E-commerce management data processing system and method based on big data analysis

Abstract

The invention discloses an e-commerce management data processing system and method based on big data analysis, and belongs to the technical field of e-commerce management. The method comprises the following steps: constructing a product database, wherein the product database comprises product sales data and product inventory data; based on the product database, constructing a set of products of the same type, and predicting the racking period of the products; constructing a same-cycle product set based on the racking cycle of the products, and calculating a monthly growth rate prediction value of the products; predicting the first month sales volume of the product; based on the sales data of the product, constructing an e-commerce management evaluation model, and calculating the predicted influence degree of the return rate and the satisfaction on the monthly growth rate of the sales volume; extracting the inventory of the products, and calculating the quantity of inventory products to be supplemented; therefore, the effective management of the product inventory is realized, the inventory quantity meets the shopping demand of consumers, the timely supply of commodities is ensured, the shopping experience of the consumers is improved, and the possibility of unsalable inventory caused by overstock of excessive commodities due to wrong judgment of merchants is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce management, and in particular to an e-commerce management data processing system and method based on big data analysis. Background Art

[0002] With the continuous development of Internet technology and the popularization of smart mobile devices such as mobile phones, the rise of e-commerce has not only lowered the threshold for information dissemination, allowing consumers to easily obtain various goods and services, but also enabled consumers to shop online anytime and anywhere, improving consumers' user experience and shopping convenience; for sellers, it has broken through geographical restrictions and directly traded with consumers through online platforms, increasing sellers' sales opportunities.

[0003] With the rapid development of the e-commerce industry, when consumers make online shopping, the e-commerce platform shows insufficient inventory, which affects consumers' shopping experience. At the same time, due to misjudgment, merchants have too many goods in stock, which will lead to unsalable inventory and the inventory quantity cannot meet consumers' shopping needs. Therefore, how to ensure the timely supply of goods and the reasonable management of inventory has become an issue we need to study. Summary of the invention

[0004] The purpose of the present invention is to provide an e-commerce management data processing system and method based on big data analysis to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] The e-commerce management data processing method based on big data analysis includes the following steps:

[0007] Step S1. Build a product database, the product database includes product sales data and product inventory data;

[0008] Step S2. Based on the product database, construct a set of products of the same type and predict the product's shelf life; based on the product's shelf life, construct a set of products of the same period and calculate the predicted monthly growth rate of the product;

[0009] Step S3. Based on the product sales data, an e-commerce management evaluation model is constructed to calculate the predicted impact of return rate and satisfaction on the monthly sales growth rate;

[0010] Step S4: Extract the inventory of the product and calculate the quantity of the inventory product to be replenished.

[0011] Furthermore, the specific implementation process of step S1 includes:

[0012] Construct a product database, which is used to store sales data and inventory data of products of the same type. The sales data of products of the same type include the shelf life, sales volume, return rate and satisfaction of the products; the inventory data of products of the same type is the inventory volume of the products.

[0013] Furthermore, the specific implementation process of step S2 includes:

[0014] Step S21. Based on the product database, extract the sales data of the same type of products and construct the same type product set SU = {s m |m∈[1,M]}, where s m represents the sales data set of the mth product of the same category, wherein the sales data set records the sales data of products of the same category, and M represents the total number of products of the same category;

[0015] Based on the same category of products, predict the product shelf life: Among them, T m Represents the sales dataset s m In the shelf cycle, T represents the predicted shelf cycle of the product;

[0016] Step S22. Based on the predicted shelf life of the product, extract the sales data set with the same predicted shelf life from the same category product set SU, and construct the same period product set PU = {s n |n∈[1,N]}, where s n represents the sales dataset of the nth product of the same category, and N represents the total number of sales datasets extracted from the product set SU of the same category;

[0017] Pre-process the sales volume of the product set PU in the same period and calculate the predicted monthly growth rate of the product: Among them, KP n |(t→t+1) represents the monthly growth rate of sales volume of the nth product of the same type from the tth month to the t+1th month, A t A represents the sales volume of the nth product of the same type in the tth month, t+1 represents the sales volume of the nth product of the same type in the t+1th month, and KP|(t→t+1) represents the predicted monthly growth rate of sales of all e-commerce products from the tth month to the t+1th month.

