Baijiu sales management method and system based on big data

Abstract

The invention relates to the technical field of internet advertisement recommendation, in particular to a Baijiu sales management method and system based on big data. The method comprises the following steps: acquiring user sales data, and constructing a current user portrait; establishing a current user portrait database, carrying out Internet advertisement recommendation according to the user data, and outputting recommendation data; setting a plurality of monitoring time periods, obtaining sales data of the monitoring time periods, and dynamically formulating a sales strategy; the system comprises a current user portrait construction module, an advertisement recommendation module and a strategy dynamic customization module. According to the method, the user portrait is constructed by acquiring the user sales data, accurate internet advertisement recommendation is performed by using the user portrait, and the sales strategy is dynamically formulated according to the real-time sales data, so that the accuracy, the conversion rate and the market response capability of white spirit sales are improved.

Description

Technical Field

[0001] This invention relates to the field of internet advertising recommendation technology, and in particular to a method and system for managing liquor sales based on big data. Background Technology

[0002] In the liquor sales sector, with the rapid development of internet technology and increasingly fierce market competition, traditional sales management models are facing numerous challenges: On the one hand, consumer demand is highly diversified and personalized. Consumers of different ages, regions, and consumption habits have different preferences for the aroma, alcohol content, brand, and packaging of baijiu. However, traditional sales management often lacks a deep and detailed understanding of consumers, making it difficult to accurately grasp their needs. This results in untargeted product recommendations that fail to effectively meet consumers' personalized needs, thereby affecting sales conversion rates and customer satisfaction.

[0003] On the other hand, while internet advertising provides a broader promotional channel for liquor sales, its effectiveness varies greatly. Many liquor companies lack scientific basis for their internet advertising, blindly investing and wasting significant advertising resources without achieving the expected marketing results. Furthermore, the lack of real-time monitoring and dynamic adjustment mechanisms for advertising effectiveness prevents companies from optimizing their advertising strategies based on market feedback, leading to persistently high advertising costs while sales performance remains limited.

[0004] In conclusion, it is essential to propose a sales management method and system for baijiu that can improve the accuracy, conversion rate, and market responsiveness of baijiu sales. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for managing liquor sales based on big data, aiming to improve the accuracy, conversion rate and market responsiveness of liquor sales.

[0006] To achieve the above objectives, this invention employs a big data-based liquor sales management method, comprising the following steps: Acquire user sales data and build a current user profile; Establish a current user profile database, recommend internet advertisements based on user data, and output the recommendation data; Set multiple monitoring time periods, obtain sales data for each monitoring period, and dynamically formulate sales strategies.

[0007] In the steps of acquiring user sales data and building the current user profile: Acquire user sales data from multiple sources, preprocess the collected data, and output sales data; Receive sales data, extract user purchase characteristics, and output characteristic data; Based on the feature data, classification and modeling are performed to generate the current user profile.

[0008] Among the steps involved in acquiring multi-source user sales data, preprocessing the collected data, and outputting sales data: The preprocessing process includes removing duplicate, erroneous, and incomplete data.

[0009] In the step of classifying and modeling based on feature data to generate the current user profile: In user classification, user characteristics are grouped to categorize users with the same purchasing and browsing behaviors into the same group. In user profiling modeling, group labels and feature descriptions are defined.

[0010] In the step of classifying and modeling based on feature data to generate the current user profile: By associating user characteristic data with their respective group tags, a detailed user profile is generated.

[0011] Among the steps involved in establishing the current user profile database, recommending internet advertisements based on user data, and outputting the recommendation data: Store the constructed multiple current user profiles into the database to establish a current user profile database; Based on the similarity between users, user-linked advertisement recommendations are made, and the recommendation results are output.

[0012] In the step of recommending user-linked ads based on the similarity between users and outputting the recommendation results: Calculate the similarity between multiple users and recommend ads to the target user based on the user set.

