Waybill allocation decision-making method and device, computer readable storage medium and equipment

Abstract

The invention relates to the technical field of computers, and provides a waybill distribution decision-making method, a waybill distribution decision-making device, a computer readable storage medium and electronic equipment, and the waybill distribution decision-making method comprises the steps: constructing a decision variable; calculating the average freight of each carrier under each multi-factor combination according to the quotation data of each carrier; the quotation data of each carrier comprises stepped quotation of each carrier for each multi-factor combination; determining a first total freight expression of the I carriers under J * L multi-factor combinations according to the decision variable and the average freight of each carrier under each multi-factor combination; taking the first total freight expression as a first objective function, and constructing a numerical constraint condition about a decision variable; and taking the minimum value of the first target function as an optimization target, solving the first target function based on a numerical constraint condition, and obtaining the value of the decision variable. According to the invention, the waybill assignment cost can be reduced to the maximum extent.

Description

Background Art

[0002] With the rapid development and progress of the Internet and computer technology, the related logistics service industry is also constantly developing towards service diversification. Logistics companies not only provide a wealth of express delivery and other transportation products, but also provide a variety of warehousing services, such as collaborative warehouses and dedicated warehouses. Warehousing services mainly store the goods of the goods supplier in the warehouse and provide storage, distribution, transportation and other services to the goods supplier. This can help the goods supplier better serve consumers and save certain supply chain costs. For warehousing + distribution services, decision makers need to consider how to choose the appropriate distribution method to maximize the savings in distribution costs. Given that there are many carriers that can provide distribution services and different carriers have different quotation methods, decision makers need to consider how to assign waybills to different carriers.

[0003] In the related art, decision makers generally compare the prices of different carriers based on historical order volumes and then select one or more carriers. However, the above solution cannot guarantee lower delivery costs.

[0004] In view of this, there is an urgent need in this field to develop a new waybill allocation decision method and device.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure. Summary of the invention

[0006] The purpose of the present disclosure is to provide a waybill allocation decision method, a waybill allocation decision device, a computer-readable storage medium and an electronic device, thereby overcoming the technical problem of high delivery costs caused by the limitations of related technologies to at least a certain extent.

[0007] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0008] According to a first aspect of the present disclosure, a waybill allocation decision method is provided, comprising:

[0009] Constructing a decision variable; the decision variable represents the pre-allocated waybill quantity for each carrier in a future period under each multi-factor combination, wherein the multi-factor combination is composed of at least a waybill flow direction and a weight range;

[0010] Calculating the average freight rate of each carrier under each combination of multiple factors according to the quotation data of each carrier; the quotation data of each carrier includes the tiered quotation of each carrier for each combination of multiple factors;

[0011] Determine a first total freight expression of I carriers under J*L multi-factor combinations according to the decision variables and the average freight of each carrier under each multi-factor combination, where I, J, and L are all integers greater than 1;

[0012] Taking the first total freight expression as a first objective function, and constructing numerical constraints on the decision variables;

[0013] The minimum value of the first objective function is taken as the optimization goal, the first objective function is solved based on the numerical constraint condition, and the value of the decision variable is obtained.

[0014] In an exemplary embodiment of the present disclosure, after determining a first total freight expression of I carriers under J*L multi-factor combinations according to the decision variables and the average freight rate of each carrier under each multi-factor combination, the method further includes:

[0015] Obtain the predicted shipping order volume of the target warehouse under each combination of the above multiple factors in the future period;

[0016] Determining a target freight rate for each combination of the multiple factors according to the predicted shipping order volume and the quotation data of each carrier;

[0017] Determine a second total freight expression according to the J*L target freights corresponding to the J*L combinations of multiple factors;

[0018] constructing a second objective function according to the difference between the first total freight expression and the second total freight expression;

[0019] The minimum value of the second objective function is taken as the optimization goal, and the second objective function is solved based on the numerical constraint condition to obtain the value of the decision variable.

[0020] In an exemplary embodiment of the present disclosure, the step of calculating the average freight rate of each carrier under each combination of multiple factors according to the quotation data of each carrier includes:

[0021] Calculate first freight data according to the quotation data; the first freight data is used to represent the average freight rate of each carrier under each combination of multiple factors when the decision variable belongs to each order quantity interval in the K order quantity intervals;

[0022] Configuring a weight variable corresponding to each order volume interval of each carrier, wherein the weight variable is within a preset value range;

[0023] Calculating a first product between each of the first freight data and each of the weight variables;

[0024] The accumulated value of the K first products is determined as the average freight rate per unit of each carrier under each combination of the multiple factors.

[0025] In an exemplary embodiment of the present disclosure, the method of determining a first total freight expression of I carriers under J*L multi-factor combinations according to the decision variables and the average freight rate of each carrier under each multi-factor combination includes:

[0026] Calculating a second product between the decision variable and the average freight rate of each carrier under each combination of the multiple factors;

[0027] The first total freight expression is determined according to the accumulated value of I*J*L second products.

[0028] In an exemplary embodiment of the present disclosure, the step of obtaining the predicted shipping order quantity of the target warehouse in the future period under each combination of the multiple factors includes:

[0029] Collecting the time series data of the shipping order quantity of the target warehouse in the historical period and the time period characteristics corresponding to the historical period;

[0030] Decomposing the time series data of the waybill quantity into time series to obtain a trend item sequence, a season item sequence and a residual item sequence; wherein the trend item sequence represents the change trend of the time series data of the waybill quantity, the season item sequence represents the change cycle of the time series data of the waybill quantity, and the residual item sequence represents the fluctuation characteristics of the time series data of the waybill quantity;

[0031] According to the trend item sequence, the season item sequence and the residual item sequence combined with the period characteristics corresponding to the historical period, the trend item prediction result, the season item prediction result and the residual item prediction result are predicted;

[0032] The predicted waybill quantity of the target warehouse under each combination of the multiple factors in a future period is determined according to the trend item prediction result, the season item prediction result and the remaining item prediction result.

[0033] In an exemplary embodiment of the present disclosure, determining the target freight rate for each combination of multiple factors according to the predicted shipping order volume and the quotation data of each carrier includes:

[0034] Determine the lowest freight rate corresponding to the target carrier with the lowest quote for each combination of multiple factors;

[0035] Obtaining a predicted standard deviation corresponding to the predicted waybill quantity, and calculating a predicted waybill quantity correction value for each combination of the multiple factors according to the predicted waybill quantity, the predicted standard deviation, and a preset waybill quantity fluctuation factor;

[0036] The target freight rate for each combination of the multiple factors is determined according to a third product between the predicted shipping order quantity correction value and the minimum freight rate.

[0037] In an exemplary embodiment of the present disclosure, taking the minimum value of the first objective function as the optimization goal, solving the first objective function based on the numerical constraint condition, and obtaining the value of the decision variable includes:

[0038] The minimum value of the first objective function is taken as the optimization goal, and the first objective function is solved based on the numerical constraints using a robust optimization solver to obtain the value of the decision variable.

[0039] In an exemplary embodiment of the present disclosure, taking the minimum value of the first objective function as the optimization goal, solving the first objective function based on the numerical constraint condition, and obtaining the value of the decision variable includes:

[0040] Simplifying the first objective function to obtain a simplified first objective function; the simplification process includes linear conversion and constant term omission;

[0041] updating the numerical constraint;

[0042] The minimum value of the simplified first objective function is taken as the optimization goal, and the simplified first objective function is solved by a linear programming solver based on the updated numerical constraint condition to obtain the value of the decision variable.

