Intelligent stock-up method and system based on precise adaptation of residual quantity and demand quantity

Abstract

The invention discloses an intelligent stock-up method and system based on precise adaptation of residual quantity and demand quantity, and belongs to the technical field of intelligent warehousing and supply chain management, and the method comprises the following steps: obtaining supplier data in real time, including inventory residual quantity, order residual quantity and supplier assessment grade data of each warehouse of a supplier; forming a multi-source and multi-dimensional data set; preprocessing the collected data to obtain a preprocessed data set; according to the collected data set, constructing a surplus-demand adaptive model; according to the actual demand quantity and the surplus-demand quantity adaptation model, stock quantity calculation is carried out on each supplier, and calculation results are fed back to the suppliers; and triggering an early warning mechanism for the non-standard suppliers. According to the invention, dynamic matching of the residual quantity and the demand quantity is realized, optimization of cargo distribution is realized, and the problems of supply and demand imbalance and inventory redundancy or shortage in a traditional distribution strategy are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent warehousing and supply chain management, and specifically to an intelligent stock replenishment method and system based on accurate matching of remaining quantity and demand. Background Art

[0002] Traditional stock replenishment methods mainly rely on stock replenishment strategies dominated by manual experience, which have problems such as low inventory turnover rate, high proportion of warehousing costs, sharp increase in logistics costs caused by emergency replenishment, and non-linear growth of labor management costs with scale. At the same time, problems such as supply-demand imbalance, inventory redundancy or shortage are likely to occur. Summary of the Invention

[0003] The technical task of the present invention is to address the above deficiencies by providing an intelligent stock replenishment method and system based on accurate matching of remaining quantity and demand, realizing dynamic matching of remaining quantity and demand, optimizing the allocation of goods, and solving the problems of supply-demand imbalance, inventory redundancy or shortage in traditional allocation strategies. Reducing the influence of human factors, lowering inventory holding costs, improving the response efficiency of the supply chain, and optimizing the allocation of resources across the entire link.

[0004] The technical solution adopted by the present invention to solve its technical problems is as follows:

[0005] An intelligent stock replenishment method based on accurate matching of remaining quantity and demand, the implementation of this method includes the following steps:

[0006] (1) Real-time obtain supplier data, including the inventory remaining quantity, order remaining quantity, and supplier assessment level data of each warehouse of the supplier, to form a multi-source and multi-dimensional data set;

[0007] (2) Preprocess the collected data to obtain a preprocessed data set;

[0008] (3) According to the collected data set, construct a remaining quantity - demand matching model applicable to the technical field of intelligent warehousing and supply chain management;

[0009] (4) According to the actual demand, calculate the stock replenishment quantity for each supplier based on the remaining quantity - demand matching model, and feedback the calculation result to the supplier;

[0010] (5) Trigger an early warning mechanism for suppliers that do not meet the standards.

[0011] Further, for the preprocessing, clean and normalize the obtained data to obtain a preprocessed data set.

[0012] Further, for the construction of the remaining quantity - demand matching model, the reference dimensions include the supplier's inventory remaining quantity, order remaining quantity, and supplier assessment level. The construction process is as follows:

[0013] First, define the model variables:

[0014] S i : The remaining inventory of supplier i,

[0015] O i : The remaining order quantity of supplier i,

[0016] G i : The evaluation grade of supplier i,

[0017] D: Total demand,

[0018] α: Safety inventory coefficient,

[0019] W i : The allocation weight of supplier i;

[0020] Conduct model calculations:

[0021] (3.1) Calculate the effective supply capacity C of the supplier i :

[0022] C i = max(S i - α × O i , 0);

[0023] The effective supply capacity C i refers to the net supply capacity after deducting the uncompleted orders to avoid over-allocation;

[0024] (3.2) Based on C i and G i calculate the allocation weight W i :

[0025]

[0026] That is, the weighted calculation of the evaluation grade and supply capacity;

[0027] (3.3) Calculate the actual allocation quantity Q according to the total demand D and the weight W i : i :

[0028] Q i = min(D × W i , S i ).

[0029] Furthermore, the remaining quantity - demand adaptation model includes the following features:

[0030] Dynamic penalty mechanism: The uncompleted order quantity O i is deducted by a factor of α to penalize the suppliers with delivery delays;

[0031] Double Constraint: Considering Physical Inventory Constraints S Simultaneously i and performance evaluation i ;

[0032] Flexible adjustment: The safety stock coefficient α is adjusted according to industry characteristics, and the value range is 1.0 to 1.5.

