Marketing management method and system based on big data analysis

Abstract

The invention discloses a marketing management method and system based on big data analysis, and relates to the technical field of marketing management, and the method comprises the steps: analyzing the behavior data of a marketing target user, and constructing a marketing target user portrait; outputting a marketing strategy of the marketing target user and the associated user through the behavior record of the associated user in combination with the portrayal analysis of the marketing target user; adjusting marketing strategies of the marketing target user and the associated user based on the market data; the adjusted marketing strategy is applied to market activities, and the marketing process and the market risk condition are monitored in real time; marketing achievements of all stages are obtained based on real-time monitoring, the marketing achievements are analyzed, a marketing change trend is recognized, a marketing strategy optimization mechanism is triggered based on the marketing change trend, and a marketing strategy is adjusted and optimized. Accurate marketing, strategy dynamic adjustment and resource optimal configuration are realized, and the marketing efficiency and effect are remarkably improved.

Description

Technical Field

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

[0002] With the intensification of market competition and the development of globalization, consumers' behavioral habits and preferences have become more and more diverse. Consumers expect companies to provide more personalized products and services, prompting companies to shift from a product-centric to a user-centric marketing approach. With the popularization of the Internet, mobile devices and the Internet of Things, users generate a large amount of data on the Internet every day, such as browsing history, social interactions, and purchasing behavior. Massive data includes not only structured data (such as transaction records, user information), but also a large amount of unstructured data (such as comments, social media content, images). The development of big data technology makes it possible to analyze and process these complex data.

[0003] Traditional user profiling technology mainly relies on basic user information and static behavior data, which cannot fully identify users' dynamic needs and complex behavior patterns, resulting in inaccurate user profiling. In addition, the identification and analysis of related users are relatively limited, making it difficult to achieve broader and more targeted coverage. Traditional marketing strategies are mostly based on pre-made plans and lack the ability to adjust in real time. When the market environment or user needs change, marketing strategies are difficult to respond in a timely manner, resulting in weakened marketing effects and low user stickiness and repurchase rates. Market changes and external risks cannot be controlled in a timely manner, and marketing strategies are difficult to respond in a timely manner when faced with sudden market changes, resulting in companies being at a disadvantage in competition and inefficient resource allocation.

[0004] Therefore, in response to the above problems, there is an urgent need for a marketing management method and system based on big data analysis. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a marketing management method and system based on big data analysis, which solves the problems of inaccurate target user positioning, lack of personalization and flexibility in marketing strategies, and unreasonable resource allocation in marketing.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a marketing management method based on big data analysis, comprising the following steps: obtaining marketing target user behavior data and market data; analyzing the marketing target user behavior data, constructing a marketing target user portrait, and identifying the associated users of the marketing target user; analyzing the behavior records of the associated users, and combining the marketing target user portrait, outputting the marketing strategies of the marketing target users and the associated users; adjusting the marketing strategies of the marketing target users and the associated users based on the market data and generating marketing priorities; applying the adjusted marketing strategies to market activities, and monitoring the marketing process and market risk status in real time; obtaining the marketing results of each stage based on the real-time monitoring of the marketing process, analyzing the marketing results, and identifying the marketing change trends, and the specific marketing change trends include market change trends and user retention trends; triggering the marketing strategy optimization mechanism based on the marketing change trends, and adjusting and optimizing the marketing strategies.

[0007] Furthermore, the marketing target user behavior data specifically includes the user's online browsing history, purchase history, click behavior, search keywords and social media interaction information; the market data specifically includes sales fluctuation data of each product, sales fluctuation data of competing products, and market share.

[0008] Further, the behavior data of the marketing target users is analyzed, a marketing target user portrait is constructed, and the specific analysis of identifying the associated users of the marketing target users is as follows: the user's online browsing records, purchase history, click behavior and search keywords are deduplicated, denoised and missing values ​​are filled, and then the user's online browsing records, purchase history, click behavior and search keywords are normalized; the age, gender and occupation of the marketing target users are identified based on the social media interaction information of the marketing target users; the consumption frequency of each type of goods of the user and the browsing proportion of each type of goods are extracted based on the normalized online browsing records, purchase history, click behavior and search keywords; the age, gender, occupation of the marketing target users and the consumption frequency of each type of goods and the browsing proportion of each type of goods are combined to generate a marketing target user portrait; the social media interaction information of the marketing target users is extracted, and the top three users who interact with the marketing target users are screened out and marked as associated users.

