A marketing method, system and storage medium based on big data

Abstract

This invention relates to the field of marketing technology, specifically disclosing a marketing method, system, and storage medium based on big data. The method includes: a data acquisition module for collecting customer personality data and customer behavior characteristic data; a customer activity analysis module for processing customer initiative assessment indices and customer purchase desire assessment indices for each customer in each monitoring period, comprehensively analyzing these to obtain a customer activity assessment index for each customer in each monitoring period, and filtering out target customers; and a marketing strategy adaptation module for optimizing marketing strategies for each target customer. This invention, by providing a marketing method, system, and storage medium based on big data, enables enterprises to prioritize their most valuable customers, rationally allocate sales or service resources, help stabilize their customer base, promote long-term customer purchasing behavior, and more effectively attract and retain customers through precision marketing, thereby improving marketing effectiveness.

Description

Technical Field

[0001] The present invention relates to the field of marketing technology, and in particular to a marketing method, system and storage medium based on big data. Background Art

[0002] At present, big data marketing is a very important part of the field of marketing technology. With the advancement of technology and the growth of market demand, providing more personalized big data marketing methods has become the norm. Accurate and efficient big data marketing systems are of great significance to improving customer satisfaction and enhancing market competitiveness.

[0003] For example, the invention patent with announcement number CN116645119B is a marketing customer acquisition method based on big data, which includes the following steps: Step 1: Based on the digital marketing data of business conducted under big data, the target customer group of the enterprise is identified; Step 2: Establish a multi-channel marketing system and conduct marketing market segmentation; Step 3: Analyze the customer portraits of target customers in the target market; Step 4: After determining the target market, the enterprise positions the enterprise, its products and the marketing methods of its products according to the characteristics of potential target customers in the target market; Step 5: Implement precise customer acquisition plans through big data technology. The enterprise determines its own marketing characteristics through market positioning, targets the preferences of customers in the target market and the positioning of marketing methods, and uses marketing strategies to obtain the recognition of potential target customers, thereby enhancing the competitiveness of products and enterprises in the market.

[0004] For example, the invention patent with announcement number CN116739670B is an advertising push marketing system and method based on big data, including an instruction processing module, a big data testing and analysis module, an advertising analysis module, a social software push marketing judgment module and a mobile terminal control module; the output end of the instruction processing module is connected to the input end of the mobile terminal control module; the output end of the big data testing and analysis module is connected to the input end of the advertising analysis module; the output end of the advertising analysis module is connected to the input end of the social software push marketing judgment module; the output end of the social software push marketing judgment module is connected to the input end of the instruction processing module.

[0005] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, it was found that the above technology has at least the following technical problems: the current big data marketing methods focus more on accurate marketing strategies and consistency of customer experience, but customers have different perceptions of different marketing strategies at different times, and the marketing effect is difficult to guarantee. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a marketing method, system and storage medium based on big data, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: The first aspect of the present invention provides a marketing system based on big data, including: a data collection module for collecting customer personality data and customer behavior characteristic data.

[0008] The customer activity analysis module is used to process customer personality data to obtain the customer initiative evaluation index of each customer in each monitoring period, process customer behavior characteristic data to obtain the customer purchase desire evaluation index of each customer in each monitoring period, conduct comprehensive analysis to obtain the customer activity evaluation index of each customer in each monitoring period, and screen target customers based on the customer activity evaluation index of each customer in each monitoring period.

[0009] The marketing strategy adaptation module is used to optimize the marketing strategy for each target customer.

[0010] As a further method, the customer personality data is processed to obtain the customer initiative evaluation index of each customer in each monitoring period. The specific processing process is: the customer personality data includes average response time, communication frequency and historical purchase times.

[0011] The critical average response time, critical communication frequency and critical historical purchase times are extracted from the big data marketing database, and the customer initiative evaluation index of each customer in each monitoring period is obtained through comprehensive analysis. The initial marketing strategy of each customer in the next monitoring period is obtained according to the customer initiative evaluation index of each customer in each monitoring period.

[0012] As a further method, the customer behavior characteristic data is processed to obtain the customer purchase desire evaluation index of each customer in each monitoring period. The specific processing process is: the customer behavior characteristic data includes page interaction frequency, page scrolling depth and product comparison times.

[0013] The critical page interaction frequency, critical page scrolling depth and critical product comparison times are extracted from the big data marketing database, and the customer purchase desire evaluation index of each customer in each monitoring period is obtained through comprehensive analysis.

[0014] As a further method, the comprehensive analysis obtains the customer activity evaluation index of each customer in each monitoring period. The specific analysis process is: based on the customer initiative evaluation index of each customer in each monitoring period and the customer purchasing desire evaluation index of each customer in each monitoring period, a comprehensive analysis is performed to obtain the customer activity evaluation index of each customer in each monitoring period. The customer activity evaluation index of each customer in each monitoring period is a quantitative indicator obtained by analyzing the customer initiative evaluation index and the customer purchasing desire evaluation index of each customer in each monitoring period.

[0015] As a further method, the target customers are screened according to the customer activity evaluation index of each customer in each monitoring period. The specific screening process is: according to the customer activity evaluation index of each customer in each monitoring period, the number of times each customer threshold is met and the average activity of each customer are analyzed, and according to the average activity of each customer and the number of times each customer threshold is met, a comprehensive analysis is performed to obtain the tag value of each customer.

[0016] The target customer marking threshold is extracted from the big data marketing database, and each customer marking value is compared with the target customer marking threshold. If a customer marking value is greater than or equal to the target customer marking threshold, the customer is marked as a target customer. If a customer marking value is less than the target customer marking threshold, the customer is not marked.

