Marketing strategy execution method and related equipment

Abstract

The invention discloses a marketing strategy execution method and related equipment. The method comprises the following steps: acquiring a historical consumption record of a user and basic information of the user; the historical consumption records of the user and the basic information of the user are input into a pre-trained consumption willingness analysis model, a user consumption willingness portrait is generated, and the consumption willingness analysis model is obtained based on training of a large number of sample historical consumption records, sample basic information and correspondingly matched sample consumption willingness portraits; calculating a strategy matching degree between each preset marketing strategy and the user consumption willingness portrait; and determining a target marketing strategy according to the preset marketing strategy with the highest strategy matching degree, and executing the target marketing strategy. According to the method and the device, the selected marketing strategy is ensured to be highly matched with the user demand, so that the pertinence and the effectiveness of the marketing activity are improved, and the marketing effect is improved.

Description

Technical Field

[0001] The present application relates to the field of computers, and more specifically, to a marketing strategy execution method and related equipment. Background Art

[0002] Current e-commerce marketing methods generally follow a pattern: after consumers complete the purchase of goods on the e-commerce platform, the system will automatically trigger the preset marketing strategy. The main form of these marketing strategies is to push marketing messages to consumers, such as recommendations for similar products, promotional information, etc., or provide product coupons to attract consumers to buy again. The core purpose of this strategy is to stimulate consumers' willingness to buy again by providing additional discounts or information, thereby increasing the company's sales and loyalty.

[0003] However, it is worth noting that existing e-commerce marketing programs often adopt a unified marketing strategy when targeting different consumers who have placed orders for specific products. This means that regardless of consumers' purchase history, preferences, spending power or other personalized characteristics, they will receive the same marketing information or coupons. Although this practice simplifies the marketing process and reduces operating costs, it also greatly limits the flexibility and targeting of marketing strategies.

[0004] The limitation of a unified marketing strategy is that it cannot fully consider the individual differences and personalized needs of consumers. For example, for consumers who often buy high-end goods, providing low-value coupons may not be attractive; while for price-sensitive consumers, they may pay more attention to promotions with large discounts. Therefore, if companies cannot formulate marketing strategies based on the personalized characteristics of consumers, the marketing effect may be greatly reduced.

[0005] In addition, unified marketing strategies may also cause dissatisfaction and resistance among consumers. When consumers often receive irrelevant marketing information, it will lead to a bad consumption experience. This will not only damage the company's brand image and consumer relations, but also affect the company's long-term development.

[0006] Based on this, the present application provides a marketing strategy execution plan that can more accurately understand consumer needs and expectations, thereby providing a more suitable marketing strategy. Summary of the invention

[0007] In view of this, the present application provides a marketing strategy execution method and related equipment to ensure that the selected marketing strategy is highly consistent with user needs, thereby improving the pertinence and effectiveness of marketing activities, thereby improving marketing results.

[0008] A marketing strategy execution method, comprising:

[0009] Obtain user historical consumption records and basic user information;

[0010] Inputting the user's historical consumption records and the user's basic information into a pre-trained consumption intention analysis model to generate a user consumption intention profile, wherein the consumption intention analysis model is trained based on a large number of sample historical consumption records, sample basic information, and corresponding matching sample consumption intention profiles;

[0011] Calculate the strategy matching degree between each preset marketing strategy and the user consumption intention profile respectively;

[0012] A target marketing strategy is determined by the preset marketing strategy with the highest strategy matching degree, and the target marketing strategy is executed.

[0013] Optionally, the consumption intention analysis model includes a data processing network, a willingness analysis network, and a portrait construction network;

[0014] The data processing network is used to perform data cleaning, format conversion and aggregation processing on the input user's historical consumption records and the user's basic information to obtain basic data for intention analysis;

[0015] The willingness analysis network analyzes the willingness analysis basic data by constructing a gradient decision tree to determine the preference analysis result and the willingness prediction result;

[0016] The portrait construction network constructs a user consumption intention portrait based on the preference analysis results and the intention prediction results.

[0017] Optionally, the willingness analysis network includes a feature extraction module, an association relationship module, a comprehensive analysis module and a willingness prediction module;

[0018] The feature extraction module is used to extract features from the willingness analysis basic data to generate basic information features, consumption behavior features, and interest preference features;

[0019] The association relationship module determines the feature association rules between the basic information features, the consumption behavior features and the interest preference features through an association rule mining algorithm;

[0020] The comprehensive analysis module constructs a gradient decision tree and generates a preference analysis result by integrating the basic information features, the consumption behavior features, the interest preference features and the feature association rules;

[0021] The willingness prediction module predicts the user's future consumption willingness based on the gradient decision tree analysis and generates a willingness prediction result.

