Price determination method and device, equipment and storage medium
By analyzing sales historical data and determining positive elastic ranges, the problem of traditional pricing models ignoring practical factors is solved, and more reasonable and accurate price determination is achieved, which enhances the company's market competitiveness.
Patent Information
- Application Number
- CN202410904633.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-08
- Publication Date
- 2024-11-01
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional economic pricing models ignore various practical factors when determining commodity prices, resulting in unreasonable prices and affecting the company's business decisions and market competitiveness.
By analyzing the sales historical data of the target product, determining the relationship between the actual selling price and the fitted predicted sales volume, determining the positive elastic range, and determining the target actual selling price that makes the composite index the largest as the recommended price of the product, Considering factors such as marketing, competitors, and life cycle.
It improves the rationality and accuracy of price determination, allowing enterprises to conduct market forecasts and competitive strategies more effectively and improve their competitiveness.
Smart Images

Figure CN118886935A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of commodity retail technology, and in particular to a price determination method, device, equipment and storage medium. Background Art
[0002] The price elasticity of demand can be used to measure the sensitivity of changes in the demand for a commodity to changes in the price of the commodity itself. The demand for a commodity is also called the sales volume of the commodity. When other conditions remain unchanged, sales volume changes with changes in price, but the direction of change is opposite. After the price rises or falls, the extent of the decrease or increase in sales volume will vary depending on the type of commodity. For elastic commodities, a slight change in price will cause a large change in sales volume; while for inelastic commodities, when the price changes greatly, only a relatively small change in sales volume will occur. In the actual operation of enterprises, more attention is paid to the changing relationship between price and total revenue. Total revenue is related to price and sales volume. When the price of elastic commodities falls, total revenue will increase, and when the price rises, total revenue will decrease. For inelastic commodities, total revenue will decrease when the price falls, and increase when the price rises. Based on the price elasticity of commodities, enterprises can make a series of business decisions such as commodity classification, pricing, and revenue optimization. Therefore, it is very important to determine the price of commodities.
[0003] At present, the process of determining the price of a commodity based on the traditional economic pricing model is as follows: assuming that the demand function of a commodity is Q, the cost function is C, profit = income - cost = P*QC, and finally find the price P that maximizes the profit.
[0004] However, the rational person hypothesis in economics denies various common real factors that affect the sales volume of goods, resulting in the price determined based on the above process being unreasonable. Summary of the invention
[0005] The present invention provides a price determination method, device, equipment and storage medium to solve the technical problem that the price determined by the related technology is not reasonable enough.
[0006] According to one aspect of the present invention, there is provided a price determination method, comprising:
[0007] Determining a first corresponding relationship between an actual selling price of the target product and a fitted predicted sales volume according to the sales history data of the target product;
[0008] According to the first corresponding relationship, a positive elasticity interval of the target product is determined; wherein the actual selling price within the positive elasticity interval is significantly negatively correlated with the corresponding fitted predicted sales volume;
[0009] According to the second corresponding relationship corresponding to the positive elasticity interval in the first corresponding relationship, the first target actual selling price that maximizes the first comprehensive index is determined, and the first target actual selling price is determined as the first recommended price of the target commodity; wherein, the first comprehensive index is a value determined based on the first sales volume and the first gross profit amount of the target commodity, the first sales volume is a value determined based on the actual selling price and the corresponding fitted predicted sales volume, and the first gross profit amount is a value determined based on the first sales volume and the cost.
[0010] According to another aspect of the present invention, there is provided a price determination device, comprising:
[0011] A first determination module, configured to determine a first corresponding relationship between an actual selling price of the target commodity and a fitted predicted sales volume according to sales history data of the target commodity;
[0012] A second determination module is used to determine the positive elasticity interval of the target product according to the first corresponding relationship; wherein the actual selling price within the positive elasticity interval is significantly negatively correlated with the corresponding fitted predicted sales volume;
[0013] The third determination module is used to determine the first target actual selling price that maximizes the first comprehensive index according to the second corresponding relationship corresponding to the positive elasticity interval in the first corresponding relationship, and determine the first target actual selling price as the first recommended price of the target product; wherein the first comprehensive index is a value determined according to the first sales volume and the first gross profit amount of the target product, the first sales volume is a value determined according to the actual selling price and the corresponding fitted predicted sales volume, and the first gross profit amount is a value determined according to the first sales volume and the cost.
[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0015] at least one processor; and
[0016] a memory communicatively connected to the at least one processor; wherein,
[0017] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the price determination method described in any embodiment of the present invention.
[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program is used to enable a processor to implement the price determination method described in any embodiment of the present invention when executed.
[0019] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the price determination method according to any one of the embodiments of the present invention is implemented.
[0020] The technical solution of the embodiment of the present invention includes: determining a first corresponding relationship between the actual selling price of the target commodity and the fitted predicted sales volume based on the sales history data of the target commodity; determining a positive elasticity interval of the target commodity based on the first corresponding relationship, wherein the actual selling price within the positive elasticity interval is significantly negatively correlated with the corresponding fitted predicted sales volume; determining a first target actual selling price that maximizes the first comprehensive index based on a second corresponding relationship corresponding to the positive elasticity interval in the first corresponding relationship, and determining the first target actual selling price as the first recommended price of the target commodity, wherein the first comprehensive index is a value determined based on the first sales volume and the first gross profit amount of the target commodity, the first sales volume is a value determined based on the actual selling price and the corresponding fitted predicted sales volume, and the first gross profit amount is a value determined based on the first sales volume and the cost. The price determination method provided in this embodiment has the following technical effects: the second corresponding relationship is the relationship corresponding to the positive elasticity interval in the first corresponding relationship determined according to the sales history data. Since the sales history data can reflect various realistic factors that affect the sales volume of goods, the determination process of the second corresponding relationship takes various realistic factors into consideration. At the same time, the actual selling price in the second corresponding relationship is significantly negatively correlated with the corresponding fitted predicted sales volume, which makes the determined first target actual selling price more reasonable, and the first target actual selling price can also maximize the first comprehensive index, thereby improving the competitiveness of the enterprise.
[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0023] Figure 1 is a flow chart of a price determination method provided by an embodiment of the present invention;
[0024] Figure 2 is a flow chart of another price determination method provided by an embodiment of the present invention;
[0025] Figure 3is a flow chart of another price determination method provided by an embodiment of the present invention;
[0026] Figure 4 is a flow chart of another price determination method provided by an embodiment of the present invention;
[0027] Figure 5 is a structural schematic diagram of a price determination device provided by an embodiment of the present invention;
[0028] Figure 6 It is a structural schematic diagram of an electronic device for implementing the price determination method of an embodiment of the present invention. DETAILED DESCRIPTION
[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the term "comprising" and any variation thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the embodiments of the present invention all comply with the relevant provisions of national laws and regulations.
