A method for big data collection and analysis and intelligent SMS sending management
Through the analysis of the big data set of user consumption activities and the construction of user portraits, the automation and precision problems of traditional SMS sending management are solved, and efficient SMS content customization and sending strategies are realized, which improves user participation and satisfaction.
Patent Information
- Application Number
- CN202411237366.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-09-05
AI Technical Summary
Traditional big data acquisition and analysis methods face challenges of diverse data sources and huge data volume, and SMS sending management relies on manual operations or simple rule engines, which cannot be automated and accurate.
By obtaining the big data set of user consumption activities, conducting consumption behavior and preference mining analysis, building user portraits, customizing SMS content, and evaluating the timing and frequency of SMS sending based on consumption behavior and preferences, and performing intelligent management.
It realizes the automation and precision of SMS sending, improves user reading rate and response rate, enhances user experience and satisfaction, and promotes the establishment and maintenance of good relationships between users and enterprises.
Smart Images

Figure CN118764830B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of short message management, and in particular to a method for managing big data collection and analysis and intelligent short message sending. Background Art
[0002] In today's information age, with the popularization of mobile Internet and the development of big data technology, more and more data are generated and accumulated, including user consumption behavior data, consumer marketing activity data, etc. How to effectively collect and analyze these big data and use intelligent means to achieve information transmission and management has become an important issue at present. In the business field, understanding users' consumption behavior and preferences is crucial to formulating accurate marketing strategies. In the process of collecting big data on user consumption activities, users' consumption data can be efficiently collected from shopping platforms, offline stores, payment systems and other channels, including purchase records, consumption preferences, consumption frequency and other information. However, traditional big data collection and analysis methods often face the challenges of diverse data sources and huge data volumes, while SMS sending management methods usually rely on manual operations or simple rule engines, which cannot achieve automation and precision in SMS sending. Summary of the invention
[0003] Based on this, it is necessary for the present invention to provide a method for big data collection and analysis and intelligent SMS sending management to solve at least one of the above technical problems.
[0004] To achieve the above purpose, a method for big data collection and analysis and intelligent SMS sending management method includes the following steps:
[0005] Step S1: Obtain a big data set of user consumption activities, and perform consumption behavior and consumption preference mining and analysis on the big data set of user consumption activities to obtain user consumption behavior data and user consumption preference data; perform potential consumption demand analysis on the big data set of user consumption activities based on the user consumption behavior data and user consumption preference data to obtain user potential consumption demand data;
[0006] Step S2: constructing a user portrait for the user consumption activity big data set to obtain a consumer user portrait model; obtaining marketing activity demand data, and performing SMS content customization analysis on the consumer user portrait model based on the user's potential consumption demand data and the marketing activity demand data to obtain personalized SMS content for the consumer user;
[0007] Step S3: evaluating and analyzing the SMS sending timing and frequency of the personalized SMS content of the consumer user according to the user consumption behavior data and the user consumption preference data, and obtaining the SMS sending timing and SMS sending frequency of the consumer user; performing timed sending processing on the personalized SMS content of the consumer user based on the SMS sending timing and SMS sending frequency of the consumer user, and obtaining the SMS sending content of the consumer user;
[0008] Step S4: Conduct SMS feedback evaluation and analysis on the content of scheduled SMS messages sent by consumer users to obtain the user reading rate and user emotional response rate of each type of SMS content; based on the user reading rate and user emotional response rate of each type of SMS content, perform intelligent management and processing on the sending method of the content of scheduled SMS messages sent by consumer users to obtain the intelligent management result of SMS sending by consumer users.
[0009] The present invention first obtains a large data set of user consumption activities in order to deeply understand the user's consumption behavior and preferences, so as to provide accurate marketing strategies and product positioning for the subsequent processing process. This data set contains a large amount of consumption information of users at different times, places and occasions. By analyzing these data, the user's consumption patterns and trends can be revealed, providing an important reference for the subsequent analysis of user consumption behavior and preferences. By performing consumption behavior analysis on the large data set of user consumption activities, it is intended to deeply understand the user's purchasing habits, consumption frequency, purchase channels and other aspects of information, and the user's consumption characteristics and behavior patterns can be discovered to provide data support for the subsequent processing process. At the same time, by performing user consumption preference mining and analysis on the standard data set of user consumption activities, it is intended to identify the user's preferences and preferences for specific products or services. This step can provide customized product preference recommendations for the subsequent processing process by mining the user's consumption preferences, so as to enhance user stickiness and loyalty, and improve user experience and satisfaction. In addition, by analyzing the potential consumption needs of the user consumption activity big data set based on the user consumption behavior data and the user consumption preference data, the purpose is to discover the user's potential consumption needs and unsatisfied purchasing desires. This step can provide innovative product development directions and SMS sending strategies for the subsequent processing process through the analysis of potential consumption needs, thereby satisfying the subsequent SMS sending management process. Secondly, by constructing user portraits for the user consumption activity big data set, this step can combine the user entity information and attribute relationships obtained by analysis, and form a comprehensive description of the user, namely the user portrait, through data analysis and modeling technology. User portraits are an abstract presentation of user characteristics, behaviors and preferences, which helps to better understand user needs and behavior patterns, thereby achieving precision marketing and personalized recommendations. By obtaining marketing activity demand data, which includes but is not limited to market research results, marketing goals, product positioning, etc., by collecting and organizing marketing activity demand data, the company's marketing goals and strategies can be clearly understood, providing guidance and basis for subsequent SMS content customization. By analyzing the SMS content customization of the consumer user portrait model based on the user's potential consumption demand data and marketing activity demand data, this step can personalize the SMS content by combining the user's consumption demand and the goal of the marketing activity to make it more in line with the user's interests and preferences, improve marketing effectiveness and user participation, and this personalized SMS content can enhance the user's sense of identity and interactivity, and promote the establishment and maintenance of a good relationship between the user and the company. Then, by evaluating and analyzing the SMS sending timing of the consumer user's personalized SMS content based on the user's consumption behavior data and the user's consumption preference data, the user's SMS reception timing is evaluated, and SMS is sent during the time period when the user's consumption activity is high, thereby improving its reading rate and response rate.The SMS sending frequency evaluation and analysis was also conducted to evaluate and analyze the user's willingness to receive SMS, determine the frequency of SMS sending, avoid causing interference or disgust to users, and maintain users' acceptance and active participation in SMS marketing. In addition, the personalized SMS content of consumer users was sent on a scheduled basis based on the consumer user's SMS sending timing and SMS sending frequency. This step is to send personalized SMS content in an appropriate time period and frequency based on the previous analysis results to improve the user's reading and response rate, thereby achieving a more accurate SMS content sending goal. Finally, SMS feedback monitoring of consumer users' SMS timed content is aimed at obtaining consumer users' SMS sending feedback information data by monitoring users' feedback information on SMS, including reply, forwarding, deletion and other behaviors, and evaluating and analyzing the reading rate and response rate, so as to evaluate the user reading rate and user emotional response rate of different types of SMS, so as to understand the user's attention and attractiveness to SMS content, and provide guidance and strategic suggestions for further improving the effectiveness of SMS marketing. In addition, the scheduled text message content of consumer users is intelligently managed based on the user reading rate and user emotional response rate of each type of text message content. The method and timing of text message delivery can be adjusted according to the user's reading preference and emotional feedback, thereby improving user satisfaction and participation, thereby achieving better automation and precision of text message delivery. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:
[0011] Figure 1 This is a schematic diagram of the steps of the big data collection and analysis and intelligent SMS sending management method of the present invention;
[0012] Figure 2 for Figure 1 Detailed step flow diagram of step S1;
[0013] Figure 3 for Figure 2 Detailed step flow chart of step S13 in FIG. DETAILED DESCRIPTION
[0014] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.
[0015] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.
[0016] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.
[0017] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for big data collection and analysis and intelligent SMS sending mode management, the method comprising the following steps:
[0018] Step S1: Obtain a big data set of user consumption activities, and perform consumption behavior and consumption preference mining and analysis on the big data set of user consumption activities to obtain user consumption behavior data and user consumption preference data; perform potential consumption demand analysis on the big data set of user consumption activities based on the user consumption behavior data and user consumption preference data to obtain user potential consumption demand data;
[0019] Step S2: constructing a user portrait for the user consumption activity big data set to obtain a consumer user portrait model; obtaining marketing activity demand data, and performing SMS content customization analysis on the consumer user portrait model based on the user's potential consumption demand data and the marketing activity demand data to obtain personalized SMS content for the consumer user;
[0020] Step S3: evaluating and analyzing the SMS sending timing and frequency of the personalized SMS content of the consumer user according to the user consumption behavior data and the user consumption preference data, and obtaining the SMS sending timing and SMS sending frequency of the consumer user; performing timed sending processing on the personalized SMS content of the consumer user based on the SMS sending timing and SMS sending frequency of the consumer user, and obtaining the SMS sending content of the consumer user;
[0021] Step S4: Conduct SMS feedback evaluation and analysis on the content of scheduled SMS messages sent by consumer users to obtain the user reading rate and user emotional response rate of each type of SMS content; based on the user reading rate and user emotional response rate of each type of SMS content, perform intelligent management and processing on the sending method of the content of scheduled SMS messages sent by consumer users to obtain the intelligent management result of SMS sending by consumer users.