[0022] Optionally, the feature extraction module includes a basic information extraction layer, a consumption behavior extraction layer and an interest preference extraction layer;

[0023] The basic information extraction layer extracts features from the age data, gender data, geographic location data, and income level data in the willingness analysis basic data to generate basic information features;

[0024] The consumption behavior extraction layer generates consumption behavior characteristics according to the purchase quantity data, purchase frequency data, and consumption amount data in the basic data according to the willingness analysis;

[0025] The interest preference extraction layer generates interest preference features based on the browsing behavior data, search behavior data, and social behavior data in the intention analysis basic data.

[0026] Optionally, calculating the strategy matching degree between the preset marketing strategy and the user consumption intention profile includes:

[0027] By evaluating the overlap between the preset marketing strategy and the target user group of the user consumption intention profile, a first matching index value is calculated;

[0028] By performing price-sensitive matching on the preset marketing strategy user and the consumption intention portrait, a second matching index value is calculated;

[0029] By evaluating the marketing applicability of the preset marketing strategy to the user's consumption intention profile, a third matching index value is calculated;

[0030] The first matching index value, the second matching index value and the third matching index value are comprehensively combined with the preset index weights to calculate the strategy matching degree between the preset marketing strategy and the user consumption intention portrait.

[0031] Optionally, also include:

[0032] If the highest strategy matching degree is less than the allowed strategy deviation value, a marketing strategy is constructed based on the user consumption intention portrait.

[0033] A marketing strategy execution device, comprising:

[0034] An information acquisition unit is used to acquire the user's historical consumption records and basic user information;

[0035] A willingness profile unit, used to input the user's historical consumption records and the user's basic information into a pre-trained consumption willingness analysis model to generate a user consumption willingness profile, wherein the consumption willingness analysis model is trained based on a large number of sample historical consumption records, sample basic information and corresponding matching sample consumption willingness profiles;

[0036] A matching calculation unit, used to calculate the strategy matching degree between each preset marketing strategy and the user consumption intention profile;

[0037] The strategy determination unit is used to determine the target marketing strategy based on the preset marketing strategy with the highest strategy matching degree, and execute the target marketing strategy.

[0038] A marketing strategy execution device, comprising a memory and a processor;

[0039] The memory is used to store programs;

[0040] The processor is used to execute the program to implement each step of the marketing strategy execution method as described in any one of the above items.

[0041] A readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, each step of the marketing strategy execution method as described in any one of the above items is implemented.

[0042] A computer program product includes a computer program, wherein the computer program executes each step of the marketing strategy execution method as described above when the computer program is executed by a processor.

[0043] It can be seen from the above technical solution that a marketing strategy execution method and related equipment provided in the embodiment of the present application first obtains the user's historical consumption records and the user's basic information, and generates a user consumption intention portrait by inputting the user's historical consumption records and the user's basic information into a pre-trained consumption intention analysis model, wherein the consumption intention analysis model is trained based on a large number of sample historical consumption records, sample basic information, and corresponding matching sample consumption intention portraits. Then, the strategy matching degree between each preset marketing strategy and the user consumption intention portrait is calculated respectively. Since the preset marketing strategy with the highest strategy matching degree is the marketing strategy that best suits the user, the preset marketing strategy with the highest strategy matching degree is determined as the target marketing strategy, and the target marketing strategy is executed.

[0044] This application can accurately generate a user consumption intention portrait by deeply analyzing the user's historical consumption records and basic user information and using a pre-trained consumption intention analysis model. This portrait not only fully reflects the user's consumption preferences, purchasing power and behavior patterns, but also reflects the user's potential needs and future consumption trends. After that, by calculating the strategic match between each preset marketing strategy and the user's consumption intention portrait, it ensures that the selected marketing strategy is highly consistent with user needs, thereby improving the pertinence and effectiveness of marketing activities, thereby improving marketing results. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application 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 embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0046] Figure 1 A flowchart of a marketing strategy execution method disclosed in an embodiment of the present application;

[0047] Figure 2 A schematic diagram of the structure of a consumption willingness analysis model disclosed in an embodiment of the present application;

[0048] Figure 3 A schematic diagram of a marketing strategy execution device disclosed in an embodiment of the present application;

[0049] Figure 4 This is a hardware structure block diagram of a marketing strategy execution device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0051] The present application can be used in many general or special computing device environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multi-processor devices, distributed computing environments including any of the above devices or equipment, etc.