[0031] The current economic volume has changed from a shortage to a surplus, and the market structure has changed from a seller's market to a buyer's market. Competition among enterprises is becoming increasingly fierce, and enterprises are increasingly constrained by market demand. Therefore, in the process of business operations, the flexible application of demand elasticity theory will help enterprises make reasonable pricing decisions and market forecasts, which is of great significance for enterprises to gain competitive advantages in market competition and thus improve economic benefits.
[0032] However, in actual applications, the sales situation of the product itself will be affected by various factors such as marketing, macroeconomics, time and seasonal trends, etc., which will affect the pricing guidance applicability of the traditional economic pricing model. This is because the assumption of rational people in economics denies various realistic factors that affect the sales volume of goods, such as hunger marketing and impulse consumption, the emergence of competing products from time to time in the market, and the impact of the life cycle of goods on the law of commodity demand. This results in the price of the goods determined based on the traditional economic pricing model being not reasonable enough. The embodiment of the present invention provides a price determination method, which can take into account various realistic factors in the pricing process, so that the determined price is more reasonable.
[0033] The price determination method provided by the embodiment of the present invention is further described in detail below through several specific embodiments.
[0034] Figure 1 : is a flow chart of a price determination method provided by an embodiment of the present invention. This embodiment can be applied to scenarios where enterprises set prices for goods. For example, it is applicable to scenarios where duty-free enterprises set prices for duty-free goods. The method can be executed by a price determination device, which can be implemented in the form of hardware and / or software. The price determination device can be configured in an electronic device, such as a computer device. Figure 1 As shown, the method includes the following steps 101 to 103.
[0035] Step 101: Determine a first corresponding relationship between the actual selling price of the target product and the fitted predicted sales volume based on the sales history data of the target product.
[0036] The target commodity in this embodiment refers to a commodity that needs to be priced. The target commodity in this embodiment may be a duty-free commodity in the duty-free industry. For example, the target commodity in this embodiment may be a perfume and cosmetics commodity.
[0037] Optionally, the commodities in this embodiment can be divided into three categories: combination commodities, substitute commodities and independent commodities. Combination commodities refer to commodities with multiple models. For example, lipsticks of different colors, each color of lipstick is a combination commodity. Substitute commodities refer to commodities with multiple specifications for the same model. For example, different volumes of liquid foundation of the same color, each volume of liquid foundation is a substitute commodity. Independent commodities refer to the rest of the commodities except combination commodities and substitute commodities. The target commodity in this embodiment can belong to any of these three categories.
[0038] The sales history data in this embodiment may include the historical retail price, historical actual selling price, and historical sales volume of the target product in the historical time period. The historical time period in this embodiment may be, for example, the past year. It can be understood that since the sales history data is the sales data that has been generated for the target product, the sales history data may reflect various realistic factors that may affect the sales volume of the product, such as hunger marketing and impulse consumption, competing products that emerge from time to time in the market, and the impact of the product life cycle on the demand law of the product.
[0039] It should be noted that the actual selling price of the target commodity in this embodiment refers to the actual price of the target commodity, that is, the price actually paid by the user in the process of purchasing the target commodity.
[0040] In step 101, a first correspondence between the actual selling price of the target product and the fitted predicted sales volume can be determined based on the sales history data of the target product by using a stage linear regression algorithm, a local weighted regression algorithm, etc. The fitted predicted sales volume in this embodiment refers to the sales volume determined based on the corresponding actual selling price according to the first correspondence relationship.
[0041] Optionally, the first corresponding relationship may be represented by a curve in a coordinate axis, or in a function form, etc., but the present embodiment is not limited thereto.
[0042] Step 102: Determine the positive elasticity interval of the target product according to the first corresponding relationship.
[0043] Among them, the actual selling price within the positive elasticity range is significantly negatively correlated with the corresponding fitted predicted sales volume.
[0044] In this embodiment, in order to facilitate the subsequent determination of the recommended price, it is necessary to determine the positive elasticity interval of the target product according to the first corresponding relationship.
[0045] The significant negative correlation in this embodiment means that the P value between the actual selling price and the corresponding fitted predicted sales volume is less than the preset P value threshold, and the regression coefficient is negative. Exemplarily, the preset P value threshold may be 0.05. That is, within the positive elasticity interval, the increase in sales volume brought about by the price reduction passes the statistical significance test.
[0046] After determining the first corresponding relationship, the positive elasticity interval can be determined according to the P value and regression coefficient between the actual selling price and the corresponding fitted predicted sales volume. It can be understood that the positive elasticity interval in this embodiment is essentially the interval to which the actual selling price belongs.
[0047] Step 103: Determine a first target actual selling price that maximizes the first comprehensive index according to a second corresponding relationship corresponding to the positive elasticity interval in the first corresponding relationship, and determine the first target actual selling price as a first recommended price for the target product.
[0048] The first comprehensive index is a value determined based on the first sales volume and the first gross profit of the target product. The first sales volume is a value determined based on the actual selling price and the corresponding fitted predicted sales volume. The first gross profit is a value determined based on the first sales volume and the cost.
[0049] Optionally, the first sales amount = actual selling price * corresponding fitting predicted sales amount. The first gross profit amount = (actual selling price * 0.96 - cost + cost * supplier subsidy ratio) * corresponding fitting predicted sales amount. The first comprehensive index = α * first sales amount + β * first gross profit amount. The first comprehensive index in this embodiment can comprehensively represent the sales and profitability of the target product to reflect the competitiveness of the enterprise.
[0050] Optionally,
[0051] In one implementation, the actual selling price can be traversed to obtain multiple actual selling prices and corresponding fitted predicted sales. Based on each actual selling price and the corresponding fitted predicted sales, the first sales amount and the first gross profit are determined. Then, based on the first sales amount and the first gross profit, a first comprehensive index is determined. Then, from the multiple first comprehensive indexes, the first target actual selling price corresponding to the largest first comprehensive index is determined. The first target actual selling price is the first recommended price of the target product.
[0052] In another implementation, the actual selling price can be traversed to obtain multiple actual selling prices and corresponding fitted predicted sales. Based on each actual selling price and the corresponding fitted predicted sales, the first sales and the first gross profit are determined. The multiple first sales are standardized by 0-1, that is, each first sales is divided by the maximum value of the first sales as the standardized first sales. The multiple first gross profits are standardized by 0-1. The first comprehensive index is then determined based on the standardized first sales and the standardized first gross profit. In this implementation, the first comprehensive index = (1 / 3) * standardized first sales + (2 / 3) * standardized first gross profit. Then, from the multiple first comprehensive indices, the first target actual selling price corresponding to the largest first comprehensive index is determined. The first target actual selling price is the first recommended price for the target product.
[0053] Optionally, in the above two implementations, before determining the first comprehensive index, the actual selling price corresponding to the negative value of the first gross profit amount may be deleted, and then the first comprehensive index corresponding to the remaining actual selling price may be calculated.
[0054] Optionally, the price determination method provided in this embodiment can also obtain an actual selling price that maximizes the first gross profit amount based on the first gross profit amount, and use it as another recommended price. In actual applications, stores or enterprises can determine the final actual selling price of the target product based on the first recommended price and the actual selling price that maximizes the first gross profit amount according to their own needs.
