Intelligent replenishment recommendation method for store, electronic equipment and computer readable storage medium

Abstract

The invention discloses a store intelligent replenishment recommendation method, electronic equipment and a computer readable storage medium, and the method comprises the steps: collecting the stock and monthly sales of store commodities, and collecting the commodity information of online hot selling commodities, the commodity information comprising a popularity score; based on the inventory amount and the monthly sales amount, calculating to obtain an inventory maintainable day number; when the inventory maintainable days are smaller than a preset threshold value, a first replenishment amount is obtained through calculation based on the predicted sales volume, the current inventory and the safety inventory in the replenishment period, the safety inventory is calculated through a formula I, and when the store commodities are online red hot selling commodities, the first replenishment amount is calculated through a formula II based on the popularity score and the monthly sales volume; adjusting the first replenishment amount according to a preset proportion to generate a second replenishment amount; and generating a replenishment order based on the first replenishment amount and / or the second replenishment amount. The problem that an existing store replenishment decision-making method is low in efficiency is solved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a store intelligent replenishment recommendation method, an electronic device and a computer-readable storage medium. Background Art

[0002] In the retail industry, store inventory management is crucial for operational efficiency and cost control. Currently, many stores rely mainly on manual experience for replenishment decisions. There are many problems with manual replenishment methods. For example, it is difficult for staff to accurately determine the replenishment quantity based on the inventory level and sales trend of the goods, which can easily lead to inventory backlogs or out-of-stock phenomena. Inventory backlogs will occupy a lot of funds and increase warehousing costs, while out-of-stock situations will affect sales performance and reduce customer satisfaction. In addition, manual analysis of large amounts of inventory and sales data is time-consuming, labor-intensive, and inefficient. With the intensification of competition in the retail industry and the expansion of store scale, there is an urgent need for a new algorithm to optimize replenishment decisions.

[0003] At the same time, with the development of social media and online marketing, popular products sold by Internet celebrities have become a hot spot for sales, but it is difficult for stores to quickly identify and replenish such products in a timely manner. Therefore, there is an urgent need for an automatic replenishment algorithm that can comprehensively consider store inventory, sales conditions, and popular products sold by Internet celebrities. Summary of the invention

[0004] In order to overcome the defects of the prior art, a store intelligent replenishment recommendation method, an electronic device and a computer-readable storage medium are provided to solve the problem of low efficiency of the existing store replenishment decision-making method.

[0005] To achieve the above purpose, a store intelligent replenishment recommendation method is provided, comprising the following steps:

[0006] Collect the inventory and monthly sales of store products, as well as the product information of popular products sold by Internet celebrities, including popularity ratings;

[0007] Calculate the number of days the inventory can last based on the inventory volume and monthly sales;

[0008] When the number of days that inventory can be maintained is less than the preset threshold, the first replenishment quantity is calculated based on the expected sales volume, current inventory, and safety stock within the replenishment cycle. The safety stock is calculated using Formula 1, which is:

[0009] SS=W1×I+W2×J+W3×K+W4×N+W5×O,

[0010] Wherein, SS is safety stock, I is the impact value of sales stability level, J is the impact value of supply reliability level, K is the impact value of product shelf life level, N is the impact value of market demand volatility level, O is the impact value of storage cost level, W1 is the sales stability weight, W2 is the supply reliability weight, W3 is the product shelf life weight, W4 is the market demand volatility weight, W5 is the storage cost weight. When the store product is a popular online product, based on the popularity score and monthly sales, the first replenishment quantity is adjusted according to the preset ratio to generate the second replenishment quantity;

[0011] A replenishment order is generated based on the first replenishment quantity and / or the second replenishment quantity.

[0012] Furthermore, the inventory quantity and monthly sales volume of the store’s merchandise are collected through the store’s inventory management system and sales record system.

[0013] Furthermore, the first replenishment quantity is calculated by formula 2, and the formula 2 is:

[0014] First replenishment quantity = (estimated sales within the replenishment cycle - current inventory) + safety stock.

