Article loading method and device, computer equipment and computer readable storage medium

Abstract

The invention discloses an article loading method and device, computer equipment and a computer readable storage medium, attribute information of a to-be-distributed target article is acquired, and the attribute information comprises at least one of article volume information and article weight information; according to the attribute information of the target article and a preset classification category, classifying the target article to obtain an article number corresponding to each classification category; the volume ratio coefficient of each classification category is obtained, the volume ratio coefficient is obtained through calculation according to the expected loading rate of the container loaded with the target object and the number of the object samples belonging to each classification category, and the object samples are objects loaded by the container under the condition that the loading rate meets the preset loading condition; and according to the article quantity and the volume ratio coefficient corresponding to each classification category, calculating the container quantity required for loading the target article through the container. According to the method, the number of the required containers can be accurately estimated, the timeliness of article transportation is improved, and the article transportation cost is reduced.

Description

Technical Field

[0001] The present application relates to the field of logistics technology, and in particular to an article loading method, device, computer equipment and computer-readable storage medium. Background Art

[0002] In the field of logistics and transportation, transportation resources are generally estimated based on the quantity of items to be transported. Due to the different volumes of items, estimation based on quantity ignores the volume factor, resulting in inaccurate estimation results, which will cause deviations between the next vehicle scheduling and actual needs, resulting in low average vehicle loading rate or overflow loading, which in turn affects the transportation timeliness and transportation costs of items. Summary of the invention

[0003] The embodiments of the present application provide a method, apparatus, computer device and computer-readable storage medium for loading items, which can accurately estimate the number of containers required, improve the timeliness of item transportation and reduce the cost of item transportation.

[0004] An article loading method provided in an embodiment of the present application includes:

[0005] Acquire attribute information of a target item to be delivered, wherein the attribute information includes at least one of item volume information and item weight information;

[0006] Classify the target objects according to the attribute information of the target objects and the preset classification categories, and obtain the number of objects corresponding to each classification category;

[0007] Obtaining a volume share coefficient of each classification category, wherein the volume share coefficient is calculated according to an expected loading rate of a container for loading the target article and the number of article samples belonging to each classification category, wherein the article samples are articles loaded in the container when the loading rate satisfies a preset loading condition;

[0008] According to the number of items and the volume ratio coefficient corresponding to each classification category, the number of containers required to load the target items through the container is calculated.

[0009] Accordingly, an embodiment of the present application further provides an article loading device, comprising:

[0010] A first information acquisition unit, configured to acquire attribute information of a target item to be delivered, wherein the attribute information includes at least one of item volume information and item weight information;

[0011] A first classification unit, configured to classify the target object according to the attribute information of the target object and a preset classification category, and obtain the number of objects corresponding to each classification category;

[0012] A coefficient acquisition unit, used to acquire a volume share coefficient of each classification category, wherein the volume share coefficient is calculated based on an expected loading rate of a container for loading the target article and the number of article samples belonging to each classification category, wherein the article samples are articles loaded in the container when the loading rate meets a preset loading condition;

[0013] The first calculation unit is used to calculate the number of containers required to load the target article through the container according to the number of articles and the volume ratio coefficient corresponding to each classification category.

[0014] In one embodiment, the article loading device further includes:

[0015] A second information acquisition unit, configured to acquire attribute information of an item sample, wherein the item sample is loaded through the container, and a loading rate of the item sample loaded in the container satisfies the preset loading condition;

[0016] A second classification unit is used to classify the item sample according to the attribute information of the item sample and the classification category to obtain the number of items in each classification category;

[0017] The second calculation unit is used to solve the volume share coefficient corresponding to each classification category according to the expected container loading rate of the container and the number of items in each classification category, so as to obtain the volume share coefficient corresponding to the items in each classification category.

[0018] In one embodiment, the second computing unit includes:

[0019] A condition generation subunit, used to generate a constraint condition for a volume ratio coefficient corresponding to the items in each classification category according to the preset loading rate and the number of items in the item sample in each classification category;

[0020] The optimization subunit is used to solve the volume share coefficient corresponding to each classification category based on the constraint conditions to obtain the volume share coefficient corresponding to the items in each classification category.

[0021] In one embodiment, the optimization subunit includes:

[0022] An enumeration module, used for enumerating volume share coefficient combinations under the constraint conditions, wherein the volume share coefficient combinations include the volume share coefficients corresponding to each classification category;

[0023] A loading rate calculation module, used to calculate a candidate loading rate corresponding to each volume share coefficient combination according to the volume share coefficient corresponding to each classification category in the volume share coefficient combination and the number of items;

[0024] A selection module is used to determine a target volume share coefficient combination according to a minimum difference between the candidate loading rate and the expected container loading rate, and obtain a volume share coefficient corresponding to each classification category according to the target volume share coefficient combination.

[0025] In one embodiment, the article loading device further includes:

[0026] A determination unit, used to determine an initial classification category;

[0027] An adjustment unit, configured to perform category adjustment based on the initial classification category to obtain a plurality of adjusted classification strategies, wherein the adjusted classification strategies include a plurality of classification categories;

[0028] A score calculation unit, used to calculate the strategy score of each adjusted classification strategy according to the attribute information of the items under each classification category in each adjusted classification strategy;

[0029] A selection unit is used to determine the preset classification category from a plurality of adjusted classification strategies according to the strategy score.