[0043] In an exemplary embodiment of the present disclosure, the numerical constraint condition includes:

[0044] The sum of the K weight variables corresponding to each carrier in K order volume intervals is equal to the specified value;

[0045] The sum of the pre-allocated shipping order quantities of each carrier under J*L multi-factor combinations is greater than the first boundary value; the first boundary value is the cumulative value of K fourth products, and each of the fourth products is the product of the weight variable corresponding to each carrier in each shipping order interval and the left boundary of each shipping order interval;

[0046] The sum of the pre-allocated shipping order quantities of each carrier under J*L multi-factor combinations is less than or equal to the second boundary value; the second boundary value is the cumulative value of K fifth products, each of which is the product of the weight variable corresponding to each carrier in each shipping order interval and the right boundary of each shipping order interval;

[0047] The sum of the pre-allocated waybill quantities of I carrier under each combination of multiple factors is equal to the predicted waybill quantity correction value for each combination of multiple factors.

[0048] According to a second aspect of the present disclosure, a waybill allocation decision device is provided, comprising:

[0049] A variable construction module, used to construct a decision variable; the decision variable represents the pre-allocated waybill quantity for each carrier in a future period under each multi-factor combination, and the multi-factor combination is composed of at least a waybill flow direction and a weight range;

[0050] A calculation module, configured to calculate the average freight rate of each carrier under each combination of multiple factors according to the quotation data of each carrier; the quotation data of each carrier includes a tiered quotation of each carrier for each combination of multiple factors;

[0051] A freight determination module, used to determine a first total freight expression of I carriers under J*L multi-factor combinations according to the decision variables and the average freight of each carrier under each multi-factor combination, where I, J, and L are all integers greater than 1;

[0052] An objective function construction module, used for taking the first total freight expression as a first objective function and constructing numerical constraints on the decision variables;

[0053] A solution module is used to take the minimum value of the first objective function as the optimization goal, solve the first objective function based on the numerical constraint condition, and obtain the value of the decision variable.

[0054] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the waybill allocation decision method described in the first aspect is implemented.

[0055] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the waybill allocation decision method described in the first aspect above by executing the executable instructions.

[0056] It can be seen from the above technical solutions that the waybill allocation decision method, waybill allocation decision device, computer-readable storage medium and electronic device in the exemplary embodiments of the present disclosure have at least the following advantages and positive effects:

[0057] In the technical solutions provided in some embodiments of the present disclosure, on the one hand, it is possible to construct decision variables and corresponding objective functions under the premise of considering the combination of multiple factors (combinations of different waybill flows, different weight ranges, etc.) and the uncertainty of future waybill volumes, thereby providing a scientific basis for decision-making, thereby solving the technical problem in related technologies that decision-makers cannot guarantee a low waybill dispatch cost due to random decisions based on their own experience, and reducing the waybill delivery cost as much as possible. Furthermore, by setting numerical constraints, the feasibility of the decision-making scheme is ensured, and unrealistic allocation schemes are avoided, thereby helping the waybill dispatch decision-makers to make more reasonable choices. On the other hand, by optimally allocating waybills, the service capabilities of the carrier and the waybill delivery needs can be better matched, thereby ensuring the timely delivery of waybills in future time periods, improving service quality and customer satisfaction, and improving overall operational quality.

[0058] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0060] Figure 1 A schematic diagram showing a flow chart of a waybill allocation decision method in an embodiment of the present disclosure;

[0061] Figure 2 A flow chart showing how to calculate the average freight rate of each carrier under each combination of multiple factors according to the quotation data of each carrier in an embodiment of the present disclosure;

[0062] Figure 3 A flow chart showing how to predict the predicted waybill quantity of a target warehouse in a future period under each multi-factor combination (jth weight interval - lth waybill flow direction) based on the STL decomposition model in an embodiment of the present disclosure;

[0063] Figure 4 A flow chart showing another method of using the minimum value of the first objective function as the optimization goal, solving the first objective function based on numerical constraints, and obtaining the value of the decision variable in the embodiment of the present disclosure;

[0064] Figure 5 A schematic diagram showing a flow chart of another waybill allocation decision method in an embodiment of the present disclosure;

[0065] Figure 6 A flow chart showing how to determine a target freight rate for each combination of multiple factors based on the predicted shipping order volume and the quotation data of each carrier in an embodiment of the present disclosure;

[0066] Figure 7 A flow chart showing how to use the minimum value of the second objective function as the optimization goal, solve the second objective function based on numerical constraints, and obtain the value of the decision variable in the embodiment of the present disclosure;

[0067] Figure 8 A schematic diagram showing a cloud computing architecture for implementing the waybill allocation decision method in an embodiment of the present disclosure;

[0068] Fig. 9 A schematic diagram showing the structure of a waybill allocation decision device in an exemplary embodiment of the present disclosure;

[0069] Fig.10 A schematic structural diagram of an electronic device in an exemplary embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0070] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0071] The terms "a", "an", "the" and "said" are used in this specification to indicate the presence of one or more elements / components / etc.; the terms "including" and "having" are used to express an open-ended inclusion and mean that additional elements / components / etc. may exist in addition to the listed elements / components / etc.; the terms "first" and "second" etc. are used only as labels and are not intended to limit the quantity of their objects.

[0072] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and their repeated descriptions will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities.

[0073] When making waybill allocation decisions, since carriers have different quotation methods, decision makers need to consider how to assign waybills to different carriers to minimize transportation costs.

[0074] In fact, the carrier's quotation is not a simple and uniform one, but a tiered quotation composed of information such as the starting address, the number of shipping orders, discounts, etc. The logistics contract with the carrier is predicted in advance. As a result, the uncertainty of future volume and tiered quotations have increased the difficulty of allocating shipping orders to the carrier. An unreasonable order splitting plan will not only fail to reduce costs, but will be worse than random order splitting. Therefore, how to formulate a reasonable order splitting strategy often plays a key role.

[0075] In the related art, decision makers generally compare the prices of different carriers based on the historical order volume and then select one or more carriers. This method has at least the following defects:

[0076] First, the uncertainty of future shipping order volume is not taken into account, and it is often estimated in a simple way based on historical shipping order volume;

[0077] Second, there is a lack of refined operations, and the allocation rules are relatively simple, without considering the distribution of orders in different weight ranges and different waybill flows.

[0078] In the embodiments of the present disclosure, a waybill allocation decision method is first provided, which at least to some extent overcomes the defect of high distribution cost in the related art.

[0079] Figure 1 A flow chart of a waybill allocation decision method in an embodiment of the present disclosure is shown. The execution subject of the waybill allocation decision method may be a server that processes the waybill.