[0022] In the embodiment of the present invention, please refer to Figure 1 As shown, it is a schematic diagram of the steps of the big data collection and analysis and intelligent SMS sending mode management method of the present invention. In this example, the big data collection and analysis and intelligent SMS sending mode management method includes the following steps:
[0023] Step S1: Obtain a big data set of user consumption activities, and perform consumption behavior and consumption preference mining and analysis on the big data set of user consumption activities to obtain user consumption behavior data and user consumption preference data; perform potential consumption demand analysis on the big data set of user consumption activities based on the user consumption behavior data and user consumption preference data to obtain user potential consumption demand data;
[0024] The embodiment of the present invention determines the data acquisition channels, including internal system records, third-party data providers, API interfaces, etc., and determines the data scope to be collected, including user consumption records, transaction information, behavior data, etc., and obtains a large amount of user consumption activity information data at different times, places and occasions from the determined data source by using corresponding technical means (such as web crawlers, data capture tools, etc.), thereby obtaining a large data set of user consumption activities. Secondly, by extracting data related to user consumption behavior from the user consumption activity big data set, including the characteristics, trends and laws of user consumption behavior, and discovering the user's consumption motivation, purchase decision process and interactive behavior, the user consumption behavior data is obtained. At the same time, by mining and analyzing the consumption preference of the user consumption activity big data set based on the user consumption behavior data obtained by analysis, the relationship between different consumption behaviors is analyzed to identify the user's preference degree and change trend for different consumption elements, thereby obtaining user consumption preference data. Then, by combining the user consumption behavior data and user consumption preference data obtained through analysis, an impact assessment algorithm is used to conduct an evaluation and analysis of the potential impact of the corresponding consumption sentiment tendencies in the large data set of user consumption activities, so as to evaluate the degree of influence of different consumption behaviors and consumption preferences on user consumption sentiment tendencies, and explore the potential influencing factors of user consumption behaviors and consumption preferences on their consumption emotions. By combining the potential influencing factors of consumption behaviors and potential influencing factors of consumption preferences obtained through analysis, a consumer demand forecasting analysis method is used to conduct a forecasting analysis on the standard data set of user consumption activities, so as to comprehensively consider the impact of consumption behaviors and consumption preferences on user needs, so as to more accurately predict users' future consumption needs, and finally obtain users' potential consumption demand data.
[0025] Step S2: constructing a user portrait for the user consumption activity big data set to obtain a consumer user portrait model; obtaining marketing activity demand data, and performing SMS content customization analysis on the consumer user portrait model based on the user's potential consumption demand data and the marketing activity demand data to obtain personalized SMS content for the consumer user;
[0026] The embodiment of the present invention uses natural language processing technology or entity recognition algorithm to identify and analyze the user consumption activity big data set to extract information entities related to the user, including but not limited to the user's name, age, gender, geographic location, etc., and uses data mining or association rule mining and other technologies to mine and analyze the consumption attribute information of each user in the user consumption activity big data set to analyze the association and rules between user consumption attributes, such as interactions between users, purchase preferences, consumption frequency, etc., and uses data analysis and modeling technology to construct a user portrait model to map the user's entity information and attribute relationship to specific features and attributes to form a comprehensive description of the user, thereby obtaining a consumer user portrait model. Secondly, by obtaining the demand for marketing activities from the marketing department or related marketing channels, including but not limited to market research results, marketing goals, product positioning, marketing activity themes, target groups, promotional content, etc., marketing activity demand data is obtained. Then, by combining the analyzed user potential consumption demand data and marketing activity demand data, the SMS content is customized for the corresponding consumer users in the consumer user portrait model, so as to analyze the consumption preferences and marketing activity needs of different consumer user groups and design personalized SMS content, including content themes, promotional information, preferential activities, etc., and finally obtain personalized SMS content for consumer users.
[0027] Step S3: evaluating and analyzing the SMS sending timing and frequency of the personalized SMS content of the consumer user according to the user consumption behavior data and the user consumption preference data, and obtaining the SMS sending timing and SMS sending frequency of the consumer user; performing timed sending processing on the personalized SMS content of the consumer user based on the SMS sending timing and SMS sending frequency of the consumer user, and obtaining the SMS sending content of the consumer user;
[0028] The embodiment of the present invention uses a data analysis tool or algorithm to evaluate the sending timing of the analyzed user consumption behavior data and user consumption preference data, so as to evaluate in which time periods sending text messages to users can achieve better results, and ensure that text messages are sent during time periods with high user consumption activity, thereby obtaining the time for sending text messages to consumer users. At the same time, by evaluating and analyzing the sending frequency of the corresponding consumer user personalized text message content, the text message sending frequency of different user groups is evaluated and analyzed, that is, the frequency of sending text messages to users is determined, and the text message sending frequency is ensured to meet the user's acceptance ability and willingness, thereby obtaining the text message sending frequency of consumer users. Then, by combining the analyzed consumer user text message sending timing and consumer user text message sending frequency, a corresponding timed sending strategy is formulated to determine the time and frequency of sending text messages to users, and by performing timed sending processing of personalized text message content for consumer users according to the timed sending strategy, while ensuring that the text message content can be effectively conveyed during the user's active time period, finally obtaining the timed sending content of consumer user text messages.
[0029] Step S4: Conduct SMS feedback evaluation and analysis on the content of scheduled SMS messages sent by consumer users to obtain the user reading rate and user emotional response rate of each type of SMS content; based on the user reading rate and user emotional response rate of each type of SMS content, perform intelligent management and processing on the sending method of the content of scheduled SMS messages sent by consumer users to obtain the intelligent management result of SMS sending by consumer users.
[0030] The embodiment of the present invention monitors and analyzes the feedback process of the content of the scheduled text messages sent by the consumer user to the user, so as to monitor the feedback information of the user on the text messages, including reply, forwarding, deletion and other behaviors, and analyze the monitored data by using a data analysis tool or algorithm to extract the user's feedback information, such as reception status, click status, etc., and obtain the user reception volume and click volume of the corresponding text messages. At the same time, the consumer user's scheduled text messages are classified and statistically processed by combining the user reception volume and click volume obtained by analysis to obtain the total user reception amount and the total user click amount of each type of scheduled text message content. Secondly, the total user reception amount and the total user click amount of each type of text message content obtained by statistical analysis are combined to evaluate and analyze the text message content of each category using a reading rate evaluation method to evaluate and calculate the user reading frequency of each type of text message content, so as to obtain the user reading rate of each type of text message content. Then, by using natural language processing technology or sentiment analysis algorithm, sentiment recognition analysis is performed on consumer user SMS feedback information to identify positive, negative or neutral sentiments, and sentiment response efficiency evaluation analysis is performed on the corresponding classified SMS content of each category to evaluate and calculate the user's sentiment response to different types of SMS, thereby obtaining the user sentiment response rate of each type of SMS content. Then, by combining the user reading rate and user sentiment response rate of each type of SMS content obtained by analysis, the corresponding consumer user SMS scheduled content sending method is managed and adjusted using intelligent algorithms or decision models, so as to adjust the SMS sending method (including batch sending, targeted sending, etc.) and timing according to the user's reading preference and sentiment feedback, and finally obtain the intelligent management result of consumer user SMS sending.
