CN114581011A - Packaging consumable recommendation method, device, equipment and storage medium - Google Patents

Packaging consumable recommendation method, device, equipment and storage medium Download PDF

Info

Publication number
CN114581011A
CN114581011A CN202210220417.3A CN202210220417A CN114581011A CN 114581011 A CN114581011 A CN 114581011A CN 202210220417 A CN202210220417 A CN 202210220417A CN 114581011 A CN114581011 A CN 114581011A
Authority
CN
China
Prior art keywords
consumable
data
commodity
packaging
order
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210220417.3A
Other languages
Chinese (zh)
Inventor
马庆吉
苏振裕
欧文祥
甘建明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Xiyin E Commerce Co ltd
Original Assignee
Nanjing Xiyin E Commerce Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing Xiyin E Commerce Co ltd filed Critical Nanjing Xiyin E Commerce Co ltd
Priority to CN202210220417.3A priority Critical patent/CN114581011A/en
Publication of CN114581011A publication Critical patent/CN114581011A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Abstract

The application discloses packaging consumable material recommendation method, device, equipment and storage medium, the application firstly converts consumable material data and order commodity data, and direct attributes of consumable materials or commodities are not directly used, so that the application range is enlarged, the algorithm calculation effect is improved, an available first consumable material set is calculated through a boxing algorithm, and then a finally recommended second consumable material set is calculated through a machine learning algorithm. With the combination of machine learning algorithm and operation and research optimization algorithm, the optimization algorithm of promptly transporting and research selects usable first consumptive material set according to the vanning algorithm, obtain the second consumptive material set of final recommendation according to the machine learning algorithm, in addition, because combine historical order consumptive material data and adopt machine learning algorithm to replace the link of current utilization consumptive material loading rate and the sequencing such as consumptive material cost, greatly promoted the rate of accuracy that the consumptive material was recommended, it selects wrong consumptive material to have solved prior art and appear easily, lead to commodity packing link inefficiency and the technical problem of extravagant consumptive material.

Description

Packaging consumable recommendation method, device, equipment and storage medium
Technical Field
The application relates to the technical field of warehouse logistics, in particular to a packaging consumable recommendation method, device, equipment and storage medium.
Background
Under the shopping environment of the E-commerce, a merchant receives shopping orders of customers at all times, the order information can be transferred to the warehouse system, and the warehouse system can pick goods and pack the goods according to the current inventory information and the order requirements and deliver the goods from the warehouse. The electronic commerce warehouse has a plurality of SKUs, and the types, the quantity, the compression properties and the like of commodities of various orders are different. The order and commodity combination is more, the order of single commodity is less, and the selection of the most appropriate consumable item for a single order is very difficult. At present, for the situation, the e-commerce determines consumables of each order by using established rules such as commodity quantity, size, class and compression property based on different logistics channels. And the packing staff inquires the rule according to the order condition so as to find out the proper consumable. And an experienced packager directly selects a proper consumable according to the order condition.
Packaging is a necessary link of warehousing business, order fulfillment efficiency can be improved by reasonably recommending packaging consumables, processing cost caused by wrong consumables is reduced, and logistics channel cost (particularly cross-border type e-commerce) is additionally generated due to improper consumable selection. In the consumable selection process, all commodities can be loaded as a primary target. If the consumable is too small for the first time, the consumable is invalidated, all commodities in the consumable need to be taken out, and new consumables are selected again to be loaded until all commodities are loaded into one consumable. In order to improve the working efficiency of packing workers, a plurality of E-commerce warehouses can work out consumable material selection rules according to logistics channels, commodity numbers, commodity quantity of each type, commodity sizes, compression attributes of commodities and the like in orders. Staff with certain packaging experience can directly select proper consumable materials according to the experience. The electronic commerce warehouse has the defects of various SKUs, various combinations of the SKUs of orders, different commodity attributes, high influence on consumable selection due to compressibility and the like, low efficiency, high logistics cost and the like.