[0018] The shelf cycle refers to the period from when a product is put on the shelf to when it is taken off the shelf; the shelf cycles of products of the same type are consistent, but may be different for different types of products, so the shelf cycle of products undergoing inventory management can be predicted by calculating the average shelf cycle of products of the same type; due to the uncontrollability of sales volume, it is impossible to directly predict sales volume, but the growth trend of sales volume is consistent, so sales volume can be predicted by the growth trend (i.e., the monthly growth rate of sales volume); in order to more accurately obtain the monthly growth rate of sales volume, narrow the range of extracted products, and use the moving average method to calculate the average of the monthly growth rate of sales volume of products of the same shelf cycle and the same type to obtain the predicted value of the monthly growth rate of the product to be predicted.

[0019] Furthermore, the specific implementation process of step S3 includes:

[0020] Step S31. Based on the same category product set SU, predict the first month sales volume of the product: Among them, a represents the first month's predicted sales volume of the product, A 1m represents the first month sales volume of the mth product of the same type;

[0021] Step S32. Construct an e-commerce management evaluation model: L = w1g(d)+w2h(x)+b1, Among them, L represents the predicted impact of return rate and satisfaction on the monthly sales growth rate, d represents the return rate, x represents the satisfaction, w1, w2, w3, w4 represent the preset risk coefficients, b1, b2, b3 represent the preset error coefficients, and D represents the preset return rate threshold.

[0022] Before merchants put products on the shelves, they can predict the sales volume of the products to be put on the shelves based on products of the same type, estimate the sales volume in the first month, and then purchase the products to be put on the shelves; the monthly growth rate of sales volume is not only consistent, but also affected by the customer's return rate and satisfaction. When the return rate and satisfaction reach a certain level, customers will think that the products put on the shelves by the merchant have quality problems, and thus choose similar products from other merchants. At this time, the monthly growth rate of sales volume will decrease.

[0023] Furthermore, the specific implementation process of step S4 includes:

[0024] Extract the inventory of the product and calculate the number of inventory products to be replenished: F = GH-OL, GH = J*[KP|(t→t+1)×(1-L)+z+1], where GH represents the estimated inventory required in the t+1th month, J represents the actual sales volume of the product in the tth month, 0L represents the inventory of the product, and z represents the preset percentage of spare inventory.

[0025] For the quantity of products to be purchased next time, it is necessary not only to calculate the sales volume of the next month, i.e., J*KP|(t→t+1)×(1-L), but also to pre-store a certain amount of inventory, i.e., J*z, to prevent the inventory quantity from being unable to meet the shopping needs of consumers when there is a surge in orders; among them, as the return rate and satisfaction rate have an increasing influence on the predicted sales growth rate, the absolute value of the monthly growth rate will decrease, and as the return rate and satisfaction rate have a decreasing influence on the predicted sales growth rate, the absolute value of the monthly growth rate will increase accordingly.

[0026] An e-commerce management data processing system based on big data analysis, the system comprising: a data storage module, a product forecasting module, an e-commerce management evaluation module and an inventory replenishment module;

[0027] The data storage module is used to construct a product database, which includes product sales data and product inventory data;

[0028] The product prediction module is used to construct a set of products of the same type and predict the shelf life of the products; based on the shelf life of the products, a set of products of the same period is constructed to calculate the monthly growth rate forecast value of the products;

[0029] The e-commerce management evaluation module constructs an e-commerce management evaluation model through product sales data to calculate the predicted impact of return rate and satisfaction on the monthly sales growth rate;

[0030] The inventory replenishment module is used to extract the inventory quantity of the product and calculate the quantity of the inventory product to be replenished.

