Card and coupon pushing method, system and device and storage medium

Abstract

The invention discloses a coupon pushing method, system and device and a storage medium, and the method comprises the steps: obtaining real-time behavior data of a target user, the real-time behavior data comprising user basic information, platform interaction data and historical order information; constructing a behavior portrait of each target user according to the user basic information, the platform interaction data and the historical order information; performing sequence pattern analysis, clustering analysis and sentiment analysis according to the user basic information, the platform interaction data and the historical order information, and constructing a user behavior model; calculating a coupon recommendation result of each target user according to the behavior portrait of each target user and the user behavior model; and pushing the coupon recommendation result of each target user to the corresponding target user based on the user behavior model. Through comprehensive analysis of user data, deep understanding of user behaviors is realized, personalized recommendation services are provided on the basis, and effective pushing of cards and coupons is realized.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a card and coupon pushing method, system, device and storage medium. Background Art

[0002] In the e-commerce and retail industries, membership cards and coupons are important tools for merchants to attract new customers, maintain the loyalty of old customers, promote sales and enhance brand awareness.

[0003] However, the traditional card and coupon push system has many defects, including lack of personalization, insufficient real-time performance, insufficient data utilization, imperfect feedback mechanism, low intelligence, single user experience, lack of multi-dimensional analysis and difficult to measure push effect. These problems result in the pushed card and coupon not meeting the current needs of users, affecting the push effect and limiting merchants' in-depth understanding of user behavior and strategy optimization. Summary of the invention

[0004] The main purpose of the present invention is to provide a card and coupon push method, system, device and storage medium, which can achieve an in-depth understanding of user behavior by comprehensively analyzing user data, and provide personalized recommendation services based on this, thereby achieving effective card and coupon push.

[0005] In order to achieve the above objectives, the embodiments of the present application provide the following technical solutions:

[0006] According to a first aspect of an embodiment of the present application, a card coupon pushing method is provided, the method comprising:

[0007] Acquire real-time behavior data of target users, including basic user information, platform interaction data, and historical order information;

[0008] Build a behavior profile of each target user based on the basic user information, platform interaction data, and historical order information;

[0009] Conduct sequence pattern analysis, cluster analysis and sentiment analysis based on the user basic information, platform interaction data and historical order information to build a user behavior model;

[0010] Calculate the card and coupon recommendation result for each target user based on the behavior profile of each target user and the user behavior model;

[0011] Based on the user behavior model, the card coupon recommendation result for each target user is pushed to the corresponding target user.

[0012] Optionally, constructing a behavior profile of each target user according to the basic user information, platform interaction data and historical order information includes:

[0013] Preprocessing the basic user information, platform interaction data and historical order information, wherein the preprocessing includes cleaning, formatting and standardization; the basic user information includes user ID, gender and registration time; the platform interaction data includes login frequency, browsing history, click-through rate and page dwell time; the historical order information includes purchase time, purchased goods, price, payment method and order status;

[0014] Extracting target features from the preprocessed data, wherein the target features include user behavior patterns and behavior trends;

[0015] Determine the user's preference results from the preprocessed data;

[0016] The target features and preference results of the user are classified using a clustering algorithm to determine the user portrait and store it in a database.

[0017] Optionally, performing sequence pattern analysis, cluster analysis and sentiment analysis according to the user basic information, platform interaction data and historical order information to construct a user behavior model includes:

[0018] Performing data cleaning on the user basic information, platform interaction data and historical order information, wherein the data cleaning includes removing noise and filling missing values;

[0019] Extracting user behavior features from the processed data, wherein the user behavior features include access frequency and browsing behavior;

[0020] Determine the user's behavior pattern using statistical analysis or machine learning algorithms based on the user's behavior characteristics;

[0021] Performing sequence pattern analysis based on the behavior pattern and user behavior characteristics to analyze the sequence pattern of user behavior, wherein the sequence pattern includes a purchase process and a browsing path;

[0022] Performing cluster analysis based on the behavior patterns and user behavior characteristics to group users with the same or similar behaviors;

[0023] Using natural language processing technology to perform sentiment analysis based on the behavior patterns and user behavior characteristics, and identify and classify the user's positive and negative sentiment information;

[0024] A user behavior model is constructed based on the results of sequence pattern analysis, cluster analysis and sentiment analysis.

[0025] Optionally, calculating the card and coupon recommendation result for each target user according to the behavior profile of each target user and the user behavior model includes:

[0026] Integrate the behavior profile of each target user with the user behavior model to obtain pre-recommendation data for the target user;

[0027] Analyze the pre-recommendation data of target users based on collaborative filtering algorithm;

[0028] The analysis results are matched with the behavior data of similar users to obtain a set of candidate coupons as the coupon recommendation results for each target user.

[0029] Optionally, the pushing of the card coupon recommendation result of each target user to the corresponding target user based on the user behavior model includes:

[0030] Based on the user behavior model, the user active time is obtained by using time series analysis; the user active time includes the frequency, duration and time distribution of user login;

[0031] Analyze the user's preferences based on the user behavior model to obtain push preferences, where the push preferences include text format and personalized information;

[0032] The card recommendation results are pushed through the selected channel according to the push preference during the user's active time.