[0052] The embodiment of the present application provides a marketing strategy execution method, which can be applied to platforms or applications such as online consumer shopping, and can also be applied to various computer terminals or smart terminals. The execution subject can be a processor or server of the computer terminal or smart terminal.

[0053] Next, the present application scheme is introduced. The present application proposes the following technical scheme, please see below for details.

[0054] Figure 1 A flowchart of a marketing strategy execution method disclosed in an embodiment of the present application.

[0055] like Figure 1 As shown, the method may include:

[0056] Step S1: Obtain the user's historical consumption records and basic user information.

[0057] Specifically, in the process of determining targeted marketing strategies, the first thing to do is to obtain the user's historical consumption records and basic information. Historical consumption records include detailed information such as the type, price, purchase frequency, and time nodes of the purchased goods. These historical consumption records can intuitively reflect the user's consumption preferences and purchasing habits. At the same time, it is also necessary to obtain the user's basic information, which is voluntarily filled in by the user when registering and can be legally known by the platform, such as age, gender, occupation, place of residence, etc. This information helps to gain an in-depth understanding of the user's consumption needs and provide solid data support for the subsequent formulation of accurate and effective marketing strategies, thereby accurately capturing and efficiently responding to user needs.

[0058] Step S2: input the user's historical consumption records and the user's basic information into a pre-trained consumption intention analysis model to generate a user consumption intention portrait.

[0059] Specifically, the consumption intention analysis model is trained based on a large number of sample historical consumption records, sample basic information, and corresponding matching sample consumption intention portraits. In order to make the consumption intention analysis model more accurate, the sample data should cover a wide range of user groups. The sample historical consumption records include detailed consumption records such as purchase history, consumption habits, and preferred product categories. The sample basic information includes basic information such as age, gender, occupation, and income. Through in-depth analysis and learning of these sample data, the model can identify patterns and trends in consumer behavior and key factors that affect consumer decisions.

[0060] When the user's historical consumption records and basic user information are input into the trained consumption intention analysis model, the model will analyze and evaluate this information. This process includes in-depth analysis of user consumption behavior and prediction of user future consumption trends. Through analytical calculations, the model can generate a user consumption intention portrait, which not only describes the user's current consumption preferences in detail, but also predicts the user's future consumption tendencies and potential needs.

[0061] Step S3: Calculate the strategy matching degree between each preset marketing strategy and the user consumption intention profile.

[0062] Specifically, calculating the strategic matching degree between each preset marketing strategy and the user's consumption intention portrait is intended to ensure that the selected marketing strategy can fit the user's actual needs and achieve precision marketing. First, a series of marketing strategies can be pre-set manually. These marketing strategies may cover different promotion methods, price strategies, product recommendation algorithms, etc., which basically cover the needs of most users and aim to meet the diverse needs of different user groups. After that, the matching degree between each preset marketing strategy and the user portrait is calculated one by one to evaluate the matching between different marketing strategies and user needs. After that, the system can filter out the adapted marketing strategy based on the strategic matching degree and execute personalized marketing activities accordingly.

[0063] Calculating the strategy matching degree between the preset marketing strategy and the user consumption intention profile may specifically include:

[0064] ① By evaluating the overlap between the preset marketing strategy and the target user group of the user consumption intention portrait, the first matching index value is calculated.

[0065] Specifically, the first matching index value is calculated by evaluating the overlap between the target user group of the preset marketing strategy and the user consumption intention profile. The core of this step is to compare the similarity or overlap between the target user group of the marketing strategy and the user group represented by the profile. If the two are highly overlapped, it means that the marketing strategy is likely to be attractive to the user, thus obtaining a higher first matching index value.

[0066] ② By performing price-sensitive matching on the preset marketing strategy users and the consumption intention portrait, a second matching index value is calculated.

[0067] Specifically, the second matching index value is calculated by price-sensitive matching of the users of the preset marketing strategy and the user consumption intention profile. This step aims to analyze the user's sensitivity to price changes and whether the price strategy in the marketing strategy is consistent with the user's price expectations. If the price discount or pricing strategy in the marketing strategy can accurately reach the user's price sensitivity point, then the second matching index value will be higher.