[0015] Furthermore, the number of days the inventory can be maintained is calculated based on the inventory and monthly sales volume by using Formula 3, and the Formula 3 is:

[0016] Number of days inventory can last = current inventory quantity / average daily sales.

[0017] The present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer program is used to control the processor to operate so as to execute a store intelligent replenishment recommendation method.

[0018] The present invention provides a computer-readable storage medium, comprising a memory and a processor, wherein the memory stores a computer program, and the computer program is used to control the processor to operate so as to execute a store intelligent replenishment recommendation method.

[0019] The beneficial effect of the present invention is that the store intelligent replenishment recommendation method of the present invention improves inventory management efficiency, reduces manual intervention, saves labor costs, and can respond to inventory changes more promptly and optimize inventory structure.

[0020] The store intelligent replenishment recommendation method of the present invention reduces inventory costs, and accurate replenishment can reduce inventory backlogs, storage costs and commodity losses.

[0021] The intelligent store replenishment recommendation method of the present invention improves sales performance, avoids out-of-stock situations, ensures the continuous supply of goods, improves customer satisfaction, and thus promotes sales growth. Timely replenishment of popular online products attracts customers, increases sales, and improves customer satisfaction.

[0022] The store intelligent replenishment recommendation method of the present invention can quickly respond to market hot spots, optimize product structure, and enhance the competitiveness of stores in the market. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0024] Figure 1 The figure is a schematic diagram of the steps of the store intelligent replenishment recommendation method according to an embodiment of the present invention.

[0025] Figure 2 FIG. 4 is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant inventions, rather than to limit the inventions. It should also be noted that, for ease of description, only the parts related to the invention are shown in the accompanying drawings.

[0027] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0028] Reference Figure 1 As shown in the figure, the present invention provides a store intelligent replenishment recommendation method, comprising the following steps:

[0029] S1. Collect the inventory and monthly sales of store products, as well as the product information of popular products sold by Internet celebrities, including popularity ratings.

[0030] The inventory and monthly sales of store products are collected through the store's inventory management system and sales record system. Specifically, the current inventory quantity of each type of store product and the daily sales data of each type of product in the past month are obtained in real time.

[0031] At the same time, by connecting to the Internet celebrity product monitoring data source (such as online hot lists, industry reports, social media data, etc.), we can obtain information on current popular Internet celebrity hot-selling products, including product names, features, popularity ratings, etc.

[0032] S2. Calculate the number of days the inventory can last based on the inventory level and monthly sales.

[0033] Calculate the average daily sales of each type of merchandise in the store over the past month. Based on the average daily sales and current inventory quantity, calculate the number of days that the inventory of each product can last.

[0034] Specifically, the number of days the inventory can be maintained is calculated based on the inventory and monthly sales volume using Formula 3, which is:

[0035] Number of days inventory can last = current inventory quantity / average daily sales.

[0036] In this embodiment, a replenishment threshold is set, and when the number of days the inventory can be maintained is lower than the threshold, a replenishment reminder is triggered.

[0037] S3. When the number of days that the inventory can be maintained is less than the preset threshold, the first replenishment quantity is calculated based on the expected sales volume, current inventory and safety stock within the replenishment cycle, where the safety stock is calculated using Formula 1, which is:

[0038] SS=W1×I+W2×J+W3×K+W4×N+W5×O,

[0039] Wherein, SS is the safety stock, I is the impact value of the sales stability level, J is the impact value of the supply reliability level, K is the impact value of the product shelf life level, N is the impact value of the market demand volatility level, O is the impact value of the storage cost level, W1 is the sales stability weight, W2 is the supply reliability weight, W3 is the product shelf life weight, W4 is the market demand volatility weight, W5 is the storage cost weight. When the store product is a popular online product, based on the popularity score and monthly sales, the first replenishment quantity is adjusted according to the preset ratio to generate the second replenishment quantity.

