Intelligent marketing service platform for financial service and method thereof

Abstract

The invention relates to the technical field of marketing strategies, in particular to an intelligent marketing service platform and method for financial services, and the platform comprises a user behavior analysis module, a customer classification module, a content adjustment module, a marketing strategy optimization module and a market trend prediction module. According to the method, the behaviors and preferences of the users can be accurately predicted by monitoring the behaviors of the users and identifying key interaction events of the users, customer groups can be more finely divided by classifying the customer data, more customized services are provided for different customer groups, the personalized experience of the customers is enhanced, and the user experience is improved. The marketing strategy is adjusted in real time to respond to the change of the market and consumer behaviors, so that the enterprise can keep leading in the market with intense competition, and the perspectiveness of the marketing strategy is enhanced through the dynamic prediction of the market trend, so that the enterprise can predict and adapt to the market change and keep the competitive advantage.

Description

Technical Field

[0001] The present invention relates to the technical field of marketing strategies, and in particular to an intelligent marketing service platform and method for financial services. Background Art

[0002] The Marketing Strategy Technology field covers the use of various tools and methods to enhance the effectiveness and efficiency of marketing activities. This includes data analysis, consumer behavior research, and multi-channel marketing technology, which conducts in-depth analysis of consumer data to predict purchase behavior and provide personalized marketing information. The Marketing Strategy Technology field also pays close attention to the integration of cross-platform marketing to ensure that brand information remains consistent and efficient across various media, thereby maximizing the return on marketing investment.

[0003] Among them, the intelligent marketing service platform for financial services aims to provide automated and highly personalized marketing solutions for the financial services industry. The platform creates customized marketing campaigns by analyzing customer data, including consumption habits, transaction history, and preference settings, thereby increasing customer engagement and cross-selling opportunities. In addition, the platform is able to adjust marketing strategies in real time to respond to changes in market dynamics and customer behavior, thereby optimizing the use of marketing resources and increasing return on investment.

[0004] Traditional service platforms lack in-depth insights into individual user behavior, resulting in insufficient personalization of marketing information. For example, real-time user data is not adequately utilized to adjust marketing strategies, making it impossible for marketing activities to adapt to rapid market changes in a timely manner, thus affecting effectiveness and user engagement. In addition, existing methods fail to effectively distinguish subtle differences between different user groups when processing large-scale data, resulting in insufficient precision in marketing activities, which is a clear disadvantage in the highly competitive financial services market. For example, failure to identify the unique responses of specific customer groups to certain marketing activities will lead to a waste of marketing resources and a decline in return on investment. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent marketing service platform and method for financial services.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: an intelligent marketing service platform for financial services, the platform comprising: The user behavior analysis module conducts time series analysis based on the user's activity records on the financial service platform, identifies key interactive events, and identifies user preferences and active time periods through statistical analysis to obtain user behavior pattern recognition results; The customer classification module analyzes the behavior patterns and preferences of differentiated users based on the user behavior pattern recognition results, combined with the user's social media interaction, purchase history and feedback data, and classifies and divides the users to obtain customer classification information; The content adjustment module adjusts the marketing content based on the customer classification information and the reactions of differentiated users to the same type of content, adjusts the priority and time of push, matches the active time period of the user, and obtains the marketing content adjustment information; The marketing strategy optimization module adjusts the information based on the marketing content, monitors the user's response to the current marketing activities, updates the marketing parameters in real time, adjusts the marketing strategy, optimizes the user's participation and satisfaction, and obtains a real-time optimization strategy; Based on the real-time optimization strategy, the market trend forecasting module analyzes marketing data over a period of time, identifies market trends, predicts market changes, predicts future market demand and potential changes in customer behavior, dynamically adjusts marketing strategies, and generates forecast adjustment information.

[0007] As a further solution of the present invention, the user behavior pattern recognition results include user active time information, key interaction indicators and behavior preference information, the customer classification information includes user social media behavior classification, consumption habit analysis classification and personal preference classification, the marketing content adjustment information includes adjusted content push time, optimized content style and enhanced user interaction method, the real-time optimization strategy includes adjusted marketing parameters, enhanced user participation and optimized push strategy, and the predictive adjustment information includes future market demand trends, predicted consumer behavior changes and market adjustment information.

[0008] As a further solution of the present invention, the user behavior analysis module includes: The interaction identification submodule extracts the user's web browsing history, product click history, and page dwell time information based on the user's activity records on the financial service platform, records the time point and duration of each interaction, and performs frequency statistics on the interaction behavior to obtain interaction event information; The activity evaluation submodule calculates the user's daily activity frequency based on the interactive event information, identifies the peak time of user activity, compares the activity levels of users in different time periods, and obtains active time evaluation information; The behavior pattern analysis submodule performs frequency statistics on interactive behaviors based on the active time evaluation information, analyzes and identifies the regularity and periodicity of user behaviors, and obtains user behavior pattern recognition results.