[0080] refer to Figure 1 According to an embodiment of the present disclosure, a waybill allocation decision method includes the following steps:

[0081] Step S110, constructing a decision variable; the decision variable represents the pre-allocated waybill quantity for each carrier in each multi-factor combination in the future period, and the multi-factor combination is at least composed of the waybill flow direction and weight range;

[0082] Step S120, calculating the average freight rate of each carrier under each multi-factor combination according to the quotation data of each carrier; the quotation data of each carrier includes a tiered quotation of each carrier for each multi-factor combination;

[0083] Step S130, determining a first total freight expression of I carriers under J*L multi-factor combinations according to the decision variables and the average freight of each carrier under each multi-factor combination, where I, J, and L are all integers greater than 1;

[0084] Step S140, taking the first total freight expression as the first objective function and constructing numerical constraints on decision variables;

[0085] Step S150, taking the minimum value of the first objective function as the optimization goal, solving the first objective function based on the numerical constraint conditions, and obtaining the value of the decision variable.

[0086] exist Figure 1 In the technical solution provided by the illustrated embodiment, on the one hand, it is possible to construct decision variables and corresponding objective functions under the premise of considering the combination of multiple factors (different waybill flow directions, combinations of different weight ranges, etc.) and the uncertainty of the future waybill volume, thereby providing a scientific basis for decision-making, thereby solving the technical problem in related technologies that decision-makers cannot guarantee a low waybill dispatch cost due to random decisions based on their own experience, and reducing the waybill delivery cost as much as possible. Furthermore, by setting numerical constraints, the feasibility of the decision-making scheme is ensured, and unrealistic allocation schemes are avoided, thereby helping the waybill decision-makers to make more reasonable choices. On the other hand, by optimally allocating waybills, the service capabilities of the carrier and the waybill delivery needs can be better matched, thereby ensuring the timely delivery of waybills in future time periods, improving service quality and customer satisfaction, and improving overall operational quality.

[0087] The following Figure 1 The specific implementation process of each step is described in detail:

[0088] Before step S110, it should be noted that the present disclosure is applied to the scenario of pre-determined allocation strategy of waybills for future time periods (for example, next month, next three months) of the target warehouse (i.e., how to assign waybills to multiple carriers to maximize cost savings). Specifically, it is necessary to decide the direction of each waybill flow for each weight range of each carrier and the amount of waybills that need to be allocated.

[0089] The carrier in the present disclosure refers to a company or enterprise that provides express delivery services. The main responsibility of the carrier is to transport the package from one location to another and meet the various requirements of the customer for the transportation process, such as transportation time, package safety, etc. Exemplarily, the number of carriers involved in the present disclosure may be I (I is an integer greater than 1), so carrier codes may be set for the above I carriers, and each carrier corresponds to a unique carrier code i, and the value of i may be 1, 2, 3...I.

[0090] The quotation data provided by each of the above-mentioned carriers can be obtained. For example, the quotation data of each carrier can be the tiered quotation provided by each carrier for a combination of different order quantity intervals (i.e., the range of the waybill quantity), different waybill directions (referring to the direction of the package from the starting point to the end point, for example: it can be the direction from city A to city B, or it can be the direction from country C to country D), and different weight intervals (i.e., the weight range of the waybill quantity). Among them, the tiered quotation refers to the different transportation costs for different order quantity intervals, waybill directions, and weight intervals. In addition, the freight of the tiered quotation depends on the first weight (in KG) of the package, the first weight price, the additional weight (in KG), and the additional weight price. The general calculation method is: freight = first weight price + (package weight - additional weight) * additional weight price.

[0091] Exemplarily, the present disclosure may summarize the order quantity ranges involved in the quotation data provided by the above-mentioned I carriers to set a list of order quantity ranges that can be selected in the subsequent decision-making process of the present disclosure, and summarize the weight ranges involved in the quotation data provided by the above-mentioned I carriers to set a list of weight ranges that can be selected in the subsequent decision-making process of the present disclosure.

[0092] Exemplarily, assume that there are a total of 2 carriers, carrier A and carrier B, and the quotation data provided by carrier A is: the number of waybills is between 2000 and 5000, the waybill flow is from Beijing to Shanghai, the first weight is 1kG, the first weight price is 20 yuan, and the additional weight price within 5KG is 4 yuan / KG; and the quotation data provided by carrier B is: 0 to 3000, the waybill flow is from Beijing to Shanghai, the first weight is 1kG, the first weight price is 15 yuan, and the additional weight price within 8KG is 5 yuan / KG, then the order quantity interval list in the present disclosure may include the following selectable order quantity intervals: 0 to 2000, 2000 to 3000, 3000 to 5000, and the weight interval list in the present disclosure may include the following selectable weight intervals: 0 to 1KG, 1 to 5KG, 5 to 8KG.

[0093] Therefore, assuming that the above single quantity interval list contains K single quantity intervals in total, a single quantity interval code k can be set for each single quantity interval in the above single quantity interval list, and the value of k can be 1, 2, 3...K.

[0094] And, assuming that the above weight interval list contains a total of J weight intervals, then for each weight interval in the above weight interval list, a weight interval code j can be set, and the value of j can be 1, 2, 3...J.

[0095] In addition, the present disclosure can also summarize the waybill flow direction list of the waybill. Assuming that the waybill flow direction list contains a total of L waybill flows, a flow direction code l can be set for each waybill flow direction, and the value of l can be 1, 2, 3...L.

[0096] Each multi-factor combination in the present disclosure refers to a combination of different weight ranges and different waybill directions. For example, any multi-factor combination may be: 0-1KG, Beijing to Shanghai.

[0097] Next reference Figure 1 , in step S110, construct decision variables.

[0098] In this step, we can construct the decision variable x i,j,l , the decision variable x i,j,l It represents the pre-allocated waybill quantity for the i-th carrier and the l-th waybill flow to the j-th weight interval in the future period. When i, j, and l take different values, the above decision variables can represent the pre-allocated waybill quantity for each weight interval and each waybill flow direction of each carrier in the future period.

[0099] Exemplarily, the above-mentioned future time period may be the next month, which may be set according to actual conditions, and the present disclosure does not make any special limitation on this.

[0100] In step S120, the average freight rate per order of each carrier under each combination of multiple factors is calculated based on the quotation data of each carrier.

[0101] In this step, the average freight rate c of each carrier i under each multi-factor combination (the jth weight interval under the lth waybill flow) can be calculated based on the quotation data of each carrier. i,j,l .

[0102] refer to Figure 2 , Figure 2 A flow chart showing how to calculate the average freight rate of each carrier under each multi-factor combination according to the quotation data of each carrier in an embodiment of the present disclosure includes steps S201 to S204:

[0103] In step S201, first freight data is calculated according to quotation data.

[0104] In this step, the first freight data is used to represent the average freight rate of each carrier under each multi-factor combination (the jth weight interval under the lth waybill flow) when the decision variable belongs to each of the K order quantity intervals. For example, the weight mean q corresponding to the jth weight interval under the lth waybill flow can be calculated first. j,l For example, assuming that the weight interval from the lth waybill flow to the jth weight interval is 0-1KG, the average weight of the jth weight interval from the lth waybill flow is 0.5KG. Then, q can be compared based on the following formula 1: j,lWhich numerical range does it belong to? Then, select the calculation formula corresponding to the corresponding numerical range in formula 1 to calculate the first freight data above

[0105]

[0106] Among them, when k takes different values, it represents that the decision variable belongs to different single quantity intervals; for each single quantity interval, It represents the first weight price of carrier i in the jth weight interval under the lth waybill flow when the decision variable belongs to the kth order quantity interval; It represents the first weight of carrier i in the jth weight interval under the lth waybill flow when the decision variable belongs to the kth order quantity interval; It represents the additional weight price of carrier i in the j-th weight interval under the l-th waybill flow when the decision variable belongs to the k-th order quantity interval.

