Digital-based supply chain management method and system

Abstract

The application relates to the technical field of data processing, and particularly discloses a digital-based supply chain management method and system, which comprises the following steps: obtaining historical order quantities of goods; clustering the historical order quantities by using an ordered sample clustering method to obtain multiple order quantity sections; obtaining a peak season central section and an off-season central section in the multiple order quantity sections, calculating a peak season merging coefficient and an off-season merging coefficient of any remaining order quantity section to perform merging, and obtaining a peak season section set, an off-season section set and a non-section set; obtaining sub-sections of each order quantity section in the peak season section set, the off-season section set and the non-section set with the highest correlation degree with the order quantity of a current time section, so as to judge the historical order quantity configuration supply quantity after a time section of a corresponding sub-section when a coefficient is greater than a preset threshold. The digital-based supply chain management method and system can reasonably divide peak seasons and off-seasons, and can avoid the problems of supply shortage or oversupply.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to a digital-based supply chain management method and system. BACKGROUND

[0002] Supply chain management is crucial for the supply-demand relationship. It helps enterprises to reasonably arrange production and inventory through accurate demand forecasting and response mechanisms, avoiding excess or shortage. At the same time, it can also strengthen inter-regional information sharing and resource coordination, effectively regulate supply and demand balance, and reduce risks. It ensures that products can be delivered on time, reduces inventory accumulation, and improves customer trust and loyalty. Supply chain management optimizes the supply-demand relationship, improves enterprise efficiency and inventory digestion capacity, and thus promotes the long-term development and market competitiveness of enterprises.

[0003] In the Chinese patent application file with the application publication number CN113743994A, a supplier's peak season prediction method, system, device and storage medium are disclosed, wherein the method comprises the following steps: obtaining historical data of the supplier; preprocessing and screening the historical data to obtain effective historical data; constructing a peak season prediction model according to a seasonal autoregressive difference moving average algorithm and the effective historical data; obtaining monthly historical data in the effective historical data, inputting the monthly historical data into the peak season prediction model, and obtaining predicted monthly data of the supplier in a future period of time; marking the peak season in the predicted monthly data to obtain the peak season of the supplier in the future period of time. However, the seasonal autoregressive difference moving average algorithm in the above-mentioned scheme has high complexity and many parameters, and it is difficult to adjust. Therefore, it is not convenient to calculate in the actual prediction process.

[0004] The ordered sample clustering method divides the ordered sample into several classes by finding the best segmentation point, so that the difference between the samples in each class is minimized, and the difference between the classes is maximized. Therefore, it can be used to cluster the historical data of the supplier to obtain the peak season section and the off-season section. Based on the supply quantity data of the peak season section and the off-season section, the current section supply quantity can be used as a reference.

[0005] However, the ordered sample clustering algorithm cannot effectively distinguish the transition section between the peak season section and the off-season section. This is because it will divide the transition section into multiple sections, thereby shortening the duration of the peak season section and the off-season section. Using this as a reference will cause problems such as supply shortage or over-supply, and will make the enterprise frequently adjust the supply quantity, leading to an increase in transportation costs and resource waste. SUMMARY

[0006] The application provides a digital-based supply chain management method and system, aiming to solve the technical problem that the transition section between the peak season and the off-season cannot be effectively distinguished in the prior art, and when the inventory is prepared by taking the peak season and the off-season as the reference, supply shortage or oversupply is caused.

[0007] The digital-based supply chain management method comprises the following steps:

[0008] Obtain the historical order quantity of the goods;

[0009] Cluster the historical order quantity by using the ordered sample clustering method to obtain a plurality of order quantity sections;

[0010] Obtain the peak season center section and the off-season center section in the plurality of order quantity sections, calculate the merging coefficient of the peak season and the merging coefficient of the off-season in any section of the remaining order quantity sections, and perform merging of any section with the peak season center section or the off-season center section to obtain a peak season section set and an off-season section set; the remaining order quantity sections that are not merged are a non-section set; wherein the merging coefficient is the product of the closeness and the stability of the order quantity section and the target center section; the stability is the difference between 1 and the ratio of the time length between the order quantity section and the nearest target center section on the left and right sides; the target center section is the peak season center section or the off-season center section;

[0011] Respectively obtain the sub-sections of each order quantity section in the peak season section set, the off-season section set and the non-section set with the highest correlation degree with the order quantity of the current period to judge the historical order quantity allocation supply quantity after the period of the corresponding sub-section when the judgment coefficient is greater than a preset threshold; wherein the judgment coefficient is the product of the ratio of the time length of the current period to the time length of the order quantity section where the corresponding sub-section is located and the closeness; the closeness represents the similarity of the order quantity of the current period and the order quantity in the sub-section.

