A cigarette supply chain management system based on big data analytics

Abstract

This invention relates to the field of cigarette supply, and more particularly to a cigarette supply chain management system based on big data analysis. The system includes a data acquisition module, a data storage module, a data analysis module, a visualization module, and a supply chain collaborative management module. The data acquisition module collects data from each stage of the cigarette supply chain, from raw material purchase to customer feedback. The data storage module stores the data. The data analysis module analyzes customer preferences. The visualization module displays the analysis results. The supply chain collaborative management module manages each part of the supply chain. This solution, by setting customer preference indicators for different retailers and for cigarettes produced by different manufacturers, helps users understand customer preferences and adjust the supply chain accordingly, catering to customer preferences as much as possible and thus improving overall profitability.

Description

Technical Field

[0001] This invention relates to the field of cigarette supply, and more particularly to a cigarette supply chain management system based on big data analysis. Background Technology

[0002] Big data analytics is a very popular data analysis technology that is widely used in various fields, and many supply chain systems have also adopted big data analytics.

[0003] For example, the prior art disclosed in CN114936818A is a smart electronic supply chain logistics big data AI management platform, an information entry system for entering supplier and customer information, including addresses; and a route network construction module for constructing the transportation route of goods between customers and suppliers based on the addresses entered in the information entry system and the input map information.

[0004] Another typical example is the existing technology disclosed in CN116739655B, which discloses an intelligent supply chain management method and system based on big data. This method includes: acquiring historical data of target stores; extracting data information corresponding to each historical period of the target stores from the historical data; evaluating the sales volume of the target stores in the current period; evaluating the impact of each out-of-stock item on the sales volume of the target stores based on the store influence value and predicted sales volume of each target store in the region, and obtaining the out-of-stock item with the lowest impact on the sales volume of the target stores in the region; adjusting the merchant's product supply chain in the region based on the target product number of the region and the predicted sales volume of each target store in the region; and transporting each of the merchant's products to the corresponding distribution center, which then transports the products to the corresponding target stores.

[0005] Let's look at an existing technology disclosed in WO2018068603A1, which discloses a supply chain management decision support system based on big data technology. It includes: an information acquisition module, used to extract data from big data sources, convert its format, and then send it to the analysis and processing module; an analysis and processing module, used to search for useful information from the data sent by the information acquisition module, integrate and analyze it, thereby providing analysis results; a visualization module, used to display the analysis results; and a support module, including a knowledge base, a textile classification database, and an access control submodule.

[0006] Currently, technologies that utilize big data to manage supply chains do not involve cigarette-related supply chains, nor do they manage supply chains based on cigarette-related big data. In order to solve the common problems in this field, this invention was made. Summary of the Invention

[0007] The purpose of this invention is to address the shortcomings of current systems by proposing a cigarette supply chain management system based on big data analysis.

[0008] To overcome the shortcomings of the prior art, the present invention adopts the following technical solution:

[0009] A cigarette supply chain management system based on big data analytics includes a data acquisition module, a data storage module, a data analysis module, a visualization module, and a supply chain collaborative management module. The data acquisition module collects data from each stage of the cigarette manufacturing process, from raw material purchase to customer feedback. The data storage module stores the data collected by the data acquisition module. The data analysis module analyzes customer preferences based on the data stored in the data storage module. The visualization module displays the analysis results of the data analysis module. The supply chain collaborative management module manages each part of the supply chain based on the analysis results of the data analysis module.

[0010] The data analysis module includes a preference index calculation module, which is used to calculate the customer's preference index for cigarettes produced by various manufacturers based on customer feedback. Users can then operate the supply chain collaborative management module based on the preference index to adjust the supply chain.

[0011] Furthermore, the supply chain includes suppliers, manufacturers, distributors, online retailers, and offline retailers. The online retailers sell cigarettes to users online and record reviews of the cigarettes, while the offline retailers sell cigarettes to users through physical stores and record user repurchase rates.

[0012] Furthermore, the data acquisition module includes a cost data acquisition unit, a production data acquisition unit, and an evaluation data acquisition unit. The cost data acquisition unit is used to collect production and sales costs for each part of the cigarette supply chain. The production data acquisition unit is used to obtain the supply volume of suppliers, the production volume of manufacturers, and the sales volume of online and offline retailers. The evaluation data acquisition unit is used to collect various evaluations from users.