[0055] The demand price elasticity in this embodiment is point elasticity, which indicates the degree of reaction of sales volume changes at a certain point on the demand curve (i.e., the curve that can characterize the first correspondence relationship) to price changes, and reflects the change in sales volume when the price changes based on the current actual selling price. Different points on the curve have different elasticities, which means that even if price cuts can increase sales of goods, blindly cutting prices may also be risky, so there is a better actual selling price or actual selling price range.
[0056] Optionally, the price determination method provided in this embodiment can also determine the inventory status of the target product, specifically including the following steps: obtaining the current full-quantity end-of-period inventory of the target product; determining the inventory status of the target product based on the current full-quantity end-of-period inventory and sales history data.
[0057] The current full-scale ending inventory in this embodiment refers to all the ending inventory of the target product at the end of the previous statistical period. It includes the inventory of each store. The statistical period in this embodiment can be a natural day. When determining the inventory status of the target product based on the current full-scale ending inventory and sales history data, it can be achieved through the following steps: determine the inventory month (Month on Hand (inventory), abbreviated as: MOH) based on the current full-scale ending inventory and sales history data; determine the inventory status of the target product based on the inventory month.
[0058] Alternatively, the formula Exemplarily, R may be 30. The total historical sales volume in the last R days refers to the sum of the daily historical sales volume in the R days closest to the current day. The actual sales days in the last R days refers to the number of days in which the target product is actually sold in the R days. For example, if the target product is sold only on 25 days out of 30 days, and the target product is not sold on the remaining 5 days, the actual sales days in the last R days is 25. Furthermore, the actual sales days in the last R days refers to the number of days in which the target product is actually sold in the R days, and the number of days on which the store inventory on that day is greater than or equal to the first inventory threshold (e.g., 10).
[0059] When determining the inventory status of the target product according to the inventory month, it can be determined based on the following rules: Rule 1: If the current full end-of-period inventory quantity < the second inventory threshold (for example, 100), the inventory status of the target product is "out of stock"; Rule 2: If the current store end-of-period inventory quantity < the third inventory threshold (for example, 15), the inventory status of the target product is "out of stock in the store"; Rule 3: If MOH < 1, the inventory status of the target product is "out of stock"; Rule 4: If MOH < 2.5, the inventory status of the target product is "tight inventory". When determining the inventory status, judge in the order of Rules 1 to 4. If the previous rule is met, the following rules will not be considered. Among them, "out of stock", "out of stock in the store", and "out of stock" are out of stock status, and "tight inventory" and other situations are normal status.
[0060] After determining the inventory status of the target product, the business personnel can determine the month in which the target product can be sold based on the inventory status.
[0061] The present embodiment provides a price determination method, including: determining a first corresponding relationship between an actual selling price and a fitted predicted sales volume of the target commodity based on sales history data of the target commodity; determining a positive elasticity interval of the target commodity based on the first corresponding relationship, wherein the actual selling price within the positive elasticity interval is significantly negatively correlated with the corresponding fitted predicted sales volume; determining a first target actual selling price that maximizes a first comprehensive index based on a second corresponding relationship corresponding to the positive elasticity interval in the first corresponding relationship, and determining the first target actual selling price as a first recommended price of the target commodity, wherein the first comprehensive index is a value determined based on a first sales volume and a first gross profit amount of the target commodity, the first sales volume is a value determined based on the actual selling price and the corresponding fitted predicted sales volume, and the first gross profit amount is a value determined based on the first sales volume and the cost. It has the following technical effects: the second corresponding relationship is the relationship corresponding to the positive elasticity interval in the first corresponding relationship determined according to the sales history data. Since the sales history data can reflect various realistic factors affecting the sales volume of goods, the determination process of the second corresponding relationship takes various realistic factors into consideration. At the same time, the actual selling price in the second corresponding relationship is significantly negatively correlated with the corresponding fitted predicted sales volume, which makes the determined first target actual selling price more reasonable. Moreover, the first target actual selling price can also maximize the first comprehensive index, thereby improving the competitiveness of the enterprise.
[0062] Figure 2 is a flow chart of another price determination method provided by an embodiment of the present invention. Figure 1Based on the illustrated embodiment and various optional implementations, the implementation process of how to determine the first corresponding relationship is described in detail. The sales history data in this embodiment includes: the historical retail price of the target product in each statistical period in the historical time period, the historical actual selling price in each statistical period, and the historical sales volume in each statistical period. Figure 2 As shown, the price determination method provided in this embodiment includes the following steps 201 to 205.
[0063] Step 201: For each statistical period, determine the discount rate within the statistical period based on the historical actual selling price and the historical retail price within the statistical period.
[0064] Optionally, the historical time period in this embodiment may be the past year. The statistical period in this embodiment may be one natural day. That is, the sales history data includes: the historical retail price of the target commodity every day in the past year, the historical actual selling price of each day, and the historical sales volume of each day. The retail price in this embodiment refers to the listing price. The following takes the statistical period of one natural day as an example to illustrate this embodiment.
[0065] Optionally, in this embodiment, the price of the target product can be determined by store. Therefore, the sales history data is the sales history data of the target store.
[0066] In one implementation, the actual historical selling price of each day in this embodiment can be determined based on the following method: the actual historical selling price of each day = the historical retail price of the day - the discount of the day - the coupon amount of the day - the free points amount of the day.
[0067] In another implementation, the historical retail price for each day in this embodiment is: (historical sales for that day + historical discount amount for that day) / historical sales for that day. In this embodiment, the historical actual selling price for each day is: (historical sales for that day - coupon amount for that day - free points for that day) / historical sales for that day.
[0068] The discount rate during the statistical period in this embodiment is: historical actual selling price / historical retail price.
[0069] Optionally, in order to further improve the rationality of the determined price, the discount rate within the statistical period can be determined after correcting the historical sales volume. The sales volume of goods will be affected by the time trend, which may be composed of two factors: passenger flow and per capita consumption capacity. This embodiment uses the number of people leaving the airport every day as a time trend factor to adjust the sales volume. Optionally, the number of people leaving the airport every day can be predicted based on the historical data of the number of people leaving a certain airport from January 1, 2022 to the present, using a long short-term memory network (Long Short-Term Memory, referred to as: LSTM), to construct a function To correct the trend of the number of people on that day, where x is the number of people leaving the airport, t is the date mark, and y is the number of people leaving the airport. t represents the number of people leaving the airport on day t.
[0070] The adjusted sales volume on day t is: When determining the daily historical retail price and the daily historical actual selling price, the adjusted historical sales volume of the day can be used to improve accuracy.
[0071] Before determining the discount rate within the statistical period in step 201, the price determination method provided in this embodiment can also perform outlier elimination. There are two types of outliers to be eliminated. The first type: records where the historical actual selling price is less than the corresponding historical retail price*0.1 (including the historical retail price, the corresponding historical actual selling price, and the corresponding historical sales volume). The second type: records where the adjusted sales volume is too large, which means exceeding the upper quartile + 5*interquartile range.