[0068] ③ By evaluating the marketing applicability of the preset marketing strategy to the user's consumption intention portrait, the third matching index value is calculated.

[0069] Specifically, the third matching index value is calculated by evaluating the marketing applicability of the preset marketing strategy to the user's consumption intention profile. This step involves considering the content, form, timing and other aspects of the marketing strategy to ensure that they are consistent with the consumption preferences, purchasing habits and other characteristics in the user profile. If the marketing strategy can accurately capture and meet the user's potential needs, the third matching index value will be significantly improved.

[0070] ④ Comprehensively combining the first matching index value, the second matching index value and the third matching index value, combined with the preset index weights, calculate the strategy matching degree between the preset marketing strategy and the user consumption intention portrait.

[0071] Specifically, the first matching index value, the second matching index value, and the third matching index value are combined with the preset weights of each index to calculate the strategic matching degree between the preset marketing strategy and the user's consumption intention profile. This process can integrate the matching degrees of various dimensions into a comprehensive index through methods such as weighted average to fully reflect the matching degree between the marketing strategy and user needs. The weight setting can be adjusted according to the company's own marketing goals and market environment to ensure that the calculation of strategic matching degree is more reasonable.

[0072] Step S4: Determine the target marketing strategy based on the preset marketing strategy with the highest strategy matching degree, and execute the target marketing strategy.

[0073] Specifically, based on the previously calculated strategic matching between each preset marketing strategy and the user's consumption intention profile, the system will automatically identify and select the strategy with the highest matching degree. This step ensures that the selected strategy can meet the user's personalized needs and preferences to the greatest extent, thereby improving the pertinence and effectiveness of marketing activities.

[0074] Once the target marketing strategy is determined, the system will immediately start the execution process. This process may include multiple steps, such as product recommendations, coupon issuance, promotional event notifications, etc., depending on the type and content of the target strategy. During the execution process, the system will ensure that all marketing information can be presented in a way that is most acceptable and understandable to users, such as through personalized emails, SMS reminders, APP push and other channels, to maximize user participation and conversion rate.

[0075] At the same time, in order to monitor and evaluate the implementation effect of the target marketing strategy, the system will collect and analyze user feedback data in real time, such as key indicators such as click-through rate, conversion rate, user satisfaction, etc. These data can not only help companies to understand users' reactions and acceptance of marketing strategies in a timely manner, but also provide important references for subsequent strategy optimization and adjustment.

[0076] In addition, in the process of formulating and implementing personalized marketing strategies, in order to maintain the flexibility and innovation of marketing strategies, this application also supports the construction of targeted marketing strategies, specifically:

[0077] If the highest strategy matching degree is less than the allowed strategy deviation value, a marketing strategy is constructed based on the user consumption intention portrait.

[0078] Specifically, when the calculated highest strategy match is less than the preset allowable strategy deviation value, this means that even the most matching preset marketing strategy cannot achieve the desired level of fit with user needs. In this case, the system will instead build a new marketing strategy based on the user's consumption intention profile. This process will make full use of the detailed information in the user profile, including the user's consumption preferences, purchasing habits, potential needs, etc., and design a marketing strategy that better meets the user's personalized needs through data analysis and creative planning.

[0079] It can be seen from the above technical solution that a marketing strategy execution method and related equipment provided in the embodiment of the present application first obtains the user's historical consumption records and the user's basic information, and generates a user consumption intention portrait by inputting the user's historical consumption records and the user's basic information into a pre-trained consumption intention analysis model, wherein the consumption intention analysis model is trained based on a large number of sample historical consumption records, sample basic information, and corresponding matching sample consumption intention portraits. Then, the strategy matching degree between each preset marketing strategy and the user consumption intention portrait is calculated respectively. Since the preset marketing strategy with the highest strategy matching degree is the marketing strategy that best suits the user, the preset marketing strategy with the highest strategy matching degree is determined as the target marketing strategy, and the target marketing strategy is executed.

[0080] This application can accurately generate a user consumption intention portrait by deeply analyzing the user's historical consumption records and basic user information and using a pre-trained consumption intention analysis model. This portrait not only fully reflects the user's consumption preferences, purchasing power and behavior patterns, but also reflects the user's potential needs and future consumption trends. After that, by calculating the strategic match between each preset marketing strategy and the user's consumption intention portrait, it ensures that the selected marketing strategy is highly consistent with user needs, thereby improving the pertinence and effectiveness of marketing activities, thereby improving marketing results.