[0009] Furthermore, by analyzing the behavior records of associated users and combining them with the portraits of marketing target users, the specific analysis of the marketing strategies of marketing target users and associated users is output as follows: behavioral data of associated users are obtained, and then the consumption frequency of each type of commodity of associated users and the browsing proportion of each type of commodity are extracted through the online browsing records, purchase histories, click behaviors and search keywords of associated users; according to the consumption frequency of each type of commodity of associated users and the browsing proportion of each type of commodity, the portraits of each associated user of the marketing target user are combined to obtain; the portraits of the marketing target users and the portraits of each associated user of the marketing target users are normalized and quantified to obtain the unique feature value of the portrait of the marketing target users and the unique feature value of the portraits of each associated user of the marketing target users; the unique feature value of the portrait of the marketing target users and the unique feature value of the portraits of each associated user of the marketing target users are normalized and quantified to obtain the unique feature value of the portrait of the marketing target users and the unique feature value of the portraits of each associated user of the marketing target users; The unique characteristic value of the portrait of each associated user and the unique characteristic value of each marketing product are calculated to obtain the Euclidean distance between the unique characteristic value of the portrait of the marketing target user and the unique characteristic value of each marketing product, as well as the Euclidean distance between the unique characteristic value of the portrait of each associated user of the marketing target user and the unique characteristic value of each marketing product; the Euclidean distance between the unique characteristic value of the portrait of the marketing target user and the unique characteristic value of each marketing product, as well as the Euclidean distance between the unique characteristic value of the portrait of each associated user of the marketing target user and the unique characteristic value of each marketing product are compared with the distance threshold respectively, and the marketing products whose Euclidean distance is greater than the distance threshold are screened out, and the remaining marketing products are output as the marketing strategy for the marketing target users and the associated users, and then the marketing strategy for the marketing target users and the associated users is adjusted according to the market data.

[0010] Furthermore, the specific analysis of the marketing strategy for marketing target users and associated users based on market data is: respectively obtaining sales fluctuation data of marketing products, sales fluctuation data of competing products, and market share output for marketing target users and associated users; the sales fluctuation data is specifically sales quantity; the sales quantity of marketing products, the sales quantity of competing products, and the market share are respectively compared with the sales upper and lower thresholds and the market share upper and lower thresholds; when the sales quantity of the marketing product is not included in the sales upper and lower thresholds, or the sales quantity of the competing product is not included in the sales upper and lower thresholds, or the market share is not included in the market share upper and lower thresholds, providing a promotion strategy for the marketing product, providing advertising for the marketing product on multiple platforms, and at the same time giving priority to marketing recommendations for the marketing product according to the size of its market share.

[0011] Furthermore, based on real-time monitoring of the marketing process, the marketing results of each stage are obtained, the marketing results are analyzed, and the specific analysis of the marketing change trend is identified as follows: the marketing results of each stage specifically include market demand, marketing product conversion rate, user repurchase rate and related user conversion rate; the market demand, marketing product conversion rate, user repurchase rate and related user conversion rate of each stage are converted into data points respectively, and then various types of data points are connected respectively to obtain a line graph of market demand changes, a line graph of marketing product conversion rate changes, a line graph of user repurchase rate changes and a line graph of related user conversion rate changes; market change trends are identified based on the line graph of market demand changes and the line graph of marketing product conversion rate changes, and user retention trends are identified based on the line graph of user repurchase rate changes and the line graph of related user conversion rate changes; the identification of market change trends specifically includes: The method is as follows: when both the line graph of market demand changes and the line graph of marketing product conversion rate changes show an upward trend, the market change trend is upward; when both the line graph of market demand changes and the line graph of marketing product conversion rate changes show a downward trend, the market change trend is downward; when the rising and falling trends of the line graph of market demand changes and the line graph of marketing product conversion rate changes are inconsistent, the market change trend is not considered; the identification of user retention trend is specifically as follows: when both the line graph of user repurchase rate changes and the line graph of related user conversion rate changes show an upward trend, the user retention trend is upward; when both the line graph of user repurchase rate changes and the line graph of related user conversion rate changes show a downward trend, the user retention trend is downward; when the rising and falling trends of the line graph of user repurchase rate changes and the line graph of related user conversion rate changes are inconsistent, the user retention trend is not considered.

[0012] Furthermore, based on the marketing change trend triggering the marketing strategy optimization mechanism, the specific adjustments and optimizations to the marketing strategy include: when the market change trend and the user retention trend are both on the rise, providing promotion strategies for marketing products, and providing advertising for marketing products on multiple platforms; when the market change trend and the user retention trend are both on the decline, triggering the marketing target user portrait and the portrait update strategy of each associated user of the marketing target user, and then changing and adjusting the marketing products, providing promotion strategies for the changed and adjusted marketing products, and providing advertising for the changed and adjusted marketing products on multiple platforms.

[0013] A marketing management system based on big data analysis, applying the above-mentioned marketing management method based on big data analysis, includes: a data acquisition module, used to acquire marketing target user behavior data and market data; a user analysis module, used to analyze the marketing target user behavior data, build a marketing target user portrait, and identify the associated users of the marketing target user; a marketing strategy output module, used to analyze the behavior records of the associated users, and output the marketing strategy of the marketing target user and the associated users in combination with the marketing target user portrait; a sequence adjustment module, used to adjust the marketing strategy of the marketing target user and the associated users based on the market data and generate a marketing priority; a real-time monitoring module, used to apply the adjusted marketing strategy to market activities, and monitor the marketing process and market risk status in real time; a marketing change trend identification module, used to obtain the marketing results of each stage based on the real-time monitoring of the marketing process, analyze the marketing results, and identify the marketing change trend, and the specific marketing change trend includes the market change trend and the user retention trend; an optimization adjustment module, used to trigger the marketing strategy optimization mechanism based on the marketing change trend, and adjust and optimize the marketing strategy.

