E-commerce platform profit analysis method and system, and commodity management method

Abstract

The invention discloses an e-commerce platform profit analysis method and system and a commodity management method. The method comprises the steps of obtaining commodity data and order data of an e-commerce platform by using a timed task, updating or newly adding the commodity data to a first database according to the number of a commodity, and updating or newly adding the order data to a second database table according to the number of an order. And performing integration processing on the data of the first database table and the second database table, and performing calculation through a preset big data model to obtain a new and old customer ratio, an actual cost price and an actual profit of the e-commerce platform. And carrying out weighted analysis on the new and old customer growth rates, the actual cost prices and the actual profits of different e-commerce platforms, and outputting a customer change-profit expectation trend analysis result of the e-commerce platform. Compared with the prior art, the method has the advantages that the relation between data is analyzed, and the cost fluctuation of the commodity can be mastered in time.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and more specifically, to an e-commerce platform profit analysis method and system, and a commodity management method. Background Art

[0002] In the current wave of digital marketing, users prefer to shop on large e-commerce platforms with many big brands and user bases. To cater to the wave of digital marketing, many companies or merchants also prefer to set up official flagship stores on these large e-commerce platforms in order to deeply reach different consumer groups and expand sales channels.

[0003] However, although many large e-commerce platforms have a massive user base, their respective e-commerce systems are relatively independent, forming fragmented information islands. As a result, product information and transaction orders cannot be uniformly managed and updated synchronously across platforms, which consumes a huge amount of time and energy of the operation management team in product cost accounting and data comparison, reduces operational efficiency, affects the timeliness of the team's control and response to product prices, and restricts the optimization and upgrading of the overall business process. In particular, for products such as fresh fruits and vegetables that are more sensitive to cost fluctuations, slow response efficiency will cause merchants to suffer greater profit losses.

[0004] The prior art discloses a cross-platform real-time report realization method, device, computer equipment and medium, which uses a configured SAPSLT server to establish a communication link with the source system, and synchronizes the report data in the source system to the target system in real time through the SAPSLT server, and then publishes the report data in a visual form by the report server, so that the report data can be viewed in real time as needed, meeting the need of the report end to view real-time data. The defect of this solution is that although the report data intercommunication and visual display between multiple different systems are realized, the connection between the data is not analyzed, and the merchant team cannot more intuitively understand the cost fluctuation trend of the goods, so as to arrange a more reasonable sales plan.

[0005] To this end, in combination with the above requirements and the defects of the existing technology, this application proposes an e-commerce platform profit analysis method and system, and a product management method. Summary of the invention

[0006] The present invention provides an e-commerce platform profit analysis method and system, and a commodity management method, which can timely grasp the cost fluctuations of commodities and dynamically adjust the allocation amount of platform commodities according to the contribution of new and old customers to the profits of the e-commerce platform.

[0007] The primary purpose of the present invention is to solve the above technical problems. The technical solution of the present invention is as follows:

[0008] A first aspect of the present invention provides an e-commerce platform profit analysis method, the method comprising the following steps:

[0009] S1. Use a scheduled task to obtain product data and order data from the e-commerce platform, update or add product data to the first database according to the product number, and update or add order data to the second database table according to the order number.

[0010] S2. Integrate and process the data in the first database table and the second database table, and calculate through a preset big data model to obtain the proportion of new and old customers, actual cost price and actual profit of the e-commerce platform.

[0011] S3. Conduct a weighted analysis on the growth rate of new and old customers, actual cost price and actual profit of different e-commerce platforms, and output the customer change-profit expectation trend analysis results of the e-commerce platforms.

[0012] Furthermore, the specific process of step S1 is: classify the product data and order data, determine whether there is a standard product unit of the product in the first database table according to the product number, and update or add it, update or add the order data in the second database table based on the order number, and circulate the inventory unit list of the product in the first database and the second database to update the inventory and cost information of the product.

