A corrugated box material generation method, device, storage medium and terminal

Abstract

The present invention discloses a material generation method, device, storage medium and terminal for a corrugated paper box, the method comprising: obtaining product parameters of a corrugated paper box to be manufactured; inputting the product parameters of the corrugated paper box to be manufactured into a pre-trained corrugated paper box material model, outputting multiple material sequences corresponding to the corrugated paper box to be manufactured and the confidence of each material sequence; the corrugated paper box material model is constructed based on an Apriori algorithm and a collaborative filtering algorithm; based on the confidence of each material sequence, a target material sequence is determined from multiple material sequences, and the target material sequence is determined as the material sequence of the corrugated paper box to be manufactured. Since the present application adopts the Apriori algorithm and the collaborative filtering algorithm to model the historical carton material data, the model can automatically generate an accurate material sequence according to the product parameters of the corrugated paper box to be manufactured, thereby improving the rationality and accuracy of the material generation of the corrugated paper box, and thus greatly reducing the raw material cost and labor cost.

Description

Technical Field

[0001] The present invention relates to the technical field of machine learning, and particularly relates to a method, device, storage medium and terminal for generating the material configuration of a corrugated cardboard box. Background Art

[0002] Paper packaging is the largest sub-industry in the packaging industry. The paper packaging industry has broad development space and is in a stage of rapid development. Energy conservation and efficiency improvement are the goals pursued by enterprises, and among them, what materials are selected for cardboard box production is a particularly important link.

[0003] Currently, before the production of cardboard boxes, sales and order review personnel in paper packaging enterprises will, according to the requirements of customers for parameters such as the corrugation type, compressive strength, and burst strength of products, manually select the materials for the cardboard box products of the production order based on experience. The key here is to consider the quality and cost of the cardboard box as a whole and minimize the cost as much as possible while ensuring the quality. However, when selecting materials based on traditional manual experience, there may be situations where the selected materials are unreasonable. The selected materials do not meet the standards, resulting in reduced cardboard box strength, poor burst resistance, poor moisture resistance, and poor product quality; or the performance of the selected materials is too high, which will greatly increase the material cost of the cardboard box. In addition, once the selected materials are unreasonable, it is necessary to rework and select materials again, which is time-consuming and laborious and affects the normal production of the order. The method of judging cardboard box materials based on human experience has the following defects: (1) It requires a large amount of business and production experience; (2) A large number of tests are required when selecting the base paper formula of the cardboard box. If the test results are unqualified, the formula needs to be changed and the experiment needs to be repeated, which requires a large amount of human and time costs; (3) It is inevitable for humans to miss real-time cardboard box material information. Summary of the Invention

[0004] Embodiments of the present application provide a method, device, storage medium and terminal for generating the material configuration of a corrugated cardboard box. To provide a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary part is not a general review, nor is it intended to identify key / important constituent elements or delineate the protection scope of these embodiments. Its sole purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0005] In a first aspect, embodiments of the present application provide a method for generating the material configuration of a corrugated cardboard box, the method including:

[0006] Obtain the product parameters of the corrugated cardboard box to be manufactured;

[0007] Input the product parameters of the corrugated cardboard box to be manufactured into a pre-trained corrugated cardboard box material configuration model, and output multiple material configuration sequences corresponding to the corrugated cardboard box to be manufactured and the confidence level of each material configuration sequence; wherein, the corrugated cardboard box material configuration model is constructed based on the Apriori algorithm and the collaborative filtering algorithm;

[0008] Determine a target material sequence from multiple material sequences based on the confidence of each material sequence, and determine the target material sequence as the material sequence of the corrugated cardboard box to be manufactured.

[0009] Optionally, determining a target material sequence from multiple material sequences based on the confidence of each material sequence includes:

[0010] Judging one by one whether the confidence of each material sequence is greater than or equal to a preset confidence threshold, and generating multiple judgment results;

[0011] Determine at least one target material sequence from multiple material sequences according to multiple judgment results;

[0012] Receive a selection instruction for at least one target material sequence, and determine the target material sequence from at least one target material sequence according to the selection instruction.

[0013] Optionally, determining at least one target material sequence from multiple material sequences according to multiple judgment results includes:

[0014] Obtain the judgment results less than the preset confidence threshold from multiple judgment results;

[0015] Eliminate the material sequences corresponding to the judgment results less than the preset confidence threshold from multiple material sequences;

[0016] Generate at least one target material sequence.

[0017] Optionally, generating a pre-trained corrugated cardboard box material model according to the following steps includes:

[0018] Obtain and preprocess the historical orders and product data of historical corrugated cardboard boxes to generate a cardboard box material dataset;

[0019] Create a corrugated cardboard box material model using the Apriori algorithm;

[0020] Input the cardboard box material dataset into the corrugated cardboard box material model to obtain an option set;

[0021] Calculate the support degree of each data item in the option set;

[0022] Compare the support degree of each data item with a preset threshold, and determine the data items with a support degree greater than the preset threshold as frequent item sets;

[0023] When the number of frequent items in the frequent item set is 1, generate an Apriori algorithm model;

[0024] Train and generate a collaborative filtering algorithm model based on a preset number of historical corrugated cardboard box data;

[0025] Merge the Apriori algorithm model and the collaborative filtering algorithm model to generate a pre-trained corrugated box material matching model.

[0026] Optionally, when the number of frequent items in the frequent item set is 1, generate the Apriori algorithm model, including:

[0027] When the number of frequent items in the frequent item set is not 1, traverse and splice each frequent item in the frequent item set to obtain a splicing option set;

[0028] Calculate the support degree of each data item in the splicing option set;

[0029] Continue to execute the step of comparing the support degree of each data item with a preset threshold until the number of item quantities in the frequent item set is 1, and generate the Apriori algorithm model.

