Method, device, electronic device, medium and program product for determining delivery quantity

By building a dual-objective prediction model, the actual delivery volume of core objects and associated objects in the inventory management of 'single supplier-multi-retailers' was solved, and the poor supply chain management effect caused by the failure to introduce cross-selling factors was achieved, and the more Efficient profit and service level optimization.

CN113298323BActive Publication Date: 2024-12-06INDUSTRIAL AND COMMERCIAL BANK OF CHINA
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202110762054.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-07-06
Publication Date
2024-12-06
Estimated Expiration
2041-07-06

AI Technical Summary

Technical Problem

In the 'single-multi-retailer' inventory management, the failure to introduce cross-selling factors has led to poor supply chain management and the existing technology has failed to effectively solve this problem.

Method used

By building a dual-objective prediction model, based on the historical sales of core objects and associated objects in the supply chain, the actual distribution volume of core objects and associated objects of each object's demand side is determined, and the constraints on total profit and service level are taken into consideration, and the constraints on total profit and service level are optimized. Distribution volume to improve supply chain management effectiveness.

Benefits of technology

It achieves more accurate delivery volume forecasts, improves the management effect of the supply chain, optimizes the overall profit and service level, reduces out-of-stock situations, and reduces costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113298323B_ABST
    Figure CN113298323B_ABST
Patent Text Reader

Abstract

The present disclosure provides a method, device, electronic device, medium and program product for determining the distribution volume, which can be applied to the financial field or other fields. The method includes: obtaining a dual-objective prediction model of a supply chain, the supply chain is composed of an object provider and n object demanders, the dual-objective prediction model is used to characterize the total profit and service level of the n object demanders, and n is an integer greater than 1; based on the historical sales of the core object and the associated object at each object demander, obtaining the first actual sales expectation of the core object and the second actual sales expectation of the associated object, the associated object having an associated sales relationship with the core object; and under the constraints of the dual-objective prediction model, based on the first actual sales expectation and the second actual sales expectation, determining the first actual distribution volume of the core object and the second actual distribution volume of the associated object distributed by the object provider to each object demander respectively.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of supply chain management, and in particular to a method, device, electronic device, medium and program product for determining a distribution quantity. Background Art

[0002] The phenomenon of cross-selling has been widely used in retail fields such as e-commerce. For example, a personalized recommendation system is built through data mining technology, and the relationship between commodities is mined according to the user's previous shopping habits, so as to achieve cross-selling. However, the introduction of cross-selling into the inventory decision-making problem of suppliers in supply chain management started relatively late, especially the research on the "single supplier-multiple retailers" problem is relatively limited, and the cross-selling factor has not been introduced, resulting in poor supply chain management results.

[0003] This section is intended to provide a background or context to the embodiments of the disclosure that are recited in the claims. No description herein is admitted to be prior art by inclusion in this section. Summary of the invention

[0004] In view of this, in order to at least partially overcome the above-mentioned technical problems existing in the related technology in the "single supplier - multiple retailers" inventory management, the present disclosure provides a method, device, electronic device, medium and program product for determining the delivery quantity by introducing cross-selling factors.

[0005] In order to achieve the above objectives, one aspect of the present disclosure provides a method for determining the distribution volume, which method may include: obtaining a dual-objective prediction model of a supply chain, the supply chain being composed of an object provider and n object demanders, the dual-objective prediction model being used to characterize the total profit and service level of the n object demanders, where n is an integer greater than 1; based on the historical sales of the core object and the associated object at each object demander, obtaining a first actual sales expectation of the core object and a second actual sales expectation of the associated object, the associated object having an associated sales relationship with the core object; and under the constraints of the dual-objective prediction model, determining the first actual distribution volume of the core object and the second actual distribution volume of the associated object distributed by the object provider to each of the object demanders respectively based on the first actual sales expectation and the second actual sales expectation.

[0006] According to an embodiment of the present disclosure, the above-mentioned method of obtaining the first actual sales expectation of the core object and the second actual sales expectation of the associated object based on the historical sales of the core object and the associated object on each object demand side may include: determining the first indicator parameter of the core object on each object demand side based on the historical sales of the core object on each object demand side, wherein the first indicator parameter includes the demand mean, standard deviation, probability density function and cumulative distribution function; determining the second indicator parameter of the associated object on each object demand side based on the historical sales of the associated object on each object demand side, wherein the second indicator parameter includes the independent demand mean, standard deviation, effective demand probability density function and cumulative distribution function; and obtaining the first actual sales expectation of the core object and the second actual sales expectation of the associated object based on at least the first indicator parameter and the second indicator parameter.

[0007] According to an embodiment of the present disclosure, obtaining the first actual sales expectation of the core object and the second actual sales expectation of the associated object at least according to the first indicator parameter and the second indicator parameter includes: the first actual sales expectation of the core object and the second actual sales expectation of the associated object can be obtained by the following formula:

[0008]

[0009] Among them, E(min{Q i , D i}) refers to the first actual sales expectation of the core object at the i-th (i≤n) object demand side, Refers to the second actual sales expectation of the associated object on the i-th object demand side. The independent demand D of the core object and the associated object on the i-th object demand side i d i All obey the normal distribution, Refers to the effective demand of the associated object on the i-th object demand side, P i 、p i They refer to the unit price of the core object and the associated object at the i-th object demand side, Q i ,q i They refer to the distribution volume of the core object and the associated object on the i-th object demand side, respectively. i 、c i They refer to the unit purchase cost of the core object and the associated object at the i-th object demand side, respectively. i 、b i They refer to the unit transportation cost of the core object and the associated object on the i-th object demand side, respectively. i 、a iThey refer to the bulk transportation costs of the core object and the associated object at the i-th object demand side, Y i ,y i They refer to the market choices of the core object and the associated object on the i-th object demand side. It refers to the average demand of the core object in the i-th object demand side. It refers to the independent demand mean of the associated object in the i-th object demand side. They refer to the standard deviation of the core object and the associated object on the i-th object demand side, Refers to the probability density function of the core object on the i-th object demand side, It refers to the probability density function of the effective demand of the associated object on the i-th object demand side, Pr(D i ≤Qi)、Pr(D i ≥Q i ) refers to the cumulative distribution function of the core object on the i-th object demand side, Refers to the cumulative distribution function of the associated object on the i-th object demand side, Refers to the demand correlation coefficient of the associated object on the i-th object demand side, λ i Refers to the correlation coefficient between the core object and the associated object on the i-th object demand side.

[0010] According to an embodiment of the present disclosure, the obtained dual-objective prediction model can be expressed as the following formula:

[0011]

[0012] Among them, F c (Q,q) refers to the total profit of the object with positive profit in each object demand side, that is, the core object of each object demand side multiplied by the corresponding market choice Y i Multiply the associated object by the corresponding market choice q i The profit sum obtained by adding up, S c (Q, q) refers to the average service level of each object demand side that actually generates distribution behavior. The independent demand D of the core object and the associated object at the i-th object demand side i d i All obey the normal distribution, Refers to the effective demand of the associated object on the i-th object demand side, P i 、p i They refer to the unit price of the core object and the associated object at the i-th object demand side, Q i ,q i They refer to the distribution volume of the core object and the associated object on the i-th object demand side, respectively. i、c i They refer to the unit purchase cost of the core object and the associated object at the i-th object demand side, respectively. i 、b i They refer to the unit transportation cost of the core object and the associated object on the i-th object demand side, respectively. i 、a i They refer to the bulk transportation costs of the core object and the associated object at the i-th object demand side, Y i ,y i They refer to the market choices of the core object and the associated object on the i-th object demand side, E(min{Q i ,D i}) refers to the first actual sales expectation of the core object at the i-th (i≤n) object demand side, Refers to the second actual sales expectation of the associated object on the i-th object demand side.