[0017] Count the target customers to obtain each target customer.

[0018] As a further method, the customer activity evaluation index of each customer in each monitoring period is analyzed to obtain the number of times each customer threshold is met and the average activity of each customer. The specific analysis process is: extracting the customer activity evaluation threshold from the big data marketing database, comparing the customer activity evaluation index of each customer in each monitoring period with the customer activity evaluation threshold, judging whether the customer activity evaluation index of each customer in each monitoring period is greater than or equal to the customer activity evaluation threshold, and marking the number of times the customer activity evaluation index of each monitoring period is greater than or equal to the customer activity evaluation threshold as the number of times the customer threshold is met, and obtaining the number of times each customer threshold is met by statistics.

[0019] The customer activity evaluation index of a customer in each monitoring cycle is accumulated, and the accumulated result is divided by the number of monitoring cycles to obtain the average activity of the customer, and the average activity of each customer is obtained by statistics.

[0020] As a further method, the marketing strategy for each target customer is optimized, and the specific process is: according to the customer activity evaluation index of each customer in each monitoring period, the customer activity evaluation index of each target customer in each monitoring period is obtained, and the customer activity evaluation index of a target customer in each monitoring period is sorted in order from large to small, and the marketing strategy corresponding to the monitoring period to which the maximum customer activity evaluation index belongs is extracted and marked as the preferred marketing strategy for the target customer.

[0021] Optimize the initial marketing strategy for each target customer based on the preferred marketing strategy of each target customer.

[0022] As a further method, the customer purchase desire evaluation index of each customer in each monitoring period is specifically expressed as follows:

[0023]

[0024] Among them, B ij represents the purchase desire evaluation index of the jth customer in the i-th monitoring period, sf ij represents the page interaction frequency of the jth customer in the i-th monitoring period, sf0 represents the critical page interaction frequency, C ij represents the page scrolling depth of the jth customer in the i-th monitoring period, C0 represents the critical page scrolling depth, T ij represents the number of product comparisons of the jth customer in the ith monitoring period, T0 represents the critical number of product comparisons, ρ1 represents the customer purchase desire evaluation influencing factor corresponding to the set page interaction frequency, ρ2 represents the customer purchase desire evaluation influencing factor corresponding to the set page scrolling depth, ρ3 represents the customer purchase desire evaluation influencing factor corresponding to the set number of product comparisons, i represents the number of each monitoring period, i=1,2,3,...,m, m represents the total number of monitoring periods, j represents the number of each customer, j=1,2,3,...,n, n represents the total number of customers.

[0025] As a further method, the marketing storage medium based on big data is characterized by: comprising: a processor and a memory and a network interface connected to the processor; the network interface is connected to a non-volatile memory in a server; the processor retrieves a computer program from the non-volatile memory through the network interface during operation, and runs the computer program through the memory to execute any one of the methods described above.

[0026] A second aspect of the present invention provides a marketing method based on big data, comprising: collecting customer personality data and customer behavior characteristic data.

[0027] The customer personality data is processed to obtain the customer initiative evaluation index of each customer in each monitoring period, the customer behavior characteristic data is processed to obtain the customer purchase desire evaluation index of each customer in each monitoring period, and the customer activity evaluation index of each customer in each monitoring period is obtained through comprehensive analysis. The target customers are screened based on the customer activity evaluation index of each customer in each monitoring period.

[0028] Optimize the marketing strategy for each target customer.

[0029] The big data marketing database is used to store big data marketing related data, including the critical average response time, the critical communication frequency, the critical number of historical purchases, the customer purchase desire evaluation influencing factor corresponding to the set page interaction frequency, the customer purchase desire evaluation influencing factor corresponding to the set page scrolling depth, the customer purchase desire evaluation influencing factor corresponding to the set product comparison number, the customer activity evaluation influencing factor corresponding to the set customer initiative evaluation index, the customer activity evaluation influencing factor corresponding to the set customer purchase desire evaluation index, the customer tag value influencing factor corresponding to the set average activity, the customer tag value influencing factor corresponding to the set threshold satisfaction number, the customer activity evaluation threshold and the target customer tag threshold.

[0030] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0031] (1) The present invention provides a marketing method, system and storage medium based on big data, which can enable enterprises to give priority to the most valuable customers and reasonably allocate sales or service resources, thereby improving management efficiency, helping enterprises to stabilize their customer base, increase market share, and promote customers' long-term purchasing behavior. It can also more effectively attract and retain customers through precision marketing, thereby improving marketing effectiveness.

[0032] (2) By evaluating the customer initiative evaluation index, the present invention helps enterprises to have a more comprehensive understanding of customer preferences, needs and behavior patterns, enables enterprises to more accurately locate target customer groups and provide them with more personalized products and services, and can promptly discover and solve problems encountered by customers during the experience process as well as problems and deficiencies in products and services, so as to make timely improvements and optimizations and improve customer satisfaction and loyalty.

[0033] (3) The present invention can predict customers' purchasing intention and trend in the future by evaluating the customer purchasing desire evaluation index, which helps enterprises adjust production plans, inventory management and marketing strategies in advance to cope with market changes, and further helps enterprises manage customer resources more effectively, and helps enterprises discover new market opportunities and innovations, and promote the innovation and upgrading of products and services. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0035] Figure 1 It is a schematic diagram of the system module of the present invention.

[0036] Figure 2It is a schematic diagram of the method flow of the present invention.

