Cargo management method, electronic equipment and computer storage medium

Abstract

The invention discloses a cargo management method, electronic equipment and a computer storage medium, and the method comprises the steps: obtaining the correlation degree corresponding to a plurality of preselected suppliers, and determining a supply end corresponding to one preselected supplier as a target supply end according to the correlation degree; in response to the received supply information and the first inventory information sent by the target supply end, inputting the supply information, the first inventory information, the production information and the second inventory information to a preset analysis model to obtain an optimal replenishment strategy; and sending the optimal replenishment strategy to the target supply end, so that the target supply end generates a warehouse-out order according to the optimal replenishment strategy. According to the invention, the supply information sent by the supply end, the first inventory information, the production information of the supply end and the second inventory information are input into the preset analysis model, and then the optimal replenishment strategy is obtained, so that the information sharing degree of the supply and demand parties and the cooperation among the links are enhanced, flexible replenishment is realized, and the inventory and logistics costs are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of cargo management, and in particular to a cargo management method, electronic equipment and computer storage medium. Background Art

[0002] At present, the cooperative relationship between the enterprise and the supplier is: the enterprise orders the required quantity of materials through purchase orders, and the supplier matches the current inventory level after receiving the purchase order and formulates a production plan. According to the purchase order, the supplier delivers the agreed quantity of materials to the enterprise before the delivery time required by the enterprise, and the enterprise receives the goods and performs settlement operations after confirming that the quantity of goods is correct.

[0003] In the above-mentioned cooperative relationship, the purchase order will be sent to the supplier only when the enterprise has demand, and the enterprise will not share other information with the supplier in other cases. However, the above-mentioned method will aggravate the bullwhip effect, causing both parties to hold a higher inventory buffer, which will invisibly increase inventory costs. Summary of the invention

[0004] The purpose of this application is to provide a cargo management method, electronic device and computer storage medium, aiming to solve the problem in the prior art that the bullwhip effect exacerbates the problem of rising inventory costs due to lack of real-time collaboration and low information sharing between the enterprise and the supply side.

[0005] To achieve the above objectives: In a first aspect, an embodiment of the present application provides a cargo management method, which is applied to a cargo warehousing management system, wherein the cargo warehousing management system includes an enterprise end and a supply end, wherein the enterprise end and the supply end are in communication connection, and the method includes: Obtaining correlations corresponding to a plurality of pre-selected suppliers, and determining a supply end corresponding to one of the pre-selected suppliers as a target supply end according to the correlations; In response to receiving the supply information and the first inventory information sent by the target supplier, inputting the supply information, the first inventory information, the own production information and the second inventory information into a preset analysis model to obtain an optimal replenishment strategy; The optimal replenishment strategy is sent to the target supplier, so that the target supplier generates a delivery order according to the optimal replenishment strategy.

[0006] In one implementation, obtaining the correlations corresponding to the plurality of pre-selected suppliers includes: Obtaining preset reference series and comparison series for each pre-selected supplier; The relevance of each of the pre-selected suppliers is determined respectively according to the reference number series and the comparison number series.

[0007] In one implementation, obtaining the correlations corresponding to the plurality of pre-selected suppliers includes: Obtaining preset reference series and comparison series for each pre-selected supplier; The relevance of each of the pre-selected suppliers is determined respectively according to the reference number series and the comparison number series.

[0008] In one embodiment, obtaining a preset reference sequence and a comparison sequence of each pre-selected supplier includes: Establishing an analysis indicator system based on pre-selected analysis indicators; The reference number series and the comparison number series are determined according to the analysis indicator system.

[0009] In one embodiment, the determining the relevance of each of the pre-selected suppliers according to the reference number series and the comparison number series respectively includes: According to the reference number series and the comparison number series, respectively obtain the grey correlation degree corresponding to each of the pre-selected suppliers on each of the analysis indicators; The relevance degree of each of the pre-selected suppliers is determined respectively according to the grey relevance degree.

[0010] In one embodiment, determining a supplier corresponding to one of the pre-selected suppliers as a target supplier according to the correlation degree includes: Performing weighted summation of the grey correlation degree corresponding to each of the pre-selected suppliers on each of the analysis indicators to obtain the correlation degree of each of the pre-selected suppliers; The supply end corresponding to the pre-selected supplier with the highest correlation is determined as the target supply end.

[0011] In one embodiment, before inputting the supply information, the first inventory information, the own production information and the second inventory information into a preset analysis model to obtain an optimal replenishment strategy, the method includes: Using a preset decision framework, the historical supply information, the historical first inventory information, the historical production information of the self, and the historical second inventory information are combined to generate a decision model; Solving the decision model using a preset learning algorithm to obtain a first sub-analysis model; constructing a reinforcement learning environment for the first sub-analysis model to obtain a second sub-analysis model; The second sub-analysis model is trained to obtain the analysis model.

