Commodity category recommendation management system based on e-commerce applet

Abstract

The invention belongs to the technical field of e-commerce, and particularly relates to a commodity category recommendation management system based on an e-commerce applet, and the system comprises the steps: analyzing historical sales records, and understanding the sales-free categories and commodities; the method comprises the steps of recommending similar or related commodity categories according to commodity categories browsed or purchased by users in the past, recommending commodity categories in which the users are interested according to behavior data of similar users, classifying the users according to different dimensions, and providing customized recommendation for different groups; setting different category priorities for the recommendation system according to different recommendation strategies, and performing feedback based on real-time data; according to a recommendation system, commodity categories seen when a user enters an applet every time are dynamically generated, the conversion rate of recommendation, the click rate of the user and the sales are evaluated through a data analysis tool, behaviors of the user on a recommendation page are analyzed, and the method has the advantages that changes of user requirements can be quickly responded, recommendation quality is continuously optimized, and user experience is improved. And it is ensured that the e-commerce platform keeps leading advantages in intense market competition.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce, and in particular to a commodity category recommendation management system based on an e-commerce applet. Background Art

[0002] E-commerce mini-programs are booming, and the demand for personalized recommendations is becoming increasingly prominent

[0003] In recent years, e-commerce mini programs have developed rapidly due to their accessible and convenient features. Users can easily browse products and place orders on the mini program platform, which greatly improves shopping efficiency. However, with the increase in mini program users and the wide variety of products, how to effectively recommend products that meet user interests and needs has become a key issue. Existing e-commerce platforms generally use recall recommendation algorithms based on browsing history or purchase records, which have limited coverage, lack of personalization, and are difficult to meet the diverse needs of users.

[0004] Traditional product category recommendation algorithms mainly rely on user behavior data, such as browsing history and purchase history, but these data are often insufficient to fully describe the user's consumption preferences and interests, resulting in a lack of pertinence in the recommendation results. At the same time, traditional algorithms are also difficult to cope with the dynamically changing product category structure and user needs, and the recommendation effect gradually decays. Therefore, it is necessary to study more intelligent, accurate, and personalized product category recommendation algorithms to enhance the user shopping experience and promote business development.

[0005] At present, some studies have tried to combine user portraits and knowledge graphs to recommend products, but there are still some shortcomings. For example, the construction method of user portraits is not perfect and cannot accurately capture user segmentation needs; the construction and maintenance costs of knowledge graphs are high, and it is difficult to achieve rapid iteration and updating. In response to the above problems, it is necessary to develop a more efficient, accurate and easy-to-operate product category recommendation management system, rooted in user portraits and knowledge graph technology, to meet the growing personalized recommendation needs of e-commerce applets;

[0006] In response to the above-mentioned technical defects, a product category recommendation management system solution based on e-commerce mini-programs is proposed. Summary of the invention

[0007] To solve the above problems, the present invention provides the following technical solutions:

[0008] A commodity category recommendation management system based on an e-commerce applet, comprising:

[0009] The data collection module records the user's browsing, searching, clicking, and purchasing behavior data, collects the price, inventory, sales volume, category, and tag information of the goods, and understands the best-selling categories and goods by analyzing the historical sales records;

[0010] Recommendation algorithm module, which recommends similar or related product categories based on the product categories that users have browsed or purchased in the past, recommends product categories that they are interested in based on the behavioral data of similar users, and recommends specific categories of products to users based on promotional activities, seasonal products and inventory information. Through deep learning algorithms, it generates personalized recommendations in real time based on user behavior and product information;

[0011] User portraits and grouping: Create user portraits based on age, gender, consumption habits, and interest preferences, classify users according to different dimensions, and provide customized recommendations for different groups;

[0012] The recommendation strategy management module sets different category priorities for the recommendation system according to different recommendation strategies, and dynamically adjusts the recommended product categories based on real-time data feedback, such as inventory changes, market demand fluctuations, and seasonal factors;

[0013] User interface and interaction design: Based on the recommendation system, dynamically generate the product categories that users see every time they enter the mini program. When users search for products, recommend related categories based on their interests or historical records to improve search conversion rates, and recommend related or similar categories to users on the product details page;

[0014] Data analysis and reporting: Through data analysis tools, we can evaluate the conversion rate, user click-through rate and sales of recommendations, analyze user behavior on recommendation pages, optimize recommendation logic, track the sales performance of recommended product categories, and optimize recommendation models.