[0030] Optionally, train and generate a collaborative filtering algorithm model based on a preset quantity of historical corrugated box data, including:

[0031] Collect a preset quantity of historical corrugated box data;

[0032] Use the collaborative filtering algorithm to construct a corrugated box material matching model, and input the historical corrugated box data into the corrugated box material matching model to obtain the product parameters of multiple similar first corrugated boxes;

[0033] Obtain the materials of the product parameters of each similar corrugated box;

[0034] Calculate the similarity matrix between multiple similar corrugated boxes according to the materials of the product parameters of each similar corrugated box, and generate the similarity matrix;

[0035] When the similarity matrix is generated, generate a pre-trained corrugated box material matching model.

[0036] Optionally, input the product parameters of the corrugated box to be manufactured into the pre-trained corrugated box material matching model, and output multiple material sequences corresponding to the corrugated box to be manufactured and the confidence level of each material sequence, including:

[0037] Input the product parameters of the corrugated box to be manufactured into the Apriori algorithm model to generate a first quantity of material sequences and the confidence level of each first material sequence;

[0038] Output a first quantity of material sequences and the confidence level of each first material sequence;

[0039] Input the product parameters of the corrugated box to be manufactured into the collaborative filtering algorithm model to obtain the product parameters of multiple similar second corrugated boxes; among them, the quantity of the product parameters of multiple similar second corrugated boxes is less than the quantity of the product parameters of the first corrugated box;

[0040] Obtain multiple materials for each second corrugated cardboard box from the product parameters of multiple similar second corrugated cardboard boxes, and generate a material set;

[0041] Obtain the existing materials of the product parameters of the corrugated cardboard box to be manufactured;

[0042] Exclude the existing materials from the material set to generate a second number of material sequences;

[0043] Calculate the confidence level of each material sequence in the second number of material sequences;

[0044] Output the second number of material sequences and the confidence level of each second material sequence.

[0045] In a second aspect, an embodiment of the present application provides a device for generating materials for a corrugated cardboard box. The device includes:

[0046] A product parameter acquisition module, configured to acquire the product parameters of the corrugated cardboard box to be manufactured;

[0047] A parameter output module, configured to input the product parameters of the corrugated cardboard box to be manufactured into a pre-trained corrugated cardboard box material model, and output a plurality of material sequences corresponding to the corrugated cardboard box to be manufactured and the confidence level of each material sequence;

[0048] Wherein, the corrugated cardboard box material model is constructed based on the Apriori algorithm and the collaborative filtering algorithm;

[0049] A material sequence determination module, configured to determine a target material sequence from a plurality of material sequences based on the confidence level of each material sequence, and determine the target material sequence as the material sequence of the corrugated cardboard box to be manufactured.

[0050] In a third aspect, an embodiment of the present application provides a computer storage medium, which stores multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the above method steps.

[0051] In a fourth aspect, an embodiment of the present application provides a terminal, which may include: a processor and a memory; wherein, the memory stores a computer program, and the computer program is suitable for being loaded and executed by the processor to perform the above method steps.

[0052] The technical solution provided by the embodiment of the present application may include the following beneficial effects:

[0053] In the embodiment of the present application, the corrugated cardboard box material generation device first obtains the product parameters of the corrugated cardboard box to be manufactured, then inputs the product parameters of the corrugated cardboard box to be manufactured into a pre-trained corrugated cardboard box material model, and outputs multiple material sequences corresponding to the corrugated cardboard box to be manufactured and the confidence level of each material sequence. The corrugated cardboard box material model is constructed based on the Apriori algorithm and the collaborative filtering algorithm; finally, the target material sequence is determined from the multiple material sequences based on the confidence level of each material sequence, and the target material sequence is determined as the material sequence of the corrugated cardboard box to be manufactured. Since the present application uses the Apriori algorithm and the collaborative filtering algorithm to model and fuse the historical cardboard box material data, the model after the fusion of the Apriori algorithm based on the frequent item set search technology and the collaborative filtering algorithm not only solves the problem of sparse material data in collaborative filtering recommendation, but also solves the problem of large computational complexity of the association rule algorithm itself, thereby improving the rationality and accuracy of generating the materials of the corrugated cardboard box, and further significantly reducing the raw material cost and labor cost.

[0054] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present invention and used together with the specification to explain the principles of the present invention.

[0056] Figure 1 is a schematic flowchart of a method for generating the materials of a corrugated cardboard box provided by an embodiment of the present application;

[0057] Figure 2 is a schematic diagram of modeling an Apriori algorithm model provided by an embodiment of the present application;

[0058] Figure 3 is a schematic diagram of the process of discovering frequent item sets by the Apriori algorithm provided by an embodiment of the present application;

[0059] Figure 4 is a schematic diagram of an application scenario of the collaborative filtering algorithm provided by an embodiment of the present application;

[0060] Figure 5A is a schematic diagram of the relationship between the product parameters of a cardboard box and the materials provided by an embodiment of the present application;

[0061] Figure 5B is a similarity matrix diagram of the product parameters of a cardboard box and the materials provided by an embodiment of the present application;

[0062] Figure 5C is another similarity matrix diagram of the product parameters of a cardboard box and the materials provided by an embodiment of the present application;

[0063] Figure 6 is a process schematic block diagram of a process for generating a material configuration of a corrugated cardboard box provided by an embodiment of the present application;

[0064] Figure 7 is a structural schematic diagram of a device for generating a material configuration of a corrugated cardboard box provided by an embodiment of the present application;

[0065] Figure 8 is a structural schematic diagram of a terminal provided by an embodiment of the present application. Specific Embodiments

[0066] The following description and the accompanying drawings fully illustrate specific embodiments of the present invention, enabling those skilled in the art to practice them.