[0040] The first replenishment quantity is calculated by formula 2, which is:

[0041] First replenishment quantity = (estimated sales within the replenishment cycle - current inventory) + safety stock.

[0042] For popular products sold by internet celebrities, determine whether to recommend restocking and the amount of restocking based on their popularity ratings, the store’s past sales of such products, and inventory levels.

[0043] For example, if a popular online product has a high popularity score, and the store has good sales in the past but low inventory, replenishment will be recommended first and the replenishment quantity will be increased appropriately. The first replenishment quantity is increased by a preset ratio (10% to 20%) to generate the second replenishment quantity, that is, the second replenishment quantity = the first replenishment quantity × (1 + preset ratio).

[0044] If a popular online product has a high popularity score, but the store has poor past sales or has a large inventory, replenishment is not recommended and the replenishment quantity is appropriately reduced. The first replenishment quantity is reduced by a preset ratio (10% to 20%) to generate the second replenishment quantity, that is, the second replenishment quantity = the first replenishment quantity × (1-preset ratio).

[0045] For the store items that need to be restocked, calculate the first restocking quantity according to Formula 2. The formula for the first restocking quantity is: Restocking quantity = (Sales volume during the estimated restocking period - Current inventory) + Safety stock. Among them, the sales volume during the estimated restocking period = Average daily sales volume × Restocking period (one month, calculated as 30 days), and the safety stock is set according to factors such as the sales stability of the item.

[0046] The calculation method of the safety stock is as follows:

[0047] Let the weight of sales stability be W1, the weight of supply reliability be W2, the weight of the product shelf life be W3, the weight of market demand volatility be W4, and the weight of storage cost be W5, and W1 + W2 + W3 + W4 + W5 = 1.

[0048] For sales stability, if the sales standard deviation S of the item within the past three months is in the range of 0 - 10 pieces, the sales stability level is L1, and the corresponding impact degree is I1; if it is in the range of 10 - 20 pieces, it is L2, and the corresponding impact degree is I2; and so on.

[0049] The supply reliability is classified according to the on-time delivery rate P of the supplier. For example, if P ≥ 95% is R1, the impact degree is J1; if 90 ≤ P < 95% is R2, the impact degree is J2, etc.

[0050] The product shelf life T is measured by the remaining shelf life days. If T ≥ 180 days is G1, the impact degree is K1; if 90 ≤ T < 180 is G2, the impact degree is K2, etc.

[0051] For market demand volatility, refer to the market research data and the industry seasonal index M. When M is in the range of 0 - 0.2, it is V1, and the impact degree is N1; when 0.2 - 0.4, it is V2, and the impact degree is N2, etc.

[0052] The storage cost C is calculated by the average daily storage cost per unit item. If C ≤ 0.1 yuan is H1, the impact degree is O1; if 0.1 < C ≤ 0.2 is H2, the impact degree is O2, etc.

[0053] Then the safety stock SS = W1 × I + W2 × J + W3 × K + W4 × N + W5 × O, where I, J, K, N, and O select the corresponding impact degree values according to the levels of the above respective factors.

[0054] Determining the safety stock through this method of comprehensive consideration of multiple factors can more accurately adapt to the characteristics of different items and changes in the market environment, ensure the scientificity and rationality of the store's restocking decisions, and effectively balance the out-of-stock risk and inventory cost.

[0055] S4. Generate a restocking order based on the first restocking quantity and / or the second restocking quantity.

[0056] A replenishment order is generated based on the first replenishment quantity, including information such as product name, replenishment quantity, and estimated arrival time (determined according to the supplier's delivery cycle).

[0057] Based on the second replenishment quantity, the popular online products to be replenished will be added to the replenishment order, including information such as product name, replenishment quantity (determined based on the above analysis), estimated arrival time (determined based on the supplier's delivery cycle), etc., to generate a complete replenishment order.