[0012] In the above scheme, the order quantity sections are merged into the corresponding peak season center section and off-season center section according to the merging coefficient of the peak season and the merging coefficient of the off-season, thereby obtaining the peak season section set, the off-season section set and the flat season section set, so that the division of the peak season, the off-season and the flat season is more accurate and reasonable, and the sub-section of the peak season section set, the off-season section set or the flat season section set with the most similar order quantity of the current period can be obtained according to the correlation degree and the judgment coefficient to allocate the supply quantity of the historical order quantity after the period of the corresponding sub-section, so that reasonable inventory can be realized, and the problem that the transition section between the peak season and the off-season cannot be effectively distinguished in the prior art, and when the inventory is prepared by taking the peak season and the off-season as the reference, supply shortage or oversupply is caused, is avoided.

[0013] Preferably, the peak season center section is the order quantity section corresponding to the maximum value of the order quantity average of all order quantity sections, and the off-season center section is the order quantity section corresponding to the minimum value of the order quantity average of all order quantity sections.

[0014] In the above scheme, the peak season center section and the off-season center section are obtained according to the extreme value of the order quantity average of all order quantity sections, so that the division of the peak season center section and the off-season center section is more reasonable, and the subsequent merging of the remaining order quantity sections is facilitated.

[0015] Preferably, the merging coefficient of the peak season and the merging coefficient of the off-season of any section in the remaining order quantity sections are calculated to merge any section with the peak season center section or the off-season center section, comprising:

[0016] When the merging coefficient of the peak season of any section in the remaining order quantity sections is greater than a preset merging coefficient, the order quantity section is merged into the peak season center section;

[0017] When the merging coefficient of the off-season of any section in the remaining order quantity sections is greater than a preset merging coefficient, the order quantity section is merged into the off-season center section.

[0018] Preferably, the closeness n 1 between the order quantity section and the peak season center section k is:

[0019] ;

[0020] The closeness n 2 between the order quantity section b and the off-season center section k is:

[0021] ;

[0022] In the formula, mean ( n ) is the order quantity average of the order quantity section n , mean ( ) is the order quantity average of the peak season center section n closest to the order quantity section , mean ( b ) is the order quantity average of the off-season center section n closest to the order quantity section b , and the peak season center section and the off-season center section b are respectively located on the left and right sides of the order quantity section n .

[0023] In the above scheme, the degree of proximity is calculated by comparing the average order volume within the order volume segment with the average order volume within the peak season center segment and the average order volume within the off-season center segment, which can truly reflect the degree of proximity of the order volume segment with the peak season center segment and the off-season center segment, respectively.

[0024] Preferably, the correlation is the Pearson correlation coefficient obtained by calculating the order volume of the current time period and the order volume of each sub-segment of the order volume segment in the peak season segment, the off-season segment, and the non-segment set.

[0025] The above scheme uses the Pearson correlation coefficient to calculate the degree of correlation, which has the advantages of simple calculation, high efficiency and wide applicability.

[0026] Preferably, the sub-segments are obtained by moving a sliding window across the order volume segments of the peak season segment set, the off-season segment set, and the non-segment set; wherein the size of the sliding window is equal to the duration of the current time period.

[0027] Preferably, the degree of proximity c for:

[0028]

[0029] In the formula, mean ( Q i (This refers to the current time period) Q i The average number of orders. mean ( Q j ) is the sub-segment Q j The average order volume, and the sub-segment Q j Compared to the current time period Q i The durations are equal.

[0030] Preferably, configuring the supply volume based on the historical order volume after the time period corresponding to the sub-segment where the judgment coefficient is greater than a preset threshold includes:

[0031] Obtain the corresponding historical order volume for the sub-segment of the current time period in different regions, and use the corresponding historical order volume as the required supply volume for the corresponding region.

[0032] Sort the required supply quantities from largest to smallest, and then allocate the required supply quantities to the corresponding regions in that order.