[0030] In one embodiment, the computing unit comprises:

[0031] A distance calculation unit, used to calculate the category distance between the classification categories in each adjusted classification strategy and the item distance between the items in each classification category according to the attribute information of the item samples corresponding to each classification category in each adjusted classification strategy;

[0032] The strategy score calculation subunit is used to calculate the strategy score of each adjusted classification strategy according to the category distance and the item distance.

[0033] In one embodiment, the first information acquisition unit includes:

[0034] A waybill information acquisition subunit is used to acquire waybill information of items to be delivered;

[0035] A sorting subunit is used to sort the items to be delivered according to the item flow direction information in the waybill information to obtain the target items corresponding to each item flow direction;

[0036] The attribute information acquisition subunit is used to acquire the attribute information of the target item according to the waybill information of the target item.

[0037] Correspondingly, an embodiment of the present application also provides a computer device, including a memory and a processor; the memory stores a computer program, and the processor is used to run the computer program in the memory to execute any one of the article loading methods provided in the embodiments of the present application.

[0038] Correspondingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store a computer program, and the computer program is loaded by a processor to execute any one of the article loading methods provided in the embodiments of the present application.

[0039] The embodiment of the present application obtains attribute information of the target item to be delivered, where the attribute information includes at least one of item volume information and item weight information; classifies the target item according to the attribute information and preset classification categories, and obtains the number of items corresponding to each classification category; obtains the volume share coefficient of each classification category, where the volume share coefficient is calculated based on the expected loading rate of the container for loading the target item and the number of item samples belonging to each classification category, where the item sample is the item loaded in the container when the loading rate meets the preset loading conditions; calculates the number of containers required to load the target item through the container according to the number of items corresponding to each classification category and the volume share coefficient.

[0040] In the embodiment of the present application, each classification category corresponds to a volume share coefficient, and the volume share coefficient represents the capacity share of the items belonging to the classification category to the container. When the target item does not have the volume information of the item, the classification category can be determined according to its weight information, and then the volume share coefficient of the item can be determined, so as to realize the generalized classification by integrating the attribute information of different dimensions of the item. When the volume data or weight data is missing, the required number of containers can still be accurately estimated, and the vehicles for transporting the items can be accurately dispatched, which can improve the timeliness of the transportation of the items and reduce the transportation cost of the items. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 is a flow chart of the article loading method provided in an embodiment of the present application;

[0043] Figure 2 It is a classification adjustment schematic diagram provided in an embodiment of the present application;

[0044] Figure 3 is a schematic diagram of an article loading system provided in an embodiment of the present application;

[0045] Figure 4 is a schematic diagram of an article loading device provided in an embodiment of the present application;

[0046] Figure 5It is a structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0048] The embodiment of the present application provides an article loading method, device, computer equipment and computer readable storage medium. The article loading device can be integrated in a computer equipment, and the computer equipment can be a server or a terminal.

[0049] The terminal may include a mobile phone, a wearable smart device, a tablet computer, a laptop computer, a personal computer (PC), and a vehicle-mounted computer.

[0050] Among them, the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, as well as big data and artificial intelligence platforms.

[0051] It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments.

[0052] This embodiment will be described from the perspective of an article loading device, which may be integrated into a computer device, which may be a server or a terminal.

[0053] An article loading method provided in an embodiment of the present application is as follows: Figure 1 As shown, the specific process of the item loading method can be as follows:

[0054] 101. Obtain attribute information of a target item to be delivered, where the attribute information includes at least one of item volume information and item weight information.

[0055] The target item may be an item to be delivered, or may be goods or documents sent by a user. Usually, there are two charging methods for sending items, namely, charging by volume or charging by weight. Therefore, the attribute information of the target item may be at least one of the item volume information or the item weight information of the target item. The item volume information includes the volume of the target item, and the item weight information includes the weight of the target item.

[0056] In actual logistics and transportation scenarios, it is necessary to sort items according to flow directions, load items with the same flow directions together, reduce multiple sorting of items due to different flow directions during the item delivery process, and improve the item delivery speed. That is, in one embodiment, the step of "obtaining attribute information of the target item to be delivered" may specifically include:

[0057] Get the waybill information of the items to be delivered;

[0058] According to the item flow information in the waybill information, the items to be delivered are sorted to obtain the target items corresponding to each item flow direction;

[0059] The attribute information of the target item is obtained according to the waybill information of the target item.

[0060] The items to be delivered may be items that have not been sorted according to the flow direction, and the target items may be items that have been sorted according to the flow direction and belong to the same flow direction, and are sent from site A to site F.

[0061] The waybill information may include information such as the direction of flow (ie, the direction of flow of items), volume, and weight of items to be delivered.

[0062] For example, the waybill information of the items to be delivered may be obtained, and the items to be delivered may be sorted according to the item flow direction information in the waybill information to obtain the target items corresponding to each item flow direction.