[0009] As a further solution of the present invention, the customer classification module includes: The social behavior analysis submodule analyzes the user's interaction data on social media based on the user behavior pattern recognition results, records the frequency of likes, comments and shares, associates the data with the user's interests and activities, evaluates the user's influence and activity on social networks, and obtains social activity indicators; The purchase behavior analysis submodule analyzes the types of goods purchased by the user, the purchase frequency, and the seasonal changes in the purchases based on the social activity index and the user's purchase history, identifies the user's consumption preferences and purchasing power, and obtains the purchase behavior analysis results; Based on the purchase behavior analysis results, the classification decision submodule evaluates the user data, classifies the user groups, identifies the market segment group to which each user belongs, and obtains customer classification information.

[0010] As a further solution of the present invention, the content adjustment module includes: The content analysis submodule analyzes the reactions of differentiated user groups to the marketing content based on the customer classification information, including text reading rate and image click counts, evaluates the performance of content types in differentiated user groups, evaluates the content effect, and obtains content effect evaluation information; The content matching submodule selects matching content formats and themes based on the content effect evaluation information and the user's active time and preferences to obtain matching optimized content; The priority adjustment submodule adjusts the push priority and time of the differentiated content based on the matching optimized content, publishes the pushed marketing content during the user's active period, optimizes the user's participation and satisfaction, and obtains marketing content adjustment information.

[0011] As a further solution of the present invention, the marketing strategy optimization module includes: The response monitoring submodule monitors the real-time response of users to the differentiated marketing activities based on the marketing content adjustment information, records the clicks, readings and forwardings of the pushed content by users, analyzes the user's interaction data, and obtains user response monitoring data; The parameter adjustment submodule analyzes the effect of the marketing activities based on the user response monitoring data, and adjusts the marketing parameters according to the user behavior and feedback, including adjusting the issuance frequency and discount strength of coupons, optimizing user participation, and generating adjusted marketing parameters; The real-time update submodule adjusts the content push plan and user interaction strategy based on the adjusted marketing parameters to match changes in the market and user behavior, including changing the marketing information content, adjusting the push strategy and updating the user interaction method, optimizing the efficiency and effectiveness of the marketing activities, and obtaining a real-time optimization strategy.

[0012] As a further solution of the present invention, the calculation formula for adjusting the marketing parameters is: ; Among them, P represents the adjusted marketing parameters, Represents the user click rate, Represents the user's purchase frequency, Represents the coupon usage rate, represents the user feedback score, B represents the basic marketing parameters, including the preliminary set coupon issuance frequency and discount strength, and a, b, c and d are weight coefficients.

[0013] As a further solution of the present invention, the market trend prediction module includes: The trend analysis submodule compares and analyzes historical marketing data with current data based on the real-time optimization strategy, identifies changes in market trends, and obtains market trend insights; The demand forecasting submodule predicts the changing trend of future market demand and potential customer behaviors, including seasonal changes in purchasing power and market acceptance of new products, based on the market trend insight information, to obtain demand change forecast information; The strategy adjustment submodule evaluates the effectiveness of the existing marketing strategy based on the demand change prediction information, dynamically adjusts the marketing strategy to match the predicted market changes, including adjusting the timeline of product promotion and the content of marketing information, and obtains prediction adjustment information.

[0014] As a further solution of the present invention, the calculation formula for identifying changes in market trends is: ; Among them, T represents the market trend score, Represents the consumer purchase frequency in historical data, Represents the number of consumer purchases in the current cycle, Represents the total number of transactions, Represents the average purchase value of the current period, represents the average purchase value in the historical period, R represents the consumer feedback ratio, , , , is the weight coefficient.