[0033] According to the above scheme, the required supply quantity of the corresponding region is sequentially configured according to the size order of the required supply quantity of different regions, so that the supply is more reasonable, and the maximum economic benefit is achieved.

[0034] Preferably, the historical order quantity is a historical order quantity in units of days.

[0035] In the above scheme, the historical order quantity in units of days is obtained, so that the obtained data is more detailed, more data details can be retained, and the subsequent calculation is more accurate.

[0036] The application also provides a digital-based supply chain management system, comprising a memory and a processor, wherein the processor executes a computer program stored in the memory to realize any of the above-mentioned digital-based supply chain management methods.

[0037] The beneficial effects are:

[0038] The scheme of the application merges the order quantity segments into the corresponding peak season center segments and off-season center segments according to the peak season merging coefficient and the off-season merging coefficient, thereby obtaining a peak season segment set, an off-season segment set and a flat season segment set, so that the division of peak season, off-season and flat season is more accurate and reasonable, and the subsegment of the peak season segment set, the off-season segment set or the flat season segment set that is most similar to the order quantity of the current period can be obtained according to the correlation degree and the judgment coefficient, so that the supply quantity can be configured according to the historical order quantity of the period after the corresponding subsegment, so that reasonable inventory can be achieved, and the problem of supply shortage or oversupply caused by the fact that the transition segment between the peak season and the off-season cannot be effectively distinguished in the prior art and the inventory is prepared by taking the peak season and the off-season as the reference. BRIEF DESCRIPTION OF DRAWINGS

[0039] The above and other objects, features and advantages of the exemplary embodiments of the present application will be more apparent from the following detailed description taken in conjunction with the accompanying drawings, which show, by way of example, several embodiments of the present application. In the drawings, like reference numerals refer to like elements, and in which:

[0040] Figure 1 The step flow chart of the digital-based supply chain management method of the embodiment of the application;

[0041] Figure 2 The structural block diagram of the digital-based supply chain management system of the embodiment of the application. DETAILED DESCRIPTION

[0042] The embodiments of the application are described in detail below, and examples of the embodiments are shown in the accompanying drawings. The embodiments described below by reference to the drawings are exemplary and are intended to explain the application, and cannot be understood as a limitation of the application.

[0043] like Figure 1 As shown, according to a first aspect of the present invention, a digital-based supply chain management method is provided, comprising the following steps:

[0044] S1. Obtain the historical order volume of goods.

[0045] The goods in this invention refer to goods with a sales cycle, that is, goods with peak and off-seasons, such as seasonal fruits and vegetables, down jackets, automobiles, etc.

[0046] Historical order volume can be obtained by reviewing the company's historical order records. This historical order volume is displayed on a daily basis, meaning the number of orders placed each day. This provides more granular data, retaining more details and leading to more accurate subsequent calculations.

[0047] The historical order volume in this invention refers to orders placed over a relatively long period, such as at least two years. Calculations, analyses, and predictions are made based on at least two years of historical order volume. Due to the large and detailed amount of data, the prediction results are more accurate, avoiding errors caused by external environmental or human factors.

[0048] S2. Use ordered sample clustering to cluster historical order volumes to obtain multiple order volume segments.

[0049] It should be noted that ordered sample clustering is an existing technology, requiring samples to be arranged in a specific order, and this order cannot be disrupted during classification; that is, samples of the same category must be adjacent to each other. The samples mentioned above refer to historical order quantities that contain a time sequence, for example... X 1, X 2, X 3, … , X n ,in X n Indicates the first n The historical order volume of the day.

[0050] The basic idea of ​​ordered sample clustering can be summarized as follows: by finding the optimal split point, ordered samples are divided into several classes, minimizing the differences within each class and maximizing the differences between classes. Specifically, this method first treats all samples as a single large class, then gradually increases the number of classes, selecting the optimal split point each time a class is added based on a loss function. In this way, as the number of classes increases, the intra-class differences gradually decrease, while the inter-class differences gradually increase, ultimately yielding an optimal classification result.

[0051] The ordered sample clustering method mainly includes the following core steps:

[0052] 1、Definition of the diameter of the class: the diameter of the class is an index to measure the difference within the class, and the commonly used diameter is expressed by the sum of the squared deviations within the class;

[0053] 2、Obtaining the loss function: the loss function is used to measure the goodness of classification, and the smaller the value is, the more reasonable the classification is. The commonly used loss function is the sum of the squared deviations within each class;

[0054] 3、Finding the optimal classification: taking the minimum value of the loss function as the target, finding the optimal segmentation point, and obtaining the optimal classification.

