Brand promotion method and system based on user positioning

Abstract

The invention relates to the technical field of brand promotion, in particular to a brand promotion method and system based on user positioning, and the method comprises the following steps: collecting user browsing history, purchase records and social media interaction data, carrying out the statistical analysis of the data, recognizing the field in which a user is interested, and constructing and generating a user interest recognition result. In the invention, through detailed analysis and real-time updating of user data, a dynamic user portrait can be constructed, promotion content can be accurately customized, advertisement content is ensured to be highly related to current interest of a user, a user behavior mode is revealed through clustering analysis, key features are extracted, an advertisement system is allowed to adaptively adjust content and putting time, and user experience is improved. According to the method, the personalized degree and effect of advertisements are remarkably improved, dynamic advertisement configuration is automatically optimized according to real-time changes of user behaviors, promotion activities can accurately aim at potential key user groups, the conversion rate and the user interaction rate are increased, and finally more effective market penetration is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of brand promotion, and in particular to a brand promotion method and system based on user positioning. Background Art

[0002] The field of brand promotion technology is mainly used to enhance brand awareness, shape brand image and promote market acceptance of products or services, combining marketing strategies, consumer behavior analysis and advertising technology to achieve effective brand information dissemination. In the modern context of digitalization and networking, brand promotion focuses on using Internet platforms, social media and mobile applications to accurately target consumer groups through data-driven marketing activities. Technological development has enabled brand promotion to adjust promotion strategies in real time through advanced algorithms and user behavior data analysis, and more accurately influence the purchase decision process of potential customers.

[0003] Among them, the user-targeted brand promotion method refers to a strategy for executing brand promotion activities by personalized positioning of users. By analyzing the user's daily behavior data to determine the user's preferences, the promotion content is customized to improve the visibility and effectiveness of the promotion content. Its uses include but are not limited to enhancing the relevance of target ads, improving user interaction and conversion rates, and optimizing the investment effect of marketing budgets. It can display relevant content to users in the places where they are most likely to be interested, thereby effectively improving brand influence and market share.

[0004] Traditional brand promotion technologies often fail to reflect changes in the market and user behavior in real time, and lack a quick response to users' latest preferences. This lag may result in advertising that may not meet users' current needs, reducing the effectiveness of advertising and user engagement. For example, if user preferences change rapidly due to some unexpected events, traditional methods may still display ads that have lost their relevance due to untimely updates, resulting in a waste of advertising resources. In addition, existing technologies are also limited in the flexibility of advertising content customization and delivery timing, making it difficult to make immediate adjustments when user behavior changes, making it difficult for brands to maintain their competitiveness in the face of a rapidly changing market environment. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a brand promotion method and system based on user positioning.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a brand promotion method based on user positioning, comprising the following steps: S1: Collect user browsing history, purchase history and social media interaction data, perform statistical analysis on the data, identify user interests, and construct and generate user interest identification results; S2: Based on the user interest identification result, the user activity data stream is obtained in real time, the user preference and activity status are updated synchronously, and a dynamically updated user profile is constructed through data integration; S3: Through the dynamically updated user portrait, the items in the brand content library are screened to match the user's current interests, and targeted content proposals are constructed according to the matching degree, the order and method of content display are optimized, and a content customization plan is formulated; S4: Apply the content customization solution to monitor user behavior data, including search habits, browsing time, and interaction frequency, and perform cluster analysis on the behavior data to reveal the user's behavior pattern, extract key features of the behavior pattern, and construct user behavior pattern insight results; S5: Based on the user behavior pattern insight results, adaptive adjustments are made, and the advertising server is configured to respond to real-time changes in user behavior, automatically optimize the advertising content and delivery time, realize dynamic optimization of advertising effects, and build dynamic advertising configuration; S6: Utilize the dynamic advertising configuration to conduct refined promotion for key users and influential groups, adjust promotion activities according to user social connections and interaction intensity, and create precise brand promotion plans.

[0007] As a further solution of the present invention, the user interest identification results include interest areas, active time periods and frequent interaction types, the user real-time portrait includes age range and interest preferences, the content customization plan includes content type, content length and content format, the user behavior pattern insight results include visit frequency, stay duration and click preference, the dynamic advertising configuration includes frequency optimization results, response speed and effect tracking records, and the precise brand promotion plan includes target user analysis results and promotion channels.

[0008] As a further solution of the present invention, the specific steps of collecting user browsing history, purchase history and social media interaction data, performing statistical analysis on the data, identifying the areas of interest of the user, and constructing and generating the user interest identification results are as follows: S101: Collect users’ browsing history, aggregate and count data, integrate purchase records, synchronize social media interaction data, confirm data consistency and integrity, and build user data sets; S102: Based on the user data set, perform data cleaning, remove outliers, fill in missing fields, standardize date and time formats, convert unstructured data into structured data tables, and obtain cleaned data; S103: Based on the cleaned data, by analyzing user transactions and interaction frequencies, identifying user core interests, marking key interest areas, and constructing and generating user interest identification results.