[0013] According to an embodiment of the present disclosure, the correlation coefficient between the core object and the associated object at the i-th object demand side can be obtained by the following formula:

[0014]

[0015] Among them, λ i It refers to the correlation coefficient between the core object and the associated object at the i-th object demand side, T A It refers to the average number of times a core object appears in each transaction record containing the core object. B It refers to the average number of times the associated object appears in each transaction record in the transaction records containing the core object. m1 refers to the number of transaction patterns containing the core object. The number of occurrences of transaction pattern j is t j In this transaction mode, the purchase amount of the core object is a j , m2 refers to the number of transaction patterns containing associated objects, and the number of occurrences of transaction pattern k is t k In this transaction mode, the purchase amount of the associated object is b k .

[0016] According to an embodiment of the present disclosure, under the constraints of the above-mentioned dual-objective prediction model, based on the above-mentioned first actual sales expectation and the above-mentioned second actual sales expectation, determining that the above-mentioned object provider distributes the first actual delivery quantity of the above-mentioned core object and the second actual delivery quantity of the above-mentioned associated object to each of the above-mentioned object demanders respectively may include: under the constraints of the above-mentioned dual-objective prediction model, based on the above-mentioned first actual sales expectation and the above-mentioned second actual sales expectation, determining that the above-mentioned object provider distributes the first original delivery quantity of the above-mentioned core object and the second original delivery quantity of the above-mentioned associated object to each of the above-mentioned object demanders respectively; obtaining the first selection variable of the above-mentioned core object in each of the above-mentioned object demanders and the second selection variable of the above-mentioned associated object in each of the above-mentioned object demanders; determining the above-mentioned first actual delivery quantity based on the above-mentioned first selection variable and the above-mentioned first original delivery quantity; and determining the above-mentioned second actual delivery quantity based on the above-mentioned second selection variable and the above-mentioned second original delivery quantity.

[0017] In order to achieve the above-mentioned objectives, another aspect of the present disclosure provides a device for determining the distribution volume, which device may include: a first acquisition module, used to acquire a dual-objective prediction model of a supply chain, the supply chain being composed of an object provider and n object demanders, the dual-objective prediction model being used to characterize the total profit and service level of the n object demanders, and n being an integer greater than 1; a second acquisition module, used to obtain a first actual sales expectation of the core object and a second actual sales expectation of the associated object based on the historical sales of the core object and the associated object at each object demander, the associated object having an associated sales relationship with the core object; and a determination module, used to determine, under the constraints of the dual-objective prediction model, based on the first actual sales expectation and the second actual sales expectation, the first actual distribution volume of the core object and the second actual distribution volume of the associated object distributed by the object provider to each of the object demanders.

[0018] In order to achieve the above objectives, another aspect of the present disclosure provides an electronic device, including: one or more processors, and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the delivery quantity as described above.

[0019] In order to achieve the above objectives, another aspect of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the method for determining the delivery quantity as described above when executed.

[0020] In order to achieve the above objective, another aspect of the present disclosure provides a computer program, wherein the computer program includes computer executable instructions, and when the instructions are executed, they are used to implement the method for determining the delivery quantity as described above.

[0021] The method for determining the delivery quantity in the inventory management for "single supplier - multiple retailers" provided in accordance with the embodiments of the present disclosure can at least partially solve / mitigate / suppress / even avoid the problem of poor supply chain management results from not introducing cross-selling factors, and thus can achieve the improvement of supply chain management results without considering cross-selling factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, in which:

[0023] Figure 1 The application scenarios of the method, device, electronic device, medium and program product for determining the delivery quantity applicable to the embodiments of the present disclosure are schematically shown;

[0024] Figure 2 A flow chart of a method for determining a delivery amount according to an embodiment of the present disclosure is schematically shown;

[0025] Figure 3 A parameter sensitivity analysis effect diagram according to an embodiment of the present disclosure is schematically shown;

[0026] Figure 4 Another parameter sensitivity analysis effect diagram according to an embodiment of the present disclosure is schematically shown;

[0027] Figure 5 A block diagram of a device for determining a delivery amount according to an embodiment of the present disclosure is schematically shown;

[0028] Figure 6 A schematic diagram schematically shows a computer-readable storage medium product suitable for implementing the method for determining a delivery amount described above according to an embodiment of the present disclosure; and

[0029] Figure 7 A block diagram of an electronic device suitable for implementing the method for determining the delivery quantity described above according to an embodiment of the present disclosure is schematically shown.

[0030] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts.

[0031] It should be noted that the drawings are not drawn to scale and that for illustrative purposes, elements of similar structure or function are generally represented by like reference numerals throughout the drawings. DETAILED DESCRIPTION

[0032] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0033] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "including", "comprising", etc. used herein indicate the presence of the above-mentioned features, steps, operations and / or components, but do not exclude the presence or addition of one or more other features, steps, operations or components. All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having meanings consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0034] In the case of using expressions such as "at least one of A, B, and C, etc.", it should generally be interpreted as the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.). In the case of using expressions such as "at least one of A, B, or C, etc.", it should generally be interpreted as the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, or C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0035] Some block diagrams and / or flow charts are shown in the accompanying drawings. It should be understood that some blocks or combinations thereof in the block diagrams and / or flow charts can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable device for determining the delivery amount, so that these instructions can create a device for implementing the functions / operations described in these block diagrams and / or flow charts when executed by the processor. The technology of the present disclosure can be implemented in the form of hardware and / or software (including firmware, microcode, etc.). In addition, the technology of the present disclosure can take the form of a computer program product on a computer-readable storage medium storing instructions, which can be used by an instruction execution system or in combination with an instruction execution system.

[0036] In the present disclosure, it should be understood that the terms involved in the present disclosure include cross-selling, cross-selling coefficient, vendor managed inventory, integer linear programming, genetic algorithm, and Pareto optimality. Cross-selling refers to an emerging marketing method that uses customer relationship management (CRM) to explore the various needs of existing customers and sell a variety of related services or products by meeting their needs. In short, it is to promote the company's product B to customers who have the company's product A. Among them, product A is the core product and product B is its related product. For example, if a customer buys a laptop, he may also need to buy a mobile hard drive or a wireless mouse. The cross-selling coefficient specifies that it is assumed that there is a supplier that provides two products with a cross-selling relationship to n (n>0) retailers, namely the core product and the related product. At the i-th (i≤n) retailer, the cross-selling coefficient between the core product and the related product is λ i (λ i≥0), that is, the sales volume of related products driven by each unit of core product sold. Vendor Managed Inventory (VMI) refers to a cooperative strategy that aims to achieve the lowest cost for both users and suppliers, in which the supplier manages the inventory under a common agreement, and constantly monitors the implementation of the agreement and amends the content of the agreement, so that inventory management can be continuously improved. In the field of supply chain management, VMI is between buyers and suppliers, which can effectively eliminate unnecessary inventory, reduce capital occupation and backlog, improve the response speed to buyers' needs, and improve the efficiency of the entire supply chain. It embodies the innovation of procurement and supply models based on the cooperation mechanism of various enterprises in the supply chain. Integer linear programming refers to an optimization model that restricts all or part of the variables in the planning to integers. If the variables are restricted to integers in the linear model, it is called integer linear programming. Genetic Algorithm (GA) refers to a computational model that simulates the biological evolution process of natural selection and genetic mechanism in Darwin's theory of biological evolution. It is an optimal solution search method that simulates the natural evolution process. Its main features are: direct operation of structural objects, no restrictions on derivation and function continuity; inherent implicit parallelism and good global optimization capabilities; using probabilistic optimization methods, it can automatically obtain and guide the optimization search space without determining rules, and adaptively adjust the search direction. The algorithm uses computer simulation operations to convert the problem-solving process into processes similar to the selection, crossover, and mutation of chromosome genes in biological evolution. When solving more complex combinatorial optimization problems, it has certain efficiency and effect advantages compared to some conventional optimization algorithms. It has been widely used in combinatorial optimization, machine learning, signal processing, adaptive control, and artificial life. Pareto optimality was proposed by Italian economist Pareto. It refers to a resource allocation state with the following properties, that is, any form of resource reconfiguration cannot benefit at least one person without harming anyone else. Usually, the resource reconfiguration that can make at least one person's situation better and no one's situation worse is called Pareto improvement, so the Pareto optimal state is the resource allocation state where Pareto improvement no longer exists.