[0015] Furthermore, the data collection module includes recording the product detail pages and category pages browsed by users, understanding which products and categories users are interested in, recording the keywords entered by users in the search box, analyzing users' potential needs and intentions, tracking the products or category links clicked by users, further refining user interests, recording users adding products to shopping carts, and whether they ultimately complete the purchase, evaluating users' purchase intentions, and recording users' purchase behavior, including purchased products, categories, quantities, and amounts, to help the system analyze which categories and products are popular with users, analyze the time users spend on each page, identify which products or categories users are more concerned about, track users' behavior paths within the mini program, and analyze the process from entry to final conversion. Steps: optimize the recommendation strategy, collect the basic attributes of each product, such as name, brand, price, inventory, sales, and rating, record the category and subcategory to which each product belongs, help the system understand the correlation between products and user preferences, enrich product information through user tags, tags automatically generated by the system, or tags manually added by merchants, collect product inventory status in real time, avoid recommending product categories that are sold out or out of stock, record detailed information for each order, including order number, user ID, product list, payment method, and purchase time, analyze sales changes of product categories in different time periods, identify best-selling categories and seasonal hot-selling products, collect relevant information on user returned products, analyze products or categories with high return rates, and optimize recommendation logic.

[0016] Furthermore, the data collection module also includes analyzing the user's consumption capacity based on the user's historical consumption records and purchase amounts to help make personalized recommendations, analyzing the user's interest preferences based on user behavior data, integrating user behavior data from other platforms, further enriching user portraits and interest tags, ensuring that data collection and storage comply with the privacy policy, and obtaining the user's explicit consent, encrypting and storing sensitive data, and protecting user information through access control mechanisms, recording every step of the user's operation through point-of-sale technology, and using relational databases, or NoSQL databases, to store and manage large amounts of user and product data.

[0017] Furthermore, the recommendation algorithm module includes analyzing the characteristics of goods that the user has browsed or purchased in the past, recommending similar or related product categories, calculating the similarity between products, using cosine similarity, Jaccard similarity or TF-IDF, building a user interest model based on the user's historical behavior, and recommending product categories similar to the user's historical behavior to the user, recommending product categories based on the behavior data of similar users, calculating the similarity between users, finding similar user groups of the target user, and recommending categories that the user likes, recommending product categories based on the similarity between products, calculating the similarity between products, and recommending other product categories similar to the product categories that the user has purchased or browsed in the past.

[0018] Furthermore, the user portrait and grouping include statistics on the user's age, gender, region, occupation, and income level data, collecting the user's behavioral data in the e-commerce mini program, analyzing the user's preferences for certain product categories, brands or specific styles based on the user's browsing, clicking, and purchasing behaviors, estimating the user's consumption capacity and willingness to purchase through the user's historical purchase amount and frequency information, analyzing the user's social circle and friend interaction data to further improve the user portrait, tracking and analyzing the user's behavioral data on the recommendation page, evaluating the click-through rate and conversion rate of recommendations, optimizing the user grouping logic, conducting A / B testing on different user grouping strategies, selecting strategies to apply to all users, and continuously optimizing grouping strategies and recommendation algorithms based on user feedback.

[0019] Furthermore, the recommendation strategy management module includes setting different recommendation rules according to business needs and user group characteristics, setting priorities for different recommendation strategies, allowing multiple strategies to be used in combination, setting recommendation strategies according to different scenarios in which users are located, recommending products similar to the categories browsed by users, or other related categories that users are interested in, recommending related accessories or matching products based on the products in the user's shopping cart, recommending related categories based on user search terms, or displaying common search results, setting different recommendation strategies according to different platforms to ensure the consistency and coherence of user experience across platforms, and dynamically adjusting recommendation strategies based on real-time user behavior data. When the inventory of goods changes, the strategy management module needs to adjust the recommendation results in a timely manner to avoid recommending sold-out goods. During specific time periods, such as seasonal changes or holidays, the strategy management module triggers specific recommendation strategies to recommend seasonal goods and holiday specials.