[0009] As a further solution of the present invention, according to the user interest identification result, the user activity data stream is obtained in real time, the user preference and activity status are updated synchronously, and the specific steps of constructing a dynamically updated user portrait through data integration are as follows: S201: Based on the user interest identification result, real-time data monitoring is performed to collect the user's online browsing behavior and social interaction frequency, track user activities in real time, and construct real-time user activity data; S202: Based on the real-time user activity data, update the user's historical preference data, compare the difference between the previous and the next data, adjust the preference settings and activity status, synchronize the changes to the user database, and build an updated user preference record; S203: Perform data integration through the updated user preference records, conduct a comprehensive analysis of user preferences, update user portrait data in real time, confirm data consistency and timeliness, and construct a dynamically updated user portrait.

[0010] As a further solution of the present invention, the items in the brand content library are screened through the dynamically updated user portrait, matching the user's current interest points, building targeted content proposals according to the matching degree, optimizing the content display order and method, and formulating the content customization plan in the following specific steps: S301: Based on the dynamically updated user portrait, connect to the brand content library, search for content items according to the user's current interest points, filter out items with high relevance by comparing content tags with interest points, and construct a filtered content list; S302: Based on the filtered content list, a matching degree analysis is performed on each item, and a cosine similarity algorithm is used to calculate the matching degree between the content item and the user's interest point by comparing the angle difference between the vectors, and the items are sorted according to the matching degree, and the logical order of content display is reorganized to construct an optimized content display order; S303: Using the optimized content display order, adjusting the display mode, adjusting the text layout, image size and user interaction elements, optimizing the content pertinence and attractiveness, and constructing a customized content display solution.

[0011] As a further solution of the present invention, the cosine similarity algorithm is based on the formula: ; Calculate the matching value between content items and user's points of interest ,in, represents the keyword vector of the content item, represents the feature vector of the corresponding content item, Represents the user's interest point vector, represents the vector of the user's interest features, represents the vector dot product, and Represents vectors and vector The modulus length is used to standardize the point product result. and is the adjustment coefficient, which is used to adjust the sensitivity and offset of the matching. and is a smoothing parameter used to avoid computational instabilities or division by zero errors.

[0012] As a further solution of the present invention, the content customization solution is applied to monitor user behavior data, including search habits, browsing time and interaction frequency, and the specific steps of revealing user behavior patterns and extracting key features of the behavior patterns by clustering the behavior data to construct user behavior pattern insight results are as follows: S401: Based on the customized content display solution, regularly capture the user's search habits, browsing time and interaction frequency, record each online activity of the user, capture the user's detailed behavior data, and construct user behavior monitoring data; S402: According to the user behavior monitoring data, key behavior indicators are screened, including page dwell time and click frequency, and the key indicators are preliminarily classified to distinguish different user behavior groups according to activity type and frequency, and construct clustered user behavior data; S403: Utilizing the clustered user behavior data, analyzing the commonalities and individualities of group behaviors, extracting key behavior patterns by comparing the behavior characteristics of different groups, revealing the user's behavior tendencies and preferences, and constructing user behavior pattern insight results.

[0013] As a further solution of the present invention, based on the user behavior pattern insight results, adaptive adjustments are made, and the advertising server is configured to respond to real-time changes in user behavior, automatically optimize the advertising content and delivery time, and achieve dynamic optimization of advertising effects. The specific steps of constructing dynamic advertising configuration are: S501: Based on the user behavior pattern insight results, configure the advertising server, set response rules, including the selection of advertising types and content update frequency triggered by user behavior, adjust the promotion strategy in real time, and construct configuration parameter setting results; S502: Using the configuration parameter setting result, automatically selecting and adjusting the advertisement content according to the user's online behavior and real-time data, synchronously updating the delivery time, and constructing the advertisement content optimization result; S503: Based on the advertising content optimization result, monitor the impact of the optimized advertising content on user behavior, collect feedback data, analyze advertising effects, adjust advertising delivery strategies according to the data, and output dynamic advertising configurations.

[0014] As a further solution of the present invention, the dynamic advertising configuration is used to carry out refined promotion for key users and influential groups, and the promotion activities are adjusted according to the user's social connection and interaction intensity. The specific steps of creating a precise brand promotion plan are as follows: S601: Analyze user social network data using the dynamic advertising configuration, identify key users and influential groups, determine the promotion target group based on the user's social activity and interaction data, and construct key user identification results; S602: Based on the key user identification results, select the advertisement type, customize the content, and adjust the delivery period, design promotion activities according to the user's social connection and interaction intensity, and build a customized promotion strategy by adjusting and matching the user's behavior changes in real time; S603: Execute the customized promotion strategy, monitor the promotion effect and user response, analyze the coverage and effect of the promotion activities, dynamically optimize the promotion content according to the real-time data, and build a precise brand promotion plan.