Due to the fact that the consumable sizes of different logistics channels are different, the established rules are different. The goods such as shoes are packed in a carton box and cannot be folded, which is a primary consideration. Different orders are mainly based on the difference of the number of commodities and are generally used as secondary judgment criteria. The commodity size is mainly according to the manual identification of packer, and the commodity size probably directly influences the consumptive material and chooses the condition, and the compressibility of different commodities has great difference moreover. Based on the above factors, rules and experience can cover most cases to select a viable consumable, but there are still cases of inefficiency, consumable waste, and selection of a wrong consumable. If the problem is converted into the three-dimensional packaging problem, the data layer information such as commodity number, commodity size, commodity compressibility, commodity category and the like is fully utilized by combining the historical order consumable data, and consumable recommendation can be better performed.
Disclosure of Invention
The application provides a packaging consumable material recommendation method, device, equipment and storage medium, which are used for solving the technical problems that in the prior art, wrong selection of consumable materials easily occurs, so that the commodity packaging link is low in efficiency and the consumable materials are wasted.
The application provides a packaging consumable recommendation method in a first aspect, which comprises the following steps:
acquiring consumable data and order commodity data;
respectively converting the consumable data and the order commodity data to obtain consumable conversion data and commodity conversion data;
calculating to obtain a first consumable set through a boxing algorithm according to the consumable conversion data and the commodity conversion data;
acquiring historical order consumable data;
and calculating to obtain a second consumable set through a machine learning algorithm according to the historical order consumable data and the first consumable set, and taking the second consumable set as a packaging consumable set of the current order.
According to the method, consumable data and order commodity data are converted at first, the direct attributes of consumables or commodities are not directly used, the application range is enlarged, the algorithm calculation effect is improved, an available first consumable set is calculated through a packing algorithm, a finally recommended second consumable set is calculated through a machine learning algorithm, and the second consumable set serves as the packaging consumable set of the current order. With the combination of machine learning algorithm and operation and research optimization algorithm, the optimization algorithm of promptly transporting and research selects usable first consumptive material set according to the vanning algorithm, obtain the second consumptive material set of final recommendation according to the machine learning algorithm, in addition, because combine historical order consumptive material data and adopt machine learning algorithm to replace the link of current utilization consumptive material loading rate and the sequencing such as consumptive material cost, the rate of accuracy that the consumptive material was recommended has greatly been promoted, thereby it selects wrong consumptive material to have solved prior art and appear easily, lead to commodity packing link inefficiency and the technical problem of extravagant consumptive material.
Optionally, the calculating, according to the consumable conversion data and the commodity conversion data, a first consumable set by a packing algorithm includes:
and calculating the loading rate of each consumable part through a maximail space algorithm according to the consumable part conversion data and the commodity conversion data so as to obtain a first consumable part set.
Optionally, the calculating, according to the historical order consumable data and the first consumable set, a second consumable set by a machine learning algorithm, and taking the second consumable set as a packaging consumable set of the current order includes:
establishing a learning model according to the historical order consumable data;
and inputting the first consumable set into the learning model to obtain a second consumable set, and taking the second consumable set as a packaging consumable set of the current order.
Optionally, the machine learning algorithm is a LightGBM algorithm.
Optionally, the converting the consumable data and the order commodity data to obtain consumable conversion data and commodity conversion data respectively includes:
converting the consumable data according to the size of the consumable to obtain consumable conversion data;
and converting the order commodity data according to the material attribute of the commodity to obtain commodity conversion data.
Optionally, the converting the consumable data according to the size of the consumable to obtain consumable conversion data includes:
and converting the consumable data of the plane size into consumable conversion data of the box size.
Optionally, the converting the order commodity data according to the material attribute of the commodity to obtain commodity conversion data includes:
and converting the deformable commodity data into compressed commodity conversion data according to the commodity compression rate.