[0037] Figure 3 It is a schematic diagram of the functional relationship between the customer activity evaluation index and the customer purchase desire evaluation index of the present invention. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0039] Reference Figure 1 As shown, the first aspect of the present invention provides a marketing system based on big data, including: a data collection module for collecting customer personality data and customer behavior characteristic data.

[0040] The customer activity analysis module is used to process customer personality data to obtain the customer initiative evaluation index of each customer in each monitoring period, process customer behavior characteristic data to obtain the customer purchase desire evaluation index of each customer in each monitoring period, conduct comprehensive analysis to obtain the customer activity evaluation index of each customer in each monitoring period, and screen target customers based on the customer activity evaluation index of each customer in each monitoring period.

[0041] The marketing strategy adaptation module is used to optimize the marketing strategy for each target customer.

[0042] Specifically, the customer personality data is processed to obtain the customer initiative evaluation index of each customer in each monitoring period. The specific processing process is: the customer personality data includes average response time, communication frequency and historical purchase times.

[0043] The critical average response time, critical communication frequency and critical historical purchase times are extracted from the big data marketing database, and the customer initiative evaluation index of each customer in each monitoring period is obtained through comprehensive analysis. The initial marketing strategy of each customer in the next monitoring period is obtained according to the customer initiative evaluation index of each customer in each monitoring period.

[0044] In a specific embodiment, the average response time refers to the average reply time of customers after receiving marketing information, and the communication frequency refers to the frequency of communication between customers and customer service. The average response time of customers, communication frequency and the number of historical purchases in each communication can be monitored through CRM (Customer Relationship Management) tools.

[0045] Furthermore, the customer initiative evaluation index of each customer in each monitoring period is specifically expressed as follows:

[0046]

[0047] Among them, A ij represents the customer initiative evaluation index of the jth customer in the ith monitoring period, v ij represents the average response time of the jth customer in the ith monitoring period, v0 represents the critical average response time, cf ij represents the communication frequency of the jth customer in the ith monitoring period, cf0 represents the critical communication frequency, Q ij represents the number of historical purchases of the jth customer in the ith monitoring period, Q0 represents the critical number of historical purchases, ω1 represents the customer initiative evaluation impact factor corresponding to the set average response time, ω2 represents the customer initiative evaluation impact factor corresponding to the set communication frequency, ω3 represents the customer initiative evaluation impact factor corresponding to the set number of historical purchases, i represents the number of each monitoring period, i=1,2,3,...,m, m represents the total number of monitoring periods, j represents the number of each customer, j=1,2,3,...,n, n represents the total number of customers.

[0048] The algorithm of this embodiment combines the customer's average response time, communication frequency and historical purchase times, and comprehensively analyzes to obtain the customer initiative evaluation index of each customer in each monitoring period. When the customer's average response time is faster, they may be more inclined to obtain a large amount of information and make a decision in a short time. At this time, the customer needs to increase the communication frequency in order to reserve sufficient information and support before making a decision. On the contrary, if the customer's average response time is slower, they may need more time to consider and weigh various factors. In this case, the customer's communication frequency will be reduced. At the same time, effective communication can help customers understand the characteristics, advantages and value of products or services more quickly, thereby accelerating the average response time. Through frequent communication, sales staff or customer service teams can promptly resolve customers' doubts and problems, enhance customers' trust and satisfaction, and thus promote customers to respond. In addition, in high-frequency communication, customers may raise more questions and doubts, which is related to On the other hand, in low-frequency communication, customers may ask fewer questions because they have limited opportunities to communicate with the customer service team. At the same time, a shorter average response time may imply better customer service and higher customer satisfaction, which helps promote customers' repeat purchase behavior, thereby increasing the number of historical purchases. Customers with a higher number of historical purchases tend to have a deeper understanding of and higher trust in the service or product, and they may be more willing to interact with responsive customer service to solve problems encountered during the purchase process or obtain more information. A higher communication frequency usually means that customers have a higher level of attention and interest in the service or product, which helps promote customers' purchasing behavior, thereby increasing the number of historical purchases. At the same time, customers with a higher number of historical purchases tend to be more willing to interact with service providers to learn about the latest product information, promotions or solve after-sales problems. Comprehensive analysis can obtain a more comprehensive, accurate and in-depth customer initiative evaluation index.

[0049] Table 1 Example of customer initiative evaluation index data for each customer in each monitoring period

[0050]