[0015] A brand promotion system based on user positioning, comprising: The user interest analysis module collects user browsing history, purchase records and social media interaction data, aggregates statistics and integrates them, performs data cleaning, identifies user core interests, marks key interest areas, and constructs and generates user interest identification results; The real-time preference update module collects the user's online browsing behavior and social interaction frequency based on the user interest identification result, tracks the user's activities in real time, updates the user's historical preference data, compares the difference between the previous and the next data and makes synchronous changes, and outputs the updated user preference record; The content matching analysis module conducts a comprehensive analysis of user preferences through the updated user preference records, updates user portrait data in real time, connects to the brand content library, and constructs a filtered content list by comparing content tags with points of interest; The content display customization module performs matching analysis on each item based on the filtered content list, calculates the similarity between the item keywords and the user's interest points, adjusts the logical order and display method of the content display, and constructs a customized content display plan; Based on the customized content display solution, the behavior pattern analysis module records each online activity of the user, captures the user's detailed behavior data, screens key behavior indicators, distinguishes different user behavior groups according to activity types and frequencies, compares the behavior characteristics of different groups, extracts key behavior patterns, reveals the user's behavior tendencies and preferences, and constructs user behavior pattern insight results; The promotion advertisement setting module configures the advertisement server, sets response rules, automatically selects and adjusts advertisement content, synchronously updates the delivery time, monitors the impact of the optimized advertisement content on user behavior, adjusts the advertisement delivery strategy, and builds dynamic advertisement configuration based on the user behavior pattern insight results; The brand precision promotion module uses the dynamic advertising configuration to identify key users and influential groups, determine the target groups for promotion, select advertising types, customize content and adjust the delivery time period, match changes in user behavior, analyze the coverage and effectiveness of promotion activities, dynamically optimize promotion content, and build a precise brand promotion plan.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, through the detailed analysis and real-time updating of user data, it is possible to build a dynamic user portrait, accurately customize promotional content, ensure that the advertising content is highly relevant to the user's current interests, reveal user behavior patterns through cluster analysis, extract key features, and allow the advertising system to adaptively adjust content and delivery time, significantly improving the personalization and effectiveness of advertisements. Dynamic advertising configuration is automatically optimized according to real-time changes in user behavior, so that promotional activities can be accurately targeted at potential key user groups, thereby improving conversion rates and user interaction rates, and ultimately achieving more effective market penetration. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the steps of the present invention; Figure 2 is a flow chart of the steps of S1 of the present invention; Figure 3 is a flow chart of the steps of S2 of the present invention; Figure 4 is a flow chart of the steps of S3 of the present invention; Figure 5 is a flow chart of the steps of S4 of the present invention; Figure 6 is a flow chart of the steps of S5 of the present invention; Figure 7 is a flow chart of the steps of S6 of the present invention; Figure 8 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0020] See also Figure 1 , a brand promotion method based on user positioning, comprising the following steps: S1: Collect user browsing history, purchase history and social media interaction data, perform statistical analysis on the data, identify user interests, and construct and generate user interest identification results; S2: Based on the results of user interest identification, obtain user activity data streams in real time, synchronously update user preferences and activity status, and build dynamically updated user portraits through data integration; S3: Through dynamically updated user portraits, the items in the brand content library are screened to match the user's current interests, and targeted content proposals are built according to the matching degree, the order and method of content display are optimized, and content customization plans are formulated; S4: Apply content customization solutions to monitor user behavior data, including search habits, browsing time, and interaction frequency. Through cluster analysis of behavior data, reveal user behavior patterns, extract key features of behavior patterns, and build user behavior pattern insights; S5: Based on the results of user behavior pattern insights, adaptive adjustments are made, and the ad server is configured to respond to real-time changes in user behavior, automatically optimize ad content and delivery time, dynamically optimize ad effects, and build dynamic ad configurations; S6: Use dynamic ad configuration to conduct refined promotions for key users and influential groups, adjust promotion activities based on user social connections and interaction intensity, and create precise brand promotion plans.

[0021] User interest identification results include interest areas, active time periods and frequent interaction types. Dynamically updated user portraits include age ranges and interest preferences. Content customization plans include content type, content length and content format. User behavior pattern insight results include visit frequency, stay duration and click preferences. Dynamic advertising configuration includes frequency optimization results, response speed and effect tracking records. Precision brand promotion plans include target user analysis results and promotion channels.

[0022] See also Figure 2, the specific steps of S1 are: S101: Collect users’ browsing history, aggregate and count data, integrate purchase records, synchronize social media interaction data, confirm data consistency and integrity, and build user data sets; Collect the browsing history of users. First, extract the browsing timestamps, page dwell time, and click sequences of users on each web page, and query the database records associated with the user ID and the corresponding web page. Use SQL queries to extract the user's activity data within a specific period, and use data segmentation technology to divide the continuous browsing behavior into separate sessions. Subsequently, aggregate and count the number of web page visits, page browsing depth, and session duration in each session to construct a preliminary user behavior feature dataset. Furthermore, integrate the user's purchase records on the e-commerce platform, associate the number of product purchases with the browsing history, and extract product information with a high purchase conversion rate. In addition, synchronize the user's likes, comments, and sharing behavior data on social media, and cross-validate with the purchase and browsing data to ensure the consistency and integrity of the data. Finally, construct a comprehensive user dataset containing user behavior and transaction history to provide a basis for subsequent data processing and analysis.

[0023] S102: Based on the user data set, perform data cleaning, remove outliers, fill in missing fields, standardize date and time formats, convert unstructured data into structured data tables, and obtain cleaned data; Based on the user data set, first identify and remove atypical user behavior records, such as frequent page refresh behaviors in a short period of time, which may be caused by automatic scripts. Use statistical methods, such as Z-score, to identify and remove outliers in numerical fields. For missing user information fields, such as age or region, use multiple interpolation methods to infer missing values ​​based on other known attributes of the user. Date and time fields are standardized using ISO8601 format to ensure consistency in subsequent processing. For unstructured data, such as user comment text, natural language processing technology is used to extract keywords and sentiment tendencies, and convert them into structured data tables, which include keyword frequencies and sentiment scores. Through these steps, a thoroughly cleaned and standardized user data set is obtained, laying a solid foundation for more in-depth user behavior analysis.