[0031] Furthermore, the data storage module constructs a product database, which is used to store sales data and inventory data of products of the same type. The sales data of products of the same type include the product's shelf life, sales volume, return rate and satisfaction; the inventory data of products of the same type is the inventory volume of the product.

[0032] Further, the product prediction module includes a shelf cycle unit and a monthly growth rate prediction unit;

[0033] The shelf cycle unit extracts the sales data of the same type of products based on the product database and constructs a product set SU of the same type = {s m |m∈[1,M]}, where s m represents the sales data set of the mth product of the same category, in which the sales data set records the sales data of products of the same category, and M represents the total number of products of the same category; based on the product set of the same category, the shelf life of the product is predicted: Where T m Represents the sales dataset s mIn the shelf cycle, T represents the predicted shelf cycle of the product; based on the predicted shelf cycle of the product, the sales data set with the same predicted shelf cycle is extracted from the same type of product set SU, and the same cycle product set PU is constructed. n |n∈[1,N]}, where s n represents the sales dataset of the nth product of the same category, and N represents the total number of sales datasets extracted from the product set SU of the same category;

[0034] The monthly growth rate prediction unit is used to pre-process the sales volume of the product set PU in the same period and calculate the monthly growth rate prediction value of the product: Among them, KP n |(t→t+1) represents the monthly growth rate of sales volume of the nth same type of product from the tth month to the t+1th month, At represents the sales volume of the nth same type of product in the tth month, A t+1 represents the sales volume of the nth product of the same type in the t+1th month, and KP|(t→t+1) represents the predicted monthly growth rate of sales of all e-commerce products from the tth month to the t+1th month.

[0035] Further, the e-commerce management evaluation module includes a first month sales volume unit and a model unit;

[0036] The first month sales unit predicts the first month sales of a product based on the same category product set SU: Among them, a represents the first month's predicted sales volume of the product, A 1m represents the first month sales volume of the mth product of the same type;

[0037] The model unit constructs an e-commerce management evaluation model: L = w1g(d)+w2h(x)+b1, Among them, L represents the predicted impact of return rate and satisfaction on the monthly sales growth rate, d represents the return rate, x represents the satisfaction, w1, w2, w3, w4 represent the preset risk coefficients, b1, b2, b3 represent the preset error coefficients, and D represents the preset return rate threshold.

[0038] Furthermore, the inventory replenishment module calculates the number of inventory products to be replenished by extracting the inventory of the product: F=GH-OL, GH=J*[KP|(t→t+1)×(1-L)+z+1], wherein GH represents the estimated required inventory in the t+1th month, J represents the actual sales volume of the product in the tth month, 0L represents the inventory of the product, and z represents the preset percentage of spare inventory.

[0039] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in the e-commerce management data processing system and method based on big data analysis provided by the present invention, by constructing a product database, the product database includes product sales data and product inventory data; based on the product database, a set of products of the same type is constructed to predict the shelf cycle of the products; based on the shelf cycle of the products, a set of products of the same cycle is constructed to calculate the predicted monthly growth rate of the products; the first-month sales volume of the products is predicted; based on the sales data of the products, an e-commerce management evaluation model is constructed to calculate the predicted impact of the return rate and satisfaction on the monthly sales growth rate; the inventory of the products is extracted, and the number of inventory products to be replenished is calculated; thereby, effective management of product inventory is achieved, the inventory quantity meets the shopping needs of consumers, and also ensures the timely supply of goods, improves the shopping experience of consumers, and reduces the possibility of merchants' inventory being unsalable due to excessive backlogs of goods due to misjudgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0041] Figure 1 It is a structural schematic diagram of an e-commerce management data processing system based on big data analysis of the present invention;

[0042] Figure 2 It is a schematic diagram of the steps of the e-commerce management data processing method based on big data analysis of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 are within the scope of protection of the present invention.