[0058] The store intelligent replenishment recommendation method of the present invention can automatically collect and analyze store inventory and sales data without manual calculation, thereby improving the timeliness and accuracy of replenishment decisions.

[0059] The store intelligent replenishment recommendation method of the present invention, through seamless connection with the store inventory management system and sales record system, automatically obtains the real-time inventory quantity of various commodities and the sales details data in the past month at preset time intervals (such as 0:00 am every day), ensuring the integrity and timeliness of the data. For example, the system will accurately record the key information such as the commodity ID, sales time, sales quantity, etc. of each sales transaction, as well as the real-time inventory quantity update of the corresponding commodity.

[0060] Before data analysis, the store intelligent replenishment recommendation method of the present invention strictly screens and verifies the collected massive data, accurately identifies and corrects abnormal situations such as negative inventory quantity (which may be caused by system failure or data entry error), abnormal high or low values ​​in sales data (such as extreme sales data during promotion activities, which need to be identified according to promotion strategies), etc., to ensure reliable data quality. At the same time, the data format and coding standards are unified, such as unifying all date formats into "YYYY-MM-DD", and the product names are standardized according to the predefined classification system, laying a solid foundation for subsequent analysis.

[0061] The intelligent store replenishment recommendation method of the present invention calculates key indicators based on a predetermined formula model, accurately counts the sales days and total sales volume in the past month for each type of commodity, and uses the formula "average daily sales volume = total sales volume / sales days" to obtain accurate average daily sales volume data; based on the real-time inventory quantity and the average daily sales volume, the formula "number of days the inventory can be maintained = current inventory quantity / average daily sales volume" is used to accurately calculate the number of days the inventory can be maintained; comprehensively considers historical sales data fluctuations, market trend forecasts (using industry big data analysis and machine learning models to predict market demand change trends) and the impact of recent special events (such as seasonal demand peaks, preparations for large-scale promotional activities, etc.), uses complex data analysis algorithms (such as moving average method, exponential smoothing method, etc.) to deeply analyze the data, explore potential rules and trends, and provide a scientific basis for replenishment decisions.

[0062] The store intelligent replenishment recommendation method of the present invention calculates personalized replenishment quantities according to the sales characteristics and inventory conditions of different commodities, thereby effectively avoiding inventory backlogs or out-of-stock problems.

[0063] For fast-moving consumer goods (such as food and beverages, daily necessities, etc.), given their relatively stable demand and high requirements for freshness, the analysis focuses on recent sales data (such as the past week). If the average daily sales volume shows a stable growth trend, the weighted average method is used when predicting sales within the replenishment cycle, giving higher weight to recent sales data (such as the sales weights of the past three days are 0.5, 0.3, and 0.2 respectively), and the replenishment quantity is calculated based on the current inventory level and safety stock (the safety stock is determined by comprehensively considering factors such as the supplier's delivery period, the shelf life of the product, and market demand fluctuations. For example, if the supplier's delivery period is 5 days, 1.5 times the average daily sales volume is used as the safety stock).

[0064] For non-rigidly needed and rapidly updated products such as fashion apparel and electronic products, in addition to historical sales data, we deeply integrate multiple information such as market trends, new product launch plans, seasonal factors, and competitive product dynamics. For example, in the early stages of the popular styles of the season or new products, we estimate the demand growth multiple (such as 2-3 times) based on market research, and determine the replenishment quantity in combination with inventory and safety stock.

[0065] For slow-selling styles, we will appropriately reduce or even suspend replenishment based on the degree of inventory backlog (e.g. if the inventory can last for more than 90 days) and the market recession trend, until the market demand turns around or the inventory drops to a reasonable level.

[0066] The store intelligent replenishment recommendation method of the present invention sets a dynamic replenishment threshold, and the dynamic replenishment threshold can be adjusted according to the actual operation of the store to adapt to changes in market demand at different stages.