[0013] Furthermore, the data storage module includes a data denoising unit, a classification and integration unit, and a database. The data denoising unit is used to denoise the data collected by the data acquisition unit, and the classification and integration unit is used to classify, integrate, and compress the denoised data into the database. The data analysis module includes a preference index calculation unit, a sales index calculation unit, and an instruction generation unit. The sales index calculation unit is used to calculate the sales indexes of various online and offline retailers, and the instruction generation unit is used to generate adjustment instructions to the supply chain collaborative management module based on the analysis results corresponding to the calculation results of the preference index calculation unit and the sales index calculation unit.

[0014] Furthermore, the supply chain collaborative management module includes a procurement quantity control unit, an order quantity control unit, a distribution control unit, and a logistics planning unit. The procurement quantity control unit is used to control the quantity of raw materials purchased from suppliers, the order quantity control unit is used to control the orders placed with the manufacturer, the distribution control unit is used to allocate the quantity of cigarettes to each retailer by the distributor within the scope permitted by the contract, and the logistics planning unit is used to plan logistics routes.

[0015] Furthermore, the workflow of the cigarette supply chain management system includes the following steps:

[0016] S1, the data acquisition module collects data from each process in the cigarette supply chain, from raw material purchase to customer feedback;

[0017] S2, the data storage module classifies and saves the data collected by the data acquisition module;

[0018] S3, the data analysis module receives the user's analysis instructions, extracts the corresponding data from the data storage module, and analyzes the customer's preference index for cigarettes produced by different manufacturers and the customer's preference index for different retailers.

[0019] S4, The visualization module displays the analysis results of the data analysis module;

[0020] S5: Users input various management parameters into the supply chain collaboration management module based on the preference indicators displayed in the visualization module, thereby managing the supply chain.

[0021] Furthermore, the workflow of the supply chain collaboration management module includes the following steps:

[0022] STEP1, the logistics planning unit plans the logistics routes based on the locations of various suppliers, manufacturers, distributors, online retailers and offline retailers;

[0023] STEP2, the purchase quantity control unit adjusts the quantity of raw materials purchased from suppliers based on the purchase quantity management parameters input by the user;

[0024] STEP3, the order quantity control unit adjusts the product order quantity from each manufacturer based on the order quantity management parameters input by the user;

[0025] STEP4, the distributor adjusts the quantity of products sent to online and offline retailers based on the distribution management parameters input by the user.

[0026] Furthermore, analyzing customer preference indicators for cigarettes produced by different manufacturers and for different retailers includes the following steps:

[0027] S31, Obtain historical ratings and reviews from customers on various online retailers on online retail platforms;

[0028] S32, obtain historical cigarette sales data from various offline retailers;

[0029] S33, calculate customer preference index for different retailers based on the acquired data.

[0030] S34. Calculate customer preference index for cigarettes produced by different manufacturers based on the acquired data.

[0031] The beneficial effects achieved by this invention are: 1. By setting customer preference indicators for different retailers and customer preference indicators for cigarettes produced by different manufacturers, it is beneficial for users to understand customer preferences and adjust the supply chain according to these preferences, so as to cater to customer preferences as much as possible and thus improve overall revenue.

[0032] 2. By setting preference adjustment weights, the influence of customer preferences for retailers on the calculation results can be reduced when calculating the cigarette preference index. This avoids misjudging customer preferences for cigarettes produced by different manufacturers during the analysis process due to customer bias, which is beneficial for users to adjust the order quantity from each manufacturer based on customer preference indexes for different cigarettes. Attached Figure Description

[0033] The invention will be further understood from the following description taken in conjunction with the accompanying drawings. The components in the drawings are not necessarily drawn to scale, but rather the emphasis is on illustrating the principles of the embodiments. In different views, the same reference numerals designate the same parts.

[0034] Figure 1 This is a schematic diagram of the structure of the present invention.

[0035] Figure 2 This is a flowchart of the process of the present invention.