[0037] Pasandideh et al. considered the two-stage supply chain model of "single supplier-single retailer" and allowed the occurrence of out-of-stock situations. Delayed orders will not be cancelled. They developed an analytical model to explore the impact of important supply chain parameters on the cost savings achieved by collaborative planning. They compared the inventory management time before and after the introduction of VMI. The results obtained through three sets of numerical simulation experiments showed that in the Economic Order Quantity (EOQ) model under VMI, when the product is out of stock, the implementation of VMI strategy can only reduce the total cost of the supply chain under certain circumstances. In other words, the cost savings brought by the implementation of collaborative plans such as VMI cannot be achieved without restrictions. Information sharing and integration between companies in the supply chain cannot be achieved. Choudhary and Shankar studied the "single-period uncertainty" problem of supply chains facing time-varying demand from end users. Using mixed integer linear programming, they analyzed and compared the benefits of suppliers, retailers and the entire system when VMI with and without independent decision-making of each member was introduced under the premise of comprehensive information sharing (IS).

[0038] Cross-selling has been widely used in retail fields such as e-commerce. For example, a personalized recommendation system is built through data mining technology, and the relationship between commodities is mined based on the user's previous shopping habits, thereby achieving cross-selling. However, the relevant technology does not consider the cross-selling factor in either the "supplier-single retailer" or the "single supplier-multiple retailers" two-level supply chain model.

[0039] Therefore, the present disclosure provides a method for determining the distribution volume, including a process for obtaining the actual sales expectation and a process for determining the actual distribution volume. In the process of obtaining the actual sales expectation, firstly, a dual-objective prediction model of the supply chain is obtained, the supply chain is composed of an object provider and n object demanders, the dual-objective prediction model is used to characterize the total profit and service level of the n object demanders, n is an integer greater than 1, and then based on the historical sales of the core object and the associated object on each object demander, the first actual sales expectation of the core object and the second actual sales expectation of the associated object are obtained, and the associated object has an associated sales relationship with the core object. After the process of obtaining the actual sales expectation is completed, under the constraints of the dual-objective prediction model, based on the first actual sales expectation and the second actual sales expectation, the first actual distribution volume of the core object and the second actual distribution volume of the associated object distributed by the object provider to each object demander are determined.

[0040] Due to the method for determining the delivery volume provided by the present invention, when determining the actual delivery volume of each object demander in the object provider direction, based on the constraints of the total profit and service level representing the n object demanders, not only the actual delivery volume of the core object can be accurately predicted, but also the actual delivery volume of the associated objects that have an associated relationship with the core object can be more accurately predicted, thereby optimizing the overall profit while improving the service level.

[0041] It should be noted that the method, device, electronic device, medium and program product for determining the distribution amount provided by the present disclosure can be used in the financial field, and can also be used in any field other than the financial field. Therefore, the application field of the method, device, electronic device, medium and program product for determining the distribution amount provided by the present disclosure is not limited.

[0042] Figure 1 The application scenario 100 of the method, device, electronic device, medium and program product for determining the delivery quantity according to the embodiment of the present disclosure is schematically shown. It should be noted that: Figure 1 What is shown are merely examples of application scenarios to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0043] like Figure 1 As shown, the application scenario 100 is applicable to a supply chain for a target object 103 composed of an object provider 101 and an object demander 102. The decision-making method adopted by the supply chain in the application scenario 100 is centralized. The disclosure stipulates that the object provider 101 and the object demander 102 are in a one-to-many relationship, that is, the object demander 102 includes n (n is an integer greater than 1) object demanders, namely object demander 1021, object demander 1022, ..., object demander 102n, so that an object provider 101 can supply the target object 103 to n object demanders respectively. Since the disclosure takes into account the factor of cross-selling, the target object 103 can include a core object 1031 and an associated object 1032, wherein the core object 1031 and the associated object 1032 are objects in a cross-selling relationship, for example, the core object 1031 can be a laptop computer, and the associated object 1032 can be a mouse in a cross-selling relationship with the laptop computer.

[0044] In the present disclosure, the object provider 101, as the provider of the target object 103, is responsible for producing the target objects 103, including the core object 1031 and the associated object 1032, which are cross-selling objects, under the limitation of specific production capacity, as a manufacturer, and is responsible for distributing the target objects 103, including the core object 1031 and the associated object 1032, which are cross-selling objects, to the object demanders 102 (including the object demanders 1021, the object demanders 1022, ..., the object demanders 102n) located in multiple surrounding cities. Due to the differences in the distribution distance and unit distribution price between the object provider 101 and the object demanders 102, the transportation costs between the object provider 101 and the object demanders 102 are also different.

[0045] In the present disclosure, the object demander 102, as the demander of the target object 103, is mainly responsible for selling the target objects 103, including the core object 1031 and the associated object 1032, which have a cross-selling relationship. It should be noted that the object demander 102 and the market are in a one-to-one relationship, that is, one object demander faces one market, so each object demander is mainly responsible for selling the target objects 103, including the core object 1031 and the associated object 1032, which have a cross-selling relationship, in the market corresponding to the city. Due to the differences between individual cities, under the influence of many factors such as the intensity of market competition, the volatility of object demand, and the recognition of object brands, the market faced by each object demander is different, so that the independent demand for the core object 1031 and / or the associated object 1032, the unit sales price, the cross-selling coefficient and other factors in the market where each object demander is located are also different. At the same time, the object provider 101 and each object demander often adopt different price policies according to different markets, so the agreed purchase price of each object demander is also different.