[0107] In step S202, a weight variable corresponding to each order volume interval of each carrier is configured, and the weight variable is within a preset numerical range.

[0108] In this step, you can configure the weight variable λ corresponding to each order volume interval of each carrier i,k , the weight variable is in a preset value range, for example: [0, 1].

[0109] In step S203, a first product between each first freight data and each weight variable is calculated.

[0110] In this step, the first product between each first freight data and each weight variable can be calculated

[0111] In step S204, the accumulated value of the K first products is determined as the average freight rate per order of each carrier under each combination of multiple factors.

[0112] In this step, the accumulated value of the K first products can be determined as the average freight rate per unit of each carrier under each multi-factor combination. Specifically, the average freight rate per unit of each carrier under each multi-factor combination can be calculated based on the following formula 2: i,j,l :

[0113]

[0114] In step S130, the first total freight expression of I carriers under J*L multi-factor combinations is determined according to the decision variables and the average freight of each carrier under each multi-factor combination, where I, J, and L are all integers greater than 1.

[0115] In this step, the first total freight expression of I carriers under J*L multi-factor combinations can be determined based on the decision variables and the average freight of each carrier under each multi-factor combination. Specifically, the second product x between the decision variables and the average freight of each carrier under each multi-factor combination can be calculated first. i,j,l c i,j,l , then, the first total freight expression can be determined based on the accumulated value of I*J*L second products

[0116] In step S140, the first total freight expression is used as the first objective function, and numerical constraints on decision variables are constructed.

[0117] In this step, the first total freight expression can be used as the first objective function, and numerical constraints for the decision variables can be constructed.

[0118] Before constructing the numerical constraints for the above decision variables, given that the numerical constraints for the above decision variables are related to the quantity of waybills of the target warehouse in the future period for each weight range-each waybill flow direction combination, but the quantity of waybills is uncertain, the present invention can first obtain the predicted quantity of waybills of the target warehouse in the future period for each multi-factor combination (jth weight range-lth waybill flow direction).

[0119] For example, the predicted shipping order volume of the target warehouse in the future period under each multi-factor combination (jth weight range-lth shipping order flow direction) can be predicted based on the STL model. Figure 3 , Figure 3 A flow chart showing how to predict the predicted waybill quantity of a target warehouse in the future period under each multi-factor combination (jth weight interval-lth waybill flow direction) based on the STL decomposition model in an embodiment of the present disclosure includes steps S301-S303:

[0120] In step S301, the time series data of the shipping order quantity of the target warehouse in the historical period and the time period characteristics corresponding to the historical period are collected.

[0121] In this step, the time series data of the shipping order quantity of the target warehouse in the historical period can be collected, and the time period characteristics corresponding to the above historical period can be collected.

[0122] Exemplarily, the historical period may be June, and thus, the time series data of the waybill quantity within the above historical period may be time series data arranged according to the actual waybill quantity for each waybill flow to each weight interval every day in June.

[0123] At the same time, the corresponding time period features in the above historical time periods can be collected. For example, the time period features of each day in June can be collected, such as non-weekends, big sales, and other features.

[0124] In step S302, the time series data of the waybill quantity is decomposed into time series to obtain a trend item sequence, a seasonal item sequence and a residual item sequence.

[0125] In this step, the above-mentioned waybill quantity time series data can be decomposed into time series through the STL model to obtain trend item sequence, season item sequence and residual item sequence. Among them, the trend item sequence represents the change trend of the waybill quantity time series data, the season item sequence represents the change cycle of the waybill quantity time series data, and the residual item sequence represents the fluctuation characteristics of the waybill quantity time series data.

[0126] In step S303, according to the trend item sequence, the season item sequence and the remaining item sequence combined with the time period characteristics corresponding to the historical time period, the trend item prediction result, the season item prediction result and the remaining item prediction result are predicted.

[0127] In this step, exemplarily, the STL model can predict the trend item based on the trend item sequence combined with the time period characteristics corresponding to the historical time period to obtain the trend item prediction result, predict the season item based on the above-mentioned season item sequence combined with the time period characteristics corresponding to the historical time period to obtain the season item prediction result, and predict the remaining item based on the above-mentioned remaining item sequence combined with the time period characteristics corresponding to the historical time period to obtain the remaining item prediction result.

[0128] In step S304, the predicted shipping order quantity of the target warehouse under each multi-factor combination in the future period is determined based on the trend item prediction results, the season item prediction results and the remaining item prediction results.

[0129] In this step, illustratively, the STL model can accumulate the above-mentioned trend item prediction results, season item prediction results and residual item prediction results to obtain the predicted waybill quantity for each waybill flow in each order quantity interval in the future period of the target warehouse.

[0130] Exemplarily, the above STL model can also output the predicted standard deviation for each predicted waybill quantity (used to measure the uncertainty of the predicted waybill quantity or the size of the prediction error). Therefore, referring to the following Table 1, Table 1 shows an exemplary table of any output result of the STL model:

[0131] Table 1

[0132]

[0133] After obtaining the predicted shipping order quantity for each order quantity interval in each shipping order flow direction in the future period of the above-mentioned target warehouse, we can construct the decision variable x i,j,l Numerical constraints, for example, the numerical constraints for the above decision variables may include the following formulas 3 to 6:

[0134]

[0135] The above formula 3 means: the K weight variables λ corresponding to each carrier in the K order volume intervals are i,k The sum is equal to the specified value 1.

[0136] The meaning of the above formula 4 is: the sum of the pre-allocated waybill quantities of each carrier under J*L multi-factor combinations is greater than the first boundary value, the first boundary value is the cumulative value of K fourth products, and each fourth product is the weight variable λ corresponding to each carrier in each waybill interval i,k The product of the left boundary e0 of each single-quantity interval.

[0137] The meaning of the above formula 5 is: the sum of the pre-allocated waybill quantities of each carrier under J*L multi-factor combinations is less than or equal to the second boundary value, and the second boundary value is the cumulative value of K fifth products, and each fifth product is the weight variable λ corresponding to each carrier i in each waybill interval k i,k and the right boundary f of each single quantity interval k The product of .

[0138] The meaning of the above formula 6 is: the sum of the pre-allocated waybill quantity of I carrier under each multi-factor combination (the jth weight interval under the lth waybill flow) is equal to the predicted waybill quantity correction value (μ j,l +ξ j,l σ j,l );

[0139] Among them, μ j,l represents the predicted waybill quantity for the jth weight interval under the lth waybill flow, σ j,l Represents the predicted shipping order volume μ j,l The prediction standard deviation, ξ j,l represents the order quantity fluctuation factor for the jth weight interval under the lth order flow, ξ j,l is a random variable used to represent the uncertainty of the waybill quantity, ξ j,l ∈P, P is the uncertainty set that defines ξ, the ξ value is in [-1,1], and the norm is less than Γ. Γ can be adjusted appropriately according to the data situation. The larger the Γ, the smaller the uncertainty space, and vice versa.