[0067] It should be clear that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0068] When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are only examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0069] In the description of the present invention, it should be understood that terms such as "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. In addition, in the description of the present invention, unless otherwise specified, "a plurality of" means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0070] The present application provides a method, apparatus, storage medium, and terminal for generating the material configuration of a corrugated cardboard box to solve the problems existing in the above-mentioned related technical problems. In the technical solution provided by the present application, since the Apriori algorithm and the collaborative filtering algorithm are used to model and fuse the historical cardboard box material configuration data, the model after the fusion of the Apriori algorithm based on the frequent item set search technology and the collaborative filtering algorithm not only solves the problem of sparse material configuration data in collaborative filtering recommendations, but also solves the problem of large computational complexity of the association rule algorithm itself, thereby improving the rationality and accuracy of generating the material configuration of the corrugated cardboard box, and further significantly reducing the raw material cost and labor cost. The following uses exemplary embodiments for detailed description.

[0071] The following will be combined with the attached Figure 1 - attached Figure 6 , to introduce in detail the method for generating the material configuration of the corrugated cardboard box provided by the embodiments of the present application. This method can be implemented depending on a computer program and can run on a device for generating the material configuration of a corrugated cardboard box based on the von Neumann architecture. This computer program can be integrated into an application or run as an independent tool-type application.

[0072] Please refer to Figure 1 , which is a schematic flowchart of a method for generating the material configuration of a corrugated cardboard box provided by an embodiment of the present application. As Figure 1 shown, the method of the embodiment of the present application may include the following steps:

[0073] S101, obtaining the product parameters of the corrugated cardboard box to be manufactured;

[0074] Among them, corrugation can be understood as the structural form of building materials, corrugations. A corrugated cardboard box is made by die-cutting, indentation, nailing or gluing the box. A corrugated cardboard box is a packaging product with the widest application. The product parameters are corrugation type, product category, compressive strength, and bursting strength.

[0075] It should be noted that in actual application scenarios, other product parameters can be selected as inputs according to the data and actual situation.

[0076] Generally, in the paper packaging industry, the corrugation type is usually divided into single corrugation, double corrugation, and triple corrugation. These three types have different shrinkage rates, so their compressive performance and impact resistance are also different; the product category is the type or exact product of the product to be packaged; the compressive strength refers to the maximum load and deformation amount until the box body is damaged under the uniformly applied dynamic pressure of a pressure testing machine, and the unit is ibs; the bursting strength is the maximum pressure applied by a hydraulic system in the manner specified by the standard when an elastic rubber film pierces a circular specimen, and its unit is kpa.

[0077] In a possible implementation, when generating the materials for a corrugated cardboard box, it is first necessary to obtain the product parameters of the corrugated cardboard box to be manufactured. These parameters can be provided by the customer or set by experts according to the customer's requirements. For example, if the product parameters of the corrugated cardboard box to be manufactured are {single corrugation, for apples, 70 ibs, 1829 kpa}, it can be known that the structure of the corrugated cardboard box to be manufactured is single corrugation, used to pack apples, with a compressive strength of 70 ibs and a bursting strength of 1829 kpa.

[0078] S102, input the product parameters of the corrugated cardboard box to be manufactured into a pre-trained corrugated cardboard box material model, and output multiple material sequences corresponding to the corrugated cardboard box to be manufactured and the confidence level of each material sequence;

[0079] Among them, the corrugated cardboard box material model is constructed based on the Apriori algorithm and the collaborative filtering algorithm;

[0080] In a possible implementation, when constructing an Apriori algorithm model based on the Apriori algorithm, first obtain and preprocess the historical orders and product data of historical corrugated cardboard boxes to generate a cardboard box material dataset, then use the Apriori algorithm to create a corrugated cardboard box material model, and then input the cardboard box material dataset into the corrugated cardboard box material model to obtain an item set. Secondly, calculate the support degree of each data item in the item set. Finally, compare the support degree of each data item with a preset threshold, and determine the data items with a support degree greater than the preset threshold as frequent item sets. When the number of frequent items in the frequent item set is 1, generate the Apriori algorithm model.

[0081] Specifically, when the number of frequent items in the frequent item set is not 1, traverse and splice each frequent item in the frequent item set to obtain a spliced item set; calculate the support degree of each data item in the spliced item set; continue to execute the step of comparing the support degree of each data item with the preset threshold until the number of items in the frequent item set is 1, and generate the Apriori algorithm model.

[0082] It should be noted that the Apriori algorithm is a classic data mining algorithm for mining frequent item sets and association rules. It uses an iterative method of layer-by-layer search, where the c-item set is used to explore the (c + 1)-item set. First, by scanning the order base paper dataset, the count of each item is accumulated, and the items that meet the minimum support are collected to find the set of frequent 1-item sets. This set is denoted as L1. Then, use L1 to find the set of frequent 2-item sets L2, use L2 to find L3, and so on, until no more frequent k-item sets can be found. Each time an Lk is found, a complete scan of the database is required.

[0083] Specifically, when constructing a corrugated box material matching model based on the Apriori algorithm, historical carton product data is first obtained, which mainly includes the corrugation type, product type, material matching, compressive strength, bursting strength, etc. of the carton products. For example, what can be obtained in this application is the sales order form and product details data of a leading enterprise in the paper packaging industry in the past 5 years. Then, the historical carton product data is preprocessed to generate a carton material matching data set. The processing methods of data preprocessing at least include column name renaming, duplicate value deletion, missing value processing, normalization processing, data sorting processing, and outlier processing.