[0012] In one embodiment, the training of the second sub-analysis model to obtain the analysis model includes: Initialize the preset strategy parameters; In each preset period, the current inventory status and the preset simulated replenishment strategy are input into the second sub-analysis model to obtain the replenishment quantity; Acquire simulated inventory information, market supply information, and cost information according to a preset learning environment and the replenishment quantity, and update the strategy parameters according to the simulated inventory information, market supply information, and cost information; Determining whether the strategy parameters reach a preset stability threshold; If yes, determining the second sub-analysis model as the analysis model; If not, the step of initializing the preset strategy parameters is executed again.

[0013] In one embodiment, after inputting the supply information, the first inventory information, the own production information and the second inventory information into a preset analysis model to obtain an optimal replenishment strategy, the method further includes: Evaluating the analysis model to determine whether the effectiveness of the optimal replenishment strategy in a real scenario reaches a preset effectiveness threshold; If yes, then proceed to the step of sending the optimal replenishment strategy to the target supply end; If not, the step of initializing the preset strategy parameters is executed again. In a second aspect, an embodiment of the present application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the cargo management method as described above when executing the computer program.

[0014] In a third aspect, an embodiment of the present application further provides a computer storage medium, wherein the computer storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the cargo management method described above are implemented.

[0015] In this application, for the enterprise side, the supply information sent by the supply side, the first inventory information, its own production information and the second inventory information are input into the preset analysis model to obtain the best replenishment strategy. In this way, the information sharing level between the supply and demand sides and the coordination between various links are strengthened, flexible replenishment is achieved, and inventory and logistics costs are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of a cargo management method provided by an embodiment of the present invention.

[0017] Figure 2 A flowchart of a cargo management method provided by another embodiment of the present invention.

[0018] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0019] Description of Figure Numbers: 310. Processor; 311. Memory; 312. Network interface; 313. Bus system. DETAILED DESCRIPTION

[0020] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0021] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0022] It should be understood that, although the terms first, second, third, etc. may be used to describe various information in this article, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this article, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "at the time of..." or "when..." or "in response to determination". Furthermore, as used in this article, the singular forms "one", "one" and "the" are intended to also include plural forms, unless there is an opposite indication in the context. It should be further understood that the terms "comprising", "including" indicate that there are described features, steps, operations, elements, components, projects, kinds, and / or groups, but do not exclude the existence, occurrence or addition of one or more other features, steps, operations, elements, components, projects, kinds, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or mean any one or any combination. Thus, “A, B, or C” or “A, B and / or C” means “any of the following: A; B; C; A and B; A and C; B and C; A, B, and C.” An exception to this definition will occur only when a combination of elements, functions, steps, or operations are inherently mutually exclusive in some manner.

[0023] It should be understood that, although the various steps in the flowchart in the embodiment of the present application are displayed in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and it can be performed in other orders. Moreover, at least a portion of the steps in the figure may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and their execution order is not necessarily performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0024] It should be noted that in this article, step codes such as S1 and S2 are used for the purpose of expressing the corresponding content more clearly and concisely, and do not constitute a substantial limitation on the order. When implementing the step, those skilled in the art may execute S2 first and then S1, etc., but these should all be within the scope of protection of this application.

[0025] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0026] In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present application, and have no specific meanings. Therefore, "module", "component" or "unit" can be used in a mixed manner.

[0027] The following is an explanation of the terms that may be involved in this application, as follows: VMI (Vendor Managed Inventory) is a supply chain management strategy whose core concept is that suppliers are responsible for effectively managing customers' inventory levels. In the VMI model, suppliers make replenishment decisions based on predetermined inventory levels agreed with customers to ensure that customers always have the right amount of inventory. This model enables suppliers to manage the entire supply chain end-to-end by sharing inventory and demand data, as well as delivery parameters, thereby improving the efficiency and responsiveness of the supply chain.

[0028] ERP system, or Enterprise Resource Planning system, is an integrated software solution that aims to optimize the resource allocation and operational efficiency of an enterprise by integrating various business processes and information systems within the enterprise. ERP system usually contains multiple modules, covering all aspects of enterprise operations, such as finance, human resources, supply chain management, customer relationship management, production management, etc.

[0029] Reference sequence: The optimal value of each indicator under ideal conditions. It represents the supplier's most ideal performance on each indicator and can be set by historical data or industry benchmark data. For example, the lowest quotation, the highest quality score, the lowest legal risk, the best financial performance, etc.

[0030] Comparison series: actual performance data of each supplier on each indicator.

[0031] MDP: (Markov Decision Process) is a mathematical framework for simulating the behavior of intelligent agents (such as robots or software programs) that make decisions in uncertain environments. MDP is particularly suitable for scenarios where a series of interdependent decisions need to be made, such as path planning, autonomous driving, financial investment decisions, etc.