This application second aspect provides a packaging consumables recommendation device, includes:
the first acquisition unit is used for acquiring consumable data and order commodity data;
the conversion unit is used for respectively converting the consumable data and the order commodity data to obtain consumable conversion data and commodity conversion data;
the first calculating unit is used for calculating a first consumable set through a boxing algorithm according to the consumable conversion data and the commodity conversion data;
the second acquisition unit is used for acquiring historical order consumable data;
and the second calculating unit is used for calculating a second consumable set through a machine learning algorithm according to the historical order consumable data and the first consumable set, and taking the second consumable set as a packaging consumable set of the current order.
A third aspect of the present application provides an electronic device, comprising a processor and a memory storing a computer program, wherein the processor implements the steps of the packaging consumable recommendation method according to the first aspect when executing the computer program.
A fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the packaging consumable recommendation method according to the first aspect.
Drawings
Fig. 1 is a schematic flowchart of a method for recommending packaging consumables according to an embodiment of the present application;
FIG. 2 is a block diagram of a model of a packaging consumable recommendation method according to an embodiment of the present disclosure;
FIG. 3 is a schematic structural diagram of a packaging consumable recommendation device according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The embodiment of the application provides a packaging consumable material recommendation method, device, equipment and storage medium, and is used for solving the technical problems that in the prior art, wrong selection of consumable materials is easy to occur, so that the efficiency of a commodity packaging link is low and consumable materials are wasted.
In order to make the objects, features and advantages of the present invention more apparent and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the embodiments described below are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1 and fig. 2, an embodiment of the present application provides a packaging consumable recommendation method, including:
s101, consumable data and order commodity data are obtained.
And S102, respectively converting the consumable data and the order commodity data to obtain consumable conversion data and commodity conversion data.
After the consumable data and the order commodity data are obtained, since the subsequent algorithm calculation is influenced by directly adopting the obtained consumable data and the order commodity data, the consumable data and the order commodity data need to be processed in the embodiment, and the processing standard includes the type, the size information, the commodity size, the commodity category and the like according to the consumable.
And S103, calculating by a boxing algorithm according to the consumable conversion data and the commodity conversion data to obtain a first consumable set.
The available first consumable set is calculated through a boxing algorithm, namely an operation and raising optimization algorithm, and it should be noted that the consumable set is preliminarily screened out and is not taken as a finally recommended consumable set.
And S104, acquiring historical order consumable data.
It should be noted that the historical order data, that is, the historical packaging data of the goods, is used as the input data of the machine learning algorithm in this embodiment. Likewise, the first set of consumables calculated by the binning algorithm is also input data to the machine learning algorithm.
And S105, calculating to obtain a second consumable set through a machine learning algorithm according to the historical order consumable data and the first consumable set, and taking the second consumable set as a packaging consumable set of the current order.
After the first consumable set is calculated through the operation and research optimization algorithm, namely the boxing algorithm, the historical order consumables are combined, the finally recommended second consumable set is obtained through calculation of the machine learning algorithm, and therefore consumables with high loading rates can be selected, and logistics cost is reduced while commodity packaging efficiency is improved.
Further, S103 specifically is:
and calculating the loading rate of each consumable part through a maximail space algorithm according to the consumable part conversion data and the commodity conversion data so as to obtain a first consumable part set.
In the data model provided in the present embodiment, the objective of the mathematical model is to find out a consumable set that can accommodate all of the commodities in the target order from all of the selectable consumables, and to select one or more consumable sets having a relatively high loading rate.
The mathematical model is as follows:
the commodity in the order G ∈ G, G has its corresponding length (l)g) Width (w)g) High (h)g) Number (n)g) And mass (v)g) Obtaining the compression rate (alpha) according to the input datag). Aiming at consumable data M of a certain logistics channel belongs to M, the consumable can be divided into a box and a bag, and the length is (l)m) Width (w)m) High (h)m) And a bag height of 0 is subsequently converted into a box, mass (v)m). The cost of the consumable is low, so the consumable is not considered here.