[0084] For example Figure 2 As shown, after the data set is preprocessed, an option set c1 is generated. Each option set has a data item. Then, through the support threshold, the frequent item set L1 is generated from c1. The data items of L1 are spliced pairwise into C2. Starting from the candidate item set C2, L2 is generated through support filtering. L2 is spliced into the candidate item set C3 according to the Apriori principle. L3 is generated through support filtering. When L3 cannot be spliced, strong association rules are generated from the frequent item set until Lk cannot be spliced when it is a single data item, thus ending.

[0085] Furthermore, when the number of frequent items in the frequent item set is not 1, each frequent item in the frequent item set is traversed and spliced to obtain a splicing option set. Then, the support of each data item in the splicing option set is calculated. Finally, the step of comparing the support of each data item with the preset threshold is continued until the number of items in the frequent item set is 1, and the Apriori algorithm model is generated.

[0086] For example, the product parameters of the historical corrugated box order data and the example data of the corresponding material matching are shown in Table 1. There are 4 historical corrugated boxes in Table 1. The product parameters of the 4 historical corrugated boxes are {B fruit 68 1829}, {C fruit 732007}, {A fruit 69 1805}, and {E fruit 56 1416} respectively. Among them

[0087] Table 1

[0088] Serial number Parameter Fitting material 1 {B fruit 68 1829} a, c, d 2 {C fruit 73 2007} b, c, e 3 {A fruit 69 1805} a, c, d 4 {E fruit 56 1416} b, e

[0089] B, C, A, and E represent the shrinkage rate of single-layer corrugation. 68, 73, and 69 are the compressive strength in pounds (ibs), and 1829, 2007, and 1805 represent the bursting strength in kilopascals (kpa). a, b, c, d, and e in the material matching represent different materials.

[0090] For example Figure 3 As shown, according to the data in Table 1, after preprocessing, a cleaned carton single product data set can be obtained. Combining with the corrugated box material matching model created by the Apriori algorithm, for example Figure 3The option set c1 in it is respectively a, b, c, d, e in the materials. Each of a, b, c, d, e corresponds to a support. For example, the support threshold is 0.5. Compare the supports corresponding to a, b, c, d, e with the support threshold to determine the materials with a support greater than 0.5 to obtain the frequent item set L1. For example, the obtained frequent item set L1 includes a, b, c, e respectively. It can be seen that L1 has 4 items. Therefore, it is necessary to traverse and combine them in pairs to obtain C2. Starting from the candidate item set C2, L2 is generated by support filtering. L2 is pieced together into the candidate item set C3 according to the Apriori principle. It can be seen that there is only one item {b, c, e} with a support greater than 0.5 in C3. Therefore, L3 {b, c, e} is the final frequent item.

[0091] In another possible implementation, when constructing a collaborative filtering algorithm model based on the collaborative filtering algorithm, first collect a preset number of historical corrugated cardboard box data, then use the collaborative filtering algorithm to construct a corrugated cardboard box material model, and input the historical corrugated cardboard box data into the corrugated cardboard box material model to obtain the product parameters of multiple similar first corrugated cardboard boxes. Then, obtain the materials of the product parameters of each similar corrugated cardboard box. Secondly, calculate the similarity matrix between multiple similar corrugated cardboard boxes according to the materials of the product parameters of each similar corrugated cardboard box to generate a similarity matrix. Finally, when the similarity matrix is generated, a collaborative filtering algorithm model is generated.

[0092] It should be noted that the user-based collaborative filtering recommendation algorithm first uses statistical techniques to find neighbor users with the same preferences as the target user, and then generates recommendations to the target user according to the preferences of the target user's neighbor users. The basic principle is to use the similarity of user access behaviors to recommend data that users may be interested in to each other. For example Figure 4 As shown, assume that user A likes item A and item C, user B likes item B, and user C likes item A, item C, and item D. From the preferences of these users, we can find that the preferences of user A and user C are relatively similar. They both like item A and item C, and user C also likes item D. Then we can infer that user A also likes item D. So item D is recommended to user A. In the collaborative filtering algorithm, the similarity calculation method between users is as follows: Let N(u) be the set of items liked by user A, and N(v) be the set of items liked by user C. Then the similarity between A and C is calculated using the formula:

[0093]

[0094] It can be seen from the above formula that the higher the similarity between users, the more items they like in common. In addition, the confidence of users in items is calculated as follows:

[0095]

[0096] After obtaining the similarity between users, the UserCF algorithm will recommend items that are liked by the k most similar users to the user. The formula on the right above measures the confidence of user u in item i in the UserCF algorithm: where S(u, k) contains the K users with the closest interests to user u, N(i) is the set of users who have acted on item i, Wuv is the similarity of interests between user u and user v, and Rvi represents the interest of user v in item i. Because the implicit feedback data of a single behavior is used, all Rvi=1.

[0097] For example, there are multiple similar first corrugated carton product parameters A, B, C, D, and there are three flute types and five materials, namely a, b, c, d, and e, respectively: Product A has two single flute materials, a and b, and one double flute material, d; Product B has one single flute material, a, and one double flute material, c; Product C has one single flute material, b, and one triple flute material, e; Product D has two double flutes, c and d, and one triple flute material, e. The relationship between carton product parameters and material solutions is as follows Figure 5A For each ingredient, the products using it are marked as 1. For example, there are two products A and B using formula a. In the matrix, they are marked as 1, as shown in Figure 5A As shown. Combined with Figure 5A The matrix shown in combined with the above similarity calculation formula can be calculated, for example, Figure 5C 's matrix.

[0098] Furthermore, after the Apriori algorithm model and the collaborative filtering algorithm model are generated according to the above process, the Apriori algorithm model and the collaborative filtering algorithm model are merged to generate a pre-trained corrugated box material model.