[0015] An intelligent marketing service method for financial services, the intelligent marketing service method for financial services is performed based on the above-mentioned intelligent marketing service platform for financial services, and comprises the following steps: S1: Based on the user's activity records on the financial service platform, identify the user's preferences and active time periods, combine the user's social media interaction, purchase history and feedback data, analyze the behavior patterns and preferences of differentiated users, classify and divide the users, and obtain customer classification information; S2: Based on the customer classification information, according to the reactions of differentiated users to similar content, the marketing content is adjusted, including text content, image selection and content layout, and the priority and time of push are adjusted to match the user's active time period, thereby obtaining marketing content adjustment information; S3: Based on the marketing content adjustment information, monitor the user's response to the current marketing activities, update the marketing parameters in real time, adjust the marketing strategy, optimize the user's participation and satisfaction, and obtain the real-time optimization strategy; S4: Based on the real-time optimization strategy, by analyzing the marketing data over a period of time, identifying market trends, predicting market changes, predicting future market demand and potential changes in customer behavior, dynamically adjusting marketing strategies, and generating forecast adjustment information.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by monitoring user behavior and identifying key interactive events of users, user behavior and preferences can be accurately predicted. By classifying customer data, customer groups can be divided more finely, and more customized services can be provided to different customer groups, thereby enhancing the personalized experience of customers and improving customer satisfaction and loyalty. By adjusting marketing strategies in real time and responding to changes in market and consumer behavior, it is ensured that marketing activities always remain in the best state, enabling enterprises to stay ahead in the fiercely competitive market. The dynamic prediction of market trends strengthens the foresight of marketing strategies, enabling enterprises to foresee and adapt to market changes and maintain competitive advantages. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flow chart of the platform of the present invention; Figure 2 It is a schematic diagram of the platform framework of the present invention; Figure 3 This is a flow chart of the user behavior analysis module of the present invention; Figure 4 A flow chart of the customer classification module of the present invention; Figure 5 A flowchart of the content adjustment module of the present invention; Figure 6 It is a flow chart of the marketing strategy optimization module of the present invention; Figure 7 It is a flow chart of the market trend prediction module of the present invention; Figure 8 It is a schematic diagram of the method steps of the present invention. DETAILED DESCRIPTION

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

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

[0020] See also Figure 1 The present invention provides a technical solution: an intelligent marketing service platform for financial services, the platform comprising: The user behavior analysis module conducts time series analysis based on the user's activity records on the financial service platform to identify key interactive events, including page visits, product clicks, and time stays. Through statistical analysis, it identifies user preferences and active time periods to obtain user behavior pattern recognition results; The customer classification module analyzes the behavior patterns and preferences of differentiated users based on the results of user behavior pattern recognition, combined with users' social media interactions, purchase history, and feedback data, and classifies and divides users to obtain customer classification information; The content adjustment module adjusts marketing content based on customer classification information and the reactions of differentiated users to similar content, including text content, image selection, and content layout, and adjusts the priority and time of push notifications to match the user's active time period to obtain marketing content adjustment information. The marketing strategy optimization module adjusts information based on marketing content, monitors user responses to current marketing activities, and updates marketing parameters in real time, including coupon issuance frequency and discount strength, adjusts marketing strategies, optimizes user engagement and satisfaction, and obtains real-time optimization strategies; The market trend forecasting module is based on real-time optimization strategies. It analyzes marketing data over a period of time, identifies market trends, predicts market changes, predicts future market demand and potential changes in customer behavior, dynamically adjusts marketing strategies, and generates forecast adjustment information; The results of user behavior pattern recognition include user active time information, key interaction indicators and behavior preference information. Customer classification information includes user social media behavior classification, consumption habit analysis classification and personal preference classification. Marketing content adjustment information includes adjusted content push time, optimized content style and enhanced user interaction methods. Real-time optimization strategies include adjusted marketing parameters, enhanced user participation and optimized push strategies. Prediction adjustment information includes future market demand trends, predicted consumer behavior changes and market adjustment information.

[0021] See also Figure 2 and Figure 3 ,The user behavior analysis module includes an interaction identification submodule, an ,activity evaluation submodule, and a behavior pattern analysis submodule; Based on the user's activity records on the financial service platform, the user's web browsing records, product click records and page dwell time within a specified time period are collected from the server. The data is acquired in real time through HTTP request logs. These records are sorted by time using SQL database query statements based on preset timestamp parameters to ensure that the time sequence of the data is consistent with the actual order of user behavior. At the same time, the start and end time of each user interaction is recorded, and the duration of each interaction is calculated using the timestamp difference. Through these data, statistical algorithms such as counters and loop structures are executed to summarize the frequency of each type of interaction to ensure that the user's interactive behavior patterns on the platform can be accurately recorded and displayed to obtain interactive event information.

[0022] The interaction identification submodule extracts the user's web browsing history, product click history, and page dwell time information based on the user's activity records on the financial service platform, records the time point and duration of each interaction, and performs frequency statistics on the interaction behavior to obtain interaction event information; The activity evaluation submodule calculates the user's daily activity frequency based on the interactive event information, identifies the peak time of user activity, compares the activity levels of users in different time periods, and obtains active time evaluation information; Based on the interactive event information, evaluate the user's activity, map the timestamp data of the interactive event to the calendar view, aggregate the data of a single day to obtain the user's daily activity frequency, and identify the peak time periods of user activity through time series analysis methods. For example, use mean statistics and standard deviation analysis to find out the time periods during the statistical period when the user's activity level is significantly higher than other time periods, mark the peak time periods, and compare the user's activity levels in different time periods. This method can effectively distinguish the differences in behavioral activity of different users in different time periods. Through data visualization techniques, such as charts and heat maps, the alienated time periods can be intuitively displayed to obtain active time evaluation information.