[0072] Step 202: Determine effective historical actual selling prices among the historical actual selling prices according to the discount rates in multiple statistical periods.
[0073] In one implementation, the historical actual selling price corresponding to the discount rate whose occurrence times are greater than a statistical threshold among the discount rates in multiple statistical periods can be determined as the effective historical actual selling price.
[0074] In another possible implementation, step 202 includes the following steps 2021 to 2024.
[0075] Step 2021: for each discount rate interval in a plurality of pre-divided discount rate intervals, determine the number of statistical periods in which the corresponding discount rate is within the discount rate interval.
[0076] Among them, each discount rate range includes an upper limit of discount rate and a lower limit of discount rate, and the difference between the upper limit of discount rate and the lower limit of discount rate in each discount rate range is equal.
[0077] Optionally, in step 2021, multiple discount rate intervals can be divided with an interval granularity of 5%: an interval of 100% to 95%, an interval of 95% to 90%, an interval of 90% to 85%, etc. In step 2021, the number of statistical periods in each discount rate interval is determined. That is, the number of statistical periods in which the corresponding discount rate falls within the discount rate interval is determined. For example, assuming that there are 4 days in total, the discount rate on the first day is 86%, the discount rate on the second day is 93%, the discount rate on the third day is 94%, and the discount rate on the fourth day is 88%. Then the number of days in the interval of 100% to 95% is 0, the number of days in the interval of 95% to 90% is 2, and the number of days in the interval of 90% to 85% is 2.
[0078] In the interval between 95% and 90%, 95% is the upper limit of the discount rate, and 90% is the lower limit of the discount rate. It can be understood that the difference between the upper limit of the discount rate and the lower limit of the discount rate in the discount rate interval is the interval granularity.
[0079] Step 2022: Sort multiple discount rate intervals according to the size of the discount rate upper limit to obtain a discount rate interval sequence.
[0080] Based on the example in step 2021, when multiple discount rate intervals are sorted in order from large to small according to the upper limit of the discount rate, the obtained discount rate interval sequence may be (interval from 100% to 95%, interval from 95% to 90%, interval from 90% to 85%). When multiple discount rate intervals are sorted in order from small to large according to the upper limit of the discount rate, the obtained discount rate interval sequence may be (interval from 90% to 85%, interval from 95% to 90%, interval from 100% to 95%).
[0081] Step 2023: Determine the effective discount rate interval in the discount rate interval sequence based on the number of statistical periods in the first discount rate interval in the discount rate interval sequence and the number of statistical periods in the last discount rate interval in the discount rate interval sequence.
[0082] In step 2023, if the number of statistical cycles in the first discount rate interval is less than the first quantity threshold, the discount rate interval is eliminated. If the number of statistical cycles in the last discount rate interval is less than the first quantity threshold, the discount rate interval is eliminated. Exemplarily, the first quantity threshold may be 5. If the number of statistical cycles in the first discount rate interval or the last discount rate interval in the discount rate interval sequence after deleting the discount rate interval is still less than the first quantity threshold, continue to delete until the number of statistical cycles in the first discount rate interval and the last discount rate interval in the discount rate interval sequence after deleting the discount rate interval are both greater than or equal to the first quantity threshold. The remaining discount rate intervals in the discount rate interval sequence are determined as valid discount rate intervals.
[0083] Furthermore, if, in the discount rate interval sequence after deleting the discount rate interval, the number of statistical cycles in the discount rate interval corresponding to the second largest discount rate upper limit is less than or equal to the second quantity threshold, the discount rate interval corresponding to the second largest discount rate upper limit and the discount rate interval corresponding to the largest discount rate upper limit are deleted. The remaining discount rate intervals in the discount rate interval sequence are determined as valid discount rate intervals. Exemplarily, the second quantity threshold is 2.
[0084] For example, suppose there are 6 discount rate intervals, and the corresponding days are: 65%-70% 3 days, 70%-75% 3 days, 75%-80% 7 days, 85%-90% 6 days, 90%-95% 2 days, 95%-100% 7 days. Assume that the first quantity threshold can be 5, and the second quantity threshold is 2. Then delete 65%-70%. And after deleting the discount rate interval, the number of days in the discount rate interval 90%-95% corresponding to the second largest discount rate upper limit in the discount rate interval sequence is less than or equal to 2, then delete 90%-95% and 95%-100%. 70%-75%, 75%-80% and 85%-90% are determined as valid discount rate intervals.
[0085] Optionally, if the number of determined valid discount rate intervals is less than or equal to 1, the target product is determined to be a low elasticity product. The recommended price based on sales is "appropriately adjustable", that is, the current actual selling price can be increased.
[0086] In step 2023, the discount range of the target product can also be determined according to the effective discount rate range. Based on the example in step 2023, the discount range of the target product is 70%-90%.
[0087] Step 2024: Determine the historical actual selling price corresponding to the statistical period within the effective discount rate range as the effective historical actual selling price.
[0088] In step 2024, based on the example in step 2023, the historical actual selling prices of 3 days within 70%-75%, the historical actual selling prices of 7 days within 75%-80%, and the historical actual selling prices of 6 days within 85%-90% are all determined as valid historical actual selling prices. That is, the historical actual selling prices of each day in the 16 days are all determined as valid historical actual selling prices.
[0089] In steps 2021 to 2024, the effective historical actual selling prices can be determined quickly and accurately, and occasional historical actual selling prices can be eliminated, thereby improving the accuracy of the first corresponding relationship determined subsequently, and further improving the accuracy and rationality of the determined prices.
[0090] Step 203: Determine a first corresponding relationship according to the effective historical actual selling price and the corresponding historical sales volume.
[0091] In this embodiment, the first corresponding relationship can be determined by using a stage linear regression algorithm, a local weighted regression algorithm, etc. Specifically, the relationship between the effective historical actual selling price and the corresponding historical sales volume can be fitted by using a local weighted regression algorithm and a stage linear regression algorithm, respectively, and it is determined whether there is a fitting tail deviation problem in the local weighted fitting. If there is such a problem, the part with the fitting tail deviation problem is replaced by the linear regression fitting result, and then the first corresponding relationship is obtained.
[0092] Optionally, before step 203, if it is determined that the number of valid historical actual selling prices (i.e., the number of days corresponding to valid historical actual selling prices) is too small, for example, the number of valid historical actual selling prices is less than or equal to 7, step 203 is not executed and "too few samples" is output.
[0093] It should be noted that if the historical sales volume is adjusted in step 201, when determining the first corresponding relationship, the first corresponding relationship is determined based on the effective historical actual selling price and the corresponding adjusted historical sales volume.
[0094] Step 204: Determine the positive elasticity interval of the target product according to the first corresponding relationship.
[0095] Among them, the actual selling price within the positive elasticity range is significantly negatively correlated with the corresponding fitted predicted sales volume.
[0096] The implementation process and technical principle of step 204 are similar to those of step 102 and will not be described in detail here.