[0033] Furthermore, the assessment level G of the supplier i i The data is quantified through the supplier's historical on-time delivery rate, quality score and service response time, and standardized into a value between 0.6 and 1.0.

[0034] Furthermore, the early warning mechanism includes sending replenishment reminders to suppliers via SMS or email, and automatically generating inventory adjustment suggestions.

[0035] Furthermore, the inventory remaining quantity and order remaining quantity are obtained in real time through the storage system.

[0036] The present invention also claims protection for an intelligent stocking system based on accurate adaptation of remaining quantity and demand quantity, comprising:

[0037] The data collection and integration module is used to obtain supplier data in real time, including the inventory balance of each supplier's warehouse, the order balance, and the supplier's assessment level data, forming a multi-source and multi-dimensional data set;

[0038] A data preprocessing module is used to preprocess the collected data to obtain a preprocessed data set;

[0039] A surplus-demand adaptation model building module is used to build a surplus-demand adaptation model based on the collected data set;

[0040] The supply quantity allocation module is used to calculate the inventory quantity of each supplier according to the actual demand quantity and the surplus quantity-demand quantity adaptation model, and feed back the calculation results to the supplier;

[0041] The early warning module is used to trigger an early warning mechanism for suppliers that fail to meet the standards;

[0042] The system specifically realizes intelligent stocking through the above method.

[0043] The present invention also claims protection for an intelligent stocking device based on accurate adaptation of surplus quantity and demand quantity, comprising: at least one memory and at least one processor;

[0044] The at least one memory is used to store a machine-readable program;

[0045] The at least one processor is used to call the machine-readable program to implement the above method.

[0046] The present invention also claims protection for a computer-readable medium, on which computer instructions are stored, and when the computer instructions are executed by a processor, the above-mentioned method can be implemented.

[0047] Compared with the prior art, the intelligent stock preparation method and system based on precise adaptation of remaining quantity and demand of the present invention have the following beneficial effects:

[0048] By constructing a multi-dimensional data-driven remaining quantity-demand adaptation model, the present invention realizes the intelligence and dynamic optimization of the supply chain stock preparation link. The specific technical effects include the following points:

[0049] 1. Improvement of inventory turnover rate and reduction of costs.

[0050] By real-time collecting the remaining quantity of the supplier's inventory and the remaining quantity of orders, and dynamically calculating the effective supply capacity in combination with the safety inventory coefficient, the system can accurately eliminate the risk of over-allocation. For example, when the uncompleted order quantity of a certain supplier is relatively high, the remaining quantity-demand adaptation model automatically deducts its allocable inventory through the formula C i = max(S i -α×O i , 0) to avoid repeated occupation of resources.

[0051] 2. Dynamical weight allocation driven by supplier performance.

[0052] Introduce the supplier assessment level as the core parameter for allocating weights, and quantify the performance data (such as delivery on-time rate, quality score) into a standardized value of 0.6 - 1.0. The weight allocation calculation formula ensures that high-performance suppliers receive more order inclinations.

[0053] 3. Dual constraints to ensure the balance between supply and demand.

[0054] The model realizes the dual constraints of physical inventory S i = min(D×W i , S i ) through the formula. i And demand quantity D.

[0055] 4. Elastic parameters adapt to industry characteristics.

[0056] The safety factor α can be flexibly adjusted according to industry characteristics. Description of the Drawings

[0057] Figure 1 is a flowchart of the intelligent stock preparation method based on precise adaptation of remaining quantity and demand provided by an embodiment of the present invention. Detailed Embodiments

[0058] The present invention will be further described below in conjunction with specific embodiments.

[0059] An embodiment of the present invention provides an intelligent stock preparation method based on the precise adaptation of the remaining quantity and the demand. The implementation of this method includes the following steps:

[0060] 1. Obtain data such as the inventory remaining quantity, order remaining quantity, and supplier assessment level of each warehouse of the supplier in real time to form a multi-source and multi-dimensional data set;

[0061] 2. Preprocess the collected data to obtain a preprocessed data set;

[0062] 3. According to the collected data set, construct a remaining quantity - demand adaptation model applicable to the technical field of intelligent warehousing and supply chain management;

[0063] 4. Calculate the stock preparation quantity for each supplier according to the actual demand and based on the remaining quantity - demand adaptation model, and feedback the calculation result to the supplier;

[0064] 5. Trigger an early warning mechanism for suppliers that do not meet the standards. For suppliers who cannot prepare goods as required, this method can provide feedback via text message or email, send a replenishment reminder to the supplier, and automatically generate a stock preparation adjustment suggestion.

[0065] Among them, for data preprocessing, the obtained data is cleaned and normalized to obtain a preprocessed data set.