[0099] In the embodiment of the present application, when outputting multiple material sequences corresponding to the corrugated cardboard box to be manufactured and the confidence of each material sequence, the product parameters of the corrugated cardboard box to be manufactured are first input into the Apriori algorithm model to generate a first number of material sequences and the confidence of each first material sequence, and then the first number of material sequences and the confidence of each first material sequence are output, and then the product parameters of the corrugated cardboard box to be manufactured are input into the collaborative filtering algorithm model to obtain the product parameters of multiple similar second corrugated cardboard boxes; wherein the number of product parameters of multiple similar second corrugated cardboard boxes is less than the number of product parameters of the first corrugated cardboard box, and then multiple materials of each second corrugated cardboard box are obtained from the product parameters of the multiple similar second corrugated cardboard boxes to generate a material set, and then the existing materials of the product parameters of the corrugated cardboard box to be manufactured are obtained, and then the existing materials are eliminated from the material set to generate a second number of material sequences, and the confidence of each material sequence in the second number of material sequences is calculated, and finally the second number of material sequences and the confidence of each second material sequence are output.

[0100] Specifically, when using the collaborative filtering algorithm model to generate the materials, first, it is necessary to find the K products most similar to the target carton product parameter u from the Figure 5C matrix, which is represented by the set S(u, K). Extract all the formulas used by the products in S and remove the materials already used by u. For each candidate material i, the degree of interest of the carton product u in it is calculated by the following formula:

[0101] where rvi represents the degree of preference of product v for formula i.

[0102] Suppose we want to recommend for the carton product parameter A, select K = 3 similar product parameters, and the similar product parameters are B, C, and D. Then the formulas they have used and A has not used are: c, e. Then calculate p(A, c) and p(A, e) respectively (here p(A, c) and p(A, e) represent the confidence levels between the carton product parameter A and the formulas c and e):

[0103]

[0104] The similarity results show that the confidence levels of the product parameter A in the material schemes c and e may be the same and relatively high. In practical applications, we set a threshold for the confidence level, such as 0.5. When the confidence level is greater than 0.5, we recommend the material scheme to the carton product parameter.

[0105] S103. Determine the target material sequence from multiple material sequences based on the confidence level of each material sequence, and determine the target material sequence as the material sequence of the corrugated carton to be manufactured.

[0106] In a possible implementation manner, when determining the target material sequence from multiple material sequences based on the confidence level of each material sequence, first, judge one by one whether the confidence level of each material sequence is greater than or equal to the preset confidence level threshold to generate multiple judgment results. Then, determine at least one target material sequence from multiple material sequences according to the multiple judgment results. Finally, receive the selection instruction for at least one target material sequence, and determine the target material sequence from at least one target material sequence according to the selection instruction.

[0107] Specifically, when determining at least one target material sequence from multiple material sequences according to the multiple judgment results, first, obtain the judgment results less than the preset confidence level threshold from the multiple judgment results. Then, remove the material sequences corresponding to the judgment results less than the preset confidence level threshold from the multiple material sequences. Finally, generate at least one target material sequence.

[0108] For example, the pre-trained corrugated box material matching model generated based on the Apriori algorithm and collaborative filtering algorithm will recommend the following several corrugated box material matching solutions: ({'200A cattle 170A corrugated 200A cattle B'}, {'130T cattle 120A corrugated 160T cattle B'}, {'250A cattle 170A corrugated 200A cattle A'}); for example, when the product parameters of the corrugated box to be manufactured are ({'double corrugated box 68 ibs 1829 kpa'}), the following recommended results are output:

[0109] ({'170A cattle 120A corrugated 170A cattle 90A corrugated 120A corrugated CB'})

[0110] ({'170H cattle 110A corrugated 170H cattle 150H cattle 110A corrugated CB'})

[0111] ({'170A cattle 90A corrugated 170H cattle 170H cattle 120A corrugated CB'});

[0112] Among them, '170A cattle' is the abbreviation of A-grade cattle cardboard with a grammage of 170; when the corrugation type is 'B' or 'A', it represents single-layer corrugation with different shrinkage rates, and the recommended formula order is face paper, corrugation, and inner paper. When the corrugation type is 'CB', it represents double-layer corrugation, and the recommended formula order is face paper, corrugation 1, core paper, corrugation 2, and inner paper.

[0113] For example Figure 6 as shown Figure 6 is a process schematic block diagram of the material matching generation process of a corrugated box provided by this application. First, historical corrugated box order data is obtained, then data cleaning is performed to obtain preprocessed data, and the preprocessed data is respectively input into the Apriori algorithm model and the collaborative filtering algorithm model, and multiple material matching solutions are output respectively. Finally, the user selects the optimal material matching solution from the material matching solutions and outputs it.

[0114] It should be noted that the Apriori algorithm based on the frequent item set search technology will output corresponding material matching sequences and confidence levels. The collaborative filtering algorithm will also output corresponding material matching sequences and confidence levels. The experimental results show that the recommended results output by using the two algorithms separately are obviously not as effective as the results output based on both algorithms at the same time. Therefore, in the algorithms used in this experimental model, it is not just a simple superposition of the two algorithms. The fusion of the two algorithms can solve the deficiencies of the respective algorithms, making the effect of the model more scientific and accurate. Further, it is also found that continuing to superimpose other algorithms, such as model-based recommendation algorithms, popularity-based recommendation algorithms, utility-based recommendation algorithms, and content-based recommendation algorithms, the generated corrugated box material matching sequence results are not as good as the results of using the technical solution of the present invention.