[0013] Furthermore, the specific process of step S2 is: obtaining supplier information, product information and customer order information from the first database and the second database, calculating the actual cost information of the product based on the supplier information and product information, dividing the customer order information into new customer order information and old customer order information, inputting a preset big data model for calculation, outputting the actual profit of each product on different e-commerce platforms, and calculating the growth rate of new and old customers through the following formula:

[0014]

[0015] Among them, G n represents the growth rate of new customers, G o represents the growth rate of old customers, a represents the number of new customers, b represents the number of old customers, T represents the current time period, and T-1 represents the previous time period.

[0016] Furthermore, the specific process of step S3 is to calculate the profit contributed by new and old customers based on the growth rate, order data and profit margin of new and old customers, use time series analysis and regression analysis to make profit forecasts, and conduct sensitivity analysis on the impact of the growth rate of new and old customers, purchase frequency and profit margin on the actual profit of the e-commerce platform, and adjust the parameters of the profit forecast formula.

[0017] Furthermore, the following formula is used to calculate the customer change-profit expectation trend:

[0018] D=QK

[0019] First, calculate the actual profit of the e-commerce platform, where D represents the actual profit, Q represents the total price of orders from new and old customers, and K represents the actual cost of the calculated goods. Then calculate the profit margin contributed by new and old customers according to the following formula:

[0020]

[0021] R nc,i +R oc,i =D i

[0022] Where P represents the predicted total profit margin, n represents the number of e-commerce platforms, and W nc represents the weight of the preset new customer growth rate, G nc,i represents the growth rate of new customers of the i-th e-commerce platform, R nc,i represents the profit contributed by new customers of the i-th e-commerce platform, C nc,i represents the actual cost of a new customer on the ith e-commerce platform, W oc Represents the weight of the preset old customer growth rate, G oc,i represents the growth rate of old customers of the i-th e-commerce platform, R oc,i represents the profit contributed by old customers of the i-th e-commerce platform, C oc,i represents the actual cost of old customers of the i-th e-commerce platform, Q i represents the total price of new and old customer orders on the i-th e-commerce platform, K i Represents the actual cost of goods on the i-th e-commerce platform; finally, combined with the daily fluctuations in commodity costs, output the customer change-profit expectation trend analysis results.

[0023] The second aspect of the present invention provides an e-commerce platform profit analysis system, which is used for the e-commerce platform profit analysis method, and includes: a product order information collection module, a data processing module, and a profit analysis module.

[0024] The commodity order information collection module uses a scheduled task to obtain commodity data and order data of the e-commerce platform, updates or adds commodity data to the first database according to the commodity number, and updates or adds order data to the second database table according to the order number; the data processing module integrates and processes the data of the first database table and the second database table, and calculates through a preset big data model to obtain the proportion of new and old customers, actual cost price and actual profit of the e-commerce platform; the profit analysis module performs a weighted analysis on the growth rate of new and old customers, actual cost price and actual profit of different e-commerce platforms, and outputs the customer change-profit expectation trend analysis results of the e-commerce platform.

[0025] The third aspect of the present invention provides a commodity management method, which specifically comprises: using the customer change-profit expectation trend analysis results obtained by the e-commerce platform profit analysis method, adjusting the market strategy of the e-commerce platform, building a feedback mechanism, and dynamically adjusting the number of commodities put on the e-commerce platform.

[0026] Furthermore, the feedback mechanism is specifically as follows: the purchase price of the goods is updated instantly through real-time tasks, and the actual cost price is calculated based on the distribution cost, the historical cost fluctuation curve is summarized, and the time intervals of high and low sales of goods are predicted using a time series-based cost forecasting method. The profit margin calculation weights contributed by new and old customers are adjusted in combination with the customer change-profit expectation trend analysis results, and the market strategy and product pricing of the e-commerce platform are adjusted.