[0032] Please refer to Figure 1 , Figure 1 A flow chart of a cargo management method is shown, which is applied to a cargo warehousing management system. The cargo warehousing management system includes an enterprise end and a supply end, and the enterprise end and the supply end are connected in communication. The method includes: S11. Obtain the correlations corresponding to the multiple pre-selected suppliers, and determine the supply end corresponding to one of the pre-selected suppliers as the target supply end according to the correlation. Specifically, in this embodiment, for the enterprise end, firstly, multiple pre-selected suppliers are screened from the supplier list, then the correlations corresponding to the multiple pre-selected suppliers are obtained, and finally, one of the pre-selected suppliers is selected according to the correlation, and the supply end corresponding to the pre-selected supplier is determined as the target supply end to be cooperated with.

[0033] S12, in response to receiving the supply information and the first inventory information sent by the target supply end, input the supply information, the first inventory information, the production information and the second inventory information of the target supply end into a preset analysis model to obtain the best replenishment strategy. Specifically, in this embodiment, the enterprise end and the target supply end can both use the ERP system as their respective management systems. For the enterprise end, by connecting its own enterprise-end ERP system with the target supply end ERP system used by the target supply end, the real-time sharing of supply information, inventory information and other information between the two parties can be achieved.

[0034] Among them, the supply information may include the types of goods that the target supplier can provide and their corresponding quantities, and the first inventory information may include the inventory quantity, type, time, etc. of the goods currently available at the target supplier, or the inventory quantity, type, time, etc. of the goods that need to be introduced in the future.

[0035] Furthermore, the enterprise side inputs the received supply information and the first inventory information, its own production information and the second inventory information into the preset analysis model to obtain the best replenishment strategy. Among them, its own production information and the second inventory information correspond to the supply information, that is, all types of goods appearing in the supply information will match its own production information and the second inventory information. Exemplarily, the supply information includes: 500W power supply * 100, then at this time, its own production information corresponds to the production quantity, model, price and other information of the 500W power supply, and the second inventory information corresponds to the inventory quantity of the 500W power supply, etc. The best replenishment strategy may include, for example, the minimum inventory level, the maximum inventory level, the current replenishment plan, etc.

[0036] S13, sending the best replenishment strategy to the target supply side, so that the target supply side generates a delivery order according to the best replenishment strategy. Specifically, in this embodiment, after sending the best replenishment strategy to the target supply side, the target supply side will configure the corresponding goods according to the best replenishment strategy, and send the generated delivery order to the enterprise side, and the enterprise side will enter the goods according to the delivery order to achieve flexible replenishment, and the enterprise side can achieve monthly or quarterly settlement according to the use situation.

[0037] By executing methods S11~S13, the flexible collaborative replenishment method based on the analytical model obtains the optimal replenishment strategy, strengthens the information sharing between the supply and demand sides and the collaboration between various links, and solves the problems of lack of real-time collaboration and low information sharing between the enterprise side and the supply side in the existing technology, resulting in a lack of information transparency among all parties in the supply chain in terms of delivery timeliness, inventory management, demand forecasting, etc., resulting in both parties holding high inventory buffers and rising inventory costs. It improves the operational efficiency between the two parties and can also promote long-term cooperation and trust.

[0038] Please refer to Figure 2 The step S11 of obtaining the correlations corresponding to the plurality of pre-selected suppliers includes: Obtain a preset reference series and a comparison series for each pre-selected supplier. Specifically, in this embodiment, the reference series is actually an ideal indicator, such as the best quotation, product quality, legal risk, production capacity, etc. that the enterprise expects the supplier to provide, and the comparison series for each pre-selected supplier corresponds to the actual situation of the above-mentioned example indicators, that is, the actual indicator.

[0039] The relevance of each pre-selected supplier is determined according to the reference series and the comparison series. Specifically, in this embodiment, the relevance is a comprehensive grey relevance, and the reference series and the comparison series are substituted into the formula in combination with the grey relevance calculation formula to calculate the relevance of each pre-selected supplier.

[0040] Optionally, obtaining a preset reference sequence and a comparison sequence of each pre-selected supplier in the above step includes: An analysis indicator system is established based on the preselected analysis indicators, and a reference series and a comparison series are determined based on the analysis indicator system. Specifically, in this embodiment, the analysis indicators may include indicator information such as product price, product quality, legal risk, and financial situation. First, an analysis indicator system is established based on the preselected analysis indicators. Secondly, a reference series and a comparison series are determined based on the analysis indicator system. Among them, the reference series is the optimal value of each analysis indicator under an ideal state. It represents the most ideal performance of the preselected suppliers on each indicator, and can be set by historical data or industry benchmark data. For example, the lowest quotation, the highest quality score, the lowest legal risk, the best financial performance, etc. The comparison series is the actual performance data of each preselected supplier on each indicator.

[0041] Furthermore, each analytical indicator may be further broken down into several sub-indicators, and data may be collected on these sub-indicators for each pre-selected supplier.

[0042] Optionally, determining the relevance of each pre-selected supplier according to the reference number series and the comparison number series in the above step includes: The grey correlation degree corresponding to each pre-selected supplier on each analysis indicator is obtained according to the reference series and the comparison series. Specifically, in this embodiment, after determining the reference series and the comparison series, the two sets of data are input into the calculation formula of the grey correlation degree, and then the grey correlation degree corresponding to each pre-selected supplier on each analysis indicator is calculated.

