Marketing method based on cross-platform design synchronization

Abstract

The invention provides a marketing method based on cross-platform design synchronization, and relates to the technical field of marketing methods, and the method comprises the steps: obtaining the login data, interaction data, total customer interaction number and purchase data of a customer on a platform in the recent week, and calculating the liveness of the customer; obtaining the number of customers on each platform and the number of platform users of each platform, calculating the customer activity coefficient of each platform according to the number of newly added users in one week, the number of active users in one week and the number of platforms, predicting the customer activity trend of each platform, and calculating the resource allocation ratio with the number of potential customers of each platform; according to the method, marketing resources are distributed, theme features, product style features and platform style features of products for marketing each time are obtained, a feature coincidence rate is calculated, product style feature types are selected, a comprehensive profit space and a popularity value of each type of platform are calculated, product popularity indexes are obtained, and hot product names are screened out to serve as main marketing products.

Description

Technical Field

[0001] The present invention relates to the technical field of marketing methods, and in particular to a marketing method based on cross-platform design synchronization. Background Art

[0002] In the modern business environment, companies often need to conduct marketing across multiple platforms to maximize coverage and influence on their target customer base. With the increasing complexity of Internet user behavior and the intensification of market competition, simple, multi-platform content delivery can no longer meet the needs of business growth. Traditional single-platform data analysis methods often cannot effectively capture changes in cross-platform user behavior and the mutual influence between different platforms. Therefore, companies urgently need a more systematic and intelligent method to analyze and integrate cross-platform data in order to more accurately identify market opportunities, optimize resource allocation, and improve the efficiency and effectiveness of marketing activities.

[0003] In the prior art, the publication number CN110807664A discloses a cross-platform customer marketing method and device, which obtains the first viewing information of the first user, the first viewing information is the first film and television drama watched by the first user; obtains the first product information according to the first film and television drama, the first product information is the related product information recommended in the first film and television drama; obtains the first label information according to the first product information; obtains the first shopping cart information of the first user on the first e-commerce platform, wherein the first shopping cart has the second product information; obtains the second label information according to the second product information; determines whether the first label information and the second label information have a first association relationship; when the first label information and the second label information have a first association relationship, the first product is placed in the first shopping cart, thereby achieving the technical effect of improving the accuracy and hit rate of e-commerce advertising. However, this solution only relies on the user's film and television drama viewing behavior and shopping cart information for recommendation, and pushes based on a specific dimension (film and television drama content, product labels, etc.), which makes it relatively limited in dealing with complex and changeable cross-platform user behaviors, and cannot capture the multi-dimensional behaviors of customers on multiple platforms.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide a marketing method based on cross-platform design synchronization to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: A marketing method based on cross-platform design synchronization, the specific steps include: Step 1: Obtain the customer's login data on a platform for the past week to calculate the customer's average daily online time and the number of new customers. Calculate the customer interaction rate based on the interaction data and the total number of customer interactions. Calculate the customer's purchasing power based on the purchase data. Calculate the customer's activity based on the average daily online time, customer interaction rate and purchasing power. Step 2: Obtain the number of customers on each platform and the number of platform users on each platform, calculate the customer share of each platform, calculate the platform popularity value based on the customer share and the number of customers, and calculate the customer activity coefficient of each platform based on the number of new users in a week, the number of active users in a week and the number of platforms, and predict the customer activity trend of each platform; Step 3: Obtain the basic information and login data of platform users of each platform, group platform users by clustering method, determine whether it is a potential customer group based on the proportion of product customers in each group to the total number of people in each group, estimate the number of potential customers, and allocate marketing resources based on the customer activity coefficient, number of potential customers and customer activity trend of each platform; Step 4: Obtain the theme features, product style features, and platform style features of each marketing product, calculate the feature overlap rate between the content style and platform style features of each product, and select the product style feature type based on the feature overlap rate; Step 5: Divide the platforms according to the customer activity coefficient, number of potential customers and customer activity trend, and count the sales volume, cost and selling price of each product type on each type of platform in a week, calculate the comprehensive profit margin and popularity value, and select popular product names as the main marketing products by calculating the product popularity index.