[0051] As shown in Table 1, the customer initiative evaluation index of each customer in each monitoring period is jointly determined by the average response time, communication frequency and historical purchase times. In a specific embodiment, m=1, the critical average response time is 12h, the critical communication frequency is 10 times / hour, the critical historical purchase times is 20 times, the customer initiative evaluation impact factor corresponding to the set average response time is 0.3, the customer initiative evaluation impact factor corresponding to the set communication frequency is 0.4, and the customer initiative evaluation impact factor corresponding to the set historical purchase times is 0.3. This formula takes into account three key factors, namely, the average response time, the communication frequency and the historical purchase times, which can help enterprises more accurately predict the sales cycle, reasonably arrange production and inventory, avoid resource waste, help enterprises quickly respond to customer needs, reduce communication costs and time, improve overall operational efficiency, and deeply understand customer pain points and needs, so as to provide more personalized services and solutions, thereby establishing closer customer relationships and improving customer loyalty. By optimizing the decision-making, communication and problem-solving processes, enterprises can shorten the sales cycle, improve conversion rates, promote business growth, and further improve market competitiveness. By standardizing the average response time, communication frequency and historical purchase times of different customers in different monitoring cycles, ensuring that they are compared at the same level, the fairness and comparability of the evaluation are improved. At the same time, v0 refers to the average response time threshold, and its setting helps to adjust the sales strategy in a targeted manner. cf0 refers to the maximum communication frequency, and its setting can avoid the waste of resources caused by frequent communication. The setting of Q0 helps to formulate differentiated marketing strategies and service plans according to the needs and characteristics of different customer groups. When the customer's purchase frequency is lower than the critical value, the enterprise can regard it as a potential lost customer. For these customers, the enterprise can take corresponding retention measures, such as providing additional discounts or services to reduce the customer churn rate; for customers with a high purchase frequency, the enterprise can provide more personalized services, such as regularly pushing new product information, exclusive discounts, etc., to enhance their loyalty. By weighting the impact of the average response time, communication frequency and historical purchase times, it reflects their relative importance in the evaluation index. The weights of different factors can be adjusted according to different needs, making the model very adaptable. It is not difficult to see that when the average response time is smaller, the communication frequency is greater, or the historical purchase times are greater, the customer initiative evaluation index is greater.By evaluating the customer initiative assessment index, companies can have a more comprehensive understanding of customer preferences, needs and behavior patterns, enable companies to more accurately locate target customer groups and provide them with more personalized products and services, and promptly discover and solve problems encountered by customers during the experience as well as problems and deficiencies in products and services, so as to make timely improvements and optimizations to improve customer satisfaction and loyalty. It can also be used as one of the indicators to predict future customer behavior and, based on these prediction results, adjust sales strategies and service models in advance to better meet customer needs. By responding to and meeting customers' proactive needs in a timely manner, companies can accelerate the sales process, shorten the sales cycle, and thus improve overall sales efficiency. Further, by optimizing resource allocation, companies can ensure that resources are used more effectively, thereby improving overall operational efficiency and market competitiveness.

[0052] It should be understood that in this embodiment, ω1, ω2 and ω3 are respectively customer initiative evaluation influencing factors corresponding to the average response time, communication frequency and historical purchase times preset in the big data marketing database, which represent the numerical values ​​of the influence of the average response time, communication frequency and historical purchase times on the customer initiative evaluation index. When used, they can be directly obtained from the big data marketing database, and the corresponding relationship can be a preset mapping relationship. For example, the average response time, communication frequency and historical purchase times and the customer initiative evaluation influencing factors corresponding to the average response time, communication frequency and historical purchase times preset in the big data marketing database form a mapping set, and the real-time average response time, communication frequency and historical purchase times are input into the mapping set to obtain the customer initiative evaluation influencing factors corresponding to the average response time, communication frequency and historical purchase times. The mapping relationship can be one-to-one or many-to-one. In this example, its value range is between 0 and 1.

[0053] It should be explained that the customer initiative evaluation index of each customer in each monitoring period in this embodiment is a quantitative indicator obtained by analyzing the average response time, communication frequency and historical purchase times of each customer in each monitoring period, and is used to quantify the customer's initiative level.

[0054] Specifically, the customer behavior characteristic data is processed to obtain the customer purchase desire evaluation index of each customer in each monitoring period. The specific processing process is: the customer behavior characteristic data includes page interaction frequency, page scrolling depth and the number of product comparisons for each browsing.

[0055] The critical page interaction frequency, critical page scrolling depth and critical product comparison times are extracted from the big data marketing database, and the customer purchase desire evaluation index of each customer in each monitoring period is obtained through comprehensive analysis.

[0056] In a specific embodiment, the page interaction frequency refers to the frequency at which a customer performs interactive operations on a product page, including clicks, slides, and zooms, during a monitoring period; the page scroll depth refers to the proportion of the page that a user scrolls down when visiting a product page; and the number of product comparisons refers to the total number of times that users compare products with each other during the monitoring period. The customer's page interaction frequency can be monitored through a CRM tool (Customer Relationship Management), and the customer's page scroll depth and product comparison number can be monitored through server logs.

[0057] Furthermore, the customer purchase desire evaluation index of each customer in each monitoring period is specifically expressed as follows:

[0058]

[0059] Among them, B ij represents the purchase desire evaluation index of the jth customer in the i-th monitoring period, sf ij represents the page interaction frequency of the jth customer in the i-th monitoring period, sf0 represents the critical page interaction frequency, C ij represents the page scrolling depth of the jth customer in the i-th monitoring period, C0 represents the critical page scrolling depth, T ij represents the number of product comparisons of the jth customer in the ith monitoring period, T0 represents the critical number of product comparisons, ρ1 represents the customer purchase desire evaluation influencing factor corresponding to the set page interaction frequency, ρ2 represents the customer purchase desire evaluation influencing factor corresponding to the set page scrolling depth, ρ3 represents the customer purchase desire evaluation influencing factor corresponding to the set number of product comparisons, i represents the number of each monitoring period, i=1,2,3,...,m, m represents the total number of monitoring periods, j represents the number of each customer, j=1,2,3,...,n, n represents the total number of customers.

[0060] The algorithm of this embodiment combines the customer's page interaction frequency, page scrolling depth and product comparison times, and comprehensively analyzes to obtain the customer purchase desire evaluation index of each customer in each monitoring period. Generally speaking, users with a high page interaction frequency tend to have a larger page scrolling depth, because users who frequently interact with the page are more likely to browse the page content in depth, thereby generating a larger scrolling depth; users with a large page scrolling depth are more likely to be exposed to multiple products on the page, thereby increasing the possibility of product comparison. When users scroll on the page, they may see different product recommendations, product introductions or product comparison information, and then compare the products; users with a high page interaction frequency are more likely to actively participate in various activities on the page, including product comparison. By interacting with the page, users can more easily obtain product information, understand product features, and compare with other products. Comprehensive analysis can obtain a more comprehensive, accurate and in-depth customer purchase desire evaluation index.