[0024] S103: Based on the cleaned data, by analyzing the user's transaction and interaction frequency, identifying the user's core interests, marking the key interest areas, and constructing and generating user interest identification results; Based on the cleaned data, the periodic patterns of user transactions and social interactions are counted to reveal the time periods when users are active and the types of interactions they prefer. Using cluster analysis technology, users are grouped according to their transaction types and interaction frequencies to identify user groups with similar behavior patterns. On this basis, association rule mining technology is used to analyze the common interests among user groups and mark the commodity categories and interactive behaviors that frequently appear together. Finally, a detailed user interest identification result is constructed and generated, which will provide customized input parameters for the personalized recommendation system.

[0025] See also Figure 3 , the specific steps of S2 are: S201: Based on the user interest identification results, real-time data monitoring is performed to collect the user's online browsing behavior and social interaction frequency, track user activities in real time, and construct real-time user activity data; Based on the results of user interest identification, the user's online browsing behavior data is continuously obtained through the API interface, such as the number of page visits, the length of stay, and the links clicked by the user. In addition, the user's interaction frequency on social media is also collected synchronously, including behavioral data such as likes, comments, and shares. Real-time data transmission is achieved through WebSocket technology to ensure that the data flow from the user end to the server is delay-free. The collected data is processed through an event-driven architecture, and each user behavior event is timestamped and user identity is authenticated to build a complete real-time user activity data set. This data set will reflect the activity status and interest changes of each user in real time, providing instant data support for subsequent user preference analysis.

[0026] S202: Based on the real-time user activity data, update the user's historical preference data, compare the difference between the previous and the next data, adjust the preference settings and activity status, synchronize the changes to the user database, and build an updated user preference record; Based on real-time user activity data, first match the real-time data with the user's historical preference data, and identify changes in user preferences through difference analysis, such as increased points of interest or decreased interaction frequency. Using this information, update the user's preference settings and adjust their weight parameters in the recommendation system. For example, if the user has recently frequently browsed fitness-related content, increase the recommendation weight of content in this field. All preference updates are synchronized to the central user database through a transaction processing mechanism to ensure data consistency and integrity. During the update process, data format standardization and cleaning are also required to ensure seamless connection between new and old data. Through these steps, a detailed and updated user preference record data table is constructed.

[0027] S203: Perform data integration through updated user preference records, conduct comprehensive analysis of user preferences, update user portrait data in real time, confirm data consistency and timeliness, and build a dynamically updated user portrait; Through the updated user preference records, data integration technology is used to merge the user preference records with other related data, such as user basic information and consumption records. Multidimensional data analysis techniques, such as principal component analysis (PCA), are applied to identify the main drivers of user preferences and adjust the various indicators of the user profile accordingly. During the integration and analysis process, the consistency of the data is verified, and the last update time of the data is recorded with a timestamp to ensure the timeliness of the data used. Finally, the user profile is rebuilt with the updated data to reflect the user's latest preferences and behavior trends. This profile will be dynamically updated to more accurately match the user's current needs and interests, and provide more personalized services and content recommendations.

[0028] See also Figure 4 , the specific steps of S3 are: S301: Based on the dynamically updated user portrait, the brand content library is connected to search for content items according to the user's current interest points, and by comparing the content tags with the interest points, items with high relevance are screened to construct a screened content list; Based on the dynamically updated user portrait, a connection is first established with the corporate brand content library, and the user's current interests are accurately matched through an efficient database query interface. During the query process, the system automatically calls the interest tags in the user portrait, such as "healthy diet" or "outdoor sports", and compares these tags with the tags of the items in the content library to evaluate the relevance between each content item and the user's interests. By setting a similarity threshold T, content items above this threshold are filtered out to ensure that the selected content is highly relevant to the user's interests. Further attribute analysis is performed on the filtered content, such as content type, release date, and user rating, to optimize the breadth and depth of content selection. Finally, a refined filtered content list is constructed, which serves as the basis for subsequent content recommendation and display.

[0029] S302: Based on the filtered content list, a matching degree analysis is performed on each item, and a cosine similarity algorithm is used to calculate the matching degree between the content item and the user's interest point by comparing the angle difference between the vectors, and the items are sorted according to the matching degree, and the logical order of content display is reorganized to construct an optimized content display order; Cosine similarity algorithm, according to the formula, ; Calculate the matching value between content items and user's points of interest ,in, represents the keyword vector of the content item, represents the feature vector of the corresponding content item, Represents the user's interest point vector, represents the vector of the user's interest features, Represents vector dot product, which calculates the sum of the products of two vectors in each dimension. and Represents vectors and vector The modulus of the vector, the Euclidean length of the vector, is used to normalize the dot product result to obtain the cosine value. and is the adjustment coefficient, which is used to adjust the sensitivity and offset of the matching degree to ensure a more adaptable matching output in a specific application scenario. and is a smoothing parameter used to avoid computational instability or division by zero errors caused by a vector whose magnitude is too small.