[0066] For the construction of the remaining quantity - demand adaptation model, the reference dimensions include the supplier's inventory remaining quantity, order remaining quantity, and supplier assessment level. The construction process is as follows:

[0067] (1) Model variable definition:

[0068] S i : The remaining inventory of supplier i,

[0069] O i : The order remaining quantity of supplier i,

[0070] G i : The assessment level of supplier i (0 - 1 standardization, G ∈ [0.6, 1.0]),

[0071] D: Total demand,

[0072] α: Safety stock coefficient,

[0073] W i : The allocation weight of supplier i;

[0074] (2) Model calculation, including:

[0075] a. Calculation of effective supply capacity: Calculate the supplier's effective supply capacity C i :

[0076] C i =max(S i -α×O i ,0);

[0077] Effective supply capacity C i Refers to the net supply capacity after deducting unfilled orders to avoid over-allocation;

[0078] b. Allocation weight calculation: based on C i and G i Calculate the allocation weight W i :

[0079]

[0080] That is, the weighted calculation of assessment level and supply capacity;

[0081] c. Calculation of actual allocation: based on total demand D and weight W i Calculate the actual distribution amount Q i :

[0082] Q i =min(D×W i ,S i ).

[0083] (3) The surplus-demand adaptation model has the following model characteristics:

[0084] Dynamic penalty mechanism: uncompleted order quantity O i Deduct a factor of α to penalize suppliers with delayed delivery;

[0085] Double Constraint: Considering Physical Inventory Constraints S Simultaneously i and performance evaluation i ;

[0086] Flexible adjustment: The safety stock coefficient α is adjusted according to industry characteristics, and the value range in this method is 1.0 to 1.5.

[0087] The assessment level G of the supplier i i The data is quantified through the supplier's historical on-time delivery rate, quality score and service response time, and standardized into a value between 0.6 and 1.0.

[0088] The early warning mechanism includes sending replenishment reminders to suppliers via SMS or email, and automatically generating inventory adjustment suggestions.

[0089] The remaining inventory and order quantity are obtained in real time through the storage system.

[0090] The following takes a large platform as an example and combines with the attached drawings to optimize the intelligent stock preparation process of its national suppliers by using the method of the present invention as follows:

[0091] 1. Data collection and integration:

[0092] The system obtains the remaining inventory S of each regional warehouse in the country in real time i , the number of unfilled orders O i and the supplier assessment level G i . For example, for supplier A, S A = 5000 tons, O A = 2000 tons, G A = 0.9.

[0093] 2. Data preprocessing:

[0094] Clean abnormal data (such as negative inventory values) and normalize all data to a unified dimension.

[0095] 3. Model parameter setting:

[0096] According to the industry characteristics, set the safety inventory coefficient α = 1.2.

[0097] 4. Effective supply capacity calculation:

[0098] The effective supply capacity of supplier A:

[0099] C A = max(5000 - 1.2×2000, 0) = 2600 (tons)

[0100] 5. Allocation weight calculation:

[0101] Assume the total demand D = 10000 tons, and ∑(G i ×C i ) of all suppliers is 15000, then the allocation weight of supplier A:

[0102]

[0103] 6. Actual stock preparation quantity calculation:

[0104] Q A = min(10000×0.156, 5000) = 1560 (tons)

[0105] 7. Feedback mechanism:

[0106] If supplier A cannot complete the allocated quantity due to insufficient inventory, the system automatically sends a text message or email to prompt the adjustment of the stock preparation plan.

[0107] An embodiment of the present invention further provides an intelligent stock preparation system based on the precise adaptation of the remaining quantity and the demand quantity. The system specifically realizes intelligent stock preparation through the intelligent stock preparation method based on the precise adaptation of the remaining quantity and the demand quantity described in the above embodiment.

[0108] The system includes:

[0109] A data collection and integration module, which is used to obtain supplier data in real time, including data such as the remaining inventory in each warehouse of the supplier, the remaining order quantity, and the supplier assessment level, and form a multi-source and multi-dimensional data set. The remaining inventory quantity and the remaining order quantity are obtained in real time through the storage system.

[0110] A data preprocessing module, which cleans and normalizes the obtained data to obtain a preprocessed data set.

[0111] A remaining quantity-demand quantity adaptation model construction module, which is used to construct a remaining quantity-demand quantity adaptation model according to the collected data set.