[0061] It should be explained that the present embodiment considers three key factors, namely, page interaction frequency, page scrolling depth, and product comparison times, which can help enterprises identify high-value customers and potential lost customers, thereby formulating more accurate marketing strategies, such as product push frequency and product discount rate, to improve customers' willingness to buy and loyalty, and help to discover problems and deficiencies in page design, so as to carry out targeted optimization and improve user experience. It can also predict future sales trends, thereby optimizing inventory levels, reducing inventory backlogs and out-of-stock risks, and further providing strong support for enterprises to formulate long-term development strategies and conduct product innovation. By standardizing the page interaction frequency, page scrolling depth, and product comparison times of different customers in different monitoring periods, ensuring that they are compared at the same level, the fairness and comparability of the evaluation are improved. At the same time, the setting of sf0, C0, and T0 helps enterprises to formulate differentiated marketing strategies and service plans. For example, for customers below the critical value, more personalized services, exclusive discounts, or membership privileges can be provided to enhance their satisfaction and loyalty. By weighting the impact of page interaction frequency, page scrolling depth and product comparison times, their relative importance in the evaluation index is reflected. The weights of different factors can be adjusted according to different needs, making the formula highly adaptable. It is not difficult to see that the greater the page interaction frequency, page scrolling depth or product comparison times, the greater the customer purchase desire evaluation index. By evaluating the customer purchase desire evaluation index, it can reflect the customer's willingness and interest in purchasing a specific product, help companies grasp market demand more accurately, understand which products are more popular with customers, and thus adjust product structure and marketing strategies to meet market demand. It can also serve as an important basis for predicting sales trends. By analyzing historical data and current market conditions, predicting customer purchase intentions and trends in the future, it helps companies adjust production plans, inventory management and marketing strategies in advance to cope with market changes, and further helps companies manage customer resources more effectively. Companies can divide customers into different groups based on their purchase intentions and interests, and take corresponding management measures. It also helps companies discover new market opportunities and innovations, and promote innovation and upgrading of products and services.

[0062] It should be understood that, in this embodiment, ρ1, ρ2 and ρ3 are respectively customer purchase desire evaluation influencing factors corresponding to the page interaction frequency, page scrolling depth and product comparison times preset in the big data marketing database, which represent the numerical values ​​of the influence degree of the page interaction frequency, page scrolling depth and product comparison times on the customer purchase desire evaluation index. When used, they can be directly obtained from the big data marketing database, and the corresponding relationship can be a pre-set mapping relationship. For example, the page interaction frequency, page scrolling depth and product comparison times and the customer purchase desire evaluation influencing factors corresponding to the page interaction frequency, page scrolling depth and product comparison times preset in the big data marketing database form a mapping set, and the real-time page interaction frequency, page scrolling depth and product comparison times are input into the mapping set to obtain the customer purchase desire evaluation influencing factors corresponding to the page interaction frequency, page scrolling depth and product comparison times. The mapping relationship can be one-to-one or many-to-one. In this example, its value range is between 0 and 1.

[0063] It should be explained that the customer purchasing desire evaluation index of each customer in each monitoring period in this embodiment is a quantitative indicator obtained by analyzing the page interaction frequency, page scrolling depth and product comparison times of each customer in each monitoring period, and is used to quantify the customer's purchasing desire level.

[0064] Specifically, a customer activity evaluation index of each customer in each monitoring period is obtained through comprehensive analysis. The specific analysis process is: based on the customer initiative evaluation index of each customer in each monitoring period and the customer purchasing desire evaluation index of each customer in each monitoring period, a customer activity evaluation index of each customer in each monitoring period is obtained through comprehensive analysis. The customer activity evaluation index of each customer in each monitoring period is a quantitative indicator obtained by analyzing the customer initiative evaluation index and the customer purchasing desire evaluation index of each customer in each monitoring period.

[0065] Furthermore, the customer activity evaluation index of each customer in each monitoring period is specifically expressed as follows:

[0066] D ij =sinh(θ1*A ij +θ2*B ij );

[0067] Among them, D ij A represents the customer activity evaluation index of the jth customer in the i-th monitoring period, ij represents the customer initiative evaluation index of the jth customer in the ith monitoring period, B ijrepresents the customer purchase desire evaluation index of the jth customer in the ith monitoring period, θ1 represents the customer activity evaluation influencing factor corresponding to the set customer initiative evaluation index, θ2 represents the customer activity evaluation influencing factor corresponding to the set customer purchase desire evaluation index, i represents the number of each monitoring period, i=1,2,3,...,m, m represents the total number of monitoring periods, j represents the number of each customer, j=1,2,3,...,n, n represents the total number of customers.

[0068] like Figure 3 As shown, in a specific embodiment, m = n = 1, θ1 = 0.4, θ2 = 0.3. ij =0.1, the functional relationship between the customer activity evaluation index and the customer purchase desire evaluation index is shown in curve a; when A ij =0.5, the functional relationship between the customer activity evaluation index and the customer purchase desire evaluation index is shown in curve b; when A ij =1, the functional relationship between the customer activity evaluation index and the customer purchase desire evaluation index is shown in curve c.