[0033] Optionally, after pushing the card and coupon recommendation result of each target user to the corresponding target user based on the user behavior model, the method further includes:

[0034] Monitor and collect user feedback data on the card recommendation results, including card usage, comments, ratings, and user click, ignore and / or unsubscribe behavior information;

[0035] Clean and integrate the collected feedback data to remove invalid or erroneous data;

[0036] Key indicators are calculated based on the processed feedback data, including open rate, click rate and conversion rate.

[0037] Optionally, the method further comprises:

[0038] The system optimizer identifies areas of user dissatisfaction through user feedback, low satisfaction scores, and negative sentiment information;

[0039] Identify user preferences through user feedback, high satisfaction ratings, and positive sentiment information;

[0040] Updating the user's behavior profile according to the user's preferences and dissatisfied areas data;

[0041] The recommendation algorithm parameters and push preferences are adjusted according to the user preferences and dissatisfied domain data.

[0042] According to a second aspect of an embodiment of the present application, a card and voucher pushing system is provided, the system comprising:

[0043] A data acquisition module is used to acquire the real-time behavior data of the target user, wherein the real-time behavior data includes basic user information, platform interaction data and historical order information;

[0044] A behavior profile module is used to construct a behavior profile of each target user based on the user basic information, platform interaction data and historical order information;

[0045] A behavior model module is used to perform sequence pattern analysis, cluster analysis and sentiment analysis based on the user basic information, platform interaction data and historical order information to build a user behavior model;

[0046] A recommendation result module, used to calculate the card and coupon recommendation result for each target user based on the behavior profile of each target user and the user behavior model;

[0047] The push module is used to push the card coupon recommendation result of each target user to the corresponding target user based on the user behavior model.

[0048] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in the first aspect above.

[0049] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer-readable instructions are stored. The computer-readable instructions can be executed by a processor to implement the method described in the first aspect above.

[0050] In summary, the embodiments of the present application provide a card coupon push method, system, device and storage medium, which obtains the real-time behavior data of the target user, including user basic information, platform interaction data and historical order information; constructs a behavior profile of each target user based on the user basic information, platform interaction data and historical order information; performs sequence pattern analysis, cluster analysis and sentiment analysis based on the user basic information, platform interaction data and historical order information to build a user behavior model; calculates the card coupon recommendation result of each target user based on the behavior profile of each target user and the user behavior model; and pushes the card coupon recommendation result of each target user to the corresponding target user based on the user behavior model. By comprehensively analyzing user data, an in-depth understanding of user behavior is achieved, and personalized recommendation services are provided based on this, so as to achieve effective push of card coupons. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0052] The structures, proportions, sizes, etc. illustrated in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with the technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantial technical significance. Any structural modification, change in proportion or adjustment of size shall still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0053] Figure 1 A schematic diagram of a card coupon push method flow provided in an embodiment of the present application;

[0054] Figure 2 A schematic diagram of the system architecture provided for an embodiment of the present application;

[0055] Figure 3 The workflow and data flow chart of the data collector provided in the embodiment of the present application;

[0056] Figure 4 A user portrait builder workflow diagram is provided for an embodiment of the present application;

[0057] Figure 5 A schematic diagram of the algorithm flow of the behavior analysis processor provided in the embodiment of the present application;

[0058] Figure 6 A schematic diagram of the working principle of the recommendation engine provided in the embodiment of the present application;

[0059] Figure 7 A logical diagram of a push manager provided in an embodiment of the present application;

[0060] Figure 8 A schematic diagram of the feedback analyzer workflow provided in an embodiment of the present application;

[0061] Fig. 9 A block diagram of a card and coupon push system provided in an embodiment of the present application;

[0062] Fig.10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown;

[0063] Fig.11A schematic diagram of a computer-readable storage medium provided in an embodiment of the present application is shown.

[0064] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0067] In addition, in the present invention, descriptions such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0068] In the present invention, unless otherwise clearly specified and limited, the terms "connection", "fixation", etc. should be understood in a broad sense. For example, "fixation" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0069] In addition, the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0070] In the e-commerce and retail industries, membership cards and coupons are common means for merchants to attract new customers, maintain old customer loyalty, promote sales, and increase brand awareness. Traditional membership card and coupon push systems are usually based on fixed rules or simple statistical analysis, such as pushing cards and coupons based on user purchase history or seasonal promotions. However, these methods often lack personalization and real-time performance, and cannot fully meet the changing needs of users. The defects and deficiencies of the existing technology include the following:

[0071] 1. Lack of personalization: The cards and coupons pushed by traditional systems are often one-size-fits-all, without considering the personalized needs and preferences of different users, resulting in poor push results.

[0072] 2. Poor real-time performance: Many systems cannot respond to changes in user behavior in real time when pushing coupons and cards, resulting in the coupons and cards being pushed no longer meeting the user's current needs.

[0073] 3. Insufficient data utilization: Existing systems often only utilize limited user data, such as purchase history, but ignore other user behavior data on the platform, such as browsing history, search habits, etc., which can provide more clues about user preferences and needs.

[0074] 4. Imperfect feedback mechanism: After pushing cards and coupons, the existing system often lacks an effective user feedback collection mechanism and is unable to adjust the push strategy based on user usage and satisfaction.