[0046] In the application scenario 100 described above, as a bipolar supply chain model of "single provider-multiple demanders", the overall profit of the entire supply chain includes the profit obtained by the object provider 101 and the profit obtained by the object demander 102. The object provider 101 obtains its profit by producing the target object 103 and distributing a certain number of target objects 103 to one or more of the n object demanders. The profit obtained by the object demander 102 is the sum of the profits obtained by each object demander. Each object demander obtains its profit by selling part or all of a certain number of target objects 103 distributed by the object provider 101. When the object provider 101 distributes the core object 1031 and / or the associated object 1032 to each object demander, the actual distribution volume of the object provider 101 and the actual demand volume of each object demander will affect the overall profit of the supply chain. Specifically, when the actual delivery quantity of core objects 1031 and / or associated objects 1032 distributed by the object provider 101 to a certain object demander is greater than the actual demand for the core objects 1031 and / or associated objects 1032 by a certain object demander, there will be a situation where the core objects 1031 and / or associated objects 1032 are in oversupply at the object demander. Since the object provider 101 distributes too many core objects 1031 and / or associated objects 1032, it incurs excessive transportation costs, and the profits obtained by the object provider 101 are lost to a certain extent, which is very disadvantageous to the object provider 101. Accordingly, when the actual delivery quantity of the core object 1031 and / or the associated object 1032 delivered by the object provider 101 to a certain object demander is less than the actual demand for the core object 1031 and / or the associated object 1032 by the certain object demander, the core object 1031 and / or the associated object 1032 will be in short supply at the object demander. Since the object demander does not have a sufficient number of core objects 1031 and / or associated objects 1032 to sell, the profit obtained by the object demander is lost to a certain extent, which is very disadvantageous for the object demander. This is a very troublesome problem.

[0047] As mentioned above, when the object provider 101 distributes the core object 1031 and the associated object 1032 to the object demander 102, the actual distribution quantity for each object demander is crucial to reduce the shortage of the object demander, and both the object provider 101 and the object demander 102 obtain the lowest cost, and the overall profit of the supply chain reaches a high level. It is in the context of the above-mentioned problem that the present disclosure establishes an optimization model to determine the actual distribution quantity of the core object 1031 and the associated object 1032 distributed by the object provider 101 to each object demander, so that when the core object 1031 and the associated object 1032 are distributed according to the actual distribution quantity, the shortage of any object demander can be reduced, and at the same time, both the object provider 101 and the object demander 102 obtain the lowest cost, and the overall profit of the supply chain reaches a high level.

[0048] The following will be combined Figure 2 to Figure 4 , the method for determining the delivery quantity and the analytical effect of parameter sensitivity of the embodiment of the present disclosure are explained in detail.

[0049] Figure 2 A flowchart of a method for determining a delivery quantity according to an embodiment of the present disclosure is schematically shown.

[0050] like Figure 2 As shown, the method 200 may include operations S210 to S230.

[0051] In operation S210, a dual-objective prediction model of a supply chain is obtained. The supply chain is composed of an object provider and n object demanders. The dual-objective prediction model is used to characterize the total profit and service level of the n object demanders, where n is an integer greater than 1.

[0052] According to an embodiment of the present disclosure, profit is related to independent demand, unit sales price, unit purchase cost, unit transportation cost, batch transportation cost, and decision variables, and service level is related to decision variables. The object provider in the supply chain can be a generator, and the object demander can be a retailer.

[0053] In specific implementation, independent demand refers to the independent demand for core products and the independent demand for related products at each retailer node, unit sales price refers to the unit sales price of core products and the unit sales price of related products at each retailer node, unit procurement cost refers to the unit procurement cost of core products and the unit procurement cost of related products at each retailer node, unit transportation cost refers to the unit transportation cost of core products and the unit transportation cost of related products at each retailer node, and bulk transportation cost refers to the bulk transportation cost of core products and the bulk transportation cost of related products at each retailer node. Decision variables may include distribution volume and market selection. Distribution volume refers to the actual distribution volume of core products and the actual distribution volume of related products at each retailer node, and market selection refers to the market selection of core products and the market selection of related products at each retailer node.

[0054] In operation S220, based on the historical sales of the core object and the associated object at each object demander, a first actual sales expectation of the core object and a second actual sales expectation of the associated object are obtained, and the associated object has an associated sales relationship with the core object.

[0055] According to an embodiment of the present disclosure, considering the factor of cross-selling, a i Cross-selling coefficient (refers to the λ for core products and related products at each retailer node i i ), demand correlation coefficient (refers to the ρ at each retailer node i i ), and the total number of retailers (n, n is a positive integer greater than 1). In the present disclosure, Y i and i The value of can be 0 or 1. Specifically, if you choose to distribute core products, then Y i Take 1, otherwise Y i Take 0. If you choose to deliver related products, then y i Take 1, otherwise y i Take 0. It should be noted that in the present disclosure, there is no restriction on the ability of the object provider to produce core products and related products, so the production capacity is ∞.

[0056] In operation S230, under the constraints of the dual-objective prediction model, based on the first actual sales volume expectation and the second actual sales volume expectation, the object provider determines the first actual delivery volume of the core object and the second actual delivery volume of the associated object to each object demander.

[0057] According to an embodiment of the present disclosure, under the constraints of the dual-objective prediction model, the object provider distributes the first actual delivery quantity of the core object and the second actual delivery quantity of the associated object to each object demander respectively so as to maximize the total profit and the highest service level.

[0058] Through the embodiments of the present disclosure, the method for determining the delivery quantity in the inventory management for "single supplier - multiple retailers" can at least partially solve / mitigate / suppress / even avoid the problem of poor supply chain management results from not introducing cross-selling factors, and thus can achieve the improvement of supply chain management results without considering cross-selling factors.

[0059] As an optional embodiment, obtaining a first actual sales expectation of the core object and a second actual sales expectation of the associated object based on the historical sales of the core object and the associated object on each object demand side may include: determining a first indicator parameter of the core object on each object demand side based on the historical sales of the core object on each object demand side, wherein the first indicator parameter includes a demand mean, a standard deviation, a probability density function, and a cumulative distribution function; determining a second indicator parameter of the associated object on each object demand side based on the historical sales of the associated object on each object demand side, wherein the second indicator parameter includes an independent demand mean, a standard deviation, an effective demand probability density function, and a cumulative distribution function; and obtaining the first actual sales expectation of the core object and the second actual sales expectation of the associated object based on at least the first indicator parameter and the second indicator parameter.

[0060] As an optional embodiment, obtaining the first actual sales expectation of the core object and the second actual sales expectation of the associated object at least according to the first indicator parameter and the second indicator parameter includes: obtaining the first actual sales expectation of the core object and the second actual sales expectation of the associated object by the following formula:

[0061]

[0062] Among them, E(min{Q i ,D i}) refers to the first actual sales expectation of the core object at the i-th (i≤n) object demand side, Refers to the second actual sales expectation of the associated object on the i-th object demand side. The independent demand D of the core object and the associated object on the i-th object demand side i d i All obey the normal distribution, Refers to the effective demand of the associated object on the i-th object demand side, P i 、p i They refer to the unit price of the core object and the associated object at the i-th object demand side, Qi ,q i They refer to the distribution volume of the core object and the associated object on the i-th object demand side, respectively. i 、c i They refer to the unit purchase cost of the core object and the associated object at the i-th object demand side, respectively. i 、b i They refer to the unit transportation cost of the core object and the associated object on the i-th object demand side, respectively. i 、a i They refer to the bulk transportation costs of the core object and the associated object at the i-th object demand side, Y i ,y i They refer to the market choices of the core object and the associated object on the i-th object demand side. It refers to the average demand of the core object in the i-th object demand side. It refers to the independent demand mean of the associated object in the i-th object demand side. They refer to the standard deviation of the core object and the associated object on the i-th object demand side, Refers to the probability density function of the core object on the i-th object demand side, It refers to the probability density function of the effective demand of the associated object on the i-th object demand side, Pr(D i ≤Q i )、Pr(D i ≥Q i ) refers to the cumulative distribution function of the core object on the i-th object demand side, Refers to the cumulative distribution function of the associated object on the i-th object demand side, Refers to the demand correlation coefficient of the associated object on the i-th object demand side, λ i Refers to the correlation coefficient between the core object and the associated object on the i-th object demand side.