[0115] In an embodiment of the present application, the corrugated cardboard box material generation device first obtains the product parameters of the corrugated cardboard box to be manufactured, then inputs the product parameters of the corrugated cardboard box to be manufactured into a pre-trained corrugated cardboard box material model, and outputs multiple material sequences corresponding to the corrugated cardboard box to be manufactured and the confidence level of each material sequence. The corrugated cardboard box material model is constructed based on the Apriori algorithm and the collaborative filtering algorithm; finally, based on the confidence level of each material sequence, a target material sequence is determined from the multiple material sequences, and the target material sequence is determined as the material sequence of the corrugated cardboard box to be manufactured. Since the present application uses the Apriori algorithm and the collaborative filtering algorithm to model and fuse historical cardboard box material data, the model after the fusion of the Apriori algorithm based on the frequent item set search technology and the collaborative filtering algorithm not only solves the problem of sparse material data in collaborative filtering recommendations, but also solves the problem of large computational complexity of the association rule algorithm itself, thereby improving the rationality and accuracy of generating the materials of the corrugated cardboard box, and further significantly reducing the raw material cost and labor cost.

[0116] The following is an embodiment of the device of the present invention, which can be used to execute the embodiment of the method of the present invention. For the details not disclosed in the embodiment of the device of the present invention, please refer to the embodiment of the method of the present invention.

[0117] Please refer to Figure 7 , which shows a schematic structural diagram of a corrugated cardboard box material generation device provided by an exemplary embodiment of the present invention. The corrugated cardboard box material generation device can be implemented as all or part of a terminal through software, hardware, or a combination of both. The device 1 includes a product parameter acquisition module 10, a parameter output module 20, and a material sequence determination module 30.

[0118] The product parameter acquisition module 10 is used to acquire the product parameters of the corrugated cardboard box to be manufactured;

[0119] The parameter output module 20 is used to input the product parameters of the corrugated cardboard box to be manufactured into a pre-trained corrugated cardboard box material model, and output multiple material sequences corresponding to the corrugated cardboard box to be manufactured and the confidence level of each material sequence;

[0120] Among them, the corrugated cardboard box material model is constructed based on the Apriori algorithm and the collaborative filtering algorithm;

[0121] The material sequence determination module 30 is used to determine a target material sequence from the multiple material sequences based on the confidence level of each material sequence, and determine the target material sequence as the material sequence of the corrugated cardboard box to be manufactured.

[0122] It should be noted that when the corrugated cardboard box material generation device provided in the above embodiments executes the corrugated cardboard box material generation method, only the division of the above functional modules is used for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the corrugated cardboard box material generation device provided in the above embodiments and the corrugated cardboard box material generation method embodiments belong to the same concept. The implementation process is shown in the method embodiments and will not be elaborated here.

[0123] The serial numbers of the above embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0124] In the embodiments of the present application, the corrugated cardboard box material generation device first obtains the product parameters of the corrugated cardboard box to be manufactured, and then inputs the product parameters of the corrugated cardboard box to be manufactured into a pre-trained corrugated cardboard box material model to output multiple material sequences corresponding to the corrugated cardboard box to be manufactured and the confidence of each material sequence. The corrugated cardboard box material model is constructed based on the Apriori algorithm and the collaborative filtering algorithm; finally, the target material sequence is determined from the multiple material sequences based on the confidence of each material sequence, and the target material sequence is determined as the material sequence of the corrugated cardboard box to be manufactured. Since the present application uses the Apriori algorithm and the collaborative filtering algorithm to model and fuse the historical cardboard box material data, the model after the fusion of the Apriori algorithm based on the frequent item set search technology and the collaborative filtering algorithm not only solves the problem of sparse material data in collaborative filtering recommendations, but also solves the problem of large computational complexity of the association rule algorithm itself, thereby improving the rationality and accuracy of generating the materials of the corrugated cardboard box, and further significantly reducing the raw material cost and labor cost.

[0125] The present invention also provides a computer-readable medium with program instructions stored thereon. When the program instructions are executed by a processor, the corrugated cardboard box material generation method provided in each of the above method embodiments is implemented.

[0126] The present invention also provides a computer program product containing instructions. When it runs on a computer, it causes the computer to execute the corrugated cardboard box material generation method of each of the above method embodiments.

[0127] Please refer to Figure 8 , which is a schematic structural diagram of a terminal provided in the embodiments of the present application. As Figure 8 shown, the terminal 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

[0128] Among them, the communication bus 1002 is used to realize the connection and communication between these components.

[0129] Among them, the user interface 1003 may include a display screen and a camera. Optionally, the user interface 1003 may further include standard wired interfaces and wireless interfaces.

[0130] Among them, the network interface 1004 may optionally include standard wired interfaces and wireless interfaces (such as WI-FI interfaces).

[0131] Among them, the processor 1001 may include one or more processing cores. The processor 1001 connects various parts within the entire terminal 1000 through various interfaces and circuits. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling the data stored in the memory 1005, the processor 1001 executes various functions of the terminal 1000 and processes data. Optionally, the processor 1001 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 1001 may integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001 and may be implemented separately by a single chip.

[0132] Among them, the memory 1005 may include a Random Access Memory (RAM), or may include a Read-Only Memory. Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store the data involved in the above-mentioned various method embodiments. Optionally, the memory 1005 may also be at least one storage device located far from the aforementioned processor 1001. As Figure 8 shown, in the memory 1005 as a computer storage medium, an operating system, a network communication module, a user interface module, and a corrugated cardboard material generation application program may be included.

[0133] In Figure 8 the terminal 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain the data input by the user; while the processor 1001 can be used to call the corrugated cardboard material generation application program stored in the memory 1005 and specifically perform the following operations:

[0134] Obtain the product parameters of the corrugated cardboard box to be manufactured;

[0135] Input the product parameters of the corrugated cardboard box to be manufactured into a pre-trained corrugated cardboard material model, and output multiple material sequences corresponding to the corrugated cardboard box to be manufactured and the confidence level of each material sequence; among them, the corrugated cardboard material model is constructed based on the Apriori algorithm and the collaborative filtering algorithm;

[0136] Determine a target material sequence from multiple material sequences based on the confidence level of each material sequence, and determine the target material sequence as the material sequence of the corrugated cardboard box to be manufactured.