[0044] See also Figure 1-Figure 2 , the present invention provides a technical solution:

[0045] An e-commerce management data processing method based on big data analysis, the method comprising the following steps:

[0046] Step S1. Build a product database, which includes product sales data and product inventory data;

[0047] Step S2. Based on the product database, construct a set of products of the same type and predict the product's shelf life; based on the product's shelf life, construct a set of products of the same period and calculate the predicted monthly growth rate of the product;

[0048] Step S3. Based on the product sales data, an e-commerce management evaluation model is constructed to calculate the predicted impact of return rate and satisfaction on the monthly sales growth rate;

[0049] Step S4: Extract the inventory of the product and calculate the quantity of the inventory product to be replenished.

[0050] Preferably, the specific implementation process of step S1 includes:

[0051] Build a product database, which is used to store sales data and inventory data of products of the same type. The sales data of products of the same type include the product's shelf life, sales volume, return rate and satisfaction; the inventory data of products of the same type is the inventory volume of the product.

[0052] Preferably, the specific implementation process of step S2 includes:

[0053] Step S21. Based on the product database, extract the sales data of the same type of products and construct the same type product set SU = {s m |m∈[1,M]}, where s m represents the sales data set of the mth product of the same type. The sales data set records the sales data of products of the same type. M represents the total number of products of the same type.

[0054] Based on the same category of products, predict the product shelf life: Among them, T m represents the shelf life in the sales dataset sm, and T represents the predicted shelf life of the product;

[0055] Step S22. Based on the predicted shelf life of the product, extract the sales data set with the same predicted shelf life from the same category product set SU, and construct the same period product set PU = {s n |n∈[1,N]}, where s n represents the sales dataset of the nth product of the same category, and N represents the total number of sales datasets extracted from the product set SU of the same category;

[0056] Pre-process the sales volume of the product set PU in the same period and calculate the predicted monthly growth rate of the product: Among them, KP n |(t→t+1) represents the monthly growth rate of sales volume of the nth product of the same type from the tth month to the t+1th month, A t A represents the sales volume of the nth product of the same type in the tth month, t+1 represents the sales volume of the nth product of the same type in the t+1th month, and KP|(t→t+1) represents the predicted monthly growth rate of sales of all e-commerce products from the tth month to the t+1th month.

[0057] For example, an e-commerce merchant launches new clothes, and the clothes are of Gothic style. The sales data of clothes in Gothic style are extracted, and a product set of the same type SU = {s1, s2, s3, s4, s5, s6, s7, s8, s9, s10} is constructed;

[0058] Among them, the shelf life of the same type of products is {6, 7, 6, 5, 6, 8, 5, 5, 6, 6} respectively, so the predicted shelf life of the product is T = (6+7+6+5+6+8+5+5+6+6) / 10 = 6, so the predicted shelf life of the product is 6 months;

[0059] Through the predicted shelf life of the product, extract products with a shelf life of 6 months from the same type of product set, that is, extract products s1, s3, s4, s6, s10, and construct the same period product set, PU = {s1, s2, s3, s4, s5};

[0060] Extract the sales volume of each product in PU {3000, 5000, 9000, 16000, 5000, 3000}, {3001, 5000, 9000, 16010, 5000, 3000}, {3000, 5000, 9000, 16000, 5000, 3000}, {3089, 5090, 9050, 18780, 5000, 3000}, {3000, 5000, 9000, 16000, 5000, 3000}, and calculate the monthly growth rate {66.67%, 80%, 77.7 7%, -56.25%, -40%}, {66.61%, 80%, 78.89%, -56.83%, -40%}, {64.78%, 80%, 77.77%, -56.25%, -40%}, {66.67%, 77.80%, 107.51%, -73.37%, -40%}, {66.67%, 80%, 77.77%, -56.25%, -40%}; the predicted monthly growth rate of the product is {66.28%, 79.56%, 83.94%, 59.79%, 40%}.