Decision variable ym: whether to adopt consumable m, ym∈(0,1)；
An objective function:
maximizing consumable loading rate:
Figure BDA0003536968380000051
wherein vg is lg × wg × hg × α g,
Figure BDA0003536968380000052
vm＝lm×wm×hm；
constraint conditions are as follows:
only one consumable can be selected to be boxed,
Figure BDA0003536968380000061
the volume of the commodity cannot be larger than that of the consumable:
Figure BDA0003536968380000062
some other constraints need to be considered in the actual packaging process, such as:
each commodity needs to meet the actual consumable (e.g., maximum size constraints);
part of the goods can not be deformed (for example, the sweater can be bent, and the shoe box can not be bent);
the commodities filled with consumables cannot be overlapped in a three-dimensional space;
in the actual use process, the model cannot be used due to overlarge complexity, and a heuristic method is adopted for processing; such as the maximal space method.
The concrete flow of the maximal space algorithm is as follows:
1. and initializing parameters. Initializing consumable size (bag is converted into box), commodity size of an order and loading rate data, and respectively converting the consumable size and the loading rate data into consumable space and commodity space representation;
2. maxiaml space was chosen. Selecting the maximum available space from the consumable available spaces;
3. and selecting the loaded commodity. Finding out the best loaded commodity according to a given evaluation mode (such as maximizing the volume utilization rate);
4. the goods are loaded into the space. Loading commodities into a maximal space, cutting the original space, and placing unused space into an available space sequence of consumables, wherein the spaces can be overlapped;
5. and judging whether the algorithm is finished or not. If all the goods loading of the order is completed, or there is no available space, then execute directly 6. Otherwise, repeating the process from 2 to 4;
6. outputting the packing result of the consumable. And outputting the loading rate if all the commodities can be loaded and placed in the order, otherwise outputting the consumables which can not be loaded.
And calculating an available first consumable set and a loading rate corresponding to each consumable according to a maxiaml space algorithm. In the prior art, the loading rate, the consumable cost and the like are generally sorted, so that the consumable result recommended at last is screened out, but the consumable result recommended at last is still not accurate enough, and consumables are easily wasted.
Further, S105 includes:
s501, establishing a learning model according to historical order consumable data;
s502, inputting the first consumable set into the learning model to obtain a second consumable set, and taking the second consumable set as a packaging consumable set of the current order.
It should be noted that, according to the first consumptive material set that the calculation of vanning algorithm obtained, combine historical order consumptive material data, utilize machine learning algorithm, calculate the probability that each consumptive material was adopted to obtain the second consumptive material set of final recommendation, improve consumptive material recommendation rate of accuracy, and then improve packing link efficiency, can also avoid extravagant consumptive material. Firstly, a learning model is constructed according to historical order consumable data, and then commodity data of a current order is input, wherein an available consumable set of the current order is a first consumable set. The characteristics included therein are: consumable size, consumable channel, number of commodities ordered, commodity size and category, compressibility, and the like.
It should be noted that the machine learning algorithm employed in the present embodiment may be a LightGBM algorithm.
Further, S102 includes:
s201, converting consumable data according to the size of the consumable to obtain consumable conversion data;
s202, converting the order commodity data according to the material attribute of the commodity to obtain commodity conversion data.
Further, S201 specifically is:
and converting the consumable data of the plane size into consumable conversion data of the box size.
It should be noted that, since the consumable material adopts the boxing algorithm, all bag type consumable materials must be converted into boxes before being used in the subsequent scheme. The rules are here designed to translate the size of the bag in the consumable into the box size.
For case consumables, two dimensions lg and wg in the bag are converted into three dimensions ln g、wn gAnd hn。
Figure BDA0003536968380000071
ln g＝lg-hn g；
wn g＝wg-hn g。
Further, S202 specifically is:
and converting the deformable commodity data into compressed commodity conversion data according to the commodity compression rate.