[0027] Furthermore, the market strategy of the e-commerce platform is adjusted according to the customer change-profit expectation trend analysis results as follows: first, determine whether the profits contributed by new and old customers are greater than the preset threshold. If both are greater than the preset threshold and the profit expectation trend is benign, the e-commerce platform strategy is adjusted to the first type; if the profits contributed by new customers are less than the preset threshold, and the profits contributed by old customers are greater than the preset threshold, and the profit expectation trend is benign, the e-commerce platform strategy is adjusted to the second type; if both are less than the preset threshold, but the profit expectation trend is benign, the e-commerce platform strategy is adjusted to the third type; if both are less than the preset threshold and the profit expectation trend is bad, the e-commerce platform strategy is adjusted to the fourth type.

[0028] Furthermore, the first type is: adding new varieties of goods, and increasing the allocation share of the old goods categories of the e-commerce platform; the second type is: launching new varieties of goods for pilot testing, launching discount activities for new customers, and increasing the goods allocation share of the e-commerce platform; the third type is: launching new varieties of goods for pilot testing, and setting up discount activities for new and old users respectively, and reducing the allocation share of old goods categories; the fourth type is: reducing the allocation share of old goods categories, increasing the discount intensity for old customers and the next-day discount intensity for new customers, and randomly canceling old goods and adding new varieties of goods.

[0029] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0030] The present invention provides a profit analysis method and system for an e-commerce platform, and a commodity management method. By acquiring commodity and order data through scheduled tasks, the actual cost of commodities with a short shelf life can be timely grasped, and then the sales share of commodities on the e-commerce platform can be reasonably adjusted; the actual needs of customers of the e-commerce platform can be abstractly analyzed, and decision-making suggestions for merchants to adjust the supply strategy of the e-commerce platform can be provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 The present invention is a flow chart of an e-commerce platform profit analysis method.

[0032] Figure 2 The present invention is a flowchart for obtaining commodity data in an embodiment of the present invention.

[0033] Figure 3 The present invention is a flowchart of obtaining order data in an embodiment of the present invention.

[0034] Figure 4 This is a schematic diagram of an e-commerce platform profit analysis system of the present invention.

[0035] Figure 5 This is a calculation diagram of the mapping relationship between commodity supply quantity and cost price in one embodiment of the present invention.

[0036] Figure 6 The present invention is a flowchart of a commodity management method. DETAILED DESCRIPTION

[0037] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0038] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0039] Example 1

[0040] like Figure 1 As shown, the present invention provides an e-commerce platform profit analysis method, which includes the following steps:

[0041] S1. Use a scheduled task to obtain product data and order data from an e-commerce platform, wherein the product data includes a product list and product details information, and the order data includes an order list and order details information. The product data is updated or added to the first database according to the product number, and the order data is updated or added to the second database table according to the order number.

[0042] S2. Integrate and process the data in the first database table and the second database table, and calculate through a preset big data model to obtain the proportion of new and old customers, actual cost price and actual profit of the e-commerce platform.

[0043] S3. Conduct a weighted analysis on the growth rate of new and old customers, actual cost price and actual profit of different e-commerce platforms, and output the customer change-profit expectation trend analysis results of the e-commerce platforms.

[0044] Based on the above technical features, the actual cost of goods with a short shelf life can be grasped in a timely manner. Combined with the profit prediction formula, the actual customer demand of the e-commerce platform can be abstractly analyzed, and decision-making recommendations are provided for merchants to adjust the supply strategy of the e-commerce platform.

[0045] The specific process of step S1 is: classify the product data and order data, determine whether there is a standard product unit of the product in the first database table according to the product number, and update or add it, update or add the order data in the second database table based on the order number, and circulate the inventory unit list of the product in the first database and the second database to update the inventory and cost information of the product.

[0046] In a specific embodiment, the process of obtaining the product list information of the e-commerce platform is as follows: Figure 2 As shown, firstly, a scheduled task is used to obtain the product list and details through the APIs of e-commerce platform A and e-commerce platform B to obtain the SPU (Standard Product Unit) of all products.

[0047] Determine whether the product SPU (Standard Product Unit) already exists in the database table tb_pull_spu according to the product_id of the product. If it does, update the information of the product SPU in the tb_pull_spu table; if it does not exist, add the information of the product SPU in the tb_pull_spu table to perform an update or addition operation.