[0014] The present invention has the following beneficial effects:

[0015] Through in-depth analysis of the user behavior data of the marketing target, an accurate user portrait can be constructed, which can clearly depict the user's preferences, needs, and purchasing habits, laying the foundation for the formulation of personalized marketing strategies; identifying related users can enable marketing to cover the relevant user groups more accurately and improve marketing efficiency and effectiveness; through market data and real-time monitoring, marketing strategies can be flexibly adjusted and optimized to ensure that marketing activities are always consistent with market changes and user needs; incorporating marketing change trends based on real-time data feedback into the optimization mechanism of marketing strategies will help to adjust marketing directions in a timely manner and avoid waste of resources due to outdated or wrong strategies; adjusting marketing strategies according to the real-time performance and changing trends of the market will ensure that the company always responds to market demand in the best state and improves market competitiveness; through real-time monitoring of marketing activities, the marketing process and market risks can be controlled in real time, potential problems can be discovered and adjusted quickly, and marketing activities can be avoided from being affected by external risks; based on big data analysis, marketing strategies can quickly respond to market dynamics and ensure that marketing activities have high adaptability and flexibility; combining market data and user behavior data, marketing priorities can be automatically output to help companies reasonably allocate marketing resources, concentrate on making efficient marketing decisions, and improve the return on investment of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of a marketing management method based on big data analysis of the present invention.

[0017] Figure 2 This is a structural diagram of a marketing management system based on big data analysis of the present invention. DETAILED DESCRIPTION

[0018] The embodiment of the present application realizes precise marketing, dynamic adjustment of strategies and optimal allocation of resources through a marketing management method and system based on big data analysis, which significantly improves the efficiency and effectiveness of marketing.

[0019] The overall idea for solving the problems in the embodiments of the present application is: based on big data analysis, through comprehensive analysis of marketing target users and market data, accurate formulation, dynamic optimization and real-time adjustment of marketing strategies are achieved to improve marketing effectiveness, user retention rate and market competitiveness.

[0020] See also Figure 1 The embodiment of the present invention provides a technical solution: a marketing management method based on big data analysis, comprising the following steps: obtaining marketing target user behavior data and market data; analyzing the marketing target user behavior data, constructing a marketing target user portrait, and identifying the associated users of the marketing target user; analyzing the behavior records of the associated users, and combining the marketing target user portrait, outputting the marketing strategy of the marketing target user and the associated users; adjusting the marketing strategy of the marketing target user and the associated users based on the market data and generating a marketing priority; applying the adjusted marketing strategy to market activities, and monitoring the marketing process and market risk status in real time; obtaining the marketing results of each stage based on the real-time monitoring of the marketing process, analyzing the marketing results, and identifying the marketing change trend, and the specific marketing change trend includes the market change trend and the user retention trend; triggering the marketing strategy optimization mechanism based on the marketing change trend, and adjusting and optimizing the marketing strategy.

[0021] Specifically, the marketing target user behavior data specifically includes the user's online browsing history, purchase history, click behavior, search keywords and social media interaction information; the market data specifically includes the sales fluctuation data of each product, the sales fluctuation data of competing products, and market share.

[0022] In this implementation scheme, online browsing history refers to the pages, products, time, length of stay, etc. browsed by users on a website or application, and is obtained through the website or application's log recording system, browser history, tracking tools (such as Google Analytics, Hotjar, etc.); purchase history refers to information such as products purchased by users in the past, purchase time, purchase frequency, purchase amount, etc., and is obtained through e-commerce platforms, POS systems, CRM (customer relationship management) systems or transaction records; click behavior refers to the advertisements, product links, buttons or other interactive elements clicked by users, and is obtained through tracking codes, reporting systems of advertising platforms (such as Facebook Ads and Google Ads); search keywords refer to the words or phrases searched by users on search engines or websites, reflecting the users' needs, interests or intentions, and are obtained through the website's search engine or platform (such as Google Search Console, search logs within the website); social media interaction information refers to the user's interaction on social media platforms, including likes, comments, shares, follows, etc., and is obtained through social media analysis tools (such as Facebook Insights, Twitter Insights, etc.); Analytics) or API to crawl data; sales fluctuation data of each product represents the sales changes of a specific product in different time periods, showing the peaks and troughs of demand, and is obtained through sales records of sales systems, ERP systems or online stores; sales fluctuation data of competing products represents the sales changes of competitors, helping to evaluate the competitive situation in the market, and is obtained through third-party market research reports, competition analysis tools (such as SimilarWeb, SEMrush, etc.) or industry reports; market share represents the proportion of a specific brand or product in the entire market, measured by sales or sales volume, and is obtained through industry analysis reports, market research data, company financial reports or market reports provided by third-party data companies.