[0097] Optionally, if the positive elasticity interval of the target product cannot be determined, the target product is determined to be a low elasticity product. The recommended price based on sales is "appropriately adjustable".
[0098] Step 205: Determine a first target actual selling price that maximizes the first comprehensive index according to a second corresponding relationship corresponding to the positive elasticity interval in the first corresponding relationship, and determine the first target actual selling price as a first recommended price for the target product.
[0099] The first comprehensive index is a value determined based on the first sales volume and the first gross profit of the target product. The first sales volume is a value determined based on the actual selling price and the corresponding fitted predicted sales volume. The first gross profit is a value determined based on the first sales volume and the cost.
[0100] The implementation process and technical principle of step 205 are similar to those of step 103, and will not be repeated here.
[0101] The price determination method provided in this embodiment determines the effective historical actual selling price in the historical actual selling price, and then determines the first corresponding relationship based on the effective historical actual selling price and the corresponding historical sales volume. It can achieve the first corresponding relationship based on the effective historical actual selling price, thereby improving the accuracy of the determined first corresponding relationship, and further improving the accuracy and rationality of the determined price.
[0102] Figure 3 is a flowchart of another price determination method provided by an embodiment of the present invention. The price determination method provided by this embodiment is Figure 1 The embodiment shown, Figure 2Based on the illustrated embodiment and various optional implementations, other steps included in the price determination method are described in detail. For the convenience of description, only other steps included in the price determination method are described in this embodiment. Figure 3 As shown, the price determination method provided in this embodiment also includes the following steps 301 to 308.
[0103] Step 301: If the current actual selling price is not within the positive elastic range, the label of the target product is determined to be elastic fluctuation, and the second recommended price is determined to be the actual selling price within the positive elastic range.
[0104] Step 301 is performed after step 102 or step 204. This embodiment is described by taking determining the price of a target commodity in a store as an example.
[0105] The current actual selling price in this embodiment refers to the actual selling price when the price needs to be determined. Optionally, the current actual selling price can be Figure 2 The effective historical actual selling prices in the illustrated embodiment are the average of the effective historical actual selling prices of several days (eg, 7 days) closest to the current time.
[0106] In this embodiment, the second suggested price of the target product and the label of the target product can be determined according to step 301 to step 308. Optionally, the judgment can be made in order based on step 301 to step 308. If the previous step is satisfied, the next step is not executed.
[0107] In step 301, if the current actual selling price is not within the positive elastic range, the label of the target product is determined to be elastic fluctuation, and the second recommended price is determined to be the actual selling price within the positive elastic range.
[0108] Step 302: According to the second corresponding relationship, determine the fitted predicted sales volume corresponding to the current actual selling price of the target product, determine the fitted predicted sales volume corresponding to the store retail price of the target product, and determine the fitted predicted sales volume corresponding to the variable price of the target product.
[0109] Optionally, the store retail price in this embodiment may be the store retail price of the most recent day.
[0110] In step 302, the fitted predicted sales volume corresponding to the current actual selling price and the fitted predicted sales volume corresponding to the store retail price can be determined based on the second corresponding relationship. In step 302, the variable price can be traversed to determine the fitted predicted sales volume corresponding to the variable price based on the second corresponding relationship.
[0111] Step 303: If the store price elasticity is always less than the first preset value, the label of the target product is determined to be low elasticity, and the second recommended price is determined to be the current actual selling price.
[0112] Among them, store price elasticity is a value determined based on the variable price and its corresponding fitted predicted sales volume, the store retail price and its corresponding fitted predicted sales volume.
[0113] Optionally, store price elasticity Among them, P represents the variable price, Q P represents the fitted predicted sales volume corresponding to the variable price. m is the store retail price, Q m Represents the fitted predicted sales volume corresponding to the store retail price.
[0114] In step 303, the store price elasticity is always less than the first preset value means that when traversing the variable price, the store price elasticity is less than the first preset value. Exemplarily, the first preset value may be 1. When the store price elasticity is always less than the first preset value, it means that the sales volume cannot be increased by lowering the actual selling price, and therefore, it is recommended to maintain the current actual selling price.
[0115] Step 304: If the store price elasticity at the current actual selling price is less than the first preset value, the label of the target product is determined to be elastic fluctuation, and the second recommended price is determined to be within the price range formed by the first price and the second price.
[0116] Among them, the first price is the variable price corresponding to the maximum value of the store price elasticity, the second price is the variable price closest to the current actual selling price that makes the store price elasticity a first preset value, and the store price elasticity at the current actual selling price is the store price elasticity corresponding to when the variable price is the current actual selling price.
[0117] In step 304, if the store price elasticity corresponding to the variable price being the current actual selling price is less than the first preset value, the second recommended price is within the price range formed by the first price and the second price. The first price is the variable price that maximizes the store price elasticity. The second price is the variable price that is closest to the current actual selling price and makes the store price elasticity equal to the first preset value.
[0118] Optionally, if the price range formed by the first price and the second price is no more than 2% away from the current actual selling price, the label of the target product is determined to be low elasticity, and it is recommended to maintain the current actual selling price.
[0119] Step 305: If the store price elasticity at the current actual selling price is greater than or equal to the first preset value, and when the current actual selling price continues to decrease, the current price elasticity is always less than the first preset value, then the label of the target product is determined to be elastic fluctuation, and the second recommended price is determined to be the current actual selling price.
[0120] Among them, the current price elasticity is a value determined based on the variable price and its corresponding fitted predicted sales volume, the current actual selling price and its corresponding fitted predicted sales volume.
[0121] Optionally, the current price elasticity Among them, P R Indicates the current actual selling price, Q R Indicates the fitted predicted sales volume corresponding to the current actual selling price.
[0122] When the current actual selling price continues to decrease, the price elasticity of the current price is always less than the first preset value, which means that if the current actual selling price continues to decrease and then traverses the variable price, the price elasticity of the current price is less than the first preset value.
[0123] Step 306: If the current actual selling price continues to decrease, and there is a price range in which the price elasticity of the current price is greater than the first preset value, the third price is determined to be the minimum price that is less than the target price and that makes the point price elasticity always greater than the first preset value, the fourth price is determined to be the maximum price within the price range formed by the target price and the current actual selling price and that makes the price elasticity of the current price always greater than the first preset value, and the second recommended price is determined to be within the recommended price range formed by the third price and the fourth price.
[0124] Among them, the point price elasticity is a value determined based on the variable price and its corresponding fitted predicted sales volume and sales history data. The target price is the variable price that makes the current price elasticity the highest within the price range less than the current actual selling price.
[0125] Optionally, point price elasticity Among them, Q P-" Indicates the historical actual selling price or the effective historical actual selling price with the smallest absolute value of the difference from the variable price P.
[0126] The maximum price within the price range formed by the target price and the current actual selling price that makes the price elasticity of the current price always greater than the first preset value refers to the maximum variable price within the price range formed by the target price and the current actual selling price that can make the price elasticity of the current price always greater than the first preset value.