[0043] The relevance of each pre-selected supplier is determined according to the grey relevance. Specifically, in one embodiment, the enterprise can select the pre-selected supplier with the highest grey relevance corresponding to a certain analysis indicator, and the grey relevance corresponding to the analysis indicator is the relevance of the pre-selected supplier. In another embodiment, the grey relevance corresponding to any N (N is less than or equal to the total number of pre-selected analysis indicators) analysis indicators is added, and the sum obtained is the relevance of the pre-selected supplier.

[0044] Optionally, the step S11 of determining a supplier corresponding to a pre-selected supplier as a target supplier according to the correlation degree includes: The supply side corresponding to the pre-selected supplier with the highest correlation is determined as the target supply side. Specifically, in this embodiment, each pre-selected supplier is sorted according to the degree of correlation, and the supply side corresponding to the pre-selected supplier with the highest correlation is determined as the target supply side for cooperation. It can be understood that the higher the correlation, the closer its performance in all aspects is to the ideal state.

[0045] Furthermore, the supply side corresponding to the pre-selected supplier with the highest correlation is determined as the target supply side, including: weighted summing the gray correlation corresponding to each pre-selected supplier on each analysis indicator to obtain the correlation of each pre-selected supplier respectively; and determining the supply side corresponding to the pre-selected supplier with the highest correlation as the target supply side. Specifically, for the pre-selected suppliers, by weighted summing the gray correlation calculated on each analysis indicator, a correlation is calculated to judge whether the pre-selected supplier's performance in various aspects meets the cooperation threshold. Then, the supply side corresponding to the pre-selected supplier with the highest correlation is determined as the target supply side to ensure the smoothness of the cooperation between the two parties in all aspects.

[0046] Based on the above steps, first, the enterprise selects several pre-selected suppliers with cooperation intentions, and inquires about prices with each pre-selected supplier separately, while collecting relevant information such as product quality, legal risks, and financial statements. Secondly, all collected relevant information is input into the preset calculation model to obtain the calculation results of each pre-selected supplier. Finally, the best supplier is selected based on the calculation results. In this way, using the gray system theory to analyze the quotation, quality, legal risk, and financial situation of each pre-selected supplier can help enterprises evaluate and select each pre-selected supplier when the information is incomplete. It is only used as an example. The specific steps are as follows: Step 1: Establish an analysis indicator system; Identify the key metrics you will use to evaluate your suppliers. In this example, choose the following four key areas: a. Price: whether the supplier's quotation is competitive; b. Quality: such as product or service quality standards, return rates, customer satisfaction, etc.; c. Legal risks: whether the supplier has any legal disputes, contract execution status, etc.; d. Financial situation: such as the supplier’s financial stability, debt repayment ability, liquidity, etc.; Each indicator can be further broken down into several sub-indicators, and data is collected for each supplier on these sub-indicators.

[0047] Step 2, determine the reference sequence and the comparison sequence; Reference sequence (ideal situation): Lowest bid: P ref = [10, 12, 11, 9]; Highest quality: Q ref = [95, 98, 97, 96]; Minimum legal risk: L ref = [1, 2, 1, 2]; Best Financial Performance: F ref = [85, 90, 88, 87]; Comparison series (supplier performance): Supplier A: A i = [12, 94, 2, 86]; Supplier B: B i = [11, 96, 1, 89]; Supplier C: C i = [10, 95, 1, 85]; Supplier D:D i = [9, 97, 2, 88]; Step 3: Data preprocessing; Since the dimensions of each indicator are different, the data needs to be standardized. The purpose of standardization is to convert data of different units into relatively comparable data, usually using the minimization or maximization method. In this example, it is assumed that the data is dimensionless.

[0048] Step 4: Calculate the grey relational degree; 4.1 In this example, the resolution coefficient ρ used to adjust the sensitivity of the grey relational degree is set to 0.5, and then the grey relational degree of each supplier on each factor is calculated using the following formula:

[0049] in, , ; as well as are the minimum and maximum absolute differences of the i-th supplier on the k-th indicator, is the value of the kth index in the reference sequence, is the value of the kth indicator of the ith supplier in the comparison sequence.

[0050] 4.2 Calculate the correlation coefficient at each moment: = min(min(| P ref -P i |, | Q ref -Q i |, | L ref -L i |, | F ref -F i |)); = max(max(| P ref -P i |, | Q ref -Q i |, | L ref -L i |, | F ref -F i |)); Assume the calculation result is: = 0; = 10; 4.3 Calculate the grey correlation degree for each supplier and each factor; For price:

[0051]

[0052]

[0053]

[0054] in, is the grey correlation degree of supplier A in terms of price; is the grey correlation degree of supplier B in terms of price; is the grey correlation degree of supplier C in terms of price; is the grey correlation degree of supplier D in terms of price.