[0061] Preferably, the specific implementation process of step S3 includes:

[0062] Step S31. Based on the same category product set SU, predict the first month sales volume of the product: Among them, a represents the first month's predicted sales volume of the product, A 1m represents the first month sales volume of the mth product of the same type;

[0063] Step S32. Construct an e-commerce management evaluation model: L = w1g(d)+w2h(x)+b1, Among them, L represents the predicted impact of return rate and satisfaction on the monthly sales growth rate, d represents the return rate, x represents the satisfaction, w1, w2, w3, w4 represent the preset risk coefficients, b1, b2, b3 represent the preset error coefficients, and D represents the preset return rate threshold.

[0064] Preferably, the specific implementation process of step S4 includes:

[0065] Extract the inventory of the product and calculate the number of inventory products to be replenished: F = GH-OL, GH = J*[KP|(t→t+1)×(1-L)+z+1], where GH represents the estimated inventory required in the t+1th month, J represents the actual sales volume of the product in the tth month, 0L represents the inventory of the product, and z represents the preset percentage of spare inventory.

[0066] For example: preset value z=0.6, t=3, inventory 0L=300, actual sales volume in the third month J=2000, predicted impact of return rate and satisfaction on sales growth rate L=0.1, growth rate KP|(3→4)=83.94%, then the number of inventory products to be replenished F=2000*[0.8394*(1-0.1)+0.6+1]-300=4411.

[0067] An e-commerce management data processing system based on big data analysis, the system includes: a data storage module, a product forecasting module, an e-commerce management evaluation module and an inventory replenishment module;

[0068] A data storage module, used to build a product database, which includes product sales data and product inventory data;

[0069] The product forecasting module is used to build a set of products of the same type and predict the shelf life of products. Based on the shelf life of products, a set of products with the same cycle is built to calculate the monthly growth rate forecast of products.

[0070] The e-commerce management evaluation module builds an e-commerce management evaluation model based on product sales data and calculates the impact of return rate and satisfaction on the predicted monthly sales growth rate;

[0071] The inventory replenishment module is used to extract the inventory quantity of the product and calculate the quantity of the inventory products to be replenished.

[0072] Specifically, the data storage module constructs a product database, which is used to store sales data and inventory data of products of the same type. The sales data of products of the same type include the product's shelf life, sales volume, return rate and satisfaction; the inventory data of products of the same type is the inventory volume of the product.

[0073] Specifically, the product forecasting module includes a shelf cycle unit and a monthly growth rate forecasting unit;

[0074] Shelf cycle unit, based on the product database, extracts the sales data of the same type of products and constructs the same type of product set SU = {s m |m∈[1,M]}, where s m represents the sales data set of the mth product of the same category. The sales data set records the sales data of products of the same category. M represents the total number of products of the same category. Based on the product set of the same category, the product shelf life is predicted: Where T m Represents the sales dataset s m In the shelf cycle, T represents the predicted shelf cycle of the product; based on the predicted shelf cycle of the product, the sales data set with the same predicted shelf cycle is extracted from the same type of product set SU, and the same cycle product set PU is constructed. n |n∈[1,N]}, where s n represents the sales dataset of the nth product of the same category, and N represents the total number of sales datasets extracted from the product set SU of the same category;

[0075] The monthly growth rate prediction unit is used to pre-process the sales volume of the product set PU in the same period and calculate the monthly growth rate prediction value of the product: Among them, KP n |(t→t+1) represents the monthly growth rate of sales volume of the nth product of the same type from the tth month to the t+1th month, A t A represents the sales volume of the nth product of the same type in the tth month, t+1 represents the sales volume of the nth product of the same type in the t+1th month, and KP|(t→t+1) represents the predicted monthly growth rate of sales of all e-commerce products from the tth month to the t+1th month.