[0063] According to the embodiments of the present disclosure, the demand mean may refer to the demand average, which is a quantity used to characterize the trend of the demand data set. In specific implementation, the sum of all demand data in a set of data may be divided by the number of demand data in the set of data. Optionally, a set of data may be obtained from the historical sales data of each object demander based on the core object and the associated object. Standard Deviation is the arithmetic square root of the arithmetic mean of the square of the deviation from the mean (i.e., variance). Standard Deviation is also called Standard Deviation, or Experimental Standard Deviation. It is most commonly used in probability statistics as a measurement basis for the degree of statistical distribution. It is the most commonly used quantitative form for reflecting the degree of dispersion of a set of data and is an important indicator of accuracy. Standard Deviation is the arithmetic square root of variance. It can be understood that the standard deviation can reflect the degree of dispersion of a data set. Two sets of data with the same mean may not have the same standard deviation. A normally distributed population, by extracting multiple as samples, can obtain the sample mean. The variance or standard deviation of the sample mean needs to be considered when estimating the population mean using the sample mean. In mathematics, the probability density function of a continuous random variable is a function that describes the probability of the output value of this random variable near a certain value point. The probability that the value of the random variable falls within a certain area is the integral of the probability density function over this area. When the probability density function exists, the cumulative distribution function is the integral of the probability density function. The cumulative distribution function (Cumulative Distribution Function), also called the distribution function, is the integral of the probability density function and can fully describe the probability distribution of a real random variable.

[0064] It should be noted that when considering cross-selling, the core products at the retailer node play a certain role in driving the sales of related products. Also known as effective demand, it can be obtained by the following formula (2):

[0065]

[0066] Among them, d i refers to the independent demand of related products without considering cross-selling, i It refers to the correlation coefficient between the core object and the associated object at the i-th object demand side, Q i Refers to the distribution volume of the core object to the i-th object demand side.

[0067] As an optional embodiment, the pre-built and acquired dual-objective prediction model is expressed as the following formula (3):

[0068]

[0069] Among them, F c (Q,q) refers to the total profit of the object with positive profit in each object demand side, that is, the core object of each object demand side multiplied by the corresponding market choice Y i The profit sum is obtained by multiplying the associated object by the corresponding market choice qi, S c (Q, q) refers to the average service level of each object demand side that actually generates distribution behavior. The independent demand D of the core object and the associated object at the i-th object demand side i d i All obey the normal distribution, Refers to the effective demand of the associated object on the i-th object demand side, P i 、p i They refer to the unit price of the core object and the associated object at the i-th object demand side, Q i ,q i They refer to the distribution volume of the core object and the associated object on the i-th object demand side, respectively. i 、c i They refer to the unit purchase cost of the core object and the associated object at the i-th object demand side, respectively. i 、b i They refer to the unit transportation cost of the core object and the associated object on the i-th object demand side, respectively. i 、a i They refer to the bulk transportation costs of the core object and the associated object at the i-th object demand side, Y i ,y i They refer to the market choices of the core object and the associated object on the i-th object demand side, E(min{Q i ,D i}) refers to the first actual sales expectation of the core object at the i-th (i≤n) object demand side, Refers to the second actual sales expectation of the associated object on the i-th object demand side.

[0070] Since the dual-objective prediction model uses a genetic algorithm, it has a good global optimization capability and has certain efficiency and effect advantages over some conventional optimization algorithms. In addition, in the linear model disclosed in the present invention, the variables are restricted to integers.

[0071] In specific implementation, the service rate can be used to approximate the proportion of demand actually met by inventory to total demand, as shown in the following formula (4):

[0072]

[0073] This can obtain the The estimation of is shown in the following formula (5):

[0074]

[0075] Due to d i and D i All obey the normal distribution. According to the additivity of the normal distribution, It still belongs to the normal distribution, and the mean and variance parameters can be derived as shown in the following formulas (6) and (7):

[0076]

[0077]

[0078] Among them, ρ i The demand correlation coefficient representing the demand for core products and related products. According to the expectation calculation formula, the parameters such as the mean and variance of the actual demand distribution of related products after cross-selling are substituted into the expectation formula to obtain the expectation of the actually satisfied demand for related products. The approximate value of is shown in the following formula (8). This eliminates the expected sign of the objective function and reduces the complexity of mathematical processing.

[0079]

[0080] In related technologies, some cross-selling related parameters can be obtained through association mining technology in data mining, such as the cross-selling factor, which is used to measure the proportion of customers willing to buy core products. i Customers of the product are also willing to buy its related products. Wong et al. (2005) established a cross-selling model for estimating cross-selling factors based on association rules and loss rules as shown in the following formula (9):

[0081]

[0082] Among them, conf(A→B) refers to the probability of core products and related products appearing at the same time in transactions containing core products, T(AB) refers to the total number of transactions that contain both core products and related products, and T(A) refers to the total number of transactions that contain core products.

[0083] The cross-selling factor estimated in the related art is not equivalent to the correlation coefficient (i.e., cross-selling coefficient) in the present disclosure because the cross-selling factor obtained through the loss rule can only reflect the correlation relationship of the order granularity, but cannot obtain the demand for related products that can be brought about by the demand for a specific unit of core product.

[0084] Therefore, as an optional embodiment, the correlation coefficient between the core object and the associated object at the i-th object demand side can be obtained by the following formula:

[0085]

[0086] Among them, λ i It refers to the correlation coefficient between the core object and the associated object at the i-th object demand side, T A It refers to the average number of times a core object appears in each transaction record containing the core object. B It refers to the average number of times the associated object appears in each transaction record in the transaction records containing the core object. m1 refers to the number of transaction patterns containing the core object. The number of occurrences of transaction pattern j is t j In this transaction mode, the purchase amount of the core object is a j , m2 refers to the number of transaction patterns containing associated objects, and the number of occurrences of transaction pattern k is t k In this transaction mode, the purchase amount of the associated object is b k .

[0087] The following will take the transaction information shown in Table 1, which is statistically calculated based on the historical transaction records of the core product A and the related product B at a certain object demander, as an example to illustrate the method for determining the correlation coefficient provided by the present disclosure.

[0088] Table 1

[0089]

[0090] As shown in Table 1, there are three transaction patterns in which core product A and related product B appear together. The total number of transaction records corresponding to each pattern is t1 (in this transaction pattern, the purchase amount of core product A is 5, and the purchase amount of related product B is 3), t2 (in this transaction pattern, the purchase amount of core product A is 2, and the purchase amount of related product B is 1), and t3 (in this transaction pattern, the purchase amount of core product A is 1, and the purchase amount of related product B is 4). There are two transaction patterns in which core product A appears independently. The total number of transaction records corresponding to each pattern is t4 (in this transaction pattern, the purchase amount of core product A is 8, and because other products are purchased, the purchase amount of related product B is 0), and t5 (in this transaction pattern, the purchase amount of core product A is 3, and because other products are purchased, the purchase amount of related product B is 0).

