Production resource management and control method and system based on data analysis

Abstract

The invention relates to the field of production resource management and control, in particular to a production resource management and control method and system based on data analysis, and the method comprises the steps: obtaining daily product demands in a historical period, constructing a historical demand sequence, and inputting the historical demand sequence into a preset prediction model to obtain a predicted demand sequence; and according to the historical demand sequence and the predicted demand sequence, calculating a standard regulation production amount, and according to the standard regulation production amount, producing a product. The inventory management cost can be reduced as much as possible under the condition of avoiding inventory shortage.

Description

Technical Field

[0001] The present invention relates to the field of production resource management and control, and in particular to a production resource management and control method and system based on data analysis. Background Art

[0002] When managing and controlling product inventory, the autoregressive integral moving average model is usually used to predict product demand, and the product production plan is adjusted according to the product demand forecast results to control product inventory. However, due to the influence of the market environment, the actual demand for the product is more uncertain than the predicted demand. When directly using the autoregressive integral moving average model forecast results to adjust the product production plan to control product inventory, if the actual demand is earlier than the predicted demand, it will lead to inventory shortages, causing delayed delivery or order cancellations; if the actual demand is later than the predicted demand, it will lead to increased inventory management costs, occupy financial resources, and be detrimental to the normal operation of the enterprise. Summary of the invention

[0003] In order to solve the problem of inconvenience in enterprise management caused by uncertainty in actual demand, the present invention provides a production resource management and control method and system based on data analysis.

[0004] In a first aspect, the present invention provides a production resource management and control method based on data analysis, which adopts the following technical solutions: The production resource control method based on data analysis includes the following steps: Obtain the daily product demand in the historical period to construct a historical demand sequence, and input the historical demand sequence into a preset forecasting model to obtain a forecast demand sequence; Calculate the production volume based on the historical demand sequence and the forecast demand sequence, and produce products based on the production volume adjusted according to the standard; Among them, the calculation method of standard control production volume is: Calculate the impact factor of the data point in the forecast demand sequence. The impact factor is positively correlated with the sum of the order cancellation loss and delayed delivery time in the historical period. A corresponding mapping function is obtained according to the inventory and maintenance cost in the historical period, and the maintenance cost increment of the data point is obtained according to the mapping function; The product of the influencing factor, the ratio of the maintenance cost increment and the data point is taken as the predicted production volume of the data point; the regulated production volume of the data point in the predicted demand sequence is calculated, and the regulated production volume is positively correlated with the predicted production volume; the product of the regulated production volume and the preset correlation coefficient is taken as the standard regulated production volume.

[0005] By correcting the data points in the forecast demand sequence to obtain the standard regulated production volume, the accuracy of the standard regulated production volume data is improved, which reduces the inventory maintenance cost while ensuring inventory, and improves the enterprise's production efficiency and product management efficiency.

[0006] Preferably, the expression for the influencing factor of a data point in the forecast demand sequence is: ; ; In the formula, is the influencing factor of the kth data point in the forecast demand sequence; k is the ordinal number of the data point in the forecast demand sequence; P is the total length of the data points in the historical demand sequence; is the ordinal number of the i-th inventory shortage in the historical demand sequence; is the total loss from order cancellation caused by the i-th inventory shortage; is the total time of delayed delivery caused by the i-th inventory shortage; i is the ordinal number of the inventory shortage; I is the total number of inventory shortages of the product within the time span; the norm function is used for linear normalization, It is the sum of the ordinal number of the kth data point in the predicted demand sequence and the total number of data points in the historical demand sequence.

[0007] The above formula can be used to calculate the impact factor, which improves the accuracy of the impact factor data and facilitates reflecting the impact of inventory shortages on data points in the forecast demand sequence.

[0008] Preferably, the expression of the maintenance cost increment is: ; In the formula, is the incremental maintenance cost of the inventory at the kth data point in the forecast demand sequence; S is the inventory on the current date; is the predicted value of the kth data point in the forecast demand sequence; () represents the mapping function between maintenance cost and inventory quantity.

[0009] The above formula can accurately reflect the relationship between maintenance cost and inventory increase, making it easier to calculate maintenance cost.

[0010] Preferably, the mapping function is obtained by fitting the mapping relationship between the maintenance cost and the inventory quantity through the least square method.