[0140] In step S150, the minimum value of the first objective function is taken as the optimization goal, and the first objective function is solved based on the numerical constraint conditions to obtain the value of the decision variable.

[0141] In this step, in an optional implementation, the minimum value of the first objective function can be used as the optimization goal, and the first objective function can be solved based on the numerical constraints using a robust optimization solver to obtain the value of the decision variable.

[0142] Exemplarily, the above-mentioned robust optimization solver can be RSOME (Robust Stochastic Optimization Made Easy) open source robust optimization framework.

[0143] In another optional implementation, given that the first objective function contains a quadratic term x i,j,l c i,j,l Therefore, in order to facilitate the use of solvers other than the robust optimization solver to solve it (i.e., to ensure the diversity of solution methods), the above-mentioned first objective function can be simplified, and then the simplified first objective function can be solved using the robust optimization solver or the linear programming solver to obtain the values ​​of the decision variables.

[0144] refer to Figure 4 , Figure 4 A flowchart showing another method of solving the first objective function based on numerical constraints to obtain the value of the decision variable by taking the minimum value of the first objective function as the optimization goal in the embodiment of the present disclosure includes steps S401 to S403:

[0145] In step S401, the first objective function is simplified to obtain a simplified first objective function.

[0146] In this step, the second objective function can be simplified to obtain a simplified first objective function. Exemplarily, the first objective function can be linearly transformed and constant term omitted (if there is no constant term, this step can be omitted) to obtain a simplified first objective function, and the simplified first objective function refers to the following formula 7:

[0147]

[0148] The linear transformation process refers to converting the quadratic term x in the first objective function i,j,l c i,j,l With the auxiliary variable z i,k to replace.

[0149] In step S402, the numerical constraint condition is updated.

[0150] In this step, after simplifying the second objective function, the above numerical constraints may be updated. Exemplarily, the updated numerical constraints include, in addition to the above formulas 3 to 6, formulas 8 to 11 obtained by linearly transforming the above numerical constraints:

[0151]

[0152] The above formula 8 means: when λ i,k =1, the i,k Substituting the value of into the above formula 2, we get z i,k The upper boundary of

[0153] The meaning of the above formula 9 is: by introducing M, it is guaranteed that i,k =1 hour Otherwise i,k ≥0, where M = the total predicted order quantity of the target warehouse in the future period (i.e. the sum of the predicted order quantities of all waybill directions and all weight ranges) * the highest bid of each carrier for different waybill directions and different weight ranges;

[0154] The above formula 10 means that z is defined according to the upper boundary of the kth order quantity interval and the highest quotation in different order directions and different weight intervals. H,0 The upper limit of

[0155] The above formula 11 means that z is defined according to the lower boundary of the kth order quantity interval and the lowest quote in different order directions and weight intervals. H,0 The lower limit of .

[0156] In step S403, the minimum value of the simplified first objective function is taken as the optimization target, and the simplified first objective function is solved by a linear programming solver based on the updated numerical constraints to obtain the values ​​of the decision variables.

[0157] In this step, the minimum value of the simplified first objective function can be used as the optimization goal, and the simplified first objective function is solved by a linear programming solver based on the updated numerical constraints to obtain the values ​​of the decision variables.

[0158] Alternatively, the minimum value of the simplified first objective function may be used as the optimization goal, and the simplified first objective function may be solved by a robust optimization solver based on updated numerical constraints to obtain the value of the decision variable.

[0159] For example, the values ​​of the decision variables finally outputted in the present disclosure can refer to the following Table 2:

[0160] Table 2

[0161]

[0162] The meaning of the above Table 2 is: in the future period, the pre-allocated waybill quantity for carrier A, with the waybill flow from Beijing to Shanghai and the weight range from 0 to 1 kg is 1,000; for carrier B, the pre-allocated waybill quantity for the waybill flow from Hangzhou to Beijing and the weight range from 10 to 15 kg is 200.

[0163] In view of the fact that the above-mentioned first objective function only includes the first total freight expression under the condition of uncertain waybill quantity, it is impossible to clarify whether the first total freight expression has necessarily achieved the effect of optimizing costs compared with the total freight decided by the decision maker based on his own experience. Therefore, the present disclosure can also construct a second objective function based on the difference between the above-mentioned first total freight expression and the second total freight expression decided by the decision maker based on his own experience, so that based on the second objective function, the cost optimization effect can be clearly known.

[0164] refer to Figure 5 , Figure 5 A flow chart of another waybill allocation decision method in an embodiment of the present disclosure is shown. The waybill allocation decision method can be performed on the basis of steps S110 to S130. Figure 5 Steps S501 to S505 in the process are performed to obtain the values ​​of the decision variables.

[0165] In step S501, the predicted shipping order quantity of the target warehouse under each combination of multiple factors in the future period is obtained.

[0166] In this step, we can Figure 3 The steps shown are used to obtain the predicted shipping order volume for the target warehouse in the future period under each combination of multiple factors, which will not be repeated here.

[0167] In step S502, a target freight rate for each combination of multiple factors is determined based on the predicted shipping order volume and the quotation data of each carrier.

[0168] In this step, the target freight rate for each multi-factor combination can be determined based on the predicted shipping order volume and the quotation data of each carrier. For details, please refer to Figure 6 , Figure 6 A flow chart showing how to determine the target freight rate for each combination of multiple factors according to the predicted shipping order volume and the quotation data of each carrier in an embodiment of the present disclosure includes steps S601 to S603:

[0169] In step S601, the lowest freight rate corresponding to the target carrier with the lowest quotation for each combination of multiple factors is determined.

[0170] In this step, the lowest freight c′ corresponding to the target carrier with the lowest quotation for each multi-factor combination (i.e., the jth weight interval under the lth waybill flow) can be determined based on the quotation data of I carriers. j,l .

[0171] In step S602, the predicted standard deviation corresponding to the predicted waybill quantity is obtained, and the predicted waybill quantity correction value for each combination of multiple factors is calculated based on the predicted waybill quantity, the predicted standard deviation and the preset order quantity fluctuation factor.

[0172] In this step, the predicted waybill quantity correction value μ for each combination of multiple factors can be calculated based on the relevant explanation of the above formula 6: j,l +ξ j,l σ j,l , I will not go into details here.

[0173] In step S603, the target freight rate for each combination of multiple factors is determined according to the third product between the predicted shipping order quantity correction value and the minimum freight rate.

[0174] In this step, the value μ can be corrected based on the predicted waybill quantity. j,l +ξ j,l σ j,l and minimum freight c′ j,l The third product between them determines the target freight rate for each multi-factor combination, that is, (μ j,l +ξ j,l σ j,l )*c′ j,l .

[0175] Next reference Figure 5 In step S503, a second total freight expression is determined according to J*L target freights corresponding to J*L combinations of multiple factors.

[0176] In this step, the second total freight expression can be determined according to J*L target freights corresponding to J*L multi-factor combinations. For example, the second total freight expression can be expressed as

[0177] In step S504, a second objective function is constructed according to the difference between the first total freight expression and the second total freight expression.