[0055] For quality:

[0056]

[0057]

[0058]

[0059] in, is the grey correlation degree of supplier A in terms of quality; is the grey correlation degree of supplier B in terms of quality; is the grey correlation degree of supplier C in terms of quality; is the grey correlation degree of supplier D in terms of quality.

[0060] Regarding legal risks:

[0061]

[0062]

[0063]

[0064] in, is the grey correlation degree of legal risk of supplier A; The gray correlation degree of legal risk of supplier B; The gray correlation degree of legal risk of supplier C; is the grey correlation degree of legal risk of supplier D.

[0065] Regarding financial performance:

[0066]

[0067]

[0068]

[0069] in, is the grey correlation degree of supplier A in financial performance; is the grey correlation degree of supplier B in financial performance; is the grey correlation degree of the financial performance of supplier C; is the grey correlation degree of the financial performance of supplier D.

[0070] Step 5, calculate the comprehensive grey relational degree; Finally, for each supplier, the comprehensive grey correlation degree is calculated by taking the weighted average of the grey correlation degrees of all indicators. The calculation can be done using the following formula:

[0071] in, is the comprehensive grey correlation degree of supplier i; n is the number of pre-selected suppliers; is the grey correlation degree of the supplier.

[0072] In this example, for each supplier's comprehensive grey correlation:

[0073]

[0074]

[0075]

[0076] Step 6: Sort the association order; By sorting the above-mentioned pre-selected suppliers according to the size of the comprehensive grey correlation degree, it can be concluded that supplier C has the highest comprehensive grey correlation degree, which means that supplier C is closest to the ideal reference series in all considered factors. Therefore, in this example, the supply end corresponding to supplier C is taken as the target supply end.

[0077] In one implementation, after the supplier corresponding to the pre-selected supplier with the highest correlation is determined as the target supplier, the enterprise can also sign a VMI agreement with the target supplier. In this way, by adopting the VMI replenishment model, the enterprise can set the minimum inventory level and the maximum inventory level, and the supplier will replenish the warehouse regularly according to the agreed inventory plan. After the enterprise actually receives the goods from the warehouse, the supplier will settle accounts with the enterprise regularly, thereby improving the synergy between the enterprise and the target supplier.

[0078] Optionally, after determining the supply end corresponding to the pre-selected supplier with the highest correlation as the target supply end, the method further includes: In response to the completion of the construction of the first management system, the first management system is controlled to communicate with the second management system of the target supply end. Specifically, in this embodiment, the enterprise end and the target supply end can both use ERP systems as their respective management systems. For the enterprise end, the first management system, that is, the enterprise end ERP system and the target supply end ERP system applied by the target supply end are connected, that is, the communication connection is achieved between the two. Either party can view the dynamic update of the other party's ERP system through its ERP system, so that the real-time sharing of supply information, inventory information and other information of both parties can be achieved.

[0079] Furthermore, the preset enterprise-side information is sent to the second management system through the first management system to establish a connection with the target supply side. Specifically, in this embodiment, the enterprise side sends customer market demand, production status, and material inventory to the ERP system of the target supply side through the interface provided by the enterprise-side EPR system, thereby achieving the purpose of establishing a connection with the target supply side, realizing information sharing, and enhancing the cooperative relationship between the two parties.

[0080] Optionally, after enabling the target supplier to generate a delivery order according to the optimal replenishment strategy in step S13, the method further includes: Create a collection order, and send the collection order to the second management system through the first management system. Specifically, in this embodiment, after the enterprise side performs the action of warehousing goods according to the outbound order sent by the target supply side, a collection order will be automatically created in the enterprise side ERP system based on the production situation, consuming materials, and sent to the target supply side ERP system through the enterprise side ERP system, so as to achieve the purpose of informing the target supply side of the actual collection situation of the goods in real time. In this way, sharing the collection situation through the interconnected ERP systems can greatly reduce the time required for confirmation and improve the efficiency of warehousing.

[0081] Among them, the pick-up order can be associated with but not limited to the following information: order number, delivery address, delivery time and place, packaging requirements, transportation method, acceptance criteria, liability for breach of contract, order tracking, material acceptance, product name, model, specifications, quantity, price, etc.

[0082] Furthermore, in response to receiving the settlement list generated by the target supply end according to the collection order, the settlement bill is transferred and remitted. Specifically, in this embodiment, for the target supply end, after receiving the collection order sent by the enterprise-side ERP system through the target supply-side ERP system, for example, a settlement list can be automatically generated monthly based on the collection order and sent to the enterprise-side ERP system. For the enterprise end, after receiving the settlement list, the corresponding accounts on the settlement list are transferred to the target supply-side ERP system through the enterprise-side ERP system. In this way, the connected ERP systems can not only realize real-time information sharing, but also realize monthly account transfer and settlement, which greatly improves the efficiency of cooperation between the two parties.