[0075] 5. Low level of system intelligence: Many push systems lack the ability to conduct intelligent analysis and learning, and cannot automatically optimize push strategies as time goes by and user behavior changes.

[0076] 6. Single user experience: Existing systems often use a single push method, such as SMS or email, when pushing cards and coupons, without considering that users may prefer or be more accustomed to receiving information through other channels.

[0077] 7. Lack of multi-dimensional analysis: Existing technologies often only consider a single dimension when analyzing user behavior, such as consumption amount or frequency, while ignoring other important dimensions of user behavior, such as time preference, brand preference, etc.

[0078] 8. The push effect is difficult to measure: The existing system lacks an effective effect measurement mechanism after pushing cards and coupons, making it difficult to accurately evaluate the success of the push activity.

[0079] Based on the problems existing in the prior art, the method provided in the embodiment of the present application forms a closed-loop personalized service process by integrating data collection, user portrait construction, behavior analysis, personalized recommendation and push management, aiming to enhance user experience, increase user stickiness, improve conversion rate and sales revenue, and provide enterprises with in-depth market insights and data-driven decision support.

[0080] Figure 1 The card coupon push method provided in the embodiment of the present application is shown, which specifically includes the following steps:

[0081] Step 101: Acquire real-time behavior data of a target user, wherein the real-time behavior data includes basic user information, platform interaction data, and historical order information;

[0082] Step 102: construct a behavior profile of each target user based on the basic user information, platform interaction data and historical order information;

[0083] Step 103: Perform sequence pattern analysis, cluster analysis and sentiment analysis based on the user basic information, platform interaction data and historical order information to build a user behavior model;

[0084] Step 104: Calculate the card and coupon recommendation result for each target user based on the behavior profile of each target user and the user behavior model;

[0085] Step 105: Push the card and coupon recommendation result for each target user to the corresponding target user based on the user behavior model.

[0086] In a possible implementation, in step 102, constructing a behavior profile of each target user according to the user basic information, platform interaction data, and historical order information includes:

[0087] The user basic information, platform interaction data and historical order information are preprocessed, and the preprocessing includes cleaning, formatting and standardization. The user basic information includes user ID, gender and registration time. The platform interaction data includes login frequency, browsing history, click-through rate and page dwell time. The historical order information includes purchase time, purchased goods, price, payment method and order status. Target features are extracted from the preprocessed data, and the target features include user behavior patterns and behavior trends. The user's preference results are determined from the preprocessed data. The user's target features and preference results are classified using a clustering algorithm to determine a user portrait and store it in a database.

[0088] The database / data warehouse is used to store user data, user portraits, behavior analysis results, recommendation results and feedback data.

[0089] In a possible implementation, in step 103, performing sequence pattern analysis, cluster analysis and sentiment analysis based on the user basic information, platform interaction data and historical order information to construct a user behavior model includes:

[0090] The user basic information, platform interaction data and historical order information are subjected to data cleaning processing, wherein the data cleaning processing includes removing noise and filling missing values; user behavior characteristics are extracted from the processed data, wherein the user behavior characteristics include access frequency and browsing behavior; the user behavior pattern is determined based on the user behavior characteristics by using statistical analysis or machine learning algorithms; a sequence pattern analysis is performed based on the behavior pattern and user behavior characteristics to analyze the sequence pattern of user behavior, wherein the sequence pattern includes purchase process and browsing path; a cluster analysis is performed based on the behavior pattern and user behavior characteristics to group users with the same or similar behaviors; a sentiment tendency analysis is performed based on the behavior pattern and user behavior characteristics using natural language processing technology to identify and classify the user's positive sentiment information and negative sentiment information; a user behavior model is constructed based on the sequence pattern analysis results, cluster analysis results and sentiment analysis results.

[0091] In a possible implementation, in step 104, calculating the card and voucher recommendation result for each target user according to the behavior profile of each target user and the user behavior model includes:

[0092] The behavior profile of each target user and the user behavior model are integrated to obtain pre-recommendation data of the target user; the pre-recommendation data of the target user is analyzed based on a collaborative filtering algorithm; the analysis result is matched with the behavior data of similar users to obtain a candidate card and coupon set as the card and coupon recommendation result for each target user.

[0093] In a possible implementation, in step 105, pushing the card and coupon recommendation result of each target user to the corresponding target user based on the user behavior model includes:

[0094] Based on the user behavior model, time series analysis is used to obtain user active time; the user active time includes the frequency, duration and time distribution of user logins; based on the user behavior model, user preferences are analyzed to obtain push preferences, and the push preferences include text format and personalized information; and the card and coupon recommendation results are pushed during the user active time through the selected channel according to the push preferences.

[0095] In a possible implementation, after pushing the card coupon recommendation result of each target user to the corresponding target user based on the user behavior model, the method further includes:

[0096] Monitor and collect user feedback data on the card recommendation results, including card usage, comments, ratings, and user click, ignore and / or unsubscribe behavior information; clean and integrate the collected feedback data to remove invalid or erroneous data; calculate key indicators based on the processed feedback data, including open rate, click-through rate and conversion rate.