[0055] Therefore, a plurality of order quantity segments can be obtained by the ordered sample clustering method, and each order quantity segment includes a plurality of historical order quantities in time sequence.

[0056] However, when the historical order quantities are clustered by the ordered sample clustering method, the historical order quantities are segmented into a plurality of order quantity segments. In the transition period between the peak season and the off-season, due to too much and too fine segmentation, the period that should belong to the peak season or the off-season is segmented out, thereby shortening the length of the peak season and the off-season. When the supply quantity is configured by taking the length of the peak season and the off-season as a reference, the problem of supply shortage or over-supply may occur, and the enterprise may frequently adjust the supply quantity, resulting in an increase in transportation cost and waste of resources. Therefore, in order to avoid the above-mentioned situation, the period that should belong to the peak season or the off-season in the transition period needs to be merged into the corresponding peak season or off-season.

[0057] S3、Obtaining the peak season center segment and the off-season center segment in the plurality of order quantity segments, calculating the merging coefficient of the peak season and the merging coefficient of the off-season in any segment of the remaining order quantity segments, to merge any segment with the peak season center segment or the off-season center segment, obtaining the peak season segment set and the off-season segment set. The remaining order quantity segments that are not merged are the non-segment set.

[0058] Among them, the non-segment set is the flat season segment set, and the flat season segment set is a set that neither belongs to the peak season segment set nor belongs to the off-season segment set.

[0059] Among them, the peak season center segment is the order quantity segment corresponding to the maximum value of the order quantity average in all order quantity segments, and the off-season center segment is the order quantity segment corresponding to the minimum value of the order quantity average in all order quantity segments.

[0060] This is because the historical order quantity is at least two years of historical order quantity, and some goods may have multiple peak seasons or off-seasons in a year, the order quantity segment belonging to the peak season will have a higher order quantity, and there will be a maximum point of the order quantity corresponding to the mean value of the order quantity, and the order quantity segment is taken as the peak season center period. Similarly, the order quantity segment belonging to the off-season will have a lower order quantity, and there will be a minimum point of the order quantity corresponding to the mean value of the order quantity, and the order quantity segment is taken as the off-season center period. And because the maximum value and the minimum value have multiple, the peak season center segment and the off-season center segment correspond to multiple.

[0061] The above-mentioned calculation of the merging coefficient of the peak season and the merging coefficient of the off-season in any of the remaining order quantity segments is to merge any of the segments with the peak season center segment or the off-season center segment, comprising:

[0062] When the merging coefficient of the peak season of any of the remaining order quantity segments is greater than the preset merging coefficient, the order quantity segment is merged into the peak season center segment;

[0063] When the merging coefficient of the off-season of any of the remaining order quantity segments is greater than the preset merging coefficient, the order quantity segment is merged into the off-season center segment.

[0064] Wherein, the value range of the preset merging coefficient is 0.6 to 0.8, preferably 0.7, of course, the size of the preset merging coefficient can be adjusted according to the need.

[0065] The present application introduces the merging coefficient, respectively merges the corresponding order quantity segment into the corresponding peak season center segment and the corresponding off-season center segment, obtains multiple peak season segments with the peak season center segment as the center and multiple off-season segments with the off-season center segment as the center, multiple peak season segments constitute a peak season segment set, and multiple off-season segments constitute an off-season segment set.

[0066] The merging coefficient is the product of the closeness and stability of the order quantity segment and the target center segment. Since the target center segment is the peak season center segment or the off-season center segment, the merging coefficient of the peak season is the product of the closeness and stability of the order quantity segment and the peak season center segment. The merging coefficient of the off-season is the product of the closeness and stability of the order quantity segment and the off-season center segment.

[0067] The specific calculation process of the merging coefficient of the peak season and the merging coefficient of the off-season is as follows:

[0068] First, the closeness of the order quantity segment and the peak season center segment and the closeness of the order quantity segment and the off-season center segment are obtained respectively.