[0083] Optionally, before inputting the supply information, the first inventory information, and the own production information and the second inventory information into a preset analysis model to obtain the best replenishment strategy in step S12, the method further includes: The historical supply information, the historical first inventory information, the historical production information and the historical second inventory information are combined using a preset decision framework to generate a decision model. Specifically, in this embodiment, the core purpose of performing this step is to define a reinforcement learning framework. Among them, the reinforcement learning problem can be modeled by a Markov decision process (MDP), which includes the following five key elements: a. State (S): The state of the system is a collection of relevant information such as market demand (supply information), inventory status (first inventory information), production status (its own production information), and inventory cost (second inventory information).

[0084] b. Action (A): Action represents the replenishment decision that the system can take at each moment.

[0085] c. Reward function (R): The reward function measures the quality of each action, with the aim of guiding the system to select actions that maximize long-term benefits.

[0086] d. State transition (Transition, T): The state transition function defines the probability of transitioning from one state to the next state.

[0087] e. Discount Factor (γ): The discount factor is used to balance the weight between current and future rewards. It is usually between 0 and 1 and is used to weigh the relationship between long-term benefits and short-term benefits.

[0088] Further, the decision model is solved using a preset learning algorithm to obtain the first sub-analysis model. Specifically, in this embodiment, the preset learning algorithm may include but is not limited to Q-learning, deep Q network, policy gradient method, proximal policy optimization algorithm, etc.

[0089] Furthermore, a reinforcement learning environment is constructed for the first sub-analysis model to obtain the second sub-analysis model. Specifically, in this embodiment, in order to train the first sub-analysis model, a simulated replenishment decision environment needs to be constructed. The simulated replenishment decision environment should have the following characteristics: a. Inventory level update rules: Inventory status is updated based on current inventory, market demand, and production. If demand exceeds inventory, a stockout may occur.

[0090] b. Market demand generation: Generate future demand based on historical data or demand forecasting models. Stochastic processes (such as Poisson distribution and normal distribution) can be used to simulate demand fluctuations.

[0091] c. Production status update: simulate production capacity and production time, and consider factors that affect production efficiency such as production speed and raw material supply.

[0092] d. Cost calculation: Inventory holding costs, out-of-stock costs, and production costs are calculated in real time and used as part of the reward function.

[0093] Furthermore, the second sub-analysis model is trained to obtain an analysis model. Specifically, in this embodiment, the second sub-analysis model is trained to learn various replenishment strategies under different conditions, and finally an analysis model capable of outputting the best replenishment strategy is obtained.

[0094] Optionally, the training of the second sub-analysis model in the above step to obtain the analysis model includes: Initialize the preset policy parameters. Specifically, in this embodiment, by initializing the Q table or policy network, the process of exploring different replenishment strategies begins. It can be understood that in the initial stage of reinforcement learning, a Q table or policy network needs to be set up. Among them, the Q table is a two-dimensional array, in which the rows represent all possible states and the columns represent all possible actions. Each cell Q(s, a) stores the expected return of taking action a in state s. The policy network is a deep learning model that determines the strategy by learning the probability distribution of input states and output actions.

[0095] During the initialization phase, all values ​​in the Q table are usually set to 0 or random values, and the weights of the policy network are randomly initialized to start the training process. The purpose of this phase is to prepare the model to start exploring different optimal replenishment strategies.

[0096] Furthermore, in each preset cycle, the current inventory status and the preset simulated replenishment strategy are input into the second sub-analysis model to obtain the replenishment quantity. Specifically, in this embodiment, in each decision cycle, the second sub-analysis model selects a replenishment quantity (action) according to the current inventory status and the learned strategy. This action will affect the inventory level and will also be affected by market demand.

[0097] Furthermore, simulated inventory information, market supply information, and cost information are obtained based on the preset learning environment and replenishment quantity. Specifically, in this embodiment, the learning environment and replenishment quantity constructed in the above steps are input into the second sub-analysis model. After the second sub-analysis model executes the action, the environment will provide feedback, including simulated inventory information, market supply information, and cost information. This information constitutes the next state of the second sub-analysis model, as well as the immediate reward associated with this state transition. The reward can be positive (for example, because replenishment meets market demand in a timely manner) or negative (for example, due to inventory backlogs caused by excessive replenishment).

[0098] The above steps simulate real-world replenishment decisions, where the second sub-analysis model will make the best decision based on the current information and learn from the results.

[0099] Further, the policy parameters are updated according to the simulated inventory information, market supply information, and cost information. Specifically, in this embodiment, according to the feedback information in the previous step, the Q value or policy network is updated so that the second sub-analysis model gradually learns the best replenishment strategy to be adopted in each state. According to the feedback (next state and reward) obtained from the environment, the model updates its Q value or policy network. Among them, in Q learning, this is usually done through the Bellman equation, which calculates the expected future return and compares it with the current Q value to update the value in the Q table.

[0100] For policy networks, updates typically involve a gradient descent algorithm that adjusts network weights by calculating a loss function (e.g., policy gradient loss) so that the action probability distribution output by the policy network is closer to the optimal policy.