[0178] In this step, a second objective function may be constructed according to the difference between the first total freight expression and the second total freight expression. For example, the second objective function may refer to the following formula 12:

[0179]

[0180] Among them, the above second objective function consists of two layers, inner and outer layers, which are and The inner layer of j,l is a random variable used to represent the uncertainty of the waybill quantity, and its value range is [-1,1]. It means taking the worst case scenario when the number of waybills is uncertain. It means minimizing the quotation difference to minimize the total freight cost after optimization. It can be understood as minimizing the total freight cost in the worst case of uncertain shipping order quantity. P is the uncertainty set that defines ξ, where the ξ value is within [-1,1] and the norm is less than Γ. Γ can be adjusted appropriately according to the data situation. The larger the Γ, the smaller the uncertainty space, and vice versa.

[0181] In step S505, the minimum value of the second objective function is taken as the optimization goal, and the second objective function is solved based on the numerical constraint conditions to obtain the value of the decision variable.

[0182] In this step, in an optional implementation, the minimum value of the second objective function can be used as the optimization goal, and the second objective function can be solved based on the numerical constraints (Formula 3-Formula 6) using a robust optimization solver to obtain the value of the decision variable.

[0183] In another optional embodiment, reference may be made to Figure 7 , Figure 7 A flow chart showing how to use the minimum value of the second objective function as the optimization goal, solve the second objective function based on the numerical constraint condition, and obtain the value of the decision variable in the embodiment of the present disclosure, including steps S701 to S703:

[0184] In step S701, the second objective function is simplified to obtain a simplified second objective function.

[0185] In this step, the second objective function may be simplified to obtain a simplified second objective function. Exemplarily, the second objective function may be linearly transformed and the constant term omitted to obtain a simplified second objective function, and the simplified second objective function is referred to the following formula 13:

[0186]

[0187] The linear transformation process refers to converting the quadratic term x in the second objective function i,j,l c i,j,l With the auxiliary variable z i,k To replace, the constant term omission is to eliminate the constant term μ j,l c′ j,l (The constant term has no effect on the optimization process and can therefore be eliminated).

[0188] In step S702, the numerical constraint condition is updated.

[0189] In this step, the updated numerical constraint conditions can refer to the relevant description of the above step S402, which will not be repeated here.

[0190] In step S703, the minimum value of the simplified second objective function is taken as the optimization target, and the simplified second objective function is solved by a linear programming solver based on the updated numerical constraints to obtain the values ​​of the decision variables.

[0191] In this step, the minimum value of the simplified second objective function can be used as the optimization goal, and the simplified second objective function is solved based on the updated numerical constraints using a linear programming solver to obtain the value of the decision variable.

[0192] Alternatively, the minimum value of the simplified second objective function may be used as the optimization goal, and the simplified second objective function may be solved based on the updated numerical constraints using a robust optimization solver to obtain the value of the decision variable.

[0193] Exemplarily, the values ​​of the decision variables finally output in the present disclosure can refer to Table 2 above. Exemplarily, in the future period, the pre-allocated waybill quantity for carrier A, with a waybill direction of Beijing-Shanghai and a weight range of 0-1KG is 1000; for carrier B, the pre-allocated waybill quantity for carrier B, with a waybill direction of Hangzhou-Beijing and a weight range of 10-15KG is 200.

[0194] It should be noted that the inventor has also compared the transportation costs between the order splitting strategy decided by this scheme and the order splitting strategy decided manually through simulation experiments. It has been verified that when the accuracy of predicting the number of waybills is low, the order splitting strategy decided by this scheme can significantly optimize the transportation costs of waybills compared to the order splitting strategy decided manually.

[0195] refer to Figure 8 , Figure 8 A schematic diagram of a cloud computing architecture for implementing the waybill allocation decision method in the embodiment of the present disclosure is shown. Figure 8 As shown:

[0196] The specific implementation of the present disclosure relies on two parts of services, the first part is Spark offline task prediction, and the second part is the order optimization algorithm service.

[0197] The data required for offline task prediction can be stored in a big data cluster. Spark+HDFS is part of a big data cluster and is used to store and process large amounts of data. Apache Spark is a fast and general big data analysis engine, while Hadoop Distributed File System (HDFS) provides a reliable data storage solution. Together, they make the analysis of large-scale data sets efficient and easy to manage.

[0198] The waybill volume prediction task and order splitting optimization algorithm can be deployed on the cloud service cluster. Thus, the cloud service cluster can predict the waybill volume in the future period based on the relevant data in the big data cluster and update the prediction results daily. The prediction algorithm can use statsmodels, fbprophet, etc., and build a robust optimization model, use the RSOME open source robust optimization framework for solution, and output the final order splitting plan for each carrier.

[0199] Among them, the cloud service cluster can include Flask+WSGL, load balancing, storage and message mechanisms, etc. Flask is a lightweight Python Web framework that allows developers to create Web applications and services. WSGI (Web Server Gateway Interface) is the standard interface between Python Web applications and Web servers. By combining Flask and WSGI, high-performance Web services can be easily developed. The role of the load balancer is to distribute network traffic among multiple servers to ensure that no server is overloaded. This helps to improve availability and response time, while also enhancing the scalability of the system. The storage and message mechanism is responsible for the persistent storage of data and internal communication. The storage mechanism can be a relational database, a NoSQL database, or other types of storage systems. The message mechanism can use message queues or event-driven methods to coordinate the interaction between different components.

[0200] Based on the above technical solutions, the present disclosure has at least the following technical effects:

[0201] Based on technologies such as order quantity prediction and robust optimization, third-party carriers are assigned to different weight ranges for different waybill flows in the warehouse, and the risk of increased costs caused by future order quantity fluctuations is reduced through methods such as robust optimization.

[0202] The present disclosure also provides a waybill allocation decision device, Fig. 9 A schematic diagram showing the structure of a waybill allocation decision device in an exemplary embodiment of the present disclosure is shown; Fig. 9 As shown, the waybill allocation decision device 900 may include a variable construction module 910, a calculation module 920, a freight determination module 930, an objective function construction module 940 and a solution module 950. Among them:

[0203] A variable construction module 910 is used to construct a decision variable; the decision variable represents the pre-allocated waybill quantity for each carrier in a future period under each multi-factor combination, and the multi-factor combination is at least composed of a waybill flow direction and a weight range;

[0204] A calculation module 920, configured to calculate the average freight rate of each carrier under each combination of multiple factors according to the quotation data of each carrier; the quotation data of each carrier includes a tiered quotation of each carrier for each combination of multiple factors;

[0205] A freight determination module 930 is used to determine a first total freight expression of I carriers under J*L multi-factor combinations according to the decision variables and the average freight of each carrier under each multi-factor combination, where I, J, and L are all integers greater than 1;

[0206] An objective function construction module 940 is used to use the first total freight expression as a first objective function and construct numerical constraints on the decision variables;

[0207] The solution module 950 is used to solve the first objective function based on the numerical constraint condition with the minimum value of the first objective function as the optimization goal, and obtain the value of the decision variable.

[0208] In an exemplary embodiment of the present disclosure, after determining the first total freight expression of I carriers under J*L multi-factor combinations according to the decision variables and the average freight rate of each carrier under each multi-factor combination, the objective function construction module 940 is further used to:

[0209] Obtain the predicted shipping order volume of the target warehouse under each combination of the above multiple factors in the future period;

[0210] Determining a target freight rate for each combination of the multiple factors according to the predicted shipping order volume and the quotation data of each carrier;

[0211] Determine a second total freight expression according to the J*L target freights corresponding to the J*L combinations of multiple factors;

[0212] constructing a second objective function according to the difference between the first total freight expression and the second total freight expression;

[0213] The minimum value of the second objective function is taken as the optimization goal, and the second objective function is solved based on the numerical constraint condition to obtain the value of the decision variable.