[0023] The behavior pattern analysis submodule counts the frequency of interactive behaviors based on the active time evaluation information, analyzes and identifies the regularity and periodicity of user behaviors, and obtains the user behavior pattern recognition results; Based on the active time evaluation information, the collected active time data is used to reprocess the data by setting time windows and sliding averages to identify the regularity and periodicity of user behavior. For example, the system may use clustering algorithms such as K-means to group user behaviors according to activity patterns. Each group represents a unique behavioral periodicity. Through comparative analysis, user groups with high frequency of behavioral patterns and obvious periodicity are identified. The analysis reveals the general rules of user behavior and can identify abnormal or atypical behavior patterns, providing a scientific basis for user behavior research and financial product design, and obtaining user behavior pattern recognition results.

[0024] See also Figure 2 and Figure 4 ,The customer classification module includes a social behavior analysis submodule, a purchase behavior analysis submodule, and a classification decision submodule; The social behavior analysis submodule analyzes the user's interaction data on social media based on the results of user behavior pattern recognition, records the frequency of likes, comments and shares, associates the data with the user's interests and activities, evaluates the user's influence and activity on social networks, and obtains social activity indicators; Based on the results of user behavior pattern recognition, data crawling tools are used to automatically obtain users' likes, comments and sharing data from social media APIs. The data contains timestamps, user IDs and interaction types. The data is cleaned and preprocessed, such as removing duplicate records and correcting data formats. Data association analysis techniques, such as association rule learning, are used to match the extracted interaction data with user interest tags. These interest tags are extracted from users' social media activities, such as group joining and topic subscriptions. The frequency of interactions under each type of tag is counted to evaluate the user's interest in different topics. Multivariate analysis methods, such as factor analysis, are used to evaluate the user's overall influence and activity on social networks. The user's interaction frequency, interest diversity and interaction breadth are comprehensively considered to determine the user's social activity index and obtain the social activity index.

[0025] The purchase behavior analysis submodule analyzes the types of goods purchased by users, purchase frequency, and seasonal changes in purchases based on social activity indicators and the user's purchase history, identifies the user's consumption preferences and purchasing power, and obtains the purchase behavior analysis results; Based on social activity indicators, the user's purchase history is integrated. The records are usually exported through the database of the e-commerce platform, including basic information such as product ID, purchase date and purchase quantity. The seasonal patterns of purchasing behavior are identified through time series analysis. For example, sliding window average is used to smooth data fluctuations and analyze the changes in user purchase frequency in different seasons. Classification algorithms, such as decision trees, are used to analyze users' consumption preferences based on product types and purchase frequencies. Preferences are based on past purchase data and users' interaction data on corresponding products on social media, such as likes and comments. Through comprehensive analysis, a full picture of users' consumption preferences and purchasing power can be portrayed, and purchase behavior analysis results can be obtained.

[0026] The classification decision submodule evaluates user data based on the purchase behavior analysis results, classifies user groups, identifies the market segment group to which each user belongs, and obtains customer classification information.

[0027] Based on the results of purchase behavior analysis, data normalization is used to ensure that data of different scales can be effectively compared. Clustering algorithms, such as hierarchical clustering, are applied to group user data. Users are assigned to different market segments based on the similarity and frequency of purchase behavior and their social activity indicators. The accuracy and effectiveness of the grouping are verified, and cross-validation and silhouette coefficients are used to evaluate the internal consistency and inter-group differences of the group. The market segment group of each user is identified, and a high degree of consistency in user behavior and characteristics within each group is ensured to obtain customer classification information.

[0028] See also Figure 2 and Figure 5 ,The content adjustment module includes a content analysis submodule, a content matching submodule, and a priority adjustment submodule; The content analysis submodule analyzes the responses of differentiated user groups to marketing content based on customer classification information, including text reading rate and image click counts, evaluates the performance of content types in differentiated user groups, and evaluates the content effect to obtain content effect evaluation information; Based on customer classification information, different user groups contained in the customer classification information are segmented, such as age, geographic location and consumption capacity. Through integrated data analysis tools, the text reading rate and image click times of specific marketing content for each group of users are counted separately. The statistics are based on the user's historical data and real-time feedback, for example, through Web log analysis and clickstream tracking. During the data processing process, SQL query language is used to filter and sort the data set to ensure the accuracy of the analysis results. Statistical methods, such as variance analysis, are applied to evaluate the differences in behavioral responses of different user groups when receiving the same content, which helps to clarify the performance effect of content types in the target user groups, provide support for marketing strategies, and obtain content effect evaluation information.