[0048] The SKU (Stock Keeping Unit) list of the circulating goods is updated or newly added through the database table tb_pull_sku, and further judged whether the SKU goods have records. If so, the SKU information of the goods in the tb_pull_spu table is updated; if not, the SKU information of the goods is added to the tb_pull_sku table.

[0049] The process of obtaining order information from e-commerce platforms is as follows: Figure 3 As shown, the process of obtaining the order list and details through the order API of e-commerce platform A and e-commerce platform B is: call the e-commerce platform A-order and e-commerce platform B open platform-order API, obtain the order list interface, and obtain the orders with status changes on the video account.

[0050] First, determine whether there is an order with order status in the interface return. If yes (Y), proceed to the next step; if no (N), end the process.

[0051] Call the Order API - Get Order Details interface to obtain the order details of each order and determine whether the order information already exists. If so (Y), update the order data to the database table tb_pull_order based on the order_id of the order; if not (N), add the order data to the database table tb_pull_order based on the order_id of the order.

[0052] Traverse the product_infos field (order product information list) in the order details, determine whether the order details information already exists in the tb_pull_order_sku_info table, and update or add the order product information to the database table tb_pull_order_sku_info.

[0053] It should be noted that when product information is updated frequently, the following solution is used to optimize data acquisition:

[0054] A phased optimization strategy is adopted, from the scheduled synchronization in the original stage, to the introduction of a blacklist mechanism to avoid invalid synchronization, to the use of multi-threading to improve synchronization efficiency, and finally data sharding processing to ensure the efficiency and accuracy of data synchronization. For example, the introduction of a blacklist mechanism in the second stage can effectively avoid repeated synchronization attempts caused by inaccessible services.

[0055] By analyzing Binlog, invalid data update operations can be identified and reduced, for example, a large number of Binlog files generated only due to time field updates can be avoided. By optimizing code logic and reducing meaningless update operations, the database IO pressure can be significantly reduced.

[0056] Adopt asynchronous processing mechanism, reasonably set cache level, and dynamically adjust cache strategy to reduce the number of database accesses and improve data access speed. Implement transaction management and adopt the final consistency model to ensure the security of data operations and data consistency.

[0057] Use appropriate timestamp design when creating tables, such as using the CURRENT_TIMESTAMP default value and ONUPDATE CURRENT_TIMESTAMP, to reduce unnecessary time field updates and thus reduce Binlog generation.

[0058] The specific process of step S2 is: obtaining supplier information, product information and customer order information from the first database and the second database, calculating the actual cost information of the product based on the supplier information and product information, dividing the customer order information into new customer order information and old customer order information, inputting the preset big data model for calculation, outputting the actual profit of each product on different e-commerce platforms, and calculating the growth rate of new and old customers through the following formula:

[0059]

[0060] Among them, G n represents the growth rate of old customers, G o represents the growth rate of old customers, a represents the number of new customers, b represents the number of old customers, T represents the current time period, and T-1 represents the previous time period.

[0061] In this embodiment, the big data model is specifically any one of TabNet and CatBoost;

[0062] When pre-training the model, we first extract product data and order data from the historical database, and perform feature engineering to obtain training and validation data sets. We then use cross entropy loss to train and validate the big data model using the training and validation data sets to obtain a pre-trained big data model.

[0063] The specific process of step S3 is: calculate the profit contributed by new and old customers according to the growth rate, order data and profit margin of new and old customers, use time series analysis and regression analysis to make profit forecasts, and adjust the parameters of the profit forecast formula by performing sensitivity analysis on the impact of the growth rate, purchase frequency and profit margin of new and old customers on the actual profit of the e-commerce platform.