[0013] Among the steps involved are: setting multiple monitoring time periods, acquiring sales data for each monitoring period, and dynamically formulating sales strategies. Based on sales market patterns, multiple monitoring time periods are set; After each monitoring period ends, acquire the sales data for that monitoring period and calculate the sales growth rate based on the sales data; Sales strategies are dynamically developed based on sales data analysis results.

[0014] Among the steps involved in dynamically formulating sales strategies based on sales data analysis results: When sales growth continues to rise, increase advertising spending and increase inventory reserves; When the sales growth rate continues to decline, promotional activities are implemented.

[0015] This invention also provides a liquor sales management system based on big data, including a current user profile construction module, an advertising recommendation module, and a strategy dynamic customization module; wherein: The current user profile building module is used to retrieve user sales data and build the current user profile. The advertising recommendation module is used to establish a current user profile database, recommend internet advertisements based on user data, and output recommendation data. The strategy dynamic customization module is used to set multiple monitoring time periods, obtain sales data for the monitoring time periods, and dynamically formulate sales strategies.

[0016] This invention discloses a big data-based liquor sales management method and system, which employs a current user profile construction module, an advertising recommendation module, and a strategy dynamic customization module to perform the following steps: acquiring user sales data and constructing a current user profile; establishing a current user profile database, recommending internet advertisements based on user data, and outputting the recommended data; setting multiple monitoring time periods, acquiring sales data for each monitoring time period, and dynamically formulating sales strategies; constructing user profiles by acquiring user sales data, using user profiles for precise internet advertising recommendations, and dynamically formulating sales strategies based on real-time sales data to improve the accuracy, conversion rate, and market responsiveness of liquor sales. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the steps of the liquor sales management method based on big data of the present invention.

[0019] Figure 2 This is a flowchart of steps S100 of the present invention.

[0020] Figure 3 This is a flowchart of steps S200 of the present invention.

[0021] Figure 4 This is a flowchart of steps S300 of the present invention.

[0022] Figure 5 This is a schematic diagram of the structure of the liquor sales management system based on big data of the present invention.

[0023] Figure 6This is a schematic diagram of the electronic device of the present invention.

[0024] 401 - Current User Profile Building Module, 402 - Ad Recommendation Module, 403 - Dynamic Strategy Customization Module. Detailed Implementation

[0025] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0026] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0027] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0028] Please see Figures 1-4 This invention provides a method for managing liquor sales based on big data, comprising the following steps: S100: Obtain user sales data and build the current user profile.

[0029] In this implementation, user sales data is acquired, and a current user profile is constructed. The specific process is as follows: S101: Acquire multi-source sales data from users, preprocess the collected data, and output sales data; S102: Receive sales data, extract user purchase characteristics, and output characteristic data; S103: Classify and model based on feature data to generate the current user profile.

[0030] In the above process, multi-source user sales data is acquired. This multi-source data includes user purchase records (including purchase time, product name, quantity, and amount) and browsing records (such as product pages viewed, dwell time, and click behavior) from e-commerce platforms; and user purchase receipts, membership consumption records, and store visit records from offline stores. Data integration: Data from different channels is integrated to ensure a unified data format for easy subsequent processing and analysis.

[0031] The collected data is preprocessed, including the removal of duplicate, erroneous, and incomplete data. Remove duplicate data: For example, duplicate purchase records of the same user on e-commerce platforms and offline stores need to be deduplicated based on user ID and purchase time.

[0032] Handling erroneous data: Data such as negative purchase quantities or abnormal amounts need to be corrected or removed.

[0033] Filling incomplete data: For missing critical data such as user ID or product name, if it cannot be supplemented through other means, the record should be removed; for missing non-critical data, the mean, median, or mode can be used to fill in the missing data. For example: If the amount for a purchase record is missing, but the unit price p and the quantity purchased n are known, the amount A = p × n can be estimated.

[0034] The preprocessed data is stored in a database or data warehouse to form a standardized sales dataset for use in subsequent steps.