[0031] The present invention first obtains a large data set of user consumption activities in order to deeply understand the user's consumption behavior and preferences, so as to provide accurate marketing strategies and product positioning for the subsequent processing process. This data set contains a large amount of consumption information of users at different times, places and occasions. By analyzing these data, the user's consumption patterns and trends can be revealed, providing an important reference for the subsequent analysis of user consumption behavior and preferences. By performing consumption behavior analysis on the large data set of user consumption activities, it is intended to deeply understand the user's purchasing habits, consumption frequency, purchase channels and other aspects of information, and the user's consumption characteristics and behavior patterns can be discovered to provide data support for the subsequent processing process. At the same time, by performing user consumption preference mining and analysis on the standard data set of user consumption activities, it is intended to identify the user's preferences and preferences for specific products or services. This step can provide customized product preference recommendations for the subsequent processing process by mining the user's consumption preferences, so as to enhance user stickiness and loyalty, and improve user experience and satisfaction. In addition, by analyzing the potential consumption needs of the user consumption activity big data set based on the user consumption behavior data and the user consumption preference data, the purpose is to discover the user's potential consumption needs and unsatisfied purchasing desires. This step can provide innovative product development directions and SMS sending strategies for the subsequent processing process through the analysis of potential consumption needs, thereby satisfying the subsequent SMS sending management process. Secondly, by constructing user portraits for the user consumption activity big data set, this step can combine the user entity information and attribute relationships obtained by analysis, and form a comprehensive description of the user, namely the user portrait, through data analysis and modeling technology. User portraits are an abstract presentation of user characteristics, behaviors and preferences, which helps to better understand user needs and behavior patterns, thereby achieving precision marketing and personalized recommendations. By obtaining marketing activity demand data, which includes but is not limited to market research results, marketing goals, product positioning, etc., by collecting and organizing marketing activity demand data, the company's marketing goals and strategies can be clearly understood, providing guidance and basis for subsequent SMS content customization. By analyzing the SMS content customization of the consumer user portrait model based on the user's potential consumption demand data and marketing activity demand data, this step can personalize the SMS content by combining the user's consumption demand and the goal of the marketing activity to make it more in line with the user's interests and preferences, improve marketing effectiveness and user participation, and this personalized SMS content can enhance the user's sense of identity and interactivity, and promote the establishment and maintenance of a good relationship between the user and the company. Then, by evaluating and analyzing the SMS sending timing of the consumer user's personalized SMS content based on the user's consumption behavior data and the user's consumption preference data, the user's SMS reception timing is evaluated, and SMS is sent during the time period when the user's consumption activity is high, thereby improving its reading rate and response rate.The SMS sending frequency evaluation and analysis was also conducted to evaluate and analyze the user's willingness to receive SMS, determine the frequency of SMS sending, avoid causing interference or disgust to users, and maintain users' acceptance and active participation in SMS marketing. In addition, the personalized SMS content of consumer users was sent on a scheduled basis based on the consumer user's SMS sending timing and SMS sending frequency. This step is to send personalized SMS content in an appropriate time period and frequency based on the previous analysis results to improve the user's reading and response rate, thereby achieving a more accurate SMS content sending goal. Finally, SMS feedback monitoring of consumer users' SMS timed content is aimed at obtaining consumer users' SMS sending feedback information data by monitoring users' feedback information on SMS, including reply, forwarding, deletion and other behaviors, and evaluating and analyzing the reading rate and response rate, so as to evaluate the user reading rate and user emotional response rate of different types of SMS, so as to understand the user's attention and attractiveness to SMS content, and provide guidance and strategic suggestions for further improving the effectiveness of SMS marketing. In addition, the scheduled text message content of consumer users is intelligently managed based on the user reading rate and user emotional response rate of each type of text message content. The method and timing of text message delivery can be adjusted according to the user's reading preference and emotional feedback, thereby improving user satisfaction and participation, thereby achieving better automation and precision of text message delivery.
[0032] Preferably, step S1 comprises the following steps:
[0033] Step S11: Acquire a large data set of user consumption activities;
[0034] Step S12: Clean and standardize the large data set of user consumption activities to obtain a standard data set of user consumption activities;
[0035] Step S13: Performing user consumption behavior analysis on the user consumption activity standard data set to obtain user consumption behavior data;
[0036] Step S14: performing user consumption preference mining and analysis on the user consumption activity standard data set based on the user consumption behavior data to obtain user consumption preference data;
[0037] Step S15: Based on the user consumption behavior data and the user consumption preference data, the user consumption activity standard data set is analyzed for potential consumption demand to obtain the user's potential consumption demand data.
[0038] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:
[0039] Step S11: Acquire a large data set of user consumption activities;
[0040] The embodiment of the present invention determines the channels for data acquisition, including internal system records, third-party data providers, API interfaces, etc., and determines the scope of data to be collected, including user consumption records, transaction information, behavior data, etc. Then, by using corresponding technical means (such as web crawlers, data capture tools, etc.), a large amount of consumption activity information data of users at different times, places and occasions is obtained from the determined data sources, and finally a large data set of user consumption activities is obtained.
[0041] Step S12: Clean and standardize the large data set of user consumption activities to obtain a standard data set of user consumption activities;
[0042] The embodiment of the present invention performs data cleaning on the collected large data set of user consumption activities to remove outliers, process missing data, process duplicate records, etc., and unifies the format of the cleaned data according to certain standards to ensure the consistency and comparability of the data, such as unifying the time format, unit conversion, naming standardization, etc., and ensures the accuracy and completeness of the data, and finally obtains a standard data set of user consumption activities.
[0043] Step S13: Performing user consumption behavior analysis on the user consumption activity standard data set to obtain user consumption behavior data;
[0044] The embodiment of the present invention extracts data fields related to user consumption records and consumption interactions from a standard data set of user consumption activities, and identifies and extracts user consumption records, including information such as purchased goods, consumption amounts, and purchase times, and extracts consumption interaction data between users, including interactive behaviors such as transactions, comments, and sharing between users. Secondly, by combining the data obtained from the above analysis, using appropriate evolutionary analysis tools, such as evolutionary maps, time series analysis, etc., an evolutionary analysis is performed on the corresponding user consumption behavior process in the standard data set of user consumption activities to analyze the evolutionary process of user consumption behavior. Then, by using appropriate user behavior analysis methods (such as user portrait analysis, user behavior path analysis, etc.), the evolutionary process of user consumption behavior obtained through evolutionary analysis is analyzed to analyze the characteristics, trends, and laws of user consumption behavior, and discover the user's consumption motivation, purchase decision process, and interactive behavior, and finally obtain user consumption behavior data.
[0045] Step S14: performing user consumption preference mining and analysis on the user consumption activity standard data set based on the user consumption behavior data to obtain user consumption preference data;
[0046] The embodiment of the present invention extracts relevant fields, such as consumption time, consumption amount, consumption location, etc., from a standard data set of user consumption activities, and performs statistical analysis on the extracted data to identify various consumption elements in user consumption activities, and uses a suitable association mining algorithm (such as association rule mining (Apriori algorithm), sequence pattern mining, etc.) to mine and analyze the consumption behavior relationship between each user consumption element to discover the consumption behavior relationship between different consumption elements, such as purchase association, behavior sequence, etc. At the same time, the corresponding user consumption elements are connected according to the consumption behavior relationship between different consumption elements obtained by analysis to form a complete consumption relationship map, and then, by combining the consumption behavior relationship map obtained by analysis, a suitable preference mining algorithm (such as a recommendation algorithm based on a map) is used to mine and analyze the user consumption situation in the standard data set of user consumption activities for consumption preferences, so as to analyze the relationship between different consumption behaviors to identify the user's preference degree and change trend for different consumption elements, and finally obtain user consumption preference data.
[0047] Step S15: Based on the user consumption behavior data and the user consumption preference data, the user consumption activity standard data set is analyzed for potential consumption demand to obtain the user's potential consumption demand data.
[0048] The embodiment of the present invention uses sentiment dictionary technology to perform sentiment analysis on text information data in a standard data set of user consumption activities to identify the user's sentiment tendency data such as preferences, dislikes, and satisfaction, and uses an impact assessment algorithm to perform potential impact assessment analysis on the corresponding user consumption sentiment tendency data by combining the user consumption behavior data and the user consumption preference data obtained by analysis, so as to evaluate the degree of influence of different consumption behaviors and consumption preferences on the user's consumption sentiment tendencies, and explore the potential influence factors of the user's consumption behavior and consumption preferences on his consumption emotions, and then, by combining the potential influence factors of consumption behavior and consumption preference obtained by analysis, use a consumption demand prediction analysis method to perform prediction analysis on the standard data set of user consumption activities, so as to comprehensively consider the influence of consumption behavior and consumption preference on user demand, so as to more accurately predict the user's future consumption demand, and finally obtain the user's potential consumption demand data.
[0049] The present invention first obtains a large data set of user consumption activities in order to deeply understand the user's consumption behavior and preferences, so as to provide accurate marketing strategies and product positioning for the subsequent processing process. This data set contains a large amount of consumption information of users at different times, places and occasions. By analyzing these data, the user's consumption patterns and trends can be revealed, providing important references for the subsequent analysis of user consumption behavior and preferences. Secondly, by performing data cleaning and standardization on the large data set of user consumption activities, it is intended to improve the quality and consistency of the data and ensure the accuracy and reliability of subsequent analysis. Through cleaning and standardization, noise and outliers in the data can be removed, the data format and unit can be unified, and the data can be made more comparable and interpretable, laying the foundation for subsequent consumption behavior analysis. Then, by performing consumption behavior analysis on the standard data set of user consumption activities that has been cleaned and standardized, it is intended to deeply understand the user's purchasing habits, consumption frequency, purchase channels and other aspects. Through consumption behavior analysis, the user's consumption characteristics and behavior patterns can be discovered, providing data support for the subsequent processing process. Next, by mining and analyzing the user consumption preference of the user consumption activity standard data set based on the user consumption behavior data, the aim is to identify the user's preferences and preferences for specific products or services. This step can provide customized product preference recommendations for the subsequent processing process by mining the user's consumption preferences, so as to enhance user stickiness and loyalty, and improve user experience and satisfaction. Finally, by analyzing the potential consumption demand of the user consumption activity standard data set based on the user consumption behavior data and the user consumption preference data, the aim is to discover the user's potential consumption demand and unsatisfied purchasing desire. This step can provide innovative product development directions and SMS sending strategies for the subsequent processing process through the analysis of potential consumption demand, thereby satisfying the subsequent SMS sending management process.
[0050] Preferably, step S13 comprises the following steps:
[0051] Step S131: extracting and processing user consumption records and consumption interactions from the user consumption activity standard data set to obtain user consumption record data and user consumption interaction data;
[0052] Step S132: performing time series change analysis on the user consumption record data and the user consumption interaction data to obtain the user consumption record time series change data and the user consumption interaction time series change data;
[0053] Step S133: Performing behavior pattern mining and analysis on the user consumption record time series change data and the user consumption interaction time series change data to obtain the user consumption record change pattern data and the user consumption interaction change pattern data;
[0054] Step S134: performing consumption behavior evolution analysis on the user consumption activity standard data set based on the user consumption record change pattern data and the user consumption interaction change pattern data to obtain the user consumption behavior evolution process;
[0055] Step S135: Analyze the user consumption behavior evolution process to obtain user consumption behavior data.