[0020] Furthermore, the user interface and interaction design help users quickly obtain important information through clear hierarchy of visual elements such as color, font size, and pictures, and adopt a simplified navigation structure to enable users to quickly find the required products and functions. In order to reduce interface congestion, drop-down menus or sidebars are used to display detailed product classifications and function options, thereby improving the neatness of the interface and user operating efficiency. The search box should always remain visible and provide intelligent recommendations and automatic completion functions to help users quickly find the required products. Personalized recommendation areas should be designed in locations that users frequently pay attention to. When the product list is long, lazy loading technology or sliding pages should be used to avoid slow page loading and improve user browsing experience. When the user clicks a button or performs an operation, the interface should provide instant feedback to ensure that the user knows that the operation has been received by the system. With the widespread use of mobile devices, supporting gesture operations will help enhance the user's natural interaction experience.

[0021] Furthermore, the data analysis and reporting include analyzing the user's operating behavior in the mini program, including visiting pages, browsing products, clicking, searching, purchasing, and exiting. By analyzing the user's path, the key nodes where the user leaves or converts are found, the process is optimized, and the sales of each product are counted, including sales, order volume, return rate, and average order value. Through the analysis of sales data, it is possible to understand whether the product is popular and unsalable, and then make adjustments to inventory and promotion strategies. For different marketing activities, their effects are analyzed, and indicators such as click-through rate, conversion rate, and ROI are evaluated to adjust future marketing strategies. Combined with user portraits and grouping functions, in-depth analysis of the behaviors and needs of different user groups is performed. Through funnel models, the user's path from entering the mini program to the final purchase is analyzed, the reasons for user loss at different stages are found, the process is optimized to improve the conversion rate, key indicators are monitored in real time, and an early warning mechanism is set up to help detect abnormal situations in a timely manner.

[0022] Furthermore, the data analysis includes analyzing the data in the database, including visual analysis of data correlation and similarity functions constructed by inner product of functions, as follows:

[0023]

[0024] in,<f,g> is the inner product of the function, f(x) is the similarity function of the data in the database, g(x) is the correlation function of the data in the database, and a and b are real numbers representing the length of the data fragments extracted from the database.

[0025] Furthermore, the data visualization includes performing normal distribution on the data in the database, and the calculation formula is as follows:

[0026]

[0027] Among them, P(x) is the normal distribution probability of the specified data in the database, μ is the data error value, σ is the variance value of the database data, and e -(x-μ)2 / (2σ 2 ) is the normal distribution ratio function of the data nodes in the database.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] In a product category recommendation management system based on an e-commerce applet of the present invention, a data collection module is used to record user browsing, searching, clicking, and purchasing behavior data, collect product price, inventory, sales volume, category, and tag information, and understand best-selling categories and products by analyzing historical sales records; a recommendation algorithm module is used to recommend similar or related product categories based on the product categories that users have browsed or purchased in the past, and to recommend product categories that they are interested in based on the behavior data of similar users, and to recommend products of specific categories to users in combination with promotional activities, seasonal products, and inventory information, and to generate personalized recommendations in real time based on user behavior and product information through a deep learning algorithm; user portraits and grouping are used to establish user portraits based on age, gender, consumption habits, and interest preferences, classify users according to different dimensions, and provide customized recommendations for different groups; recommendation strategy management Module, set different category priorities for the recommendation system according to different recommendation strategies, and dynamically adjust the recommended product categories based on real-time data feedback, such as inventory changes, market demand fluctuations, and seasonal factors; User interface and interaction design, according to the recommendation system, dynamically generate the product categories that users see each time they enter the mini program. When users search for products, recommend related categories based on their interests or historical records to improve search conversion rates, and recommend related or similar categories to users on the product details page; Data analysis and reporting, through data analysis tools, evaluate the conversion rate of recommendations, user click-through rate, and sales, analyze user behavior on recommendation pages, optimize recommendation logic, track the sales performance of recommended product categories, optimize the recommendation model to be able to quickly respond to changes in user needs, continuously optimize recommendation quality, and ensure that e-commerce platforms maintain their leading edge in the fierce market competition. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0031] Figure 1 This is a schematic diagram of the overall framework of a commodity category recommendation management system based on an e-commerce applet in the present invention;

[0032] Figure 2 The figure is an overall schematic diagram of a computer device in a commodity category recommendation management system based on an e-commerce applet according to the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] like Figure 1-2 A product category recommendation management system based on an e-commerce applet, comprising:

[0035] The data collection module records the user's browsing, searching, clicking, and purchasing behavior data, collects the price, inventory, sales volume, category, and tag information of the goods, and understands the best-selling categories and goods by analyzing the historical sales records;