[0007] Furthermore, the login data includes online time, number of online times, registration time, and number of registrations; The calculation formula for the average daily online time is: in, is the average daily online time, For the The online time of each online session, is the number of online times, , are all positive integers, ; The interactive data includes the number of product views, likes, comments, and shares; The calculation formula of the customer interaction rate is: in, is the customer interaction rate, is the number of views, For the number of likes, is the number of comments, is the number of shares, is the total number of customer interactions; The purchase data includes the number of purchases, the purchase amount, and the number of products purchased; The calculation formula of the customer purchasing power is: in, For purchasing power, is the number of purchases, is the purchase amount, The quantity of products purchased.

[0008] Furthermore, the calculation formula of the customer activity is: in, For customer activity, They are the weights of average daily online time, customer interaction rate, and customer purchasing power. ; when When the customer is detected, the customer is judged to be an active customer; in, The threshold for determining customer activity.

[0009] Furthermore, the calculation formula of the customer share is: in, For customer share, is the number of product customers in the platform, is the number of platform users; The calculation formula of the platform heat value is: in, is the platform heat value.

[0010] Furthermore, the calculation formula of the customer activity coefficient is: in, is the customer activity coefficient, is the number of active users in a week, The number of new users per week. is the number of platforms, For the platforms; The calculation formula for predicting the customer activity trend of each platform is: in, Active trends for customers, is the activity decay coefficient, For time.

[0011] Furthermore, the basic information includes age, gender, income, and duration of platform use; Behavioral characteristics include purchase history, visit frequency, browsing time, and interaction frequency; The steps to group platform users by clustering are: The basic information and login data are transformed into a feature data set: in, They are age, gender, income, platform usage time, and registration time. is the online time, is the number of online times; Random Selection data nodes as the initial centroid, represents the number of categories after clustering, is a positive integer, where The initial centroid is expressed as: in, Respectively represent The age, gender, income, platform usage time, registration time, online time, and online times of the data nodes as the initial centroid, is a positive integer, and ; For each platform user's feature, calculate its distance to each initial centroid and assign it to the cluster represented by the nearest centroid. The formula for calculating the distance to the initial centroid is: in, Indicates The initial centroid and The distance between data nodes, Respectively represent The age, gender, income, platform usage time, registration time, online time, and online times of the data nodes as the initial centroid, is a positive integer; For each cluster, after each clustering is completed, the mean of all points in the cluster is recalculated and used as the feature data of the new centroid. The update formula for the centroid feature data is: in, Indicates that the The number of data nodes of the centroid, Respectively indicate the assignment to The data nodes of the centroids correspond to the age, gender, income, platform usage time, registration time, online time, and online times of the platform users. Respectively represent the age, gender, income, platform usage time, registration time, online time, and online times of the updated centroid; Based on the updated feature vector of the centroid, clustering is performed again until the change of all centroid positions is less than the threshold, then the clustering is considered stable and the clustering is terminated.

[0012] Furthermore, the calculation formula for estimating the number of potential customers is: in, is the number of potential customers, For the The number of potential customers in the group, is the number of potential customer groups, , All are positive integers; The calculation steps for allocating marketing resources based on the customer activity coefficient, number of potential customers and customer activity trend of each platform are as follows: Calculate resource allocation ratio: in, is the resource allocation ratio, is the number of potential customers, Active trends for customers, is the customer activity coefficient, is the number of platforms, For the platforms, They are the weights of the number of potential customers, customer activity trend, and customer activity coefficient respectively.

[0013] Furthermore, the subject features include brand positioning, quality requirements, and corporate logo; The product style features include humor, emotionality, color, design, and font; The platform style features include humor, emotionality, color, design, and fonts; The steps of calculating the overlap rate between the content style and the platform style features of each product are as follows: in, is the characteristic overlap rate, is the number of overlapping style features, For product style characteristics, It is the platform style feature; when When determining whether the product style and characteristics are suitable for the platform.