[0036] Figure 3 This is a flowchart of the supply chain collaborative management module of the present invention.

[0037] Figure 4 The present invention provides a flowchart for analyzing customer preference indices for cigarettes produced by different manufacturers and customer preference indices for different retailers. Detailed Implementation

[0038] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can understand the advantages and effects of the present invention from the content disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and various details in this specification can also be modified and changed based on different viewpoints and applications without departing from the spirit of the present invention. Furthermore, the accompanying drawings of the present invention are for simple illustrative purposes only and are not depictions of actual dimensions; this is stated beforehand. The following embodiments will further describe the relevant technical content of the present invention in detail, but the disclosed content is not intended to limit the scope of protection of the present invention.

[0039] Example 1: According to Figure 1 , Figure 2 , Figure 3 and Figure 4 This embodiment provides 1. A cigarette supply chain management system based on big data analysis, characterized in that it includes a data acquisition module, a data storage module, a data analysis module, a visualization module, and a supply chain collaborative management module; the data acquisition module is used to collect data from each process of cigarette production from raw material purchase to customer feedback; the data storage module is used to store the data collected by the data acquisition module; the data analysis module is used to analyze customer preferences based on the data stored in the data storage module; the visualization module is used to display the analysis results of the data analysis module; and the supply chain collaborative management module is used to manage each part of the supply chain based on the analysis results of the data analysis module.

[0040] The data analysis module includes a preference index calculation module, which is used to calculate the customer's preference index for cigarettes produced by various manufacturers based on customer feedback. Users can then operate the supply chain collaborative management module based on the preference index to adjust the supply chain.

[0041] Specifically, the preference index is used to characterize the degree of customer liking for a retailer or cigarette. The higher the preference index, the more the customer likes the corresponding retailer or cigarette.

[0042] 2. The cigarette supply chain management system based on big data analysis according to claim 1, characterized in that the supply chain includes suppliers, manufacturers, distributors, online retailers and offline retailers, wherein the online retailers are used to sell cigarettes to users through the network and record evaluations of the cigarettes, and the offline retailers are used to sell cigarettes to users through offline stores and record user repurchase rates.

[0043] 3. A cigarette supply chain management system based on big data analysis according to claim 2, characterized in that the data acquisition module includes a cost data acquisition unit, a production data acquisition unit, and an evaluation data acquisition unit; the cost data acquisition unit is used to collect the production costs and sales costs of each part of the cigarette supply chain; the production data acquisition unit is used to obtain the supply volume of suppliers, the production volume of manufacturers, and the sales volume of online and offline retailers; and the evaluation data acquisition unit is used to collect various evaluations from users.

[0044] 4. A cigarette supply chain management system based on big data analysis according to claim 3, characterized in that the data storage module includes a data denoising unit, a classification and integration unit, and a database; the data denoising unit is used to denoise the data collected by the data acquisition unit; the classification and integration unit is used to classify and integrate the denoised data and compress it into the database; the data analysis module includes a preference index calculation unit, a sales index calculation unit, and an instruction generation unit; the sales index calculation unit is used to calculate the sales indexes of each online retailer and offline retailer; the instruction generation unit is used to generate adjustment instructions to the supply chain collaborative management module based on the analysis results corresponding to the calculation results of the preference index calculation unit and the sales index calculation unit.

[0045] Specifically, the sales indicators are used to represent sales performance; the higher the sales indicators, the better the cigarette sales performance.

[0046] 5. A cigarette supply chain management system based on big data analysis according to claim 4, characterized in that the supply chain collaborative management module includes a purchase quantity control unit, an order quantity control unit, a distribution control unit, and a logistics planning unit, wherein the purchase quantity control unit is used to control the quantity of raw materials purchased from suppliers, the order quantity control unit is used to control the orders placed with the manufacturer, the distribution control unit is used to allocate the quantity of cigarettes to each retailer by the distributor within the scope permitted by the contract, and the logistics planning unit is used to plan logistics routes.