[0029] The content matching submodule selects matching content formats and topics based on content effect evaluation information and user active time and preferences to obtain matching optimized content; Based on the content effect evaluation information, content optimization and matching are carried out, and the user's active time data is analyzed. The data is obtained by tracking and recording the user's login time and activity patterns in the application, combined with the user's interest preferences. The preferences are obtained by analyzing the user's past browsing and interaction behaviors. Through machine learning algorithms such as logistic regression, the user's behavior patterns are analyzed, and the content format and theme that best suits the user's preferences are selected to ensure that the selected content meets the user's needs to the greatest extent possible. Through analysis and matching, the matching optimized content suitable for each user group is determined.

[0030] The priority adjustment submodule adjusts the push priority and time of differentiated content based on matching optimized content, publishes push marketing content during user active periods, optimizes user engagement and satisfaction, and obtains marketing content adjustment information.

[0031] Based on matching and optimizing content, the push priority of different content is adjusted according to its characteristics. In the process, the user's behavioral data is analyzed, especially the active data in different time periods. The data is obtained through user active time analysis, and the peak period of user activity is evaluated. The push time of the content is adjusted according to the time period to ensure that the content is pushed at the moment when the user is most likely to participate. The adjustment of the push strategy is completed through simulation testing and historical data comparison to ensure the effectiveness and accuracy of the push strategy. Through strategy adjustment, the module optimizes user participation and satisfaction and obtains marketing content adjustment information.

[0032] See also Figure 2 and Figure 6 ,The marketing strategy optimization module includes a response monitoring submodule, a parameter adjustment submodule, and a real-time update submodule; The response monitoring submodule adjusts information based on marketing content, monitors users’ real-time responses to differentiated marketing activities, records users’ clicks, readings, and forwardings of pushed content, analyzes users’ interaction data, and obtains user response monitoring data; Adjust information based on marketing content, track users' real-time reactions to pushed marketing content, use Web tracking technologies, such as pixel tags and cookies, to record users' clicks, readings and forwarding behaviors, transmit tracking data to the back-end server in real time via HTTP event streams, perform preliminary time stamping and user identity authentication on the data to ensure data integrity and accuracy, apply data mining technologies, such as association rule analysis, to deeply analyze users' interaction patterns and reaction speeds, and analyze to help identify users' preferences and neglect behaviors for specific marketing content. Generate user response monitoring data through the monitoring and analysis process.

[0033] The parameter adjustment submodule analyzes the effect of marketing activities based on user response monitoring data, and adjusts marketing parameters according to user behavior and feedback, including adjusting the frequency of coupon issuance and discount intensity, optimizing user participation, and generating adjusted marketing parameters; The calculation formula for adjusting marketing parameters is: ; Among them, P represents the adjusted marketing parameters, Represents the user click rate, Represents the user's purchase frequency, Represents the coupon usage rate, represents the user feedback score, B represents the basic marketing parameters, including the preliminary set coupon issuance frequency and discount strength, and a, b, c and d are weight coefficients.

[0034] formula: ; Parameter meaning and acquisition method: : User click rate, It is calculated by counting the number of times a user clicks on a marketing campaign divided by the number of impressions over a certain period of time. This is a ratio pulled directly from a marketing data dashboard that reflects the user's interest and level of interaction with a specific marketing content.

[0035] : User purchase frequency, Indicates the number of purchases made by users within a certain period of time after a marketing campaign. This data is usually obtained through sales records on e-commerce platforms, showing the user's purchasing behavior response.

[0036] : Coupon usage rate, It is calculated by calculating the proportion of coupons actually used among the issued coupons, usually obtained directly from the marketing database to evaluate the acceptance of promotional activities.

[0037] : User feedback score, It is usually calculated by averaging the ratings collected from users in post-purchase feedback or through social media and online surveys. This score helps companies understand the overall satisfaction of users with a campaign or product.

[0038] B: Basic marketing parameters, B includes the initial coupon issuance frequency and discount strength. The parameters are set based on historical data and market research, and can be dynamically adjusted according to current market conditions.

[0039] a, b, c, and d are weight coefficients. a adjusts the influence of click-through rate, as a high click-through rate indicates high engagement. b adjusts the combined effect of purchase frequency and coupon usage rate, ensuring that both are properly considered when the coupon policy is adjusted. c ensures that the impact of user satisfaction on the final marketing strategy is reasonably measured and its influence is adjusted based on market feedback. d is used to adjust the role of basic marketing parameters in the new strategy to ensure that the basic settings are updated in sync with market changes.

[0040] Calculation example: set up: (User click rate is 5%), (User purchased 30 times in one month), (40% coupon usage rate), (average user feedback score is 4.5), B=100 (basic marketing parameters, initial coupon issuance frequency), , , , d=0.9 (weight coefficient of each parameter).