[0067] Adjusting the replenishment threshold example:

[0068] For example, the target inventory turnover rate is set at 3 times per month. When the actual inventory turnover rate is lower than 2 times for two consecutive weeks, the inventory turnover is judged to be too slow, and the system automatically reduces the replenishment threshold appropriately (such as from 7 days to 5 days) to speed up inventory turnover. On the contrary, if the inventory turnover rate is higher than 4 times for a month and the out-of-stock rate is lower than 2%, it indicates that sales are booming and inventory control is good. The replenishment threshold can be appropriately increased (such as from 7 days to 9 days). The replenishment frequency can be reduced while ensuring sales continuity, thereby optimizing procurement costs and inventory holding costs.

[0069] At the same time, taking seasonal factors into consideration, before the peak sales season arrives, the replenishment threshold is increased in advance based on historical sales data and market forecasts (such as increasing the threshold by 2-3 days one month in advance) to ensure sufficient inventory during the peak season; after the peak season ends, the threshold is lowered in a timely manner based on actual sales conditions and inventory backlog conditions to accelerate inventory digestion and capital recovery.

[0070] In addition, for special promotions or market emergencies, store managers can manually fine-tune replenishment thresholds based on experience and real-time market feedback. The system will instantly optimize the replenishment strategy based on the adjusted thresholds to ensure a high degree of unity between operational flexibility and market adaptability.

[0071] The store intelligent replenishment recommendation method of the present invention automatically determines and recommends replenishment of intelligent Internet celebrity products based on popularity and store conditions, thereby seizing sales hotspots.

[0072] The store intelligent replenishment recommendation method of the present invention improves inventory management efficiency, reduces manual intervention, saves labor costs, and can respond to inventory changes more promptly and optimize inventory structure.

[0073] The store intelligent replenishment recommendation method of the present invention reduces inventory costs, and accurate replenishment can reduce inventory backlogs, storage costs and commodity losses.

[0074] The intelligent store replenishment recommendation method of the present invention improves sales performance, avoids out-of-stock situations, ensures the continuous supply of goods, improves customer satisfaction, and thus promotes sales growth. Timely replenishment of popular online products attracts customers, increases sales, and improves customer satisfaction.

[0075] The store intelligent replenishment recommendation method of the present invention can quickly respond to market hot spots, optimize product structure, and enhance the competitiveness of stores in the market.

[0076] In order to further illustrate the specific steps of the store intelligent replenishment recommendation method of the present invention, the following examples and comparison columns are cited for comparative explanation.

[0077] Example 1

[0078] Taking a store of a convenience store chain as an example, we first connect to the store’s inventory management system and sales record system to obtain real-time inventory data of various commodities and sales data for the past month.

[0079] Use the algorithm to calculate the average daily sales volume. For example, the total sales volume of beverage products in the past month is 1,200 bottles, and the average daily sales volume is 40 bottles. The current inventory is 200 bottles, and the inventory can be maintained for 5 days.

[0080] Set the replenishment threshold to 7 days. When the inventory can be maintained for less than 7 days, a replenishment reminder is triggered.

[0081] For beverage products, assuming that the safety stock is set at 100 bottles, the expected sales volume within the replenishment cycle is 40×30=1200 bottles, and the replenishment quantity = (1200-200)+100=1100 bottles.

[0082] For the internet-famous milk bars, the replenishment quantity was decided to be 80 bars based on their popularity and store sales (the replenishment quantity was appropriately increased considering their hot trends and past sales speed).

[0083] Generate a replenishment order with the information of online celebrity milk bars and beverage replenishment products, including product name, replenishment quantity, estimated arrival time (determined according to the supplier's delivery cycle, such as milk bars will arrive within 5 days from the supplier, and beverages will arrive within 4 days from the supplier), etc., and send it to the purchasing staff.

[0084] Experimental conditions:

[0085] Select stores of a certain size and with stable customer traffic for testing to ensure that the sales data is representative.