[0047] 6. A cigarette supply chain management system based on big data analysis according to claim 5, characterized in that the workflow of the cigarette supply chain management system includes the following steps:

[0048] S1, the data acquisition module collects data from each process in the cigarette supply chain, from raw material purchase to customer feedback;

[0049] S2, the data storage module classifies and saves the data collected by the data acquisition module;

[0050] S3, the data analysis module receives the user's analysis instructions, extracts the corresponding data from the data storage module, and analyzes the customer's preference index for cigarettes produced by different manufacturers and the customer's preference index for different retailers.

[0051] S4, The visualization module displays the analysis results of the data analysis module;

[0052] S5: Users input various management parameters into the supply chain collaboration management module based on the preference indicators displayed in the visualization module, thereby managing the supply chain.

[0053] Specifically, users can adjust the number of orders placed with different manufacturers and the number of cigarettes given to different retailers based on customer preference indicators for cigarettes produced by different manufacturers and customer evaluations of different retailers. The specific operation method is to input the required management parameters into each unit of the supply chain collaboration management module in the management system, and each unit of the supply chain collaboration management module adjusts each part of the supply chain according to the management parameters.

[0054] 7. A cigarette supply chain management system based on big data analysis according to claim 6, characterized in that the workflow of the supply chain collaborative management module includes the following steps:

[0055] STEP1, the logistics planning unit plans the logistics routes based on the locations of various suppliers, manufacturers, distributors, online retailers and offline retailers;

[0056] Specifically, the route planning unit plans the logistics route using a route planning algorithm;

[0057] STEP2, the purchase quantity control unit adjusts the quantity of raw materials purchased from suppliers based on the purchase quantity management parameters input by the user;

[0058] STEP3, the order quantity control unit adjusts the product order quantity from each manufacturer based on the order quantity management parameters input by the user;

[0059] STEP4, the distributor adjusts the quantity of products sent to online and offline retailers based on the distribution management parameters input by the user.

[0060] Specifically, the procurement volume management parameter can be the quantity of various raw materials purchased from suppliers, the order management parameter can be the quantity of orders placed from each manufacturer, the distribution management parameter can be the quantity of products delivered to various online and offline retailers, the procurement volume management parameter can be adjusted by the user according to the required target sales volume of cigarettes, the order management parameter can be adjusted by the user according to the customer's preference index for cigarettes produced by different manufacturers, and the distribution management parameter can be adjusted by the user according to the customer's preference index for different retailers.

[0061] 8. A cigarette supply chain management system based on big data analysis according to claim 7, characterized in that analyzing customer preference indicators for cigarettes produced by different manufacturers and customer preference indicators for different retailers includes the following steps:

[0062] S31, Obtain historical ratings and reviews from customers on various online retailers on online retail platforms;

[0063] S32, obtain historical cigarette sales data from various offline retailers;

[0064] S33, calculate customer preference index for different retailers based on the acquired data.

[0065] The data analysis module can calculate the preference index for offline retailers based on the following formula:

[0066]

[0067] Where XXph is a customer preference index for offline retailers, A is the number of customers visiting the offline retailer in that month (the same person making multiple visits is counted as one person), back is the repeat customer rate of the offline retailer in that month (the repeat customer rate is the ratio of the number of people who visited the retailer two or more times in that month to the total number of customers), e is a natural constant, and time... a H represents the number of visits by the a-th visitor in that month. a The total spending of the a-th customer at this offline retailer in that month;

[0068] The data analytics module can calculate the online retailer preference index according to the following formula:

[0069]

[0070] Where XSph is a customer preference index for the online retailer, B is the number of visitors to the online retailer in that month (multiple visits by the same person are counted as one person), Back is the online retailer's repeat customer rate in that month, which is the ratio of the number of people who visited the online retailer two or more times in that month to the total number of visitors, e is a natural constant, and time... b H represents the number of visits by the b-th visitor in that month. b Let HP be the total spending of the bth customer at this online retailer that month, and let HP be the online retailer's positive review rate for that month. ver The average score of retailer-related ratings received by online retailers in that month, grade max This represents the upper limit of the retailer-related ratings that an online retailer receives in that month. These retailer-related ratings include ratings unrelated to product quality, such as customer service attitude and delivery speed.

[0071] S34. Calculate customer preference index for cigarettes produced by different manufacturers based on the acquired data.