[0041] Calculate the adjusted marketing parameter P: ; P=105.8634 represents the adjusted marketing strategy index, which reflects the comprehensive effect of user click rate, purchase frequency, coupon usage rate and user satisfaction under given weights. The results are used to guide how to adjust the coupon issuance frequency and discount intensity to maximize the marketing effect.

[0042] The real-time update submodule adjusts the content push plan and user interaction strategy based on the adjusted marketing parameters to match changes in the market and user behavior, including changing the marketing information content, adjusting the push strategy and updating the user interaction method, optimizing the efficiency and effectiveness of marketing activities, and obtaining real-time optimization strategies.

[0043] Based on the adjusted marketing parameters, re-plan the content push plan and user interaction strategy, analyze the latest changes in market dynamics and user behavior, such as detecting changes in keyword popularity through real-time market trend analysis tools, and adjust the content of marketing information according to the analysis results. For example, update the keywords and visual elements in the promotional information to match the user's latest interests. At the same time, adjust the push strategy, such as changing the push time to align with the user's active peak. In addition, update the user interaction method, such as introducing new interactive functions or optimizing existing interactive processes to improve user experience and interaction quality. Through adjustment, optimize the efficiency and effectiveness of the entire marketing campaign and obtain real-time optimization strategies.

[0044] See also Figure 2 and Figure 7,The market trend forecasting module includes a trend analysis submodule, a demand forecasting submodule, and an adjustment strategy submodule; The trend analysis submodule compares and analyzes historical marketing data with current data based on real-time optimization strategies, identifies changes in market trends, and obtains insights into market trends; The calculation formula for identifying changes in market trends is: ; Among them, T represents the market trend score, Represents the consumer purchase frequency in historical data, Represents the number of consumer purchases in the current cycle, Represents the total number of transactions, Represents the average purchase value of the current period, represents the average purchase value in the historical period, R represents the consumer feedback ratio, , , and is the weight coefficient.

[0045] formula: ; Parameter meaning and acquisition method: Historical purchase frequency, It is calculated by dividing the total number of purchases made by consumers in a certain period in the past (such as the past 12 months) by the total number of days, reflecting historical purchasing activity.

[0046] The number of purchases in the current period, It is calculated by counting the number of purchases made by all consumers in the most recent cycle (usually the most recent month), reflecting the market activity in the current cycle.

[0047] Total number of transactions, Represents the total number of transactions in the market during the same current period, used to measure the overall size of the market.

[0048] Average purchase value of the current period, It is calculated by dividing the total amount of all transactions in the current period by the number of transactions, reflecting the average amount of each transaction.

[0049] Average purchase value over historical periods, Similarly, the total amount of all transactions in the past period is divided by the number of transactions to compare the changes in purchase value.

[0050] R is the consumer feedback ratio, which is calculated by dividing the number of positive feedbacks received in the current cycle by the total number of feedbacks, reflecting consumer satisfaction.

[0051] , , and is the weight coefficient, Influence of historical purchase frequency, The contribution to the overall score of market trends reflects the dependence of market trends on historical data. By comparing the ratio of current purchases to total transactions, we can assess the market activity, which can help us understand the relative changes in consumer activity in the overall market. Calculate the absolute change between current and historical purchase values, taking the square root to balance out extreme value fluctuations. The use of provides a way to measure the influence of consumer feedback, and the logarithmic transformation helps stabilize variability in the analysis and amplify the influence of smaller changes in feedback ratios.

[0052] Calculation example: set up: (Indicates that the average daily historical purchase frequency is 0.8 times), (Number of purchases in the current cycle), (Total number of transactions in the current period), (average purchase value in the current period), (average purchase value over historical periods), (95% positive feedback rate) , , , (various weight coefficients).

[0053] Formula and calculation: ; The calculated result is T=0.912835, which represents the market trend score. A higher value indicates that the market is showing a positive trend relative to historical data, such as an increase in purchase frequency and purchase value, as well as high consumer satisfaction. This score helps decision makers understand the current dynamics of the market and adjust marketing strategies accordingly.

[0054] The demand forecasting submodule predicts future market demand trends and potential customer behaviors based on market trend insights, including seasonal changes in purchasing power and market acceptance of new products, and obtains demand change forecast information; Based on market trend insight information, through predictive models such as regression analysis and random forest algorithms in machine learning, predict the changing trends of future market demand, extract features from market trend data, such as extracting time nodes, sales peaks, and user feedback enthusiasm, etc., through model training and verification, predict seasonal changes in market demand and market acceptance of new products, such as analyzing the potential audience and expected purchasing response of upcoming products, and integrating socioeconomic factors and industry development trends into the predictive model to enhance the accuracy and practicality of the forecast and generate comprehensive demand change forecast information.