[0014] Furthermore, the calculation formula of the comprehensive profit margin is: in, For the comprehensive profit margin, is the selling price of the product type, is the cost of the product type, Type of sales, When it is 1, it represents the platform type divided based on the customer activity coefficient. When it is 2, it means the platform type is divided based on the number of potential customers. When it is 3, it means the platform type is divided based on the customer activity trend; The calculation formula of the heat value is: in, is the heat value, is the number of product types; The calculation formula of the product popularity index is: in, It is the product popularity index; when When the product is displayed, it is judged as a popular product.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: by obtaining the login data, interaction data, total number of customer interactions and purchase data of customers on a platform in the past week, the number of customers on each platform and the number of platform users on each platform are calculated, and the customer activity coefficient of each platform is calculated according to the number of new users in a week, the number of active users in a week and the number of platforms, and the customer activity trend of each platform is predicted, and the resource allocation ratio is calculated with the number of potential customers on each platform, marketing resources are allocated, the theme characteristics, product style characteristics and platform style characteristics of the products marketed each time are obtained, and the product style characteristic type is selected by calculating the feature overlap rate, and the product popularity index is obtained by calculating the comprehensive profit margin and heat value of each type of platform, and the popular product names are screened out as the main marketing products: The present invention can accurately predict and allocate marketing resources based on comprehensive analysis of customer activity, number of platform users, active trends, and number of potential customers, thereby achieving precise coverage of different platforms and user groups. By calculating the overlap rate of product and platform style features, product selection is optimized to make marketing more targeted and efficient. In addition, by combining comprehensive profit margins and popularity values ​​to screen popular products, not only can marketing effectiveness be improved, but resource utilization can also be maximized, sales growth can be driven, and product market matching can be improved to enhance brand competitiveness. This method achieves accurate resource allocation and personalized product promotion, improving the effectiveness and benefits of the overall marketing strategy; The present invention also calculates customer activity, customer share and platform popularity value, so that enterprises can accurately evaluate and predict user activities on different platforms, so as to better formulate dynamic and personalized marketing strategies. Secondly, through cluster analysis and identification of potential customer groups, enterprises can more scientifically predict the number and needs of potential customers and optimize the effect of marketing activities. In addition, by selecting product styles based on feature overlap rate, enterprises can ensure that their products are highly matched with the platform background style, thereby improving user experience and purchasing tendencies. According to customer activity coefficient, number of potential customers and customer activity trend, platforms are divided into types. By combining data from these three angles, it is ensured that the selected hot-selling products not only have potential, but also can achieve good market performance in the short term. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0017] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0018] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0019] Example

[0020] See also Figure 1 , the present invention provides a technical solution: A marketing method based on cross-platform design synchronization, the specific steps include: Step 1: Obtain the customer's login data on a platform for the past week to calculate the customer's average daily online time and the number of new customers. Calculate the customer interaction rate based on the interaction data and the total number of customer interactions. Calculate the customer's purchasing power based on the purchase data. Calculate the customer activity based on the average daily online time, customer interaction rate, and purchasing power.

[0021] In this embodiment, the login data includes online time, number of online times, registration time, and number of registrations; The calculation formula for the average daily online time is: in, is the average daily online time, For the The online time of each online session, is the number of online times, , are all positive integers, .

[0022] The average daily online time is the average time customers spend on the platform every day. It reflects the frequency of customers' use and the attractiveness of the platform. It measures the frequency of users' use and the attractiveness of the platform. A high average daily online time indicates that customers have a high interest and stickiness in the platform content, which represents the user's activity.

[0023] The interactive data includes the number of product views, likes, comments, and shares; The calculation formula of the customer interaction rate is: in, is the customer interaction rate, is the number of views, For the number of likes, is the number of comments, is the number of shares, is the total number of customer interactions.