[0081] Figure 2 A schematic diagram of the structure of a consumption willingness analysis model disclosed in an embodiment of the present application.

[0082] In some embodiments of the present application, Figure 2 The consumption willingness analysis model is introduced.

[0083] like Figure 2 As shown, the consumption intention analysis model may specifically include a data processing network 10, a willingness analysis network 20 and a portrait construction network 30.

[0084] Data Processing Network 10:

[0085] The data processing network is used to perform data cleaning, format conversion and aggregation processing on the input user historical consumption records and the user basic information to obtain basic data for intention analysis.

[0086] Specifically, as the starting point of the entire analysis process, the data processing network undertakes the task of preprocessing the user's historical consumption records and basic information. This network ensures data quality by removing redundant and erroneous information through data cleaning; unifies data from different sources and formats into a standard format that can be analyzed through format conversion; and integrates scattered data into basic data for comprehensive analysis through aggregation processing.

[0087] Willingness Analysis Network 20:

[0088] The willingness analysis network analyzes the willingness analysis basic data by constructing a gradient decision tree to determine the preference analysis results and willingness prediction results.

[0089] Specifically, the willingness analysis network uses a gradient decision tree to conduct an in-depth analysis of the processed basic data. The gradient decision tree is a powerful classification and regression tool that can automatically learn the characteristic patterns in the data and classify and predict the user's consumption preferences based on these patterns. In this network, the gradient decision tree determines the user's preference analysis results by analyzing the basic data, which includes a detailed description of the user's favorite product types, brands, price ranges, etc. At the same time, it also predicts the user's consumption willingness, that is, the user's possible purchasing behavior and consumption trends in the future.

[0090] The intention analysis network 20 further includes a feature extraction module 210 , an association relationship module 220 , a comprehensive analysis module 230 and a intention prediction module 240 .

[0091] The feature extraction module 210 is used to extract features from the willingness analysis basic data to generate basic information features, consumption behavior features, and interest preference features.

[0092] The association relationship module 220 determines the feature association rules between the basic information features, the consumption behavior features and the interest preference features through an association rule mining algorithm;

[0093] The comprehensive analysis module 230 constructs a gradient decision tree and generates a preference analysis result by integrating the basic information features, the consumption behavior features, the interest preference features and the feature association rules;

[0094] The willingness prediction module 240 predicts the user's future consumption willingness based on the gradient decision tree analysis and generates a willingness prediction result.

[0095] Specifically, the feature extraction module extracts feature information that is crucial to the analysis of user consumption willingness from the basic data of willingness analysis, including basic information features, consumption behavior features, and interest preference features. The association relationship module uses the association rule mining algorithm to conduct in-depth analysis of basic information features, consumption behavior features, and interest preference features to determine the feature association rules between them. These association rules reveal the interaction and influence between user features. On the basis of feature extraction and association relationship analysis, the comprehensive analysis module further integrates all key features and information to construct a gradient decision tree. The gradient decision tree is a powerful machine learning model that can automatically learn and generate decision paths based on the input feature data to achieve accurate classification and prediction of user consumption preferences. In this module, the gradient decision tree generates detailed preference analysis results by analyzing the integrated feature data. These results fully reflect the user's consumption preferences and potential needs. The willingness prediction module predicts the user's future consumption willingness based on the analysis results of the gradient decision tree. It uses the prediction ability of the gradient decision tree, combined with the user's historical consumption behavior and the current market environment, to generate accurate willingness prediction results. These prediction results not only include information such as the product type, brand, price range, etc. that the user may purchase, but also reflect the user's possible consumption trends and purchasing behavior in the future.

[0096] The feature extraction module 210 includes a basic information extraction layer 211, a consumption behavior extraction layer 212 and an interest preference extraction layer 213;

[0097] The basic information extraction layer 211 extracts features from the age data, gender data, geographic location data, and income level data in the willingness analysis basic data to generate basic information features;

[0098] The consumption behavior extraction layer 212 generates consumption behavior features according to the purchase quantity data, purchase frequency data, and consumption amount data in the basic data according to the willingness analysis;

[0099] The interest preference extraction layer 213 generates interest preference features according to the browsing behavior data, search behavior data, and social behavior data in the intention analysis basic data.