[0112] The reference dimensions include the remaining inventory of the supplier, the remaining order quantity, and the supplier assessment level. The construction process is as follows:

[0113] (1) Model variable definition:

[0114] S i : The remaining inventory of supplier i,

[0115] O i : The remaining order quantity of supplier i,

[0116] G i : The assessment level of supplier i (0-1 standardization, G∈[0.6,1.0]),

[0117] D: Total demand,

[0118] α: Safety stock coefficient,

[0119] W i : The allocation weight of supplier i;

[0120] (2) Model calculation, including:

[0121] a. Effective supply capacity calculation: Calculate the effective supply capacity C i :

[0122] C i =max(S i -α×O i ,0);

[0123] The effective supply capacity C i refers to the net supply capacity after deducting the uncompleted orders to avoid over-allocation;

[0124] b. Allocation weight calculation: Based on C i and G i calculate the allocation weight W i :

[0125]

[0126] That is, the weighted calculation of the assessment level and supply capacity;

[0127] c. Actual allocation quantity calculation: According to the total demand D and the weight W i calculate the actual allocation quantity Q i :

[0128] Q i = min(D × W i , S i ).

[0129] (3) The remaining quantity - demand adaptation model has the following model characteristics:

[0130] Dynamic penalty mechanism: The unfulfilled order quantity O i is deducted by a factor of α, punishing the suppliers with delivery delays;

[0131] Dual constraints: Consider both the physical inventory limit S i and the performance evaluation G i ;

[0132] Elastic adjustment: The safety inventory coefficient α is adjusted according to industry characteristics, and the value range in this method is from 1.0 to 1.5.

[0133] The assessment level G of the supplier i i is comprehensively quantified through the supplier's historical delivery on - time rate, quality score, and service response time, and standardized to a value within the range of 0.6 to 1.0.

[0134] The supply quantity allocation module is used to calculate the stock - preparation quantity for each supplier according to the actual demand and based on the remaining quantity - demand adaptation model, and feedback the calculation results to the suppliers;

[0135] The warning module is used to trigger a warning mechanism for non - compliant suppliers. The warning mechanism includes sending a replenishment reminder to the suppliers via text message or email and automatically generating a stock - preparation adjustment suggestion.

[0136] The process of the system realizing intelligent stock - preparation is as follows:

[0137] 1. Obtain data such as the remaining inventory quantity, remaining order quantity, and supplier assessment level in each warehouse of the suppliers, forming a multi - source and multi - dimensional data set;

[0138] 2. Preprocess the collected data to obtain a preprocessed data set;

[0139] 3. Based on the collected data set, construct a remaining quantity - demand adaptation model applicable to the field of intelligent warehousing and supply chain management technology;

[0140] 4. According to the actual demand, calculate the stock preparation quantity for each supplier according to the model, and feedback the calculation results to the suppliers;

[0141] 5. For suppliers who cannot prepare goods as required, the present invention can provide feedback by means of text messages or emails.

[0142] An embodiment of the present invention also provides an intelligent stock preparation device based on precise adaptation of remaining quantity and demand, including: at least one memory and at least one processor;

[0143] The at least one memory is used to store machine-readable programs;

[0144] The at least one processor is used to call the machine-readable program to implement the intelligent stock preparation method based on precise adaptation of remaining quantity and demand described in the above embodiment.

[0145] An embodiment of the present invention also provides a computer-readable medium, on which computer instructions are stored. When the computer instructions are executed by a processor, the processor executes the intelligent stock preparation method based on precise adaptation of remaining quantity and demand described in the above embodiment. Specifically, a system or device equipped with a storage medium can be provided. On this storage medium, software program codes for implementing the functions of any one of the above embodiments are stored, and the computer (or CPU or MPU) of the system or device is enabled to read and execute the program codes stored in the storage medium.

[0146] In this case, the program code read from the storage medium itself can implement the functions of any one of the above embodiments. Therefore, the program code and the storage medium storing the program code constitute a part of the present invention.

[0147] Embodiments of the storage medium for providing program codes include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Optionally, the program code can be downloaded from a server computer via a communication network.

[0148] In addition, it should be clear that not only can part or all of the actual operations be completed by executing the program code read by a computer, but also by the operating system operating on the computer and other components based on the instructions of the program code, thereby implementing the functions of any one of the above embodiments.

[0149] In addition, it can be understood that the program code read from the storage medium is written into the memory provided in the expansion board inserted into the computer or into the memory provided in the expansion unit connected to the computer. Subsequently, based on the instructions of the program code, the CPU and other components installed on the expansion board or the expansion unit execute part or all of the actual operations, thereby implementing the functions of any one of the above embodiments.