[0024] Customer interaction rate refers to the proportion of customer interactions on the platform to their total visits. A high interaction rate indicates that customers are not only using the platform, but also actively participating in the content, reflecting a high degree of customer engagement. Customers who interact frequently are more loyal to the brand and can become brand communicators. Marketers can increase brand exposure through user-generated content (such as comments and sharing), which helps to discover user interests: by analyzing user interaction behavior, it is possible to accurately understand which products or services they are interested in, thereby optimizing subsequent product recommendations or advertising strategies.

[0025] The purchase data includes the number of purchases, the purchase amount, and the number of products purchased; The calculation formula of the customer purchasing power is: in, For purchasing power, is the number of purchases, is the purchase amount, The quantity of products purchased.

[0026] A customer's purchase frequency, purchase amount, and number of products purchased are a comprehensive measure of the customer's purchasing behavior and consumption potential for the brand. A high purchasing power indicates that the customer is not only an active user but also a heavy consumer, with a high purchase intention for the brand's products, which can help identify potential customers: By tracking purchasing power, marketers can discover potential customers who have a low purchase frequency but a large purchase amount, and provide targeted incentives and promotions.

[0027] In this embodiment, the calculation formula of the customer activity is: in, For customer activity, They are the weights of average daily online time, customer interaction rate, and customer purchasing power. ; when When the customer is detected, the customer is judged to be an active customer; in, The threshold for determining customer activity.

[0028] As a comprehensive indicator, customer activity can accurately reflect the overall participation and value contribution of customers on the platform. The level of customer activity reflects the stickiness of customers. The higher the activity, the closer the connection between customers and the platform. This means that customers not only use the platform frequently, but also actively interact on the platform, such as browsing, liking, commenting, sharing, etc. Therefore, activity can be used as an important indicator to determine whether customers have long-term interest and loyalty to a brand or platform. Through the analysis of customer activity, companies can identify which customer groups are the most active and have the greatest purchasing potential. Based on this information, advertising strategies can be optimized to ensure that advertising content can cover the most valuable customer groups, thereby improving advertising efficiency and conversion rates.

[0029] Step 2: Obtain the number of customers on each platform and the number of platform users on each platform, calculate the customer share of each platform, calculate the platform popularity value based on the customer share and the number of customers, and calculate the customer activity coefficient of each platform based on the number of new users per week, the number of active users per week, and the number of platforms, and predict the customer activity trend of each platform.

[0030] In this embodiment, the calculation formula of the customer share is: in, For customer share, is the number of product customers in the platform, is the number of platform users; The calculation formula of the platform heat value is: in, is the platform heat value; In this embodiment, the calculation formula of the customer activity coefficient is: in, is the customer activity coefficient, is the number of active users in a week, The number of new users per week. is the number of platforms, For the platforms; The calculation formula for predicting the customer activity trend of each platform is: in, Active trends for customers, is the activity decay coefficient, For time.

[0031] By calculating the customer activity coefficient of each platform, enterprises can determine the customer activity of each platform and the proportion of customers on each platform. For example, a platform with a high activity coefficient means that it can effectively maintain the activity of existing customers and attract new customers to join. Predicting the activity trend of the platform can foresee in advance which platforms may become future growth points, helping enterprises to make strategic layouts in advance. Through the activity coefficient and trend prediction, enterprises can more accurately predict the user growth of a certain platform. For example, if the activity coefficient of a platform continues to rise, it means that it not only successfully attracts new users, but also can maintain the long-term activity of users, so its user growth may continue to accelerate in the future. Through differentiated analysis of activity, enterprises can quickly identify which platforms need more marketing support and which platforms are already in a strong competitive position, so as to make more accurate market decisions. This predictive ability enables enterprises to accurately grasp the growth trend of users and avoid missing key market opportunities or making ineffective resource investments.