[0023] Specifically, the behavior data of marketing target users are analyzed, a marketing target user portrait is constructed, and the specific analysis of identifying the associated users of the marketing target users is as follows: the user's online browsing records, purchase history, click behavior and search keywords are deduplicated, denoised and missing values ​​are filled, and then the user's online browsing records, purchase history, click behavior and search keywords are normalized; the age, gender and occupation of the marketing target user are identified based on the social media interaction information of the marketing target user; the consumption frequency of each type of commodity of the user and the browsing proportion of each type of commodity are extracted based on the normalized online browsing records, purchase history, click behavior and search keywords; the age, gender, occupation of the marketing target user and the consumption frequency of each type of commodity and the browsing proportion of each type of commodity are combined to generate a marketing target user portrait; the social media interaction information of the marketing target user is extracted, and the top three users who interact with the marketing target user are screened out and marked as associated users.

[0024] In this implementation scheme, normalization processing specifically means unifying data of different magnitudes into a standard range (e.g., 0 to 1) to make the comparison between different data more fair, and specifically, numerical normalization is performed through data processing tools (e.g., Python's Pandas library, Excel, etc.); the user's age, gender, and occupation are identified through social media interaction information or other registration information, and specifically extracted through the user's public information on the social platform or through questionnaires and information filled out during registration; the consumption frequency of goods indicates the purchase frequency of users under a certain category of goods (e.g., the number of times a user purchases a certain category of goods per month), and the browsing percentage indicates the proportion of users' total browsing behavior when browsing a certain category of goods. The consumption frequency and browsing percentage are specifically identified and obtained by analyzing the user's purchase history record and online browsing record (including product category, browsing time, page dwell time, etc.); the interaction frequency refers to the number of interactions between the marketing target user and a certain content, platform or service of other users, including clicks, comments, shares, likes, etc., and is an important indicator for measuring user association, and is specifically obtained by using analytical tools (e.g., Google Analytics, Facebook Insights, etc.) to track and record user interaction behaviors, or by using statistical data on user interactions provided by social media platforms.

[0025] Specifically, by analyzing the behavior records of associated users and combining them with the portraits of marketing target users, the specific analysis of the marketing strategies of marketing target users and associated users is output as follows: behavioral data of associated users is obtained, and then the consumption frequency of various commodities of associated users and the browsing proportion of various commodities are extracted through the online browsing records, purchase histories, click behaviors and search keywords of associated users; the consumption frequency of various commodities of associated users and the browsing proportion of various commodities are combined to obtain the portraits of each associated user of the marketing target user; the portraits of the marketing target users and the portraits of each associated user of the marketing target users are normalized and quantified to obtain the unique characteristic value of the portrait of the marketing target users and the unique characteristic value of the portraits of each associated user of the marketing target users; the unique characteristic value of the portrait of the marketing target users, the unique characteristic value of the portraits of each associated user of the marketing target users and the unique characteristic value of each marketing product are calculated to obtain the Euclidean distance between the unique characteristic value of the portrait of the marketing target users and the unique characteristic value of each marketing product, as well as the unique characteristic value of the marketing target users. The Euclidean distance between the unique feature value of the portrait of each associated user of the marketing target user and the unique feature value of each marketing product is calculated. The specific Euclidean distance calculation expression is: d=|AP|, where d represents the Euclidean distance between the unique feature value of the portrait of the marketing target user and the unique feature value of each marketing product or the Euclidean distance between the unique feature value of the portrait of each associated user of the marketing target user and the unique feature value of each marketing product, A represents the unique feature value of the portrait of the marketing target user or the unique feature value of each marketing product, and P represents the unique feature value of the marketing product; the Euclidean distance between the unique feature value of the portrait of the marketing target user and the unique feature value of each marketing product and the Euclidean distance between the unique feature value of the portrait of each associated user of the marketing target user and the unique feature value of each marketing product are compared with the distance threshold respectively, and the marketing products whose Euclidean distance is greater than the distance threshold are screened out, and the remaining marketing products are output as the marketing strategy for the marketing target users and the associated users, and then the marketing strategy for the marketing target users and the associated users is adjusted according to the market data.

[0026] In this implementation scheme, by analyzing the behavioral data of marketing target users and their associated users and combining them with product features, personalized marketing strategies can be generated for each user group, which can not only help predict user needs, but also improve the accuracy of advertising and product promotions and increase conversion rates; by identifying associated users and combining their behavioral data, social effects can be used to promote marketing, which helps to discover potential needs and interests, thereby expanding the marketing target user group; generating marketing strategies through data analysis reduces decision-making that relies on intuition and experience, improves the scientific nature and accuracy of the strategies, and normalization and similarity calculations ensure fair comparison of different data sources and provide a more objective perspective.

