Article packaging processing method and device

Abstract

The invention discloses an article packaging processing method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of obtaining a target order, and determining at least one target article in the target order and the number of the target articles; determining a package coefficient of each target article; wherein the package coefficient of the target article is used for representing the number of the target articles which can be loaded by a single standard package; determining a package specification and / or a package number corresponding to the target order according to the package coefficient and the article number of each target article; wherein the package specification and / or the package number are / is used for packaging the target article in the target order. According to the implementation mode, the package specification or the package number needed by article packaging can be accurately determined, and the consumable cost can be accurately controlled while the articles are conveniently packaged.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to an article packing processing method and apparatus. Background Art

[0002] With the rapid development of e-commerce and modern logistics industry, more and more users purchase articles online. After receiving a user order, an order system sends article information related to the order to a warehouse management system for positioning, picking, sorting, rechecking and packing, and then delivering the goods to the customer.

[0003] During the article packing process, there are often problems such as difficulty in determining the packing specifications or the number of packages. For example, there are situations where a large box contains small articles, or a small box cannot hold large articles, which causes inconvenience to article packing and makes it difficult to control the consumable cost. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide an article packing processing method and apparatus, which can accurately determine the packing specifications or the number of packages required for article packing, facilitate the packing process of articles, and can also accurately control the consumable cost.

[0005] In a first aspect, embodiments of the present invention provide an article packing processing method, including:

[0006] Obtaining a target order, and determining at least one target article in the target order and the quantity of each target article;

[0007] Determining a packing coefficient of each target article; wherein the packing coefficient of the target article is used to represent the quantity of the target article that can be loaded in a single standard package;

[0008] According to the packing coefficient and the quantity of each target article, determining the packing specifications and / or the number of packages corresponding to the target order; wherein the packing specifications and / or the number of packages are used to pack the target articles in the target order.

[0009] Optionally, before determining the packing coefficient of each target article, the method further includes:

[0010] Determining an initial packing coefficient of the target article;

[0011] Obtaining historical packing information of the target article;

[0012] Optimizing the initial packing coefficient of the target article according to the historical packing information of the target article to generate the packing coefficient of the target article.

[0013] Optionally, optimizing the initial packing coefficient of the target item according to the historical packing information of the target item to generate the packing coefficient of the target item includes:

[0014] Determining a plurality of actual packing coefficients of the target item according to the historical packing information of the target item;

[0015] Optimizing the initial packing coefficient of the target item according to the plurality of actual packing coefficients of the target item to generate an optimized packing coefficient of the target item;

[0016] Determining the credibility corresponding to the optimized packing coefficient;

[0017] In response to the credibility being greater than a preset threshold, determining the optimized packing coefficient as the packing coefficient of the target item.

[0018] Optionally, determining a plurality of actual packing coefficients of the target item according to the historical packing information of the target item includes:

[0019] Determining the current packing information from the historical packing information;

[0020] Determining the packing type corresponding to the current packing information;

[0021] In response to the packing type representing single-item packing, determining the packing specification and packing quantity corresponding to the packing information; and determining the actual packing coefficient of the target item according to the packing specification and packing quantity corresponding to the packing information;

[0022] In response to the packing type representing mixed packing, determining the packing specification, a plurality of packed items and the packing quantity of each of the packed items corresponding to the packing information; and determining the actual packing coefficient of the target item according to the packing specification, the plurality of packed items and the packing quantity of each of the packed items corresponding to the packing information; wherein the plurality of packed items include the target item.

[0023] Optionally, determining the actual packing coefficient of the target item according to the packing specification, the plurality of packed items and the packing quantity of each of the packed items corresponding to the packing information includes:

[0024] Determining each other item among the plurality of packed items, where the other item is different from the target item;

[0025] Determining the packing coefficient of each of the other items;

[0026] Determining the weighted sum of the packing coefficients of each of the other items with the packing quantity of each of the other items as the weight;

[0027] Determine the actual packing coefficient of the target item according to the packing specifications corresponding to the packing information, the weights of the packing coefficients, and the number of packages of the target item.

[0028] Optionally, determining the credibility corresponding to the optimized packing coefficient includes:

[0029] Determine the initial credibility of the target item;

[0030] Obtain multiple packing information of the target item during a statistical period, and determine the comparison packing coefficients corresponding to each packing information;

[0031] For each comparison packing coefficient, determine the difference between the optimized packing coefficient and the comparison packing coefficient; in response to the difference being within a preset range, increase the credibility of the target item by a first preset value; in response to the difference not being within the preset range, reduce the credibility of the target item by a second preset value.