[0127] Step 307: If the recommended price range covers the target positive elasticity range, the label of the target product is determined to be stable elasticity or increasing elasticity.
[0128] Among them, the target positive elasticity interval is a positive elasticity interval that is smaller than the current actual selling price.
[0129] Step 308: If the recommended price range does not cover the target positive elasticity range, the label of the target product is determined to be elastic fluctuation.
[0130] In step 307 and step 308, the label of the target product can be determined according to the relationship between the recommended price range and the target positive elasticity range. The recommended price range covers the target positive elasticity range, which means that the recommended price range completely includes the target positive elasticity range. The recommended price range does not cover the target positive elasticity range, which means that the recommended price range does not completely include the target positive elasticity range or does not include the target positive elasticity range.
[0131] The label "low elasticity" in this embodiment means that it is impossible to increase sales by lowering the actual selling price. The label "elastic fluctuation" means that it is possible to increase sales by lowering the actual selling price. The label "elastic increasing" means that it is more suitable to lower the actual selling price to increase sales. The labels of the target products determined in this embodiment can assist in determining the direction of better discount adjustments for the target products, provide a reference for retail stores to make differentiated promotional strategies, and ultimately make more optimized product pricing decisions.
[0132] It can be understood that the second recommended price determined in this embodiment is a price based on sales volume.
[0133] Optionally, in this embodiment, the final actual selling price may be determined based on the first suggested price and the second suggested price.
[0134] The price determination method provided in this embodiment can determine the label and the second recommended price of the target product through various price elasticities, thereby further improving the rationality and accuracy of the determined price.
[0135] Figure 4 FIG. 1 is a flowchart of another method for determining a price provided by an embodiment of the present invention. Figures 1 to 3 Based on the illustrated embodiment and various optional implementations, other steps included in the price determination method when the target product is a substitute product are described in detail. The target product in this embodiment includes multiple target sub-products. Figure 4 As shown, the price determination method provided in this embodiment includes the following steps.
[0136] Step 401: Determine a first corresponding relationship between the actual selling price of the target product and the fitted predicted sales volume based on the sales history data of the target product.
[0137] Step 402: Determine the positive elasticity interval of the target product according to the first corresponding relationship.
[0138] Among them, the actual selling price within the positive elasticity range is significantly negatively correlated with the corresponding fitted predicted sales volume.
[0139] Step 403: Determine a first target actual selling price that maximizes the first comprehensive index according to a second corresponding relationship corresponding to the positive elasticity interval in the first corresponding relationship, and determine the first target actual selling price as a first recommended price for the target product.
[0140] The first comprehensive index is a value determined based on the first sales volume and the first gross profit of the target product. The first sales volume is a value determined based on the actual selling price and the corresponding fitted predicted sales volume. The first gross profit is a value determined based on the first sales volume and the cost.
[0141] The implementation process and technical principle of step 401 and step 101, step 402 and step 102, and step 403 and step 103 are similar, and will not be repeated here.
[0142] In this embodiment, when determining the historical sales volume of each target sub-commodity, it can be determined based on the following method: historical sales volume = original historical sales volume * specification multiple. The original historical sales volume may also be the adjusted original historical sales volume adjusted as in the implementation method of step 201. The specification multiple in this embodiment refers to the multiple compared to the minimum specification. Assuming that the target sub-commodity is liquid foundation, the specification of target sub-commodity 1 is 50 ml, the specification of target sub-commodity 2 is 100 ml, and the specification of target sub-commodity 3 is 150 ml. Then the minimum specification is 50 ml. The specification multiple of target sub-commodity 1 is 1. The specification multiple of target sub-commodity 2 is 2. The specification multiple of target sub-commodity 3 is 3.
[0143] Step 404: Determine, based on the pre-trained machine learning model, a third recommended price for each target sub-commodity that maximizes the second comprehensive index.
[0144] The machine learning model is used to determine the model predicted sales volume of each target sub-commodity according to the actual selling prices of multiple target sub-commodities. The second comprehensive index is a value determined according to the second sales volume and the second gross profit of the target commodity. The second sales volume is a value determined according to the actual selling price of each target sub-commodity and the corresponding model predicted sales volume. The second gross profit is a value determined according to the second sales volume and the cost.
[0145] Before step 404, it is necessary to train the machine learning model. The training process includes the following steps.
[0146] 1) Data integration and preprocessing: Obtain the historical retail price of each target sub-commodity in each statistical period in the historical time period, the historical actual selling price in each statistical period, and the historical sales volume in each statistical period.
[0147] 2) Outlier elimination: This is similar to the implementation in step 201 and will not be described in detail here.
[0148] 3) Convert to wide table: This step includes three aspects. ① Convert the actual selling price and sales volume of each target sub-commodity to a wide table, with the same row representing the actual selling price and sales volume of each target sub-commodity on a valid day. ② Complete the data based on the inventory status of each target sub-commodity. ③ Allocate the sales volume of the target sub-commodity.
[0149] 4) Training and validation: Split the above dataset (including the historical actual selling price and historical sales volume of each target sub-product in each statistical period) into a training set and a validation set at a ratio of 3:1, and train them using multiple machine learning models to obtain the model predicted sales volume q of each target sub-product when the series price is combined. $ =f(p " ,p ( ,…,p * ), n represents the number of target sub-products, p $ represents the actual selling price of the i-th target sub-product. The validation set is used for validation to obtain the accuracy of the four methods. For example, the accuracy can be measured by the root mean square error (RMSE).
[0150] 5) Construct a prediction set: The prediction set is a price combination of each target sub-commodity, which is nested layer by layer, with the outer layer being the target sub-commodities with smaller specifications and the inner layer being the target sub-commodities with larger specifications.
[0151] 6) Prediction and result adjustment: Use the above-mentioned machine learning models to make predictions separately.
[0152] For each target sub-product, a price combination can be input into the machine learning model to determine the model predicted sales volume of the target sub-product. Multiple price combinations and corresponding model predicted sales volumes can be obtained.
[0153] The second comprehensive index in this embodiment = x * second sales + y * second gross profit. The second sales is a value determined based on the actual selling price of each target sub-commodity and the corresponding model predicted sales. Optionally, the second sales is the sum of the sales of multiple target sub-commodities. The second gross profit is a value determined based on the second sales and cost. Second gross profit = (actual selling price * 0.96-cost + cost * supplier subsidy ratio) * corresponding model predicted sales.
[0154] Optionally, similar to the implementation of the first comprehensive index in step 103, the second comprehensive index may also be: (1 / 3)*standardized second sales amount+(2 / 3)*standardized second gross profit amount.
[0155] Based on the pre-trained machine learning model, a third recommended price for each target sub-commodity that maximizes the second comprehensive index can be determined.
[0156] The price determination method provided in this embodiment determines the third recommended price of each target sub-commodity that maximizes the second comprehensive index through a machine learning model. In the scenario of alternative commodities, the machine learning model is used to fit the central trend in complex situations to determine the recommended price of each target sub-commodity, thereby avoiding the change in the price of a target sub-commodity in the alternative commodities affecting the sales of other target sub-commodities, and realizing the joint adjustment of the prices of each target sub-commodity, thereby further improving the competitiveness of the enterprise.