[0086] Establish good information communication channels with suppliers to ensure accurate supply cycle information.

[0087] The data source for monitoring Internet celebrity products is stable and the information is updated in a timely manner.

[0088] Expected results:

[0089] After implementing the algorithm, the store's inventory turnover rate increased and the out-of-stock rate decreased. It is expected that the inventory turnover rate will increase by 20% within three months and the out-of-stock rate will be reduced to less than 5%. The sales share of popular products sold by Internet celebrities will increase by 15%.

[0090] Comparative Example 1

[0091] Comparative Example 1 uses manual replenishment. In the same period of time, the inventory turnover rate increased by 5% per month on average when replenishing manually, the out-of-stock rate was 10% on average, and the sales share of popular online products increased slowly (about 5%). After implementing the algorithm, the inventory turnover rate increased significantly and the out-of-stock situation was significantly improved.

[0092] The design concept of the store intelligent replenishment recommendation method of the present invention is based on data analysis and prediction, with the goal of optimizing inventory management, to achieve automation and scientific replenishment decision-making. It integrates internal operation data and external market hot spot data to achieve intelligent and accurate replenishment decision-making.

[0093] The intelligent store replenishment recommendation method of the present invention is based on the principles of data analysis and prediction, and aims to realize intelligent decision-making for store replenishment by integrating multi-source data. For conventional commodities, historical sales data is used to predict future demand, and the replenishment quantity is determined based on the inventory level to ensure that the inventory can meet sales without causing backlogs. For popular online products, the principle is to monitor market dynamics in real time, capture information about products with high popularity on the Internet, and combine the historical sales performance of stores for such products and the current inventory status to determine the necessity and replenishment quantity.

[0094] Specifically, the average daily sales of various commodities (including regular and Internet celebrity commodities) are calculated by statistically analyzing the sales data of the past month, which serves as the basis for predicting future sales trends. The number of days the inventory can be maintained is then calculated based on the current inventory quantity, and compared with the preset replenishment threshold to trigger a replenishment reminder. For Internet celebrity commodities, their popularity score is an important reference factor. The higher the popularity and the greater the store's sales potential (quantitatively evaluated from dimensions such as customer repurchase rate, new product acceptance speed, word-of-mouth communication effect, and market demand growth slope), the more inclined it is to recommend replenishment and increase the replenishment quantity, so as to seize sales hotspots, meet customer potential needs, and avoid the risks of over-replenishment.

[0095] The data collection of the store intelligent replenishment recommendation method of the present invention is to collect the inventory quantity and sales data of goods from the store's internal system (inventory management system and sales record system) to ensure the accuracy and real-time nature of the data.

[0096] Collect information on popular online celebrity products from external online celebrity product monitoring data sources (online hot list API, social media monitoring tools, industry report databases, etc.), including product name, popularity score, related feature descriptions, etc.

[0097] The data analysis and processing model of the store intelligent replenishment recommendation method of the present invention is:

[0098] Average daily sales calculation model: For each category of goods (regular and internet celebrity goods), use summation and division operations to calculate the average daily sales in the past month. The formula is: average daily sales = total sales in the past month / number of days in the past month (30 days).

[0099] Inventory maintenance days calculation model: Use the current inventory quantity divided by the average daily sales to get the inventory maintenance days. The formula is: Inventory maintenance days = current inventory quantity / average daily sales.

[0100] Internet celebrity product popularity evaluation model: Based on the Internet celebrity product popularity data obtained from different data sources (such as online search popularity, social media discussion volume, number of likes, etc.), the popularity score is calculated by weighted summation or other appropriate statistical methods. For example, the weight of online search popularity is set to 0.4, the weight of social media discussion volume is set to 0.3, and the weight of likes is set to 0.3. The calculated popularity score = online search popularity × 0.4 + social media discussion volume × 0.3 + number of likes × 0.3 (the specific weights can be adjusted and optimized according to actual conditions).