[0069] The algorithm of this embodiment combines the customer initiative evaluation index and the customer purchase desire evaluation index of each customer in each monitoring period, and comprehensively analyzes to obtain the customer activity evaluation index of each customer in each monitoring period. In many cases, there is a positive correlation between the customer initiative evaluation index and the customer purchase desire evaluation index, that is, when customers show a higher initiative, they tend to also show a stronger willingness to buy. This may be because customers have a strong interest in the product or service and are therefore more willing to interact with the company and learn about relevant information; but in some cases, there may also be a negative correlation between the two indexes. For example, when customers are dissatisfied or disappointed with the company's products or services, they may reduce their interaction with the company, that is, reduce the initiative evaluation index, and at the same time reduce their willingness to buy, that is, reduce the purchase desire evaluation index. Comprehensive analysis can obtain a more comprehensive, accurate, and in-depth customer activity evaluation index.

[0070] It should be explained that two key factors, namely the customer initiative evaluation index and the customer purchase desire evaluation index, are considered in this embodiment, which can help enterprises identify those customers with high purchase potential and loyalty and invest more energy and resources to maintain and develop them, and can also formulate differentiated marketing strategies, such as for customers with high initiative and high purchase desire, more personalized services and discounts can be provided; for customers with low initiative and high purchase desire, their purchase intention can be stimulated through advertising and promotional activities, and when the initiative and purchase desire of customers show a significant decline, the enterprise can timely discover and take measures to intervene, which helps to reduce potential sales risks and losses and ensure the steady development of the enterprise. By weighting the impact of the customer initiative evaluation index and the customer purchase desire evaluation index, it reflects their relative importance in the evaluation index, and the weights of different factors can be adjusted according to different needs, so that the formula has good adaptability. It is not difficult to see that the larger the customer initiative evaluation index or the customer purchase desire evaluation index, the larger the customer activity evaluation index. By evaluating the customer activity assessment index, the customer base can be segmented more finely, which helps companies better meet customer expectations, improve customer satisfaction and loyalty, and further optimize resource allocation, investing more marketing resources in high-value customers to improve marketing efficiency and return on investment. By deeply analyzing customer activity data, companies can discover customer behavior patterns and preference changes, which helps companies adjust marketing strategies and service plans in a timely manner to meet customers' changing needs, thereby enhancing customer stickiness and loyalty.

[0071] It should be understood that in this embodiment, θ1 and θ2 are respectively customer activity assessment influencing factors corresponding to the customer initiative assessment index and the customer purchasing desire assessment index preset in the big data marketing database, which represent the numerical values ​​of the degree of influence of the customer initiative assessment index and the customer purchasing desire assessment index on the customer activity assessment index. When used, they can be directly obtained from the big data marketing database, and their corresponding relationship can be a pre-set mapping relationship. For example, the customer initiative assessment index and the customer purchasing desire assessment index form a mapping set with the customer activity assessment influencing factors corresponding to the customer initiative assessment index and the customer purchasing desire assessment index preset in the big data marketing database. The real-time customer initiative assessment index and the customer purchasing desire assessment index are input into the mapping set to obtain the customer activity assessment influencing factors corresponding to the customer initiative assessment index and the customer purchasing desire assessment index. The mapping relationship can be one-to-one or many-to-one. In this example, its value range is between 0 and 1.

[0072] Specifically, target customers are screened based on the customer activity evaluation index of each customer in each monitoring period. The specific screening process is: according to the customer activity evaluation index of each customer in each monitoring period, the number of times each customer threshold is met and the average activity of each customer are obtained; according to the average activity of each customer and the number of times each customer threshold is met, a comprehensive analysis is performed to obtain the tag value of each customer.

[0073] The target customer marking threshold is extracted from the big data marketing database, and each customer marking value is compared with the target customer marking threshold. If a customer marking value is greater than or equal to the target customer marking threshold, the customer is marked as a target customer. If a customer marking value is less than the target customer marking threshold, the customer is not marked.

[0074] Count the target customers to obtain each target customer.

[0075] Furthermore, based on the customer activity evaluation index of each customer in each monitoring period, the number of times each customer threshold is met and the average activity of each customer are obtained. The specific analysis process is: extracting the customer activity evaluation threshold from the big data marketing database, comparing the customer activity evaluation index of each customer in each monitoring period with the customer activity evaluation threshold, judging whether the customer activity evaluation index of each customer in each monitoring period is greater than or equal to the customer activity evaluation threshold, and marking the number of times the customer activity evaluation index of each monitoring period is greater than or equal to the customer activity evaluation threshold as the number of times the customer threshold is met, and obtaining the number of times each customer threshold is met by statistics.

[0076] The customer activity evaluation index of a customer in each monitoring cycle is accumulated, and the accumulated result is divided by the number of monitoring cycles to obtain the average activity of the customer, and the average activity of each customer is obtained by statistics.

[0077] Specifically, the specific numerical expression of each customer tag value is:

[0078]

[0079] Among them, M j represents the tag value of the jth customer, Ac j represents the average activity of the jth customer, Sa j represents the number of times the threshold is met by the jth customer, Sa0 represents the maximum number of times the threshold is met, β1 represents the customer tag value impact factor corresponding to the set average activity, β2 represents the customer tag value impact factor corresponding to the set number of times the threshold is met, j represents the customer number, j=1,2,3,...,n, and n represents the total number of customers.

[0080] The algorithm of this embodiment combines the number of times each customer threshold is met and the average activity of each customer, and comprehensively analyzes to obtain the mark value of each customer. When the number of times the customer threshold is met increases, it usually means that the customer's activity is also increasing. Because customers need to reach or exceed the threshold set by the enterprise to be included in the statistics of the number of times they are met, the increase in the number of times the customer threshold is met is often accompanied by an increase in the average activity of the customer. This positive correlation indicates that the marketing strategy and service quality of the enterprise may be having a positive impact on customers, prompting them to interact with products or services more frequently; customers who meet the customer threshold more often often have higher loyalty and stickiness to the company's products or services. They are more willing to maintain a long-term cooperative relationship with the company and are willing to pay more for the company's products or services. This increase in loyalty and stickiness will also be reflected in the increase in the average activity of customers, because customers with high loyalty and stickiness are more likely to frequently use the company's products or services, thereby pushing up the overall average activity of customers. Comprehensive analysis can obtain more comprehensive, accurate and in-depth mark values ​​for each customer.