[0157] Figure 5 Schematic diagram of a price determination device provided by an embodiment of the present invention. Figure 5 As shown, the price determination device provided in this embodiment includes the following modules: a first determination module 51 , a second determination module 52 and a third determination module 53 .
[0158] The first determination module 51 is used to determine a first corresponding relationship between the actual selling price and the fitted predicted sales volume of the target commodity according to the sales history data of the target commodity.
[0159] The second determining module 52 is used to determine the positive elasticity interval of the target product according to the first corresponding relationship.
[0160] Among them, the actual selling price within the positive elasticity range is significantly negatively correlated with the corresponding fitted predicted sales volume.
[0161] The third determination module 53 is used to determine a first target actual selling price that maximizes the first comprehensive index according to a second corresponding relationship corresponding to the positive elasticity interval in the first corresponding relationship, and determine the first target actual selling price as a first recommended price for the target product.
[0162] The first comprehensive index is a value determined based on the first sales volume and the first gross profit of the target product. The first sales volume is a value determined based on the actual selling price and the corresponding fitted predicted sales volume. The first gross profit is a value determined based on the first sales volume and cost.
[0163] In one embodiment, the sales history data includes: the historical retail price of the target product in each statistical period in the historical time period, the historical actual selling price in each statistical period, and the historical sales volume in each statistical period. The first determination module 51 is specifically used to: for each statistical period, determine the discount rate in the statistical period according to the historical actual selling price in the statistical period and the historical retail price; determine the effective historical actual selling price in the historical actual selling price according to the discount rates in multiple statistical periods; determine the first corresponding relationship according to the effective historical actual selling price and the corresponding historical sales volume.
[0164] In one embodiment, in terms of determining the effective historical actual selling prices in the historical actual selling prices based on the discount rates in multiple statistical periods, the first determination module 51 is specifically used to: for each discount rate interval in the multiple pre-divided discount rate intervals, determine the number of statistical periods whose corresponding discount rates are within the discount rate interval, wherein each discount rate interval includes an upper discount rate limit and a lower discount rate limit, and the difference between the upper discount rate limit and the lower discount rate limit in each discount rate interval is equal; sort the multiple discount rate intervals according to the size of the upper discount rate limit to obtain a discount rate interval sequence; determine the effective discount rate interval in the discount rate interval sequence based on the number of statistical periods in the first discount rate interval in the discount rate interval sequence and the number of statistical periods in the last discount rate interval in the discount rate interval sequence; determine the historical actual selling price corresponding to the statistical period in the effective discount rate interval as the effective historical actual selling price.
[0165] In one embodiment, the device further includes: a fourth determining module, a fifth determining module, a sixth determining module, a seventh determining module, an eighth determining module, a ninth determining module and a tenth determining module.
[0166] The fourth determination module is used to determine that the label of the target product is elastic fluctuation if the current actual selling price is not within the positive elastic range, and determine that the second recommended price is the actual selling price within the positive elastic range.
[0167] The fifth determination module is used to determine the fitting predicted sales volume corresponding to the current actual selling price of the target product, the fitting predicted sales volume corresponding to the store retail price of the target product, and the fitting predicted sales volume corresponding to the variable price of the target product based on the second corresponding relationship.
[0168] The sixth determination module is used to determine that the label of the target product is low elasticity if the store price elasticity is always less than the first preset value, and determine that the second recommended price is the current actual selling price. The store price elasticity is a value determined based on the variable price and its corresponding fitted predicted sales volume, the store retail price and its corresponding fitted predicted sales volume.
[0169] The seventh determination module is used to determine that the label of the target product is elastic fluctuation if the store price elasticity at the current actual selling price is less than the first preset value, and determine that the second recommended price is within the price range formed by the first price and the second price. The first price is the variable price corresponding to the maximum value of the store price elasticity, and the second price is the variable price closest to the current actual selling price that makes the store price elasticity the first preset value. The store price elasticity at the current actual selling price is the store price elasticity corresponding to when the variable price is the current actual selling price.
[0170] The eighth determination module is used to determine that the label of the target product is elastic fluctuation, and the second recommended price is determined to be the current actual selling price, if the store price elasticity at the current actual selling price is greater than or equal to the first preset value, and when the current actual selling price continues to decrease, the current price elasticity is always less than the first preset value. The current price elasticity is a value determined based on the variable price and its corresponding fitted predicted sales volume, the current actual selling price and its corresponding fitted predicted sales volume.
[0171] The ninth determination module is used to determine the third price as the minimum price less than the target price and making the point price elasticity always greater than the first preset value if there is a price range that makes the current price elasticity greater than the first preset value when the current actual selling price continues to decrease, determine the fourth price as the maximum price within the price range formed by the target price and the current actual selling price and making the current price elasticity always greater than the first preset value, and determine that the second recommended price is within the recommended price range formed by the third price and the fourth price. Among them, the point price elasticity is a value determined based on the variable price and its corresponding fitted predicted sales volume and the sales history data, and the target price is the variable price within the price range less than the current actual selling price that makes the current price elasticity the highest;
[0172] The tenth determination module is used to determine that the label of the target product is elastically stable or elastically increasing if the recommended price range covers the target positive elastic range, wherein the target positive elastic range is a positive elastic range that is smaller than the current actual selling price.
[0173] The tenth determination module is further configured to determine that the label of the target product is elastic fluctuation if the recommended price range does not cover the target positive elastic range.
[0174] In one embodiment, the device further comprises an acquisition module and an eleventh determination module. The acquisition module is used to acquire the current full-quantity end-of-period inventory of the target commodity. The eleventh determination module is used to determine the inventory status of the target commodity according to the current full-quantity end-of-period inventory and the sales history data.
[0175] In one embodiment, the target commodity is a substitute commodity, and the target commodity includes a plurality of target sub-commodities. The device further includes a twelfth determination module, which is used to determine the third recommended price of each of the target sub-commodities that maximizes the second comprehensive index based on a pre-trained machine learning model. The machine learning model is used to determine the model predicted sales volume of each of the target sub-commodities based on the actual selling prices of the plurality of target sub-commodities, the second comprehensive index is a value determined based on the second sales volume and the second gross profit of the target commodity, the second sales volume is a value determined based on the actual selling price of each of the target sub-commodities and the corresponding model predicted sales volume, and the second gross profit is a value determined based on the second sales volume and the cost.
[0176] The price determination device provided in the embodiment of the present invention can execute the price determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0177] Figure 6 is a schematic diagram of the structure of an electronic device that implements the price determination method of an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0178] like Figure 6 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0179] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0180] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as a price determination method.
[0181] In some embodiments, the price determination method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the price determination method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the price determination method in any other suitable manner (e.g., by means of firmware).
[0182] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0183] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0184] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0185] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0186] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0187] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0188] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the price determination method provided by any embodiment of the present invention.