[0076] Specifically, the e-commerce management evaluation module includes the first month sales volume unit and the model unit;

[0077] The first month sales unit predicts the first month sales of a product based on the same category product set SU: Among them, a represents the first month's predicted sales volume of the product, A 1m represents the first month sales volume of the mth product of the same type;

[0078] Model unit, construct e-commerce management evaluation model: L = w1g(d) + w2h(x) + b1, Among them, L represents the predicted impact of return rate and satisfaction on the monthly sales growth rate, d represents the return rate, x represents the satisfaction, w1, w2, w3, w4 represent the preset risk coefficients, b1, b2, b3 represent the preset error coefficients, and D represents the preset return rate threshold.

[0079] Specifically, the inventory replenishment module calculates the number of inventory products to be replenished by extracting the inventory of the product: F=GH-0L, GH=J*[KP|(t→t+1)×(1-L)+z+1], where GH represents the estimated required inventory in the t+1th month, J represents the actual sales volume of the product in the tth month, OL represents the inventory of the product, and z represents the preset spare inventory percentage.

[0080] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0081] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An e-commerce management data processing method based on big data analysis, characterized in that: The method comprises the following steps: Step S1. Build a product database, the product database includes product sales data and product inventory data; Step S2. Based on the product database, construct a set of products of the same type and predict the product's shelf life; based on the product's shelf life, construct a set of products of the same period and calculate the predicted monthly growth rate of the product; Step S3. Based on the product sales data, an e-commerce management evaluation model is constructed to calculate the predicted impact of return rate and satisfaction on the monthly sales growth rate; Step S4: Extract the inventory of the product and calculate the quantity of the inventory product to be replenished.

2. The e-commerce management data processing method based on big data analysis according to claim 1 is characterized in that: The specific implementation process of step S1 includes: Construct a product database, which is used to store sales data and inventory data of products of the same type. The sales data of products of the same type include the shelf life, sales volume, return rate and satisfaction of the products; the inventory data of products of the same type is the inventory volume of the products.

3. The e-commerce management data processing method based on big data analysis according to claim 2 is characterized in that: The specific implementation process of step S2 includes: Step S21. Based on the product database, extract the sales data of the same type of products and construct the same type product set SU = {s m |m∈[1,M]}, where s m represents the sales data set of the mth product of the same category, wherein the sales data set records the sales data of products of the same category, and M represents the total number of products of the same category; Based on the same category of products, predict the product shelf life: Among them, T m Represents the sales dataset s m In the shelf cycle, T represents the predicted shelf cycle of the product; Step S22. Based on the predicted shelf life of the product, extract the sales data set with the same predicted shelf life from the same category product set SU, and construct the same cycle product set PU = {s n |n∈[1,N]}, where s n represents the sales dataset of the nth product of the same category, and N represents the total number of sales datasets extracted from the product set SU of the same category; Pre-process the sales volume of the product set PU in the same period and calculate the predicted monthly growth rate of the product: Among them, KP n |(t→t+1) represents the monthly growth rate of sales volume of the nth product of the same type from the tth month to the t+1th month, A t A represents the sales volume of the nth product of the same type in the tth month, t+1 represents the sales volume of the nth product of the same type in the t+1th month, and KP|(t→t+1) represents the predicted monthly growth rate of sales of all e-commerce products from the tth month to the t+1th month.

4. The e-commerce management data processing method based on big data analysis according to claim 3 is characterized in that: The specific implementation process of step S3 includes: Step S31. Based on the same category product set SU, predict the first month sales volume of the product: Among them, a represents the first month's predicted sales volume of the product, A 1m represents the first month sales volume of the mth product of the same type; Step S32. Construct an e-commerce management evaluation model: L = w1g(d)+w2h(x)+b1, Among them, L represents the predicted impact of return rate and satisfaction on the monthly sales growth rate, d represents the return rate, x represents the satisfaction, w1, w2, w3, w4 represent the preset risk coefficients, b1, b2, b3 represent the preset error coefficients, and D represents the preset return rate threshold.