It should be noted that the commodities can be divided into deformable commodities and non-deformable commodities, and the boxing algorithm can be only used for the non-deformable commodities, and only the deformable commodities need to be converted in this embodiment. And converting the deformable commodity into a compressed commodity according to the compression rate of the commodity. The feasible commodity is converted into a corresponding cuboid. In the boxing process, all non-deformable commodities are preferentially boxed; and the specific size of the deformable commodity is combined with the actual size of the used space to finally determine the actual size of the compressed deformable commodity in the boxing process.
According to the method, consumable data and order commodity data are converted firstly, the direct attributes of consumables or commodities are not directly used, the use range is enlarged, the algorithm calculation effect is improved, an available first consumable set is calculated through a packing algorithm, a finally recommended second consumable set is calculated through a machine learning algorithm, and the second consumable set is used as a packaging consumable set of a current order. With the combination of machine learning algorithm and operation and research optimization algorithm, the optimization algorithm of promptly transporting and research selects usable first consumptive material set according to the vanning algorithm, obtain the second consumptive material set of final recommendation according to the machine learning algorithm, in addition, because combine historical order consumptive material data and adopt machine learning algorithm to replace the link of current utilization consumptive material loading rate and the sequencing such as consumptive material cost, the rate of accuracy that the consumptive material was recommended has greatly been promoted, thereby it selects wrong consumptive material to have solved prior art and appear easily, lead to commodity packing link inefficiency and the technical problem of extravagant consumptive material.
The above is a detailed description of an embodiment of a method for recommending packaging consumables provided by the present application, and the following is a detailed description of an embodiment of a device for recommending packaging consumables provided by the present application, and a device for recommending packaging consumables described below and a method for recommending packaging consumables described above may be referred to in correspondence.
Referring to fig. 3, an embodiment of the present application provides a packaging consumable recommendation device, including:
a first acquiring unit 201 for acquiring consumable data and order commodity data.
The conversion unit 202 is configured to convert the consumable data and the order commodity data respectively to obtain consumable conversion data and commodity conversion data.
The first calculating unit 203 is configured to calculate a first consumable set through a packaging algorithm according to the consumable conversion data and the commodity conversion data.
And a second obtaining unit 204 for obtaining the historical order consumable data.
And the second calculating unit 205 is configured to calculate a second consumable set according to the historical order consumable data and the first consumable set by using a machine learning algorithm, and use the second consumable set as a packaging consumable set of the current order.
Further, the first calculating unit 203 is specifically configured to:
and calculating the loading rate of each consumable through a maximum space algorithm according to the consumable conversion data and the commodity conversion data to obtain a first consumable set.
Further, the second calculation unit 205 includes:
and the building subunit is used for building a learning model according to the historical order consumable data.
And the input subunit is used for inputting the first consumable set into the learning model to obtain a second consumable set, and taking the second consumable set as the packaging consumable set of the current order.
It should be noted that the machine learning algorithm employed in the present embodiment may be a LightGBM algorithm.
Further, the conversion unit 202 includes:
and the first conversion subunit is used for converting the consumable data according to the size of the consumable to obtain consumable conversion data.
And the second conversion subunit is used for converting the order commodity data according to the material attribute of the commodity to obtain commodity conversion data.
Further, the first converting subunit is specifically:
and converting the consumable data of the plane size into consumable conversion data of the box size.
Further, the second converting subunit is specifically:
and converting the deformable commodity data into compressed commodity conversion data according to the commodity compression rate.
According to the method, consumable data and order commodity data are converted firstly, the direct attributes of consumables or commodities are not directly used, the use range is enlarged, the algorithm calculation effect is improved, an available first consumable set is calculated through a packing algorithm, a finally recommended second consumable set is calculated through a machine learning algorithm, and the second consumable set is used as a packaging consumable set of a current order. With the combination of machine learning algorithm and operation and research optimization algorithm, the optimization algorithm of promptly transporting and research selects usable first consumptive material set according to the vanning algorithm, obtain the second consumptive material set of final recommendation according to the machine learning algorithm, in addition, because combine historical order consumptive material data and adopt machine learning algorithm to replace the link of current utilization consumptive material loading rate and the sequencing such as consumptive material cost, the rate of accuracy that the consumptive material was recommended has greatly been promoted, thereby it selects wrong consumptive material to have solved prior art and appear easily, lead to commodity packing link inefficiency and the technical problem of extravagant consumptive material.