[0032] Optionally, determining the initial packing coefficient of the target item includes:

[0033] Obtain the attribute information of the target item;

[0034] Input the attribute information of the target item into the packing coefficient recommendation model;

[0035] Determine the initial packing coefficient of the target item according to the output of the packing coefficient recommendation model.

[0036] In a second aspect, an embodiment of the present invention provides an item packing processing device, including:

[0037] An order acquisition module, configured to acquire a target order, determine at least one target item in the target order, and the quantity of each target item;

[0038] A coefficient determination module, configured to determine the packing coefficient of each target item; wherein, the packing coefficient of the target item is used to represent the number of target items that can be loaded in a single standard package;

[0039] A packing processing module, configured to determine the packing specifications and / or the number of packages corresponding to the target order according to the packing coefficients and the quantities of the target items; wherein, the packing specifications and / or the number of packages are used to perform packing processing on the target items in the target order.

[0040] In a third aspect, an embodiment of the present invention provides an electronic device, including:

[0041] One or more processors;

[0042] A storage device for storing one or more programs,

[0043] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any of the above embodiments.

[0044] In a fourth aspect, an embodiment of the present invention provides a computer-readable medium, on which a computer program is stored, and when the program is executed by a processor, the method described in any of the above embodiments is implemented.

[0045] One embodiment of the above invention has the following advantages or beneficial effects: determining at least one target item in a target order and the quantity of each target item. According to the package coefficient and the quantity of each target item, determining the package specification and / or the number of packages corresponding to the target order. The package coefficient of a target item is used to represent the quantity of the target item that can be loaded in a single standard package. By using the package coefficient, it is possible to accurately determine the package specification or the number of packages required for packing items, which is convenient for packing items and can also accurately control the consumable cost.

[0046] The further effects of the above non-conventional optional methods will be described in conjunction with specific embodiments below. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention. Among them:

[0048] Figure 1 is a schematic diagram of the process of an item packing processing method provided by an embodiment of the present invention;

[0049] Figure 2 is a schematic diagram of the process of a package coefficient determination method provided by an embodiment of the present invention;

[0050] Figure 3 is a schematic diagram of the process of another package coefficient determination method provided by an embodiment of the present invention;

[0051] Figure 4 is a schematic diagram of the structure of an item packing processing device provided by an embodiment of the present invention;

[0052] Figure 5 is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] The exemplary embodiments of the present invention will be described below in conjunction with the accompanying drawings. Various details of the embodiments of the present invention are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, descriptions of well-known functions and structures are omitted in the following description for clarity and conciseness.

[0054] It should be noted that in the technical solutions of the embodiments of the present invention, the acquisition, storage, use, processing, etc. of data all comply with the relevant regulations of national laws and regulations.

[0055] Figure 1 is a schematic diagram of the process of an article packing processing method provided by an embodiment of the present invention. As Figure 1 shown, the method includes:

[0056] Step 101: Obtain a target order, and determine at least one target article in the target order and the quantity of each target article.

[0057] Step 102: Determine the packing coefficient of each target article; wherein, the packing coefficient of the target article is used to represent the quantity of the target article that can be loaded in a single standard package.

[0058] Different articles correspond to different packing coefficients. For some special articles, such as special-shaped articles, high-value articles, odor-absorbing articles, etc., only one article can be loaded in one package.

[0059] Step 103: Determine the package specification and / or the number of packages corresponding to the target order according to the packing coefficient and the quantity of each target article; wherein, the package specification and / or the number of packages are used to pack the target articles in the target order.

[0060] Packages of various specifications and materials can be set to pack the articles. The packages can be divided by material into: packing cartons, packing bags, packing foam boxes, etc. For packages of different specifications, according to the loading volume of the package, the package specification of each package is determined. For example, if the loading volume of the first package is 1.2 times the loading volume of the standard package, then the package specification of the first package is 1.2. If the loading volume of the second package is half of the loading volume of the standard package, then the package specification of the second package is 0.5.

[0061] There are many ways to determine the package specifications and / or the number of packages corresponding to a target order according to the package coefficients and the number of items of each target item. For example, determine the attribute information of each target item in the target order. According to the attribute information of the item, determine whether the target item needs to be individually packaged. If each target item is a special-shaped item, a high-value item, a flavor-transferring item, etc., then each item needs to be individually packaged. For each item, determine the package coefficient of the item, and select the package with the smallest package specification from the packages whose package specifications are not less than this package coefficient as the package specification corresponding to the target item.