[0189] In the process of implementation, the computer program product can be written in one or more programming languages or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).
[0190] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0191] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A price determination method, It is characterized in that include: Determining a first corresponding relationship between an actual selling price of the target product and a fitted predicted sales volume according to the sales history data of the target product; According to the first corresponding relationship, a positive elasticity interval of the target product is determined; wherein the actual selling price within the positive elasticity interval is significantly negatively correlated with the corresponding fitted predicted sales volume; According to the second corresponding relationship corresponding to the positive elasticity interval in the first corresponding relationship, the first target actual selling price that maximizes the first comprehensive index is determined, and the first target actual selling price is determined as the first recommended price of the target commodity; wherein, the first comprehensive index is a value determined based on the first sales volume and the first gross profit amount of the target commodity, the first sales volume is a value determined based on the actual selling price and the corresponding fitted predicted sales volume, and the first gross profit amount is a value determined based on the first sales volume and the cost.
2. The method according to claim 1, It is characterized in that The sales history data includes: the historical retail price of the target product in each statistical period in the historical time period, the historical actual selling price in each statistical period, and the historical sales volume in each statistical period; The determining, based on the sales history data of the target commodity, a first corresponding relationship between the actual selling price of the target commodity and the fitted predicted sales volume includes: For each statistical period, determining the discount rate within the statistical period according to the historical actual selling price within the statistical period and the historical retail price; Determining, according to the discount rates in the plurality of statistical periods, a valid historical actual selling price among the historical actual selling prices; The first corresponding relationship is determined according to the effective historical actual selling price and the corresponding historical sales volume.
3. The method according to claim 2, It is characterized in that Determining the effective historical actual selling prices in the historical actual selling prices according to the discount rates in the plurality of statistical periods includes: For each of the multiple pre-divided discount rate intervals, determine the number of statistical periods whose corresponding discount rate is within the discount rate interval; wherein each of the discount rate intervals includes an upper limit of the discount rate and a lower limit of the discount rate, and the difference between the upper limit of the discount rate and the lower limit of the discount rate in each of the discount rate intervals is equal; sorting the plurality of discount rate intervals according to the size of the discount rate upper limit to obtain a discount rate interval sequence; Determine the effective discount rate interval in the discount rate interval sequence according to the number of statistical periods in the first discount rate interval in the discount rate interval sequence and the number of statistical periods in the last discount rate interval in the discount rate interval sequence; The historical actual selling price corresponding to the statistical period within the effective discount rate range is determined as the effective historical actual selling price.
4. The method according to claim 1, It is characterized in that The method further comprises: If the current actual selling price is not within the positive elastic range, the label of the target product is determined to be elastic fluctuation, and the second suggested price is determined to be the actual selling price within the positive elastic range; According to the second corresponding relationship, determine the fitted predicted sales volume corresponding to the current actual selling price of the target product, determine the fitted predicted sales volume corresponding to the store retail price of the target product, and determine the fitted predicted sales volume corresponding to the variable price of the target product; If the store price elasticity is always less than the first preset value, the label of the target product is determined to be low elasticity, and the second recommended price is determined to be the current actual selling price; wherein the store price elasticity is a value determined according to the variable price and its corresponding fitted predicted sales volume, the store retail price and its corresponding fitted predicted sales volume; If the store price elasticity at the current actual selling price is less than the first preset value, the label of the target product is determined to be elastic fluctuation, and the second recommended price is determined to be in the price range formed by the first price and the second price; wherein the first price is the variable price corresponding to the maximum value of the store price elasticity, the second price is the variable price closest to the current actual selling price that makes the store price elasticity the first preset value, and the store price elasticity at the current actual selling price is the store price elasticity corresponding to when the variable price is the current actual selling price.
5. The method according to claim 4, It is characterized in that The method further comprises: If the store price elasticity at the current actual selling price is greater than or equal to the first preset value, and when the current actual selling price continues to decrease, the current price elasticity is always less than the first preset value, then the label of the target product is determined to be elastic fluctuation, and the second recommended price is determined to be the current actual selling price; wherein the current price elasticity is a value determined based on the variable price and its corresponding fitted predicted sales volume, the current actual selling price and its corresponding fitted predicted sales volume; If the current actual selling price continues to decrease, and there is a price range that makes the price elasticity of the current price greater than the first preset value, the third price is determined to be the minimum price that is less than the target price and makes the price elasticity of the point greater than the first preset value, the fourth price is determined to be the maximum price within the price range formed by the target price and the current actual selling price and makes the price elasticity of the current price greater than the first preset value, and the second recommended price is determined to be within the recommended price range formed by the third price and the fourth price; wherein the price elasticity of the point is a value determined based on the variable price and its corresponding fitted predicted sales volume and the sales history data, and the target price is the variable price within the price range less than the current actual selling price that makes the price elasticity of the current price the highest; If the recommended price range covers the target positive elasticity range, the label of the target product is determined to be stable elasticity or increasing elasticity; wherein the target positive elasticity range is a positive elasticity range that is smaller than the current actual selling price; If the recommended price range does not cover the target positive elasticity range, it is determined that the label of the target product is elastic fluctuation.
6. The method according to claim 1, It is characterized in that The method further comprises: Obtain the current full ending inventory of the target product; The inventory status of the target product is determined according to the current full period-end inventory and the sales history data.
7. The method according to claim 1, It is characterized in that The target product is a substitute product, and the target product includes multiple target sub-products; The method further comprises: According to a pre-trained machine learning model, determine the third recommended price of each of the target sub-commodities that maximizes the second comprehensive index; wherein the machine learning model is used to determine the model predicted sales volume of each of the target sub-commodities based on the actual selling prices of the multiple target sub-commodities, and the second comprehensive index is a value determined based on the second sales volume and the second gross profit of the target commodity, the second sales volume is a value determined based on the actual selling price of each of the target sub-commodities and the corresponding model predicted sales volume, and the second gross profit is a value determined based on the second sales volume and cost.
8. A price determination device, It is characterized in that include: A first determination module, configured to determine a first corresponding relationship between an actual selling price of the target commodity and a fitted predicted sales volume according to sales history data of the target commodity; A second determination module is used to determine the positive elasticity interval of the target product according to the first corresponding relationship; wherein the actual selling price within the positive elasticity interval is significantly negatively correlated with the corresponding fitted predicted sales volume; The third determination module is used to determine the first target actual selling price that maximizes the first comprehensive index according to the second corresponding relationship corresponding to the positive elasticity interval in the first corresponding relationship, and determine the first target actual selling price as the first recommended price of the target product; wherein the first comprehensive index is a value determined according to the first sales volume and the first gross profit amount of the target product, the first sales volume is a value determined according to the actual selling price and the corresponding fitted predicted sales volume, and the first gross profit amount is a value determined according to the first sales volume and the cost.
9. An electronic device, It is characterized in that The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the price determination method according to any one of claims 1 to 7.
10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, and the computer program is used to enable a processor to implement the price determination method according to any one of claims 1 to 7 when executed.