[0055] The strategy adjustment submodule evaluates the effectiveness of existing marketing strategies based on demand change forecast information, dynamically adjusts marketing strategies to match predicted market changes, including adjusting the timeline of product promotion and the content of marketing information, and obtaining forecast adjustment information.

[0056] Based on the demand change forecast information, evaluate and adjust the existing marketing strategy to better adapt to the changes in market expectations. Analyze the key variables and potential influencing factors pointed out in the forecast information, such as changes in user purchasing power and expectations for acceptance of new products. Combined with the company's marketing goals and resource allocation, dynamically adjust the timeline of product promotion, such as advancing or postponing the market introduction of specific products, update marketing information content, such as adjusting advertising slogans and promotional materials to more accurately reflect market demand and consumer expectations, use simulation tests and historical data analysis to verify the effectiveness of adjustment strategies, ensure that marketing adjustments are consistent with market dynamics, and form forecast adjustment information.

[0057] See also Figure 8 , an intelligent marketing service method for financial services, based on the above-mentioned intelligent marketing service platform for financial services, comprises the following steps: S1: Based on the user's activity records on the financial service platform, identify the user's preferences and active time periods, combine the user's social media interaction, purchase history and feedback data, analyze the behavior patterns and preferences of differentiated users, classify and divide the users, and obtain customer classification information; S2: Based on customer classification information and the reactions of differentiated users to similar content, the marketing content is adjusted, including text content, image selection, and content layout. The priority and time of push are adjusted to match the user's active time period to obtain marketing content adjustment information. S3: Based on the marketing content adjustment information, monitor the user's response to the current marketing activities, update the marketing parameters in real time, including the coupon issuance frequency and discount strength, adjust the marketing strategy, optimize user participation and satisfaction, and obtain real-time optimization strategies; S4: Based on real-time optimization strategies, by analyzing marketing data over a period of time, identifying market trends, predicting market changes, predicting future market demand and potential changes in customer behavior, dynamically adjusting marketing strategies, and generating forecast adjustment information.

[0058] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent marketing service platform for financial services, characterized in that: The platform includes: The user behavior analysis module conducts time series analysis based on the user's activity records on the financial service platform, identifies key interactive events, and identifies user preferences and active time periods through statistical analysis to obtain user behavior pattern recognition results; The customer classification module analyzes the behavior patterns and preferences of differentiated users based on the user behavior pattern recognition results, combined with the user's social media interaction, purchase history and feedback data, and classifies and divides the users to obtain customer classification information; The content adjustment module adjusts the marketing content based on the customer classification information and the reactions of differentiated users to the same type of content, adjusts the priority and time of push, matches the active time period of the user, and obtains the marketing content adjustment information; The marketing strategy optimization module adjusts the information based on the marketing content, monitors the user's response to the current marketing activities, updates the marketing parameters in real time, adjusts the marketing strategy, optimizes the user's participation and satisfaction, and obtains a real-time optimization strategy; Based on the real-time optimization strategy, the market trend forecasting module analyzes marketing data over a period of time, identifies market trends, predicts market changes, predicts future market demand and potential changes in customer behavior, dynamically adjusts marketing strategies, and generates forecast adjustment information.

2. The intelligent marketing service platform for financial services according to claim 1 is characterized in that the user behavior pattern recognition results include user active time information, key interaction indicators and behavior preference information, the customer classification information includes user social media behavior classification, consumption habit analysis classification and personal preference classification, the marketing content adjustment information includes adjusted content push time, optimized content style and enhanced user interaction method, the real-time optimization strategy includes adjusted marketing parameters, enhanced user participation and optimized push strategy, and the predictive adjustment information includes future market demand trends, predicted consumer behavior changes and market adjustment information.

3. The intelligent marketing service platform for financial services according to claim 1, characterized in that: The user behavior analysis module includes: The interaction identification submodule extracts the user's web browsing history, product click history, and page dwell time information based on the user's activity records on the financial service platform, records the time point and duration of each interaction, and performs frequency statistics on the interaction behavior to obtain interaction event information; The activity evaluation submodule calculates the user's daily activity frequency based on the interactive event information, identifies the peak time of user activity, compares the activity levels of users in different time periods, and obtains active time evaluation information; The behavior pattern analysis submodule performs frequency statistics on interactive behaviors based on the active time evaluation information, analyzes and identifies the regularity and periodicity of user behaviors, and obtains user behavior pattern recognition results.