[0101] Replenishment Quantity Calculation Model

[0102] Regular commodity replenishment quantity: calculated according to the formula replenishment quantity = (estimated sales volume within the replenishment cycle - current inventory) + safety stock. Expected sales volume within the replenishment cycle = average daily sales volume × replenishment cycle (30 days), and safety stock is determined through experience or data analysis based on factors such as commodity sales stability and supply cycle.

[0103] The following data analysis methods are used to determine the safety stock:

[0104] Historical out-of-stock data statistics method: Count the number of out-of-stock times and out-of-stock quantities of goods in a certain period of time in the past, and analyze the frequency and distribution of out-of-stock quantities. If the number of out-of-stock times is frequent and the out-of-stock quantity fluctuates greatly, increase the safety stock appropriately. For example, if a certain product has been out of stock 10 times in the past year, with an average out-of-stock quantity of 20 pieces, the safety stock can be increased by a certain proportion (such as 20%) on the original basis to cope with potential out-of-stock risks, enhance the reliability of inventory supply, ensure sales continuity, and improve customer satisfaction and store operation stability.

[0105] Internet celebrity product replenishment quantity: Based on the regular replenishment quantity calculation, adjustments are made according to the popularity score of the Internet celebrity product and the store's past sales. When the popularity score is above a certain threshold and past sales are good, the replenishment quantity is increased by a certain percentage (such as 20%-50%); if the popularity score is low or past sales are poor, the replenishment quantity is reduced or not replenished.

[0106] Replenishment decision model

[0107] The comparison between the number of days the inventory can be maintained and the replenishment threshold determines whether to replenish regular products. If the number of days the inventory can be maintained is lower than the replenishment threshold, the replenishment process is triggered and the replenishment quantity calculation model is used to calculate the replenishment quantity.

[0108] For online celebrity products, the results of the popularity evaluation model, past sales and current inventory levels are combined to comprehensively determine whether to replenish and the replenishment quantity. Online celebrity products that meet the replenishment conditions are integrated with regular replenishment products to generate the final replenishment order.

[0109] In the entire algorithm model, each model collaborates with each other, and data flows and processes between different models, ultimately realizing the function of automatically generating scientific and reasonable replenishment orders based on store inventory, sales conditions, and popular online products. At the same time, as the business develops and data accumulates, the parameters in the algorithm model (such as weights, thresholds, etc.) can be continuously optimized and adjusted to improve the accuracy and adaptability of the algorithm.

[0110] The store intelligent replenishment recommendation method of the present invention is based on feedback adjustment of data analysis:

[0111] Sales data deviation analysis: Regularly (such as monthly) compare actual sales data with sales predicted by the algorithm and calculate the deviation rate. If the predicted sales of a certain product is 100 pieces, and the actual sales are 120 pieces, the deviation rate is 20%. For product categories with large deviations, retrospectively analyze the weights of related influencing factors (such as promotional activities, seasonal factors, market trend changes, etc.). For example, it is found that the sales of a certain type of product increased significantly during a promotion, but the algorithm did not fully consider the promotion weight, so the weight of the promotion factor in the sales forecast model is appropriately increased (such as from 0.2 to 0.3) to optimize future forecast accuracy.

[0112] Inventory turnover rate monitoring: Continuously monitor inventory turnover rate indicators. If the overall inventory turnover rate in a certain period is lower than the industry average or the store target value (for example, the target inventory turnover rate is 3 times per month, but the actual turnover rate is only 2 times), analyze the inventory backlog and out-of-stock situation of the goods. For goods with serious backlogs, reduce their replenishment threshold (for example, from 7 days to 5 days), and at the same time reduce the safety stock factor in the replenishment quantity calculation (for example, from 1.5 to 1.2); for goods that are frequently out of stock, adjust the parameters in the opposite direction to improve the timeliness of replenishment and the rationality of replenishment quantity, dynamically adapt to the rhythm of market demand, and improve inventory operation efficiency.