[0097] In a possible implementation, the method further includes: a system optimizer identifying areas of user dissatisfaction through user feedback, low satisfaction scores, and negative sentiment information; identifying user preferences through user feedback, high satisfaction scores, and positive sentiment information; updating the user's behavioral portrait based on the user preferences and dissatisfied area data; and adjusting recommendation algorithm parameters and push preferences based on the user preferences and dissatisfied area data.

[0098] In summary, this application obtains the behavioral data of target users in real time, which includes the user's basic information, interaction records on the platform, and the user's purchase history. Using the collected data, the system creates a behavioral portrait for each target user, which integrates the user's personal characteristics, interaction behaviors, and consumption habits. Further, through in-depth analysis of user basic information, interaction data, and order information, the system conducts sequence pattern analysis, cluster analysis, and sentiment analysis to build a more accurate user behavior model. Combining the user's behavioral portrait and behavioral model, the system can calculate personalized card recommendation results for each user, thereby providing recommendations that are more in line with user needs. Finally, based on the analysis results of the user behavior model, the calculated personalized card recommendation results are intelligently pushed to the corresponding target users to improve user engagement and satisfaction.

[0099] The card coupon pushing method provided in the embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0100] Figure 2 One of the system architectures applicable to the card and voucher push method provided in the embodiment of the present application is shown. The system adopts a modular design, and the modules interact through APIs to ensure the flexibility and scalability of the system. The system backend uses high-performance servers and databases to ensure the efficiency and stability of data processing. The front-end design takes user experience into consideration and provides an intuitive and easy-to-use interface for users to view and manage pushed cards and vouchers.

[0101] Using a microservices architecture, the system is divided into multiple independent services, each responsible for a specific function:

[0102] System architecture={DataCollectionService,UserProfileService,BehaviorAnalysisService,RecommendationService,PushService,FeedbackService,OptimizationService}

[0103] The services communicate with each other through message queues and API gateways to ensure the scalability and maintainability of the system. The user interface and merchant interface represent the entry points for users and merchants to interact with the system, respectively. The data collector is responsible for collecting user behavior data and storing these data in the database. The user profile builder extracts data from the database to build a detailed profile of each user. The behavior analysis processor uses the user profile to perform in-depth analysis and identify the user's behavior patterns. The recommendation engine generates personalized membership card recommendations based on the results of the behavior analysis and the user profile. The push manager is responsible for pushing the cards generated by the recommendation engine to users. Users receive pushes and provide feedback through the user interface, which is collected and analyzed by the feedback analyzer. The system optimizer optimizes the recommendation engine and user profile builder based on the results of the feedback analyzer to improve system performance and user satisfaction.

[0104] Based on the above system architecture, the card coupon push method provided in the embodiment of the present application specifically includes the following stages:

[0105] Phase 1: Collect user behavior data.

[0106] Collect various behavioral data of users on the platform, including but not limited to user browsing records, purchase history, search keywords, click-through rate, stay time, favorite products, evaluation feedback, etc. Data collection must comply with privacy protection regulations to ensure the security and privacy of user information. Encryption technology can also be used to ensure the security and privacy of user data.

[0107] In this stage, data collectors can be used to collect user behavior data from various data sources (such as user interfaces, transaction systems, browsing logs, etc.). Design data collection interfaces to capture user behavior on the platform in real time, including but not limited to:

[0108] D user = {Browsing history ,Purchase history ,Search keywords ,Click rate ,Stay time ,Collecti.

[0109] Data preprocessing is also performed in this stage, where the collected raw data are cleaned, formatted, and standardized to facilitate subsequent analysis.

[0110] Figure 3 The workflow and data flow of the data collector are shown, including:

[0111] Step 1: The data collector captures various behavioral data of users on the platform in real time. Collect user behavior data sources, user behaviors on the platform, including browsing, searching, purchasing and other activities.

[0112] Step 2: Data cleaning: Process the collected raw data to remove invalid or erroneous information.

[0113] Step 3: Data storage: Save the cleaned data into a database to ensure data security and accessibility.

[0114] Step 4: Data labeling: Categorize and label the stored data, which helps in organizing and retrieving the data more efficiently.

[0115] Step 5: Data Indexing: Create indexes to improve the efficiency of data query and make data retrieval faster.

[0116] Step 6: Data Warehouse / Data Lake: Transfer the indexed data to a data warehouse or data lake to prepare for further analysis and processing.

[0117] This process ensures the quality and availability of the data, providing a basis for subsequent user behavior analysis and personalized recommendations.

[0118] Phase 2: Build user portraits.

[0119] Use machine learning algorithms to analyze the collected user data and build a behavioral portrait of each user, including the user's basic attributes (such as age, gender, geographic location), consumption habits, preferences, purchasing power and other multi-dimensional characteristics. During the portrait construction process, a dynamic update mechanism is used to reflect the latest changes in user behavior. Use clustering algorithms to classify user data and build user portraits:

[0120] P user =f(D user )

[0121] Where f is a function, based on user behavior data D user To determine the user profile P user multi-dimensional features.

[0122] In this stage, a user profile builder can be used to process the collected data, extract features, and build a user profile that reflects user preferences, behavioral habits, and purchasing patterns. Figure 4 The User Profile Builder workflow is shown below:

[0123] Step 1: Collect the original data source: the user's behavior records on the platform as the starting point of the user behavior data.