[0072] The data analysis module can calculate the customer's preference index for cigarettes produced by different manufacturers based on the following formula:

[0073]

[0074] Where PH is a customer preference index for cigarettes produced by a particular manufacturer, X is the number of offline retailers selling cigarettes produced by that manufacturer, and k is the number of offline retailers. x Adjust the weights for the preference of the xth offline retailer, like x Let be the preference parameter of the customers of the x-th offline retailer for cigarettes produced by this manufacturer; Y be the number of online retailers selling cigarettes produced by this manufacturer, and k be the number of online retailers. y Adjust the weights for the preference of the y-th online retailer, like y Let y be the preference parameter of the customers of the y-th online retailer for cigarettes produced by this manufacturer;

[0075] I represents the number of people who purchased cigarettes from this manufacturer at the xth offline retailer in that month. H represents the number of purchases made by the i-th customer of the x-th offline retailer who buys cigarettes produced by this manufacturer. ix The total purchase amount of the i-th customer who purchased cigarettes produced by this manufacturer from the x-th offline retailer;

[0076] J represents the number of people who purchased cigarettes from this manufacturer from the y-th online retailer that month. H represents the number of purchases made by the j-th customer of the y-th online retailer who buys cigarettes produced by this manufacturer. jyGRADE represents the total purchase amount of the j-th customer who purchases cigarettes from this manufacturer from the y-th online retailer. very This represents the average score among the ratings related to cigarettes produced by this manufacturer received by the y-th online retailer in that month; GRADE maxy This represents the upper limit of the ratings related to cigarettes produced by this manufacturer that the y-th online retailer receives in that month; the cigarette-related ratings may include ratings for taste, flavor, etc.

[0077] Specifically, the data analysis unit stores preference index ranges set by those skilled in the art based on experience. By determining the preference index range in which the value of the preference index falls, the customer's preference for different retailers can be evaluated and graded according to the range. The higher the grade, the higher the degree of preference. The preference adjustment weights for online and offline retailers can be set according to the corresponding grade of their preference index. There are a total of 5 grades. When the grade is 1, the preference adjustment weight is set to 1.2. When the grade is 2, the preference adjustment weight is set to 1.1, and so on. By setting the preference adjustment weights, the influence of the customer's preference for retailers on the calculation results can be reduced when calculating the preference index for cigarettes.

[0078] The beneficial effects of this solution are: 1. By setting customer preference indicators for different retailers and for cigarettes produced by different manufacturers, users can understand customer preferences and adjust the supply chain accordingly to better cater to customer preferences, thereby improving overall revenue.

[0079] 2. By setting preference adjustment weights, the influence of customer preferences for retailers on the calculation results can be reduced when calculating the cigarette preference index. This avoids misjudging customer preferences for cigarettes produced by different manufacturers during the analysis process due to customer bias, which is beneficial for users to adjust the order quantity from each manufacturer based on customer preference indexes for different cigarettes.

[0080] Example 2: This example should be understood as including all the features of any of the foregoing examples, and further improving upon them. It also includes a supply chain adjustment calculation unit in the data analysis module. The supply chain adjustment calculation unit is used to calculate adjustment parameters. Users can use the adjustment parameters as a reference to adjust the supply chain management module. The adjustment parameters are reference values ​​after adjusting various parameters of the supply chain.

[0081] The order quantity adjustment parameter can be calculated using the following formula:

[0082]

[0083] Where TZ is the order volume adjustment parameter for the manufacturer corresponding to PH, i.e., the number of orders placed with that manufacturer next month; ph is the cigarette preference threshold. When the preference index is greater than or equal to the cigarette preference threshold, the cigarettes produced by that manufacturer are considered popular; when the preference index is less than the cigarette preference threshold, the cigarettes produced by that manufacturer are considered unpopular. ph is set by those skilled in the art based on experience; and DING is the order volume placed with the manufacturer corresponding to PH this month. max For the maximum allowed order quantity, DING min For the minimum permissible order quantity, DING max and DING min It can be obtained through an agreement with the manufacturer; if no corresponding agreement exists, DING max Let it be positive infinity, DING min Set to 0;

[0084] The sales volume adjustment parameters can be calculated using the following formula:

[0085]

[0086] Wherein, XSTZ is the online retailer's sales volume adjustment parameter, i.e., the amount of cigarettes sent to the retailer next month, XSph is the preference index corresponding to the online retailer, SELL is the online retailer's cigarette sales rate for the month, XIAO is the amount of cigarettes sent to the online retailer for the month, and VXSph is the online preference index reference value, which is set by those skilled in the art based on the average of the preference indices of various online retailers.