[0137] In one embodiment, when the processor 1001 determines a target material sequence from multiple material sequences based on the confidence level of each material sequence, it specifically performs the following operations:

[0138] Judging one by one whether the confidence level of each material sequence is greater than or equal to a preset confidence threshold, and generating multiple judgment results;

[0139] Determine at least one target material sequence from multiple material sequences according to the multiple judgment results;

[0140] Receive a selection instruction for at least one target material sequence, and determine the target material sequence from the at least one target material sequence according to the selection instruction.

[0141] In one embodiment, when the processor 1001 determines at least one target material sequence from multiple material sequences according to multiple judgment results, the following operations are specifically performed:

[0142] Obtain the judgment results less than the preset confidence threshold from the multiple judgment results;

[0143] Exclude the material sequences corresponding to the judgment results less than the preset confidence threshold from the multiple material sequences;

[0144] Generate at least one target material sequence.

[0145] In one embodiment, when the processor 1001 generates a pre-trained corrugated box material model according to the following steps, the following operations are specifically performed:

[0146] Obtain and preprocess the historical orders and product data of historical corrugated boxes to generate a corrugated box material dataset;

[0147] Create a corrugated box material model using the Apriori algorithm;

[0148] Input the corrugated box material dataset into the corrugated box material model to obtain an option set;

[0149] Calculate the support degree of each data item in the option set;

[0150] Compare the support degree of each data item with the preset threshold, and determine the data items with support degrees greater than the preset threshold as frequent item sets;

[0151] When the number of frequent items in the frequent item set is 1, generate an Apriori algorithm model;

[0152] Generate a collaborative filtering algorithm model based on a preset number of historical corrugated box data;

[0153] Merge the Apriori algorithm model and the collaborative filtering algorithm model to generate a pre-trained corrugated box material model.

[0154] In one embodiment, when the processor 1001 generates an Apriori algorithm model when the number of frequent items in the frequent item set is 1, the following operations are specifically performed:

[0155] When the number of frequent items in the frequent item set is not 1, traverse and splice each frequent item in the frequent item set to obtain a spliced option set;

[0156] Calculate the support of each data item in the calculation splicing option set;

[0157] Continue to execute the step of comparing the support of each data item with the preset threshold until the number of items in the frequent item set is 1, and generate the Apriori algorithm model.

[0158] In one embodiment, when the processor 1001 executes the training to generate the collaborative filtering algorithm model based on the preset number of historical corrugated carton data, the following operations are specifically performed:

[0159] Collect the preset number of historical corrugated carton data;

[0160] Construct a corrugated carton material matching model using the collaborative filtering algorithm, and input the historical corrugated carton data into the corrugated carton material matching model to obtain the product parameters of multiple similar first corrugated cartons;

[0161] Obtain the materials of the product parameters of each similar corrugated carton;

[0162] Calculate the similarity matrix between multiple similar corrugated cartons according to the materials of the product parameters of each similar corrugated carton, and generate the similarity matrix;

[0163] When generating the similarity matrix, generate a pre-trained corrugated carton material matching model.

[0164] In one embodiment, when the processor 1001 executes inputting the product parameters of the corrugated carton to be manufactured into the pre-trained corrugated carton material matching model and outputting multiple material sequences corresponding to the corrugated carton to be manufactured and the confidence of each material sequence, the following operations are specifically performed:

[0165] Input the product parameters of the corrugated carton to be manufactured into the Apriori algorithm model to generate the first number of material sequences and the confidence of each first material sequence;

[0166] Output the first number of material sequences and the confidence of each first material sequence;

[0167] Input the product parameters of the corrugated carton to be manufactured into the collaborative filtering algorithm model to obtain the product parameters of multiple similar second corrugated cartons; wherein, the number of the product parameters of multiple similar second corrugated cartons is less than the number of the product parameters of the first corrugated cartons;

[0168] Obtain the multiple materials of each second corrugated carton from the product parameters of multiple similar second corrugated cartons to generate a material set;

[0169] Obtain the existing materials of the product parameters of the corrugated carton to be manufactured;

[0170] Exclude the existing materials from the set of materials to generate a second quantity of material sequences;

[0171] Calculate the confidence of each material sequence in the second quantity of material sequences;

[0172] Output the second quantity of material sequences and the confidence of each second material sequence.

[0173] In the embodiments of the present application, the material generation device for corrugated cardboard boxes first obtains the product parameters of the corrugated cardboard box to be manufactured, then inputs the product parameters of the corrugated cardboard box to be manufactured into a pre-trained corrugated cardboard box material model, and outputs a plurality of material sequences corresponding to the corrugated cardboard box to be manufactured and the confidence of each material sequence. The corrugated cardboard box material model is constructed based on the Apriori algorithm and the collaborative filtering algorithm; finally, the target material sequence is determined from the plurality of material sequences based on the confidence of each material sequence, and the target material sequence is determined as the material sequence of the corrugated cardboard box to be manufactured. Since the present application uses the Apriori algorithm and the collaborative filtering algorithm to model and fuse the historical cardboard box material data, the model after the fusion of the Apriori algorithm based on the frequent item set search technology and the collaborative filtering algorithm not only solves the problem of sparse material data in collaborative filtering recommendations, but also solves the problem of large computational complexity of the association rule algorithm itself, thereby improving the rationality and accuracy of generating the materials for corrugated cardboard boxes, and further significantly reducing the raw material cost and labor cost.

[0174] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program for generating the materials of the corrugated cardboard box can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.