[0062] Another example is to determine the package coefficient and the number of items corresponding to each target item in the target order, and determine the weighted sum of the package coefficients of each target item with the number of items of each target item as the weight. Select the package with the smallest package specification from the packages whose package specifications are not less than the weighted sum of this package coefficient as the package specification corresponding to the target order, and determine that the number of packages is 1.

[0063] Assume that the target order is packed using standard packages. After receiving the order request, determine multiple target items in the order request, including: item 1, item 2,..., item n. Calculate whether the package coefficient of item 1 plus the package coefficient of item 2 is greater than or equal to 1. If not, continue to calculate whether the package coefficient of item 1 plus the package coefficient of item 2 plus the package coefficient of item 3 is greater than or equal to 1. If the package coefficient of item 1 plus the package coefficient of item 2 plus the package coefficient of item 3 is equal to 1, then put item 1, item 2, and item 3 in the same package.

[0064] If the package coefficient of item 1 plus the package coefficient of item 2 plus the package coefficient of item 3 is greater than 1, then put item 1 and item 2 in the same package. Calculate whether the package coefficient of item 3 plus the package coefficient of item 4 is greater than or equal to 1. And so on, until all items are placed in the packages.

[0065] In the solution of the embodiment of the present invention, at least one target item in the target order and the number of items of each target item are determined. According to the package coefficients and the number of items of each target item, the package specifications and / or the number of packages corresponding to the target order are determined. The package coefficient of the target item is used to represent the number of target items that can be loaded in a single standard package. Using the package coefficient, the package specifications or the number of packages required for item packing can be accurately determined, which brings convenience to item packing and can also accurately control the consumable cost.

[0066] To facilitate the implementation of the solution of the embodiment of the present invention. The following introduces a method for determining the package coefficient. Figure 2 It is a schematic diagram of the flow of a method for determining the package coefficient provided by an embodiment of the present invention. As Figure 2 shown, the method includes:

[0067] Step 201: Determine the initial packing coefficient of the target item.

[0068] The packing information of the target item within the statistical period can be screened out. Based on the packing information, multiple packing coefficients of the target item are determined. The statistical value of the multiple packing coefficients is calculated and used as the initial packing coefficient of the target item. The statistical value can be the average value, the mode, etc.

[0069] In an embodiment of the present invention, determining the initial packing coefficient of the target item includes: obtaining the attribute information of the target item; inputting the attribute information of the target item into the packing coefficient recommendation model; and determining the initial packing coefficient of the target item according to the output of the packing coefficient recommendation model.

[0070] The attribute information may include: item length, item width, item height, item volume, item weight, item three - level category, item value, item corresponding order type, whether the item is abnormal, whether the item is liquid, etc. The packing coefficient recommendation model can adopt a deep neural network model.

[0071] Step 202: Obtain the historical packing information of the target item.

[0072] Step 203: Optimize the initial packing coefficient of the target item according to the historical packing information of the target item to generate the packing coefficient of the target item.

[0073] The historical packing information is the packaging information corresponding to the target item during the actual packing process. The historical packing information can better reflect the actual packing situation of the target item.

[0074] In the solution of the embodiment of the present invention, the initial packing coefficient of the target item is first determined, and then the historical packing information of the target item is used to optimize the initial packing coefficient of the target item, so that the finally generated packing coefficient of the target item has better accuracy.

[0075] Figure 3 It is a schematic diagram of the process of a method for determining a packing coefficient provided by another embodiment of the present invention. As Figure 3 shown, the method includes:

[0076] Step 301: Determine the initial packing coefficient of the target item.

[0077] Step 302: Obtain the historical packing information of the target item.

[0078] Step 303: Determine multiple actual packing coefficients of the target item according to the historical packing information of the target item.

[0079] Determine the current packaging information from the historical packaging information; determine the packaging type corresponding to the current packaging information; in response to the packaging type indicating single-item packaging, determine the package specifications and the number of packages corresponding to the packaging information; determine the actual package coefficient of the target item according to the package specifications and the number of packages corresponding to the packaging information.

[0080] Single-item packaging indicates that the packaged parcel contains only the target item. In the case where the packaging type indicates single-item packaging, the actual package coefficient = package specifications / number of packages. For example, using a package with package specifications of 0.8 to package 4 target items, the actual package coefficient of the target item is 0.2.

[0081] Mixed packaging indicates that the packaged parcel contains other items in addition to the target item. If the packaging type indicates mixed packaging, determine the package specifications corresponding to the packaging information, multiple packaged items, and the number of packages for each packaged item; determine the actual package coefficient of the target item according to the package specifications corresponding to the packaging information, multiple packaged items, and the number of packages for each packaged item; where the multiple packaged items include the target item.