[0087] XXTZ is the sales volume adjustment parameter for offline retailers, i.e., the amount of cigarettes sent to the retailer next month; XXph is the preference index corresponding to the offline retailer; sell is the cigarette sales rate of the offline retailer in this month; xiao is the amount of cigarettes sent to the offline retailer in this month; and VXXph is the reference value of the offline preference index. The reference value of the preference index is set by those skilled in the art based on the average value of the preference index of each offline retailer.

[0088] The beneficial effects of this embodiment are as follows: It sets adjustment parameters for sales volume and order volume, and obtains the adjustment parameters based on various preference indicators. This is beneficial for providing users with a reference based on customers' preferences for different retailers and cigarettes. Users can refer to the above parameters to adjust the order volume from the manufacturer and the sales volume distributed to different retailers, thereby improving the revenue brought by the supply chain.

[0089] The above-disclosed content is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Therefore, all equivalent technical changes made based on the description and drawings of the present invention are included within the scope of protection of the present invention. Furthermore, the elements therein can be updated as technology develops. The above units are merely examples, and those skilled in the art can adopt corresponding units according to actual needs when implementing this solution.

Claims

1. A cigarette supply chain management system based on big data analytics, characterized in that, It includes a data acquisition module, a data storage module, a data analysis module, a visualization module, and a supply chain collaborative management module. The data acquisition module is used to collect data from each process of cigarette production, from raw material purchase to customer feedback. The data storage module is used to store the data collected by the data acquisition module. The data analysis module is used to analyze customer preferences based on the data stored in the data storage module. The visualization module is used to display the analysis results of the data analysis module. The supply chain collaborative management module is used to manage each part of the supply chain based on the analysis results of the data analysis module. The data analysis module includes a preference index calculation module, which calculates customer preference indices for cigarettes produced by various manufacturers based on customer feedback. Users then use these preference indices to operate the supply chain collaborative management module, thereby adjusting the supply chain. The supply chain includes suppliers, manufacturers, distributors, online retailers, and offline retailers. Online retailers sell cigarettes to users online and record customer reviews. Offline retailers sell cigarettes to users through physical stores and record customer repurchase rates. The data acquisition module includes a cost data acquisition unit, a production data acquisition unit, and an evaluation data acquisition unit. The cost data acquisition unit collects production and sales costs for each part of the cigarette supply chain. The production data acquisition unit obtains... The system includes supplier supply volume, manufacturer output, and sales volume of online and offline retailers. The evaluation data collection unit is used to collect various user evaluations. The data storage module includes a data denoising unit, a classification and integration unit, and a database. The data denoising unit is used to reduce noise in the data collected by the data collection unit. The classification and integration unit is used to classify, integrate, and compress the denoised data into the database. The data analysis module includes a preference index calculation unit, a sales index calculation unit, and an instruction generation unit. The sales index calculation unit is used to calculate the sales index of each online and offline retailer. The instruction generation unit is used to generate adjustment instructions to the supply chain collaborative management module based on the analysis results corresponding to the calculation results of the preference index calculation unit and the sales index calculation unit. The supply chain collaborative management module includes a purchase volume control unit, an order volume control unit, a distribution control unit, and a logistics planning unit. The purchase volume control unit is used to control the amount of raw materials purchased from suppliers. The order volume control unit is used to control the orders placed with the manufacturer. The distribution control unit is used to allocate the amount of cigarettes to each retailer by the distributor within the scope permitted by the contract. The logistics planning unit is used to plan logistics routes. The workflow of the cigarette supply chain management system includes the following steps: S1, the data acquisition module collects data from each process in the cigarette supply chain, from raw material purchase to customer feedback; S2, the data storage module classifies and saves the data collected by the data acquisition module; S3, the data analysis module receives the user's analysis instructions, extracts the corresponding data from the data storage module, and analyzes the customer's preference index for