[0081] It should be explained that two key factors are considered in this embodiment, namely the number of times each customer threshold is met and the average activity of each customer, which helps the enterprise to understand the characteristics and needs of each customer group more accurately. For those customers whose current activity is not high but the number of times the threshold is met is gradually increasing, the enterprise can regard them as potential high-value customers and adopt corresponding marketing strategies to cultivate them. By weighting the impact of the number of times each customer threshold is met and the average activity of each customer, it reflects their relative importance in the evaluation index. The weights of different factors can be adjusted according to different needs, making the formula very adaptable. It is not difficult to see that the greater the number of times each customer threshold is met or the average activity of each customer, the greater the mark value of each customer. At the same time, the maximum number of times the threshold is met represented by Sa0 is the same as the total number of monitoring cycles. Its setting helps to ensure that it is compared with the average activity at the same magnitude, which improves the fairness and comparability of the evaluation. By evaluating the tag value of each customer, the company can be provided with a quick overview of customer value and priority, allowing the company to prioritize the most valuable customers and reasonably allocate sales or service resources, thereby improving management efficiency. This helps the company stabilize its customer base, increase market share, and promote long-term customer purchasing behavior. It can also more effectively attract and retain customers through precision marketing, thereby improving marketing effectiveness.

[0082] It should be explained that the tag value of each customer in the present embodiment is a quantitative indicator obtained by analyzing the number of times each customer threshold is met and the average activity of each customer, and is used to quantify the degree to which the customer needs to be tagged. Once the tag value of a user is greater than the target customer tag threshold, the user is tagged. The more active the customer is, the more likely he or she should be tagged as a target customer.

[0083] Specifically, the marketing strategy for each target customer is optimized. The specific process is: according to the customer activity evaluation index of each customer in each monitoring period, the customer activity evaluation index of each target customer in each monitoring period is obtained, and the customer activity evaluation index of a target customer in each monitoring period is sorted in order from large to small, and the marketing strategy corresponding to the monitoring period to which the maximum customer activity evaluation index belongs is extracted and marked as the preferred marketing strategy for the target customer.

[0084] Optimize the initial marketing strategy for each target customer based on the preferred marketing strategy of each target customer.

[0085] It should be explained that, in this embodiment, the customer initiative evaluation index of each target customer in each monitoring period is input into the big data marketing database to match the initial marketing strategy of each target customer in the next monitoring period. The marketing strategy includes product push frequency and product discount rate for different target customers. The product push frequency and discount rate in the initial marketing strategy and the preferred marketing strategy are summed and averaged, marked as the product push frequency and discount rate of the final marketing strategy, and marketing is carried out to the target customers according to the product push frequency and discount rate of the final marketing strategy.

[0086] Reference Figure 2 As shown, the second aspect of the present invention provides a method for a marketing system based on big data, including: collecting customer personality data and customer behavior characteristic data.

[0087] The customer personality data is processed to obtain the customer initiative evaluation index of each customer in each monitoring period, the customer behavior characteristic data is processed to obtain the customer purchase desire evaluation index of each customer in each monitoring period, and the customer activity evaluation index of each customer in each monitoring period is obtained through comprehensive analysis. The target customers are screened based on the customer activity evaluation index of each customer in each monitoring period.

[0088] Optimize the marketing strategy for each target customer.

[0089] The big data marketing database is used to store big data marketing related data, including the critical average response time, the critical communication frequency, the critical number of historical purchases, the customer purchase desire evaluation influencing factor corresponding to the set page interaction frequency, the customer purchase desire evaluation influencing factor corresponding to the set page scrolling depth, the customer purchase desire evaluation influencing factor corresponding to the set product comparison number, the customer activity evaluation influencing factor corresponding to the set customer initiative evaluation index, the customer activity evaluation influencing factor corresponding to the set customer purchase desire evaluation index, the customer tag value influencing factor corresponding to the set average activity, the customer tag value influencing factor corresponding to the set threshold satisfaction number, the customer activity evaluation threshold and the target customer tag threshold.

[0090] The third aspect of the present invention provides a marketing storage medium based on big data, characterized in that it includes: a processor and a memory and a network interface connected to the processor; the network interface is connected to a non-volatile memory in a server; the processor retrieves a computer program from the non-volatile memory through the network interface during operation, and runs the computer program through the memory to execute any one of the methods described above.

[0091] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A marketing system based on big data, characterized in that: include: Data collection module, used to collect customer personality data and customer behavior characteristic data; The customer activity analysis module is used to process customer personality data to obtain the customer initiative evaluation index of each customer in each monitoring period, process customer behavior characteristic data to obtain the customer purchase desire evaluation index of each customer in each monitoring period, conduct comprehensive analysis to obtain the customer activity evaluation index of each customer in each monitoring period, and screen each target customer according to the customer activity evaluation index of each customer in each monitoring period; The marketing strategy adaptation module is used to optimize the marketing strategy for each target customer.