[0069] Those skilled in the art will understand that the closer an order volume segment is to the peak season's central area, the closer its order volume is to that of the peak season's central area. Conversely, the closer an order volume segment is to the off-season's central area, the closer its order volume is to that of the off-season's central area. Therefore, the degree of proximity between an order volume segment and the peak season's central area can be calculated using the average order volume within that segment and the average order volume within the peak season's central area.

[0070] Specifically, order volume segment n and peak season central area proximity k 1 is:

[0071] ;

[0072] Order volume range n and the central area during the off-season b proximity k 2 is:

[0073] ;

[0074] In the formula, mean ( n () represents the order volume segment n The average order volume mean ( (This refers to the order volume segment) n The recent peak season in the central area The average order volume mean ( b (This refers to the order volume segment) n The recent off-season in the central area b The average order volume, and the peak season in the central area and the central area during the off-season b Located in the order volume segment n The left and right sides.

[0075] In some alternative embodiments, order volume segment n and peak season central area proximity k 1 is: ;

[0076] Order volume range n and the central area during the off-season b proximity k 2 is: ;

[0077] In the formula, t ( ,b ) is the length of time between the order volume segment and the peak center segment b , and the peak center segment t and the off-peak center segment are the nearest peak center segment and off-peak center segment, respectively, to the left and right of the order volume segment ,n . n ) is the length of time between the order volume segment t and the peak center segment b, n , and the peak center segment n and the off-peak center segment b are the nearest peak center segment and off-peak center segment, respectively, to the left and right of the order volume segment . b n

[0078] Second, the stability of the order volume segment is obtained.

[0079] The stability is the difference between 1 and the ratio of the length of time between the order volume segment and the nearest target center segment to the left and right of the order volume segment. That is, the stability is the difference between 1 and the ratio of the length of time between the order volume segment and the nearest peak center segment and off-peak center segment to the left and right of the order volume segment.

[0080] Specifically, the stability of the order volume segment n is w n :

[0081] ;

[0082] wherein t ( n ) is the length of time of the order volume segment n , t ( ,b ) is the length of time between the peak center segment and the off-peak center segment b , and the peak center segment and the off-peak center segment b are the nearest peak center segment and off-peak center segment, respectively, to the left and right of the order volume segment n .

[0083] ​​The closer the time length ratio between the order quantity section and the nearest peak season central section and off-season central section on the left and right sides thereof is to 1, the more stable the order quantity in the order quantity section is, and thus the order quantity section neither belongs to the peak season central section nor the off-season central section. Therefore, the difference between 1 and the time length ratio between the order quantity section and the nearest peak season central section and off-season central section on the left and right sides thereof is used as the stability degree.

[0084] Finally, the merging coefficient of the peak season and the merging coefficient of the off-season are obtained. Specifically, the merging coefficient of the peak season is:

[0085] order quantity section n the merging coefficient of the peak season is:

[0086] ;

[0087] order quantity section n the merging coefficient of the off-season is:

[0088] ;

[0089] In the formula, k 1 is the closeness of the order quantity section n and the peak season central section , k 2 is the closeness of the order quantity section n and the off-season central section b , w n the stability degree of the order quantity section n .

[0090] According to the merging coefficient of the peak season and the merging coefficient of the off-season of the order quantity section, the order quantity section is merged into the corresponding peak season central section and off-season central section, so that the division of the peak season and the off-season is more accurate and reasonable, and the problem of supply shortage or oversupply caused by the shortening of the time length of the peak season and the off-season when the historical order quantity is divided by using the ordered sample clustering is avoided.

[0091] S4, respectively acquiring the sub-sections of each order quantity section in the peak season section set, off-season section set and non-section set with the highest order quantity related degree of the current period, to judge the historical order quantity configuration supply quantity after the period in which the corresponding sub-section with a coefficient greater than a preset threshold value is located.

[0092] The preset threshold value ranges from 0.6 to 0.8, preferably 0.7, and the size of the preset threshold value can be adjusted as needed.

[0093] Through steps S1 to S3, although multiple complete peak season segments, off-season segments and flat season segments are obtained, in the actual goods sales process, the order quantity of the current period and the order quantity in the above periods cannot be completely consistent, and it is also uncertain which period the current period is in, i.e., which period of the peak season segment, the off-season segment or the flat season segment. Therefore, it is necessary to obtain one sub-segment in the peak season segment set, one sub-segment in the off-season segment set and one sub-segment in the flat season segment set which have the highest correlation degree with the order quantity of the current period, i.e., to obtain three sub-segments which only represent the trend most similar to the change trend of the order quantity of the current period. Then, the sub-segment closest to the order quantity of the current period is determined according to the judgment coefficient.