[0030] and The feature vectors representing content items and user interest points have the same dimension, and each dimension corresponds to the quantitative value of a specific attribute. They are obtained through content analysis and user behavior data, such as using the TF-IDF algorithm to extract and quantify keywords from text content.

[0031] Dot Product Calculate the sum of the products of two vectors in each dimension, representing the similarity measure between the vectors.

[0032] and It is the adjustment coefficient, which is adjusted according to the actual application needs, such as optimizing on the historical matching data by minimizing the prediction error to ensure that the coefficient reflects the real user preference. To enhance the effect of vector dot product, Used to prevent the denominator from being zero and adjust the baseline matching.

[0033] and is the smoothing parameter, usually set to a small positive number to avoid division by zero errors in the calculation. and , ensuring that all inputs can be stably operated at different magnitudes.

[0034] Mould length and is the Euclidean length of the vector, calculated as the square root of the sum of the squares of its dimensions.

[0035] set up , , , , .

[0036] Compute the vector dot product: ; Calculate the vector modulus: ; ; Insert the formula to calculate the similarity: ; The results show that the matching degree between content items and user interest points is , which represents the matching degree adjusted on the cosine similarity of the feature vectors and is suitable for optimizing the ranking of items in content recommendation systems.

[0037] S303: using the optimized content display order, adjusting the display method, adjusting the text layout, image size and user interaction elements, optimizing the content pertinence and attractiveness, and building a customized content display plan; Adopt the optimized content display order and further adjust the display method to enhance the relevance and attractiveness of the content. The adjustment strategies include modifying the text layout and optimizing the font size and line spacing to improve reading comfort. Intelligently adjust the image size to ensure that the image displays well on different devices and is highly coordinated with the text content. In addition, adjust the position and style of user interaction elements such as buttons and links to make them more prominent and easy to operate. Through these adjustments, not only the visual appeal of the content is improved, but also the interactivity of the user interface is optimized. These improvements are based on user behavior data and feedback, aiming to provide users with a more customized and interactive content display solution. The final solution will enhance user engagement and satisfaction and effectively improve the overall experience of content consumption.

[0038] See also Figure 5 , the specific steps of S4 are: S401: Based on the customized content display solution, regularly capture the user's search habits, browsing time and interaction frequency, record each online activity of the user, capture the user's detailed behavior data, and build user behavior monitoring data; Based on the customized content display solution, in order to better understand user behavior, users' search habits, browsing time and interaction frequency are captured regularly. The specific implementation steps include deploying JavaScript tracking code on the user's browsing page to record the user's click events, page scrolling behavior and dwell time in each section in real time. Through HTTP requests, the behavioral data is sent to the back-end server and then stored in the behavioral data warehouse. In addition, for interactions on social media platforms, such as likes, comments and shares, data synchronization is also performed through API calls. All collected data is timestamped for subsequent time series analysis. Through these methods, the system can capture the detailed behavior of users on the website in detail, build a comprehensive user behavior monitoring data set, and provide a basis for further user behavior analysis.

[0039] S402: based on the user behavior monitoring data, screen key behavior indicators, including page dwell time and click frequency, preliminarily classify the key indicators, distinguish different user behavior groups according to activity type and frequency, and construct clustered user behavior data; Based on the user behavior monitoring data, key behavior indicators such as page dwell time and click frequency are first screened out through data processing algorithms. These indicators are statistically analyzed to identify abnormal data points and clean them to ensure the accuracy and availability of the data. Furthermore, clustering algorithms in machine learning, such as K-means or DBSCAN, are used to divide users into different groups based on their behavior indicators. This classification process is based on the similarity of user behavior and can effectively distinguish user groups with different activity patterns. For example, users with high-frequency interactions but short dwell time are classified into one category, while users who read for a long time but interact less frequently are classified into another category. Through classification, segmented clustered user behavior data is constructed, which helps to more accurately understand the characteristics and needs of different user groups.

[0040] S403: Analyze the commonalities and individualities of group behaviors by using clustered user behavior data, extract key behavior patterns by comparing the behavior characteristics of different groups, reveal user behavior tendencies and preferences, and construct user behavior pattern insight results; Using clustered user behavior data, we conduct in-depth group behavior analysis and compare behavioral characteristics between different groups, such as average browsing time, interaction type, and frequency. This comparison reveals the commonalities and individuality of each group, helping to identify representative behavior patterns. For example, young user groups may tend to browse quickly and interact frequently, while older users may pay more attention to the depth and quality of content. Conduct logical analysis and pattern recognition on behavioral patterns to extract key behavioral trends, such as increases or decreases in user activity within a specific time period. Insights from analyzing and building user behavior patterns not only help optimize content recommendation algorithms, but also provide a basis for marketing strategies to better meet user needs and preferences.