4. The intelligent marketing service platform for financial services according to claim 1, characterized in that: The customer classification module includes: The social behavior analysis submodule analyzes the user's interaction data on social media based on the user behavior pattern recognition results, records the frequency of likes, comments and shares, associates the data with the user's interests and activities, evaluates the user's influence and activity on social networks, and obtains social activity indicators; The purchase behavior analysis submodule analyzes the types of goods purchased by the user, the purchase frequency, and the seasonal changes in the purchases based on the social activity index and the user's purchase history, identifies the user's consumption preferences and purchasing power, and obtains the purchase behavior analysis results; Based on the purchase behavior analysis results, the classification decision submodule evaluates the user data, classifies the user groups, identifies the market segment group to which each user belongs, and obtains customer classification information.

5. The intelligent marketing service platform for financial services according to claim 1, characterized in that: The content adjustment module includes: The content analysis submodule analyzes the reactions of differentiated user groups to the marketing content based on the customer classification information, including text reading rate and image click counts, evaluates the performance of content types in differentiated user groups, evaluates the content effect, and obtains content effect evaluation information; The content matching submodule selects matching content formats and themes based on the content effect evaluation information and the user's active time and preferences to obtain matching optimized content; The priority adjustment submodule adjusts the push priority and time of the differentiated content based on the matching optimized content, publishes the pushed marketing content during the user's active period, optimizes the user's participation and satisfaction, and obtains marketing content adjustment information.

6. The intelligent marketing service platform for financial services according to claim 1, characterized in that: The marketing strategy optimization module includes: The response monitoring submodule monitors the real-time response of users to the differentiated marketing activities based on the marketing content adjustment information, records the clicks, readings and forwardings of the pushed content by users, analyzes the user's interaction data, and obtains user response monitoring data; The parameter adjustment submodule analyzes the effect of the marketing activities based on the user response monitoring data, and adjusts the marketing parameters according to the user behavior and feedback, including adjusting the issuance frequency and discount strength of coupons, optimizing user participation, and generating adjusted marketing parameters; The real-time update submodule adjusts the content push plan and user interaction strategy based on the adjusted marketing parameters to match changes in the market and user behavior, including changing the marketing information content, adjusting the push strategy and updating the user interaction method, optimizing the efficiency and effectiveness of the marketing activities, and obtaining a real-time optimization strategy.

7. The intelligent marketing service platform for financial services according to claim 6, characterized in that: The calculation formula for adjusting the marketing parameters is: ； Among them, P represents the adjusted marketing parameters, Represents the user click rate, Represents the user's purchase frequency, Represents the coupon usage rate, represents the user feedback score, B represents the basic marketing parameters, including the preliminary set coupon issuance frequency and discount strength, and a, b, c and d are weight coefficients.

8. The intelligent marketing service platform for financial services according to claim 1, characterized in that: The market trend forecasting module includes: The trend analysis submodule compares and analyzes historical marketing data with current data based on the real-time optimization strategy, identifies changes in market trends, and obtains market trend insights; The demand forecasting submodule predicts the changing trend of future market demand and potential customer behaviors, including seasonal changes in purchasing power and market acceptance of new products, based on the market trend insight information, to obtain demand change forecast information; The strategy adjustment submodule evaluates the effectiveness of the existing marketing strategy based on the demand change prediction information, dynamically adjusts the marketing strategy to match the predicted market changes, including adjusting the timeline of product promotion and the content of marketing information, and obtains prediction adjustment information.

9. The intelligent marketing service platform for financial services according to claim 8, characterized in that: The calculation formula for identifying changes in market trends is: ； Among them, T represents the market trend score, Represents the consumer purchase frequency in historical data, Represents the number of consumer purchases in the current cycle, Represents the total number of transactions, Represents the average purchase value of the current period, represents the average purchase value in the historical period, R represents the consumer feedback ratio, , , , is the weight coefficient.

10. An intelligent marketing service method for financial services, characterized in that: The intelligent marketing service platform for financial services according to any one of claims 1 to 9 is implemented, comprising the following steps: Based on the user's activity records on the financial service platform, identify the user's preferences and active time periods, combine the user's social media interaction, purchase history and feedback data, analyze the behavior patterns and preferences of differentiated users, classify and divide users, and obtain customer classification information; Based on the customer classification information, according to the reactions of differentiated types of users to similar content, the marketing content is adjusted, including text content, image selection and content layout, and the priority and time of push are adjusted to match the user's active time period, thereby obtaining marketing content adjustment information; Based on the marketing content adjustment information, monitor the user's response to the current marketing activities, update the marketing parameters in real time, optimize the user's participation and satisfaction, and obtain a real-time optimization strategy; Based on the real-time optimization strategy, by analyzing the marketing data over a period of time, identifying market trends, predicting market changes, predicting future market demand and potential changes in customer behavior, dynamically adjusting marketing strategies, and generating forecast adjustment information.

Images