[0101] This step allows the model to gradually learn the optimal replenishment decision to take in each state, that is, how much should be replenished to maximize the cumulative reward given the inventory level and market demand.

[0102] Further, it is determined whether the policy parameters reach the preset stability threshold; if so, the second sub-analysis model is determined as the analysis model; if not, the step of initializing the preset policy parameters is re-executed. Specifically, in this embodiment, after multiple iterations of training, the model will gradually stabilize and be able to output a replenishment strategy close to the optimal. It can be understood that in each iteration, the model will undergo a process of environmental interaction and policy update. As the number of iterations increases, the Q value or policy network of the model will gradually stabilize, which means that the model has learned the optimal replenishment strategy under various conditions. By determining whether the policy parameters reach the preset stability threshold, it is determined whether the second sub-analysis model can be regarded as the final analysis model. If so, it proves that the model can output a replenishment strategy close to the optimal, and the model at this time is the analysis model. If not, it proves that there are still unstable factors in the model and it needs to be repeatedly retrained. At this time, the step of initializing the preset policy parameters is re-executed. These strategies can help enterprises minimize inventory costs and avoid the risk of over-replenishment or out-of-stock while meeting market demand.

[0103] Thus, the entire training process mentioned above involves the model learning how to make the best replenishment decision under different inventory conditions through interaction with the environment. Through continuous learning and updating, the model can gradually improve its decision-making quality, and finally when the optimal replenishment strategy is reached or close to the optimal one, the corresponding model is determined as the analysis model.

[0104] Optionally, after inputting the supply information, the first inventory information, and the own production information and the second inventory information into a preset analysis model to obtain the best replenishment strategy in step S12, the method further includes: The analysis model is evaluated to determine whether the effectiveness of the optimal replenishment strategy in the real scenario reaches a preset effective threshold. Specifically, in this embodiment, after the optimal replenishment strategy is obtained through the analysis model, the analysis model will also be finally evaluated to ensure the effectiveness of the simulated replenishment strategy in the real scenario.

[0105] If the effectiveness of the optimal replenishment strategy in the actual scenario reaches a preset effectiveness threshold, the step of sending the optimal replenishment strategy to the target supply end is entered.

[0106] If the effectiveness of the optimal replenishment strategy in the real scene does not reach the preset effective threshold, the step of initializing the preset strategy parameters is re-executed. Specifically, in this embodiment, when the effectiveness of the simulated replenishment strategy in the real scene is evaluated and judged to be less than the preset effective threshold, it proves that the analysis model still has defects and needs to be repeatedly retrained. At this time, the step of initializing the preset strategy parameters is re-executed. These strategies can help enterprises minimize inventory costs and avoid the risk of over-replenishment or out-of-stock while meeting market demand.

[0107] In one embodiment, the historical inventory status can be input into a preset demand forecasting model to achieve the purpose of updating the simulated replenishment strategy. The historical inventory status can be the corresponding inventory status in any time interval in the past, for example, it can be in days, months, quarters, and years. For example, the current month is October, and the historical inventory status can be the inventory status in October of last year, the inventory status of the previous quarter, the inventory status of the previous month, or the inventory status seven days ago. The demand forecasting model will generate future demand based on the historical inventory status, for example, using a random process (such as Poisson distribution, normal distribution) to update the simulated replenishment strategy.

[0108] After updating the simulated replenishment strategy, the step of initializing the preset strategy parameters is re-executed. When the analysis model is evaluated and it is determined that the effectiveness of the simulated replenishment strategy in the real scenario reaches the preset effective threshold, the obtained second sub-analysis model is determined as the analysis model that executes the step of "inputting the supply information, the first inventory information, the own production information and the second inventory information into the preset analysis model to obtain the best replenishment strategy".

[0109] Based on the same inventive concept as the above embodiments, an embodiment of the present invention provides an electronic device, such as Figure 3 As shown, the device includes: a processor 310 and a memory 311 storing a computer program; wherein, Figure 3 The processor 310 shown in the figure is not used to indicate that the number of the processor 310 is one, but is only used to indicate the positional relationship of the processor 310 relative to other devices. In actual applications, the number of the processor 310 may be one or more; similarly, Figure 3 The memory 311 shown in the figure has the same meaning, that is, it is only used to refer to the position relationship of the memory 311 relative to other devices. In practical applications, the number of memories 311 can be one or more. When the processor 310 runs the computer program, the method applied to the above device is implemented.

[0110] The device may also include: at least one network interface 312. The various components in the device are coupled together via a bus system 313. It is understood that the bus system 313 is used to achieve connection and communication between these components. In addition to the data bus, the bus system 313 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Figure 3 Various buses are labeled as bus system 313.

[0111] The memory 311 may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory may be a disk memory or a tape memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAMbus random access memory (DRRAM, Direct Rambus Random Access Memory).The memory 311 described in the embodiments of the present invention is intended to include but is not limited to these and any other suitable types of memories.