[0082] Specifically, determine each other item among the multiple packaged items, where the other items are different from the target item; determine the package coefficient of each other item; determine the weighted sum of the package coefficients of each other item with the number of packages of each other item as the weight; determine the actual package coefficient of the target item according to the package specifications corresponding to the packaging information, the weighted sum of the package coefficients, and the number of packages of the target item.

[0083] In the case where the packaging type indicates mixed packaging, the actual package coefficient = (package specifications - weighted sum of package coefficients) / number of packages of the target item. For example, using a package with package specifications of 1.5 to package 2 target items, 3 first items, and 1 second item. The package coefficient of the first item is 0.2, and the package coefficient of the second item is 0.7, then the actual package coefficient of the target item is (1.5 - (3 * 0.2 + 0.5)) / 2 = 0.2.

[0084] For the same item, a certain weight deviation can be set between the package coefficient of mixed packaging and the package coefficient of single-item packaging. For example, when the package of the target item is shipped out alone, the package coefficient of the target item is 0.9. When the target item is shipped out mixed with other items, the package coefficient of the target item is 0.85 or 0.95, depending on the specific item attributes. That is, when multiple items are combined into one package, compared with a single item combined into one package, the package coefficient will be enlarged or reduced by a certain proportion. Specifically, for the items shipped out in historical combinations, the item information, item attribute information, combination information corresponding to each item, and the corresponding final package combination plan (i.e., the combined package coefficient) are trained in a supervised manner, and finally a combined item package coefficient change model is obtained.

[0085] Step 304: Optimize the initial packing coefficient of the target item according to multiple actual packing coefficients of the target item to generate an optimized packing coefficient of the target item.

[0086] The statistical value of multiple actual packing coefficients of the target item can be determined as the optimized packing coefficient of the target item. The weighted sum, mode, etc. of the statistical value of multiple actual packing coefficients and the initial packing coefficient can be determined as the optimized packing coefficient of the target item. The initial packing coefficient and multiple actual packing coefficients can also be input into a packing coefficient optimization model to obtain the optimized packing coefficient of the target item. The statistical value can be the mean, mode, or maximum probability, etc.

[0087] Step 305: Determine the credibility corresponding to the optimized packing coefficient.

[0088] Specifically, determine the initial credibility of the target item; obtain multiple packing information of the target item during the statistical period, and determine the comparison packing coefficient corresponding to each packing information; for each comparison packing coefficient, determine the difference between the optimized packing coefficient and the comparison packing coefficient; in response to the difference being within the preset range, increase the credibility of the target item by a first preset value; in response to the difference not being within the preset range, decrease the credibility of the target item by a second preset value.

[0089] The credibility is used to characterize the credibility and accuracy of the packing coefficient. During the outbound process of an item, the actual consumables used can be used to measure the credibility of the current item's packing coefficient. The following is the formula for the initial credibility, where S represents the initial credibility.

[0090]

[0091] When the item is a special-shaped, high-value item, has a strong smell, etc., since the above items need to be packaged separately, the credibility corresponding to the item is 1. For the calculation formula of the remaining items, the actual consumables used for single-item packing and the actual consumables data for mixed packing with other items can be comprehensively considered to obtain the credibility S of the packing coefficient.

[0092] The comparison packing coefficient corresponding to the packing information is the consumables data actually used during the packing process of the item. The calculation method of the comparison packing coefficient is the same as the calculation method of the above actual packing coefficient.

[0093] Determine the difference between the optimized packing coefficient and the comparison packing coefficient; in response to the difference being within the preset range, increase the credibility of the target item by a first preset value; in response to the difference not being within the preset range, decrease the credibility of the target item by a second preset value.

[0094] For example, if the optimized packing coefficient of an item is 1 and the initial credibility coefficient is 0.6. After N shipments, if the comparison packing coefficients corresponding to the N shipments are all 1 and N is greater than the preset threshold, the credibility of the packing coefficient is set to 1.

[0095] If the comparison packing coefficient of a shipment is close to the optimized packing coefficient, the credibility increases by a first preset value, which can be set according to requirements, such as 0.1. If the comparison packing coefficient of a shipment is quite different from the optimized packing coefficient, the credibility decreases, and the credibility decreases by a second preset value, which can be set according to requirements, such as 0.1.