[0032] Step 3: Obtain the basic information and login data of platform users of each platform, group the platform users by clustering method, determine whether it is a potential customer group based on the proportion of product customers in each group to the total number of people in each group, estimate the number of potential customers, and allocate marketing resources based on the customer activity coefficient, number of potential customers and customer activity trend of each platform.

[0033] The platform users are grouped by clustering, and the proportion of product customers in each group is used to determine whether it is a potential customer group, and the number of potential customers is further estimated. This process can effectively allocate marketing resources more accurately based on the characteristics of different user groups. Specifically, this method can discover the potential of different types of users, improve marketing accuracy, increase resource utilization, and maximize the user value of the platform.

[0034] Through cluster analysis, enterprises can identify user groups with similar habits and behavior patterns or needs, and can clearly identify which user groups may become potential customers. For example, in a certain group, the proportion of customers of a product is relatively high, indicating that the group has a strong interest in or purchase potential for the product. These users are considered potential customers. Clustering can help enterprises quickly discover segmented groups with high value potential from large-scale user data, thereby avoiding blindly investing resources in all users.

[0035] Estimating the number of potential customers can help companies identify which user groups are worth investing more marketing resources in. If a user group has a large number of potential customers and a high conversion rate, then the company can increase marketing investment in this group. With real-time potential customer number estimation, companies can adjust marketing strategies in a timely manner according to market and user dynamics. For example, if the number of potential customers in a certain group increases in a short period of time, the company can immediately develop a new marketing plan for this group to maximize its growth potential.

[0036] In this embodiment, the basic information includes age, gender, income, and platform usage time; Behavioral characteristics include purchase history, visit frequency, browsing time, and interaction frequency; The steps to group platform users by clustering are: The basic information and login data are transformed into a feature data set: in, They are age, gender, income, platform usage time, and registration time. is the online time, is the number of online times; Random Selection data nodes as the initial centroid, represents the number of categories after clustering, is a positive integer, where The initial centroid is expressed as: in, Respectively represent The age, gender, income, platform usage time, registration time, online time, and online times of the data nodes as the initial centroid, is a positive integer, and ; For each platform user's feature, calculate its distance to each initial centroid and assign it to the cluster represented by the nearest centroid. The formula for calculating the distance to the initial centroid is: in, Indicates The initial centroid and The distance between data nodes, Respectively represent The age, gender, income, platform usage time, registration time, online time, and online times of the data nodes as the initial centroid, is a positive integer; For each cluster, after each clustering is completed, the mean of all points in the cluster is recalculated and used as the feature data of the new centroid. The update formula for the centroid feature data is: in, Indicates that the The number of data nodes of the centroid, Respectively indicate the assignment to The data nodes of the centroids correspond to the age, gender, income, platform usage time, registration time, online time, and online times of the platform users. Respectively represent the age, gender, income, platform usage time, registration time, online time, and online times of the updated centroid; Based on the updated feature vector of the centroid, clustering is performed again until the change of all centroid positions is less than the threshold, then the clustering is considered stable and the clustering is terminated.

[0037] In this embodiment, the calculation formula for estimating the number of potential customers is: in, is the number of potential customers, For the The number of potential customers in the group, is the number of potential customer groups, , All are positive integers; The calculation steps for allocating marketing resources based on the customer activity coefficient, number of potential customers and customer activity trend of each platform are as follows: Calculate resource allocation ratio: in, is the resource allocation ratio, is the number of potential customers, Active trends for customers, is the customer activity coefficient, is the number of platforms, For the platforms, They are the weights of the number of potential customers, customer activity trend, and customer activity coefficient respectively.

[0038] The allocation of marketing resources is a crucial step. By obtaining the basic information and login data of each platform user and grouping platform users using clustering methods, potential customer groups can be identified, and marketing resources can be allocated based on customer activity coefficients, the number of potential customers, and customer activity trends. The role of marketing resources in this process is to ensure that marketing activities can more accurately and effectively reach users who are most likely to make purchases.