[0027] The unique feature value of the marketing target user portrait represents a quantitative representation of the core feature set used to uniquely identify and describe the marketing target user. It integrates multiple dimensional information of the target user, including age, gender, occupation, consumption frequency of various commodities and browsing proportion of various commodities, to form a unique identifier. Specifically, the user's age, gender, occupation, consumption frequency of various commodities and browsing proportion of various commodities are encoded, and then combined into a unique feature value according to a certain algorithm or model; the unique feature value of the portrait of each associated user of the marketing target user represents a quantitative representation of the core feature set of the associated user, which is used to describe the characteristics and preferences of the associated user. The characteristics of the associated user are extracted and encoded, and then combined into a unique feature value based on the extracted characteristics to represent the unique feature value of the portrait of the associated user; the unique feature value of each marketing product represents a quantitative representation of the core feature set of each marketing product, which is used to describe the attributes and characteristics of the product. Specifically, key attributes are extracted from the product description, classification, market status, and user repurchase status, the extracted product attributes are encoded, and combined into a unique feature value according to certain rules or algorithms.

[0028] The specific unique feature value can also be obtained by weighted comprehensive calculation of each feature. The calculation expression is: In the formula, S represents the unique eigenvalue, i represents the number of each feature, n represents the total number of features, and α i represents the specific value of the i-th feature, f i Indicates the weight of the ith feature, which is set by professionals in the relevant field or by the relative importance of each feature. Specifically, for the unique feature value of the marketing target user portrait, each feature is the user's age, gender, occupation, consumption frequency of each type of goods, and browsing proportion of each type of goods; for the unique feature value of the associated user portrait, each feature is the consumption frequency of each type of goods of the associated user and browsing proportion of each type of goods; for the unique feature value of each marketing product, each feature is the product consumer age, product audience gender, product repurchase rate, and product market share.

[0029] The distance threshold is set based on experience or optimized through a machine learning algorithm based on historical data. It is used to determine whether the similarity between the marketing product and the user portrait is high enough to decide whether to recommend the product. Data such as market trends, competitor analysis, and user feedback are included to adjust and optimize marketing strategies.

[0030] Specifically, the specific analysis of the marketing strategy for marketing target users and related users based on market data is as follows: respectively obtain the sales fluctuation data of marketing products, sales fluctuation data of competing products, and market share for marketing target users and related users; the sales fluctuation data is specifically sales quantity; the sales quantity of marketing products, the sales quantity of competing products, and the market share are compared with the upper and lower sales thresholds and the upper and lower market share thresholds respectively; when the sales quantity of the marketing product is not included in the upper and lower sales thresholds, or the sales quantity of the competing product is not included in the upper and lower sales thresholds, or the market share is not included in the upper and lower market share thresholds, provide promotion strategies for the marketing products, provide advertising for the marketing products on multiple platforms, and at the same time give priority to marketing recommendations for the marketing products according to the size of their market share.

[0031] In this implementation scheme, by analyzing sales fluctuation data, sales fluctuation data of competing products and market share, it is possible to identify which products have poor performance or large sales fluctuations, so as to provide targeted promotion strategies for these products. For example, when the sales volume of a product is below a certain threshold, sales can be increased through promotional activities; according to the performance of sales fluctuations and market share, the design can give priority to recommending products with a large market share for marketing, thereby increasing market share and product exposure. This strategy helps to improve the efficiency of the use of marketing budgets; combined with multi-platform advertising, it can increase product visibility, attract more potential customers, and enhance product market performance; through real-time monitoring of sales fluctuation data and market share, marketing strategies can be adjusted in a timely manner to avoid the ineffectiveness of marketing strategies due to market fluctuations, and ensure that strategies are adapted to market dynamics.

[0032] The upper and lower sales thresholds are used to determine whether the sales volume of a product meets the expected standards. If the sales volume of a product is lower than the lower threshold or higher than the upper threshold, it means that the sales status of the product is abnormal and a promotion strategy needs to be adopted. By analyzing the sales data of the product over a period of time, the range of sales fluctuations can be calculated and the upper and lower ranges of regular sales can be determined. Specifically, the sales fluctuation range can be determined based on the standard deviation and mean of the product's historical sales volume. The upper and lower thresholds are set to the mean of the sales volume plus or minus one standard deviation. You can also set reasonable sales thresholds by observing the sales data of similar competing products and combining market trends.

[0033] The upper and lower thresholds of market share are used to determine whether the product's share in the market is in line with expectations. If the market share is lower than the threshold, the market share can be increased through promotional means or other marketing activities. If the market share is higher, the product can be recommended as a priority to increase its market coverage. By analyzing the product's past market share, calculating the average and fluctuation range, a reasonable market share threshold can be obtained. Specifically, the market share can be estimated by the sales share of a certain type of product in the market over a certain period of time. The market share standard that the product should achieve can also be determined in combination with the market share of competing products, or the overall market share distribution of the industry can be understood through third-party market research reports or industry data, and reasonable market share thresholds can be set based on this.