[0091] The cross-selling coefficient of the core product A and the related product B at the demand side of the object is calculated by the above formula:

[0092]

[0093] As an optional embodiment, under the constraints of the dual-objective prediction model, based on the first actual sales expectation and the second actual sales expectation, determining the first actual delivery quantity of the core object and the second actual delivery quantity of the associated object distributed by the object provider to each object demander respectively may include: under the constraints of the dual-objective prediction model, based on the first actual sales expectation and the second actual sales expectation, determining the first original delivery quantity of the core object and the second original delivery quantity of the associated object distributed by the object provider to each object demander respectively; obtaining the first selection variable of the core object on each object demander and the second selection variable of the associated object on each object demander; determining the first actual delivery quantity based on the first selection variable and the first original delivery quantity; and determining the second actual delivery quantity based on the second selection variable and the second original delivery quantity.

[0094] According to an embodiment of the present disclosure, the first original distribution quantity Q of the core object is obtained by solving the dual-objective model. i and the second original configuration quantity q of the associated object i After that, the decision variables can be transformed by the following formula, that is, the actual value of the distribution volume (including the first actual distribution volume Q of the core object) i ' and the second actual configuration quantity q of the associated object i '). The calculation principle is the same as when cross-selling is not considered. The original distribution volume in the solution is multiplied by the market selection variable to obtain the actual distribution volume of the two commodities at each node.

[0095]

[0096] Among them, Y i and i The value of can be 0 or 1. Specifically, if you choose to distribute core products, then Y i Take 1, otherwise Y i Take 0. If you choose to deliver related products, then y i Take 1, otherwise y i Take 0.

[0097] In the context of the booming e-commerce era, through the method for determining the delivery volume provided by the embodiment of the present disclosure, a centralized VMI system model introducing cross-selling can be constructed, further improving the existing theoretical system of VMI problems and cross-selling problems, more accurately predicting demand, and optimizing overall profits while improving service levels.

[0098] Figure 3 A parameter sensitivity analysis effect diagram according to an embodiment of the present disclosure is schematically shown.

[0099] For the sake of simplicity, the parameters such as the unit procurement cost of core products, the unit procurement cost of related products, the unit sales price of core products, the unit sales price of related products, the unit transportation cost of core products, the unit transportation cost of related products, the bulk transportation cost of core products, and the bulk transportation cost of related products are fixed. It is assumed that the independent demand for core products and related products follows a normal distribution, and its distribution parameters are consistent with the problem of no transportation cost, and the capacity constraint is not considered.

[0100] like Figure 3 As shown in the figure, the maximum total profit of the supply chain (horizontal axis) and the maximum average service rate of the retailer (vertical axis) are analyzed for the sensitivity of the demand correlation coefficient ρ. This problem belongs to nonlinear bi-objective optimization and is solved by genetic algorithm. We first discuss the impact of the demand correlation coefficient ρ. The value of the cross-selling coefficient is fixed and λ is set to 0.5. The changes in the approximate optimal solution to maximize the total cost and average service level when ρ = 0.25, 0.5, 0.75, 1 are discussed respectively. The optimization results are shown in Figure 3 As shown, the horizontal axis represents the maximum overall profit under the corresponding parameter combination, and the vertical axis represents the highest service level. The Pareto front composed of triangles represents the approximate optimal solution when cross-selling is not considered, and the Pareto fronts composed of the remaining five-pointed stars represent the approximate optimal solutions under several ρ parameters when cross-selling is considered. After observation, it is found that the solution considering cross-selling is closer to the front and upper than that not considering cross-selling. Therefore, under the same overall profit, the service level considering cross-selling is higher, and under the same service level, the overall profit brought by considering cross-selling is greater. The approximate optimal solutions under the same demand correlation coefficient ρ are almost the same. This shows that the parameter ρ hardly affects the approximate value solution under cross-selling.

[0101] Alternatively, fix ρ=0.5 and discuss the impact of the cross-selling coefficient.

[0102] Figure 4 Another parameter sensitivity analysis effect diagram according to an embodiment of the present disclosure is schematically shown. Figure 4 As shown in the sensitivity analysis effect diagram of the maximum total profit of the supply chain (horizontal axis) and the maximum average service rate of retailers (vertical axis) with respect to the cross-selling coefficient, it can be seen that the curves surrounded by the five-pointed stars from top to bottom represent the Pareto frontier of the total profit and average service level of the 10 retailer nodes when λ=0.25, 0.5, 0.75, and 1 respectively. Figure 4The sensitivity analysis effect diagram of the total profit of the supply chain and the average service rate of retailers with respect to the cross-selling coefficient shows the following conclusions: the Pareto frontier with cross-selling is closer to the front than that without cross-selling. At the same overall profit level, considering cross-selling leads to a higher average service level; or at the same average service level, considering cross-selling leads to higher overall profit. By comparing the two dimensions of overall profit and average service level, it can be seen that the benefits of considering cross-selling are greater than those of not considering cross-selling. The larger the cross-selling coefficient, the closer the Pareto optimum is to the origin. Therefore, when considering cross-selling, the larger the cross-selling coefficient, the greater the overall benefit.

[0103] Figure 5 A block diagram of an apparatus for determining a delivery quantity according to an embodiment of the present disclosure is schematically shown.

[0104] like Figure 5 As shown, the device 500 may include a first acquisition module 510 , a second acquisition module 520 , and a determination module 530 .

[0105] The first acquisition module 510 is used to acquire a dual-objective prediction model of a supply chain. The supply chain is composed of an object provider and n object demanders. The dual-objective prediction model is used to characterize the total profit and service level of the n object demanders, where n is an integer greater than 1. Optionally, the first acquisition module 510 can be used to execute, for example Figure 2 The operation S210 described above will not be described in detail here.

[0106] The second acquisition module 520 is used to obtain the first actual sales expectation of the core object and the second actual sales expectation of the associated object based on the historical sales of the core object and the associated object on each object demand side, and the associated object has an associated sales relationship with the core object. Optionally, the second acquisition module 520 can be used to perform Figure 2 The operation S220 described above will not be described in detail here.

[0107] The determination module 530 is used to determine the first actual distribution volume of the core object and the second actual distribution volume of the associated object to be distributed by the object provider to each object demander based on the first actual sales volume expectation and the second actual sales volume expectation under the constraints of the dual-objective prediction model. Optionally, the determination module 530 can be used to perform Figure 2 The operation S230 described above will not be described in detail here.

[0108] As an optional embodiment, the second acquisition module may include: a first determination submodule, used to determine the first indicator parameters of the core object on each object demand side based on the historical sales of the core object on each object demand side, wherein the first indicator parameters include the demand mean, standard deviation, probability density function and cumulative distribution function; a second determination submodule, used to determine the second indicator parameters of the associated object on each object demand side based on the historical sales of the associated object on each object demand side, wherein the second indicator parameters include the independent demand mean, standard deviation, effective demand probability density function and cumulative distribution function; and a first acquisition submodule, used to obtain the first actual sales expectation of the core object and the second actual sales expectation of the associated object based on at least the first indicator parameter and the second indicator parameter.