[0039] Marketing resources can be understood as a series of tools, means, budgets or strategies used in marketing activities to attract, convert and retain users. Specifically, marketing resources can include the following types, namely advertising budgets, promotion channels, content resources, preferential strategies, customer service, brand cooperation and technical tools. Through cluster analysis and data analysis methods such as customer activity and potential customer estimation, the system can accurately allocate resources to adapt to the characteristics of different platforms and user groups and maximize the effectiveness of marketing.

[0040] Step 4: Obtain the theme features, product style features, and platform style features of each product being marketed, calculate the feature overlap rate between the content style and platform style features of each product, and select the product style feature type based on the feature overlap rate.

[0041] Each product has certain themes and style characteristics, which can include humor, emotionality, color, design, font, etc. For example, the style characteristics of a product may be happy or lively, which reflects the style design and user perception of the product.

[0042] Each platform has its own unique user group and design style. The style characteristics of the platform may include interface color, interaction method, emotional type, etc. For example, the style of a social platform focusing on young people may tend to be lively and personalized, while a business platform for professionals may tend to be more concise and formal.

[0043] By comparing product style features with platform style features, their feature overlap rate can be calculated. Feature overlap rate refers to the degree of match between product features and platform features. For example, if a social platform that is popular among young people launches a colorful and avant-garde product, the overlap rate between the style of this product and the platform style may be high; on the contrary, if a serious style product with a business theme appears on a social platform, the overlap rate is low and may not be favored by users.

[0044] Based on the calculation results of the feature overlap rate, the marketing system will decide whether to adjust the style of the product to adapt to the characteristics of the platform. For example, if the style of a product is highly mismatched with the characteristics of the platform's user group, the system may suggest changing the way the product is displayed (such as changing the color, image, description style, etc.) or recommending products of other styles to ensure that the product can match the preferences of the platform's users, thereby improving the conversion rate.

[0045] When the platform and product styles are highly overlapped, the dissemination effect of marketing content is usually better. By calculating the feature overlap rate, the marketing system can identify the match between the product and the platform. If the match is found to be low, the system will automatically adjust the product presentation (such as using different colors, layouts or copywriting) or adjust product recommendations to achieve a better adaptation effect. For example, if the style of a product is fashionable and avant-garde, but the user preferences of the target platform are more inclined to a simple and classic style, then the system may adjust the product's display picture or copywriting description to make its style more in line with the psychological expectations of the users of the platform.

[0046] In this embodiment, the subject features include brand positioning, quality requirements, and corporate logo; The product style features include humor, emotionality, color, design, and font; The platform style features include humor, emotionality, color, design, and fonts; The steps of calculating the overlap rate between the content style and the platform style features of each product are as follows: in, is the characteristic overlap rate, is the number of overlapping style features, For product style characteristics, It is the platform style feature; when When determining whether the product style and characteristics are suitable for the platform.

[0047] Step 5: Divide the platforms according to the customer activity coefficient, number of potential customers and customer activity trend, and count the sales volume, cost and selling price of each product type on each type of platform in a week, calculate the comprehensive profit margin and popularity value, and select popular product names as the main marketing products by calculating the product popularity index.

[0048] By classifying platforms into types based on customer activity coefficient, number of potential customers and customer activity trend, and combining data from these three perspectives, we can ensure that marketing activities not only focus on the most active users at present, but also tap potential customers and predict products that may be hot-selling in the future. This comprehensive analysis can provide more comprehensive and in-depth market insights and avoid focusing on a single dimension. A single perspective may have biases or omissions, but screening from three perspectives can more comprehensively evaluate the market performance of products. For example, although a product has a large number of potential customers, if its activity is low, it may not be quickly converted into sales. Therefore, the combination of the three dimensions can ensure that the selected hot-selling products not only have potential, but also achieve good market performance in the short term. By screening out the hot-selling products with the best comprehensive performance, the effectiveness of marketing activities can be maximized. These products perform well in multiple dimensions, which means that they have high market appeal and user willingness to buy, and thus have a higher conversion rate. Hot-selling products that are comprehensively screened usually have strong market competitiveness. In the short term, they can attract the attention of a large number of users, prompt more purchases, and help brands stand out in a highly competitive market. By ensuring high exposure and continuous promotion of such products, brands can establish a stronger market position.