[0063] The article loading method provided in the embodiment of the present application can estimate the number of containers required to load the target articles of each article flow. First, it is necessary to obtain the attribute information of the target articles based on the waybill information of the target articles of each article flow.

[0064] If the target item information has item volume information, the item volume information is preferentially obtained as the attribute information of the target item. If the target item does not have item volume information, the item weight information of the target item is obtained as the attribute information of the target item.

[0065] The container for loading the target items can be a cage, a container, a shelf, or other equipment for loading items, wherein the cage can be a cage prefabricated in the logistics field according to transportation requirements, with accessories of certain size and characteristics, such as a foldable handle and a cart.

[0066] In the subsequent steps 102-104, the number of containers required for loading can be predicted based on the attribute information of the target item. The specific process is detailed in the description of the subsequent steps and will not be repeated here.

[0067] 102. Classify the target objects according to the attribute information of the target objects and the preset classification categories, and obtain the number of objects corresponding to each classification category.

[0068] The preset classification category may be a pre-set category, such as a category that may be pre-set by a developer, operator or other staff member. Several volume intervals and weight intervals may be set to classify target items, for example, a volume greater than 5m 3 , greater than 2m 3 And less than 5m 3 Less than 2m 3 , greater than 5kg and less than 5kg, etc.; the preset classification categories can also be categories calculated based on algorithms, etc.

[0069] For example, if the attribute information of the target item includes item volume information, the target item is classified according to the target item volume information; if the attribute information of the target item does not include item volume information, the target item is classified according to the target item weight information to obtain the classification category corresponding to each target item and the number of target items in each classification category.

[0070] 103. Obtain a volume share coefficient for each classification category. The volume share coefficient is calculated based on an expected loading rate of a container for loading target items and the number of item samples belonging to each classification category. The item samples are items loaded into the container when the loading rate meets a preset loading condition.

[0071] The volume share coefficient of each classification category can represent the proportion of the container capacity occupied by each item belonging to the classification category. According to the volume share coefficient of the classification category and the number of items under the classification category, the number of containers required for all items under the classification category can be calculated; according to the volume share coefficient of each classification category and the corresponding number of items, the number of containers required to load items of all classification categories can be calculated.

[0072] Among them, the volume share coefficient can be calculated based on the item sample, which is the item in the set of items loaded in the container when the loading rate of the container meets the preset loading conditions. According to the item sample, the distribution of items of different classification categories in the container when the loading rate of the container meets the preset loading conditions can be determined, so that the volume share coefficient of the items without item volume information can be estimated.

[0073] The volume share coefficient of each classification category may be determined before calculating the number of containers for loading the target items, that is, before the step of “obtaining the volume share coefficient of each classification category”, the method for loading items provided in the present application may further include:

[0074] Acquiring attribute information of an item sample, the item sample is loaded through a container, and a loading rate of the item sample loaded in the container satisfies a preset loading condition;

[0075] Classify the items in the item sample according to the attribute information and classification category of the item sample, and obtain the number of items in each classification category;

[0076] According to the expected container loading rate of the container and the number of items in each classification category, the volume share coefficient corresponding to each classification category is solved to obtain the volume share coefficient corresponding to the items in each classification category.

[0077] Among them, the expected container loading rate can be a loading rate range, and the loading rate range can be determined according to the loading rate of the container during actual transportation. The expected container loading rate can constrain the container loading rate to fluctuate within a reasonable range; optionally, the expected container loading can also be the actual loading rate of the item sample.

[0078] For example, the items loaded in the container whose loading rate meets the preset loading condition can be obtained from the historical container loading data to obtain an item set, and the items in the item set are item samples. Each item set can be considered as a sample for solving a set of volume ratio coefficients. The preset loading condition can be that the loading rate is greater than a preset threshold (such as 95%, or 90%, etc.).

[0079] For each item set, the item samples are classified according to their attribute information to obtain the classification category corresponding to each item sample and the number of items in each classification category.

[0080] The volume share coefficient of each classification category can be predicted by the neural network model. Specifically, after classifying the item samples, the attribute information of the item samples and the corresponding classification categories are input into the neural network model, and the volume share coefficient of each classification category is predicted by the neural network model. The predicted loading rate of the item samples in the container is calculated according to the predicted volume share coefficient, and the loss value is calculated according to the predicted loading rate and the actual loading rate. Then, the neural network model is trained according to the loss value until the loss value is less than a preset threshold value, and the predicted volume share coefficient output by the neural network model at this time is used as the volume share coefficient.

[0081] Optionally, the volume share coefficients may be constrained according to the expected container loading rate to find the optimal volume share coefficient combination, that is, in one embodiment, the step of "solving the volume share coefficient corresponding to each classification category according to the expected container loading rate of the container and the number of items in each classification category to obtain the volume share coefficient corresponding to the items in each classification category" includes:

[0082] Generate a constraint condition for the volume ratio of each item in each classification category according to the expected container loading rate and the number of items in the item sample in each classification category;

[0083] Based on the constraints, the volume ratio coefficient corresponding to each classification category is solved to obtain the volume ratio coefficient corresponding to the items in each classification category.