2. The marketing system based on big data according to claim 1, characterized in that: The customer personality data is processed to obtain the customer initiative evaluation index of each customer in each monitoring period. The specific processing process is: The customer personality data includes average response time, communication frequency, and number of historical purchases; The critical average response time, critical communication frequency and critical historical purchase times are extracted from the big data marketing database, and the customer initiative evaluation index of each customer in each monitoring period is obtained through comprehensive analysis. The initial marketing strategy of each customer in the next monitoring period is obtained according to the customer initiative evaluation index of each customer in each monitoring period.

3. The marketing system based on big data according to claim 1, characterized in that: The customer behavior characteristic data is processed to obtain the customer purchase desire evaluation index of each customer in each monitoring period. The specific processing process is as follows: The customer behavior characteristic data includes page interaction frequency, page scrolling depth, and product comparison times; The critical page interaction frequency, critical page scrolling depth and critical product comparison times are extracted from the big data marketing database, and the customer purchase desire evaluation index of each customer in each monitoring period is obtained through comprehensive analysis.

4. The marketing system based on big data according to claim 3 is characterized by: The comprehensive analysis obtains the customer activity evaluation index of each customer in each monitoring period. The specific analysis process is as follows: According to the customer initiative evaluation index of each customer in each monitoring period and the customer purchasing desire evaluation index of each customer in each monitoring period, a comprehensive analysis is performed to obtain the customer activity evaluation index of each customer in each monitoring period. The customer activity evaluation index of each customer in each monitoring period is a quantitative indicator obtained by analyzing the customer initiative evaluation index and the customer purchasing desire evaluation index of each customer in each monitoring period.

5. The marketing system based on big data according to claim 4 is characterized by: The target customers are obtained by screening according to the customer activity evaluation index of each customer in each monitoring period. The specific screening process is as follows: According to the customer activity evaluation index of each customer in each monitoring period, the number of times each customer threshold is met and the average activity of each customer are obtained. According to the average activity of each customer and the number of times each customer threshold is met, the mark value of each customer is obtained through comprehensive analysis; Extracting the target customer marking threshold from the big data marketing database, comparing each customer marking value with the target customer marking threshold, if a customer marking value is greater than or equal to the target customer marking threshold, marking the customer as the target customer, if a customer marking value is less than the target customer marking threshold, not marking the customer; Count the target customers to obtain each target customer.

6. The marketing system based on big data according to claim 5, characterized in that: The customer activity evaluation index analysis of each customer in each monitoring period is used to obtain the number of times each customer threshold is met and the average activity of each customer. The specific analysis process is as follows: Extracting a customer activity evaluation threshold from a big data marketing database, comparing the customer activity evaluation index of each customer in each monitoring period with the customer activity evaluation threshold, determining whether the customer activity evaluation index of each customer in each monitoring period is greater than or equal to the customer activity evaluation threshold, and marking the number of times the customer activity evaluation index of each monitoring period is greater than or equal to the customer activity evaluation threshold as the number of times the customer threshold is satisfied, and obtaining the number of times each customer threshold is satisfied by statistics; The customer activity evaluation index of a customer in each monitoring cycle is accumulated, and the accumulated result is divided by the number of monitoring cycles to obtain the average activity of the customer, and the average activity of each customer is obtained by statistics.

7. The marketing system based on big data according to claim 2, characterized in that: The specific process of optimizing the marketing strategy for each target customer is as follows: According to the customer activity evaluation index of each customer in each monitoring period, the customer activity evaluation index of each target customer in each monitoring period is obtained, and the customer activity evaluation index of a target customer in each monitoring period is sorted in descending order, and the marketing strategy corresponding to the monitoring period to which the maximum customer activity evaluation index belongs is extracted and marked as the preferred marketing strategy for the target customer; Optimize the initial marketing strategy for each target customer based on the preferred marketing strategy of each target customer.

8. The marketing system based on big data according to claim 3 is characterized by: The specific numerical expression of the customer purchase desire evaluation index of each customer in each monitoring period is: Among them, B ij represents the purchase desire evaluation index of the jth customer in the i-th monitoring period, sf ij represents the page interaction frequency of the jth customer in the i-th monitoring period, sf0 represents the critical page interaction frequency, C ij represents the page scrolling depth of the jth customer in the i-th monitoring period, C0 represents the critical page scrolling depth, T ij represents the number of product comparisons of the jth customer in the ith monitoring period, T0 represents the critical number of product comparisons, ρ1 represents the customer purchase desire evaluation influencing factor corresponding to the set page interaction frequency, ρ2 represents the customer purchase desire evaluation influencing factor corresponding to the set page scrolling depth, ρ3 represents the customer purchase desire evaluation influencing factor corresponding to the set number of product comparisons, i represents the number of each monitoring period, i=1,2,3,...,m, m represents the total number of monitoring periods, j represents the number of each customer, j=1,2,3,...,n, n represents the total number of customers.

9. A method for a marketing system based on big data as described in any one of claims 1 to 8, characterized in that: include: Collect customer personality data and customer behavior characteristic data; The customer personality data is processed to obtain the customer initiative evaluation index of each customer in each monitoring period, the customer behavior characteristic data is processed to obtain the customer purchase desire evaluation index of each customer in each monitoring period, and the customer activity evaluation index of each customer in each monitoring period is obtained through comprehensive analysis. The target customers are screened according to the customer activity evaluation index of each customer in each monitoring period; Optimize the marketing strategy for each target customer.

10. A marketing storage medium based on big data, characterized in that: include: Processors and memory and network interfaces connected to the processors; The network interface is connected to a non-volatile memory in the server; When running, the processor retrieves a computer program from the non-volatile memory through the network interface, and runs the computer program through the memory to execute the method described in any one of claims 1 to 8.

Images