[0056] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 2 FIG. 1 is a schematic diagram of a detailed step flow chart of step S13 in FIG. 1 . In this embodiment, step S13 includes the following steps:
[0057] Step S131: extracting and processing user consumption records and consumption interactions from the user consumption activity standard data set to obtain user consumption record data and user consumption interaction data;
[0058] The embodiment of the present invention extracts data fields related to user consumption records and consumption interactions, such as user ID, consumption time, consumption amount, consumption location, interaction object, etc., from the user consumption activity standard data set, and identifies and extracts the user's consumption records, including information such as purchased goods, consumption amount, and purchase time, and at the same time extracts consumption interaction data between users, including interactive behaviors such as transactions, comments, and sharing between users, to finally obtain user consumption record data and user consumption interaction data.
[0059] Step S132: performing time series change analysis on the user consumption record data and the user consumption interaction data to obtain the user consumption record time series change data and the user consumption interaction time series change data;
[0060] The embodiment of the present invention analyzes user consumption record data and user consumption interaction data by using a time series change analysis method to analyze the changing trend of user consumption records over time, including fluctuations in consumption amounts, changes in purchase frequency, etc., and analyzes the changes in user consumption interactions over time, including increases and decreases in the number of transactions, changes in the number of comments, etc., to ultimately obtain user consumption record time series change data and user consumption interaction time series change data.
[0061] Step S133: Performing behavior pattern mining and analysis on the user consumption record time series change data and the user consumption interaction time series change data to obtain the user consumption record change pattern data and the user consumption interaction change pattern data;
[0062] The embodiments of the present invention use appropriate behavior pattern mining algorithms (such as cluster analysis, time series pattern mining, etc.) to perform change pattern mining and analysis on the time series change data of user consumption records and the time series change data of user consumption interactions, so as to analyze the change patterns of user consumption records and identify typical patterns of different user consumption behaviors, such as holiday shopping, participation in promotional activities, etc. Similarly, pattern mining and analysis is performed on the consumption interaction data to discover typical patterns of user consumption interactions, such as peak hours of social interactions, comment trends of popular products, etc., and finally obtain user consumption record change pattern data and user consumption interaction change pattern data.
[0063] Step S134: performing consumption behavior evolution analysis on the user consumption activity standard data set based on the user consumption record change pattern data and the user consumption interaction change pattern data to obtain the user consumption behavior evolution process;
[0064] The embodiment of the present invention uses appropriate evolutionary analysis tools, such as evolutionary maps, time series analysis, etc., to combine the user consumption record change pattern data and the user consumption interaction change pattern data obtained by analysis to perform evolutionary analysis on the corresponding user consumption behavior process in the user consumption activity standard data set, so as to analyze the evolution process of user consumption behavior, including the correlation changes and evolution laws of consumption records and consumption interactions, and finally obtain the evolution process of user consumption behavior.
[0065] Step S135: Analyze the user consumption behavior evolution process to obtain user consumption behavior data.
[0066] The embodiments of the present invention use appropriate user behavior analysis methods (such as user portrait analysis, user behavior path analysis, etc.) to analyze the evolution process of user consumption behavior obtained through evolutionary analysis, so as to analyze the characteristics, trends and laws of user consumption behavior, and discover the user's consumption motivation, purchase decision process and interactive behavior, and finally obtain user consumption behavior data.
[0067] The present invention firstly extracts and processes the user consumption records and consumption interactions of the user consumption activity standard data set, aiming to extract the user's consumption records and consumption interaction information from the original data for subsequent analysis. Through the extraction process, the consumption behavior and interaction activities in the large data set can be structured, thereby forming a data set of two dimensions of user consumption record data and user consumption interaction data, laying the foundation for subsequent time series change analysis and behavior pattern mining. Secondly, by performing time series change analysis on the user consumption record data and the user consumption interaction data, it is aimed to understand the changing trend of the user's consumption behavior and interaction activities over time. This step can identify the periodicity, trend and mutation point of the consumption behavior and interaction activities through time series change analysis, thereby providing data support for subsequent behavior pattern mining and consumption behavior evolution analysis. Then, by performing behavior pattern mining analysis on the user consumption record time series change data and the user consumption interaction time series change data, it is aimed to discover the potential patterns and laws of the user's consumption behavior and interaction activities. This step can identify the user's consumption preferences, behavior habits and interaction characteristics in different time periods and scenarios through behavior pattern mining, providing theoretical support for subsequent consumption behavior evolution analysis. Next, we conduct consumption behavior evolution analysis on the standard data set of user consumption activities based on the data of user consumption record change patterns and user consumption interaction change patterns, aiming to reveal the development process and trend of user consumption behavior. Through consumption behavior evolution analysis, we can deeply understand the changes in user behavior during the consumption process, including the evolution of consumption preferences, changes in purchase frequency, etc., and provide reference opinions for subsequent processing. Finally, we conduct user consumption behavior analysis on the evolution process of user consumption behavior, aiming to summarize the characteristics and laws of user consumption behavior. Through consumption behavior analysis, we can discover the user's consumption motivation, purchase decision process and interactive behavior, thereby providing data support for subsequent processing.
[0068] Preferably, step S14 comprises the following steps:
[0069] Step S141: Perform consumption element statistical analysis on the user consumption activity standard data set to obtain a user consumption activity consumption element set;
[0070] The embodiment of the present invention extracts relevant fields from the standard data set of user consumption activities, such as consumption time, consumption amount, consumption location, etc., and performs statistical analysis on the extracted data to identify various consumption elements in user consumption activities, such as purchased goods, consumption location, payment method, etc., and finally obtains a consumption element set of user consumption activities.
[0071] Step S142: performing consumption node labeling processing on each consumption element in the consumption element set of the user's consumption activity to obtain the consumption element node of the user's consumption activity;
[0072] The embodiment of the present invention determines the labeling method of each consumption element on the consumption node by designing corresponding node labeling rules, for example, marking different consumption elements as different consumption nodes, and processes each consumption element in the consumption element set of the user consumption activity by using the designed node labeling rules to convert the consumption elements into specific consumption nodes, and finally obtain the consumption element node of the user consumption activity.
[0073] Step S143: Based on the user consumption behavior data, the consumption behavior relationship between the consumption element nodes of each user consumption activity is mined and analyzed to obtain the consumption behavior relationship between different consumption activity entity nodes;
[0074] The embodiment of the present invention mines and analyzes the consumption behavior relationship between consumption element nodes of each user's consumption activity by using a suitable association relationship mining algorithm (such as association rule mining (Apriori algorithm), sequence pattern mining, etc.) to discover the consumption behavior relationship between different consumption element nodes, such as purchase association, behavior sequence, etc., and finally obtain the consumption behavior relationship between different consumption activity entity nodes.
[0075] Step S144: constructing a consumption relationship map of the consumption element nodes of the user's consumption activities according to the consumption behavior relationship between different consumption activity entity nodes, so as to obtain a consumption behavior relationship map of the user's consumption activities;
[0076] The embodiment of the present invention connects the corresponding consumption element nodes of each user consumption activity according to the consumption behavior relationship between different consumption activity entity nodes obtained through analysis to form a complete consumption relationship map, and finally obtains a user consumption activity consumption behavior relationship map.
[0077] Step S145: Based on the user consumption activity consumption behavior relationship map, the user consumption preference mining and analysis is performed on the user consumption activity standard data set to obtain the user consumption preference data.
[0078] The embodiment of the present invention uses a suitable preference mining algorithm (such as a graph-based recommendation algorithm) to conduct consumption preference mining and analysis on the user consumption situation in the user consumption activity standard data set by combining the user consumption activity consumption behavior relationship graph obtained by analysis, so as to analyze the relationship between different consumption behaviors to identify the user's preference degree and changing trend for different consumption elements, and finally obtain the user's consumption preference data.
[0079] The present invention firstly performs consumption element statistical analysis on the standard data set of user consumption activities. The purpose of this step is to form a consumption element set of user consumption activities by statistically analyzing each element of consumption activities, so as to identify and summarize all elements that affect consumption behavior, including but not limited to product types, prices, purchase time, purchase locations, etc., and provide basic data for subsequent consumption behavior analysis. Secondly, by performing consumption node labeling processing on each consumption element in the consumption element set of user consumption activities, the purpose is to convert the consumption elements into specific consumption nodes, which is convenient for subsequent relationship mining and analysis. The key of this step is to assign an identifier to each consumption element, so as to facilitate further consumption behavior relationship mining and analysis. Then, by performing consumption behavior relationship mining and analysis between consumption element nodes of each user consumption activity based on user consumption behavior data, it is intended to discover the association and influence between different consumption activity entity nodes. The key of this step is to analyze the user's consumption behavior, such as purchase, browsing, evaluation, etc., and then to mine the association between different consumption nodes, so as to lay the foundation for building a consumption relationship map. Next, the consumption relationship map of the consumption element nodes of the user's consumption activities is constructed according to the consumption behavior relationship between different consumption activity entity nodes to form a user consumption activity consumption behavior relationship map. The key to this step is to be able to visualize the relationship between consumption nodes as a map, so as to more intuitively understand the connection and influence between consumption behaviors. Finally, the user consumption preference mining and analysis of the user consumption activity standard data set based on the user consumption activity consumption behavior relationship map aims to discover the user's consumption preferences and trends. The key to this step is to identify the user's preference for different consumption elements and the change trend by analyzing the relationship between consumption behaviors, so as to provide customized product preference recommendations for subsequent processing.
[0080] Preferably, step S15 comprises the following steps:
[0081] Step S151: Performing user consumption sentiment analysis on the user consumption activity standard data set to obtain user consumption activity consumption sentiment tendency data;
[0082] The embodiment of the present invention uses sentiment dictionary technology to perform sentiment analysis on text information data in a standard data set of user consumption activities, so as to identify emotional factors such as user preferences, dislikes, and satisfaction, and understand the user's attitudes and emotional tendencies towards different products or services, and finally obtain user consumption activity consumption emotional tendency data.
[0083] Step S152: Perform behavior sequence frequent pattern mining analysis on the user consumption behavior data to obtain user consumption behavior sequence frequent pattern data;
[0084] The embodiment of the present invention mines and analyzes the user consumption behavior data obtained by analysis by using a sequence mining algorithm (such as Apriori, FP-Growth, etc.) to find out frequently occurring behavior sequence patterns, and reveal the user's consumption behavior rules and habits, and finally obtain the user's consumption behavior sequence frequent pattern data.
[0085] Step S153: Based on the frequent pattern data of the user's consumption behavior sequence, the consumption emotion tendency data of the user's consumption activity is evaluated and analyzed for potential influence of the behavior, so as to obtain the potential consumption influence factor of the user's frequent consumption behavior;
[0086] The embodiment of the present invention uses an impact assessment algorithm to conduct potential impact assessment and analysis on the corresponding user consumption activity consumption emotion tendency data by combining the frequent pattern data of user consumption behavior sequences obtained through analysis, so as to evaluate the degree of influence of different consumption behaviors on user consumption emotion tendencies, establish a mapping relationship between influence factors and emotion tendencies, and explore the potential influence factors of user consumption behaviors on their consumption emotions, and finally obtain the potential consumption influence factors of users' frequent consumption behaviors.
[0087] Step S154: Based on the user consumption preference data, the user consumption activity consumption sentiment tendency data is evaluated and analyzed for potential influence of preference, so as to obtain the potential consumption influence factor of the user consumption preference;
[0088] The embodiment of the present invention uses an impact assessment algorithm to perform an impact assessment analysis on the corresponding user consumption activity consumption emotion tendency data by combining the user consumption preference data obtained through analysis, so as to analyze the preference factors in the user consumption activity consumption emotion tendency data, and evaluate and analyze the degree of influence of these preference factors on the consumption emotion tendency, and at the same time analyze the influence factors of the user's consumption preference on his consumption emotion, and finally obtain the potential consumption influence factors of the user's consumption preference.
[0089] Step S155: Based on the potential consumption influencing factors of the user's frequent consumption behavior and the potential consumption influencing factors of the user's consumption preference, a consumption demand forecasting analysis is performed on the user's consumption activity standard data set to obtain the user's potential consumption demand data.
[0090] The embodiment of the present invention uses a consumption demand prediction analysis method to perform predictive analysis on a standard data set of user consumption activities by combining the potential consumption influencing factors of user frequent consumption behaviors and the potential consumption influencing factors of user consumption preferences obtained by analysis, so as to comprehensively consider the impact of consumption behaviors and consumption preferences on user needs, so as to more accurately predict the user's future consumption needs, and finally obtain the user's potential consumption demand data.
[0091] The present invention first analyzes the user consumption emotion analysis of the user consumption activity standard data set, aiming to understand the user's attitude and emotional tendency towards different products or services by analyzing the emotions generated by the user in the consumption activity, and then provide a basis for formulating personalized marketing strategies. For example, identify the user's emotional factors such as likes, dislikes, satisfaction, etc., so as to better meet their needs and improve user experience and loyalty. Secondly, by mining and analyzing the frequent patterns of the user's consumption behavior data, the purpose is to find the patterns that frequently appear in the user's behavior sequence during the consumption process. This step can reveal the user's purchasing habits, behavioral laws and other information by mining frequent patterns, and provide data support for subsequent behavioral impact assessment and demand forecasting. For example, it is found that when users buy a certain commodity, they often buy other related commodities, or have fixed purchase time and place. Then, by analyzing the user's consumption behavior sequence frequent pattern data, the user's consumption activity consumption emotion tendency data is evaluated and analyzed for the potential impact of behavior, aiming to explore the potential impact factors of the user's consumption behavior on his consumption emotion. This step can understand the degree of influence of different behavior patterns on user emotions by analyzing the relationship between consumption behavior and consumption emotion, thereby providing a basis for more accurate understanding of user needs and behaviors. Next, based on the user consumption preference data, the potential impact assessment analysis of the user consumption activity consumption sentiment tendency data is carried out. The purpose is to analyze the factors that affect the user's consumption preference on his consumption sentiment. This step can better understand the user's emotional tendency towards different products or services by deeply understanding the user's preferences, and provide a basis for personalized recommendations and customized marketing. Finally, based on the potential consumption influencing factors of the user's frequent consumption behavior and the potential consumption influencing factors of the user's consumption preference, the consumption demand forecast analysis is carried out on the user's consumption activity standard data set. This step can more accurately predict the user's future consumption demand by comprehensively considering the impact of consumption behavior and consumption preference on user demand, and provide a reference for the subsequent SMS sending customization process.
[0092] Preferably, step S2 comprises the following steps:
[0093] Step S21: Performing user entity recognition analysis on the user consumption activity big data set to obtain a user-related information entity set;
[0094] The embodiment of the present invention uses natural language processing technology or entity recognition algorithm to identify and analyze a large data set of user consumption activities to extract information entities related to the user, including but not limited to the user's name, age, gender, geographic location, etc., and finally obtain a user-related information entity set.
[0095] Step S22: Performing user attribute relationship mining and analysis on the user consumption activity big data set to obtain user consumption attribute relationships;
[0096] The embodiments of the present invention mine and analyze the consumption attribute information of each user in the big data set of user consumption activities by using data mining or association rule mining techniques, so as to analyze the association and rules between the user consumption attributes, such as the interaction between users, purchase preferences, consumption frequency, etc., and gain an in-depth understanding of the behavioral characteristics and consumption patterns of the user groups, and finally obtain the user consumption attribute relationship.
[0097] Step S23: constructing a user portrait for the user consumption activity big data set based on the user-related information entity set and the user consumption attribute relationship to obtain a consumption user portrait model;
[0098] The embodiment of the present invention uses data analysis and modeling technology to construct a user portrait model by combining the user-related information entity set and the user consumption attribute relationship obtained by analysis, so as to map the user's entity information and attribute relationship into specific features and attributes to form a comprehensive description of the user, namely, the user portrait model, and finally obtain a consumer user portrait model.
[0099] Step S24: Obtaining marketing activity demand data;
[0100] The embodiment of the present invention obtains marketing activity demand from the marketing department or related marketing channels, including but not limited to market research results, marketing goals, product positioning, marketing activity themes, target groups, promotional content, etc., and finally obtains marketing activity demand data.
[0101] Step S25: Based on the user's potential consumption demand data and marketing activity demand data, the consumer user portrait model is analyzed for SMS content customization to obtain personalized SMS content for the consumer user.
[0102] The embodiment of the present invention customizes the SMS content for the corresponding consumer users in the consumer user portrait model by combining the user's potential consumption demand data and marketing activity demand data obtained through analysis, so as to analyze the consumption preferences and marketing activity needs of different consumer user groups, and design personalized SMS content, including content themes, promotional information, preferential activities, etc., to finally obtain personalized SMS content for consumer users.
[0103] The present invention firstly performs user entity recognition analysis on a large data set of user consumption activities, and can accurately identify entity information related to users from massive data, including but not limited to the user's name, age, gender, geographic location, etc. The key to this step is to use advanced natural language processing and data mining technology to extract structured user information entity sets from unstructured data, laying the foundation for the subsequent construction of user portraits. Secondly, by performing user attribute relationship mining analysis on a large data set of user consumption activities, it aims to discover attribute relationships between users, such as interactions, purchase preferences, consumption frequency, etc. between users. This step can deeply understand the behavioral characteristics and consumption patterns of user groups by mining user attribute relationships, provide data support for building user portraits, and help to better understand the target user group. Then, by constructing a user portrait for a large data set of user consumption activities based on user-related information entity sets and user consumption attribute relationships, this step is to combine the user's entity information and attribute relationships, and form a comprehensive description of the user, i.e., user portraits, through data analysis and modeling technology. User portraits are an abstract presentation of user characteristics, behaviors, and preferences, which helps to better understand user needs and behavior patterns, thereby achieving precision marketing and personalized recommendations. Next, by obtaining marketing activity demand data, which includes but is not limited to market research results, marketing goals, product positioning, etc., by collecting and organizing marketing activity demand data, we can clearly understand the company's marketing goals and strategies, provide guidance and basis for subsequent SMS content customization, and ensure that the customized content is consistent with marketing activity needs. Finally, by conducting SMS content customization analysis on the consumer user portrait model based on user potential consumption demand data and marketing activity demand data, this step can personalize SMS content by combining user consumption needs and marketing activity goals to make it more in line with user interests and preferences, improve marketing effectiveness and user participation, and this personalized SMS content can enhance user identity and interactivity, and promote the establishment and maintenance of a good relationship between users and companies.
[0104] Preferably, step S25 comprises the following steps:
[0105] Step S251: performing user group segmentation processing on the consumer user portrait model to obtain different consumer user segmentation groups;
[0106] The embodiment of the present invention uses a clustering algorithm or a classification algorithm to segment the user group by using the constructed consumer user portrait model, so as to divide the large user group into several segmented groups, each group having similar consumption characteristics and behavior patterns, and help to more accurately understand the needs and preferences of different user groups, and finally obtain different consumer user segmented groups.
[0107] Step S252: performing consumption preference demand identification and analysis on different consumer user segments based on the user potential consumption demand data to obtain consumption preference demand data of different consumer user segments;
[0108] The embodiment of the present invention uses data mining algorithms or machine learning techniques to analyze different consumer user segments by combining the user potential consumption demand data obtained through analysis, so as to analyze the consumption preference demands of different consumer user segments, and identify the main consumption preferences and demand characteristics of each group, and finally obtain the consumption preference demand data of different consumer user groups.
[0109] Step S253: performing demand matching analysis on different consumer user segments based on the marketing activity demand data to obtain marketing activity related demand data of different consumer user segments;
[0110] The embodiments of the present invention match and analyze the marketing activity demand data with the consumption preference demands of different consumer user segments to determine the types and contents of marketing activities suitable for different groups, and accurately determine the direction and strategy of marketing activities for each group by analyzing the purchasing habits, interests and behavioral characteristics of different groups, and finally obtain the marketing activity-related demand data of different consumer user groups.
[0111] Step S254: Perform SMS content customization analysis on the consumer user portrait model based on the consumption preference demand data of different consumer user groups and the demand data related to marketing activities to obtain personalized SMS content for consumer users.
[0112] The embodiment of the present invention customizes SMS content for corresponding consumer users in the consumer user portrait model by combining the consumption preference demand data of different consumer user groups and the demand data related to marketing activities obtained by analysis, so as to analyze the consumption preferences and marketing activity needs of different consumer user groups to design personalized SMS content, including content themes, promotional information, preferential activities, etc., and finally obtain personalized SMS content for consumer users.
[0113] The present invention firstly performs user group segmentation processing on the consumer user portrait model, and can divide a large user group into several segmented groups, each group having similar consumption characteristics and behavior patterns. This segmentation can help to more accurately understand the needs and preferences of different user groups, so as to carry out marketing activities and personalized customization services in a targeted manner, and improve marketing effects and user satisfaction. Secondly, by performing consumption preference demand identification analysis on different consumer user segmented groups based on user potential consumption demand data, the consumption preferences and demand characteristics of each group can be deeply excavated. This step can find its potential consumption preferences and demand trends by analyzing the consumption behavior of users under different time, scenes and product categories, and provide important reference basis for subsequent personalized SMS content customization. Then, by performing demand matching analysis on different consumer user segmented groups based on marketing activity demand data, it is intended to match marketing activities with user needs, ensure that marketing strategies are consistent with the characteristics of target user groups, and accurately determine the direction and strategy of marketing activities for each group by analyzing the purchasing habits, interests and behavior characteristics of different groups, and improve marketing effects and user participation. Finally, SMS content customization analysis is performed on the consumer user portrait model based on the consumption preference demand data of different consumer user groups and the marketing activity-related demand data to personalize the SMS content. This step combines the user's consumption preferences and marketing activity needs to tailor the SMS content to make it more in line with the user's needs and interests, improve the SMS reading rate and conversion rate, and thus achieve better marketing results.
[0114] Preferably, step S3 comprises the following steps:
[0115] Step S31: Analyze the user's consumption behavior data and the user's consumption preference data at the user's consumption active stage to obtain the user's consumption active stage status data;
[0116] The embodiment of the present invention uses data analysis tools or algorithms to identify and analyze the active consumption stages of the user's consumption behavior data and user consumption preference data obtained by analysis, so as to analyze the user's consumption frequency, purchase preference and behavior pattern, etc. to determine the user's active consumption stage status, that is, the user's consumption activity time period includes several stages, and finally obtain the user's active consumption stage status data.
[0117] Step S32: monitoring and analyzing the active time period of the user's consumption active stage status data to obtain the length of the user's consumption active time period; evaluating and analyzing the timing of sending SMS messages for the consumer user's personalized customized SMS content according to the length of the user's consumption active time period to obtain the consumer user's SMS sending timing;
[0118] The embodiment of the present invention monitors and analyzes the time period by combining the user consumption active stage status data obtained by analysis to identify the user's active time period, that is, the time period when the user consumes actively in a day, thereby obtaining the length of the user's active consumption time period. Then, by combining the length of the user's active consumption time period obtained by analysis, the corresponding consumer user's personalized customized text message content is evaluated and analyzed for sending timing, so as to evaluate in which time periods sending text messages to users can achieve better results, and ensure that text messages are sent during time periods with high user consumption activity, and finally obtain the consumer user's text message sending timing.
[0119] Step S33: Based on the length of the user's active consumption period, an activity evaluation and analysis is performed on the user's active consumption stage status data to obtain the user's consumption activity;
[0120] The embodiment of the present invention uses an activity evaluation algorithm to evaluate and analyze the corresponding user consumption active stage status data by combining the analyzed user consumption active time period to evaluate the user's consumption activity, understand the user's participation level and frequency in consumption activities, and finally obtain the user's consumption activity.
[0121] Step S34: Based on the user consumption activity, a user SMS receiving willingness degree calculation formula is used to perform a willingness statistical calculation on the consumer user's personalized customized SMS content to obtain the user's consumption activity SMS receiving willingness degree;
[0122] The embodiment of the present invention forms a suitable calculation formula for the user's willingness to receive text messages by combining the quantity parameter of the consumer user's personalized customized text message content, the reception influence weight parameter, the user's reception frequency, the time range parameter, the time variable parameter, the user's consumption active time influence factor, the user's consumption activity and related parameters, and performs a statistical calculation of the willingness of the consumer user's personalized customized text message content to quantitatively analyze the user's willingness to receive text messages, and finally obtains the user's willingness to receive active consumer text messages.
[0123] Step S35: evaluating and analyzing the SMS sending frequency of the consumer user's personalized SMS content according to the consumer user's willingness to receive SMS, and obtaining the consumer user's SMS sending frequency;
[0124] The embodiment of the present invention uses the user's active consumption SMS receiving willingness obtained by quantitative calculation to evaluate and analyze the sending frequency of the corresponding consumer user's personalized customized SMS content, so as to evaluate and analyze the SMS sending frequency of different user groups, that is, to determine the frequency of sending SMS to users, and ensure that the SMS sending frequency is in line with the user's acceptance ability and willingness, and finally obtain the consumer user's SMS sending frequency.
[0125] Step S36: based on the consumer user's SMS sending timing and the consumer user's SMS sending frequency, the consumer user's personalized SMS content is sent on a scheduled basis to obtain the consumer user's SMS content that is sent on a scheduled basis.
[0126] The embodiment of the present invention formulates a corresponding scheduled sending strategy by combining the analyzed timing and frequency of SMS sending of consumer users to determine the time and frequency of sending SMS to users, and performs scheduled sending processing of personalized SMS content for consumer users according to the scheduled sending strategy, while ensuring that the SMS content can be effectively conveyed during the user's active time period, and finally obtains the scheduled SMS content of the consumer user.
[0127] The present invention first analyzes the user's consumption active stage by analyzing the user's consumption behavior data and the user's consumption preference data. This step aims to understand the user's consumption activity in different time periods, so as to determine the user's consumption active stage status. By analyzing the user's consumption frequency, purchase preference and behavior pattern, etc., the user's consumption status at different stages can be obtained, which provides a basis for subsequent personalized marketing and SMS sending opportunities. Secondly, by monitoring and analyzing the active time period of the user's consumption active stage status data to determine the user's consumption active time period, the user's consumption activity level and the length of the active time period can be found, and the SMS sending opportunity evaluation and analysis can be performed on the personalized SMS content of the consumer user according to the length of the user's consumption active time period to evaluate the user's SMS receiving opportunity, and ensure that the SMS is sent in the time period with high user consumption activity, so as to improve its reading rate and response rate. At the same time, by evaluating and analyzing the user's consumption active stage status data based on the length of the user's consumption active time period, the user's consumption activity can be determined. This step can understand the user's participation in consumption activities and frequency by evaluating the user's consumption activity, which provides a basis for the subsequent SMS sending frequency and content customization, so as to achieve personalized marketing and improve user satisfaction. Then, based on the user's consumption activity, the user's willingness to receive SMS is calculated by using the user's SMS receiving willingness calculation formula to perform a statistical calculation of the willingness of the consumer user's personalized SMS content. This step aims to quantify the user's willingness to receive SMS based on the user's consumption activity and SMS receiving willingness, so as to more accurately determine the recipients and content design of the SMS content, and improve the effect of SMS marketing and user experience. Next, the SMS sending frequency of the consumer user's personalized SMS content is evaluated and analyzed based on the user's willingness to receive SMS, so as to evaluate and analyze the user's willingness to receive SMS, determine the frequency of SMS sending, avoid causing interference or disgust to the user, and maintain the user's acceptance and active participation in SMS marketing. Finally, the personalized SMS content of the consumer user is sent at a scheduled time based on the consumer user's SMS sending time and the consumer user's SMS sending frequency. This step is to send personalized SMS content within an appropriate time period and frequency based on the previous analysis results to improve the user's reading and response rate, thereby achieving a more accurate SMS content sending goal.
[0128] Preferably, the calculation formula of the user's SMS receiving willingness in step S34 is specifically:
[0129] ;
[0130] In the formula, The user's willingness to receive active SMS messages. The number of SMS messages personalized for consumer users, It is the item index parameter of the number of SMS contents. For the The weight parameter of the influence of receiving personalized SMS content for each consumer user, For the The frequency of receiving SMS content customized by each consumer user, is the time range parameter, is the time variable parameter, For in time The influencing factor of user consumption active time at For in time The consumption activity of users at It is the correction coefficient of the user's willingness to receive active SMS.
[0131] The present invention obtains a calculation formula for the user's willingness to receive text messages by using a specific mathematical model and after verification, which is used to perform statistical calculations on the willingness of consumer users to customize text message content. The calculation formula for the user's willingness to receive text messages uses corresponding influence weights to consider that different personalized customized text message contents have different influences on the user's willingness to receive text messages. This weight parameter can reflect the importance of different contents, thereby affecting the user's willingness to receive text messages. The formula also uses The parameter reflects the frequency of users receiving each personalized SMS content, that is, the user's interest in each content. A high frequency of reception means that the user is more interested, thus increasing the willingness to receive. Secondly, the formula also uses the user consumption active time influence factor Taking into account that users have different consumption activities in different time periods, this reflects the impact of time on users receiving text messages. At the same time, the formula also takes into account the user's consumption activity It reflects the overall consumption activity of users, and users with high activity may be more likely to receive and respond to text messages, thus increasing their willingness to receive them. In addition, the formula also introduces a correction coefficient, which can be used to adjust the calculation results to adapt to different situations or improve the accuracy of the calculation. By comprehensively considering these factors, the user's willingness to receive text messages can better evaluate the consumer user's willingness to receive personalized text message content, thereby providing important data support for determining the timing and frequency of text message sending. In summary, this formula fully takes into account the user's willingness to receive text messages due to consumption activity. , the number of personalized SMS messages that consumers have customized , item index parameter of the number of SMS contents , No. The weight parameter of receiving personalized SMS content for each consumer user , No. Frequency of receiving SMS content customized by consumer users , time range parameter , time variable parameter , at time The influencing factor of user consumption active time at , at time User consumption activity at , the correction coefficient of the user's willingness to receive active SMS , based on the user's willingness to receive SMS The correlation between the above parameters constitutes a functional relationship This formula can realize the statistical calculation process of the willingness of consumer users to customize the content of SMS, and at the same time, the correction coefficient of the willingness of users to receive active SMS consumption is used The introduction of can be adjusted according to the errors that occur in the calculation process, thereby improving the accuracy and applicability of the calculation formula for the user's willingness to receive text messages.
[0132] Preferably, step S4 comprises the following steps:
[0133] Step S41: monitoring and analyzing the SMS feedback of the consumer user's scheduled SMS content to obtain the consumer user's SMS feedback information data;
[0134] The embodiment of the present invention monitors and analyzes the feedback process after the consumer user's scheduled text message content is sent to the user, so as to monitor the user's feedback information on the sent text messages, including reply, forwarding, deletion and other behaviors, and analyze the monitored data by using data analysis tools or algorithms to extract the user's feedback information, such as reception status, click status, etc., and finally obtain the consumer user's text message sending feedback information data.
[0135] Step S42: Performing a statistical analysis of user reception and clicks on the consumer user's SMS feedback information data to obtain the user reception volume and user click volume of each consumer user's SMS message;
[0136] The embodiment of the present invention organizes and compiles statistics on the consumer user text message sending feedback information data obtained through user feedback analysis by using a statistical analysis method, so as to statistically calculate the reception volume and click volume of each text message content based on the user's reception and click situation of the text messages, and finally obtain the user reception volume and user click volume of each text message sent by the consumer user.
[0137] Step S43: performing classification evaluation and analysis on the reading rate of the SMS content sent regularly by the consumer user according to the number of users receiving each SMS and the number of users clicking each SMS, so as to obtain the user reading rate of each SMS content;
[0138] The embodiment of the present invention classifies and statistically processes the scheduled SMS contents of consumer users corresponding to the user reception volume and user click volume of each SMS sent by consumer users obtained by combined analysis, so as to obtain the total user reception volume and the total user click volume of each type of scheduled SMS contents, and uses the reading rate evaluation method to evaluate and analyze the SMS contents of each category by combining the total user reception volume and the total user click volume of each type of scheduled SMS contents obtained by statistical analysis, so as to evaluate and calculate the user reading frequency of each type of SMS contents, understand the user's attention degree and attractiveness to each type of SMS contents, and finally obtain the user reading rate of each type of SMS contents.
[0139] Step S44: performing user emotional feedback recognition analysis on the consumer user's SMS feedback information data to obtain the consumer user's SMS content emotional feedback status data; performing response rate classification evaluation analysis on the consumer user's SMS content based on the consumer user's SMS content emotional feedback status data to obtain the user emotional response rate of each type of SMS content;
[0140] The embodiment of the present invention uses natural language processing technology or sentiment analysis algorithm to perform sentiment recognition analysis on the consumer user's SMS feedback information data to identify positive, negative or neutral sentiments, and understand the user's sentiment preferences and attitude tendencies, thereby obtaining the consumer user's SMS content sentiment feedback status data. Then, by combining the analyzed consumer user SMS content sentiment feedback status data, the sentiment response efficiency of each category of SMS content corresponding to the classification is evaluated and analyzed to evaluate and calculate the user's sentiment response to different types of SMS, and finally obtain the user sentiment response rate of each type of SMS content.
[0141] Step S45: Based on the user reading rate and user emotional response rate of each type of SMS content, intelligent management processing is performed on the sending mode of the scheduled SMS content of the consumer user to obtain the intelligent management result of the SMS sending of the consumer user.
[0142] The embodiment of the present invention uses an intelligent algorithm or decision model to manage and adjust the sending method of the corresponding consumer user's scheduled text message content by combining the user reading rate and user emotional response rate of each type of text message content obtained by analysis, so as to adjust the text message sending method (including batch sending, targeted sending, etc.) and timing according to the user's reading preference and emotional feedback, and finally obtain the intelligent management result of consumer user text message sending.
[0143] The present invention first monitors and analyzes the content of the consumer user's SMS sent regularly, and aims to obtain the consumer user's SMS sending feedback information data by monitoring the user's feedback information on the SMS, including reply, forwarding, deletion and other behaviors. These data will help to understand the user's reaction and preference to different types of SMS, and provide an important basis for subsequent SMS content optimization and personalized customization. Secondly, by performing user reception and click statistics analysis on the consumer user's SMS sending feedback information data, the user reception volume and click volume of each SMS can be obtained. This step can evaluate the SMS delivery effect and the user's interest level by statistically analyzing the user's reception and click situation of the SMS, thereby providing data support for subsequent SMS content optimization and sending strategy adjustment. Then, by performing a reading rate classification evaluation and analysis on the consumer user's SMS sent regularly according to the user reception volume and user click volume of each consumer user's SMS, the user reading rate of different types of SMS can be evaluated, and the user's attention and attractiveness to the SMS content can be understood, and guidance and strategic suggestions can be provided for further improving the SMS marketing effect. Next, the emotional feedback recognition and analysis of consumer users’ SMS feedback information data is performed to obtain the emotional feedback status data of consumer users’ SMS content. This step can identify the emotional feedback of users on SMS content, including positive, negative or neutral, etc., and can understand the emotional preferences and attitudes of users, providing a reference for the subsequent SMS content adjustment and personalized customization. At the same time, the response rate classification evaluation and analysis of consumer users’ SMS content is also performed based on the emotional feedback status data of consumer users’ SMS content to understand the user emotional response rate of various SMS content. Finally, the intelligent management and processing of the sending method of consumer users’ SMS content based on the user reading rate and user emotional response rate of various SMS content can be used to adjust the SMS sending method and timing according to the user’s reading preference and emotional feedback, improve user satisfaction and participation, and achieve more effective SMS marketing management and precision marketing goals.
[0144] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.
[0145] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.
Claims
1. A method for big data collection and analysis and intelligent SMS sending management, characterized in that: The following steps are involved: Step S1: Obtain a big data set of user consumption activities, and perform consumption behavior and consumption preference mining and analysis on the big data set of user consumption activities to obtain user consumption behavior data and user consumption preference data; perform potential consumption demand analysis on the big data set of user consumption activities based on the user consumption behavior data and user consumption preference data to obtain user potential consumption demand data; Step S2: constructing a user portrait for the user consumption activity big data set to obtain a consumer user portrait model; obtaining marketing activity demand data, and performing SMS content customization analysis on the consumer user portrait model based on the user's potential consumption demand data and the marketing activity demand data to obtain personalized SMS content for the consumer user; Step S3: evaluating and analyzing the timing and frequency of SMS sending of the personalized SMS content of the consumer user according to the consumer behavior data and the consumer preference data, and obtaining the SMS sending timing and SMS sending frequency of the consumer user; Based on the consumer user's SMS sending timing and the consumer user's SMS sending frequency, the consumer user's personalized SMS content is sent on a scheduled basis to obtain the consumer user's SMS content that is sent on a scheduled basis; Step S4: performing SMS feedback evaluation and analysis on the content of SMS sent regularly by consumer users to obtain the user reading rate and user emotional response rate of various SMS contents; Based on the user reading rate and user emotional response rate of various types of SMS content, the sending mode of the consumer user's SMS content is intelligently managed and processed to obtain the intelligent management result of the consumer user's SMS sending; wherein step S4 includes the following steps: Step S41: monitoring and analyzing the SMS feedback of the consumer user's scheduled SMS content to obtain the consumer user's SMS feedback information data; Step S42: Performing a statistical analysis of user reception and clicks on the consumer user's SMS feedback information data to obtain the user reception volume and user click volume of each consumer user's SMS message; Step S43: performing classification evaluation and analysis on the reading rate of the SMS content sent regularly by the consumer user according to the number of users receiving each SMS and the number of users clicking each SMS, so as to obtain the user reading rate of each SMS content; Step S44: performing user emotional feedback recognition analysis on the consumer user's SMS feedback information data to obtain the consumer user's SMS content emotional feedback status data; performing response rate classification evaluation analysis on the consumer user's SMS content based on the consumer user's SMS content emotional feedback status data to obtain the user emotional response rate of each type of SMS content; Step S45: Based on the user reading rate and user emotional response rate of each type of SMS content, intelligent management processing is performed on the sending mode of the scheduled SMS content of the consumer user to obtain the intelligent management result of the SMS sending of the consumer user.
2. The method for big data collection and analysis and intelligent SMS sending management according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Acquire a large data set of user consumption activities; Step S12: Clean and standardize the large data set of user consumption activities to obtain a standard data set of user consumption activities; Step S13: Performing user consumption behavior analysis on the user consumption activity standard data set to obtain user consumption behavior data; Step S14: performing user consumption preference mining and analysis on the user consumption activity standard data set based on the user consumption behavior data to obtain user consumption preference data; Step S15: Based on the user consumption behavior data and the user consumption preference data, the user consumption activity standard data set is analyzed for potential consumption demand to obtain the user's potential consumption demand data.
3. The method for big data collection and analysis and intelligent SMS sending management according to claim 2 is characterized in that: Step S13 includes the following steps: Step S131: extracting and processing user consumption records and consumption interactions from the user consumption activity standard data set to obtain user consumption record data and user consumption interaction data; Step S132: performing time series change analysis on the user consumption record data and the user consumption interaction data to obtain the user consumption record time series change data and the user consumption interaction time series change data; Step S133: Performing behavior pattern mining and analysis on the user consumption record time series change data and the user consumption interaction time series change data to obtain the user consumption record change pattern data and the user consumption interaction change pattern data; Step S134: performing consumption behavior evolution analysis on the user consumption activity standard data set based on the user consumption record change pattern data and the user consumption interaction change pattern data to obtain the user consumption behavior evolution process; Step S135: Analyze the user consumption behavior evolution process to obtain user consumption behavior data.
4. The method for big data collection and analysis and intelligent SMS sending management according to claim 2 is characterized in that: Step S14 includes the following steps: Step S141: Perform consumption element statistical analysis on the user consumption activity standard data set to obtain a user consumption activity consumption element set; Step S142: performing consumption node labeling processing on each consumption element in the consumption element set of the user's consumption activity to obtain the consumption element node of the user's consumption activity; Step S143: Based on the user consumption behavior data, the consumption behavior relationship between the consumption element nodes of each user consumption activity is mined and analyzed to obtain the consumption behavior relationship between different consumption activity entity nodes; Step S144: constructing a consumption relationship map of the consumption element nodes of the user's consumption activities according to the consumption behavior relationship between different consumption activity entity nodes, so as to obtain a consumption behavior relationship map of the user's consumption activities; Step S145: Based on the user consumption activity consumption behavior relationship map, the user consumption preference mining and analysis is performed on the user consumption activity standard data set to obtain the user consumption preference data.
5. The method for big data collection and analysis and intelligent SMS sending management according to claim 2 is characterized in that: Step S15 includes the following steps: Step S151: Performing user consumption sentiment analysis on the user consumption activity standard data set to obtain user consumption activity consumption sentiment tendency data; Step S152: Perform behavior sequence frequent pattern mining analysis on the user consumption behavior data to obtain user consumption behavior sequence frequent pattern data; Step S153: Based on the frequent pattern data of the user's consumption behavior sequence, the consumption emotion tendency data of the user's consumption activity is evaluated and analyzed for potential influence of the behavior, so as to obtain the potential consumption influence factor of the user's frequent consumption behavior; Step S154: Based on the user consumption preference data, the user consumption activity consumption sentiment tendency data is evaluated and analyzed for potential influence of preference, so as to obtain the potential consumption influence factor of the user consumption preference; Step S155: Based on the potential consumption influencing factors of the user's frequent consumption behavior and the potential consumption influencing factors of the user's consumption preference, a consumption demand forecasting analysis is performed on the user's consumption activity standard data set to obtain the user's potential consumption demand data.
6. The method for big data collection and analysis and intelligent SMS sending management according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: Performing user entity recognition analysis on the user consumption activity big data set to obtain a user-related information entity set; Step S22: Performing user attribute relationship mining and analysis on the user consumption activity big data set to obtain user consumption attribute relationships; Step S23: constructing a user portrait for the user consumption activity big data set based on the user-related information entity set and the user consumption attribute relationship to obtain a consumption user portrait model; Step S24: Obtaining marketing activity demand data; Step S25: Based on the user's potential consumption demand data and marketing activity demand data, the consumer user portrait model is analyzed for SMS content customization to obtain personalized SMS content for the consumer user.
7. The method for big data collection and analysis and intelligent SMS sending management according to claim 6 is characterized in that: Step S25 includes the following steps: Step S251: performing user group segmentation processing on the consumer user portrait model to obtain different consumer user segmentation groups; Step S252: performing consumption preference demand identification and analysis on different consumer user segments based on the user potential consumption demand data to obtain consumption preference demand data of different consumer user segments; Step S253: performing demand matching analysis on different consumer user segments based on the marketing activity demand data to obtain marketing activity related demand data of different consumer user segments; Step S254: Perform SMS content customization analysis on the consumer user portrait model based on the consumption preference demand data of different consumer user groups and the demand data related to marketing activities to obtain personalized SMS content for consumer users.
8. The method for big data collection and analysis and intelligent SMS sending management according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Analyze the user's consumption behavior data and the user's consumption preference data at the user's consumption active stage to obtain the user's consumption active stage status data; Step S32: monitoring and analyzing the active time period of the user's consumption active stage status data to obtain the length of the user's consumption active time period; evaluating and analyzing the timing of sending SMS messages for the consumer user's personalized customized SMS content according to the length of the user's consumption active time period to obtain the consumer user's SMS sending timing; Step S33: Based on the length of the user's active consumption period, an activity evaluation and analysis is performed on the user's active consumption stage status data to obtain the user's consumption activity; Step S34: Based on the user consumption activity, a user SMS receiving willingness degree calculation formula is used to perform a willingness statistical calculation on the consumer user's personalized customized SMS content to obtain the user's consumption activity SMS receiving willingness degree; Step S35: evaluating and analyzing the SMS sending frequency of the consumer user's personalized SMS content according to the consumer user's willingness to receive SMS, and obtaining the consumer user's SMS sending frequency; Step S36: based on the consumer user's SMS sending timing and the consumer user's SMS sending frequency, the consumer user's personalized SMS content is sent on a scheduled basis to obtain the consumer user's SMS content that is sent on a scheduled basis.
9. The method for big data collection and analysis and intelligent SMS sending management according to claim 8, characterized in that: The calculation formula of the user's willingness to receive text messages in step S34 is specifically: In the formula, The user's willingness to receive active SMS messages. The number of SMS messages personalized for consumer users, It is the item index parameter of the number of SMS contents. For the The weight parameter of the influence of receiving personalized SMS content for each consumer user, For the The frequency of receiving SMS content customized by each consumer user, is the time range parameter, is the time variable parameter, For in time The influencing factor of user consumption active time at For in time The consumption activity of users at It is the correction coefficient of the user's willingness to receive active SMS.