[0094] The specific process is as follows:

[0095] S41, respectively obtain three sub-segments with the highest correlation degree with the order quantity of the current period. The three sub-segments include one sub-segment in the peak season segment set, one sub-segment in the off-season segment set and one sub-segment in the flat season segment set.

[0096] The current period refers to a period of time before today, and the length of the current period can be 5 days, 10 days, 15 days, etc., which can be selected as needed.

[0097] The above sub-segments are obtained by moving the sliding window in each order quantity segment in the peak season segment set, the off-season segment set and the non-segment set, respectively, wherein the size of the sliding window is equal to the length of the current period.

[0098] The correlation degree is the Pearson correlation coefficient obtained by calculating the order quantity of the current period and the order quantity of the sub-segment of each order quantity segment in the peak season segment set, the off-season segment set and the non-segment set (i.e., the flat season segment set), respectively.

[0099] The Pearson correlation coefficient is used to measure the correlation between two variables, and its value is between-1 and 1. When the value is 1, it means that the two variables are completely positively correlated, when the value is-1, it means that the two variables are completely negatively correlated, and when the value is 0, it means that the two variables have no linear correlation. The Pearson correlation coefficient is used to calculate the correlation degree, which has the advantages of simple calculation, high efficiency and wide application range.

[0100] Specifically, the Pearson correlation coefficient r The calculation formula of the Pearson correlation coefficient is as follows:

[0101]

[0102] In the formula, x iany order volume of the sub-segments of each order volume segment in the set of peak season segments, the set of off-season segments and the non-segmented set, y i any order volume of the current time period; the average order volume of the sub-segments of each order volume segment in the set of peak season segments, the set of off-season segments and the non-segmented set; the average order volume of the current time period; n the length of the current time period.

[0103] Through the above calculation formula, a plurality of Pearson correlation coefficients corresponding to the set of peak season segments r 1, a plurality of Pearson correlation coefficients corresponding to the set of off-season segments r 2, and a plurality of Pearson correlation coefficients corresponding to the set of flat season segments r 3. The maximum value, i.e. the value closest to 1, of r 1, r 2, r 3 respectively, is obtained r 1max , r 2max , r 3max . Then r 1max the corresponding sub-segment is the sub-segment of the set of peak season segments with the highest correlation degree with the order volume of the current time period, r 2max the corresponding sub-segment is the sub-segment of the set of off-season segments with the highest correlation degree with the order volume of the current time period, r 3max the corresponding sub-segment is the sub-segment of the set of flat season segments with the highest correlation degree with the order volume of the current time period.

[0104] The three sub-segments obtained at this time only represent the trend of change closest to the order volume of the current time period, and do not represent the actual order volume, i.e. the order volume in the sub-segment and the order volume of the current time period may have a large difference, so it is necessary to determine the sub-segment closest to the order volume of the current time period.

[0105] Of course, other methods can also be used to calculate the correlation degree, such as Spearman correlation coefficient, Kendall correlation coefficient, etc.

[0106] S42, configuring the supply quantity with the historical order quantity after the time period where the corresponding sub-segment with a judgment coefficient greater than a preset threshold value is located.

[0107] The corresponding sub-segment obtained in this step is the sub-segment closest to the current time period, which can be considered to be similar to the order volume of the current time period in the next period of time, so the supply quantity can be configured with reference to the historical order quantity after the time period where the sub-segment is located.

[0108] Wherein, the judging coefficient is the product of the ratio of the time length of the current time period and the time length of the order amount section where the corresponding sub-section locates and the closeness. The closeness represents the similarity of the order amount of the current time period and the order amount in the sub-section.

[0109] The calculation process of the judging coefficient is as follows:

[0110] Firstly, the closeness is obtained.

[0111] The closeness of the order amount of the current time period and the order amount in the sub-section c is:

[0112]

[0113] In the formula, mean Q i is the order amount average of the current time period, mean Q j is the order amount average of the sub-section, Q j and the time length of the current time period Q i is equal.

[0114] In this step, by comparing the similarity of the order amount average of the current time period and the order amount average of the sub-section, the closeness of the order amount in the current order amount section and the order amount of the sub-section can be reflected.