[0096] Step 306: In response to the credibility being greater than the preset threshold, determine the optimized packing coefficient as the packing coefficient of the target item.

[0097] If the credibility is greater than the preset threshold, stop the loop and determine the optimized packing coefficient as the packing coefficient of the target item.

[0098] Step 307: In response to the credibility not being greater than the preset threshold, re-obtain the historical packing information of the target item, and the re-obtained historical packing information has not been used to optimize the packing coefficient of the target item.

[0099] If the credibility is not greater than the preset threshold, it means that the accuracy of the optimized packing coefficient is not high. Re-obtain the packing information that has not been used to optimize the packing coefficient of the target item and execute step 303 until the credibility is greater than the preset threshold.

[0100] In the solution of the embodiment of the present invention, multiple actual packing coefficients of the target item are determined according to the historical packing information of the target item. According to the multiple actual packing coefficients of the target item, the initial packing coefficient of the target item is optimized to generate the optimized packing coefficient of the target item. And determine the credibility corresponding to the optimized packing coefficient, and control the program to iterate continuously according to the credibility until a packing coefficient with high accuracy is obtained.

[0101] The packing system and credibility of the item can be set based on the following rules. Count the consumables used for single-item packing or mixed packing of the target item by different packing personnel on different dates, and determine the number of packages that meet the current packing coefficient. If the number of packages that meet the current packing coefficient exceeds the specified threshold, determine that the credibility of the packing coefficient is 1. The specified threshold can be set as needed.

[0102] The consumables used for single-piece packaging or mixed packaging of the same item vary greatly depending on different dates or different packers. The credibility can be determined based on the dispersion of the consumables used in different packages. For example, the initial package coefficient of item A is 0.8, and the package coefficients obtained through historical calculations are 0.7, 0.65, and 0.82 respectively. The initial package coefficient of item B is 0.8, and the package coefficients obtained through historical calculations are 0.75, 0.75, and 0.82 respectively. Since the dispersion of the package coefficient of item B is lower than that of item A, the credibility of item B is higher than that of item A.

[0103] For items with a low credibility coefficient, the package coefficient of the item can be optimized in the following way. Obtain the packaging information of the single-piece packaging of the item by different times and different operators, and calculate the first statistical value of the historical package coefficient, such as the average value and the maximum probability value. Obtain the packaging information of the mixed packaging of the item and other items with high credibility by different times and different operators, and calculate the second statistical value of the historical package coefficient, such as the average value and the maximum probability value. For example, the current package coefficient of item M is 0.4, and the package coefficients obtained through historical calculations are 0.5, 0.5, 0.55, and 0.5. Then, according to the principle of the maximum probability, the package coefficient of the current item should be optimized to 0.5.

[0104] Continuously optimize the package coefficient of the item. Finally, when the credibility of the item's package coefficient is greater than the preset threshold, the package coefficient of the item is no longer optimized.

[0105] For example, the package coefficient of item M is 0.1, and the corresponding credibility is 1. The package coefficient of item O is 0.4, and the corresponding credibility is 1. Multiple items M and item O are assembled into package 1. The package coefficient of item N is 0.3, and the corresponding credibility is 0.5. The package coefficient of item Y is 0.5, and the corresponding credibility is 0.6. Multiple items N and item Y are assembled into package 2. The credibility of the package coefficients of the items in package 1 is very high. While the credibility of the items in package 2 is not high. Therefore, the space allocation and utilization of package 1 are more reasonable and more in line with the actual situation.

[0106] In an embodiment of the present invention, determining the initial package coefficient of the target item includes: obtaining the attribute information of the target item; inputting the attribute information of the target item into the package coefficient recommendation model; and determining the initial package coefficient of the target item according to the output of the package coefficient recommendation model. The package coefficient recommendation model can be constructed based on the following steps.

[0107] Step S1: Obtain the multi-dimensional attribute information of multiple items with high credibility as sample data. Obtain the corresponding package coefficients of the above multiple items as label data.

[0108] The attribute information may include: item length, item width, item height, item volume, item weight, category information, item value, the order type corresponding to the item, whether the item is irregularly shaped, whether the item is a liquid, etc. Among them, the length, width, height, volume, and weight should all be less than the loading limit of the package. For different category information of items, there are significant differences in their package coefficients. The fillers of beauty products and cleaning paper products are different, and the package coefficients are very different. Irregularly shaped or liquid items cannot be mixed with other items, and their package coefficients are very different. The label data indicates the package coefficient of the item.