[0084] For example, the expected container filling rate can be the filling rate interval [b u ,b l ], assuming that there are M sets of items, h categories, and the number of items in k categories are {k1, k2, k3, k..., h}, then the constraints can be:

[0085]

[0086] Under this constraint, the difference in volume ratio between different classification categories is maximized to distinguish different classification categories as much as possible, so the optimization index can be:

[0087] Thus, a combination of volume share coefficients that maximizes z is solved, and the volume share coefficient of each classification category is obtained.

[0088] Optionally, the volume ratio coefficient can be solved by an operations research optimization algorithm, which can be implemented using operations research optimization tools such as Gurobi, Lingo, ortools, CPLEX or XPRESS. It can also be solved by introducing Lagrange multipliers and then using LIBSVM for machine learning methods.

[0089] Optionally, the loading rate of the volume share coefficient combination may also be calculated, and the optimal share coefficient combination may be sought by minimizing the difference between the actual loading rate and the loading rate. That is, in one embodiment, the step of "solving the volume share coefficient corresponding to each classification category based on the constraint condition to obtain the volume share coefficient corresponding to the items in each classification category" includes:

[0090] Enumerate volume share coefficient combinations under constraints, where the volume share coefficient combinations include the volume share coefficients corresponding to each classification category;

[0091] According to the volume share coefficient and the number of items corresponding to each classification category in the volume share coefficient combination, the candidate loading rate corresponding to each volume share coefficient combination is calculated;

[0092] According to the minimum gap between the candidate loading rate and the expected container loading rate, the target volume share coefficient combination is determined, and the volume share coefficient corresponding to each classification category is obtained according to the target volume share coefficient combination.

[0093] The expected container loading rate may be a real loading rate, which is used to constrain the volume share coefficient so that the loading rate calculated based on the volume share coefficient does not exceed the real loading rate.

[0094] For example, suppose there are M sets of items, h categories, and the number of items in k categories is {k1,k2,k3,k...,k h}, then the constraint can be A is the desired container filling rate.

[0095] Enumerate the volume share coefficient combinations that meet the constraint condition, and calculate the corresponding loading rate according to each volume share coefficient combination, and then calculate the loss between the loading rate and the expected container loading rate. The loss calculation is shown in the following formula:

[0096]

[0097] in, The volume share coefficient corresponding to each classification category in the volume share coefficient combination is determined as the target volume share coefficient combination, and the volume share coefficient of each classification category in the target volume share coefficient combination is used for subsequent estimation of the number of containers.

[0098]

[0099] Optionally, the preset classification category can also be obtained by adjusting the initial classification category. The initial classification category can be preset by developers, operators or other staff. For example, several volume intervals and weight intervals can be set to classify the target items. Classification according to the initial classification category can be considered as rough classification. An aggregate classification evaluation method can be defined based on the attribute information of the target item, and the initial classification category can be adjusted according to the aggregate classification evaluation method to obtain the preset classification category. That is, in one embodiment, before the step of "classifying the item sample according to the attribute information of the item sample and the preset classification category to obtain the number of items corresponding to each classification category", the item loading method provided in the embodiment of the present application can also include:

[0100] Determine initial classification categories;

[0101] Performing category adjustment based on the initial classification category to obtain multiple adjusted classification strategies, the adjusted classification strategies including multiple classification categories;

[0102] Calculate the strategy score of each adjusted classification strategy according to the attribute information of the items under each classification category in each adjusted classification strategy;

[0103] A preset classification category is determined from a plurality of adjusted classification strategies according to the strategy score.

[0104] The initial classification categories may be a group of categories pre-set by developers for classifying items, and the above classification categories are obtained by adjusting the initial classification categories.

[0105] For example, the initial classification categories may be determined, and an adjusted classification strategy may be obtained by adjusting the number of classification categories (eg, increasing classification categories) and adjusting the intervals corresponding to the classification categories. The adjusted classification strategy includes a set of categories for classifying items.

[0106] The item samples are classified according to a set of classification categories in the adjusted classification strategy, the number of categories corresponding to each classification category is obtained, the distance between each classification is calculated (maximizing the inter-class distance), and the inter-class distance is used as the strategy score. The calculation formula can be shown as follows:

[0107]

[0108] Among them, L B represents the distance between classes, k represents the number of classification categories in the adjusted classification strategy, m represents the mean volume or weight of the item samples, and m j It represents the mean volume / mean weight of the item samples under the j-th classification category of the adjusted classification strategy.

[0109] Seek an adjusted classification strategy that maximizes the inter-class distance. Maximizing the inter-class distance expects to maximize the distance distinction between each classification center and distinguish the two classification categories as much as possible.

[0110] Optionally, the optimal adjusted classification strategy can be solved based on minimizing the intra-class distance. The intra-class distance can be used as a strategy score. Minimizing the intra-class distance expects each classification to be as dense as possible. The calculation formula of the intra-class distance can be as follows:

[0111]

[0112] Among them, L c represents the intra-class distance, k represents the number of classification categories in the adjusted classification strategy, and m jIt represents the volume mean or weight mean of the item samples in the jth classification category after the classification strategy is adjusted. The volume or weight of the i-th item sample under the j-th classification category, n j It represents the number of items in the jth classification category of the adjusted classification strategy, and N represents the number of item samples in an item set, or the total number of item samples in multiple item sets.