[0115] In some alternative embodiments, the closeness can also be represented by the normalized value of the difference of the sum of the order amount of the current time period and the order amount of the sub-section. Wherein, the sum can also be the median or the mode.

[0116] Secondly, the ratio of the time length of the current time period and the time length of the order amount section where the corresponding sub-section locates is obtained. The ratio d is:

[0117] In the formula, t i is the time length of the current time period, t j is the time length of the order amount section where the corresponding sub-section locates. The longer the time length of the current time period is, the larger the ratio is. Therefore, the time length of the current time period is closer to the time length of the order amount section where the corresponding sub-section locates, which prevents the judging error caused by the too high judging coefficient due to the too short time. d

[0118] Finally, the judging coefficient is calculated.

[0119] ​​​​​​​​judgment coefficient p is: p = c x d ;

[0120] In the formula, c is the closeness of the order quantity of the current period and the order quantity in the sub-section, d is the ratio of the duration of the current period and the order quantity section duration of the corresponding sub-section.

[0121] In some embodiments, when the judgment coefficient is greater than a preset threshold, the historical order quantity after the period in which the corresponding sub-section is located is configured to the supply quantity, comprising:

[0122] Firstly, the corresponding historical order quantity after the period in which the corresponding sub-section of the current period of different regions is located is obtained respectively, and the corresponding historical order quantity is taken as the required supply quantity of the corresponding region.

[0123] Specifically, the historical order quantity of the same goods of different regions respectively executes the steps S1 to S4, and the sub-sections of the current period of different regions corresponding to the peak season section set, the off-season section set and each order quantity section in the non-section set of the region can be obtained. And the corresponding historical order quantity after the period in which the corresponding sub-section is located is taken as the required supply quantity of the corresponding region. Because there are regional differences in different regions, the corresponding sub-sections are different, and the required supply quantity is also different. Therefore, when the required supply quantity of different regions is configured, the priority of the configuration is also different.

[0124] Secondly, each required supply quantity is sorted from large to small, and the required supply quantity of the corresponding region is configured in turn according to the order of each required supply quantity.

[0125] Through this step, the region with larger required supply quantity can be supplied preferentially, and when the supply of the region is completed, other regions are supplied in turn, and finally the supply of all regions is completed. In this way, the required supply quantity of each region can be reasonably configured, the supply of the region with the largest required supply quantity is preferentially guaranteed, and the maximum economic benefit can be achieved.

[0126] In the digital-based supply chain management method of the application, according to the merging coefficient of the peak season and the merging coefficient of the off-season, the order quantity section is merged into the corresponding peak season center section and off-season center section, thereby obtaining the peak season section set, the off-season section set and the flat season section set, so that the division of the peak season, the off-season and the flat season is more accurate and reasonable. According to the correlation degree and the judgment coefficient, the sub-section of the peak season section set, the off-season section set or the flat season section set most similar to the order quantity of the current period can be obtained, so as to configure the supply quantity according to the historical order quantity after the period in which the corresponding sub-section is located, so that reasonable inventory can be realized, and the problem that the transition section between the peak season and the off-season cannot be effectively distinguished in the prior art is avoided. When the peak season and the off-season are taken as the reference for inventory, the problems of supply shortage or over-supply are caused.

[0127] As Figure 2 shown, according to the second aspect of the present application, there is also provided a digitized-based supply chain management system, the system comprising a memory and a processor, the processor executing a computer program stored in the memory to implement the digitized-based supply chain management method according to the first aspect of the present application.

[0128] The system also comprises other components well known to those skilled in the art such as a communication bus and a communication interface, the arrangement and function of which are known in the art and thus will not be described here in detail.

[0129] In the present application, the aforementioned memory can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device. For example, the computer readable storage medium can be any suitable magnetic storage medium or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random-Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store the desired information and that can be accessed by an application, module, or both. Any such computer storage media can be part of the device or accessible or connectable thereto. Any application or module described in the present application can be implemented by computer readable / executable instructions stored or otherwise held by such computer readable media.

[0130] In the description of the present application, the meaning of "a plurality of" is at least two, for example two, three or more, etc., unless otherwise explicitly specified.

[0131] Although the present application has been shown and described with respect to several embodiments thereof, it will be apparent that equivalents, substitutes and modifications will occur to others skilled in the art without departing from the spirit and technical scope of the present application. It is to be understood that various alternatives to the embodiments of the application described herein can be employed in practicing the application.