[0036] Recommendation algorithm module, which recommends similar or related product categories based on the product categories that users have browsed or purchased in the past, recommends product categories that they are interested in based on the behavioral data of similar users, and recommends specific categories of products to users based on promotional activities, seasonal products and inventory information. Through deep learning algorithms, it generates personalized recommendations in real time based on user behavior and product information;

[0037] User portraits and grouping: Create user portraits based on age, gender, consumption habits, and interest preferences, classify users according to different dimensions, and provide customized recommendations for different groups;

[0038] The recommendation strategy management module sets different category priorities for the recommendation system according to different recommendation strategies, and dynamically adjusts the recommended product categories based on real-time data feedback, such as inventory changes, market demand fluctuations, and seasonal factors;

[0039] User interface and interaction design: Based on the recommendation system, dynamically generate the product categories that users see every time they enter the mini program. When users search for products, recommend related categories based on their interests or historical records to improve search conversion rates, and recommend related or similar categories to users on the product details page;

[0040] Data analysis and reporting: Through data analysis tools, we can evaluate the conversion rate, user click-through rate and sales of recommendations, analyze user behavior on recommendation pages, optimize recommendation logic, track the sales performance of recommended product categories, and optimize recommendation models.

[0041] Specifically, the data collection module includes recording the product details pages and category pages browsed by users, understanding which products and categories users are interested in, recording the keywords entered by users in the search box, analyzing users' potential needs and intentions, tracking the products or category links clicked by users, specifically refining user interests, recording users adding products to shopping carts, and whether they ultimately complete the purchase, evaluating users' purchase intentions, and recording users' purchase behaviors, including purchased products, categories, quantities, and amounts, helping the system analyze which categories and products are popular with users, analyzing the time users spend on each page, identifying which products or categories users pay more attention to, tracking users' behavior paths within the mini program, and analyzing the steps from entry to final conversion. Step 1: Optimize recommendation strategies, collect basic attributes of each product, such as name, brand, price, inventory, sales, and ratings, record the category and subcategory to which each product belongs, help the system understand the correlation between products and user preferences, enrich product information through user tags, tags automatically generated by the system, or tags manually added by merchants, collect product inventory status in real time, avoid recommending product categories that are sold out or out of stock, record detailed information for each order, including order number, user ID, product list, payment method, and purchase time, analyze sales changes of product categories in different time periods, identify best-selling categories and seasonal hot-selling products, collect relevant information on user returned products, analyze products or categories with high return rates, and optimize recommendation logic.

[0042] Specifically, the data collection module also includes analyzing the user's consumption capacity based on the user's historical consumption records and purchase amounts, helping to make personalized recommendations, analyzing the user's interest preferences based on user behavior data, integrating user behavior data from other platforms, and specifically enriching user portraits and interest tags, ensuring that data collection and storage comply with the privacy policy, and obtaining the user's explicit consent, encrypting and storing sensitive data, and protecting user information through access control mechanisms, recording every step of the user's operation through point-of-sale technology, and using relational databases, or NoSQL databases, to store and manage large amounts of user and product data.

[0043] Specifically, the recommendation algorithm module includes analyzing the characteristics of goods that the user has browsed or purchased in the past, recommending similar or related product categories, calculating the similarity between products, using cosine similarity, Jaccard similarity or TF-IDF, building a user interest model based on the user's historical behavior, and recommending product categories similar to the user's historical behavior to the user, recommending product categories based on the behavior data of similar users, calculating the similarity between users, finding similar user groups of the target user, and recommending categories that the user likes, recommending product categories based on the similarity between products, calculating the similarity between products, and recommending other product categories similar to the product categories that the user has purchased or browsed in the past.

[0044] Specifically, the user portrait and grouping include statistics on the user's age, gender, region, occupation, and income level data, collecting the user's behavioral data in the e-commerce mini program, analyzing the user's preferences for certain product categories, brands or specific styles based on the user's browsing, clicking, and purchasing behaviors, estimating the user's consumption capacity and willingness to purchase through the user's historical purchase amount and frequency information, analyzing the user's social circle and friend interaction data to specifically improve the user portrait, tracking and analyzing the user's behavioral data on the recommendation page, evaluating the click-through rate and conversion rate of recommendations, optimizing the user grouping logic, conducting A / B testing on different user grouping strategies, selecting strategies to apply to all users, and continuously optimizing grouping strategies and recommendation algorithms based on user feedback.