Fig. 4 illustrates a physical structure diagram of an electronic device. As shown in fig. 4, the present invention also provides an electronic device, which may include: a processor (processor)310, a Communication Interface (Communication Interface)320, a memory (memory)330 and a Communication bus 340, wherein the processor 310, the Communication Interface 320 and the memory 330 complete the Communication with each other through the Communication bus 340. Processor 310 may invoke computer programs in memory 330 to perform the steps of a method for packaging consumable recommendation, including, for example:
acquiring consumable data and order commodity data;
respectively converting consumable data and order commodity data to obtain consumable conversion data and commodity conversion data;
calculating to obtain a first consumable set through a boxing algorithm according to the consumable conversion data and the commodity conversion data;
acquiring historical order consumable data;
and calculating to obtain a second consumable set through a machine learning algorithm according to the historical order consumable data and the first consumable set, and taking the second consumable set as the packaging consumable set of the current order.
In addition, the logic instructions in the memory 330 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
On the other hand, embodiments of the present application further provide a computer-readable storage medium, where a processor-readable storage medium stores a computer program, where the computer program is configured to cause a processor to perform the steps of the method provided in each of the above embodiments, for example, including:
acquiring consumable data and order commodity data;
respectively converting consumable data and order commodity data to obtain consumable conversion data and commodity conversion data;
calculating to obtain a first consumable set through a boxing algorithm according to the consumable conversion data and the commodity conversion data;
acquiring historical order consumable data;
and calculating to obtain a second consumable set through a machine learning algorithm according to the historical order consumable data and the first consumable set, and taking the second consumable set as a packaging consumable set of the current order.
The processor-readable storage medium can be any available medium or data storage device that can be accessed by a processor, including, but not limited to, magnetic memory (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical memory (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor memory (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND FLASH), Solid State Disks (SSDs)), etc.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or 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 solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A packaging consumable recommendation method is characterized by comprising the following steps:
acquiring consumable data and order commodity data;
respectively converting the consumable data and the order commodity data to obtain consumable conversion data and commodity conversion data;
calculating to obtain a first consumable set through a boxing algorithm according to the consumable conversion data and the commodity conversion data;
acquiring historical order consumable data;
and calculating to obtain a second consumable set through a machine learning algorithm according to the historical order consumable data and the first consumable set, and taking the second consumable set as a packaging consumable set of the current order.
2. The packaging consumable recommendation method according to claim 1, wherein the calculating a first consumable set by a packaging algorithm according to the consumable conversion data and the commodity conversion data comprises:
and calculating the loading rate of each consumable part through a maximail space algorithm according to the consumable part conversion data and the commodity conversion data so as to obtain a first consumable part set.
3. The packaging consumable recommendation method according to claim 1, wherein the calculating a second consumable set according to the historical order consumable data and the first consumable set by a machine learning algorithm, and using the second consumable set as a packaging consumable set of a current order comprises:
establishing a learning model according to the historical order consumable data;
and inputting the first consumable set into the learning model to obtain a second consumable set, and taking the second consumable set as a packaging consumable set of the current order.
4. The packaging consumable recommendation method of claim 3, wherein the machine learning algorithm is a LightGBM algorithm.
5. The packaging consumable recommendation method according to claim 1, wherein the converting the consumable data and the order commodity data to obtain consumable conversion data and commodity conversion data respectively comprises:
converting the consumable data according to the size of the consumable to obtain consumable conversion data;
and converting the order commodity data according to the material attribute of the commodity to obtain commodity conversion data.
6. The packaging consumable recommendation method according to claim 5, wherein converting the consumable data according to the size of the consumable to obtain consumable conversion data comprises:
and converting the consumable data of the plane size into consumable conversion data of the box size.