[0100] Specifically, the basic information extraction layer is responsible for processing and analyzing the basic information of users in the willingness analysis basic data. It uses advanced data processing technology and algorithms to extract key basic information features from age data, gender data, geographic location data and income level data. The consumption behavior extraction layer is responsible for extracting consumption behavior features from users' purchase behavior data. By analyzing the purchase quantity data, purchase frequency data and consumption amount data, it can deeply understand users' purchasing habits, consumption ability and consumption trends. These consumption behavior features not only reflect the current consumption status of users, but also predict users' future consumption potential and purchase intentions. The interest preference extraction layer is responsible for extracting interest preference features from users' browsing behavior data, search behavior data and social behavior data. By using technologies such as natural language processing, text mining and social network analysis, it can accurately capture users' preference for specific products, brands or activities, as well as users' interests and hot spots. These interest preference features are crucial to understanding users' personalized needs and potential consumption intentions. The feature extraction module can comprehensively and efficiently extract the key feature information required for users' consumption intention analysis through the collaborative work of the basic information extraction layer, consumption behavior extraction layer and interest preference extraction layer.

[0101] Image building network 30:

[0102] The portrait construction network constructs a user consumption intention portrait based on the preference analysis results and the intention prediction results.

[0103] Specifically, the portrait construction network constructs a user consumption intention portrait based on the preference analysis results and intention prediction results output by the intention analysis network. This portrait is an intuitive display of the user's consumption intention. It contains information on the user's consumption preferences, purchasing habits, potential needs, etc. Through the portrait construction network, complex user data can be converted into a consumption intention portrait that is easy to understand and apply, which is an important basis for the subsequent formulation of marketing strategies and the provision of personalized services.

[0104] A marketing strategy execution device provided in an embodiment of the present application is described below. The marketing strategy execution device described below and the marketing strategy execution method described above can refer to each other.

[0105] See also Figure 3 , Figure 3 A schematic diagram of a marketing strategy execution device disclosed in an embodiment of the present application.

[0106] like Figure 3 As shown, the marketing strategy execution device may include:

[0107] Information acquisition unit A1, used to acquire user's historical consumption records and user basic information;

[0108] The willingness profile unit A2 is used to input the user's historical consumption records and the user's basic information into a pre-trained consumption willingness analysis model to generate a user consumption willingness profile, wherein the consumption willingness analysis model is trained based on a large number of sample historical consumption records, sample basic information and corresponding matching sample consumption willingness profiles;

[0109] A matching calculation unit A3, used to calculate the strategy matching degree between each preset marketing strategy and the user consumption willingness profile;

[0110] The strategy determination unit A4 is used to determine the target marketing strategy based on the preset marketing strategy with the highest strategy matching degree, and execute the target marketing strategy.

[0111] It can be seen from the above technical solution that a marketing strategy execution method and related equipment provided in the embodiment of the present application first obtains the user's historical consumption records and the user's basic information, and generates a user consumption intention portrait by inputting the user's historical consumption records and the user's basic information into a pre-trained consumption intention analysis model, wherein the consumption intention analysis model is trained based on a large number of sample historical consumption records, sample basic information, and corresponding matching sample consumption intention portraits. Then, the strategy matching degree between each preset marketing strategy and the user consumption intention portrait is calculated respectively. Since the preset marketing strategy with the highest strategy matching degree is the marketing strategy that best suits the user, the preset marketing strategy with the highest strategy matching degree is determined as the target marketing strategy, and the target marketing strategy is executed.

[0112] This application can accurately generate a user consumption intention portrait by deeply analyzing the user's historical consumption records and basic user information and using a pre-trained consumption intention analysis model. This portrait not only fully reflects the user's consumption preferences, purchasing power and behavior patterns, but also reflects the user's potential needs and future consumption trends. After that, by calculating the strategic match between each preset marketing strategy and the user's consumption intention portrait, it ensures that the selected marketing strategy is highly consistent with user needs, thereby improving the pertinence and effectiveness of marketing activities, thereby improving marketing results.

[0113] Optionally, the consumption intention analysis model includes a data processing network, a willingness analysis network, and a portrait construction network;

[0114] The data processing network is used to perform data cleaning, format conversion and aggregation processing on the input user's historical consumption records and the user's basic information to obtain basic data for intention analysis;

[0115] The willingness analysis network analyzes the willingness analysis basic data by constructing a gradient decision tree to determine the preference analysis result and the willingness prediction result;

[0116] The portrait construction network constructs a user consumption intention portrait based on the preference analysis results and the intention prediction results.

