to the material attributes of the product to obtain product conversion data.
[0111] Furthermore, the first conversion subunit is specifically:
[0112] Convert the consumables data of the plane size into the consumables data of the box size.
[0113] Furthermore, the second conversion subunit is specifically:
[0114] According to the compression rate of the product, the deformable product data is converted into compressed product conversion data.
[0115] This embodiment first converts the consumables data and order product data, instead of directly using the direct attributes of the consumables or products, which not only expands the scope of use but also improves the effect of algorithm calculation. Then, the available first consumables set is calculated through the packing algorithm, and then the final recommended second consumables set is calculated through the machine learning algorithm, and the second consumables set is used as the packaging consumables set for the current order. The machine learning algorithm and the operations optimization algorithm are combined, and the available first consumables set is selected according to the packing algorithm, i.e., the operations optimization algorithm, and the final recommended second consumables set is obtained according to the machine learning algorithm. In addition, since the historical order consumables data is combined and the machine learning algorithm is used to replace the existing sorting process using consumables loading rate and consumables cost, the accuracy of consumables recommendation is greatly improved, thereby solving the technical problem that the prior art is prone to wrong selection of consumables, resulting in low efficiency and waste of consumables in the product packaging process.
[0116] Figure 4 The following is a schematic diagram of the physical structure of an electronic device. Figure 4 As shown, the present invention further provides an electronic device, which may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call a computer program in the memory 330 to execute the steps of a packaging consumables recommendation method, for example including:
[0117] Obtain consumables data and order product data;
[0118] The consumables data and the order product data are converted respectively to obtain consumables conversion data and product conversion data;
[0119] Obtaining a first consumables set by calculating through a packing algorithm according to the consumables conversion data and the commodity conversion data;
[0120] Get historical order consumables data;
[0121] According to the historical order consumables data and the first consumables set, a second consumables set is calculated by a machine learning algorithm, and the second consumables set is used as the packaging consumables set for the current order.
[0122] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0123] On the other hand, an embodiment of the present application further provides a computer-readable storage medium, wherein the processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the steps of the methods provided in the above embodiments, for example, including:
[0124] Obtain consumables data and order product data;
[0125] The consumables data and the order product data are converted respectively to obtain consumables conversion data and product conversion data;
[0126] Obtaining a first consumables set by calculating through a packing algorithm according to the consumables conversion data and the commodity conversion data;
[0127] Get historical order consumables data;
[0128] According to the historical order consumables data and the first consumables set, a second consumables set is calculated by a machine learning algorithm, and the second consumables set is used as the packaging consumables set for the current order.
[0129] The processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.
[0130] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0131] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A packaging consumables recommendation method, characterized in that: include: Obtain consumables data and order product data; The consumables data and the order product data are converted respectively to obtain consumables conversion data and product conversion data; Obtaining a first consumables set by calculating through a packing algorithm according to the consumables conversion data and the commodity conversion data; Get historical order consumables data; According to the historical order consumables data and the first consumables set, a second consumables set is calculated by a machine learning algorithm, and the second consumables set is used as the packaging consumables set of the current order; The step of calculating the first consumables set by a packing algorithm according to the consumables conversion data and the commodity conversion data includes: According to the consumable conversion data and the commodity conversion data, the loading rate of each consumable is calculated by using a maximal space algorithm to obtain a first consumable set; Wherein, the maximal space algorithm includes: Step 1, initializing the consumable size, the product size of the order and the loading rate data, converting the consumable size into the consumable space and converting the product size into the product space; Step 2, selecting the maximum available space in the consumable space; Step 3, selecting a target to load goods into the goods space according to a preset evaluation method and the goods space, wherein the evaluation method includes maximizing volume utilization; Step 4, loading the target product into the consumable space, cutting the unused space, and placing the unused space into the consumable available space sequence; Step 5: If all the goods of the order have been packed or there is no available space, proceed to step 6; otherwise, repeat the process of steps 2-4; Step 6, output the packing result of the current consumables. If all the goods of the order are packed, output the loading rate corresponding to the current consumables, otherwise output that the current consumables cannot be loaded.
2. The packaging consumables recommendation method according to claim 1, characterized in that: The step of calculating a second consumables set by a machine learning algorithm based on the historical order consumables data and the first consumables set, and using the second consumables set as a packaging consumables set for the current order includes: Building a learning model based on the historical order consumables data; The first consumables set is input into the learning model to obtain a second consumables set, and the second consumables set is used as the packaging consumables set of the current order.
3. The packaging consumables recommendation method according to claim 2, characterized in that: The machine learning algorithm is the LightGBM algorithm.
4. The packaging consumables recommendation method according to claim 1, characterized in that: The step of converting the consumables data and the order commodity data respectively to obtain consumables conversion data and commodity conversion data includes: Convert the consumables data according to the size of the consumables to obtain consumables conversion data; The order product data is converted according to the material attributes of the product to obtain product conversion data.
5. The packaging consumables recommendation method according to claim 4, characterized in that: The step of converting the consumables data according to the size of the consumables to obtain consumables conversion data includes: The consumables data of the plane size is converted into consumables conversion data of the box size.
6. The packaging consumables recommendation method according to claim 4, characterized in that: The converting the order product data according to the material attributes of the product to obtain product conversion data includes: According to the compression rate of the product, the deformable product data is converted into compressed product conversion data.
7. A packaging consumables recommendation device, characterized in that: include: A first acquisition unit, used to acquire consumables data and order product data; A conversion unit, used to convert the consumables data and the order commodity data respectively to obtain consumables conversion data and commodity conversion data; A first calculation unit, configured to calculate a first consumables set by a packing algorithm according to the consumables conversion data and the commodity conversion data; A second acquisition unit, used to acquire historical order consumables data; The second calculation unit is used to calculate a second consumable set through a machine learning algorithm based on the historical order consumable data and the first consumable set, and use the second consumable set as the packaging consumable set of the current order.
8. An electronic device comprising a processor and a memory storing a computer program, characterized in that: When the processor executes the computer program, the steps of the packaging consumables recommendation method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the packaging consumables recommendation method according to any one of claims 1 to 6 are implemented.