[0049] In this embodiment, the calculation formula of the comprehensive profit margin is: in, For the comprehensive profit margin, is the selling price of the product type, is the cost of the product type, Type of sales, When it is 1, it represents the platform type divided based on the customer activity coefficient. When it is 2, it means the platform type is divided based on the number of potential customers. When it is 3, it means the platform type is divided based on the customer activity trend; The calculation formula of the heat value is: in, is the heat value, is the number of product types; The calculation formula of the product popularity index is: in, It is the product popularity index; when When the product is displayed, it is judged as a popular product.

[0050] The product popularity index is a comprehensive indicator that takes into account the market popularity and profit margin of the product, reflecting the market attention of the product in a certain period of time. The higher the popularity value, the more attention and demand the product has received from consumers, which indicates the potential and attractiveness of the product in the market, and also reflects the competitiveness of the product in the market. If a product can stand out from many competitors and attract the attention of a large number of users, its popularity index will be relatively high. It also represents the profitability of the product. The larger the profit margin, the higher the net profit that each sale of the product can bring. Through this index, companies can make marketing decisions more scientifically and effectively, enhance market competitiveness and improve overall profitability.

[0051] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0052] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0053] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0054] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A marketing method based on cross-platform design synchronization, characterized in that: The specific steps include: Step 1: Obtain the customer's login data on a platform for the past week to calculate the customer's average daily online time and the number of new customers. Calculate the customer interaction rate based on the interaction data and the total number of customer interactions. Calculate the customer's purchasing power based on the purchase data. Calculate the customer's activity based on the average daily online time, customer interaction rate and purchasing power. Step 2: Obtain the number of customers on each platform and the number of platform users on each platform, calculate the customer share of each platform, calculate the platform popularity value based on the customer share and the number of customers, and calculate the customer activity coefficient of each platform based on the number of new users in a week, the number of active users in a week and the number of platforms, and predict the customer activity trend of each platform; Step 3: Obtain the basic information and login data of platform users of each platform, group platform users by clustering method, determine whether it is a potential customer group based on the proportion of product customers in each group to the total number of people in each group, estimate the number of potential customers, and allocate marketing resources based on the customer activity coefficient, number of potential customers and customer activity trend of each platform; Step 4: Obtain the theme features, product style features, and platform style features of each marketing product, calculate the feature overlap rate between the content style and platform style features of each product, and select the product style feature type based on the feature overlap rate; Step 5: Divide the platforms according to the customer activity coefficient, number of potential customers and customer activity trend, and count the sales volume, cost and selling price of each product type on each type of platform in a week, calculate the comprehensive profit margin and popularity value, and select popular product names as the main marketing products by calculating the product popularity index.

2. A marketing method based on cross-platform design synchronization according to claim 1, characterized in that: The login data includes online time, number of online visits, registration time, and number of registrations; The calculation formula for the average daily online time is: in, is the average daily online time, For the The online time of each online session, is the number of online times, , are all positive integers, ; The interactive data includes the number of product views, likes, comments, and shares; The calculation formula of the customer interaction rate is: in, is the customer interaction rate, is the number of views, For the number of likes, is the number of comments, is the number of shares, is the total number of customer interactions; The purchase data includes the number of purchases, the purchase amount, and the number of products purchased; The calculation formula of the customer purchasing power is: in, For purchasing power, is the number of purchases, is the purchase amount, The quantity of products purchased.

3. A marketing method based on cross-platform design synchronization according to claim 2, characterized in that: The calculation formula of the customer activity is: in, For customer activity, They are the weights of average daily online time, customer interaction rate, and customer purchasing power. ; when When the customer is detected, the customer is judged to be an active customer; in, The threshold for determining customer activity.