Claims

1. A digital-based supply chain management method, characterized in that, Includes the following steps: Obtain the historical order volume of the goods; The ordered sample clustering method was used to cluster historical order volumes, resulting in multiple order volume segments; The system obtains peak season and off-season center segments from multiple order volume segments. It then calculates the peak season merging coefficient and off-season merging coefficient for any segment within the remaining order volume segments. This allows for merging any segment with either the peak season or off-season center segment, resulting in a peak season segment set and an off-season segment set. Unmerged remaining order volume segments are designated as non-segment sets. The merging coefficient is the product of the proximity and stability between the order volume segment and the target center segment. Stability is defined as 1 divided by the ratio of the duration between the order volume segment and its nearest target center segments on either side. The target center segment is either the peak season center segment or the off-season center segment. The system retrieves the sub-segments of each order volume segment from the peak season segment set, off-season segment set, and non-segment set that have the highest correlation with the order volume of the current time period. The system then configures the supply volume based on the historical order volume of the corresponding sub-segment after the time period when the judgment coefficient is greater than a preset threshold. The judgment coefficient is the product of the ratio of the current time period duration to the duration of the order volume segment in which the corresponding sub-segment is located and the degree of similarity. The degree of similarity represents the similarity between the order volume of the current time period and the order volume within the sub-segment.

2. The digital-based supply chain management method according to claim 1, characterized in that, The peak season center segment is the order volume segment corresponding to the maximum value of the average order volume among all order volume segments, and the off-season center segment is the order volume segment corresponding to the minimum value of the average order volume among all order volume segments.

3. The digital-based supply chain management method according to claim 1, characterized in that, The calculation of the peak season consolidation coefficient and off-season consolidation coefficient for any segment within the remaining order volume segment, in order to consolidate any segment with either the peak season center segment or the off-season center segment, includes: When the peak season merging coefficient of any segment in the remaining order volume segment is greater than the preset merging coefficient, the order volume segment is merged into the peak season center segment. When the merging coefficient of the off-season in any segment of the remaining order volume is greater than the preset merging coefficient, the order volume segment is merged into the off-season central segment.

4. The digital-based supply chain management method according to claim 1, characterized in that, Order volume range n and peak season central area proximity k 1 is: ； Order volume range n and the central area during the off-season b proximity k 2 is: ； In the formula, mean ( n () represents the order volume segment n The average order volume mean ( (This refers to the order volume segment) n The recent peak season in the central area The average order volume mean ( b (This refers to the order volume segment) n The recent off-season in the central area b The average order volume, and the peak season in the central area and the central area during the off-season b Located in the order volume segment n The left and right sides.

5. The digital-based supply chain management method according to claim 1, characterized in that, The correlation is the Pearson correlation coefficient obtained by calculating the order volume of the current time period and the order volume of each sub-segment of the order volume segment in the peak season segment, the off-season segment, and the non-segment set.

6. The digital-based supply chain management method according to claim 1, characterized in that, The sub-segments are obtained by moving a sliding window across the order volume segments in the peak season segment set, the off-season segment set, and the non-segment set, respectively; wherein the size of the sliding window is equal to the duration of the current time period.

7. The digital-based supply chain management method according to claim 1, characterized in that, The degree of proximity c for: In the formula, mean ( Q i (This refers to the current time period) Q i The average number of orders. mean ( Q j ) is the sub-segment Q j The average order volume, and the sub-segment Q j Compared to the current time period Q i The durations are equal.

8. The digital-based supply chain management method according to claim 1, characterized in that, The configuration of supply volume based on historical order volume after the time period corresponding to the sub-segment where the judgment coefficient is greater than a preset threshold includes: Obtain the corresponding historical order volume for the sub-segment of the current time period in different regions, and use the corresponding historical order volume as the required supply volume for the corresponding region. Sort the required supply quantities from largest to smallest, and then allocate the required supply quantities to the corresponding regions in that order.

9. The digital-based supply chain management method according to claim 1, characterized in that, The historical order volume refers to the historical order volume in days.

10. A digital-based supply chain management system, comprising a memory and a processor, characterized in that, The processor executes the computer program stored in the memory to implement the digital-based supply chain management method as described in any one of claims 1 to 9.

Images