[0113] Optionally, the strategy score may be calculated based on the inter-class distance and the intra-class distance, and the optimal adjusted classification strategy may be solved based on the strategy score. That is, in one embodiment, the step of "calculating the strategy score of each adjusted classification strategy based on the attribute information of the items under each classification category in each adjusted classification strategy" may specifically include:

[0114] According to the attribute information of the item samples corresponding to each classification category in each adjusted classification strategy, the category distance between the classification categories in each adjusted classification strategy and the item distance between the items in each classification category are calculated;

[0115] Based on the category distance and item distance, the policy score of each adjusted classification policy is calculated.

[0116] For example, the inter-class information entropy of each adjusted classification strategy can be calculated, and the inter-class information entropy can be used as the strategy score to seek an adjusted classification strategy that maximizes the inter-class information entropy. The maximization of the inter-class information entropy expects that each classification is as uniform as possible. The calculation formula can be as follows:

[0117]

[0118] p i It represents the ratio of the number of items in the i-th classification category in the adjusted classification strategy to the total number of items in all classification categories in the adjusted classification strategy.

[0119] In one embodiment, the optimization index may also be set as: argmax{H c +(L B +1) / (L c +1)|, the calculation of this optimization index not only avoids the problem of incomparable differences between dimensions of different dimensions, but also avoids the ambiguity of introducing hyperparameter variables, and has better guidance in the classification evaluation and comparison process.

[0120] In the above process of solving the optimal adjusted classification strategy, the classification categories based on the volume of the items can be adjusted first to obtain the adjusted classification strategy for the classification categories based on the volume of the items, and then the classification categories based on the weight of the items can be adjusted to obtain the adjusted classification strategy for the classification categories based on the weight of the items.

[0121] The classification categories for classifying item volumes are adjusted, and the adjusted classification strategy can be obtained as follows Figure 2 As shown, there are 12 classification categories in total, with low overlap and good discrimination between different categories.

[0122] Based on the above process, the attribute information of different dimensions (volume / weight) of the items can be integrated to classify the items. Based on the generalized category estimation method, even when the attribute data of a single dimension is incomplete or inaccurate, classification and estimation of the required number of containers can still be performed.

[0123] Optionally, after the classification categories are obtained by classifying the initial classification categories, the volume share coefficients of the classification categories may be calculated.

[0124] 104. Calculate the number of containers required to load the target items through the container according to the number of items and the volume ratio coefficient corresponding to each classification category.

[0125] Assume that for a given site A to site F (for example, from Beijing to Shenzhen), the cumulative number of caged items in a certain period of time t is set Ω, and there are a total of w different pre-sorting directions (for example, to different areas in Shenzhen), and the item classification set is {C1, C2, C3, C..., C h}, the corresponding volume ratio is {θ1,θ2,θ3,θ...,θ h}, the number of each category in each flow direction is expressed as {n1,n2,n3,n...,n h}, then the cumulative cage value from site A to site F in a certain period of time t is:

[0126]

[0127] Optionally, the product of the number of items in each classification category and the volume ratio coefficient may be rounded up to increase the error tolerance.

[0128] The flow direction can be a spatial code obtained according to the delivery destination of the goods, and the size of the area is set according to application needs.

[0129] Described from the perspective of the item loading system, such as Figure 3As shown, the item loading system may include three system modules, namely a coefficient pre-training module, a real-time data access module and a container quantity estimation module.

[0130] Among them, the coefficient pre-training module is used to find the optimal classification strategy for classifying items based on the attribute information of the item samples offline, as well as to find the optimal volume ratio coefficient combination.

[0131] The real-time data access module is used to obtain the target items to be delivered, obtain the attribute information of the items based on the AI ​​camera scan, and obtain the attribute information and flow direction of the target items based on the waybill information of the target items to be delivered, and group the target items according to the flow direction. Then, the attribute information of the target items and the corresponding flow grouping information are summarized and input into the container quantity estimation module.

[0132] The container quantity estimation module estimates the required number of containers based on the classification strategy and volume ratio coefficient combination obtained by the offline volume coefficient pre-training module, as well as the attribute information of the target items and the corresponding traffic grouping information input by the real-time data access module, and inputs the number of containers.

[0133] Optionally, after the target items are loaded, the loading rate of the container can be calculated, and the items loaded in the container whose loading rate meets the conditions can be used as item samples to adjust the optimal classification strategy and volume ratio coefficient combination to achieve a more accurate estimation of the number of containers.

[0134] As can be seen from the above, the embodiment of the present application obtains attribute information of the target items to be delivered, where the attribute information includes at least one of item volume information and item weight information; classifies the target items according to the attribute information of the target items and preset classification categories, and obtains the number of items corresponding to each classification category; obtains the volume share coefficient of each classification category, where the volume share coefficient is calculated based on the expected loading rate of the container for loading the target items, and the number of item samples belonging to each classification category, where the item sample is the item loaded in the container when the loading rate meets the preset loading conditions; calculates the number of containers required to load the target items through the container according to the number of items corresponding to each classification category and the volume share coefficient.