[0045] Specifically, the recommendation strategy management module includes setting different recommendation rules according to business needs and user group characteristics, setting priorities for different recommendation strategies, allowing multiple strategies to be used in combination, setting recommendation strategies according to different scenarios in which users are located, recommending products similar to the categories browsed by users, or other related categories that users are interested in, recommending related accessories or matching products based on the products in the user's shopping cart, recommending related categories based on user search terms, or displaying common search results, setting different recommendation strategies according to different platforms to ensure the consistency and coherence of user experience across platforms, and dynamically adjusting recommendation strategies based on real-time user behavior data. When the inventory of goods changes, the strategy management module needs to adjust the recommendation results in a timely manner to avoid recommending sold-out goods. During specific time periods, such as seasonal changes or holidays, the strategy management module triggers specific recommendation strategies to recommend seasonal goods and holiday specials.

[0046] Specifically, the user interface and interaction design help users quickly obtain important information through clear hierarchy of visual elements such as color, font size, and pictures, and adopt a simplified navigation structure to enable users to quickly find the required products and functions. In order to reduce interface congestion, drop-down menus or sidebars are used to display detailed product classifications and function options, thereby improving the neatness of the interface and user operating efficiency. The search box should always remain visible, and provide intelligent recommendations and automatic completion functions to help users quickly find the required products. Personalized recommendation areas should be designed in locations that users frequently pay attention to. When the product list is long, lazy loading technology or sliding pages should be used to avoid slow page loading and improve user browsing experience. When a user clicks a button or performs an operation, the interface should provide instant feedback to ensure that the user knows that the operation has been received by the system. With the widespread use of mobile devices, supporting gesture operations will help enhance the user's natural interaction experience.

[0047] Specifically, the data analysis and reporting include analyzing the user's operating behavior in the mini program, including visiting pages, browsing products, clicking, searching, purchasing, and exiting. By analyzing the user's path, the key nodes where the user leaves or converts are found, the process is optimized, and the sales of each product are counted, including sales, order volume, return rate, and average order value. Through the analysis of sales data, it is possible to understand whether a product is popular or unsalable, and then make adjustments to inventory and promotion strategies. For different marketing activities, their effects are analyzed, and indicators such as click-through rate, conversion rate, and ROI are evaluated to adjust future marketing strategies. Combined with user portraits and grouping functions, in-depth analysis is conducted on the behavior and needs of different user groups. The funnel model is used to analyze the user's path from entering the mini program to the final purchase, and the reasons for user loss at different stages are found out. The process is optimized to improve the conversion rate, key indicators are monitored in real time, and an early warning mechanism is set up to help detect abnormal situations in a timely manner.

[0048] Generate customized reports based on different role requirements (such as operations, marketing, product managers, etc.). For example, operations personnel need to understand product sales and inventory, while marketing personnel are more concerned with ROI of marketing activities, user conversion rate, etc.

[0049] Multi-dimensional analysis report: The report should be able to display data by different dimensions (such as time, region, user group, product category, etc.). For example, analyze the user's activity in different time periods by time or view sales performance by region.

[0050] Charts and visualization: Through visualization tools (such as line charts, bar charts, pie charts, funnel charts, etc.), data can be made more intuitive, making it easier for decision makers to quickly understand and analyze the trends behind the data.

[0051] Trend analysis and forecasting: In addition to displaying current data, the report should also have trend analysis functions, such as product sales trends, user growth trends, etc., and predict future trends through historical data to provide reference for decision-making.

[0052] Export and share: Reports can be exported to multiple formats (such as Excel, PDF, etc.), and can be shared with team members via email, system messages, etc.

[0053] Traffic indicators: such as PV (page views), UV (unique visitors), bounce rate, length of stay, etc., help evaluate the traffic and user stickiness of the mini program.

[0054] User indicators: including the number of new user registrations, number of active users, retention rate, etc., to evaluate user acquisition and retention effects.

[0055] Conversion indicators: such as shopping cart addition rate, order conversion rate, payment success rate, etc., analyze the key conversion links from user browsing to purchase.

[0056] Financial indicators: including total sales, net profit, average order value, user lifetime value (LTV), etc., to help evaluate the financial performance of e-commerce mini programs.

[0057] Product indicators: such as product click-through rate, add-to-cart rate, inventory turnover rate, etc., analyze the performance of different products and provide a basis for product recommendations and inventory management.

[0058] Data collection and processing: Collect user behavior data through tracking technology, API interfaces, etc. Data processing uses ETL (extraction, transformation, loading) tools to clean and integrate data to ensure data accuracy and consistency.