[0035] Receive sales data and extract user purchase characteristics, including purchase behavior characteristics and browsing behavior characteristics.

[0036] Among them, the characteristics of purchasing behavior are: Purchase frequency: Calculates the number of purchases a user makes within a certain period. For example, user u's purchase frequency in a month is: ; Among them, I (purchase event) i ) is an indicator function that indicates whether the i-th purchase event has occurred.

[0037] Purchase Amount: Calculates the user's total purchase amount over a certain period. For example, user u's total purchase amount in one month is: ; Where p i Let n be the unit price of the product purchased for the i-th time. i For the quantity purchased.

[0038] Purchase Preference: Calculates the degree of user preference for different product categories. For example, user u's preference for Maotai-flavor liquor is: ; Where n i The quantity of a certain type of baijiu to be purchased.

[0039] Among them, browsing behavior characteristics: Browsing time: Calculates the average time a user spends on a product page. For example, user u's average time spent on a certain product page is: ; Where t i Let m be the dwell time during the i-th visit, and m be the number of visits.

[0040] Browsing frequency: Calculates the number of times a user views a product page.

[0041] The extracted feature data is organized into a structured format (such as a table or feature vector) to facilitate subsequent classification and modeling.

[0042] Classification and modeling are performed based on feature data.

[0043] Among the user categories: Clustering algorithms, such as K-means, are used to group user characteristics, classifying users with similar purchasing and browsing behaviors into the same group. For example, the K-means algorithm can be used to divide users into high-end, mid-range, and low-end consumer groups. The specific steps are as follows: First, determine the number of clusters, k, into which the users will be divided. This value of k is usually determined based on business requirements or through methods such as the Elbow Method. Then, randomly select k users from all users as initial cluster centers. These initial centers can be completely random or selected based on some heuristic to reduce the number of iterations required for algorithm convergence.

[0044] Calculate the distance of each user to each cluster center and assign them to the cluster containing the nearest cluster center. Distance calculation: For each user, calculate the distance between them and all cluster centers. A commonly used distance metric is Euclidean distance, assuming user i's feature vector is x. i =(x i1 x i2 , ..., x im The eigenvector of cluster center j is c. j =(c j1 c j2 c jm If ), then the Euclidean distance d from user i to cluster center j is...ij for: ; After calculating the distance between a user and all cluster centers, the cluster center with the smallest distance is selected, and the user is assigned to the corresponding cluster.

[0045] Recalculate the cluster centers for each cluster, which are the characteristic mean values ​​of users within the cluster: After all users are assigned to the appropriate clusters, the new cluster centers for each cluster need to be recalculated.

[0046] For each cluster, calculate the mean of the feature vectors of all its users, and use this mean as the new cluster center. Assume there are n users in cluster j. i There are 1 user, and the user feature vector is x. i Then the new cluster center c j The feature vectors are: ; The above process enables the new cluster centers to better represent the average characteristics of users within the cluster.

[0047] Repeat the above process of calculating distance, assigning clusters, and updating cluster centers until the cluster centers no longer change significantly or the preset maximum number of iterations is reached. Generally, the algorithm can be considered converged when the change in cluster centers is less than a certain threshold.

[0048] Through the above iterative process, the K-means algorithm can divide users into k clusters with similar characteristics, thus providing a foundation for subsequent user profile construction and precision marketing.

[0049] In user profile modeling: Based on the clustering results, define labels and feature descriptions for each user group. For example: High-end business groups: high purchase frequency, large purchase amount, preference for high-end Maotai-flavor liquor, and long browsing time.

[0050] Young and fashionable consumers: moderate purchase frequency, preference for light-aroma baijiu with novel packaging, high browsing frequency but short dwell time.

[0051] User profile generation: This involves associating user characteristic data with their respective group tags to generate a detailed user profile. For example, user u's profile might include information such as "age 30-35, male, first-tier city, average monthly purchase amount over 5000 yuan, preference for Maotai-flavor liquor, and purchases 2-3 times per month."