[0135] In the embodiment of the present application, each classification category corresponds to a volume share coefficient, and the volume share coefficient represents the capacity share of the items belonging to the classification category to the container. When the target item does not have the volume information of the item, the classification category can be determined according to its weight information, and then the volume share coefficient of the item can be determined, so as to realize the generalized classification by integrating the attribute information of different dimensions of the item. When the volume data or weight data is missing, the required number of containers can still be accurately estimated, and then the vehicles for transporting the items can be accurately dispatched, thereby reducing the transportation cost of the items.

[0136] In order to facilitate better implementation of the article loading method provided in the embodiment of the present application, an article loading device is also provided in one embodiment. The meanings of the terms are the same as those in the above-mentioned article loading method, and the specific implementation details can refer to the description in the method embodiment.

[0137] The article loading device may be integrated into a computer device, such as Figure 4 As shown, the article loading device may include: a first information acquisition unit 301, a first classification unit 302, a coefficient acquisition unit 303 and a first calculation unit 304, which are specifically as follows:

[0138] (1) A first information acquisition unit 301 is used to acquire attribute information of a target item to be delivered, where the attribute information includes at least one of item volume information and item weight information.

[0139] In one embodiment, the first information acquisition unit may include a waybill information acquisition subunit, a sorting subunit and an attribute information acquisition subunit, specifically:

[0140] Waybill information acquisition subunit: used to obtain waybill information of items to be delivered;

[0141] Sorting subunit: used to sort the items to be delivered according to the item flow direction information in the waybill information, and obtain the target items corresponding to each item flow direction;

[0142] Attribute information acquisition subunit: used to acquire the attribute information of the target item according to the waybill information of the target item.

[0143] (2) A first classification unit 302 is used to classify the target object according to the attribute information of the target object and the preset classification categories, and obtain the number of objects corresponding to each classification category.

[0144] (3) Coefficient acquisition unit 303: used to obtain the volume share coefficient of each classification category. The volume share coefficient is calculated based on the expected loading rate of the container for loading the target item and the number of item samples belonging to each classification category. The item sample is the item loaded in the container when the loading rate meets the preset loading conditions.

[0145] In one embodiment, the article loading device may further include a second information acquisition unit, a second classification unit, and a second calculation unit. Specifically:

[0146] A second information acquisition unit is used to acquire attribute information of an item sample, the item sample is loaded through a container, and the loading rate of the item sample loaded in the container meets a preset loading condition;

[0147] The second classification unit is used to classify the item samples according to the attribute information and classification categories of the item samples, and obtain the number of items in each classification category;

[0148] The second calculation unit is used to solve the volume share coefficient corresponding to each classification category according to the expected container loading rate of the container and the number of items in each classification category, so as to obtain the volume share coefficient corresponding to the items in each classification category.

[0149] In one embodiment, the second computing unit may include a condition generating subunit and an optimization subunit, specifically:

[0150] Condition generation subunit: used to generate constraint conditions for the volume ratio coefficient corresponding to the items in each classification category according to the preset loading rate and the number of items in the item sample in each classification category;

[0151] Optimization subunit: used to solve the volume ratio coefficient corresponding to each classification category based on the constraint conditions, and obtain the volume ratio coefficient corresponding to the items in each classification category.

[0152] In one embodiment, the optimization subunit may include an enumeration module, a loading rate calculation module and a selection module, specifically:

[0153] Enumeration module: used to enumerate volume ratio coefficient combinations under constraints. The volume ratio coefficient combinations include the volume ratio coefficients corresponding to each classification category.

[0154] Loading rate calculation module: used to calculate the candidate loading rate corresponding to each volume share coefficient combination according to the volume share coefficient and the number of items corresponding to each classification category in the volume share coefficient combination;

[0155] Selection module: used to determine the target volume share coefficient combination according to the minimum gap between the candidate loading rate and the expected container loading rate, and obtain the volume share coefficient corresponding to each classification category according to the target volume share coefficient combination.

[0156] In one embodiment, the article loading device may further include a determination unit, an adjustment unit, a score calculation unit, and a selection unit. Specifically:

[0157] Determination unit: used to determine the initial classification category;

[0158] Adjustment unit: used for adjusting the category based on the initial classification category to obtain multiple adjusted classification strategies, the adjusted classification strategies including multiple classification categories;

[0159] A score calculation unit: used to calculate the strategy score of each adjusted classification strategy according to the attribute information of the items under each classification category in each adjusted classification strategy;

[0160] A selection unit is used to determine a preset classification category from a plurality of adjusted classification strategies according to a strategy score.

[0161] In one embodiment, the calculation unit may include a distance calculation unit and a strategy score calculation subunit, specifically:

[0162] A distance calculation unit: used to calculate the category distance between the classification categories in each adjusted classification strategy and the item distance between the items in each classification category according to the attribute information of the item samples corresponding to each classification category in each adjusted classification strategy;

[0163] Strategy score calculation subunit: used to calculate the strategy score of each adjusted classification strategy according to the category distance and item distance.