7. The packaging consumable recommendation method according to claim 5, wherein the converting the order commodity data according to the material attribute of the commodity to obtain commodity conversion data comprises:
and converting the deformable commodity data into compressed commodity conversion data according to the commodity compression rate.
8. A packaging consumable recommendation device is characterized by comprising:
the first acquisition unit is used for acquiring consumable data and order commodity data;
the conversion unit is used for respectively converting the consumable data and the order commodity data to obtain consumable conversion data and commodity conversion data;
the first calculating unit is used for calculating a first consumable set through a boxing algorithm according to the consumable conversion data and the commodity conversion data;
the second acquisition unit is used for acquiring historical order consumable data;
and the second calculation unit is used for calculating a second consumable set through a machine learning algorithm according to the historical order consumable data and the first consumable set, and taking the second consumable set as a packaging consumable set of the current order.
9. An electronic device comprising a processor and a memory storing a computer program, wherein the processor implements the steps of the packaging consumable recommendation method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of a packaging consumable recommendation method according to any one of claims 1 to 7.
CN202210220417.3A 2022-03-08 2022-03-08 Packaging consumable recommendation method, device, equipment and storage medium Pending CN114581011A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210220417.3A CN114581011A (en) 2022-03-08 2022-03-08 Packaging consumable recommendation method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210220417.3A CN114581011A (en) 2022-03-08 2022-03-08 Packaging consumable recommendation method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114581011A true CN114581011A (en) 2022-06-03

Family

ID=81779444

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210220417.3A Pending CN114581011A (en) 2022-03-08 2022-03-08 Packaging consumable recommendation method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114581011A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114742326A (en) * 2022-06-09 2022-07-12 清华大学深圳国际研究生院 Three-dimensional boxing method for irregular articles
CN117114822A (en) * 2023-10-24 2023-11-24 成都花娃网络科技有限公司 Flower material and consumable material sorting method and system

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114742326A (en) * 2022-06-09 2022-07-12 清华大学深圳国际研究生院 Three-dimensional boxing method for irregular articles
CN117114822A (en) * 2023-10-24 2023-11-24 成都花娃网络科技有限公司 Flower material and consumable material sorting method and system
CN117114822B (en) * 2023-10-24 2023-12-26 成都花娃网络科技有限公司 Flower material and consumable material sorting method and system

Similar Documents

Publication Publication Date Title
CN112001535B (en) Logistics boxing method, device, equipment and storage medium
CN110097315B (en) Container determination method, container determination device, medium, and computing apparatus
CN114581011A (en) Packaging consumable recommendation method, device, equipment and storage medium
KR101813887B1 (en) Method and apparatus for providing guide for pallet loading
US9818235B1 (en) Item dimension verification at packing
CN104246801B (en) Container selection in material process facility
CN109272135B (en) Method for packing articles and relative equipment
US20190193956A1 (en) System for dynamic pallet-build
CN109919424B (en) Container determination method and device, medium and computing equipment
US20150019387A1 (en) Box-last packaging system
CN110135960A (en) A kind of packaging recommended method, apparatus and system
CN109816303B (en) Packing material processing method and device for packing operation
US20200265381A1 (en) Return ordering system and method
CN108242018A (en) The processing method of order, apparatus and system
CN110111168A (en) Order processing method and device
TW201830180A (en) Storage location assignment device and method for storage location assignment
EP3862939A1 (en) System and method for autonomous multi-bin parcel loading system
CN109823627A (en) Method applied to electric business assembling product shipment
JP6604586B2 (en) Electronic commerce apparatus, electronic commerce method, and electronic commerce program
CN112874927B (en) Logistics packaging box type recommendation method
JP6216480B1 (en) Product picking / storage work instruction device
CN111695966B (en) Intelligent packing material recommending and boxing method and system
CN110070246B (en) Method and device for generating boxing scheme
US20160371629A1 (en) Method for cost efficient fulfillment
WO2016053747A1 (en) Box-last packaging system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination