Mobile marketing system based on Internet of Things technology

Abstract

The invention discloses a mobile marketing system based on the Internet of Things technology, and relates to the technical field of mobile marketing, and the system comprises the following components: a data collection and analysis module which collects data, including use habits, preferences and position information, of a user in real time through the Internet of Things technology when the user uses an intelligent device, and uses a statistical analysis technology to obtain a statistical analysis result; according to the invention, through a statistical analysis technology utilized by the data collection and analysis module, the data of the user when using the intelligent equipment is collected and analyzed in real time, the behavior pattern and preference of the user are deeply mined, and the user experience is improved. According to the method and the system, the marketing content with high individuation is pushed to the user, the pertinence of the marketing information and the user receiving degree are greatly improved, the purchasing willingness and the conversion rate of the user can be improved, and the trust and loyalty of the user to an enterprise can be enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of mobile marketing, and specifically provides a mobile marketing system based on Internet of Things technology. Background Art

[0002] With the rapid development of Internet of Things technology, its applications in various fields have become increasingly widespread. In the field of mobile marketing, the application of Internet of Things technology has also demonstrated great potential and value. However, most traditional mobile marketing methods are based on user historical data and static analysis, pushing standardized or predefined marketing content in order to attract users' attention. This approach often ignores the real-time changes in user needs and the dynamics of the market environment, resulting in limited marketing effects and even potentially causing user aversion, making it difficult to accurately grasp users' true needs and feedback.

[0003] Therefore, it is of great practical application value to develop a new marketing system that can utilize big data analysis and personalized recommendation technology to deeply mine user data, discover patterns and trends in user behavior, and provide strong support for personalized marketing. A mobile marketing system based on Internet of Things technology must be able to: collect and analyze user data in real time, provide personalized marketing content push, and also implement a real-time interaction and feedback mechanism to strengthen communication and connection between users and enterprises, improve marketing effects and user experience, and create greater commercial value for enterprises.

[0004] However, most traditional mobile marketing systems on the current market can only meet some of the above requirements, unable to meet enterprises' needs for real-time and interactive marketing efficiency and accuracy, lacking an effective real-time interaction and feedback mechanism. Enterprises are difficult to accurately grasp users' true needs and feedback, and thus cannot adjust marketing strategies in a timely manner to improve user experience. Therefore, it is necessary to develop a mobile marketing system based on Internet of Things technology that can comprehensively achieve the above features and is more perfect and efficient to solve the above problems and provide stronger support for enterprise marketing. Summary of the Invention

[0005] The purpose of the present invention is to make up for the deficiencies of the existing technology and provide a mobile marketing system based on Internet of Things technology. It can achieve personalized marketing content push by adopting personalized recommendation algorithms, utilize clustering algorithms and time series analysis technology to deeply mine user data, discover patterns and trends in user behavior, and provide strong support for personalized marketing.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: A mobile marketing system based on Internet of Things technology, characterized in that the system includes the following components:

[0007] Data Collection and Analysis Module: This module collects data in real time on users' use of smart devices through Internet of Things technology, including usage habits, preferences, and location information. Using statistical analysis techniques, it deeply mines user data to provide user portraits and behavior analysis for enterprises;

[0008] Personalized Marketing Content Push Module: Based on user portraits and behavior analysis, it pushes personalized marketing content to users. Through personalized recommendation algorithms based on collaborative filtering, according to users' purchase history and browsing records, it recommends relevant products or services to users to improve conversion rates;

[0009] Real-time Interaction and Feedback Module: It uses smart devices to provide a real-time interaction and feedback mechanism. Users can use smart devices to interact with enterprises at any time, put forward demands or feedback on usage experiences. Enterprises can receive user feedback in real time and respond and process it quickly, thereby enhancing user satisfaction and loyalty;

[0010] Cross-platform Integrated Marketing Module: Utilizing the cross-platform characteristics of the Internet of Things, it integrates data and resources from multiple platforms to achieve cross-platform integrated marketing. Through a unified marketing management system, enterprises can coordinate marketing activities on different platforms to improve marketing efficiency and brand influence;

[0011] Intelligent Marketing Decision-making Module: This module uses time series analysis methods to analyze and predict massive data, providing intelligent marketing decision-making support for enterprises. Through data-driven decision-making methods, enterprises can more accurately grasp market trends and formulate effective marketing strategies.

[0012] Furthermore, the specific steps of the data collection and analysis module are as follows:

[0013] (1) Device Connection and Data Access: Through the Internet of Things, connect users' smart devices (such as smartphones, smartwatches, smart home devices) to the system to ensure that the devices can upload user data in real time;

[0014] (2) Data Collection: Collect various types of data on users' usage from the connected devices, including usage habits (such as click frequency, browsing duration), preferences (such as purchase records, browsing content), and location information (such as GPS positioning data);

[0015] (3) Data Preprocessing: Remove duplicate, incorrect, or invalid data to ensure the accuracy and integrity of the data, and convert the data into a unified format for convenient subsequent analysis and processing;

[0016] (5) Data Analysis: Conduct basic statistical analysis on the data (such as mean algorithms), and use big data to deeply mine user data to discover patterns, trends, and correlation relationships in user behavior;

[0017] (6)User Portrait and Behavior Analysis: Based on user data, construct user portraits, including users' basic information, interest preferences, and consumption habits, conduct in-depth analysis of users' behaviors, identify users' potential needs and purchase intentions, and provide a basis for subsequent personalized marketing content push.

[0018] Furthermore, the specific steps of the personalized marketing content push module are as follows:

[0019] (1)User Portrait Construction: Based on the user data provided by the data collection and analysis module, construct a detailed user portrait, which includes users' basic information (such as age, gender, region), interest preferences (such as shopping preferences, browsing content), and consumption habits (such as purchase frequency, purchase time);

[0020] (2)Behavior Analysis: Further analyze users' behaviors on the basis of constructing user portraits, which includes identifying users' active time periods, purchase intentions, and potential needs;

[0021] (3)Content Matching and Screening: Based on the results of user portraits and behavior analysis, screen out highly matched content for users from the marketing content library, involving the classification and tagging of marketing content for quick matching to target users;

[0022] (4)Personalized Push Strategy Formulation: According to user portraits, behavior analysis results, and content matching situations, use personalized recommendation algorithms to formulate personalized push strategies, including determining the push time, frequency, channels, as well as the priority and order of push content.

[0023] (5)Real-time Push and Feedback Collection: Through the real-time interaction and feedback module, push personalized marketing content to users and collect users' feedback, which can be in various forms such as click-through rate, conversion rate, and user evaluations;

[0024] (6)Effect Evaluation and Optimization: According to users' feedback and marketing effect data, evaluate the effectiveness of personalized push strategies and optimize the strategies based on the evaluation results.

[0025] Furthermore, the specific steps of the real-time interaction and feedback module are as follows:

[0026] (1)User Interaction Initiation: Users enter the marketing interface through intelligent devices (such as mobile phones, tablets, computers) and can choose to interact with the enterprise. The interaction methods include sending text messages, voice messages, pictures, or videos;

[0027] (2)Message Transmission and Reception: Users' interaction messages are transmitted to the enterprise's server in real time through the Internet of Things. The server receives and parses these messages, extracts users' intentions and feedback information;

[0028] (3) Feedback content processing: The enterprise server processes the user's feedback content, including classification, analysis, and storage. Based on the type and content of the feedback, the server can trigger corresponding response mechanisms;

[0029] (4) Real-time response and feedback: Based on the user's feedback content, the enterprise sends response information to the user in real-time through intelligent devices. The response is an answer to the user's question, product usage suggestions, and promotional activities;

[0030] (5) Interaction record and tracking: The system records every interaction process between the user and the enterprise, including interaction time, content, and response.

[0031] Further, the specific steps of the cross-platform integrated marketing module are as follows:

[0032] (1) Platform data collection: Collect user data from various platforms (such as social media, e-commerce platforms, offline stores). This data includes the user's browsing records, purchase records, and comment feedback;

[0033] (2) Data integration and behavior analysis: Clean and integrate the collected data to eliminate redundant and incorrect data and ensure data consistency and accuracy. Based on the integrated data, conduct in-depth analysis of the user's behavior to understand the user's consumption habits and interest preferences;

[0034] (3) Formulate cross-platform marketing strategies: According to the results of user behavior analysis, use clustering algorithms to segment users and formulate cross-platform marketing strategies, including content push and activity arrangements on different platforms;

[0035] (4) Marketing execution and monitoring: Execute the formulated marketing strategies on various platforms and monitor the marketing effects in real-time, including indicators such as click-through rate and conversion rate;

[0036] (5) Effect evaluation and optimization: Based on the monitoring results, evaluate the marketing effects and optimize and adjust the marketing strategies according to the evaluation results.

[0037] Further, the specific steps of the intelligent marketing decision-making module are as follows:

[0038] (1) Data sorting: The enterprise collects relevant internal and external data and cleans and sorts it. Internal data includes customer data, sales data, and product data, which are usually stored in the enterprise's internal database or CRM system. External data can be obtained from market research reports and social media comments;

[0039] (2) Data mining: Analyze and mine the completed data collation to obtain information about customer behavior and purchase preferences, and use various time series analysis methods to identify patterns and trends in the data;

[0040] (3) Decision-making and implementation: Based on the results of data mining, formulate specific marketing decisions, such as the selection of target markets, product pricing strategies, and the arrangement of promotional activities. These decisions aim to maximize marketing effectiveness, enhance the company's market share and profitability.

[0041] Further, the data collection and analysis module understands the general characteristics of user behavior through statistical analysis, and uses basic mean algorithms for statistics. Its operation method and formula are: The mean is the sum of all values divided by the number of values, used to represent the "average" or "central" position of the data: , is the sum of all values of, n is the number of values. Suppose a set of data on the browsing duration of a website page by users is collected in the data collection and analysis module. This set of data includes the browsing durations (in minutes) of 5 users: [10, 15, 20, 25, 30]. Calculate the sum of the data = 10 + 15 + 20 + 25 + 30 = 100. Divide the sum by the number to get the mean . The mean browsing duration of this group of users for a certain website page is 20 minutes. Analyze the average browsing duration of users for this website page, and further analyze users' browsing habits and interest preferences. Mean analysis can provide quantitative indicators of user behavior. By calculating the mean of user behavior, such as average click frequency and average browsing duration, the general behavior characteristics of users can be intuitively understood. This helps enterprises identify the common habits and trends of users, thus better understanding user needs and market dynamics. At the same time, comparing the mean data of different time periods can reveal seasonal or cyclical changes in user behavior, which helps enterprises predict future market trends and make corresponding adjustments.

[0042] Further, the personalized marketing content push module analyzes the behavior data of users through personalized recommendation algorithms based on collaborative filtering, finds user groups with similar interests, and recommends content to the current user according to the behavior of these similar users. Use the cosine similarity method to calculate the similarity between users, that is: , and are two users, I is the set of all commodities, and are respectively users and The score for product i, the value range of cosine similarity is between -1 and 1. The closer the value is to 1, the more similar the two vectors are, that is, the more likely the user is to be interested in the marketing content. Calculating the similarity between the user and the marketing content can more accurately find out the content that the user is interested in, thereby improving the accuracy of recommendations. For each user, find the k users who are most similar to him / her, and generate a recommendation list based on the purchase behaviors of these similar users. This list can be updated in real time based on the user's historical behaviors and interest preference information to achieve personalized marketing content push. Precise recommendations can reduce the time for users to search and filter, making it easier for them to find the content they are interested in, thereby enhancing the user experience and triggering the user's purchase behavior, thus increasing the marketing effect.

[0043] Furthermore, the cross-platform integrated marketing module divides users into different groups through a clustering algorithm, helping the marketing team to more deeply understand the needs and preferences of different user groups, thereby formulating more precise and personalized marketing strategies. Its operation method and formula are as follows: collect user data from multiple platforms (such as social media, e-commerce platforms, offline stores), including the user's purchase records, browsing behaviors, and interaction feedbacks. Extract the features related to user behaviors and preferences from the collected raw data. These features include the user's purchase frequency, purchased product categories, browsing duration, number of likes or comments. Use a clustering algorithm (such as K-means) to perform clustering analysis on the data, that is: randomly select K initial centroids (i.e., clustering centers), assign each data point to the nearest centroid to form K clusters, recalculate the centroid of each cluster until the position of the centroid no longer changes significantly or reaches the preset number of iterations. Use the Euclidean distance formula to calculate the distance between the data point and the centroid: , where x and y are two data points (or centroids), and n is the number of feature dimensions. and are the values of vectors x and y in the i-th dimension respectively. The algorithm will divide the data into different groups according to the similarity or distance between users. Users within each group have similar behavior patterns or preferences. After clustering, each group represents a user group with similar characteristics and behavior patterns. The marketing team can further analyze the characteristics of these groups, understand the needs and preferences of different user groups, and push content or activity information that matches their interests and needs to different user groups, which can increase the click-through rate, conversion rate, and user engagement of marketing activities, thereby enhancing the overall marketing effect, allocating marketing resources, and avoiding wasting them on inefficient or irrelevant user groups, thus achieving cost control and benefit maximization.

[0044] Furthermore, the intelligent marketing decision-making module uses the moving average method in time series analysis, enabling enterprises to more accurately grasp the sales trend, avoid blind following or lagging reactions. Its operation mode and formula are as follows: Enterprises organize the daily sales data collected into a time series format, that is, data points arranged in chronological order. Let be the sales amount on the t-th day, and n be the size of the moving average window. Then the moving average value on the t-th day is calculated by the formula: , add up the sales amounts of the most recent n days, and then divide by n to obtain the average value. This average value is the moving average sales amount on the t-th day. According to the prediction results of the sales trend, enterprises can reasonably arrange the production plan to ensure that the production capacity matches the market demand, improve production efficiency and resource utilization rate. By understanding the changes in the sales trend, enterprises can formulate targeted marketing strategies, such as adjusting prices, launching promotional activities, or optimizing the product portfolio, thereby enhancing the marketing effect and market competitiveness. Through the moving average method, enterprises can smooth out the short-term fluctuations in the sales data, making it easier to identify the long-term trend. This trend analysis helps enterprises make more informed decisions, adjust inventory levels, formulate marketing strategies, and predict future sales performance.

[0045] Compared with the prior art, the mobile marketing system based on Internet of Things technology has the following beneficial effects:

[0046] First, through the statistical analysis technology and personalized recommendation algorithm utilized by the data collection and analysis module and the personalized marketing content push module of the present invention, data of users when using intelligent devices is collected and analyzed in real time, deeply mining the behavior patterns and preferences of users, and pushing highly personalized marketing content to users, greatly improving the pertinence of marketing information and the acceptance degree of users. This not only helps to enhance the purchase intention and conversion rate of users, but also can enhance the trust and loyalty of users to the enterprise.

[0047] Second, through the cross-platform integrated marketing module of the present invention, the system can integrate data and resources of multiple platforms to achieve cross-platform collaborative marketing. This can not only avoid the problem of information silos between different platforms, but also realize the unified management and coordination of marketing activities, improving marketing efficiency. At the same time, the intelligent marketing decision-making module enables enterprises to formulate more accurate and effective marketing strategies based on data analysis and prediction, thereby enhancing brand influence and market competitiveness, and bringing greater commercial value and development space to enterprises.

[0048] Other advantages, objectives, and features of the present invention will be described to some extent in the subsequent specification, and to some extent, will be obvious to those skilled in the art based on the study of the following text, or can be learned from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0050] Figure 1 It is a flow operation diagram of a mobile marketing system based on Internet of Things technology.

[0051] Figure 2 It is a flow chart of a mobile marketing system based on Internet of Things technology. Detailed implementation manners

[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0053] Embodiment 1

[0054] A mobile marketing system based on Internet of Things technology, the system includes the following components:

[0055] Data collection and analysis module: This module collects data of users when using smart devices in real time through Internet of Things technology, including usage habits, preferences, location information, and uses statistical analysis technology to deeply mine user data to provide user portraits and behavior analysis for enterprises;

[0056] Personalized marketing content push module: Based on user portraits and behavior analysis, it pushes personalized marketing content to users. Through a personalized recommendation algorithm based on collaborative filtering, according to the purchase history and browsing records of users, it recommends relevant products or services to users to improve conversion rates;

[0057] Real-time interaction and feedback module: It uses smart devices to provide a real-time interaction and feedback mechanism. Users can use smart devices to interact with enterprises at any time, put forward requirements or feedback usage experiences. Enterprises can receive user feedback in real time and respond and process it quickly, thereby improving user satisfaction and loyalty;

[0058] Cross-platform integrated marketing module: Utilizing the cross-platform characteristics of the Internet of Things, it integrates data and resources of multiple platforms to achieve cross-platform integrated marketing. Through a unified marketing management system, enterprises can coordinate marketing activities on different platforms to improve marketing efficiency and brand influence;

[0059] Intelligent Marketing Decision-making Module: This module uses time series analysis methods to analyze and predict massive amounts of data, providing intelligent marketing decision-making support for enterprises. Through a data-driven decision-making approach, enterprises can more accurately grasp market trends and formulate effective marketing strategies.

[0060] Data Collection and Analysis Module: First, using Internet of Things technology, connect users' intelligent devices (such as smartphones, tablets) to the system. These devices can upload real-time data on users' browsing and purchasing on e-commerce platforms. Clean and organize the collected data, removing duplicate, incorrect, or invalid data to ensure data accuracy and integrity. At the same time, convert the data into a unified format for convenient subsequent analysis and processing. Understand the general characteristics of user behavior through statistical analysis. Use basic mean algorithms for statistics. Its operation method and formula are: The mean is the sum of all values divided by the number of values, used to represent the "average" or "central" position of the data: , is the sum of all values and n is the number of values. Suppose a set of data on the browsing duration of users on a certain website page is collected in the Data Collection and Analysis Module. This set of data includes the browsing durations (in minutes) of 5 users: [10, 15, 20, 25, 30]. Calculate the sum of the data = 10 + 15 + 20 + 25 + 30 = 100. Divide the sum by the number to get the mean . The mean browsing duration of this group of users on a certain website page is 20 minutes. Analyze the average browsing duration of users on this website page, and further analyze users' browsing habits and interest preferences. Mean analysis can provide quantitative indicators of user behavior. By calculating the mean of user behavior, such as average click frequency and average browsing duration, the general behavior characteristics of users can be intuitively understood. This helps enterprises identify the common habits and trends of users, thus better understanding user needs and market dynamics. At the same time, based on the results of data analysis, the system constructs a detailed user profile for users, including users' basic information, interest preferences, and consumption habits. Conduct in-depth analysis of users' behavior, identify users' potential needs and purchase intentions. Compare the mean data of different time periods to reveal seasonal or cyclical changes in user behavior, which helps enterprises predict future market trends and make corresponding adjustments.

[0061] Through the statistical analysis using the data collection and analysis module, enterprises can more accurately grasp user behavior and market demand. Based on the results of user profiling and behavior analysis, enterprises can formulate more precise and personalized marketing strategies, improve marketing effectiveness and user satisfaction. By comparing the mean data of different time periods, enterprises can reveal seasonal or cyclical changes in user behavior, which helps predict future market trends and make corresponding adjustments.

[0062] Example 2

[0063] The system includes the following components:

[0064] Data collection and analysis module: This module collects data in real time on users' use of smart devices through Internet of Things technology, including usage habits, preferences, and location information. Using statistical analysis techniques, it deeply mines user data and provides user profiling and behavior analysis for enterprises.

[0065] Personalized marketing content push module: Based on user profiling and behavior analysis, it pushes personalized marketing content to users. Through a personalized recommendation algorithm based on collaborative filtering, according to users' purchase history and browsing records, it recommends relevant products or services to users to improve conversion rates.

[0066] Real-time interaction and feedback module: It uses smart devices to provide a real-time interaction and feedback mechanism. Users can use smart devices to interact with enterprises at any time, put forward demands or feedback on usage experiences. Enterprises can receive users' feedback in real time and respond and process it quickly, thereby enhancing user satisfaction and loyalty.

[0067] Cross-platform integrated marketing module: Using the cross-platform characteristics of the Internet of Things, it integrates data and resources from multiple platforms to achieve cross-platform integrated marketing. Through a unified marketing management system, enterprises can coordinate marketing activities on different platforms, improve marketing efficiency and brand influence.

[0068] Intelligent marketing decision-making module: This module uses time series analysis methods to analyze and predict massive data, providing intelligent marketing decision-making support for enterprises. Through a data-driven decision-making approach, enterprises can more accurately grasp market trends and formulate effective marketing strategies.

[0069] The personalized marketing content push module first obtains the user's behavior data through the data collection and analysis module, including click frequency, browsing duration, and purchase records. Then, it preprocesses the data to remove duplicate, incorrect, or invalid data, ensuring the accuracy and integrity of the data. Based on the preprocessed user data, the system constructs detailed user profiles for users, including basic information, interest preferences, and consumption habits. These profile information provides important basis for subsequent personalized recommendations. The system uses a personalized recommendation algorithm of collaborative filtering to analyze the user's behavior data and calculates the similarity between users using the cosine similarity method, that is: , and are two users, and I is the set of all products. and are the ratings of user and for product i respectively. The value range of the cosine similarity is between -1 and 1. The closer the value is to 1, the more similar the two vectors are, that is, the more likely the user is to be interested in the marketing content. By calculating the cosine similarity between users, the system finds user groups with similar interests. The calculation of the cosine similarity takes into account the ratings of users for products and can more accurately measure the similarity between users. For each user, the system finds the k users most similar to him / her and generates a recommendation list based on the purchase behaviors of these similar users. The recommendation list can be updated in real time based on the user's historical behaviors and interest preference information to ensure that the recommended content always meets the personalized needs of users. Finally, the system pushes personalized marketing content to users through smart devices. These contents may include product recommendations, coupons, and event information, aiming to increase the user's purchase intention and conversion rate.

[0070] Through the personalized recommendation algorithm used by the personalized marketing content push module, the e-commerce platform can more accurately grasp the interests and needs of users and provide personalized marketing content for users. This accurate recommendation can reduce the time for users to search and filter, improving the user experience. At the same time, the personalized marketing content is more likely to attract the attention and interest of users, ensuring that the recommendation always meets the personalized needs of users. This helps to enhance the loyalty and stickiness of users to the platform and improve the marketing effect.