[0109] Examples of the sample data and the label data are as follows: (item length, item width, item height, item volume, item weight, the third-level category of the item, item value, the order type corresponding to the item, whether the item is irregularly shaped, whether the item is a liquid, etc.) - (package coefficient).

[0110] Step S2: Clean and normalize the sample data such as the multi-dimensional attribute information of the item and the corresponding label data.

[0111] The data of fixed classification can be processed into numerical types. For example, the order type is identified as 0, 1, 2. Volume, weight, etc. are usually in digital form, but the measurement dimensions are different. The sample data can be transformed by a certain mathematical transformation method to make the original data dimensionless, that is, the values of each index are at the same quantity level, avoiding the influence of the data dimension on model training. For example, the number of items is converted into a compressed value between [0,1] through min-max normalization or z-score normalization, etc. Normalizing the data can speed up the process of model training and improve the efficiency of model training.

[0112] Step S3: Based on the sample feature data and the sample label data obtained in the above steps, train to obtain the package coefficient recommendation model.

[0113] Take the sample feature data such as the new item attributes as the input data of the model, and the item package coefficient label data as the output data of the model, and train the package coefficient recommendation model to learn the relationship between the sample feature data and the sample label data. Then, by minimizing the model loss function, continuously iterate and optimize the parameters of the model until the set accuracy value is reached.

[0114] The above training model can adopt a deep neural network model. The process of training with a deep neural network model is as follows: Input multiple historical sample data of multiple dimensions into a multi-layer neural network for training. Use the processed dimensionless sample data as the input. Use the label data as the supervised label data. Construct the relevant parameters of the multi-layer neural network, including the number of layers of neurons, randomly initialize the weight values, learning rate, etc.

[0115] Use the processed sample data and label data mentioned above as the training data of the neural network model. Optimize and solve using algorithms such as gradient descent or Adam. Use sigmod as the activation function to output probability values between 0 and 1, and use the cross-entropy loss function to evaluate the model. Learn the relationship between the sample feature data and the sample label data. Then, by minimizing the model loss function, continuously iterate and optimize the parameters of the model until the set accuracy value is reached, and finally obtain a package coefficient recommendation model.

[0116] There may be errors in the package coefficient recommendation model. A feedback mechanism can be set up so that the package coefficient results can be corrected through the feedback of the staff to further correct the package coefficient recommendation model. And use the newly obtained sample data and label data as the training data set to update the model.

[0117] Step S4: Obtain various dimensional attribute information of the currently initialized item, construct multi-dimensional feature data, and input it into the pre-trained package coefficient recommendation model to obtain the initial package coefficient of the initialized item.

[0118] The initial package coefficient is continuously updated with the item package information (separate packing out of the warehouse or mixed packing out of the warehouse) collected during the subsequent item out-of-warehouse according to the iteration steps of the package coefficient and credibility, and finally an accurate package coefficient is obtained.

[0119] In the solution of the embodiment of the present invention, the accuracy of the package coefficient is evaluated by credibility, and after several package out-of-warehouses of the item's package coefficient, it is finally updated and iterated to an accurate package coefficient, avoiding the problem of the package coefficient remaining unchanged.

[0120] For the package coefficient of the initialized item, by collecting the attribute information with high package coefficient credibility as the sample data of the training sample, and the package coefficient corresponding to the above item data as the label data, a package coefficient recommendation model is generated by training the pre-constructed machine learning model. The initialized item is an item that has never maintained a package coefficient. For the target initialized item, when obtaining the target input data corresponding to the target item, the package coefficient is automatically recommended, which not only avoids the problem of low efficiency of manual maintenance, but also improves the reliability and accuracy of the initial package coefficient. The initial package coefficient can be repeatedly iterated to obtain a final package coefficient with high credibility.

[0121] Figure 4 It is a schematic structural diagram of an item packing processing device provided by an embodiment of the present invention. As Figure 4 shown, the device includes:

[0122] An order acquisition module 401, configured to acquire a target order, determine at least one target item in the target order, and the quantity of each target item;

[0123] A coefficient determination module 402, configured to determine the packing coefficient of each target item; wherein, the packing coefficient of a target item is used to represent the quantity of the target item that can be loaded in a single standard package;

[0124] A packing processing module 403, configured to determine the package specification and / or the number of packages corresponding to the target order according to the packing coefficient and the quantity of each target item; wherein, the package specification and / or the number of packages are used to perform packing processing on the target items in the target order.

[0125] Optionally, it further includes:

[0126] A coefficient generation module, configured to determine the initial packing coefficient of a target item;

[0127] Acquire the historical packing information of the target item;

[0128] According to the historical packing information of the target item, perform optimization processing on the initial packing coefficient of the target item to generate the packing coefficient of the target item.