[0041] See also Figure 6 , the specific steps of S5 are: S501: Based on the user behavior pattern insight results, configure the advertising server, set response rules, including the selection of advertising types and content update frequency triggered by user behavior, adjust the promotion strategy in real time, and build configuration parameter setting results; Based on the results of user behavior pattern insights, first configure the relevant response rules on the advertising server. These rules are based on user behavior data, such as click-through rate and page browsing depth, to determine what type of advertising is most suitable for displaying to a specific user group. Specific operations include setting up a variety of advertising selection logic. For example, for users who frequently browse content on a specific topic, priority is given to pushing ads related to that topic. The setting of content update frequency is based on user activity. For those active users who log in daily, the advertising content will be updated more frequently to provide freshness and increase user stickiness. All parameter settings are performed through the advertising management background. Administrators can monitor and adjust promotion strategies in real time to adapt to market changes and user feedback, and then build detailed configuration parameter setting results, which directly affect the effect of advertising display and user experience.

[0042] S502: Using the configuration parameter setting results, automatically selecting and adjusting the advertising content according to the user's online behavior and real-time data, synchronously updating the delivery time, and constructing the advertising content optimization results; Using the results of the configuration parameter settings, the automated system adjusts the advertising content based on the user's online behavior and real-time data. By analyzing the user's recent behavioral changes, such as increasing the dwell time on a certain category, the advertising content that matches the changes is automatically selected from the advertising library for display. In addition, the advertising delivery time is also synchronized with the user's online peak period to ensure the timeliness and relevance of the advertising display. This process is carried out through advanced data analysis tools and real-time data processing systems to ensure timely updating and optimization of advertising content. Through continuous data feedback loops and adjustments, advertising content optimization results are constructed, which helps to improve advertising exposure and user conversion rates.

[0043] S503: Based on the advertising content optimization results, monitor the impact of the optimized advertising content on user behavior, collect feedback data, analyze advertising effects, adjust advertising delivery strategies according to the data, and output dynamic advertising configurations; Based on the optimization results of advertising content, monitoring the impact of advertising content on user behavior becomes a key step. By setting up tracking pixels and user behavior monitoring tools, user interaction data on optimized advertising content, such as clicks, viewing time, and conversions, is collected to analyze the actual effectiveness of advertising, and detect which advertising content is most attractive to users and triggers actual purchases or behavioral changes. Based on the analysis results, advertising strategies are dynamically adjusted to reflect the latest preferences and behavior patterns of users. For example, if a certain advertising content shows a low conversion rate, its display frequency will be reduced, or the advertising message will be adjusted to be more in line with user needs. The output dynamic advertising configuration results provide companies with data-driven decision support, helping to achieve more efficient and personalized advertising delivery strategies.

[0044] See also Figure 7 , the specific steps of S6 are: S601: Analyze user social network data using dynamic advertising configuration, identify key users and influential groups, determine promotion target groups based on user social activity and interaction data, and construct key user identification results; With dynamic ad configuration, we first analyze user social network data to identify key users and highly influential groups. Through data mining techniques, we extract users’ social interaction data, such as the frequency of sharing, commenting, and liking, as well as the connection density and bridging roles in the user network. Using this data, we use social network analysis (SNA) to identify users who are at the core of the social network and who generally have high communication capabilities and influence. At the same time, we evaluate users’ social activity and judge their potential as promotion targets through data on their daily activities. Based on these analysis results, we construct key user identification results, laying the foundation for precise marketing activities and ensuring that promotion resources are effectively allocated to the most influential users.

[0045] S602: Based on the key user identification results, select the type of advertisement, customize the content, and adjust the delivery time period. Design promotion activities according to the user's social connection and interaction intensity. Build a customized promotion strategy by adjusting and matching the user's behavior changes in real time. Based on the results of key user identification, further selection of advertising types and customization of content are carried out. According to the interests and social connections of the identified key users, advertising content that matches their interaction intensity and interests is designed. For example, for users who often participate in outdoor sports discussions, advertisements for related equipment are pushed first. At the same time, the delivery time period is adjusted to ensure that the advertisement is displayed during the most active time period of the user to increase the visibility and interaction rate of the advertisement. In this process, the adjustment of advertising content and time period is carried out dynamically, and the promotion strategy is continuously optimized by real-time monitoring of user behavior and feedback. Through these steps, a customized promotion strategy is built, aiming to improve the effectiveness of advertising and user engagement through fine-tuning.

[0046] S603: Execute customized promotion strategies, monitor promotion effects and user responses, analyze the coverage and effects of promotion activities, dynamically optimize promotion content based on real-time data, and build precise brand promotion plans; Execute customized promotion strategies and monitor the real-time effects of promotion activities and user responses. Use various analytical tools, such as click-through rate and conversion rate tracking, to evaluate the coverage and actual effects of promotion activities. In addition, collect user feedback, such as comments and direct feedback, to provide data support for further optimization of promotion content. Based on these real-time data, dynamically adjust advertising content and promotion strategies, such as by adjusting advertising messages or visual elements to better attract user attention, and ultimately build a precise brand promotion plan that not only enhances the brand's market influence, but also enhances user participation and satisfaction.