[0064] In a specific embodiment, the process of obtaining the mapping relationship between sku and cost price is as follows: Figure 5As shown, first query the product information obtained by S101 and S102 to form a product list. The user selects a product SPU to obtain a list of all SKUs under the SPU. The user selects one or more product SKUs from the SKU list. Entering the cost price setting page, the user can set the supplier and cost price for the selected product SKU. The user clicks the "Export sku cost price" button to import the sku and cost price from the Excel file. Complete the mapping relationship between sku and cost price. According to S101, S102, S103, and S104, obtain product information, order information, and cost price information, and associate this information through the product ID; the flowchart on the right shows the relationship between product ID, product information, cost price information, and order information, and finally obtains the sales volume, actual cost, and profit of the product.

[0065] The following formula is used to calculate the customer change-profit expectation trend:

[0066] D=QK

[0067] First, calculate the actual profit of the e-commerce platform, where D represents the actual profit, Q represents the total price of orders from new and old customers, and K represents the actual cost of the calculated goods. Then calculate the profit margin contributed by new and old customers according to the following formula:

[0068]

[0069] R nc,i +R oc,i =D i

[0070] Where P represents the predicted total profit margin, n represents the number of e-commerce platforms, and W nc represents the weight of the preset new customer growth rate, G nc,i represents the growth rate of new customers of the i-th e-commerce platform, R nc,i represents the profit contributed by new customers of the i-th e-commerce platform, C nc,i represents the actual cost of a new customer on the ith e-commerce platform, W oc Represents the weight of the preset old customer growth rate, G oc,i represents the growth rate of old customers of the i-th e-commerce platform, R oc,i represents the profit contributed by old customers of the i-th e-commerce platform, C oc,i represents the actual cost of old customers of the i-th e-commerce platform, Q i represents the total price of new and old customer orders on the i-th e-commerce platform, K i Represents the actual cost of goods on the i-th e-commerce platform; finally, combined with the daily fluctuations in commodity costs, output the customer change-profit expectation trend analysis results.

[0071] It should be noted that the profit forecasting formula can more accurately predict the profit change trend of the e-commerce platform by comprehensively considering the growth rate, profit margin, actual cost and total order price of new and old customers.

[0072] In a specific embodiment, suppliers can be added in the system background, and the database table tb_brand can be used to determine whether the supplier name already exists. All product SPUs and SKUs of e-commerce platform A and e-commerce platform B can be viewed, and exports and cost price settings can be performed. All order data and order cost prices can be viewed, and order lists and after-sales order lists can be batch exported.

[0073] According to the above technical features, the present invention can timely grasp the cost fluctuations of commodities, and dynamically adjust the allocation amount of platform commodities according to the contribution of new and old customers to the profits of the e-commerce platform, thereby solving the problem that the merchant team cannot more intuitively understand the cost fluctuation trend of commodities.

[0074] Example 2

[0075] Based on the above embodiment 1, combined with Figure 4 This embodiment describes in detail the specific contents of an e-commerce platform profit analysis system of the present invention.

[0076] The e-commerce platform profit analysis system is as follows: Figure 4 As shown, it includes: commodity order information collection module, data processing module, and profit analysis module.

[0077] The commodity order information collection module uses a scheduled task to obtain commodity data and order data of the e-commerce platform, updates or adds commodity data to the first database according to the commodity number, and updates or adds order data to the second database table according to the order number; the data processing module integrates and processes the data of the first database table and the second database table, and calculates through a preset big data model to obtain the proportion of new and old customers, actual cost price and actual profit of the e-commerce platform; the profit analysis module performs a weighted analysis on the growth rate of new and old customers, actual cost price and actual profit of different e-commerce platforms, and outputs the customer change-profit expectation trend analysis results of the e-commerce platform.

[0078] Example 3

[0079] like Figure 6 As shown, the present invention also provides a commodity management method, which specifically comprises: using the customer change-profit expectation trend analysis results obtained by the profit analysis method of an e-commerce platform, adjusting the market strategy of the e-commerce platform, building a feedback mechanism, and dynamically adjusting the number of commodities put on the e-commerce platform.