[0034] The sales fluctuation data of marketing products refers to the changes in the sales quantity of products in different time periods. It is used to analyze the stability or volatility of product sales. It obtains historical sales data through sales records of e-commerce platforms or POS systems, ERP systems, or through industry market research reports, identifies sales fluctuations of marketing products, and understands product sales trends. The sales fluctuation data of competing products helps evaluate the market competition situation and judge the performance of target products in the market. The sales quantity and fluctuation data of competing products are obtained through third-party market research data and competition analysis tools (such as SimilarWeb, SEMrush). The sales situation of specific products can also be obtained through competition reports provided by market research companies.

[0035] Specific promotional strategies include discounts, coupons, limited-time sales, etc.; multi-platform advertising is used to increase product exposure, attract more potential customers, and give priority to products with a larger market share to increase their exposure opportunities and further expand market share.

[0036] Specifically, based on the real-time monitoring of the marketing process, the marketing results of each stage are obtained, the marketing results are analyzed, and the specific analysis of the marketing change trend is identified as follows: the marketing results of each stage specifically include market demand, marketing product conversion rate, user repurchase rate and related user conversion rate; the market demand, marketing product conversion rate, user repurchase rate and related user conversion rate of each stage are converted into data points respectively, and then various data points are connected respectively to obtain a line graph of market demand changes, a line graph of marketing product conversion rate changes, a line graph of user repurchase rate changes and a line graph of related user conversion rate changes; the market change trend is identified based on the line graph of market demand changes and the line graph of marketing product conversion rate changes, and the user retention trend is identified based on the line graph of user repurchase rate changes and the line graph of related user conversion rate changes; the identification of market change trends is specifically as follows: : When both the line graph of market demand changes and the line graph of marketing product conversion rate changes show an upward trend, the market change trend is upward; when both the line graph of market demand changes and the line graph of marketing product conversion rate changes show a downward trend, the market change trend is downward; when the rising and falling trends of the line graph of market demand changes and the line graph of marketing product conversion rate changes are inconsistent, the market change trend is not considered; identifying user retention trends specifically: when both the line graph of user repurchase rate changes and the line graph of related user conversion rate changes show an upward trend, the user retention trend is upward; when both the line graph of user repurchase rate changes and the line graph of related user conversion rate changes show a downward trend, the user retention trend is downward; when the line graph of user repurchase rate changes and the line graph of related user conversion rate changes are inconsistent, the user retention trend is not considered.

[0037] In this implementation plan, by real-time monitoring of the marketing results at each stage, changes in the market and user behavior can be discovered in a timely manner, and marketing strategies can be quickly responded to and adjusted; by analyzing various indicators, companies can make more scientific decisions based on data rather than relying on intuition or experience; systematic analysis methods help companies identify market trends and user retention trends, which is of great significance for formulating long-term marketing strategies; by analyzing the marketing results at each stage, companies can better allocate marketing resources and focus on high-potential markets and user groups.

[0038] Market demand refers to the demand for products in the target market, which is obtained through market research, sales data analysis, etc.; marketing product conversion rate refers to the proportion of users who actually purchase products after being exposed to marketing activities, which is obtained through user behavior tracking and sales data; user repurchase rate refers to the proportion of users who have already purchased a product and then purchase it again, which is obtained through customer database analysis; associated user conversion rate refers to the proportion of other users associated with a certain user who are converted into buyers, which is calculated through social network analysis or recommendation system; change line graph specifically uses data visualization tools (such as Excel, Tableau, Python's Matplotlib, etc.) to plot the sorted data points into a line graph to facilitate the observation of changing trends.

[0039] Specifically, based on the marketing change trend, the marketing strategy optimization mechanism is triggered, and the marketing strategy is adjusted and optimized including: when the market change trend and the user retention trend are both on the rise, a promotion strategy is provided for the marketing product, and advertising of the marketing product is provided on multiple platforms; when the market change trend and the user retention trend are both on the decline, the marketing target user portrait and the portrait update strategy of each associated user of the marketing target user are triggered, and the marketing product is changed and adjusted, a promotion strategy is provided for the changed and adjusted marketing product, and advertising of the changed and adjusted marketing product is provided on multiple platforms.

[0040] In this implementation plan, by real-time monitoring of market and user retention trends, marketing strategies can be adjusted in a timely manner to adapt to changes in the external environment and ensure the effectiveness of marketing activities; when both market and user retention are increasing, promotional strategies and advertising can be targeted at potential user groups to improve conversion rates; and when market and user retention are declining, updating user portraits helps companies understand the needs of target users more clearly, thereby formulating more accurate marketing strategies; according to changes in the market and user retention, the channels and content of advertising are optimized to avoid wasting resources on channels with poor results and improve overall marketing efficiency; timely adjustment and optimization of products and their marketing strategies can better meet user needs, thereby improving user satisfaction and loyalty and reducing churn; through targeted promotional strategies and multi-platform advertising, new users can be effectively attracted and existing users can be retained, thereby promoting sales and revenue growth and enhancing the company's ability to respond to market fluctuations.