[0011] Preferably, the expression for regulating production volume is: ; In the formula, To predict the regulated production volume at the kth data point in the demand sequence; The predicted production volume for the kth data point in the forecast demand sequence; To predict the demand sequence The predicted production volume for each data point; To predict the demand sequence The predicted production volume for each data point; The step size for increasing the ordinal number of the data points in the forecast demand sequence; is a function that preserves positive values; is the linear normalized function line; To control the total step length.

[0012] By correcting the data points in the forecast demand sequence through the above formula, the accuracy of regulating production volume is improved, making it easier to regulate product production volume.

[0013] Preferably, the expression of standard regulation production volume is: ; In the formula, To predict the standard control production volume of the kth data point in the demand sequence; To predict the regulated production volume at the kth data point in the demand sequence; is the predicted value of the kth data point in the forecast demand sequence; The ordinal number of the data point in the forecast demand sequence; is the number of data points in the forecast demand sequence.

[0014] By correcting the regulated production volume to obtain the standard regulated production volume, the accuracy of the standard regulated production volume is improved, a theoretical basis is provided for regulating the production volume of the product, and it is convenient to control the production volume of the product.

[0015] In a second aspect, the present invention provides a production resource management and control system based on data analysis, which adopts the following technical solutions: The production resource management and control system based on data analysis includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the production resource management and control method based on data analysis is implemented.

[0016] The present invention has the following technical effects: The present invention obtains inventory shortage influencing factors, counts inventory maintenance costs under different inventory levels of products, obtains inventory maintenance cost increments under predicted demand at each data point in the predicted demand sequence, obtains predicted production volume at each data point according to the inventory maintenance cost increments, inventory shortage influencing factors, and predicted values ​​at each data point in the predicted demand sequence, and obtains standard regulated production volume based on the predicted production volume, which can reduce inventory management costs as much as possible while avoiding inventory shortages, and facilitates the management of production resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0018] Figure 1 It is a method flow chart of a production resource management and control method based on data analysis according to an embodiment of the present invention.

[0019] Figure 2 It is a structural block diagram of a production resource management and control system based on data analysis according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0021] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0022] The embodiment of the present invention discloses a production resource management and control method based on data analysis, referring to Figure 1 , including the following steps, as follows: S1. Obtain the daily product demand in the historical period to build a historical demand sequence.

[0023] The daily product demand of the product to be predicted in the recent period is obtained from the enterprise order storage module as the product historical demand sequence. The product demand of each day is the total order volume of the product on that day. For example, the total order volume of each day in the past 180 days is obtained to construct the historical demand sequence. Due to data loss or storage errors, the product historical demand sequence may have missing values. When there are missing values ​​in the product historical demand sequence, the missing values ​​in the product historical demand sequence can be supplemented by interpolation processing.

[0024] S2. Input the historical demand sequence into a preset forecasting model to obtain a forecasted demand sequence.

[0025] The forecasting model is an autoregressive integrated moving average model. The unit root test method is used to detect whether the historical demand sequence is stable. If the product historical demand sequence is non-stationary, differential processing is performed until the historical demand sequence is in a stable state. The differential order is the total number of differentials. The autocorrelation coefficient and partial autocorrelation coefficient of each data point in the product historical demand sequence are calculated to obtain the autocorrelation diagram and partial autocorrelation diagram of the product historical demand sequence. According to the autocorrelation diagram and partial autocorrelation diagram of the product historical demand sequence, the lag value corresponding to the significant peak in the partial autocorrelation diagram is used as the number of autoregressive terms, and the lag value corresponding to the significant peak in the autocorrelation diagram is used as the number of moving average terms. In this way, the differential order, number of autoregressive terms, and number of moving average terms of the autoregressive integrated moving average model are obtained. The forecast period p is set to 30 days, and the historical demand sequence is input into the autoregressive integrated moving average model to obtain the forecast demand sequence. The forecast demand sequence is the product demand for each day in a future forecast period.

[0026] S3. Calculate the impact factor of the data points in the forecast demand sequence. The impact factor is positively correlated with the sum of the order cancellation loss and the delayed delivery time in the historical period.

[0027] The expression for the impact factor of a data point in the forecast demand sequence is: ; ; In the formula, is the influencing factor of the kth data point in the forecast demand sequence; k is the ordinal number of the data point in the forecast demand sequence, for example, the ordinal number corresponding to the 5th data point is 5; P is the total length of the data points in the historical demand sequence, which can also be understood as the total number of data points; is the ordinal number of the i-th inventory shortage in the historical demand sequence. For example, if the first inventory shortage occurred on the 10th day in the historical demand sequence, then ; is the total loss from order cancellation caused by the i-th inventory shortage; is the total time of delayed delivery caused by the i-th inventory shortage, in days; i is the ordinal number of the inventory shortage; I is the total number of inventory shortages of the product within the time span; the norm function is used for linear normalization, It is the sum of the ordinal number of the kth data point in the predicted demand sequence and the total number of data points in the historical demand sequence.