[0080] The feedback mechanism is specifically as follows: the purchase price of the goods is updated instantly through real-time tasks, and the actual cost price is calculated based on the distribution cost, the historical cost fluctuation curve is summarized, and the time intervals of high and low sales of goods are predicted using a time series-based cost forecasting method. The profit margin calculation weights contributed by new and old customers are adjusted in combination with the customer change-profit expectation trend analysis results, and the market strategy and product pricing of the e-commerce platform are adjusted.

[0081] In a specific embodiment, the purchase price of the product is updated instantly through the real-time task, the actual cost price is calculated according to the distribution cost, the historical cost fluctuation curve is summarized, and the time interval of high and low sales volume of the product is predicted by the cost prediction method based on the time series. The specific contents are:

[0082] First, collect and record historical data related to commodity costs, including raw material prices, production costs, transportation costs, etc. Through these data, analyze the trend of cost changes over time. Secondly, the data is differentiated to eliminate trend and seasonal factors, and then autoregression and moving average are used to build a model, and the mean square error (MSE) or root mean square error (RMSE) is used to measure the prediction error of the model.

[0083] The time series-based cost prediction method is an LSTM (Long Short-Term Memory Network) model. The model is based on historical sales data and external factors that may affect sales, such as holidays, promotional activities, etc., to calculate high-sales time periods and low-sales time periods based on the historical sales data. The following formula is used for deduction:

[0084]

[0085] i t =σ(W·[x t ,h t-1 ]+b)

[0086]

[0087] o t =σ(W·[x t ,h t-1 ]+b)

[0088] h t =o t *tanh(C t )

[0089] Among them, x t is the input at time step t, h t is the hidden state at time step t, C t is the memory unit at time step t, W and b are weight and bias parameters, and σ is the sigmoid activation function.

[0090] According to the above formula, first, it is necessary to collect historical sales data of the e-commerce platform, including sales volume, timestamps, promotional activities, seasonal factors and other factors that may affect sales volume. These data need to be cleaned, processed and converted into a format acceptable to the model. The processed data is converted into a format suitable for the LSTM model, where X is the past sales data and y is the sales forecast for the next time point. The LSTM model is trained using the prepared data set. After the training is completed, the LSTM model is used to predict future sales volume. Sales forecasts for continuous time periods can be generated, and the comparison between the forecast results and the actual sales volume can be displayed through visualization tools to evaluate the accuracy of the model.

[0091] Based on the high-sales time periods and low-sales time periods calculated by the model, merchants can arrange corresponding marketing methods or adjust inventory quantities and sales prices in advance to maximize profits.

[0092] The market strategy of the e-commerce platform is adjusted according to the results of the customer change-profit expectation trend analysis as follows: first, determine whether the profits contributed by new and old customers are greater than the preset threshold. If both are greater than the preset threshold and the profit expectation trend is benign, the e-commerce platform strategy is adjusted to the first type; if the profits contributed by new customers are less than the preset threshold, and the profits contributed by old customers are greater than the preset threshold, and the profit expectation trend is benign, the e-commerce platform strategy is adjusted to the second type; if both are less than the preset threshold, but the profit expectation trend is benign, the e-commerce platform strategy is adjusted to the third type; if both are less than the preset threshold and the profit expectation trend is bad, the e-commerce platform strategy is adjusted to the fourth type.

[0093] The first type is: adding new varieties of goods, increasing the allocation share of the old goods on the e-commerce platform; the second type is: launching new varieties of goods for pilot testing, launching discount activities for new customers, and increasing the goods allocation share of the e-commerce platform; the third type is: launching new varieties of goods for pilot testing, and setting up discount activities for new and old users respectively, reducing the allocation share of old goods; the fourth type is: reducing the allocation share of old goods, increasing the discount for old customers and the next-day discount for new customers, and randomly canceling old goods and adding new varieties of goods.