[0129] Optionally, the coefficient generation module is specifically configured to:

[0130] According to the historical packing information of the target item, determine multiple actual packing coefficients of the target item;

[0131] According to the multiple actual packing coefficients of the target item, perform optimization processing on the initial packing coefficient of the target item to generate the optimized packing coefficient of the target item;

[0132] Determine the credibility corresponding to the optimized packing coefficient;

[0133] In response to the credibility being greater than a preset threshold, determine the optimized packing coefficient as the packing coefficient of the target item.

[0134] Optionally, the coefficient generation module is specifically configured to:

[0135] Determine the current packing information from the historical packing information;

[0136] Determine the packing type corresponding to the current packing information;

[0137] In response to the packing type indicating single-item packing, determine the package specification and the number of packages corresponding to the packing information; according to the package specification and the number of packages corresponding to the packing information, determine the actual packing coefficient of the target item;

[0138] In response to the packaging type indicating hybrid packaging, determine the package specifications corresponding to the packaging information, multiple packaged items, and the packaging quantity of each packaged item; determine the actual package coefficient of the target item according to the package specifications corresponding to the packaging information, multiple packaged items, and the packaging quantity of each packaged item; wherein, the multiple packaged items include the target item.

[0139] Optionally, the coefficient generation module is specifically configured to:

[0140] Determine each other item among the multiple packaged items, where the other item is different from the target item;

[0141] Determine the package coefficient of each other item;

[0142] Using the packaging quantity of each other item as a weight, determine the weighted sum of the package coefficients of each other item;

[0143] Determine the actual package coefficient of the target item according to the package specifications corresponding to the packaging information, the weighted sum of the package coefficients, and the packaging quantity of the target item.

[0144] Optionally, the coefficient generation module is specifically configured to:

[0145] Determine the initial credibility of the target item;

[0146] Obtain multiple packaging information of the target item during the statistical period, and determine the comparison package coefficient corresponding to each packaging information;

[0147] For each comparison package coefficient, determine the difference between the optimized package coefficient and the comparison package coefficient; in response to the difference being within the preset range, increase the credibility of the target item by a first preset value; in response to the difference not being within the preset range, decrease the credibility of the target item by a second preset value.

[0148] Optionally, the coefficient generation module is specifically configured to:

[0149] Obtain the attribute information of the target item;

[0150] Input the attribute information of the target item into the package coefficient recommendation model;

[0151] Determine the initial package coefficient of the target item according to the output of the package coefficient recommendation model.

[0152] An embodiment of the present invention provides an electronic device, including:

[0153] One or more processors;

[0154] A storage device for storing one or more programs,

[0155] When one or more programs are executed by one or more processors, the one or more processors implement the method of any of the above embodiments.

[0156] Reference is made below to Figure 5 , which shows a schematic structural diagram of a computer system 500 of a terminal device suitable for implementing the embodiments of the present invention. Figure 5 The terminal device shown is only an example and should not impose any limitation on the functions and scope of use of the embodiments of the present invention.

[0157] As Figure 5 shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage section 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the system 500 are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0158] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as required. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as required so that a computer program read from it can be installed into the storage section 508 as required.

[0159] In particular, according to the embodiments disclosed in the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program codes for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 509 and / or installed from the removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, the above functions defined in the system of the present invention are executed.

[0160] It should be noted that the computer-readable medium shown in the present invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, in which the computer-readable program code is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0161] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the above module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the block can occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0162] The modules involved in the embodiments of the present invention can be implemented in software or in hardware. The described modules can also be provided in a processor. For example, they can be described as: an order acquisition module, a coefficient determination module, and a packaging processing module. Among them, the names of these modules do not constitute a limitation to the modules themselves in some cases. For example, the order acquisition module can also be described as "a module for acquiring a target order, determining at least one target item in the target order, and the quantity of each target item".

[0163] As another aspect, the present invention also provides a computer-readable medium, which can be included in the device described in the above embodiments; or can exist alone without being assembled into the device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by the device, the device includes:

[0164] acquiring a target order, determining at least one target item in the target order, and the quantity of each target item;

[0165] determining the packaging coefficient of each target item; wherein the packaging coefficient of the target item is used to represent the quantity of the target item that can be loaded in a single standard package;

[0166] determining the package specification and / or the number of packages corresponding to the target order according to the packaging coefficient and the quantity of each target item; wherein the package specification and / or the number of packages are used for packaging the target items in the target order.