[0028] in, It represents the loss caused by the i-th inventory shortage, including the monetary loss caused by order cancellation and the reputation loss caused by delayed delivery time. When the loss coefficient caused by the i-th inventory shortage is higher, the impact caused by the i-th inventory shortage is higher; It represents the impact of the i-th inventory shortage on the k-th data point of the forecast demand sequence. When the date of the i-th inventory shortage is closer to the date of the k-th sampling point of the forecast demand sequence, the i-th inventory shortage is more likely to be caused by poor management and control of recent production resources, and the impact ratio on the forecasted data point is higher; when the overall impact of all inventory shortages is higher and the impact ratio on the forecasted sampling point is higher, the inventory impact factor of the k-th data point of the forecast demand sequence is higher. The inventory impact factor represents the negative impact of inventory shortages on the forecasted product demand.

[0029] S4. Obtain a corresponding mapping function according to the inventory and maintenance cost in the historical period, and obtain the maintenance cost increment of the data point according to the mapping function.

[0030] The maintenance cost of inventory under different inventory levels is counted, and the mapping relationship between maintenance cost and inventory level is fitted by the least squares method to obtain the mapping function C(x), which means that the maintenance cost when the inventory level is x is C(x).

[0031] The expression of maintenance cost increment is: ; In the formula, is the incremental maintenance cost of the inventory at the kth data point in the forecast demand sequence; S is the inventory on the current date; is the kth data point in the forecast demand sequence.

[0032] Since the increase in inventory will incur additional storage and maintenance costs, and the predicted demand is greatly affected by the market environment, additional costs will be incurred when the predicted demand is higher than the actual demand. Therefore, when the incremental inventory maintenance cost is high, the amount of products produced according to the predicted demand can be appropriately reduced.

[0033] S5. The product of the influencing factor, the maintenance cost increment ratio and the data point is taken as the predicted production volume of the data point.

[0034] The expression for predicting production volume is: ; In the formula, The predicted production volume for the kth data point in the forecast demand sequence; To predict the inventory impact factor of the kth data point in the demand sequence; To predict the maintenance cost increment of the kth data point in the demand sequence; is the predicted value of the kth data point in the forecast demand sequence.

[0035] in, To predict the inventory control index of the kth data point in the demand sequence, if the inventory impact factor of a single data point in the demand sequence is high and the inventory maintenance cost increment is low, the inventory control index is high, and production should be carried out as much as possible according to the predicted demand of the data point to avoid shortages again; if the inventory impact factor of a single data point in the demand sequence is low and the inventory maintenance cost increment is high, the inventory control index is low, and the product quantity corresponding to the predicted demand should be reduced as much as possible to avoid excessive production leading to increased inventory maintenance costs.

[0036] S6. Calculate the regulated production volume of the data points in the forecast demand sequence. The regulated production volume is positively correlated with the forecast production volume.

[0037] The expression for regulating production volume is: ; In the formula, To predict the demand sequence The production volume of each data point; To predict the demand sequence The predicted production volume for each data point; To predict the demand sequence The predicted production volume for each data point; To predict the demand sequence The predicted production volume for each data point; The step size for increasing the ordinal number of the data points in the forecast demand sequence; is a function that preserves positive values; is the linear normalized function line; To control the total step length.

[0038] in, It indicates the growth trend of production volume predicted within the control date range at the kth data point in the forecast demand sequence; Indicates the proportional coefficient of increasing production volume. When the predicted production volume within the control date range of a data point is high and the predicted production volume growth trend is high, the possibility of consuming more inventory in the future is high, and the production volume produced according to the predicted demand on that date can be appropriately increased.

[0039] S7. The product of the regulated production volume and the preset correlation coefficient is used as the standard regulated production volume.

[0040] The expression of standard regulation production volume is: ; In the formula, To predict the standard control production volume of the kth data point in the demand sequence; To predict the regulated production volume at the kth data point in the demand sequence; is the predicted value of the kth data point in the forecast demand sequence; k is the ordinal number of the data point in the forecast demand sequence; p is the number of data points in the forecast demand sequence.