[0047] See also Figure 8 , a brand promotion system based on user positioning, comprising: The user interest analysis module collects user browsing history, purchase records and social media interaction data, aggregates statistics and integrates them, performs data cleaning, identifies user core interests, marks key interest areas, and constructs and generates user interest identification results; The real-time preference update module collects the user's online browsing behavior and social interaction frequency based on the user's interest identification results, tracks user activities in real time, updates the user's historical preference data, compares the difference between the previous and the next data, makes synchronous changes, and outputs the updated user preference record; The content matching analysis module conducts a comprehensive analysis of user preferences through updated user preference records, updates user portrait data in real time, connects to the brand content library, and builds a filtered content list by comparing content tags with points of interest; The content display customization module performs matching analysis on each item based on the filtered content list, calculates the similarity between the item keywords and the user's interest points, adjusts the logical order and display method of the content display, and builds a customized content display plan; The behavior pattern analysis module is based on customized content display solutions, records each online activity of users, captures detailed user behavior data, screens key behavior indicators, distinguishes different user behavior groups according to activity types and frequencies, compares the behavioral characteristics of different groups, extracts key behavior patterns, reveals user behavior tendencies and preferences, and constructs user behavior pattern insight results; The promotional advertising setting module configures the advertising server, sets response rules, automatically selects and adjusts advertising content, synchronously updates the delivery time, monitors the impact of optimized advertising content on user behavior, adjusts advertising delivery strategies, and builds dynamic advertising configurations based on the results of user behavior pattern insights. The brand precision promotion module uses dynamic advertising configuration to identify key users and influential groups, determine the target group for promotion, select advertising types, customize content, and adjust delivery time periods, match changes in user behavior, analyze the coverage and effectiveness of promotional activities, dynamically optimize promotional content, and build a precise brand promotion plan.

[0048] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A brand promotion method based on user positioning, characterized in that: The following steps are involved: Collect user browsing history, purchase records, and social media interaction data, perform statistical analysis on the data, identify areas of interest to users, and construct and generate user interest identification results; According to the user interest identification result, the user activity data stream is obtained in real time, the user preference and activity status are updated synchronously, and a dynamically updated user profile is constructed through data integration; Through the dynamically updated user portrait, the items in the brand content library are screened to match the user's current interests, and targeted content proposals are constructed according to the matching degree, the order and method of content display are optimized, and content customization plans are formulated; Apply the content customization solution to monitor user behavior data, including search habits, browsing time, and interaction frequency, and perform cluster analysis on the behavior data to reveal user behavior patterns, extract key features of the behavior patterns, and construct user behavior pattern insight results; Based on the user behavior pattern insight results, adaptive adjustments are made, and the advertising server is configured to respond to real-time changes in user behavior, automatically optimize the advertising content and delivery time, realize dynamic optimization of advertising effects, and build dynamic advertising configuration; By utilizing the dynamic advertising configuration, refined promotions can be conducted for key users and influential groups, and promotion activities can be adjusted according to the user's social connections and interaction intensity to create precise brand promotion plans.

2. The brand promotion method based on user positioning according to claim 1, characterized in that: The user interest identification results include interest areas, active time periods and frequent interaction types, the user real-time portrait includes age range and interest preferences, the content customization plan includes content type, content length and content format, the user behavior pattern insight results include visit frequency, stay duration and click preferences, the dynamic advertising configuration includes frequency optimization results, response speed and effect tracking records, and the precise brand promotion plan includes target user analysis results and promotion channels.

3. The brand promotion method based on user positioning according to claim 1, characterized in that: Collect user browsing history, purchase history and social media interaction data, perform statistical analysis on the data, identify areas of interest to users, and construct and generate user interest identification results. The specific steps are: Collect users’ browsing history, aggregate data, integrate purchase records, synchronize social media interaction data, confirm data consistency and integrity, and build user data sets; Based on the user data set, perform data cleaning, remove outliers, fill in missing fields, standardize date and time formats, convert unstructured data into structured data tables, and obtain cleaned data; Based on the cleaned data, by analyzing user transactions and interaction frequencies, the user's core interests are identified, key interest areas are marked, and user interest identification results are constructed and generated.

4. The brand promotion method based on user positioning according to claim 1, characterized in that: According to the user interest identification result, the user activity data stream is obtained in real time, the user preference and activity status are updated synchronously, and the specific steps of constructing a dynamically updated user portrait through data integration are as follows: Based on the user interest identification results, real-time data monitoring is performed to collect the user's online browsing behavior and social interaction frequency, track user activities in real time, and build real-time user activity data; Based on the real-time user activity data, update the user's historical preference data, compare the difference between the previous and the next data, adjust the preference settings and activity status, synchronize the changes to the user database, and build an updated user preference record; Through the updated user preference records, data integration is performed, user preferences are comprehensively analyzed, user portrait data is updated in real time, data consistency and timeliness are confirmed, and dynamically updated user portraits are constructed.

5. The brand promotion method based on user positioning according to claim 1, characterized in that: Through the dynamically updated user portrait, the items in the brand content library are screened to match the user's current interests, and targeted content proposals are constructed according to the matching degree to optimize the content display order and method. The specific steps for formulating content customization plans are as follows: Based on the dynamically updated user portrait, the brand content library is connected to retrieve content items for the user's current points of interest, and by comparing content tags with points of interest, items with high relevance are screened to construct a screened content list; Based on the filtered content list, a matching degree analysis is performed on each item, and a cosine similarity algorithm is used to calculate the matching degree between the content item and the user's interest point by comparing the angle difference between the vectors, and the items are sorted according to the matching degree, and the logical order of content display is reorganized to construct an optimized content display order; The optimized content display sequence is used to adjust the display method, adjust the text layout, image size and user interaction elements, optimize the content relevance and attractiveness, and build a customized content display plan.