[0124] Step 2: Data preprocessing: Clean, format and standardize the raw data to make it suitable for further analysis.

[0125] Step 3: Feature extraction: Identify and extract key features from the preprocessed data, such as purchase frequency, preferred product categories, user active time periods, etc.

[0126] Step 4: User behavior analysis: Identify user behavior patterns and trends by analyzing the extracted features.

[0127] Step 5: User preference modeling: Using the results of behavioral analysis, build a model to predict user preferences and needs.

[0128] Step 6: User profile construction: Combine the results of feature extraction and user preference modeling to form a detailed user profile. Store the constructed user profile in the database for use by the recommendation system.

[0129] This process ensures the accuracy and practicality of user portraits and provides a basis for personalized recommendations.

[0130] Phase 3: User behavior analysis.

[0131] Use data analysis techniques, such as cluster analysis, association rule mining, and sequence pattern mining, to conduct in-depth analysis of user behavior and identify user behavior patterns and potential needs, such as user purchase cycles, preference changes, brand loyalty, and other key information. Apply sequence pattern mining technology to identify user behavior patterns: Pattern behavior =SequenceMining(D user ). Discover user preferences and potential needs through association rule learning algorithms: Rules association =AssociationLearning(D user ).

[0132] Behavioral analysis processors can be used at this stage to apply statistical analysis and machine learning algorithms to identify user behavior patterns and trends. Figure 5 The behavior analysis processor algorithm flow is shown, including the data analysis techniques used:

[0133] Step 1: Input user data: Obtain user data from the user portrait database as the starting point for analysis.

[0134] Step 2: Data cleaning and preprocessing: Remove noise from the data, fill in missing values, and ensure data integrity. Standardize the data to eliminate the impact of different dimensions.

[0135] Step 3: Feature selection: Identify and select features that are important for user behavior analysis in the preprocessed data.

[0136] Step 4: User behavior pattern recognition and association rule mining: Use statistical analysis or machine learning algorithms to identify and understand user behavior patterns. Use algorithms such as Apriori or FP-Growth to discover correlations between user behaviors, such as items that users often buy together.

[0137] Step 5: Sequential pattern analysis, cluster analysis, sentiment analysis: Use sequence mining techniques, such as PrefixSpan or GSP, to analyze the sequential patterns of user behavior, such as the user's purchase process or browsing path. Use clustering algorithms, such as K-means or hierarchical clustering, to group users to identify user groups with similar behavioral characteristics. Use natural language processing technology to analyze the sentiment tendency of user comments and feedback to identify users' positive or negative emotions.

[0138] Step 6: Comprehensive analysis and model building: Integrate the above analysis results to build a comprehensive user behavior model to more accurately predict user behavior.

[0139] Step 7: Output behavior analysis results: Output the constructed model and analysis results for use by the recommendation engine to generate personalized recommendations.

[0140] By comprehensively using a variety of data analysis technologies, the understanding and prediction accuracy of user behavior are improved, providing strong support for personalized services.

[0141] Phase 4: Card and voucher matching.

[0142] Based on the output of the behavior analysis engine, an intelligent algorithm is designed to match the corresponding membership cards and coupons. The algorithm considers user portraits, behavior patterns, market trends, seasonal factors, etc. to achieve personalized recommendations. The algorithm uses machine learning techniques such as collaborative filtering and content recommendation to continuously optimize the recommendation effect.

[0143] Design recommendation algorithms to match cards and coupons based on user profiles and behavior patterns: C recommend =Recommender(P user ,Pattern behavior ). The recommendation algorithm considers the following factors: C recommend ∝α·P user +β·Pattern behavior+γ·MarketTrends+δ·Seasonality. α, β, γ, δ are weight coefficients, which are adjusted according to experiments to optimize the recommendation effect.

[0144] In this stage, a recommendation engine can be used to combine the user portraits and behavior analysis results obtained in the above two stages, and use recommendation algorithms (such as collaborative filtering, content-based recommendations, etc.) to generate personalized membership card recommendations.

[0145] Figure 6 This shows how the recommendation engine works, including how to match user profiles and behavior analysis results:

[0146] Step 1: Get user data from the user portrait database and get behavior analysis results from the behavior analysis processor; the user portrait database stores detailed information and portraits of users, providing basic data for recommendation. The behavior analysis processor provides the user's behavior analysis results, including key information such as user behavior patterns and preferences.

[0147] Step 2: The recommendation engine integrates data from the user profile database and the behavior analysis processor.

[0148] Step 3: Use algorithms (such as collaborative filtering) to recommend coupons by analyzing the user's historical behavior and the behavior of similar users. Apply content recommendation algorithms to match corresponding coupons based on the attributes and preferences in the user profile.

[0149] Step 4: Candidate coupon evaluation: Evaluate the candidate coupon set obtained by the matching algorithm and select the coupon that is most likely to arouse the user's interest.

[0150] Step 5: Personalized recommendation generation: Based on the evaluation results, a final personalized recommendation list is generated, which is designed to meet the user's personalized needs.