[0094] In a specific embodiment, firstly, customer data of the store is collected, including transaction records of new and old customers. The amount, time, and customer type (new or old) of each transaction are recorded. Secondly, customers are divided into new and old customers according to their purchase history. Among them, new customers refer to customers who purchase in the store for the first time, and old customers refer to customers who have previous purchase records. The increase and decrease trends of new and old customers are analyzed. This can be achieved by calculating the growth rate of new and old customers in a specific time period. Then the contribution of new and old customers to profits is calculated. This usually involves calculating the purchase frequency, average transaction amount and profit margin of each type of customer. The profit margin can be calculated by the difference between cost and income. According to the profit prediction formula, combined with the cost structure of the store (fixed cost and variable cost), the expected profit of the store is calculated. Among them, the total revenue can be decomposed into the revenue contributed by new customers and the revenue contributed by old customers. Sensitivity analysis is performed on the variables in the model to understand the impact of different factors (such as customer growth rate, purchase frequency, profit margin, etc.) on the store's profit. The store's operating data and market feedback are continuously monitored, and the profit calculation model and market strategy are adjusted according to the actual situation. Finally, a detailed analysis report is output, including data collection, analysis methods, prediction results and strategy recommendations.

[0095] According to the above technical features, the present invention can timely grasp the actual cost of goods with a short shelf life by obtaining goods and order data through scheduled tasks, and then reasonably adjust the sales share of goods on the e-commerce platform; it can perform abstract analysis on the actual needs of customers of the e-commerce platform, and provide decision-making suggestions for merchants to adjust the supply strategy of the e-commerce platform.

[0096] In the embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. A person of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium, which, when executed, executes the steps of the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media capable of storing program codes.

[0097] Alternatively, if the above-mentioned embodiments of the present invention are implemented in the form of software function modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media capable of storing program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0098] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. The icons describing the structural positional relationships in the accompanying drawings are only used for exemplary purposes and are not to be construed as limiting the present invention. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and is not possible to list all the embodiments here. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the scope of protection of the claims of the present invention.

Claims

1. A profit analysis method for an e-commerce platform, characterized in that: The following steps are involved: S1. Use a scheduled task to obtain product data and order data from the e-commerce platform, update or add product data to the first database according to the product number, and update or add order data to the second database table according to the order number; S2. Integrate and process the data in the first database table and the second database table, and calculate through a preset big data model to obtain the proportion of new and old customers, actual cost price and actual profit of the e-commerce platform; S3. Conduct a weighted analysis on the growth rate of new and old customers, actual cost price and actual profit of different e-commerce platforms, and output the customer change-profit expectation trend analysis results of the e-commerce platforms.

2. The profit analysis method of an e-commerce platform according to claim 1, characterized in that: The specific process of step S1 is: classify the product data and order data, determine whether there is a standard product unit of the product in the first database table according to the product number, and update or add it, update or add the order data in the second database table based on the order number, and circulate the inventory unit list of the product in the first database and the second database to update the inventory and cost information of the product.

3. The profit analysis method of an e-commerce platform according to claim 2, characterized in that: The specific process of step S2 is: obtaining supplier information, product information and customer order information from the first database and the second database, calculating the actual cost information of the product based on the supplier information and product information, dividing the customer order information into new customer order information and old customer order information, inputting the preset big data model for calculation, outputting the actual profit of each product on different e-commerce platforms, and calculating the growth rate of new and old customers through the following formula: Among them, G n represents the growth rate of new customers, G o represents the growth rate of old customers, a represents the number of new customers, b represents the number of old customers, T represents the current time period, and T-1 represents the previous time period.

4. The profit analysis method of an e-commerce platform according to claim 3, characterized in that: The specific process of step S3 is: calculate the profit contributed by new and old customers according to the growth rate, order data and profit margin of new and old customers, use time series analysis and regression analysis to make profit forecasts, and adjust the parameters of the profit forecast formula by performing sensitivity analysis on the impact of the growth rate, purchase frequency and profit margin of new and old customers on the actual profit of the e-commerce platform.