[0109] As an optional embodiment, the first obtaining submodule is used to obtain the first actual sales expectation of the core object and the second actual sales expectation of the associated object by using the following formula:

[0110]

[0111] Among them, E(min{Q i ,D i}) refers to the first actual sales expectation of the core object at the i-th (i≤n) object demand side, Refers to the second actual sales expectation of the associated object on the i-th object demand side. The independent demand D of the core object and the associated object on the i-th object demand side i d i All obey the normal distribution, Refers to the effective demand of the associated object on the i-th object demand side, P i 、p i They refer to the unit price of the core object and the associated object at the i-th object demand side, Q i ,q i They refer to the distribution volume of the core object and the associated object on the i-th object demand side, respectively. i 、c i They refer to the unit purchase cost of the core object and the associated object at the i-th object demand side, respectively. i 、b i They refer to the unit transportation cost of the core object and the associated object on the i-th object demand side, respectively. i 、a i They refer to the bulk transportation costs of the core object and the associated object at the i-th object demand side, Y i ,y i They refer to the market choices of the core object and the associated object on the i-th object demand side. It refers to the average demand of the core object in the i-th object demand side. It refers to the independent demand mean of the associated object in the i-th object demand side. They refer to the standard deviation of the core object and the associated object on the i-th object demand side, Refers to the probability density function of the core object on the i-th object demand side, It refers to the probability density function of the effective demand of the associated object on the i-th object demand side, Pr(D i ≤Q i )、Pr(D i ≥Q i ) refers to the cumulative distribution function of the core object on the i-th object demand side, Refers to the cumulative distribution function of the associated object on the i-th object demand side, Refers to the demand correlation coefficient of the associated object on the i-th object demand side, λ i Refers to the correlation coefficient between the core object and the associated object on the i-th object demand side.

[0112] As an optional embodiment, the obtained dual-objective prediction model is expressed as the following formula:

[0113]

[0114] Among them, F c (Q,q) refers to the total profit of the object with positive profit in each object demand side, that is, the core object of each object demand side multiplied by the corresponding market choice Y i The profit sum is obtained by multiplying the associated object by the corresponding market choice qi, S c (Q, q) refers to the average service level of each object demand side that actually generates distribution behavior. The independent demand D of the core object and the associated object at the i-th object demand side i d i All obey the normal distribution, Refers to the effective demand of the associated object on the i-th object demand side, P i 、p i They refer to the unit price of the core object and the associated object at the i-th object demand side, Q i ,q i They refer to the distribution volume of the core object and the associated object on the i-th object demand side, respectively. i 、c i They refer to the unit purchase cost of the core object and the associated object at the i-th object demand side, respectively. i 、b iThey refer to the unit transportation cost of the core object and the associated object on the i-th object demand side, respectively. i 、a i They refer to the bulk transportation costs of the core object and the associated object at the i-th object demand side, Y i ,y i They refer to the market choices of the core object and the associated object on the i-th object demand side, E(min{Q i ,D i}) refers to the first actual sales expectation of the core object at the i-th (i≤n) object demand side, Refers to the second actual sales expectation of the associated object on the i-th object demand side.

[0115] As an optional embodiment, the correlation coefficient between the core object and the associated object at the i-th object demand side may be obtained by the following formula:

[0116]

[0117] Among them, λ i It refers to the correlation coefficient between the core object and the associated object at the i-th object demand side, T A It refers to the average number of times a core object appears in each transaction record containing the core object. B It refers to the average number of times the associated object appears in each transaction record in the transaction records containing the core object. m1 refers to the number of transaction patterns containing the core object. The number of occurrences of transaction pattern j is t j In this transaction mode, the purchase amount of the core object is a j , m2 refers to the number of transaction patterns containing associated objects, and the number of occurrences of transaction pattern k is t k In this transaction mode, the purchase amount of the associated object is b k .

[0118] It should be noted that in the above formulas (1) to (14) of the present disclosure, the same parameter represents the same meaning, which will not be repeated in some cases, and reference can be made to the corresponding description.

[0119] As an optional embodiment, the determination module may include: a third determination submodule, used to determine, under the constraints of the dual-objective prediction model, based on the first actual sales expectation and the second actual sales expectation, the first original delivery quantity of the core object and the second original delivery quantity of the associated object distributed by the object provider to each object demander; a second acquisition submodule, used to obtain the first selection variable of the core object at each object demander and the second selection variable of the associated object at each object demander; a fourth determination submodule, used to determine the first actual delivery quantity based on the first selection variable and the first original delivery quantity; and a fifth determination submodule, used to determine the second actual delivery quantity based on the second selection variable and the second original delivery quantity.

[0120] It should be noted that the implementation methods, technical problems solved, functions realized, and technical effects achieved of each module in the embodiment of the device for determining the delivery quantity are the same or similar to the implementation methods, technical problems solved, functions realized, and technical effects achieved of each corresponding step in the embodiment of the method for determining the delivery quantity, and they will not be repeated here.

[0121] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FNGAs), programmable logic arrays (NLAs), systems on chips, systems on substrates, systems on packages, application specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0122] For example, the first acquisition module, the second acquisition module, the determination module, the first determination submodule, the second determination submodule, the first acquisition submodule, the third determination submodule, the second acquisition submodule, the fourth determination submodule, and the fifth determination submodule can be combined in one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first acquisition module, the second acquisition module, the determination module, the first determination submodule, the second determination submodule, the first acquisition submodule, the third determination submodule, the second acquisition submodule, the fourth determination submodule, and the fifth determination submodule can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FNGA), a programmable logic array (NLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation modes of software, hardware and firmware or in a suitable combination of any of them. Alternatively, at least one of the first acquisition module, the second acquisition module, the determination module, the first determination submodule, the second determination submodule, the first acquisition submodule, the third determination submodule, the second acquisition submodule, the fourth determination submodule, and the fifth determination submodule can be at least partially implemented as a computer program module, and when the computer program module is executed, the corresponding function can be executed.

[0123] Figure 6 A schematic diagram of a computer-readable storage medium product suitable for implementing the method for determining the delivery quantity described above according to an embodiment of the present disclosure is schematically shown.

[0124] In some possible implementations, various aspects of the present invention may also be implemented in the form of a program product, which includes a program code. When the program product is run on a device, the program code is used to enable the device to perform the aforementioned operations (or steps) in the method for determining the delivery amount according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification. For example, the electronic device may perform the following steps: Figure 2 Operations S210 to S230 shown in FIG.

[0125] The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (ENROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0126] like Figure 6 As shown, a program product 600 for determining the delivery amount according to an embodiment of the present invention is described, which can be in a portable compact disk read-only memory (CD-ROM) and includes program code, and can be run on a device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution device, system or device.

[0127] The readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, in which a readable program code is carried. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, system, or device. The program code contained on the readable medium may be transmitted using any suitable medium, including, but not limited to, wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0128] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C", language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user computing device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAA) or a wide area network (WAA), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0129] Figure 7 A block diagram of an electronic device suitable for implementing the method for determining the delivery quantity described above according to an embodiment of the present disclosure is schematically shown. Figure 7 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0130] like Figure 7 As shown, the electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 to a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (e.g., a CNU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include an onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0131] In RAM 703, various programs and data required for the operation of electronic device 700 are stored. Processor 701, ROM 702, and RAM 703 are connected to each other via bus 704. Processor 701 executes various operations of the method flow according to the embodiment of the present disclosure by executing the programs in ROM 702 and / or RAM 703. It should be noted that the programs may also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 may also execute the programs stored in the one or more memories according to the embodiment of the present disclosure. Figure 2 Operations S210 to S230 shown in FIG.

[0132] According to an embodiment of the present disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, which is also connected to the bus 704. The system 700 may also include one or more of the following components connected to the I / O interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 708 including a hard disk, etc.; and a communication portion 709 including a network interface card such as an LAA card, a modem, etc. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage portion 708 as needed.

[0133] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the processor 701, the above-mentioned functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the system, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0134] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiment; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method for determining the delivery quantity according to the embodiment of the present disclosure is implemented, including: Figure 2 Operations S210 to S230 shown in FIG.