[0167] According to the technical solution of the embodiments of the present invention, at least one target item in the target order and the quantity of each target item are determined. According to the packaging coefficient and the quantity of each target item, the package specification and / or the number of packages corresponding to the target order are determined. The packaging coefficient of the target item is used to represent the quantity of the target item that can be loaded in a single standard package. By using the packaging coefficient, the package specification or the number of packages required for item packaging can be accurately determined, which brings convenience to item packaging and can also precisely control the consumable cost.

[0168] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. An article packaging processing method, characterized in that, Including: Obtain a target order, and determine at least one target item in the target order and the quantity of each target item; Determine the packing coefficient of each target item; wherein, the packing coefficient of the target item is used to represent the quantity of the target item that can be loaded in a single standard package; According to the packing coefficient and quantity of each target item, determine the packing specification and / or the number of packages corresponding to the target order; wherein, the packing specification and / or the number of packages are used to pack the target items in the target order.

2. The method according to claim 1, characterized in that, Before determining the packing coefficient of each target item, it further includes: Determine the initial packing coefficient of the target item; Obtain the historical packing information of the target item; According to the historical packing information of the target item, perform optimization processing on the initial packing coefficient of the target item to generate the packing coefficient of the target item.

3. The method according to claim 2, wherein The step of performing optimization processing on the initial packing coefficient of the target item according to the historical packing information of the target item to generate the packing coefficient of the target item includes: According to the historical packing information of the target item, determine multiple actual packing coefficients of the target item; According to the multiple actual packing coefficients of the target item, perform optimization processing on the initial packing coefficient of the target item to generate the optimized packing coefficient of the target item; Determine the credibility corresponding to the optimized packing coefficient; In response to the credibility being greater than a preset threshold, determine the optimized packing coefficient as the packing coefficient of the target item.

4. The method according to claim 3, wherein The step of determining multiple actual packing coefficients of the target item according to the historical packing information of the target item includes: Determine the current packing information from the historical packing information; Determine the packing type corresponding to the current packing information; In response to the packing type representing single-item packing, determine the packing specification and the number of packages corresponding to the packing information; according to the packing specification and the number of packages corresponding to the packing information, determine the actual packing coefficient of the target item; In response to the packing type representing mixed packing, determine the packing specification, multiple packed items and the packing quantity of each packed item corresponding to the packing information; according to the packing specification, multiple packed items and the packing quantity of each packed item corresponding to the packing information, determine the actual packing coefficient of the target item; wherein, the multiple packed items include the target item.

5. The method according to claim 4, characterized in that, The step of determining the actual packing coefficient of the target item according to the packing specification, multiple packed items and the packing quantity of each packed item corresponding to the packing information includes: Determine each other item among the multiple packed items, and the other item is different from the target item; Determine the packing coefficient of each other item; Using the packing quantity of each other item as a weight, determine the weighted sum of the packing coefficients of each other item; According to the packing specification corresponding to the packing information, the weighted sum of the packing coefficients and the packing quantity of the target item, determine the actual packing coefficient of the target item.

6. The method according to claim 3, characterized in that, The step of determining the credibility corresponding to the optimized packing coefficient includes: Determine the initial credibility of the target item; Obtain multiple packing information of the target item during the statistical period, and determine the comparison package coefficient corresponding to each packing information; For each comparison package coefficient, determine the difference between the optimized package coefficient and the comparison package coefficient; in response to the difference being within the preset range, increase the credibility of the target item by a first preset value; in response to the difference not being within the preset range, reduce the credibility of the target item by a second preset value.

7. The method according to claim 2, characterized in that, The determining the initial package coefficient of the target item includes: Obtain the attribute information of the target item; Input the attribute information of the target item into the package coefficient recommendation model; Determine the initial package coefficient of the target item according to the output of the package coefficient recommendation model.

8. An article packaging and processing device, characterized in that, Include: An order acquisition module, configured to acquire a target order, determine at least one target item in the target order and the quantity of each target item; A coefficient determination module, configured to determine the package coefficient of each target item; wherein, the package coefficient of the target item is used to represent the quantity of the target item that can be loaded in a single standard package; A packing processing module, configured to determine the package specification and / or the number of packages corresponding to the target order according to the package coefficient and the quantity of each target item; wherein, the package specification and / or the number of packages are used to perform packing processing on the target items in the target order.

9. An electronic device, characterized in that, Include: One or more processors; A storage device, configured to store one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, The program, when executed by the processor, implements the method according to any one of claims 1-7.

Images