[0071] Example 3

[0072] Based on Example 1 and Example 2, the steps of the system are as follows:

[0073] (1) Data collection and analysis

[0074] The system collects user data through Internet of Things devices;

[0075] Uses statistical analysis techniques to deeply mine the collected data and extract user behavior patterns and trends;

[0076] Generate user profiles and behavior analysis reports.

[0077] (2)Personalized marketing content push

[0078] Receive user profiles and behavior analysis reports for data collection and analysis;

[0079] Based on user profiles and behavior analysis, screen matching content from the marketing content library;

[0080] Generate a personalized marketing content recommendation list for users and push the personalized marketing content to users.

[0081] (3)Real-time interaction and feedback

[0082] Users interact with the enterprise in real time through intelligent devices, putting forward requirements or feedback;

[0083] Users' interaction messages are transmitted to the enterprise's server in real time through the Internet of Things;

[0084] The enterprise server receives and processes users' feedback, including classification, analysis, and response;

[0085] Based on the processing results, the enterprise sends response information to users in real time through intelligent devices.

[0086] (4)Cross-platform integrated marketing

[0087] Collect user data from various platforms, integrate and clean data from different platforms;

[0088] Based on the integrated data, formulate cross-platform marketing strategies;

[0089] Execute the formulated marketing strategies on various platforms, monitor the marketing effects in real time, and conduct evaluations.

[0090] (5)Intelligent marketing decision-making

[0091] Integrate and analyze internal and external data of the enterprise;

[0092] Use data mining techniques to discover patterns and trends in the data, and based on the data mining results, formulate specific marketing decisions;

[0093] Execute the formulated marketing decisions and monitor the effects.

[0094] It is obvious to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

Claims

1. A mobile marketing system based on Internet of Things technology, characterized in that, The system includes the following components: Data collection and analysis module: This module collects user data in real time when using smart devices through Internet of Things technology, including usage habits, preferences, and location information. Using statistical analysis techniques, it deeply mines user data to provide user portraits and behavior analysis for enterprises; Personalized marketing content push module: Based on user portraits and behavior analysis, it pushes personalized marketing content to users. Through personalized recommendation algorithms based on collaborative filtering, according to users' purchase history and browsing records, it recommends relevant products or services to users to improve conversion rates; Real-time interaction and feedback module: Utilizes smart devices to provide a real-time interaction and feedback mechanism. Users can use smart devices to interact with enterprises at any time, put forward demands or feedback on usage experiences. Enterprises can receive user feedback in real time and respond and process it quickly, thereby enhancing user satisfaction and loyalty; Cross-platform integrated marketing module: Utilizes the cross-platform characteristics of the Internet of Things to integrate data and resources from multiple platforms to achieve cross-platform integrated marketing. Through a unified marketing management system, enterprises can coordinate marketing activities on different platforms to improve marketing efficiency and brand influence; Intelligent marketing decision-making module: This module uses time series analysis methods to analyze and predict massive data to provide intelligent marketing decision-making support for enterprises. Through data-driven decision-making methods, enterprises can more accurately grasp market trends and formulate effective marketing strategies.

2. The mobile marketing system based on the Internet of Things technology according to claim 1, characterized in that, The specific steps of the data collection and analysis module are as follows: (1) Device connection and data access: Connect users' smart devices (such as smartphones, smartwatches, smart home devices) to the system through the Internet of Things to ensure that the devices can upload user data in real time; (2) Data collection: Collect various types of data of users during the usage process from the connected devices, including usage habits (such as click frequency, browsing duration), preferences (such as purchase records, browsing content), and location information (such as GPS positioning data); (3) Data preprocessing: Remove duplicate, incorrect, or invalid data to ensure the accuracy and integrity of the data, and convert the data into a unified format for convenient subsequent analysis and processing; (4) Data analysis: Conduct basic statistical analysis on the data (such as mean algorithms), and use big data to deeply mine user data to discover patterns, trends, and correlations in user behavior; (5) User portrait and behavior analysis: Based on user data, construct user portraits, including users' basic information, interest preferences, and consumption habits, and conduct in-depth analysis of users' behaviors to identify users' potential needs and purchase intentions, providing a basis for subsequent personalized marketing content push.