[0117] Optionally, the willingness analysis network includes a feature extraction module, an association relationship module, a comprehensive analysis module and a willingness prediction module;

[0118] The feature extraction module is used to extract features from the willingness analysis basic data to generate basic information features, consumption behavior features, and interest preference features;

[0119] The association relationship module determines the feature association rules between the basic information features, the consumption behavior features and the interest preference features through an association rule mining algorithm;

[0120] The comprehensive analysis module constructs a gradient decision tree and generates a preference analysis result by integrating the basic information features, the consumption behavior features, the interest preference features and the feature association rules;

[0121] The willingness prediction module predicts the user's future consumption willingness based on the gradient decision tree analysis and generates a willingness prediction result.

[0122] Optionally, the feature extraction module includes a basic information extraction layer, a consumption behavior extraction layer and an interest preference extraction layer;

[0123] The basic information extraction layer extracts features from the age data, gender data, geographic location data, and income level data in the willingness analysis basic data to generate basic information features;

[0124] The consumption behavior extraction layer generates consumption behavior characteristics according to the purchase quantity data, purchase frequency data, and consumption amount data in the basic data according to the willingness analysis;

[0125] The interest preference extraction layer generates interest preference features based on the browsing behavior data, search behavior data, and social behavior data in the intention analysis basic data.

[0126] Optionally, the matching calculation unit may include:

[0127] A first matching unit, configured to calculate a first matching index value by evaluating the target user group overlap between the preset marketing strategy and the user consumption intention profile;

[0128] A second matching unit is used to calculate a second matching index value by performing price-sensitive matching on the preset marketing strategy user and the consumption intention portrait;

[0129] A third matching unit, configured to calculate a third matching index value by evaluating the marketing applicability of a preset marketing strategy to the user's consumption intention profile;

[0130] The matching comprehensive unit is used to comprehensively calculate the strategy matching degree between the preset marketing strategy and the user consumption intention portrait by combining the first matching index value, the second matching index value and the third matching index value with the preset index weights.

[0131] Optionally, the marketing strategy execution device may further include:

[0132] A strategy construction unit is used to construct a marketing strategy based on the user consumption intention portrait when the highest strategy matching degree is less than the allowed strategy deviation value.

[0133] The marketing strategy execution apparatus provided in the embodiments of the present application can be applied to a marketing strategy execution device. Figure 4 The hardware structure diagram of the marketing strategy execution device is shown in FIG. Figure 4 ,The hardware structure of the marketing strategy execution device may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;

[0134] In the embodiment of the present application, the number of the processor 1, the communication interface 2, the memory 3, and the communication bus 4 is at least one, and the processor 1, the communication interface 2, and the memory 3 communicate with each other through the communication bus 4;

[0135] The processor 1 may be a central processing unit CPU, or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention, etc.;

[0136] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), etc., such as at least one disk memory;

[0137] The memory stores a program, and the processor can call the program stored in the memory, wherein the program is used to:

[0138] Obtain user historical consumption records and basic user information;

[0139] Inputting the user's historical consumption records and the user's basic information into a pre-trained consumption intention analysis model to generate a user consumption intention profile, wherein the consumption intention analysis model is trained based on a large number of sample historical consumption records, sample basic information, and corresponding matching sample consumption intention profiles;

[0140] Calculate the strategy matching degree between each preset marketing strategy and the user consumption intention profile respectively;

[0141] A target marketing strategy is determined by the preset marketing strategy with the highest strategy matching degree, and the target marketing strategy is executed.

[0142] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0143] The embodiment of the present application further provides a readable storage medium, which may store a program suitable for execution by a processor, wherein the program is used to:

[0144] Obtain user historical consumption records and basic user information;

[0145] Inputting the user's historical consumption records and the user's basic information into a pre-trained consumption intention analysis model to generate a user consumption intention profile, wherein the consumption intention analysis model is trained based on a large number of sample historical consumption records, sample basic information, and corresponding matching sample consumption intention profiles;

[0146] Calculate the strategy matching degree between each preset marketing strategy and the user consumption intention profile respectively;

[0147] A target marketing strategy is determined by the preset marketing strategy with the highest strategy matching degree, and the target marketing strategy is executed.

[0148] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0149] The present application also provides a computer program product, including a computer program. When the computer program is executed by a processor, the execution method is as follows:

[0150] Obtain user historical consumption records and basic user information;

[0151] Inputting the user's historical consumption records and the user's basic information into a pre-trained consumption intention analysis model to generate a user consumption intention profile, wherein the consumption intention analysis model is trained based on a large number of sample historical consumption records, sample basic information, and corresponding matching sample consumption intention profiles;

[0152] Calculate the strategy matching degree between each preset marketing strategy and the user consumption intention profile respectively;

[0153] A target marketing strategy is determined by the preset marketing strategy with the highest strategy matching degree, and the target marketing strategy is executed.