[0041] See also Figure 2, a marketing management system based on big data analysis, applying the above-mentioned marketing management method based on big data analysis, including: a data acquisition module, used to acquire marketing target user behavior data and market data; a user analysis module, used to analyze the marketing target user behavior data, build a marketing target user portrait, and identify the associated users of the marketing target user; a marketing strategy output module, used to analyze the behavior records of the associated users, and output the marketing strategy of the marketing target user and the associated users in combination with the marketing target user portrait; a sequence adjustment module, used to adjust the marketing strategy of the marketing target user and the associated users based on the market data and generate a marketing priority; a real-time monitoring module, used to apply the adjusted marketing strategy to market activities, and monitor the marketing process and market risk status in real time; a marketing change trend identification module, used to obtain the marketing results of each stage based on the real-time monitoring of the marketing process, analyze the marketing results, and identify the marketing change trend, and the specific marketing change trend includes the market change trend and the user retention trend; an optimization adjustment module, used to trigger the marketing strategy optimization mechanism based on the marketing change trend, and adjust and optimize the marketing strategy.

[0042] In summary, this application has at least the following effects:

[0043] By acquiring and analyzing the behavioral data of marketing target users, accurate user portraits can be constructed to accurately locate target users; by identifying the associated users of marketing target users and analyzing the behavioral records of these associated users, the marketing scope can be further expanded and potential customer groups can be discovered; by adjusting marketing strategies based on market data, it can be ensured that marketing strategies keep pace with market changes and improve the flexibility and adaptability of strategies; generating marketing priorities helps companies allocate resources reasonably and invest limited resources in the most promising markets and user groups; based on real-time monitoring of the marketing process and analysis of marketing results, companies can identify marketing trends, including market trends and user retention trends; through precise marketing strategies and personalized services, companies can better meet user needs and expectations, improve user satisfaction and loyalty, and bring continuous business growth and profit improvement to the company.

[0044] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods and systems. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0045] The present invention is described with reference to the flowcharts and structure diagrams of the methods and systems according to the embodiments of the present invention. It should be understood that each process and combination of modules in the flowcharts and structure diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts. Figure 1 process or multiple processes and structures Figure 1 A device that specifies functionality in a module or modules.

[0046] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 process or multiple processes and structures Figure 1 A function specified in a module or multiple modules.

[0047] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 process or multiple processes and structures Figure 1 Steps to specify functionality in a module or multiple modules.

[0048] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0049] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A marketing management method based on big data analysis, characterized in that: The following steps are involved: Obtain marketing target user behavior data and market data; Analyze the behavior data of marketing target users, build marketing target user portraits, and identify the associated users of marketing target users; Analyze the behavior records of related users and combine them with the marketing target user portrait to output the marketing strategy for the marketing target users and related users; Adjust the marketing strategies for target users and associated users based on market data and generate marketing priorities; Apply the adjusted marketing strategies to market activities and monitor the marketing process and market risk status in real time; Based on real-time monitoring of the marketing process, we can obtain marketing results at each stage, analyze the marketing results, and identify marketing change trends. Specific marketing change trends include market change trends and user retention trends. Trigger the marketing strategy optimization mechanism based on the marketing change trend and adjust and optimize the marketing strategy.

2. The marketing management method based on big data analysis according to claim 1, characterized in that: The marketing target user behavior data specifically includes the user's online browsing history, purchase history, click behavior, search keywords and social media interaction information; The market data specifically includes sales fluctuation data of each product, sales fluctuation data of competing products, and market share.

3. The marketing management method based on big data analysis according to claim 2 is characterized in that: Analyze the marketing target user behavior data, build a marketing target user portrait, and identify the marketing target user's associated users. The specific analysis is as follows: Remove duplication, denoise, and fill missing values ​​from users' online browsing records, purchase history, click behaviors, and search keywords, and then normalize them; Extract the social media interaction information of marketing target users to identify their age, gender and occupation; Based on the normalized online browsing records, purchase history, click behavior and search keywords, extract the consumption frequency of each type of goods and the browsing proportion of each type of goods; Combine the target user's age, gender, occupation, consumption frequency of each product, and browsing percentage to generate a target user profile. Based on the social media interaction information of the marketing target users, the top three users with the highest interaction frequency with the marketing target users are selected and marked as associated users.