[0164] (4) A first calculation unit 304: used to calculate the number of containers required to load the target items through the container according to the number of items and the volume ratio coefficient corresponding to each classification category.

[0165] As can be seen from the above, the article loading device of the embodiment of the present application obtains the attribute information of the target article to be delivered through the first information acquisition unit 301, and the attribute information includes at least one of the article volume information and the article weight information; the first classification unit 302 classifies the target article according to the attribute information of the target article and the preset classification category, and obtains the number of articles corresponding to each classification category; the coefficient acquisition unit 303 obtains the volume share coefficient of each classification category, and the volume share coefficient is calculated according to the expected loading rate of the container for loading the target article, and the number of article samples belonging to each classification category, and the article sample is the article loaded in the container when the loading rate meets the preset loading conditions; the first calculation unit 304 calculates the number of containers required to load the target article through the container according to the number of articles corresponding to each classification category and the volume share coefficient.

[0166] In the embodiment of the present application, each classification category corresponds to a volume share coefficient, and the volume share coefficient represents the capacity share of the items belonging to the classification category to the container. When the target item does not have the volume information of the item, the classification category can be determined according to its weight information, and then the volume share coefficient of the item can be determined, so as to realize the generalized classification by integrating the attribute information of different dimensions of the item. When the volume data or weight data is missing, the required number of containers can still be accurately estimated, and then the vehicles for transporting the items can be accurately dispatched, thereby reducing the transportation cost of the items.

[0167] The present application also provides a computer device, which may be a terminal or a server. Figure 5 As shown, it shows a schematic diagram of the structure of the computer device involved in the embodiment of the present application, specifically:

[0168] The computer device may include components such as a processor 1001 with one or more processing cores, a memory 1002 with one or more computer-readable storage media, a power supply 1003, and an input unit 1004. Those skilled in the art will appreciate that Figure 5 The computer device structure shown in the figure does not constitute a limitation on the computer device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0169] The processor 1001 is the control center of the computer device. It uses various interfaces and lines to connect various parts of the entire computer device. By running or executing software programs and / or modules stored in the memory 1002 and calling data stored in the memory 1002, it executes various functions of the computer device and processes data, thereby monitoring the computer device as a whole. Optionally, the processor 1001 may include one or more processing cores; preferably, the processor 1001 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and computer programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 1001.

[0170] The memory 1002 can be used to store software programs and modules. The processor 1001 executes various functional applications and data processing by running the software programs and modules stored in the memory 1002. The memory 1002 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, a computer program required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 1002 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 1002 may also include a memory controller to provide the processor 1001 with access to the memory 1002.

[0171] The computer device also includes a power supply 1003 for supplying power to various components. Preferably, the power supply 1003 can be logically connected to the processor 1001 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 1003 can also include any components such as one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators.

[0172] The computer device may further include an input unit 1004, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0173] Although not shown, the computer device may further include a display unit, etc., which will not be described in detail herein. Specifically, in this embodiment, the processor 1001 in the computer device will load the executable files corresponding to the processes of one or more computer programs into the memory 1002 according to the following instructions, and the processor 1001 will run the computer programs stored in the memory 1002, thereby realizing various functions, as follows:

[0174] Acquire attribute information of a target item to be delivered, the attribute information including at least one of item volume information and item weight information;

[0175] Classify the target objects according to the attribute information of the target objects and the preset classification categories, and obtain the number of objects corresponding to each classification category;

[0176] Obtaining a volume share coefficient for each classification category, the volume share coefficient being calculated based on an expected loading rate of a container for loading target items and the number of item samples belonging to each classification category, where the item samples are items loaded into the container when the loading rate meets a preset loading condition;

[0177] According to the number of items and volume ratio coefficient corresponding to each classification category, the number of containers required to load the target items through the container is calculated.

[0178] The specific implementation of the above operations can be found in the previous embodiments and will not be described in detail here.

[0179] As can be seen from the above, the computer device of the embodiment of the present application can obtain attribute information of the target item to be delivered, where the attribute information includes at least one of item volume information and item weight information; classify the target item according to the attribute information of the target item and the preset classification category, and obtain the number of items corresponding to each classification category; obtain the volume share coefficient of each classification category, where the volume share coefficient is calculated based on the expected loading rate of the container for loading the target item, and the number of item samples belonging to each classification category, where the item sample is the item loaded in the container when the loading rate meets the preset loading conditions; calculate the number of containers required to load the target item through the container according to the number of items corresponding to each classification category and the volume share coefficient.

[0180] In the embodiment of the present application, each classification category corresponds to a volume share coefficient, and the volume share coefficient represents the capacity share of the items belonging to the classification category to the container. When the target item does not have the volume information of the item, the classification category can be determined according to its weight information, and then the volume share coefficient of the item can be determined, so as to realize the generalized classification by integrating the attribute information of different dimensions of the item. When the volume data or weight data is missing, the required number of containers can still be accurately estimated, and then the vehicles for transporting the items can be accurately dispatched, thereby reducing the transportation cost of the items.

[0181] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in various optional implementations in the above-mentioned embodiments.