[0151] Step 6: Output the recommendation results: Output the generated personalized recommendation results for the next step. The push manager is responsible for pushing the recommendation results to users through appropriate channels to ensure that users can receive personalized card and coupon recommendations.

[0152] This working principle of the recommendation engine ensures the personalization and accuracy of the recommendation process, improves user satisfaction and engagement, and also increases conversion rates and user loyalty.

[0153] Phase 5: Personalized push.

[0154] Push the matched membership cards and coupons to users through the channels they prefer, such as APP notifications, SMS, emails, social media, etc. Push strategies take into account factors such as user active time, push frequency, and user feedback to improve push acceptance and effectiveness. Design push strategies based on user active time and preferences: strategy =g(P user ,Time active ,Channel preference ). The push module adopts a multi-channel push mechanism to maximize the push effect.

[0155] In this stage, a push manager can be used to select the most appropriate push channel and time based on user preferences and behavior analysis and execute push operations. It is also responsible for managing push strategies, including selecting push channels, determining push times, and customizing push content. Figure 7 This is the push manager logic, showing how to select push channels based on different user preferences:

[0156] Step 1: Get recommendation results: Receive personalized recommendation lists from the recommendation engine, which are generated based on user profiles and behavior analysis. Push manager: It is the central link responsible for delivering recommendation results to users. The user preference database stores user preference information, including their preferences for push channels (such as APP notifications, emails, SMS, etc.) and push time preferences.

[0157] Step 2: Push channel selection: Select the most appropriate push channel based on the information in the user preference database to ensure that the information can be delivered in the way that users are most likely to accept.

[0158] Step 3: Push timing optimization: Analyze user active time data and select the time when users are most active or most likely to accept push notifications to increase push delivery rate and attention.

[0159] Step 4: Customize push content: Customize push content according to user preferences, including copywriting, format, personalized information, etc., to increase user click-through rate and engagement.

[0160] Step 5: Push execution: Execute the push operation through the selected channel to ensure that the customized push content can be successfully sent to users.

[0161] Step 6: Collect user feedback and evaluate push effects: Monitor and collect user feedback on push content, including user clicks, ignores, unsubscribes, etc. Evaluate the effectiveness of push by analyzing user feedback and behavior data, focusing on key indicators such as open rate, click rate, and conversion rate.

[0162] This logical process of the push manager ensures that push activities are highly personalized and targeted, which helps to improve user experience and the overall effectiveness of push. According to the results of the push effect evaluation, the push strategy is adjusted and optimized to improve the accuracy and effectiveness of push and better meet user needs.

[0163] Phase 6: Feedback collection.

[0164] Collect user feedback on the pushed coupons, including usage of coupons, satisfaction surveys, user comments, etc. The feedback data is used to evaluate the push effect and fed back to the behavior analysis engine and coupon matching algorithm to optimize subsequent pushes. Design a feedback mechanism to collect user usage and satisfaction with pushed coupons: Feedback data =CollectFeedback(C recommend ).

[0165] At this stage, a push manager can be used to manage push strategies, including selecting push channels, determining push times, and customizing push content. Figure 8 Here’s the Feedback Analyzer workflow, including how user feedback is collected and processed:

[0166] Step 1: Push content: Personalized recommended content sent to users by the push manager.

[0167] Step 2: Collect user interaction data: user responses to pushed content, including clicks, purchases, ignoring, or providing feedback. Collect user feedback data: Explicit feedback: opinions directly expressed by users, such as ratings and comments. Implicit feedback: user behavior data, such as click-through rate, purchase behavior, etc.

[0168] Step 3: Data cleaning and integration: Clean the collected feedback data to remove invalid or erroneous data. Integrate the data to ensure data quality and consistency and prepare for analysis.

[0169] Step 4: Classify the feedback data into three categories: positive, negative, and neutral for subsequent processing.

[0170] Step 5: Enhance similar push and adjust push strategy:

[0171] For positive feedback, identify and enhance or increase the push of similar content to meet user preferences. For negative feedback, analyze the reasons and adjust the push strategy, which may include changing the push content, channel or time. For neutral feedback, conduct in-depth analysis to determine the user's specific needs and preferences to provide a basis for personalized recommendations.

[0172] Step 6: System Optimizer: Receive the analysis results of the feedback analyzer for further system optimization. Optimize user portraits and recommendation algorithms: Based on the feedback analysis results, adjust the user portraits to more accurately reflect user preferences. Optimize the recommendation algorithm to improve the relevance of push notifications and user satisfaction.

[0173] This workflow of the feedback analyzer ensures that the system can self-adjust and optimize based on real-time feedback from users, thereby continuously improving user experience and push effects.

[0174] Phase 7: System optimization.

[0175] Based on the collected feedback data, machine learning technology is used to continuously optimize user portraits, behavior analysis engines, and card-voucher matching algorithms. The system optimization module also includes an anomaly detection mechanism that can identify and handle anomalies during the push process. Use feedback data to optimize user portraits, behavior analysis engines, and card-voucher matching algorithms:

[0176] Optimize(f,SequenceMining,AssociationLearning,Recommender)=Feedback data .