5. The profit analysis method of an e-commerce platform according to claim 4, characterized in that: The following formula is used to calculate the customer change-profit expectation trend: D=QK First, calculate the actual profit of the e-commerce platform, where D represents the actual profit, Q represents the total price of orders from new and old customers, and K represents the actual cost of the calculated goods. Then calculate the profit margin contributed by new and old customers according to the following formula: Rnc+Roc=D Where P represents the predicted total profit margin, n represents the number of e-commerce platforms, and W nc represents the weight of the preset new customer growth rate, G nc,i represents the growth rate of new customers of the i-th e-commerce platform, R nc,i represents the profit contributed by new customers of the i-th e-commerce platform, C nc,i represents the actual cost of a new customer on the ith e-commerce platform, W oc Represents the weight of the preset old customer growth rate, G oc,i represents the growth rate of old customers of the i-th e-commerce platform, R oc,i represents the profit contributed by old customers of the i-th e-commerce platform, C oc,i represents the actual cost of old customers of the i-th e-commerce platform, Q i represents the total price of new and old customer orders on the i-th e-commerce platform, K i Represents the actual cost of goods on the i-th e-commerce platform; finally, combined with the daily fluctuations in commodity costs, output the customer change-profit expectation trend analysis results.

6. An e-commerce platform profit analysis system, the system being used for an e-commerce platform profit analysis method as claimed in any one of claims 1 to 5, characterized in that: Including: commodity order information collection module, data processing module, profit analysis module; The commodity order information collection module uses a scheduled task to obtain commodity data and order data of the e-commerce platform, updates or adds commodity data to the first database according to the commodity number, and updates or adds order data to the second database table according to the order number; the data processing module integrates and processes the data of the first database table and the second database table, and calculates through a preset big data model to obtain the proportion of new and old customers, actual cost price and actual profit of the e-commerce platform; the profit analysis module performs a weighted analysis on the growth rate of new and old customers, actual cost price and actual profit of different e-commerce platforms, and outputs the customer change-profit expectation trend analysis results of the e-commerce platform.

7. A commodity management method, characterized in that: The customer change-profit expectation trend analysis results obtained by the e-commerce platform profit analysis method as described in any one of claims 1 to 5 are used to adjust the market strategy of the e-commerce platform, build a feedback mechanism, and dynamically adjust the number of products released on the e-commerce platform.

8. A commodity management method according to claim 7, characterized in that: The specific feedback mechanism is as follows: the purchase price of the goods is updated instantly through real-time tasks, and the actual cost price is calculated based on the distribution cost, the historical cost fluctuation curve is summarized, and the time intervals of high and low sales of goods are predicted using a time series-based cost forecasting method. Combined with the customer change-profit expectation trend analysis results, the profit margin calculation weights contributed by new and old customers are adjusted, and the market strategy and product pricing of the e-commerce platform are adjusted.

9. A commodity management method according to claim 8, characterized in that: The market strategy of the e-commerce platform is adjusted according to the results of the customer change-profit expectation trend analysis as follows: first, determine whether the profits contributed by new and old customers are greater than the preset threshold. If both are greater than the preset threshold and the profit expectation trend is benign, the e-commerce platform strategy is adjusted to the first type; if the profits contributed by new customers are less than the preset threshold, and the profits contributed by old customers are greater than the preset threshold, and the profit expectation trend is benign, the e-commerce platform strategy is adjusted to the second type; if both are less than the preset threshold, but the profit expectation trend is benign, the e-commerce platform strategy is adjusted to the third type; if both are less than the preset threshold and the profit expectation trend is bad, the e-commerce platform strategy is adjusted to the fourth type.

10. A commodity management method according to claim 9, characterized in that: The first type is: adding new varieties of goods, increasing the allocation share of the old goods on the e-commerce platform; the second type is: launching new varieties of goods for pilot testing, launching discount activities for new customers, and increasing the goods allocation share of the e-commerce platform; the third type is: launching new varieties of goods for pilot testing, and setting up discount activities for new and old users respectively, reducing the allocation share of old goods; the fourth type is: reducing the allocation share of old goods, increasing the discount for old customers and the next-day discount for new customers, and randomly canceling old goods and adding new varieties of goods.

Images