[0112] The memory 311 in the embodiment of the present invention is used to store various types of data to support the operation of the device. Examples of these data include: any computer program used to operate on the device, such as an operating system and an application; contact data; phone book data; messages; pictures; videos, etc. Among them, the operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application program may include various applications, such as a media player (Media Player), a browser (Browser), etc., which are used to implement various application services. Here, the program that implements the method of the embodiment of the present invention may be included in the application program.

[0113] Based on the same inventive concept as the above-mentioned embodiment, this embodiment further provides a computer-readable storage medium, in which a computer program is stored. The computer-readable storage medium may be a ferromagnetic random access memory (FRAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); it may also be various devices including one or any combination of the above-mentioned memories, such as a mobile phone, a computer, a tablet device, a personal digital assistant, etc. When the computer program stored in the computer-readable storage medium is executed by the processor, the above-mentioned method is implemented. For the specific steps implemented when the computer program is executed by the processor, please refer to Figure 1 The description of the illustrated embodiment will not be repeated here.

[0114] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0115] In this document, the terms "comprises," "comprising," or any other variations thereof, are intended to cover a non-exclusive inclusion of elements other than those listed and may also include additional elements not expressly listed.

[0116] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A cargo management method, applied to a cargo warehousing management system, wherein the cargo warehousing management system comprises an enterprise end and a supply end, wherein the enterprise end and the supply end are in communication connection, and wherein: The method comprises: Obtaining correlations corresponding to a plurality of pre-selected suppliers, and determining a supply end corresponding to one of the pre-selected suppliers as a target supply end according to the correlations; In response to receiving the supply information and the first inventory information sent by the target supplier, inputting the supply information, the first inventory information, the own production information and the second inventory information into a preset analysis model to obtain an optimal replenishment strategy; The optimal replenishment strategy is sent to the target supplier, so that the target supplier generates a delivery order according to the optimal replenishment strategy.

2. The method according to claim 1, characterized in that The obtaining of the correlations corresponding to the plurality of pre-selected suppliers includes: Obtaining preset reference series and comparison series for each pre-selected supplier; The relevance of each of the pre-selected suppliers is determined respectively according to the reference number series and the comparison number series.

3. The method according to claim 2, characterized in that The step of obtaining a preset reference sequence and a comparison sequence of each pre-selected supplier includes: Establishing an analysis indicator system based on pre-selected analysis indicators; The reference number series and the comparison number series are determined according to the analysis indicator system.

4. The method according to claim 2, characterized in that: The determining the relevance of each of the pre-selected suppliers according to the reference number series and the comparison number series respectively includes: According to the reference number series and the comparison number series, respectively obtain the grey correlation degree corresponding to each of the pre-selected suppliers on each of the analysis indicators; The relevance degree of each of the pre-selected suppliers is determined respectively according to the grey relevance degree.

5. The method according to claim 4, characterized in that The step of determining a supplier corresponding to one of the pre-selected suppliers as a target supplier according to the correlation degree includes: Performing weighted summation of the grey correlation degree corresponding to each of the pre-selected suppliers on each of the analysis indicators to obtain the correlation degree of each of the pre-selected suppliers; The supply end corresponding to the pre-selected supplier with the highest correlation is determined as the target supply end.

6. The method according to claim 1, characterized in that Before inputting the supply information, the first inventory information, the own production information and the second inventory information into a preset analysis model to obtain the best replenishment strategy, the method includes: Using a preset decision framework, the historical supply information, the historical first inventory information, the historical production information of the self, and the historical second inventory information are combined to generate a decision model; Solving the decision model using a preset learning algorithm to obtain a first sub-analysis model; constructing a reinforcement learning environment for the first sub-analysis model to obtain a second sub-analysis model; The second sub-analysis model is trained to obtain the analysis model.

7. The method according to claim 6, characterized in that The step of training the second sub-analysis model to obtain the analysis model comprises: Initialize the preset strategy parameters; In each preset period, the current inventory status and the preset simulated replenishment strategy are input into the second sub-analysis model to obtain the replenishment quantity; Acquire simulated inventory information, market supply information, and cost information according to a preset learning environment and the replenishment quantity, and update the strategy parameters according to the simulated inventory information, market supply information, and cost information; Determining whether the strategy parameters reach a preset stability threshold; If yes, determining the second sub-analysis model as the analysis model; If not, the step of initializing the preset strategy parameters is executed again.

8. The method according to claim 7, characterized in that After inputting the supply information, the first inventory information, the own production information and the second inventory information into a preset analysis model to obtain an optimal replenishment strategy, the method further includes: Evaluating the analysis model to determine whether the effectiveness of the optimal replenishment strategy in a real scenario reaches a preset effectiveness threshold; If yes, then proceed to the step of sending the optimal replenishment strategy to the target supply end; If not, the step of initializing the preset strategy parameters is executed again.

9. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the cargo management method according to any one of claims 1 to 8 when executing the computer program.

10. A computer storage medium, characterized in that: The computer storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the cargo management method according to any one of claims 1 to 8 are implemented.

Images