4. The marketing management method based on big data analysis according to claim 3 is characterized in that: By analyzing the behavior records of associated users and combining them with the marketing target user portrait, the specific analysis of the marketing strategy for the marketing target user and associated users is output as follows: Obtain behavioral data of associated users, and then extract the consumption frequency of various commodities of associated users and the browsing proportion of various commodities through the associated users' online browsing records, purchase history, click behavior and search keywords; Based on the consumption frequency of various commodities of related users and the browsing proportion of various commodities, the portraits of each related user of the marketing target user are obtained; Normalize and quantify the portrait of the marketing target user and the portraits of each user associated with the marketing target user to obtain the unique feature value of the portrait of the marketing target user and the unique feature value of the portraits of each user associated with the marketing target user; The unique feature value of the portrait of the marketing target user, the unique feature value of the portrait of each associated user of the marketing target user, and the unique feature value of each marketing product are calculated respectively to obtain the Euclidean distance between the unique feature value of the portrait of the marketing target user and the unique feature value of each marketing product, and the Euclidean distance between the unique feature value of the portrait of each associated user of the marketing target user and the unique feature value of each marketing product; The Euclidean distance between the unique feature value of the marketing target user portrait and the unique feature value of each marketing product, as well as the Euclidean distance between the unique feature value of the portrait of each associated user of the marketing target user and the unique feature value of each marketing product are compared with the distance threshold, and the marketing products whose Euclidean distance is greater than the distance threshold are screened out, and the remaining marketing products are output as the marketing strategies for the marketing target users and associated users, and then the marketing strategies for the marketing target users and associated users are adjusted according to the market data.

5. The marketing management method based on big data analysis according to claim 4 is characterized in that: The specific analysis of the marketing strategy for marketing target users and associated users based on the market data is as follows: Obtaining sales fluctuation data of marketing products, sales fluctuation data of competitive products, and market share output for marketing target users and associated users respectively; The sales fluctuation data specifically refers to sales quantity; Compare the sales volume of marketing products, sales volume of competing products and market share with the upper and lower sales thresholds and the upper and lower market share thresholds respectively; When the sales volume of the marketing product is not included in the upper and lower sales thresholds, or the sales volume of the competing product is not included in the upper and lower sales thresholds, or the market share is not included in the upper and lower market share thresholds, provide promotion strategies for the marketing product and provide advertising for the marketing product on multiple platforms. At the same time, give priority marketing recommendations to the marketing product according to the size of its market share.

6. The marketing management method based on big data analysis according to claim 1 is characterized in that: Based on the real-time monitoring of the marketing process, we can obtain the marketing results at each stage, analyze the marketing results, and identify the specific analysis of marketing change trends: The marketing results of each stage include market demand, marketing product conversion rate, user repurchase rate and associated user conversion rate; The market demand, marketing product conversion rate, user repurchase rate and related user conversion rate at each stage are converted into data points respectively, and then various data points are connected respectively to obtain line graphs of changes in market demand, marketing product conversion rate, user repurchase rate and related user conversion rate; Identify market trends based on the line graphs of changes in market demand and marketing product conversion rates, and identify user retention trends based on the line graphs of changes in user repurchase rates and related user conversion rates; The identification of the market change trend is specifically: when both the line graph of the change in market demand and the line graph of the change in the marketing product conversion rate show an upward trend, the market change trend is an upward trend; When both the line graph of market demand changes and the line graph of marketing product conversion rate changes show a downward trend, the market change trend is downward; When the rising and falling trends of the line graph of market demand changes and the line graph of marketing product conversion rate changes are inconsistent, the market change trend is not considered; The identification of the user retention trend is specifically: when the line graph of the change of the user repurchase rate and the line graph of the change of the associated user conversion rate both show an upward trend, the user retention trend is an upward trend; When both the line graph of user repurchase rate and the line graph of associated user conversion rate show a downward trend, the user retention trend is downward; When the rising and falling trends of the line graph of the user repurchase rate and the line graph of the associated user conversion rate are inconsistent, the user retention trend is not considered.

7. The marketing management method based on big data analysis according to claim 6 is characterized in that: The marketing strategy optimization mechanism is triggered based on the marketing change trend. The specific adjustments and optimizations of the marketing strategy include: When both the market change trend and user retention trend are on the rise, provide promotional strategies for marketing products and provide advertising for marketing products on multiple platforms; When both the market change trend and the user retention trend are downward, the marketing target user portrait and the portrait update strategy of each associated user of the marketing target user are triggered, and then the marketing products are changed and adjusted, a promotion strategy is provided for the changed and adjusted marketing products, and advertising of the changed and adjusted marketing products is provided on multiple platforms.

8. A marketing management system based on big data analysis, applying a marketing management method based on big data analysis as claimed in any one of claims 1 to 7, characterized in that: include: Data acquisition module, used to obtain marketing target user behavior data and market data; User analysis module, used to analyze the behavior data of marketing target users, build marketing target user portraits, and identify the associated users of marketing target users; The marketing strategy output module is used to analyze the behavior records of related users and output the marketing strategies of the marketing target users and related users in combination with the marketing target user portraits; A sequence adjustment module is used to adjust the marketing strategies of marketing target users and associated users based on market data and generate marketing priorities; Real-time monitoring module, used to apply the adjusted marketing strategies to market activities and monitor the marketing process and market risk status in real time; The marketing change trend identification module is used to obtain the marketing results of each stage based on the real-time monitoring of the marketing process, analyze the marketing results, and identify the marketing change trends. The specific marketing change trends include market change trends and user retention trends; The optimization and adjustment module is used to trigger the marketing strategy optimization mechanism based on the marketing change trend and adjust and optimize the marketing strategy.

Images