6. The brand promotion method based on user positioning according to claim 1, characterized in that: The cosine similarity algorithm, according to the formula, ； Calculate the matching value between content items and user's points of interest ,in, represents the keyword vector of the content item, represents the feature vector of the corresponding content item, Represents the user's interest point vector, represents the vector of the user's interest features, represents the vector dot product, and Represents vectors and vector The modulus length is used to standardize the point product result. and is the adjustment coefficient, which is used to adjust the sensitivity and offset of the matching. and is a smoothing parameter used to avoid computational instabilities or division by zero errors.

7. The brand promotion method based on user positioning according to claim 1, characterized in that: The specific steps of applying the content customization solution to monitor user behavior data, including search habits, browsing time, and interaction frequency, revealing user behavior patterns through cluster analysis of behavior data, extracting key features of behavior patterns, and constructing user behavior pattern insight results are as follows: Based on the customized content display solution, regularly capture the user's search habits, browsing time and interaction frequency, record each online activity of the user, capture the user's detailed behavior data, and build user behavior monitoring data; Based on the user behavior monitoring data, key behavior indicators are screened, including page dwell time and click frequency, and the key indicators are preliminarily classified to distinguish different user behavior groups according to activity type and frequency, and to construct clustered user behavior data; The clustered user behavior data is used to analyze the commonalities and individualities of group behaviors. By comparing the behavioral characteristics of different groups, key behavior patterns are extracted to reveal users' behavioral tendencies and preferences, and to construct user behavior pattern insight results.

8. The brand promotion method based on user positioning according to claim 1, characterized in that: Based on the user behavior pattern insight results, adaptive adjustments are made, and the advertising server is configured to respond to real-time changes in user behavior, automatically optimize the advertising content and delivery time, and achieve dynamic optimization of advertising effects. The specific steps for building dynamic advertising configuration are: Based on the user behavior pattern insight results, configure the advertising server, set response rules, including the selection of advertising types and content update frequency triggered by user behavior, adjust the promotion strategy in real time, and build configuration parameter setting results; Using the configuration parameter setting results, automatically select and adjust the advertising content according to the user's online behavior and real-time data, synchronously update the delivery time, and construct the advertising content optimization results; Based on the advertising content optimization results, monitor the impact of the optimized advertising content on user behavior, collect feedback data, analyze advertising effects, adjust advertising delivery strategies based on the data, and output dynamic advertising configurations.

9. The brand promotion method based on user positioning according to claim 1, characterized in that: By using the dynamic advertising configuration, we can conduct refined promotion for key users and influential groups, adjust the promotion activities according to the user's social connection and interaction intensity, and create a precise brand promotion plan. Utilize the dynamic advertising configuration to analyze user social network data, identify key users and influential groups, determine the promotion target group based on the user's social activity and interaction data, and construct key user identification results; Based on the key user identification results, select the type of advertisement, customize the content, and adjust the delivery period. Design promotion activities according to the user's social connection and interaction intensity. Build a customized promotion strategy by adjusting and matching user behavior changes in real time. Execute the customized promotion strategy, monitor promotion effects and user responses, analyze the coverage and effects of promotion activities, dynamically optimize promotion content based on real-time data, and build precise brand promotion plans.

10. A brand promotion system based on user positioning, characterized in that: According to a user positioning-based brand promotion method according to any one of claims 1 to 9, the system comprises: The user interest analysis module collects user browsing history, purchase records and social media interaction data, aggregates statistics and integrates them, performs data cleaning, identifies user core interests, marks key interest areas, and constructs and generates user interest identification results; The real-time preference update module collects the user's online browsing behavior and social interaction frequency based on the user interest identification result, tracks the user's activities in real time, updates the user's historical preference data, compares the difference between the previous and the next data and makes synchronous changes, and outputs the updated user preference record; The content matching analysis module conducts a comprehensive analysis of user preferences through the updated user preference records, updates user portrait data in real time, connects to the brand content library, and constructs a filtered content list by comparing content tags with points of interest; The content display customization module performs matching analysis on each item based on the filtered content list, calculates the similarity between the item keywords and the user's interest points, adjusts the logical order and display method of the content display, and constructs a customized content display plan; Based on the customized content display solution, the behavior pattern analysis module records each online activity of the user, captures the user's detailed behavior data, screens key behavior indicators, distinguishes different user behavior groups according to activity types and frequencies, compares the behavior characteristics of different groups, extracts key behavior patterns, reveals the user's behavior tendencies and preferences, and constructs user behavior pattern insight results; The promotion advertisement setting module configures the advertisement server, sets response rules, automatically selects and adjusts advertisement content, synchronously updates the delivery time, monitors the impact of the optimized advertisement content on user behavior, adjusts the advertisement delivery strategy, and builds dynamic advertisement configuration based on the user behavior pattern insight results; The brand precision promotion module uses the dynamic advertising configuration to identify key users and influential groups, determine the target groups for promotion, select advertising types, customize content and adjust the delivery time period, match changes in user behavior, analyze the coverage and effectiveness of promotion activities, dynamically optimize promotion content, and build a precise brand promotion plan.

Images