[0154] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0155] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0156] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0157] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A marketing strategy execution method, characterized in that: include: Obtain user historical consumption records and basic user information; Inputting the user's historical consumption records and the user's basic information into a pre-trained consumption intention analysis model to generate a user consumption intention profile, wherein the consumption intention analysis model is trained based on a large number of sample historical consumption records, sample basic information, and corresponding matching sample consumption intention profiles; Calculate the strategy matching degree between each preset marketing strategy and the user consumption intention profile respectively; A target marketing strategy is determined by the preset marketing strategy with the highest strategy matching degree, and the target marketing strategy is executed.

2. The method according to claim 1, characterized in that The consumption intention analysis model includes a data processing network, a willingness analysis network and a portrait construction network; The data processing network is used to perform data cleaning, format conversion and aggregation processing on the input user's historical consumption records and the user's basic information to obtain basic data for intention analysis; The willingness analysis network analyzes the willingness analysis basic data by constructing a gradient decision tree to determine the preference analysis result and the willingness prediction result; The portrait construction network constructs a user consumption intention portrait based on the preference analysis results and the intention prediction results.

3. The method according to claim 2, characterized in that The willingness analysis network includes a feature extraction module, an association relationship module, a comprehensive analysis module and a willingness prediction module; The feature extraction module is used to extract features from the willingness analysis basic data to generate basic information features, consumption behavior features, and interest preference features; The association relationship module determines the feature association rules between the basic information features, the consumption behavior features and the interest preference features through an association rule mining algorithm; The comprehensive analysis module constructs a gradient decision tree and generates a preference analysis result by integrating the basic information features, the consumption behavior features, the interest preference features and the feature association rules; The willingness prediction module predicts the user's future consumption willingness based on the gradient decision tree analysis and generates a willingness prediction result.

4. The method according to claim 3, characterized in that The feature extraction module includes a basic information extraction layer, a consumption behavior extraction layer and an interest preference extraction layer; The basic information extraction layer extracts features from the age data, gender data, geographic location data, and income level data in the willingness analysis basic data to generate basic information features; The consumption behavior extraction layer generates consumption behavior characteristics according to the purchase quantity data, purchase frequency data, and consumption amount data in the basic data according to the willingness analysis; The interest preference extraction layer generates interest preference features based on the browsing behavior data, search behavior data, and social behavior data in the intention analysis basic data.

5. The method according to claim 1, characterized in that Calculating the strategy matching degree between the preset marketing strategy and the user consumption intention profile, including: By evaluating the overlap between the preset marketing strategy and the target user group of the user consumption intention profile, a first matching index value is calculated; By performing price-sensitive matching on the preset marketing strategy user and the consumption intention portrait, a second matching index value is calculated; By evaluating the marketing applicability of the preset marketing strategy to the user's consumption intention profile, a third matching index value is calculated; The first matching index value, the second matching index value and the third matching index value are comprehensively combined with the preset index weights to calculate the strategy matching degree between the preset marketing strategy and the user consumption intention portrait.

6. The method according to claim 1, characterized in that Also includes: If the highest strategy matching degree is less than the allowed strategy deviation value, a marketing strategy is constructed based on the user consumption intention portrait.

7. A marketing strategy execution device, characterized in that: include: An information acquisition unit is used to acquire the user's historical consumption records and basic user information; A willingness profile unit, used to input the user's historical consumption records and the user's basic information into a pre-trained consumption willingness analysis model to generate a user consumption willingness profile, wherein the consumption willingness analysis model is trained based on a large number of sample historical consumption records, sample basic information and corresponding matching sample consumption willingness profiles; A matching calculation unit, used to respectively calculate the strategy matching degree between each preset marketing strategy and the user consumption intention profile; The strategy determination unit is used to determine the target marketing strategy based on the preset marketing strategy with the highest strategy matching degree, and execute the target marketing strategy.

8. A marketing strategy execution device, characterized in that: including memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the marketing strategy execution method as described in any one of claims 1-6.

9. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the marketing strategy execution method as described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, each step of the marketing strategy implementation method as described in any one of claims 1 to 6 is executed.

Images