3. The mobile marketing system based on Internet of Things technology according to claim 1, wherein, The specific steps of the personalized marketing content push module are as follows: (1) User portrait construction: Based on the user data provided by the data collection and analysis module, construct a detailed user portrait, which includes users' basic information (such as age, gender, region), interest preferences (such as shopping preferences, browsing content), and consumption habits (such as purchase frequency, purchase time); (2) Behavior analysis: Further analyze the user's behavior based on the constructed user profile, which includes identifying the user's active time period, purchase intention, and potential needs; (3) Content matching and screening: Based on the results of user profiling and behavior analysis, screen out highly matched content for the user from the marketing content library, involving the classification and tagging of marketing content for quick matching to target users; (4) Personalized push strategy formulation: According to the user profile, behavior analysis results, and content matching situation, use personalized recommendation algorithms to formulate personalized push strategies, including determining the push time, frequency, channels, as well as the priority and order of the push content.

4. (5) Real-time push and feedback collection: Through the real-time interaction and feedback module, push personalized marketing content to users and collect user feedback, which can be in various forms such as click-through rate, conversion rate, and user evaluations; (6) Effect evaluation and optimization: Evaluate the effectiveness of the personalized push strategy based on user feedback and marketing effect data, and optimize the strategy according to the evaluation results.

5. An mobile marketing system based on Internet of Things technology according to claim 1, characterized in that, The specific steps of the real-time interaction and feedback module are as follows: (1) User interaction initiation: The user enters the marketing interface through intelligent devices (such as mobile phones, tablets, computers) and can choose to interact with the enterprise. The interaction methods include sending text messages, voice messages, pictures, or videos; (2) Message transmission and reception: The user's interaction messages are transmitted to the enterprise's server in real-time through the Internet of Things. The server receives and parses these messages to extract the user's intentions and feedback information; (3) Feedback content processing: The enterprise server processes the user's feedback content, including classification, analysis, and storage. According to the type and content of the feedback, the server can trigger corresponding response mechanisms; (4) Real-time response and feedback: The enterprise sends response information to the user in real-time through intelligent devices according to the user's feedback content. The response is the answer to the user's question, product usage suggestions, and promotional activities; (5) Interaction record and tracking: The system records every interaction process between the user and the enterprise, including the interaction time, content, and response.

6. The mobile marketing system based on Internet of Things technology according to claim 1, characterized in that, The specific steps of the cross-platform integrated marketing module are as follows: (1) Platform data collection: Collect user data from various platforms (such as social media, e-commerce platforms, offline stores). This data includes the user's browsing records, purchase records, and comment feedback; (2) Data integration and behavior analysis: Clean and integrate the collected data to eliminate redundant and incorrect data and ensure data consistency and accuracy. Based on the integrated data, conduct in-depth analysis of the user's behavior to understand the user's consumption habits and interest preferences; (3) Formulate cross-platform marketing strategies: According to the results of user behavior analysis, use clustering algorithms to segment users and formulate cross-platform marketing strategies, including content push and activity arrangements on different platforms; (4) Marketing execution and monitoring: Execute the formulated marketing strategies on various platforms and monitor the marketing effects in real-time, including indicators such as click-through rate and conversion rate; (5) Effect evaluation and optimization: Based on the monitoring results, evaluate the marketing effects and optimize and adjust the marketing strategies according to the evaluation results.

7. A mobile marketing system based on Internet of Things technology according to claim 1, characterized in that, Specific steps of the intelligent marketing decision-making module: (1) Data collation: The enterprise collects relevant internal and external data and conducts cleaning and collation. Internal data includes customer data, sales data, and product data, which are usually stored in the enterprise's internal database or CRM system. External data can be obtained from market research reports and social media comments; (2) Data mining: Analyze and mine the completed data collation to obtain information about customer behavior and purchase preferences, and use various time series analysis methods to identify patterns and trends in the data; (3) Decision-making and implementation: Based on the results of data mining, formulate specific marketing decisions, such as the selection of target markets, product pricing strategies, and the arrangement of promotional activities. These decisions aim to maximize marketing effects and enhance the enterprise's market share and profitability.

8. The mobile marketing system based on Internet of Things technology according to claim 2, characterized in that, The data collection and analysis module understands the general characteristics of user behavior through statistical analysis. It uses a basic mean algorithm for statistics. Its operation mode and formula are as follows: The mean is the sum of all values divided by the number of values, which is used to represent the "average" or "central" position of the data: , is the sum of all values , n is the number of values. Suppose a set of data on the browsing duration of a certain website page by users is collected in the data collection and analysis module. This set of data includes the browsing durations (in minutes) of 5 users: [10, 15, 20, 25, 30]. Calculate the sum of the data = 10 + 15 + 20 + 25 + 30 = 100. Divide the sum by the number to get the mean . The mean of the browsing duration of this group of users on a certain website page is 20 minutes. By analyzing the average browsing duration of users, the browsing habits and interest preferences of users can be further analyzed. Mean analysis can provide quantitative indicators of user behavior. By calculating the mean of user behavior, such as the average click frequency and average browsing duration, the general behavior characteristics of users can be intuitively understood. This helps enterprises identify the general habits and trends of users, so as to better understand user needs and market dynamics. At the same time, by comparing the mean data of different time periods, the seasonal or periodic changes in user behavior can be revealed, which helps enterprises predict future market trends and make corresponding adjustments.