[0177] The reinforcement learning algorithm in machine learning is used to automatically adjust the weight coefficient and optimization strategy. In this stage, the system optimizer can be used to optimize the user portrait, recommendation algorithm and push strategy using feedback data. A detailed description of how the system optimizer uses feedback data to optimize the system:

[0178] Step 1: User feedback data: Collect user interactions and feedback on pushed content, including key indicators such as click-through rate, purchase behavior, and user satisfaction surveys.

[0179] Step 2: Feedback Analyzer: Responsible for the initial collection and analysis of user feedback data to identify areas of user preferences and dissatisfaction.

[0180] Step 3: Feedback data processing: Clean the collected feedback data to remove invalid or erroneous information. Integrate data from different sources to form a unified data set. Classify the data to distinguish between positive, negative, and neutral feedback.

[0181] Step 4: System Optimizer: Receives processed feedback data and starts the system optimization process.

[0182] Step 5: User portrait optimization: Update the user portrait based on feedback data to ensure the accuracy of user preferences and behavioral characteristics. Use machine learning technology to continuously adjust the user portrait to adapt to changes in user behavior.

[0183] Step 6: Recommendation algorithm optimization: Adjust the parameters of the recommendation algorithm based on user feedback to improve the personalization and accuracy of recommendations. Explore and test new recommendation algorithms to better meet user needs.

[0184] Step 7: Push strategy optimization: Adjust the time, channel and content of push according to user feedback to improve user engagement. Implement personalized push strategy to ensure that push content matches user preferences and behavior patterns.

[0185] Step 8: Performance evaluation: Use methods such as A / B testing to evaluate the effectiveness of optimization measures. Monitor key performance indicators such as user engagement, conversion rate, etc. to evaluate the impact of optimization.

[0186] Step 9: Iterative optimization: Based on the results of performance evaluation, continuously iterate and optimize the system to adapt to changes in user behavior and market demand, and continuously improve user experience.

[0187] Through this process, the system optimizer ensures that the system can continue to learn and adapt, achieve more accurate and personalized services, and ultimately improve user satisfaction and business results.

[0188] In summary, the embodiment of the present application provides a card coupon push method, which obtains the real-time behavior data of the target user, the real-time behavior data includes user basic information, platform interaction data and historical order information; constructs a behavior profile of each target user based on the user basic information, platform interaction data and historical order information; performs sequence pattern analysis, cluster analysis and sentiment analysis based on the user basic information, platform interaction data and historical order information to build a user behavior model; calculates the card coupon recommendation result of each target user based on the behavior profile of each target user and the user behavior model; and pushes the card coupon recommendation result of each target user to the corresponding target user based on the user behavior model. By comprehensively analyzing user data, an in-depth understanding of user behavior is achieved, and personalized recommendation services are provided based on this, so as to achieve effective push of card coupons.

[0189] Based on the same technical concept, the embodiment of the present application also provides a card and coupon push system, such as Fig. 9 As shown, the system comprises:

[0190] The data acquisition module 901 is used to acquire the real-time behavior data of the target user, wherein the real-time behavior data includes basic user information, platform interaction data and historical order information;

[0191] A behavior profile module 902 is used to construct a behavior profile of each target user based on the user basic information, platform interaction data and historical order information;

[0192] The behavior model module 903 is used to perform sequence pattern analysis, cluster analysis and sentiment analysis based on the user basic information, platform interaction data and historical order information to build a user behavior model;

[0193] The recommendation result module 904 is used to calculate the card and coupon recommendation result for each target user according to the behavior profile of each target user and the user behavior model;

[0194] The push module 905 is used to push the card coupon recommendation result of each target user to the corresponding target user based on the user behavior model.

[0195] The present application also provides an electronic device corresponding to the method provided in the above embodiment. Fig.10 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. The electronic device 20 may include: a processor 200, a memory 201, a bus 202 and a communication interface 203, wherein the processor 200, the communication interface 203 and the memory 201 are connected via the bus 202; the memory 201 stores a computer program that can be run on the processor 200, and the processor 200 executes the method provided by any of the aforementioned embodiments of the present application when running the computer program.

[0196] The memory 201 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one physical port (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0197] The bus 202 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 201 is used to store programs, and the processor 200 executes the programs after receiving execution instructions. The method disclosed in any implementation of the aforementioned embodiment of the present application may be applied to the processor 200, or implemented by the processor 200.

[0198] The processor 200 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 200. The above processor 200 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201 and completes the steps of the above method in combination with its hardware.

[0199] The electronic device provided in the embodiment of the present application and the method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, operated or implemented by them.

[0200] The present application also provides a computer-readable storage medium corresponding to the method provided in the above embodiment. Fig.11 The computer-readable storage medium shown is a CD 30 on which a computer program (ie, a program product) is stored. When the computer program is run by a processor, the method provided in any of the aforementioned embodiments is executed.

[0201] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0202] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0203] It should be noted that:

[0204] The algorithm and display provided herein are not inherently related to any particular computer, virtual device or other equipment. Various general purpose devices can also be used together with the teachings based on this. According to the above description, it is obvious to construct the structure required for this type of device. In addition, the application is not directed to any specific programming language. It should be understood that the content of the application described herein can be realized using various programming languages, and the description of the specific language above is to disclose the best mode of implementation of the application.