[0059] Data warehouse: Build a big data warehouse (such as Hadoop, Hive) to store massive amounts of user and business data and support subsequent complex queries and analysis.

[0060] Analysis tools: Use data analysis platforms (such as Google Analytics, Tableau, Power BI) to analyze and visualize data, supporting real-time analysis and trend analysis of data.

[0061] Machine learning and AI analysis: Use machine learning algorithms (such as cluster analysis and predictive models) to deeply explore the value of data. For example, predict the probability of repurchase through user behavior and predict inventory demand through product sales.

[0062] Big data processing framework: Use big data processing frameworks (such as Spark and Flink) to support streaming processing of real-time data and ensure that the system can dynamically generate reports and monitor.

[0063] Data encryption: During data transmission and storage, ensure encryption of user data and business data to prevent data leakage.

[0064] Permission management: Role-based permission control ensures that personnel at different levels can only access reports and data related to their responsibilities, avoiding unnecessary data leakage risks.

[0065] Data privacy compliance: Comply with privacy protection regulations such as GDPR to ensure that users' personal information is protected and their privacy rights are respected.

[0066] Data-driven decision-making: Based on the results of data analysis, the business processes of the mini program are continuously optimized, such as product recommendations, inventory management, marketing activities, etc., to improve overall operational efficiency and user satisfaction.

[0067] Continuous monitoring and feedback loop: Regularly evaluate various business indicators and adjust operational strategies according to changes. For example, when the conversion rate of a certain product is found to have dropped, it can be optimized by adjusting the product display method, launching promotional activities, etc.

[0068] Automated reporting and smart push: Generate reports regularly through automated tools and push key information to relevant personnel, helping the team to keep abreast of operational dynamics and make quick adjustments. The data analysis and reporting module is the decision-making core of e-commerce mini programs. Through in-depth analysis of user behavior, sales data, marketing effects, etc., the platform can fully grasp business dynamics, discover potential problems, and optimize business processes through data-driven. At the same time, the visualization and automation functions of data reports can help management quickly understand key information and make more scientific decisions.

[0069] Specifically, the data analysis includes analyzing the data in the database, including building a visualization analysis of data correlation and similarity functions using the inner product of the function, as follows:

[0070]

[0071] in,<f,g> is the inner product of function, f(x) is the similarity function of the data in the database, g(x) is the correlation function of the data in the database, a and b are real numbers representing the length of the data fragments intercepted in the database. The inner product of function is calculated on the data according to the length of the data in the database, the similar and related data are processed together, and the visual analysis is performed.

[0072] Specifically, the data visualization includes performing normal distribution on the data in the database, and the calculation formula is as follows:

[0073]

[0074] Among them, P(x) is the normal distribution probability of the specified data in the database, μ is the data error value, σ is the variance value of the database data, and e -(x-μ)2 / (2σ 2 ) is the normal distribution ratio function of the data nodes in the database.

[0075] According to another aspect of the present invention, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned commodity category recommendation management system based on the e-commerce mini program when executing the computer program. The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WI FI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.;

[0076] Those skilled in the art will understand that Figure 2 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0077] The working principle of the commodity category recommendation management system based on the e-commerce applet of the present invention is as follows: through the data collection module, the user's browsing, searching, clicking, and purchasing behavior data are recorded, and the price, inventory, sales volume, category, and tag information of the commodity are collected, and the best-selling categories and commodities are understood by analyzing the historical sales records; the recommendation algorithm module recommends similar or related commodity categories based on the commodity categories that the user has browsed or purchased in the past, and recommends the commodity categories that they are interested in based on the behavior data of similar users, and recommends specific categories of commodities to users in combination with promotional activities, seasonal commodities and inventory information, and generates personalized recommendations in real time based on user behavior and commodity information through a deep learning algorithm; user portrait and grouping, establish user portraits based on age, gender, consumption habits, and interest preferences, classify users according to different dimensions, and provide customized recommendations for different groups; recommendation strategy The management module sets different category priorities for the recommendation system according to different recommendation strategies, and dynamically adjusts the recommended product categories based on real-time data feedback, such as inventory changes, market demand fluctuations, and seasonal factors; the user interface and interaction design dynamically generates the product categories that users see each time they enter the mini program according to the recommendation system. When users search for products, relevant categories are recommended based on their interests or historical records to improve search conversion rates, and related or similar categories are recommended to users on the product details page; data analysis and reporting, through data analysis tools, evaluates recommendation conversion rates, user click-through rates, and sales, analyzes user behavior on recommendation pages, optimizes recommendation logic, tracks the sales performance of recommended product categories, and optimizes recommendation models to be able to quickly respond to changes in user needs, continuously optimize recommendation quality, and ensure that e-commerce platforms maintain their leading edge in the fierce market competition.