[0052] The generated user profiles are stored in a database for use in subsequent advertising recommendations and sales strategy development.

[0053] S200: Establish a current user profile database, recommend internet advertisements based on user data, and output the recommendation data.

[0054] In this implementation, a current user profile database is established, internet advertising recommendations are made based on user data, and the recommended data is output. The specific process is as follows: S201: Store the constructed multiple current user profiles in the database to establish a current user profile database; S202: Based on the similarity between users, perform user-linked ad recommendations and output the recommendation results.

[0055] In the above process, multiple constructed current user profiles are stored in the database to establish a current user profile database. A collaborative filtering algorithm is used to calculate the similarity between users, based on the similarity between users, such as cosine similarity: To calculate the similarity between users, suppose the feature vectors of user u and user v are x and x, respectively. u =(x u1 x u2 , ..., x um ) and x v =(x v1 x v2 , ..., x vm If ), then the similarity sim(u,v) between user u and user v is: ; in, and These are the feature mean values ​​for users u and v, respectively.

[0056] Based on the calculated user similarity, find the k users most similar to the target user u, forming a set of similar users N(u).

[0057] Based on the ad clicks and purchase behaviors of users in the similar user set N(u), ads that the target user u may be interested in are recommended. For example, if n users among the similar users clicked or purchased an ad for a certain type of liquor, then that ad is recommended to the target user u.

[0058] The recommended results are compiled into an ad placement list, which includes information such as ad content, placement channels, and placement time.

[0059] Send the ad placement list to the internet advertising platform for ad placement, and evaluate and optimize the recommendation effect based on metrics such as ad click-through rate and conversion rate.

[0060] S300: Set multiple monitoring time periods, obtain sales data for each monitoring period, and dynamically formulate sales strategies.

[0061] In this implementation, multiple monitoring time periods are set, sales data within each monitoring period is acquired, and sales strategies are dynamically formulated. The specific process is as follows: S301: Based on sales market patterns, multiple monitoring time periods are set; S302: After each monitoring period ends, acquire the sales data for that monitoring period and calculate the sales growth rate based on the sales data; S303: Dynamically formulate sales strategies based on sales data analysis results.

[0062] In the above process, we study the seasonal patterns of the baijiu (Chinese liquor) sales market. For example, during traditional festivals such as the Spring Festival and Mid-Autumn Festival, the demand for baijiu typically increases significantly because these festivals are important occasions for family gatherings and entertaining guests, leading to strong demand for baijiu as a traditional beverage. We also analyze the impact cycle of promotional activities on sales. For instance, during large-scale promotional events on e-commerce platforms, sales data fluctuates significantly in the period before and after the event. Finally, we consider the impact of new product launches on sales. New products may initially attract a large number of consumers' attention and purchases, but the sales momentum will gradually change thereafter.

[0063] Based on the aforementioned market patterns, multiple monitoring time periods can be set. These periods can also be further refined or adjusted according to the company's own sales rhythm and business needs.

[0064] After each monitoring period ends, acquire the sales data for that monitoring period and calculate the sales growth rate based on the sales data.

[0065] Sales data is collected from various channels, including the company's sales system, e-commerce platform backend, and sales records from offline stores, for each monitoring period. This data includes, but is not limited to, sales volume, sales revenue, sales region distribution, and the sales percentage of different products.

[0066] For example, export the sales details of all liquor products within each monitoring period from the sales system, including product name, sales quantity, sales price, sales amount, sales date, sales region, and other information.

[0067] Calculate the sales growth rate for each monitoring period to measure changes in sales performance. Assuming the current monitoring period is t and the previous monitoring period was t-1, the formula for calculating the sales growth rate Gt is: ; Among them, S t This represents the sales revenue for the current monitoring period, S. t-1 This represents the sales revenue for the previous monitoring period.

[0068] In-depth analysis of sales data for each monitoring period is conducted, including not only sales growth rate but also analysis of sales trends for different products, performance differences in sales regions, and the effectiveness of promotional activities.