4. The marketing method based on cross-platform design synchronization according to claim 1, characterized in that: The calculation formula of the customer share is: in, For customer share, is the number of product customers in the platform, is the number of platform users; The calculation formula of the platform heat value is: in, is the platform heat value.

5. A marketing method based on cross-platform design synchronization according to claim 4, characterized in that: The calculation formula of the customer activity coefficient is: in, is the customer activity coefficient, is the number of active users in a week, The number of new users per week. is the number of platforms, For the platforms; The calculation formula for predicting the customer activity trend of each platform is: in, Active trends for customers, is the activity decay coefficient, For time.

6. The marketing method based on cross-platform design synchronization according to claim 1, characterized in that: The basic information includes age, gender, income, and duration of platform use; Behavioral characteristics include purchase history, visit frequency, browsing time, and interaction frequency; The steps to group platform users by clustering are: The basic information and login data are transformed into a feature data set: in, They are age, gender, income, platform usage time, and registration time. is the online time, is the number of online times; Random Selection data nodes as the initial centroid, represents the number of categories after clustering, is a positive integer, where The initial centroid is expressed as: in, Respectively represent The age, gender, income, platform usage time, registration time, online time, and online times of the data nodes as the initial centroid, is a positive integer, and ; For each platform user's feature, calculate its distance to each initial centroid and assign it to the cluster represented by the nearest centroid. The formula for calculating the distance to the initial centroid is: in, Indicates The initial centroid and The distance between data nodes, Respectively represent The age, gender, income, platform usage time, registration time, online time, and online times of the data nodes as the initial centroid, is a positive integer; For each cluster, after each clustering is completed, the mean of all points in the cluster is recalculated and used as the feature data of the new centroid. The update formula for the centroid feature data is: in, Indicates that the The number of data nodes of the centroid, Respectively indicate the assignment to The data nodes of the centroids correspond to the age, gender, income, platform usage time, registration time, online time, and online times of the platform users. Respectively represent the age, gender, income, platform usage time, registration time, online time, and online times of the updated centroid; Based on the updated feature vector of the centroid, clustering is performed again until the change of all centroid positions is less than the threshold, then the clustering is considered stable and the clustering is terminated.

7. The marketing method based on cross-platform design synchronization according to claim 1, characterized in that: The calculation formula for estimating the number of potential customers is: in, is the number of potential customers, For the The number of potential customers in the group, is the number of potential customer groups, , All are positive integers; The calculation steps for allocating marketing resources based on the customer activity coefficient, number of potential customers and customer activity trend of each platform are as follows: Calculate resource allocation ratio: in, is the resource allocation ratio, is the number of potential customers, Active trends for customers, is the customer activity coefficient, is the number of platforms, For the platforms, They are the weights of the number of potential customers, customer activity trend, and customer activity coefficient respectively.

8. The marketing method based on cross-platform design synchronization according to claim 1, characterized in that: The subject features include brand positioning, quality requirements, and corporate logo; The product style features include humor, emotionality, color, design, and font; The platform style features include humor, emotionality, color, design, and fonts; The steps of calculating the overlap rate between the content style and the platform style features of each product are as follows: in, is the characteristic overlap rate, is the number of overlapping style features, For product style characteristics, It is the platform style feature; when When determining whether the product style and characteristics are suitable for the platform.

9. The marketing method based on cross-platform design synchronization according to claim 1, characterized in that: The calculation formula of the comprehensive profit margin is: in, For the comprehensive profit margin, is the selling price of the product type, is the cost of the product type, Type of sales, When it is 1, it represents the platform type divided based on the customer activity coefficient. When it is 2, it means the platform type is divided based on the number of potential customers. When it is 3, it means the platform type is divided based on the customer activity trend; The calculation formula of the heat value is: in, is the heat value, is the number of product types; The calculation formula of the product popularity index is: in, It is the product popularity index; when When the product is displayed, it is judged as a popular product.

Images