[0078] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A commodity category recommendation management system based on e-commerce mini-programs, characterized in that: include: The data collection module records the user's browsing, searching, clicking, and purchasing behavior data, collects the price, inventory, sales volume, category, and tag information of the goods, and understands the best-selling categories and goods by analyzing the historical sales records; Recommendation algorithm module, which recommends similar or related product categories based on the product categories that users have browsed or purchased in the past, recommends product categories that they are interested in based on the behavioral data of similar users, and recommends specific categories of products to users based on promotional activities, seasonal products and inventory information. Through deep learning algorithms, it generates personalized recommendations in real time based on user behavior and product information; User portraits and grouping: Create user portraits based on age, gender, consumption habits, and interest preferences, classify users according to different dimensions, and provide customized recommendations for different groups; The recommendation strategy management module sets different category priorities for the recommendation system according to different recommendation strategies, and dynamically adjusts the recommended product categories based on real-time data feedback, such as inventory changes, market demand fluctuations, and seasonal factors; User interface and interaction design: Based on the recommendation system, dynamically generate the product categories that users see every time they enter the mini program. When users search for products, recommend related categories based on their interests or historical records to improve search conversion rates, and recommend related or similar categories to users on the product details page; Data analysis and reporting: Through data analysis tools, we can evaluate the conversion rate, user click-through rate and sales of recommendations, analyze user behavior on recommendation pages, optimize recommendation logic, track the sales performance of recommended product categories, and optimize recommendation models.

2. A product category recommendation management system based on an e-commerce applet according to claim 1, characterized in that: The data collection module includes recording the product details pages and category pages browsed by users, understanding which products and categories users are interested in, recording the keywords entered by users in the search box, analyzing users' potential needs and intentions, tracking the product or category links clicked by users, further refining user interests, recording users adding products to shopping carts and whether they ultimately complete the purchase, evaluating users' purchase intentions, and recording users' purchase behaviors, including purchased products, categories, quantities, and amounts, helping the system analyze which categories and products are popular with users, analyzing the time users stay on each page, identifying which products or categories users pay more attention to, tracking users' behavior paths within the mini program, and analyzing the steps from entry to final conversion. Optimize recommendation strategies, collect basic attributes of each product, such as name, brand, price, inventory, sales, and ratings, record the category and subcategory to which each product belongs, help the system understand the correlation between products and user preferences, enrich product information through user tags, tags automatically generated by the system, or tags manually added by merchants, collect product inventory status in real time, avoid recommending product categories that are sold out or out of stock, record detailed information for each order, including order number, user ID, product list, payment method, and purchase time, analyze sales changes of product categories in different time periods, identify best-selling categories and seasonal hot-selling products, collect relevant information on user returned products, analyze products or categories with high return rates, and optimize recommendation logic.

3. A product category recommendation management system based on an e-commerce applet according to claim 2, characterized in that: The data collection module also includes analyzing the user's consumption capacity based on the user's historical consumption records and purchase amounts to help make personalized recommendations, analyzing the user's interest preferences based on user behavior data, integrating user behavior data from other platforms, further enriching user portraits and interest tags, ensuring that data collection and storage comply with the privacy policy, and obtaining the user's explicit consent, encrypting and storing sensitive data, and protecting user information through access control mechanisms, recording every step of the user's operation through point-of-sale technology, and using relational databases or NoSQL databases to store and manage large amounts of user and product data.

4. A product category recommendation management system based on an e-commerce applet according to claim 3, characterized in that: The recommendation algorithm module includes analyzing the characteristics of goods that the user has browsed or purchased in the past, recommending similar or related product categories, calculating the similarity between products, using cosine similarity, Jaccard similarity or TF-IDF, building a user interest model based on the user's historical behavior, and recommending product categories similar to their historical behavior to the user, recommending product categories based on the behavior data of similar users, calculating the similarity between users, finding similar user groups of the target user, and recommending categories that the user likes, recommending product categories based on the similarity between products, calculating the similarity between products, and recommending other product categories similar to the product categories that the user has purchased or browsed in the past.