[0205] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0206] Similarly, it should be understood that in order to streamline the present application and help understand one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following intention: the claimed application requires more features than the features clearly stated in each claim. More specifically, as reflected in the claims below, the inventive aspects are less than all the features of the single embodiment disclosed above. Therefore, the claims following the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present application.

[0207] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0208] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0209] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in the creation device of the virtual machine according to the embodiment of the present application. The application can also be implemented as a device or device program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0210] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

Claims

1. A card and coupon push method, characterized in that: The method comprises: Acquire real-time behavior data of target users, including basic user information, platform interaction data, and historical order information; Build a behavior profile of each target user based on the basic user information, platform interaction data, and historical order information; Conduct sequence pattern analysis, cluster analysis and sentiment analysis based on the user basic information, platform interaction data and historical order information to build a user behavior model; Calculate the card and coupon recommendation result for each target user based on the behavior profile of each target user and the user behavior model; Based on the user behavior model, the card coupon recommendation result for each target user is pushed to the corresponding target user.

2. The method according to claim 1, characterized in that The constructing a behavior profile of each target user based on the user basic information, platform interaction data and historical order information includes: Preprocessing the basic user information, platform interaction data and historical order information, wherein the preprocessing includes cleaning, formatting and standardization; the basic user information includes user ID, gender and registration time; the platform interaction data includes login frequency, browsing history, click-through rate and page dwell time; the historical order information includes purchase time, purchased goods, price, payment method and order status; Extracting target features from the preprocessed data, wherein the target features include user behavior patterns and behavior trends; Determine the user's preference results from the preprocessed data; The target features and preference results of the user are classified using a clustering algorithm to determine the user portrait and store it in a database.

3. The method according to claim 1, characterized in that The method of performing sequence pattern analysis, cluster analysis and sentiment analysis based on the user basic information, platform interaction data and historical order information to construct a user behavior model includes: Performing data cleaning on the user basic information, platform interaction data and historical order information, wherein the data cleaning includes removing noise and filling missing values; Extracting user behavior features from the processed data, wherein the user behavior features include access frequency and browsing behavior; Determine the user's behavior pattern using statistical analysis or machine learning algorithms based on the user's behavior characteristics; Performing sequence pattern analysis based on the behavior pattern and user behavior characteristics to analyze the sequence pattern of user behavior, wherein the sequence pattern includes a purchase process and a browsing path; Performing cluster analysis based on the behavior patterns and user behavior characteristics to group users with the same or similar behaviors; Using natural language processing technology to perform sentiment analysis based on the behavior patterns and user behavior characteristics, and identify and classify the user's positive and negative sentiment information; A user behavior model is constructed based on the results of sequence pattern analysis, cluster analysis and sentiment analysis.

4. The method according to claim 1, characterized in that The calculating the card and coupon recommendation result for each target user according to the behavior profile of each target user and the user behavior model includes: Integrate the behavior profile of each target user with the user behavior model to obtain pre-recommendation data for the target user; Analyze the pre-recommendation data of target users based on collaborative filtering algorithm; The analysis results are matched with the behavior data of similar users to obtain a set of candidate coupons as the coupon recommendation results for each target user.

5. The method according to claim 1, characterized in that The pushing of the card coupon recommendation result of each target user to the corresponding target user based on the user behavior model includes: Based on the user behavior model, the user active time is obtained by using time series analysis; the user active time includes the frequency, duration and time distribution of user login; Analyze the user's preferences based on the user behavior model to obtain push preferences, where the push preferences include text format and personalized information; The card coupon recommendation results are pushed through the selected channel according to the push preference during the user's active time.

6. The method according to claim 1, characterized in that After pushing the card and coupon recommendation result of each target user to the corresponding target user based on the user behavior model, the method further includes: Monitor and collect user feedback data on the card recommendation results, including card usage, comments, ratings, and user click, ignore and / or unsubscribe behavior information; Clean and integrate the collected feedback data to remove invalid or erroneous data; Key indicators are calculated based on the processed feedback data, including open rate, click rate and conversion rate.

7. The method according to claim 6, characterized in that The method further comprises: The system optimizer identifies areas of user dissatisfaction through user feedback, low satisfaction scores, and negative sentiment information; Identify user preferences through user feedback, high satisfaction ratings, and positive sentiment information; Updating the user's behavior profile according to the user's preferences and dissatisfied areas data; The recommendation algorithm parameters and push preferences are adjusted according to the user preferences and dissatisfied domain data.

8. A card and coupon push system, characterized in that: The system comprises: A data acquisition module is used to acquire the real-time behavior data of the target user, wherein the real-time behavior data includes basic user information, platform interaction data and historical order information; A behavior profile module is used to construct a behavior profile of each target user based on the user basic information, platform interaction data and historical order information; A behavior model module is used to perform sequence pattern analysis, cluster analysis and sentiment analysis based on the user basic information, platform interaction data and historical order information to build a user behavior model; A recommendation result module, used to calculate the card and coupon recommendation result for each target user based on the behavior profile of each target user and the user behavior model; The push module is used to push the card and coupon recommendation results of each target user to the corresponding target user based on the user behavior model.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Computer-readable instructions are stored thereon, and the computer-readable instructions can be executed by a processor to implement the method according to any one of claims 1-7.

Images