[0069] For example, analysis revealed that a certain high-end baijiu saw a significant increase in sales around the Spring Festival, but lower sales during regular sales periods; while another mid-to-low-end baijiu experienced substantial sales growth during e-commerce platform promotions. Furthermore, comparing sales data from different sales regions identified areas with better and worse sales performance and analyzed the reasons for this.

[0070] Sales strategy development: Product Strategy: Adjust product inventory based on sales trends. Increase inventory in advance for products that sell well during specific periods to avoid stockouts; reduce inventory for poorly selling products to lower inventory costs. Optimize the product mix to meet the needs of different sales regions and consumer groups. For example, increase the supply of premium baijiu in high-end consumption areas and launch related gift sets; launch smaller-packaged, stylishly designed baijiu products for younger consumers on e-commerce platforms.

[0071] Pricing Strategy: Adjust product prices flexibly based on sales growth rate and market competition. During peak sales seasons or promotional events, prices can be appropriately increased or maintained at the original price to obtain higher profits; during off-seasons, prices can be lowered through discounts, spending reductions, and other promotional activities to stimulate consumption. For example, around the Spring Festival, high-end liquor can maintain its original price or even be appropriately increased to reflect the scarcity and quality of the product; during e-commerce promotions, significant discounts can be offered on mid-to-low-end liquor to attract consumers.

[0072] Promotional Strategy: Optimize promotional plans based on the effectiveness analysis of promotional activities. For promotions with significant results, increase investment and expand the scope of the activities; for those with poor results, adjust or cancel them promptly. For example, if it is found that live-streaming e-commerce significantly boosted the sales of a certain type of liquor during an e-commerce campaign, then the frequency and intensity of live-streaming e-commerce can be increased in subsequent promotional activities.

[0073] Channel Strategy: Allocate resources rationally based on the sales performance of different sales channels. Increase support for high-performing channels, such as increasing advertising and providing more promotional activities; for low-performing channels, analyze the reasons and make improvements or adjustments. For example, if offline stores are found to be performing well in a specific region, the number of stores in that region can be increased or the store layout optimized; if a store on an e-commerce platform is not performing well, the store can be renovated, product displays optimized, or customer service improved.

[0074] In this invention, user sales data is first acquired, and a current user profile is constructed. Then, a current user profile database is established, and internet advertising recommendations are made based on the user data, with the recommended data output. Finally, multiple monitoring time periods are set, sales data for each monitoring time period is acquired, and sales strategies are dynamically formulated. By acquiring user sales data to construct user profiles, using user profiles to make precise internet advertising recommendations, and dynamically formulating sales strategies based on real-time sales data, the accuracy, conversion rate, and market responsiveness of liquor sales can be improved.

[0075] Corresponding to the aforementioned embodiments of the liquor sales management method based on big data, this application also provides embodiments of a liquor sales management system based on big data.

[0076] Figure 5 This is a block diagram illustrating a big data-based liquor sales management system according to an exemplary embodiment. (Refer to...) Figure 5 The system may include: a current user profile building module 401, an advertising recommendation module 402, and a strategy dynamic customization module 403; wherein: The current user profile building module 401 is used to retrieve user sales data and build a current user profile; The advertising recommendation module 402 is used to establish a current user profile database, recommend internet advertisements based on user data, and output recommendation data; The strategy dynamic customization module 403 is used to set multiple monitoring time periods, obtain sales data for the monitoring time periods, and dynamically formulate sales strategies.

[0077] In this embodiment, the current user profile construction module 401 acquires user sales data and constructs a current user profile; the advertising recommendation module 402 establishes a current user profile database, performs internet advertising recommendations based on user data, and outputs recommendation data; the strategy dynamic customization module 403 sets multiple monitoring time periods, acquires sales data for the monitoring time periods, and dynamically formulates sales strategies; by acquiring user sales data to construct user profiles, using user profiles to perform precise internet advertising recommendations, and dynamically formulating sales strategies based on real-time sales data, the accuracy, conversion rate, and market responsiveness of liquor sales can be improved.