[0214] In an exemplary embodiment of the present disclosure, the calculation module 920 calculates the average freight rate of each carrier under each combination of multiple factors according to the quotation data of each carrier, including:

[0215] Calculate first freight data according to the quotation data; the first freight data is used to represent the average freight rate of each carrier under each combination of multiple factors when the decision variable belongs to each order quantity interval in the K order quantity intervals;

[0216] Configuring a weight variable corresponding to each order volume interval of each carrier, wherein the weight variable is within a preset value range;

[0217] Calculating a first product between each of the first freight data and each of the weight variables;

[0218] The accumulated value of the K first products is determined as the average freight rate per unit of each carrier under each combination of the multiple factors.

[0219] In an exemplary embodiment of the present disclosure, the freight determination module 930 determines a first total freight expression of I carriers under J*L multi-factor combinations according to the decision variables and the average freight of each carrier under each multi-factor combination, including:

[0220] Calculating a second product between the decision variable and the average freight rate of each carrier under each combination of the multiple factors;

[0221] The first total freight expression is determined according to the accumulated value of I*J*L second products.

[0222] In an exemplary embodiment of the present disclosure, the objective function construction module 940 obtains the predicted shipping order quantity of the target warehouse under each combination of the multiple factors in the future period, including:

[0223] Collecting the time series data of the shipping order quantity of the target warehouse in the historical period and the time period characteristics corresponding to the historical period;

[0224] Decomposing the time series data of the waybill quantity into time series to obtain a trend item sequence, a season item sequence and a residual item sequence; wherein the trend item sequence represents the change trend of the time series data of the waybill quantity, the season item sequence represents the change cycle of the time series data of the waybill quantity, and the residual item sequence represents the fluctuation characteristics of the time series data of the waybill quantity;

[0225] According to the trend item sequence, the season item sequence and the residual item sequence combined with the period characteristics corresponding to the historical period, the trend item prediction result, the season item prediction result and the residual item prediction result are predicted;

[0226] The predicted waybill quantity of the target warehouse under each combination of the multiple factors in a future period is determined according to the trend item prediction result, the season item prediction result and the remaining item prediction result.

[0227] In an exemplary embodiment of the present disclosure, the objective function construction module 940 determines the target freight rate for each combination of the multiple factors according to the predicted shipping order volume and the quotation data of each carrier, including:

[0228] Determine the lowest freight rate corresponding to the target carrier with the lowest quote for each combination of multiple factors;

[0229] Obtaining a predicted standard deviation corresponding to the predicted waybill quantity, and calculating a predicted waybill quantity correction value for each combination of the multiple factors according to the predicted waybill quantity, the predicted standard deviation, and a preset waybill quantity fluctuation factor;

[0230] The target freight rate for each combination of the multiple factors is determined according to a third product between the predicted shipping order quantity correction value and the minimum freight rate.

[0231] In an exemplary embodiment of the present disclosure, the solution module 950 takes the minimum value of the first objective function as the optimization goal, solves the first objective function based on the numerical constraint condition, and obtains the value of the decision variable, including:

[0232] The minimum value of the first objective function is taken as the optimization goal, and the first objective function is solved based on the numerical constraints using a robust optimization solver to obtain the value of the decision variable.

[0233] In an exemplary embodiment of the present disclosure, the solution module 950 takes the minimum value of the first objective function as the optimization goal, solves the first objective function based on the numerical constraint condition, and obtains the value of the decision variable, including:

[0234] Simplifying the first objective function to obtain a simplified first objective function; the simplification process includes linear conversion and constant term omission;

[0235] updating the numerical constraint;

[0236] The minimum value of the simplified first objective function is taken as the optimization goal, and the simplified first objective function is solved by a linear programming solver based on the updated numerical constraint condition to obtain the value of the decision variable.

[0237] In an exemplary embodiment of the present disclosure, the numerical constraint condition includes:

[0238] The sum of the K weight variables corresponding to each carrier in K order volume intervals is equal to the specified value;

[0239] The sum of the pre-allocated shipping order quantities of each carrier under J*L multi-factor combinations is greater than the first boundary value; the first boundary value is the cumulative value of K fourth products, and each of the fourth products is the product of the weight variable corresponding to each carrier in each shipping order interval and the left boundary of each shipping order interval;

[0240] The sum of the pre-allocated shipping order quantities of each carrier under J*L multi-factor combinations is less than or equal to the second boundary value; the second boundary value is the cumulative value of K fifth products, each of which is the product of the weight variable corresponding to each carrier in each shipping order interval and the right boundary of each shipping order interval;

[0241] The sum of the pre-allocated waybill quantities of I carrier under each combination of multiple factors is equal to the predicted waybill quantity correction value for each combination of multiple factors.

[0242] The specific details of each module in the above-mentioned waybill allocation decision device have been described in detail in the corresponding waybill allocation decision method, so they will not be repeated here.

[0243] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0244] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0245] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0246] The present disclosure also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or may exist independently without being assembled into the electronic device.

[0247] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof. More specific examples of computer-readable storage media may 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 thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0248] Computer-readable storage media can send, propagate or transmit programs for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable storage 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.

[0249] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiments.

[0250] In addition, an electronic device capable of implementing the above method is also provided in an embodiment of the present disclosure.

[0251] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0252] Refer to the following Fig.10 The electronic device 1000 according to this embodiment of the present disclosure is described. Fig.10 The electronic device 1000 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0253] like Fig.10As shown, the electronic device 1000 is in the form of a general computing device. The components of the electronic device 1000 may include, but are not limited to: at least one processor 1010, at least one memory 1020, a bus 1030 connecting different system components (including the memory 1020 and the processor 1010), and a display 1040.

[0254] The memory stores program codes, which can be executed by the processor 1010, so that the processor 1010 executes the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processor 1010 can execute the following steps: Figure 1 As shown in: Step S110, constructing a decision variable; the decision variable represents the pre-allocated waybill quantity for each carrier in each multi-factor combination in the future period, and the multi-factor combination is composed of at least a waybill flow direction and a weight range; Step S120, calculating the average freight rate of each carrier under each multi-factor combination according to the quotation data of each carrier; the quotation data of each carrier includes the step quotation of each carrier for each multi-factor combination; Step S130, determining the first total freight expression of I carriers under J*L multi-factor combinations according to the decision variables and the average freight rate of each carrier under each multi-factor combination, where I, J, and L are all integers greater than 1; Step S140, taking the first total freight expression as the first objective function, and constructing numerical constraints on the decision variables; Step S150, taking the minimum value of the first objective function as the optimization target, solving the first objective function based on the numerical constraints, and obtaining the value of the decision variable.

[0255] The memory 1020 may include a readable medium in the form of a volatile storage, such as a random access memory (RAM) 10201 and / or a cache memory 10202 , and may further include a read-only memory (ROM) 10203 .