[0175] The above-disclosed are only the preferred embodiments of the present application. Of course, the scope of the rights of the present application cannot be limited thereby. Therefore, equivalent changes made according to the claims of the present application still fall within the scope covered by the present application.

Claims

1. A method for producing materials for corrugated paper boxes, characterized in that: The method comprises: Obtain product parameters of the corrugated box to be manufactured; Input the product parameters of the corrugated paper box to be manufactured into a pre-trained corrugated paper box material matching model, and output multiple material matching sequences corresponding to the corrugated paper box to be manufactured and the confidence of each material matching sequence; wherein the corrugated paper box material matching model is constructed based on the Apriori algorithm and the collaborative filtering algorithm; Based on the confidence of each of the material sequences, a target material sequence is determined from the multiple material sequences, and the target material sequence is determined as the material sequence of the corrugated paper box to be manufactured; wherein, Follow these steps to generate a pre-trained corrugated box material model, including: Obtain and preprocess historical corrugated carton order and product data to generate carton material dataset; Use Apriori algorithm to create a corrugated box material model; Inputting the carton material data set into the corrugated carton material model to obtain an option set; Calculate the support of each data item in the option set; Compare the support of each data item with a preset threshold, and determine the data items whose support is greater than the preset threshold as frequent itemsets; When the number of frequent items in the frequent item set is 1, an Apriori algorithm model is generated; Generate collaborative filtering algorithm model based on a preset amount of historical corrugated box data training; The Apriori algorithm model is combined with the collaborative filtering algorithm model to generate a pre-trained corrugated box material model.

2. The method according to claim 1, characterized in that The step of determining a target material sequence from the plurality of material sequences based on the confidence level of each material sequence includes: Determine one by one whether the confidence of each material sequence is greater than or equal to a preset confidence threshold, and generate multiple determination results; Determine at least one target material sequence from the multiple material sequences according to the multiple judgment results; A selection instruction for the at least one target material sequence is received, and a target material sequence is determined from the at least one target material sequence according to the selection instruction.

3. The method according to claim 2, characterized in that The step of determining at least one target material sequence from the plurality of material sequences according to the plurality of judgment results comprises: Acquire a judgment result less than the preset confidence threshold from the multiple judgment results; Eliminate, from the plurality of material sequences, material sequences corresponding to judgment results less than the preset confidence threshold; At least one target material sequence is generated.

4. The method according to claim 1, characterized in that When the number of frequent items in the frequent item set is 1, generating an Apriori algorithm model includes: When the number of frequent items in the frequent item set is not 1, traversing and splicing the frequent items in the frequent item set to obtain a splicing option set; Calculate the support of each data item in the splicing option set; Continue to perform the step of comparing the support of each data item with a preset threshold until the number of quantitative items in the frequent itemset is 1, and then generate an Apriori algorithm model.

5. The method according to claim 1, characterized in that The collaborative filtering algorithm model is generated based on the training of a preset amount of historical corrugated box data, including: Collect a preset amount of historical corrugated box data; A corrugated paper box material matching model is constructed by using a collaborative filtering algorithm, and the historical corrugated paper box data is input into the corrugated paper box material matching model to obtain product parameters of a plurality of similar first corrugated paper boxes; Obtaining the material matching of the product parameters of each of the similar corrugated paper boxes; Calculating a similarity matrix between the plurality of similar corrugated paper boxes according to the material matching of the product parameters of each of the similar corrugated paper boxes to generate a similarity matrix; When the similarity matrix is ​​generated, a pre-trained corrugated box material model is generated.

6. The method according to claim 5, characterized in that The step of inputting the product parameters of the corrugated paper box to be manufactured into a pre-trained corrugated paper box material matching model, and outputting a plurality of material matching sequences corresponding to the corrugated paper box to be manufactured and the confidence of each of the material matching sequences comprises: Inputting the product parameters of the corrugated paper box to be manufactured into the Apriori algorithm model to generate a first number of material sequences and a confidence level of each first material sequence; Outputting the first number of material sequences and the confidence level of each first material sequence; Inputting the product parameters of the corrugated paper box to be manufactured into a collaborative filtering algorithm model to obtain a plurality of similar product parameters of a second corrugated paper box; wherein the number of the plurality of similar product parameters of the second corrugated paper box is less than the number of the product parameters of the first corrugated paper box; Acquire multiple materials of each of the second corrugated paper boxes from the product parameters of the multiple similar second corrugated paper boxes to generate a material set; Obtaining existing materials for product parameters of the corrugated paper box to be manufactured; Eliminating the existing ingredients from the ingredient set to generate a second number of ingredient sequences; Calculating the confidence of each ingredient sequence in the second number of ingredient sequences; The second number of material sequences and the confidence level of each second material sequence are output.

7. A material generation device for corrugated paperboard boxes using the method described in any one of claims 1 to 6, characterized in that: The device comprises: A product parameter acquisition module, used to acquire product parameters of the corrugated paper box to be manufactured; A parameter output module, used for inputting the product parameters of the corrugated paper box to be manufactured into a pre-trained corrugated paper box material matching model, and outputting a plurality of material matching sequences corresponding to the corrugated paper box to be manufactured and the confidence of each of the material matching sequences; The corrugated box material matching model is constructed based on the Apriori algorithm and the collaborative filtering algorithm; A material sequence determination module is used to determine a target material sequence from the multiple material sequences based on the confidence of each of the material sequences, and determine the target material sequence as the material sequence of the corrugated paper box to be manufactured.

8. A computer storage medium, characterized in that: The computer storage medium stores a plurality of instructions, which are suitable for being loaded by a processor and executing the method steps according to any one of claims 1 to 6.

9. A terminal, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method steps as claimed in any one of claims 1 to 6.

Images