[0150] The present invention has been described in detail above with reference to the drawings and preferred embodiments. However, the present invention is not limited to these disclosed embodiments. Based on the above-mentioned multiple embodiments, those skilled in the art can know that more embodiments of the present invention can be obtained by combining the code review means in the above different embodiments, and these embodiments are also within the protection scope of the present invention.

Claims

1. An intelligent stock preparation method based on precise adaptation of remaining quantity and demand, characterized in that, The implementation of this method includes the following steps: (1) Obtain supplier data in real time, including the remaining inventory quantity, remaining order quantity, and supplier assessment grade data of each warehouse of the supplier, and form a multi-source and multi-dimensional data set; (2) Preprocess the collected data to obtain a preprocessed data set; (3) Construct a remaining quantity - demand adaptation model based on the collected data set; (4) Calculate the stocking quantity for each supplier according to the actual demand and the remaining quantity - demand adaptation model, and feedback the calculation results to the supplier; (5) Trigger an early warning mechanism for suppliers that do not meet the standards.

2. The intelligent stock preparation method based on the precise adaptation of the remaining quantity and the demand according to claim 1, wherein For the above-mentioned preprocessing, clean and normalize the obtained data to obtain a preprocessed data set.

3. The intelligent stock preparation method based on precise adaptation of remaining quantity and demand according to claim 1, wherein, For the construction of the remaining quantity - demand adaptation model, the reference dimensions include the remaining inventory quantity of the supplier, the remaining order quantity, and the supplier assessment grade. The construction process is as follows: First, define the model variables: S i : The remaining inventory of supplier i, O i : The remaining order quantity of Supplier i G i : The assessment level of supplier i D: Total demand, α: Safety inventory coefficient, W i : The allocation weight of supplier i; Model calculation: (3.1) Calculate the effective supply capacity C of the supplier i :[[]]END]] C i = max(S i - α × O i , 0); (3.2) Based on C i and G i Calculate the allocation weight W i : (3.3) Calculate the actual allocation quantity Q based on the total demand D and the weight W i Calculate the actual allocation quantity Q i : Q i = min(D × W i , S i ).

4. The intelligent stock preparation method based on precise adaptation of remaining quantity and demand according to claim 3, characterized in that, The remaining quantity - demand adaptation model includes the following characteristics: Dynamic penalty mechanism: the number of uncompleted orders O i Deduct by a factor of α to penalize the supplier with delayed delivery; Dual constraints: considering both the physical inventory limit S i and the performance evaluation G i ; Elastic adjustment: The safety inventory coefficient α is adjusted according to industry characteristics, and its value range is from 1.0 to 1.

5.

5. The intelligent stock preparation method based on precise adaptation of remaining quantity and demand according to claim 3, characterized in that The assessment level G of the supplier i i It is comprehensively quantified by the supplier's historical delivery on-time rate, quality score, and service response time, and standardized to a value within the range of 0.6 to 1.

0.

6. The intelligent stock preparation method based on precise adaptation of remaining quantity and demand according to claim 1, characterized in that The early warning mechanism includes sending a replenishment reminder to the supplier via text message or email, and automatically generating a stocking adjustment suggestion.

7. The intelligent stockpiling method based on the precise adaptation of the remaining quantity and the demand according to claim 1, wherein, The remaining inventory quantity and the remaining order quantity are obtained in real time through the storage system.

8. An intelligent stock preparation system based on precise adaptation of remaining quantity and demand, characterized in that, It includes: A data collection and integration module, which is used to obtain supplier data in real time, including the remaining inventory quantity, remaining order quantity, and supplier assessment grade data of each warehouse of the supplier, and form a multi-source and multi-dimensional data set; A data preprocessing module, which is used to preprocess the collected data to obtain a preprocessed data set; A remaining quantity - demand adaptation model construction module, which is used to construct a remaining quantity - demand adaptation model based on the collected data set; A supply quantity allocation module, which is used to calculate the stocking quantity for each supplier according to the actual demand and the remaining quantity - demand adaptation model, and feedback the calculation results to the supplier; An early warning module, which is used to trigger an early warning mechanism for suppliers that do not meet the standards; This system specifically realizes intelligent stocking through the method described in any one of claims 1 to 7.

9. An intelligent stockpiling device based on the precise adaptation of the remaining quantity and the demand, characterized in that, It includes: At least one memory and at least one processor; The at least one memory is used to store machine-readable programs; The at least one processor is used to call the machine-readable program to implement the method described in any one of claims 1 to 7.

10. A computer-readable medium, characterized in that, Computer instructions are stored on the computer-readable medium, and when the computer instructions are executed by the processor, the method described in any one of claims 1 to 7 can be realized.

Images