[0256] Memory 1020 may also include a program / utility 10204 having a set (at least one) of program modules 10205, such program modules 10205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0257] The bus 1030 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0258] The electronic device 1000 may also communicate with one or more external devices 1100 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 1000, and / or may communicate with any device that enables the electronic device 1000 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 1050. Furthermore, the electronic device 1000 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 1060. As shown, the network adapter 1060 communicates with other modules of the electronic device 1000 via a bus 1030. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1000, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0259] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A waybill allocation decision method, characterized in that: include: Construct decision variables; The decision variable represents the pre-allocated waybill quantity for each carrier in each multi-factor combination in the future period, and the multi-factor combination is composed of at least the waybill flow direction and the weight range; Calculating the average freight rate of each carrier under each combination of multiple factors according to the quotation data of each carrier; the quotation data of each carrier includes the tiered quotation of each carrier for each combination of multiple factors; Determine a first total freight expression of I carriers under J*L multi-factor combinations according to the decision variables and the average freight of each carrier under each multi-factor combination, where I, J, and L are all integers greater than 1; Taking the first total freight expression as a first objective function, and constructing numerical constraints on the decision variables; The minimum value of the first objective function is taken as the optimization goal, the first objective function is solved based on the numerical constraint condition, and the value of the decision variable is obtained.

2. The method according to claim 1, characterized in that After determining a first total freight expression of I carrier under J*L multi-factor combinations according to the decision variables and the average freight rate of each carrier under each multi-factor combination, the method further includes: Obtain the predicted shipping order volume of the target warehouse under each combination of the above multiple factors in the future period; Determining a target freight rate for each combination of the multiple factors according to the predicted shipping order volume and the quotation data of each carrier; Determine a second total freight expression according to the J*L target freights corresponding to the J*L combinations of multiple factors; constructing a second objective function according to the difference between the first total freight expression and the second total freight expression; The minimum value of the second objective function is taken as the optimization goal, and the second objective function is solved based on the numerical constraint condition to obtain the value of the decision variable.

3. The method according to claim 1, characterized in that The calculating, based on the quotation data of each carrier, the average freight rate of each carrier under each combination of multiple factors includes: Calculate first freight data according to the quotation data; the first freight data is used to represent the average freight rate of each carrier under each combination of multiple factors when the decision variable belongs to each order quantity interval in the K order quantity intervals; Configuring a weight variable corresponding to each order volume interval of each carrier, wherein the weight variable is within a preset value range; Calculating a first product between each of the first freight data and each of the weight variables; The accumulated value of the K first products is determined as the average freight rate per unit of each carrier under each combination of the multiple factors.

4. The method according to claim 3, characterized in that: The method of determining a first total freight expression of I carrier under J*L multi-factor combinations according to the decision variables and the average freight of each carrier under each multi-factor combination includes: Calculating a second product between the decision variable and the average freight rate of each carrier under each combination of the multiple factors; The first total freight expression is determined according to the accumulated value of I*J*L second products.

5. The method according to claim 2, characterized in that: The obtaining of the predicted shipping order quantity of the target warehouse in the future period under each combination of the multiple factors includes: Collecting the time series data of the shipping order quantity of the target warehouse in the historical period and the time period characteristics corresponding to the historical period; Decomposing the time series data of the waybill quantity into time series to obtain a trend item sequence, a season item sequence and a residual item sequence; wherein the trend item sequence represents the change trend of the time series data of the waybill quantity, the season item sequence represents the change cycle of the time series data of the waybill quantity, and the residual item sequence represents the fluctuation characteristics of the time series data of the waybill quantity; According to the trend item sequence, the season item sequence and the residual item sequence combined with the period characteristics corresponding to the historical period, the trend item prediction result, the season item prediction result and the residual item prediction result are predicted; The predicted waybill quantity of the target warehouse under each combination of the multiple factors in a future period is determined according to the trend item prediction result, the season item prediction result and the remaining item prediction result.

6. The method according to claim 5, characterized in that The step of determining the target freight rate for each combination of the multiple factors according to the predicted shipping order volume and the quotation data of each carrier includes: Determine the lowest freight rate corresponding to the target carrier with the lowest quote for each combination of multiple factors; Obtaining a predicted standard deviation corresponding to the predicted waybill quantity, and calculating a predicted waybill quantity correction value for each combination of the multiple factors according to the predicted waybill quantity, the predicted standard deviation, and a preset waybill quantity fluctuation factor; The target freight rate for each combination of the multiple factors is determined according to a third product between the predicted shipping order quantity correction value and the minimum freight rate.

7. The method according to claim 4, characterized in that The step of taking the minimum value of the first objective function as the optimization goal, solving the first objective function based on the numerical constraint condition, and obtaining the value of the decision variable includes: The minimum value of the first objective function is taken as the optimization goal, and the first objective function is solved based on the numerical constraints using a robust optimization solver to obtain the value of the decision variable.

8. The method according to claim 4, characterized in that The step of taking the minimum value of the first objective function as the optimization goal, solving the first objective function based on the numerical constraint condition, and obtaining the value of the decision variable includes: Simplifying the first objective function to obtain a simplified first objective function; the simplification process includes linear conversion and constant term omission; updating the numerical constraint; The minimum value of the simplified first objective function is taken as the optimization goal, and the simplified first objective function is solved by a linear programming solver based on the updated numerical constraint condition to obtain the value of the decision variable.

9. The method according to any one of claims 1 to 8, characterized in that: The numerical constraints include: The sum of the K weight variables corresponding to each carrier in K order volume intervals is equal to the specified value; The sum of the pre-allocated shipping order quantities of each carrier under J*L multi-factor combinations is greater than the first boundary value; the first boundary value is the cumulative value of K fourth products, and each of the fourth products is the product of the weight variable corresponding to each carrier in each shipping order interval and the left boundary of each shipping order interval; The sum of the pre-allocated shipping order quantities of each carrier under J*L multi-factor combinations is less than or equal to the second boundary value; the second boundary value is the cumulative value of K fifth products, each of which is the product of the weight variable corresponding to each carrier in each shipping order interval and the right boundary of each shipping order interval; The sum of the pre-allocated waybill quantities of I carrier under each combination of multiple factors is equal to the predicted waybill quantity correction value for each combination of multiple factors.

10. A waybill allocation decision device, characterized in that: include: Variable construction module, used to construct decision variables; The decision variable represents the pre-allocated waybill quantity for each carrier in each multi-factor combination in the future period, and the multi-factor combination is composed of at least the waybill flow direction and the weight range; A calculation module, configured to calculate the average freight rate of each carrier under each combination of multiple factors according to the quotation data of each carrier; the quotation data of each carrier includes a tiered quotation of each carrier for each combination of multiple factors; A freight determination module, used to determine a first total freight expression of I carriers under J*L multi-factor combinations according to the decision variables and the average freight of each carrier under each multi-factor combination, where I, J, and L are all integers greater than 1; An objective function construction module, used for taking the first total freight expression as a first objective function and constructing numerical constraints on the decision variables; A solution module is used to take the minimum value of the first objective function as the optimization goal, solve the first objective function based on the numerical constraint condition, and obtain the value of the decision variable.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the waybill allocation decision method described in any one of claims 1 to 9 is implemented.

12. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to execute the waybill allocation decision method described in any one of claims 1 to 9 by executing the executable instructions.

Images