[0182] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by a computer program, or by controlling related hardware through a computer program. The computer program may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0183] To this end, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. The computer program can be loaded by a processor to execute any one of the article loading methods provided in the embodiments of the present application.

[0184] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0185] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0186] Since the computer program stored in the computer-readable storage medium can execute any one of the article loading methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any one of the article loading methods provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0187] The above is a detailed introduction to an article loading method, device, computer equipment and computer-readable storage medium provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for loading items, It is characterized in that include: Acquire attribute information of a target item to be delivered, wherein the attribute information includes at least one of item volume information and item weight information; Classify the target objects according to the attribute information of the target objects and the preset classification categories, and obtain the number of objects corresponding to each classification category; Obtaining a volume share coefficient of each classification category, wherein the volume share coefficient is calculated according to an expected loading rate of a container for loading the target article and the number of article samples belonging to each classification category, wherein the article samples are articles loaded in the container when the loading rate satisfies a preset loading condition; According to the number of items and the volume ratio coefficient corresponding to each classification category, the number of containers required to load the target items through the container is calculated.

2. The method according to claim 1, It is characterized in that Before obtaining the volume share coefficient of each classification category, the method further includes: Acquiring attribute information of an item sample, the item sample is loaded through the container, and a loading rate of the item sample loaded in the container satisfies the preset loading condition; Classify the item samples according to the attribute information of the item samples and the classification categories to obtain the number of items in each classification category; According to the expected container loading rate of the container and the number of items in each classification category, the volume share coefficient corresponding to each classification category is solved to obtain the volume share coefficient corresponding to the items in each classification category.

3. The method according to claim 2, It is characterized in that According to the expected container loading rate of the container and the number of items in each classification category, the volume share coefficient corresponding to each classification category is solved to obtain the volume share coefficient corresponding to the items in each classification category, including: Generate a constraint condition for a volume ratio coefficient corresponding to the items in each classification category according to the expected container loading rate and the number of items in the item sample in each classification category; Based on the constraint conditions, the volume share coefficient corresponding to each classification category is solved to obtain the volume share coefficient corresponding to the items in each classification category.

4. The method according to claim 2, It is characterized in that Solving the volume ratio coefficient corresponding to each classification category based on the constraint condition to obtain the volume ratio coefficient corresponding to the items in each classification category includes: Enumerating a volume share coefficient combination under the constraint condition, wherein the volume share coefficient combination includes a volume share coefficient corresponding to each classification category; Calculate the candidate loading rate corresponding to each volume share coefficient combination according to the volume share coefficient and the number of items corresponding to each classification category in the volume share coefficient combination; According to the minimum gap between the candidate loading rate and the expected container loading rate, a target volume share coefficient combination is determined, and the volume share coefficient corresponding to each classification category is obtained according to the target volume share coefficient combination.

5. The method according to claim 2, It is characterized in that Before classifying the target objects according to the attribute information of the target objects and the preset classification categories to obtain the number of objects corresponding to each classification category, the method further includes: Determine initial classification categories; Performing category adjustment based on the initial classification category to obtain a plurality of adjusted classification strategies, wherein the adjusted classification strategies include a plurality of classification categories; Calculate the strategy score of each adjusted classification strategy according to the attribute information of the items under each classification category in each adjusted classification strategy; The preset classification category is determined from a plurality of adjusted classification strategies according to the strategy score.

6. The method according to claim 5, It is characterized in that The step of calculating the strategy score of each adjusted classification strategy according to the attribute information of the items in each classification category in each adjusted classification strategy comprises: According to the attribute information of the item samples corresponding to each classification category in each adjusted classification strategy, the category distance between the classification categories in each adjusted classification strategy and the item distance between the items in each classification category are calculated; A strategy score of each adjusted classification strategy is calculated according to the category distance and the item distance.

7. The method according to any one of claims 1 to 6, It is characterized in that The step of obtaining the attribute information of the target item to be delivered includes: Get the waybill information of the items to be delivered; Sorting the items to be delivered according to the item flow direction information in the waybill information to obtain the target items corresponding to each item flow direction; The attribute information of the target item is obtained according to the waybill information of the target item.

8. An article loading device, It is characterized in that include: A first information acquisition unit, configured to acquire attribute information of a target item to be delivered, wherein the attribute information includes at least one of item volume information and item weight information; A first classification unit, configured to classify the target object according to the attribute information of the target object and a preset classification category, and obtain the number of objects corresponding to each classification category; A coefficient acquisition unit, used to acquire a volume share coefficient of each classification category, wherein the volume share coefficient is calculated based on an expected loading rate of a container for loading the target article and the number of article samples belonging to each classification category, wherein the article samples are articles loaded in the container when the loading rate meets a preset loading condition; The first calculation unit is used to calculate the number of containers required to load the target article through the container according to the number of articles and the volume ratio coefficient corresponding to each classification category.

9. A computer device, It is characterized in that It comprises a memory and a processor; the memory stores a computer program, and the processor is used to run the computer program in the memory to execute the article loading method according to any one of claims 1 to 7.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium is used to store a computer program, and the computer program is loaded by a processor to execute the article loading method according to any one of claims 1 to 7.

Images