[0113] The data of the performance test of the store intelligent replenishment recommendation method of the present invention includes the difference analysis between the prior art and the algorithm of the present invention under specific indicators:

[0114] Specific indicators include inventory turnover rate, out-of-stock rate, and sales share of popular online celebrity products. Data was collected for three months before and after the implementation of the algorithm in the test store. The results showed that compared with manual replenishment, the inventory turnover rate increased from 8% per month to 25% per month after the implementation of this algorithm, the out-of-stock rate decreased from 8% to less than 3%, and the sales share of popular online celebrity products increased from 5% to 15%, fully demonstrating the advantages of this algorithm in inventory management and sales promotion.

[0115] The present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer program is used to control the processor to operate so as to execute a store intelligent replenishment recommendation method.

[0116] Reference below Figure 2 , which shows a schematic structural diagram of an electronic device 600 suitable for implementing some embodiments of the present invention. Figure 2 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0117] like Figure 2As shown, the electronic device 600 may include a processing device 601 (processor, such as a central processing unit), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 (memory) into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0118] Typically, the following devices may be connected to the I / O interface 605: input devices 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 607 including, for example, a display, a speaker, a vibrator, etc.; storage devices 608 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 609. The communication devices 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Figure 2 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 2 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0119] The present invention provides a computer-readable storage medium, including a memory and a processor, wherein the memory stores a computer program, and the computer program is used to control the processor to operate to execute a method for intelligent store replenishment recommendation. The computer-readable storage medium may be included in the device / apparatus / system described in the above embodiment; or it may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present invention is implemented.

[0120] According to an embodiment of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0121] In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present invention, a computer-readable storage medium may include the ROM 602 and / or the RAM 603 described above and / or one or more memories other than the ROM 602 and the RAM 603.

[0122] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other.

Claims

1. A store intelligent replenishment recommendation method, characterized in that: The following steps are involved: Collect the inventory and monthly sales of store products, and collect product information of popular products sold by Internet celebrities, including popularity scores; Calculate the number of days the inventory can be maintained based on the inventory volume and monthly sales volume; When the number of days that the inventory can be maintained is less than a preset threshold, a first replenishment quantity is calculated based on the expected sales volume within the replenishment cycle, the current inventory, and the safety stock, wherein the safety stock is calculated using Formula 1, which is: SS=W1×I+W2×J+W3×K+W4×N+W5×O, Wherein, SS is safety stock, I is the impact value of sales stability level, J is the impact value of supply reliability level, K is the impact value of product shelf life level, N is the impact value of market demand volatility level, O is the impact value of storage cost level, W1 is the sales stability weight, W2 is the supply reliability weight, W3 is the product shelf life weight, W4 is the market demand volatility weight, W5 is the storage cost weight. When the store product is a popular online product, based on the popularity score and monthly sales, the first replenishment quantity is adjusted according to a preset ratio to generate the second replenishment quantity; A replenishment order is generated based on the first replenishment quantity and / or the second replenishment quantity.

2. The store intelligent replenishment recommendation method according to claim 1, characterized in that: The inventory and monthly sales of store merchandise are collected through the store’s inventory management system and sales record system.

3. The store intelligent replenishment recommendation method according to claim 1, characterized in that: The first replenishment quantity is calculated by formula 2, and the formula 2 is: First replenishment quantity = (estimated sales within the replenishment cycle - current inventory) + safety stock.

4. The store intelligent replenishment recommendation method according to claim 1, characterized in that: Based on the inventory and monthly sales, the number of days the inventory can be maintained is calculated using Formula 3, which is: Number of days inventory can be maintained = current inventory quantity / average daily sales.

5. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the computer program is used to control the processor to operate so as to execute the store intelligent replenishment recommendation method according to any one of claims 1 to 4.

6. A computer-readable storage medium, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the computer program is used to control the processor to operate so as to execute the store intelligent replenishment recommendation method according to any one of claims 1 to 4.

Images