5. The e-commerce management data processing method based on big data analysis according to claim 4 is characterized in that: The specific implementation process of step S4 includes: Extract the inventory of the product and calculate the number of inventory products to be replenished: F = GH-OL, GH=J*[KP|(t→t+1)×(1-L)+z+1], where GH represents the estimated inventory required in the t+1th month, J represents the actual sales volume of the product in the tth month, OL represents the inventory of the product, and z represents the preset percentage of spare inventory.

6. E-commerce management data processing system based on big data analysis, characterized in that: The system includes: a data storage module, a product forecasting module, an e-commerce management and evaluation module, and an inventory replenishment module; The data storage module is used to construct a product database, which includes product sales data and product inventory data; The product prediction module is used to construct a set of products of the same type and predict the shelf life of the products; based on the shelf life of the products, a set of products of the same period is constructed to calculate the monthly growth rate forecast value of the products; The e-commerce management evaluation module constructs an e-commerce management evaluation model through product sales data to calculate the predicted impact of return rate and satisfaction on the monthly sales growth rate; The inventory replenishment module is used to extract the inventory quantity of the product and calculate the quantity of the inventory product to be replenished.

7. The e-commerce management data processing system based on big data analysis according to claim 6 is characterized by: The data storage module constructs a product database, which is used to store sales data and inventory data of products of the same type. The sales data of products of the same type include the shelf life, sales volume, return rate and satisfaction of the products; the inventory data of products of the same type is the inventory volume of the products.

8. The e-commerce management data processing system based on big data analysis according to claim 7 is characterized by: The product prediction module includes a shelf cycle unit and a monthly growth rate prediction unit; The shelf cycle unit extracts the sales data of the same type of products based on the product database and constructs a product set SU of the same type = {s m |m∈[1,M]}, where s m represents the sales data set of the mth product of the same category, in which the sales data set records the sales data of products of the same category, and M represents the total number of products of the same category; based on the product set of the same category, the shelf life of the product is predicted: Where T m Represents the sales dataset s m In the shelf cycle, T represents the predicted shelf cycle of the product; based on the predicted shelf cycle of the product, the sales data set with the same predicted shelf cycle is extracted from the same type of product set SU, and the same cycle product set PU is constructed. n |n∈[1,N]}, where s n represents the sales dataset of the nth product of the same category, and N represents the total number of sales datasets extracted from the product set SU of the same category; The monthly growth rate prediction unit is used to pre-process the sales volume of the product set PU in the same period and calculate the monthly growth rate prediction value of the product: Among them, KP n |(t→t+1) represents the monthly growth rate of sales volume of the nth same type of product from the tth month to the t+1th month, At represents the sales volume of the nth same type of product in the tth month, A t+1 represents the sales volume of the nth product of the same type in the t+1th month, and KP|(t→t+1) represents the predicted monthly growth rate of sales of all e-commerce products from the tth month to the t+1th month.

9. The e-commerce management data processing system based on big data analysis according to claim 8, characterized in that: The e-commerce management evaluation module includes a first month sales volume unit and a model unit; The first month sales unit predicts the first month sales of a product based on the same category product set SU: Among them, a represents the first month's predicted sales volume of the product, A 1m represents the first month sales volume of the mth product of the same type; The model unit constructs an e-commerce management evaluation model: L = w1g(d)+w2h(x)+b1, Among them, L represents the predicted impact of return rate and satisfaction on the monthly sales growth rate, d represents the return rate, x represents the satisfaction, w1, w2, w3, w4 represent the preset risk coefficients, b1, b2, b3 represent the preset error coefficients, and D represents the preset return rate threshold.

10. The e-commerce management data processing system based on big data analysis according to claim 9, characterized in that: The inventory replenishment module calculates the number of inventory products to be replenished by extracting the inventory of the product: F = GH-OL, GH=J*[KP|(t→t+1)×(1-L)+z+1], where GH represents the estimated inventory required in the t+1th month, J represents the actual sales volume of the product in the tth month, OL represents the inventory of the product, and z represents the preset percentage of spare inventory.

Images