cigarettes produced by different manufacturers and the customer's preference index for different retailers. S4, The visualization module displays the analysis results of the data analysis module; S5, users input various management parameters into the supply chain collaboration management module based on the preference indicators displayed in the visualization module, thereby managing the supply chain; The workflow of the supply chain collaboration management module includes the following steps: STEP1, the logistics planning unit plans the logistics routes based on the locations of various suppliers, manufacturers, distributors, online retailers and offline retailers; STEP2, the purchase quantity control unit adjusts the quantity of raw materials purchased from suppliers based on the purchase quantity management parameters input by the user; STEP3, the order quantity control unit adjusts the product order quantity from each manufacturer based on the order quantity management parameters input by the user; STEP 4, the distributor adjusts the quantity of products delivered to online and offline retailers based on distribution management parameters input by the user; analyzing customer preference indicators for cigarettes produced by different manufacturers and customer preference indicators for different retailers includes the following steps: S31, Obtain historical ratings and reviews from customers on various online retailers on online retail platforms; S32, obtain historical cigarette sales data from various offline retailers; S33, Calculate customer preference index for different retailers based on the acquired data; S34, Calculate the customer's preference index for cigarettes produced by different manufacturers based on the acquired data; The data analysis module calculates the preference index for offline retailers based on the following formula: ； in, Here, A represents the number of customers visiting the offline retailer in that month, with the same person making multiple visits counted as one person. "back" represents the repeat customer rate for that month, which is the ratio of customers who visited the retailer two or more times to the total number of customers. "e" is a natural constant. The number of visits by the a-th visitor in that month. The total spending of the a-th customer at this offline retailer in that month; The data analysis module calculates the online retailer preference index based on the following formula: ； in, Here, B represents the number of customers who visited the online retailer in that month, with the same person making multiple visits counted as one person. Back represents the repeat customer rate for that month, which is the ratio of the number of customers who visited the online retailer two or more times to the total number of customers. e is a natural constant. For the b-th customer, this represents the number of visits in that month. For the bth customer, this represents the total spending at this online retailer that month. For online retailers, the positive review rate for the month. This represents the average score of retailer-related ratings received by online retailers that month. This represents the upper limit of the retailer-related ratings that an online retailer receives in the current month. These retailer-related ratings include ratings for customer service attitude and / or delivery speed, which are unrelated to product quality itself. S34, Calculate the customer's preference index for cigarettes produced by different manufacturers based on the acquired data; The data analysis module calculates the customer's preference index for cigarettes produced by different manufacturers based on the following formula: ； ； ； in, This is an indicator of customer preference for cigarettes produced by a particular manufacturer. The number of offline retailers selling cigarettes manufactured by this company. Adjust the weights for the preference for the xth offline retailer. Let Y be the preference parameter of the customers of the xth offline retailer for cigarettes produced by this manufacturer; Y is the number of online retailers selling cigarettes produced by this manufacturer. Adjust the weights for the preference of the y-th online retailer. Let y be the preference parameter of the customers of the y-th online retailer for cigarettes produced by this manufacturer; I represents the number of people who purchased cigarettes from this manufacturer at the xth offline retailer in that month. This represents the number of purchases made by the i-th customer at the x-th offline retailer who purchased cigarettes manufactured by this company. The total purchase amount of the i-th customer who purchased cigarettes produced by this manufacturer from the x-th offline retailer; J represents the number of people who purchased cigarettes from this manufacturer from the y-th online retailer that month. This represents the number of purchases made by the j-th customer who purchased cigarettes from this manufacturer from the y-th online retailer. Let y be the total purchase amount of the j-th customer who purchases cigarettes manufactured by this manufacturer from the y-th online retailer. This represents the average score among the cigarette-related ratings obtained by the y-th online retailer in that month from the manufacturer's products. This represents the upper limit of the ratings for cigarettes produced by this manufacturer that the y-th online retailer receives in that month; the cigarette-related ratings include taste and / or flavor ratings.

Images