5. A product category recommendation management system based on an e-commerce applet according to claim 4, characterized in that: The user portrait and grouping include statistics on the user's age, gender, region, occupation, and income level data, collection of user behavior data in the e-commerce mini program, analysis of the user's preferences for certain product categories, brands or specific styles based on the user's browsing, clicking, and purchasing behavior, estimation of the user's consumption capacity and willingness to purchase through the user's historical purchase amount and frequency information, analysis of the user's social circle and friend interaction data to further improve the user portrait, tracking and analyzing the user's behavior data on the recommendation page, evaluating the click-through rate and conversion rate of recommendations, optimizing the user grouping logic, conducting A / B testing on different user grouping strategies, selecting strategies to apply to all users, and continuously optimizing grouping strategies and recommendation algorithms based on user feedback.

6. A product category recommendation management system based on an e-commerce applet according to claim 5, characterized in that: The recommendation strategy management module includes setting different recommendation rules according to business needs and user group characteristics, setting priorities for different recommendation strategies, allowing multiple strategies to be used in combination, setting recommendation strategies according to different scenarios in which users are located, recommending products similar to the categories browsed by users, or other related categories that users are interested in, recommending related accessories or matching products based on the products in the user's shopping cart, recommending related categories based on user search terms, or displaying common search results, setting different recommendation strategies according to different platforms to ensure the consistency and coherence of user experience across platforms, and dynamically adjusting recommendation strategies based on real-time user behavior data. When the inventory of goods changes, the strategy management module needs to adjust the recommendation results in a timely manner to avoid recommending sold-out goods. During specific time periods, such as seasonal changes or holidays, the strategy management module triggers specific recommendation strategies to recommend seasonal goods and holiday specials.

7. A commodity category recommendation management system based on an e-commerce applet according to claim 6, characterized in that: The user interface and interaction design help users quickly obtain important information through the clear hierarchy of visual elements such as color, font size, and pictures, and adopt a simplified navigation structure to enable users to quickly find the required products and functions. In order to reduce interface congestion, drop-down menus or sidebars are used to display detailed product classifications and function options, thereby improving the neatness of the interface and user operating efficiency. The search box should always remain visible and provide intelligent recommendations and automatic completion functions to help users quickly find the required products. The personalized recommendation area should be designed in a location that users frequently pay attention to. When the product list is long, lazy loading technology or sliding pages should be used to avoid slow page loading and improve user browsing experience. When the user clicks a button or performs an operation, the interface should provide instant feedback to ensure that the user knows that the operation has been received by the system. With the widespread use of mobile devices, supporting gesture operations will help enhance the user's natural interaction experience.

8. A commodity category recommendation management system based on an e-commerce applet according to claim 6, characterized in that: The data analysis and reporting include analyzing the user's operating behavior in the mini program, as well as visiting pages, browsing products, clicking, searching, purchasing, and exiting. By analyzing the user's path, the key nodes where the user leaves or converts are found, the process is optimized, and the sales of each product are counted, including sales, order volume, return rate, and average order value. Through the analysis of sales data, it is possible to understand whether a product is popular or unsalable, and then adjust inventory and promotion strategies. For different marketing activities, their effects are analyzed, and indicators such as click-through rate, conversion rate, and ROI are evaluated to adjust future marketing strategies. Combined with user portraits and grouping functions, in-depth analysis is conducted on the behavior and needs of different user groups. The user's path from entering the mini program to the final purchase is analyzed through funnel models, etc., to find out the reasons for user loss at different stages, optimize processes to improve conversion rates, monitor key indicators in real time, and set up early warning mechanisms to help detect abnormal situations in a timely manner.

9. A commodity category recommendation management system based on an e-commerce applet according to claim 8, characterized in that: The data analysis includes analyzing the data in the database, including building a visualization analysis of data correlation and similarity functions using the inner product of the function, as follows: in,<f,g> is the inner product of the function, f(x) is the similarity function of the data in the database, g(x) is the correlation function of the data in the database, and a and b are real numbers representing the length of the data fragments extracted from the database.

10. A commodity category recommendation management system based on an e-commerce applet according to claim 9, characterized in that the data visualization includes normal distribution of the data in the database, and the calculation formula is as follows: in, P(x) is the normal distribution probability of the specified data in the database, μ is the data error value, σ is the variance value of the database data, where e -(x-μ)2 (2σ2) is the normal distribution proportion function of the data nodes in the database.

Images