[0041] The predicted regulated production volume is standardized through the ratio of the predicted value to the regulated production volume to obtain the standard regulated production volume. The product production plan is adjusted according to the standard regulated production volume, and the product inventory is managed. Specifically, the corresponding products are produced according to the standard regulated production volume of each data point in the predicted demand sequence, thereby achieving production resource control that minimizes inventory management costs while avoiding inventory shortages as much as possible.

[0042] By regulating production volume through standards, companies can control the quality of each link in the procurement workflow, standardize business processes and the accurate storage of raw materials. At the same time, data from each link can be uploaded and stored in real time to provide data support for the company's operational analysis.

[0043] Combination Figure 2 As shown, an embodiment of the present invention also discloses a production resource management and control system based on data analysis, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a production resource management and control method based on data analysis according to the present invention is implemented.

[0044] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0045] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high bandwidth memory HBM (High Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0046] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0047] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A production resource control method based on data analysis, characterized in that: Includes steps: Obtain the daily product demand in the historical period to construct a historical demand sequence, and input the historical demand sequence into a preset forecasting model to obtain a forecast demand sequence; Calculate the production volume based on the historical demand sequence and the forecast demand sequence, and produce products based on the production volume adjusted according to the standard; Among them, the calculation method of standard control production volume is: Calculate the impact factor of the data point in the forecast demand sequence. The impact factor is positively correlated with the sum of the order cancellation loss and delayed delivery time in the historical period. A corresponding mapping function is obtained according to the inventory and maintenance cost in the historical period, and the maintenance cost increment of the data point is obtained according to the mapping function; The product of the influencing factor, the ratio of the maintenance cost increment and the data point is taken as the predicted production volume of the data point; the regulated production volume of the data point in the predicted demand sequence is calculated, and the regulated production volume is positively correlated with the predicted production volume; the product of the regulated production volume and the preset correlation coefficient is taken as the standard regulated production volume.

2. The production resource management and control method based on data analysis according to claim 1 is characterized in that: The expression for the impact factor of a data point in the forecast demand sequence is: ； ； In the formula, is the influencing factor of the kth data point in the forecast demand sequence; k is the ordinal number of the data point in the forecast demand sequence; P is the total length of the data points in the historical demand sequence; is the ordinal number of the i-th inventory shortage in the historical demand sequence; is the total loss from order cancellation caused by the i-th inventory shortage; is the total delivery delay time caused by the i-th inventory shortage; i is the inventory shortage ordinal number; I is the total number of inventory shortages of the product within the time span; the norm function is used for linear normalization, It is the sum of the ordinal number of the kth data point in the predicted demand sequence and the total number of data points in the historical demand sequence.

3. The production resource management and control method based on data analysis according to claim 1 is characterized in that: The expression of maintenance cost increment is: ； In the formula, To predict the maintenance cost increment of the inventory at the kth data point in the demand sequence; S is the inventory quantity on the current date; is the predicted value of the kth data point in the forecast demand sequence; () represents the mapping function between maintenance cost and inventory quantity.

4. The production resource management and control method based on data analysis according to claim 3 is characterized in that: The mapping function is obtained by fitting the mapping relationship between maintenance cost and inventory quantity through the least squares method.

5. The production resource management and control method based on data analysis according to claim 1 is characterized in that: The expression for regulating production volume is: ； In the formula, To predict the regulated production volume at the kth data point in the demand sequence; is the predicted production volume for the kth data point in the forecast demand sequence; To predict the demand sequence The predicted production volume for each data point; To predict the demand sequence The predicted production volume for each data point; The step size for increasing the ordinal number of the data points in the forecast demand sequence; is a function that preserves positive values; is the linear normalized function line; To control the total step length.

6. The production resource management and control method based on data analysis according to claim 1, characterized in that: The expression of standard regulation production volume is: ； In the formula, To predict the standard control production volume of the kth data point in the demand sequence; To predict the regulated production volume at the kth data point in the demand sequence; is the predicted value of the kth data point in the forecast demand sequence; The ordinal number of the data point in the forecast demand sequence; is the number of data points in the forecast demand sequence.

7. The production resource management and control method based on data analysis according to claim 1 is characterized in that: The prediction model is an autoregressive integrated moving average model.

8. The production resource management and control system based on data analysis is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the production resource management and control method based on data analysis according to any one of claims 1 to 7 is implemented.

Images