[0078] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0079] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0080] Accordingly, this application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; and when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the above-described big data-based liquor sales management method. Figure 6 The diagram shown is a hardware structure diagram of any device with data processing capabilities, used in an embodiment of the present invention, to provide a liquor sales management system based on big data. (Except for...) Figure 6 In addition to the processor, memory, and network interface shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0081] Accordingly, this application also provides a computer-readable storage medium storing computer instructions, which, when executed by a processor, implement the aforementioned big data-based liquor sales management method. The computer-readable storage medium can be an internal storage unit of any data-processing device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data-processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data-processing device, and can also be used to temporarily store data that has been output or will be output.

[0082] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0083] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A method for managing liquor sales based on big data, characterized in that, Includes the following steps: Acquire user sales data and build a current user profile; Establish a current user profile database, recommend internet advertisements based on user data, and output the recommendation data; Set multiple monitoring time periods, obtain sales data for each monitoring period, and dynamically formulate sales strategies.

2. The liquor sales management method based on big data as described in claim 1, characterized in that, In the steps of acquiring user sales data and building the current user profile: Acquire user sales data from multiple sources, preprocess the collected data, and output sales data; Receive sales data, extract user purchase characteristics, and output characteristic data; Based on the feature data, classification and modeling are performed to generate the current user profile.

3. The liquor sales management method based on big data as described in claim 2, characterized in that, In the steps of acquiring multi-source user sales data, preprocessing the collected data, and outputting sales data: The preprocessing process includes removing duplicate, erroneous, and incomplete data.

4. The liquor sales management method based on big data as described in claim 2, characterized in that, In the step of classifying and modeling based on feature data to generate the current user profile: In user classification, user characteristics are grouped to categorize users with the same purchasing and browsing behaviors into the same group. In user profiling modeling, group labels and feature descriptions are defined.

5. The liquor sales management method based on big data as described in claim 4, characterized in that, In the step of classifying and modeling based on feature data to generate the current user profile: By associating user characteristic data with their respective group tags, a detailed user profile is generated.

6. The liquor sales management method based on big data as described in claim 1, characterized in that, In the steps of establishing the current user profile database, making internet advertising recommendations based on user data, and outputting recommendation data: Store the constructed multiple current user profiles into the database to establish a current user profile database; Based on the similarity between users, user-linked advertisement recommendations are made, and the recommendation results are output.

7. The liquor sales management method based on big data as described in claim 6, characterized in that, In the steps of recommending user-advertisements based on the similarity between users and outputting the recommendation results: Calculate the similarity between multiple users and recommend ads to the target user based on the user set.

8. The liquor sales management method based on big data as described in claim 1, characterized in that, In the steps of setting multiple monitoring time periods, obtaining sales data for each monitoring period, and dynamically formulating sales strategies: Based on sales market patterns, multiple monitoring time periods are set; After each monitoring period ends, acquire the sales data for that monitoring period and calculate the sales growth rate based on the sales data; Sales strategies are dynamically developed based on sales data analysis results.

9. The liquor sales management method based on big data as described in claim 8, characterized in that, In the step of dynamically formulating sales strategies based on sales data analysis results: When sales growth continues to rise, increase advertising spending and increase inventory reserves; When the sales growth rate continues to decline, promotional activities are implemented.

10. A liquor sales management system based on big data, applied to the liquor sales management method based on big data as described in claim 1, characterized in that, This includes the current user profile building module, the ad recommendation module, and the strategy dynamic customization module; among which: The current user profile building module is used to retrieve user sales data and build the current user profile. The advertising recommendation module is used to establish a current user profile database, recommend internet advertisements based on user data, and output recommendation data. The strategy dynamic customization module is used to set multiple monitoring time periods, obtain sales data for the monitoring time periods, and dynamically formulate sales strategies.

Images