[0135] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (ENROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 702 and / or RAM 703 described above and / or one or more memories other than ROM 702 and RAM 703.

[0136] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0137] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0138] The embodiments of the present disclosure are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, a person skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A method for determining a delivery quantity, comprising: Obtaining a dual-objective forecasting model of a supply chain, the supply chain consisting of an object provider and n object demanders, the dual-objective forecasting model being used to characterize the total profit and service level of the n object demanders, where n is an integer greater than 1; Based on the historical sales of the core object and the associated object on each object demand side, a first actual sales expectation of the core object and a second actual sales expectation of the associated object are obtained, wherein the associated object has an associated sales relationship with the core object, including: Based on the historical sales volume of the core object in each object demand side, determining the first indicator parameter of the core object in each object demand side, wherein the first indicator parameter includes the demand mean, standard deviation, probability density function and cumulative distribution function; Based on the historical sales volume of the associated object at each object demand side, determine the second indicator parameter of the associated object at each object demand side, wherein the second indicator parameter includes the independent demand mean, standard deviation, effective demand probability density function and cumulative distribution function; obtaining a first actual sales expectation of the core object and a second actual sales expectation of the associated object at least according to the first indicator parameter and the second indicator parameter; and Under the constraints of the dual-objective prediction model, based on the first actual sales expectation and the second actual sales expectation, the object provider determines the first actual delivery quantity of the core object and the second actual delivery quantity of the associated object to each object demander respectively.

2. The method according to claim 1, wherein: The obtaining of the first actual sales expectation of the core object and the second actual sales expectation of the associated object at least according to the first indicator parameter and the second indicator parameter comprises: obtaining the first actual sales expectation of the core object and the second actual sales expectation of the associated object by the following formula: in, Refers to the first actual sales expectation of the core object on the i-th object demand side, Refers to the second actual sales expectation of the associated object on the i-th object demand side, and the independent demand of the core object and the associated object on the i-th object demand side , All obey the normal distribution, Refers to the effective demand of the associated object on the i-th object demand side, , They refer to the unit prices of the core object and the associated object at the i-th object demander, respectively. , They refer to the distribution volume of the core object and the associated object on the i-th object demand side, respectively. , They refer to the unit purchase cost of the core object and the associated object at the i-th object demand side. , They refer to the unit transportation costs of the core object and the associated object on the i-th object demand side, respectively. , They refer to the bulk transportation costs of the core object and the associated object on the i-th object demand side, respectively. , They refer to the market choices of the core object and the associated object on the i-th object demand side. It refers to the average demand of the core object in the i-th object demand side. It refers to the independent demand mean of the associated object on the i-th object demand side. , They refer to the standard deviation of the core object and the associated object on the i-th object demand side, Refers to the probability density function of the core object on the i-th object demand side, It refers to the probability density function of the effective demand of the associated object on the i-th object demand side. , Refers to the cumulative distribution function of the core object on the i-th object demand side, , Refers to the cumulative distribution function of the associated object on the i-th object demand side, Refers to the demand correlation coefficient of the associated object on the i-th object demand side, It refers to the correlation coefficient between the core object and the associated object on the i-th object demand side, i≤n.

3. The method according to claim 1, wherein: The obtained dual-objective prediction model is expressed as the following formula: in, It refers to the total profit of the object with positive profit in each object demand side, that is, the core object of each object demand side multiplied by the corresponding market choice Multiply the associated object by the corresponding market choice y i The profit sum obtained by adding up is It refers to the average service level of each object demand side that actually generates the distribution behavior, the independent demand of the core object and the associated object on the i-th object demand side , All obey the normal distribution, Refers to the effective demand of the associated object on the i-th object demand side, , They refer to the unit prices of the core object and the associated object at the i-th object demander, respectively. , They refer to the distribution volume of the core object and the associated object on the i-th object demand side, respectively. , They refer to the unit purchase cost of the core object and the associated object at the i-th object demand side. , They refer to the unit transportation costs of the core object and the associated object on the i-th object demand side, respectively. , They refer to the bulk transportation costs of the core object and the associated object on the i-th object demand side, respectively. , They refer to the market choices of the core object and the associated object on the i-th object demand side. Refers to the first actual sales expectation of the core object on the i-th object demand side, Refers to the second actual sales expectation of the associated object at the i-th object demand side, i≤n.

4. The method according to claim 2, wherein: The correlation coefficient between the core object and the associated object on the i-th object demand side is obtained by the following formula: in, Refers to the correlation coefficient between the core object and the associated object on the i-th object demand side. Refers to the average number of times a core object appears in each transaction record that contains the core object. Refers to the average number of times the associated object appears in each transaction record that contains the core object. Refers to the number of transaction modes that contain core objects. The number of occurrences of is In this transaction mode, the purchase amount of the core object is c j , Refers to the number of transaction modes that contain associated objects. The number of occurrences of is In this transaction mode, the purchase amount of the associated object is d k .

5. The method according to claim 1, wherein: The determining, under the constraint of the dual-objective prediction model, based on the first actual sales volume expectation and the second actual sales volume expectation, that the object provider distributes a first actual distribution volume of the core object and a second actual distribution volume of the associated object to each object demander respectively comprises: Under the constraints of the dual-objective forecasting model, based on the first actual sales volume expectation and the second actual sales volume expectation, determining that the object provider distributes a first original distribution volume of the core object and a second original distribution volume of the associated object to each object demander respectively; Obtain a first selection variable of the core object on each object demand side and a second selection variable of the associated object on each object demand side; determining the first actual delivery amount based on the first selection variable and the first original delivery amount; and Based on the second selection variable and the second original delivery amount, the second actual delivery amount is determined.

6. A device for determining a delivery amount, comprising: A first acquisition module is used to acquire a dual-objective prediction model of a supply chain, wherein the supply chain is composed of an object provider and n object demanders, and the dual-objective prediction model is used to characterize the total profit and service level of the n object demanders, where n is an integer greater than 1; The second acquisition module is used to obtain a first actual sales expectation of the core object and a second actual sales expectation of the associated object based on the historical sales of the core object and the associated object on each object demand side, wherein the associated object has an associated sales relationship with the core object, including: Based on the historical sales volume of the core object in each object demand side, determining the first indicator parameter of the core object in each object demand side, wherein the first indicator parameter includes the demand mean, standard deviation, probability density function and cumulative distribution function; Based on the historical sales volume of the associated object at each object demand side, determine the second indicator parameter of the associated object at each object demand side, wherein the second indicator parameter includes the independent demand mean, standard deviation, effective demand probability density function and cumulative distribution function; obtaining a first actual sales expectation of the core object and a second actual sales expectation of the associated object at least according to the first indicator parameter and the second indicator parameter; and A determination module is used to determine, under the constraints of the dual-objective prediction model, based on the first actual sales expectation and the second actual sales expectation, the first actual delivery quantity of the core object and the second actual delivery quantity of the associated object distributed by the object provider to each object demander.

7. An electronic device comprising: one or more processors; as well as a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are caused to execute the method according to any one of claims 1 to 5. 8 . A computer-readable storage medium storing computer-executable instructions, which, when executed, cause a processor to perform the method according to claim 1 .

9. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is performed.

Citation Information

Patent Citations

  • Object distribution method and system, computer system and computer readable storage medium

    CN110135673A

  • Main and distribution network integrated dynamic resource allocation method and device

    CN110650047A