9. The mobile marketing system based on Internet of Things technology according to claim 3, characterized in that The personalized marketing content push module analyzes the behavior data of users through a personalized recommendation algorithm based on collaborative filtering, finds user groups with similar interests, and recommends content to the current user according to the behaviors of these similar users. The cosine similarity method is used to calculate the similarity between users, that is: , and are two users, and I is the set of all commodities. and are the ratings of user and for commodity i respectively. The value range of cosine similarity is between -1 and 1. The closer the value is to 1, the more similar the two vectors are, that is, the more likely the user is to be interested in the marketing content. Calculating the similarity between the user and the marketing content can more accurately find the content that the user is interested in, thereby improving the accuracy of recommendation. For each user, find the k users who are most similar to him / her, and generate a recommendation list according to the purchase behaviors of these similar users. This list can be updated in real time based on the information of the user's historical behaviors and interest preferences to achieve personalized marketing content push. Precise recommendation can reduce the time for users to search and filter, making it easier for them to find the content they are interested in, thereby enhancing the user experience and triggering the user's purchase behavior, thus increasing the marketing effect.

10. A mobile marketing system based on Internet of Things technology according to claim 5, characterized in that, The cross-platform integrated marketing module divides users into different groups through clustering algorithms, helping the marketing team to understand the needs and preferences of different user groups more deeply, so as to formulate more accurate and personalized marketing strategies. Its operation mode and formula are as follows: collect user data from multiple platforms (such as social media, e-commerce platforms, offline stores), including users' purchase records, browsing behaviors, and interaction feedbacks. Extract features related to user behaviors and preferences from the collected raw data. These features include users' purchase frequencies, purchased product categories, browsing durations, and the number of likes or comments. Use clustering algorithms (such as K-means) to perform clustering analysis on the data, that is: randomly select K initial centroids (i.e., clustering centers), assign each data point to the nearest centroid to form K clusters, recalculate the centroids of each cluster until the positions of the centroids no longer change significantly or reach the preset number of iterations. Use the Euclidean distance formula to calculate the distance between a data point and a centroid: , where x and y are two data points (or centroids), and n is the number of feature dimensions, and are the values of vectors x and y in the i-th dimension respectively. The algorithm will divide the data into different groups according to the similarity or distance between users. Users within each group have similar behavior patterns or preferences. After clustering, each group represents a user group with similar characteristics and behavior patterns. The marketing team can further analyze the characteristics of these groups, understand the needs and preferences of different user groups, and push content or activity information that matches their interests and needs to different user groups, which can increase the click-through rate, conversion rate, and user engagement of marketing activities, thus improving the overall marketing effect, allocating marketing resources, avoiding waste on inefficient or irrelevant user groups, and thus achieving cost control and benefit maximization.

11. The mobile marketing system based on Internet of Things technology according to claim 6, wherein The intelligent marketing decision-making module uses the moving average method in time series analysis, enabling enterprises to more accurately grasp sales trends, avoid blind following or lagged responses. Its operation mode and formula are as follows: Enterprises organize the daily sales data collected into a time series format, that is, data points arranged in chronological order. Let be the sales amount on the t-th day, and n be the size of the moving average window. Then the moving average value on the t-th day is calculated by the formula: , add up the sales amounts of the most recent n days, and then divide by n to obtain the average value. This average value is the moving average sales amount on the t-th day. According to the prediction results of the sales trend, enterprises can reasonably arrange production plans to ensure that production capacity matches market demand, improve production efficiency and resource utilization rate. By understanding the changes in the sales trend, enterprises can formulate targeted marketing strategies, such as adjusting prices, launching promotional activities or optimizing product portfolios, thereby enhancing marketing effects and market competitiveness. Through the moving average method, enterprises can smooth out short-term fluctuations in sales data, making it easier to identify long-term trends. This trend analysis helps enterprises make more informed decisions, adjust inventory levels, formulate marketing strategies and predict future sales performance.

Images