CN119558901A - A marketing strategy execution method and related equipment - Google Patents
A marketing strategy execution method and related equipment Download PDFInfo
- Publication number
- CN119558901A CN119558901A CN202411741697.8A CN202411741697A CN119558901A CN 119558901 A CN119558901 A CN 119558901A CN 202411741697 A CN202411741697 A CN 202411741697A CN 119558901 A CN119558901 A CN 119558901A
- Authority
- CN
- China
- Prior art keywords
- consumption
- user
- willingness
- strategy
- marketing strategy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0222—During e-commerce, i.e. online transactions
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0239—Online discounts or incentives
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Recommending goods or services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本申请公开了一种营销策略执行方法和相关设备，方法包括：获取用户历史消费记录以及用户基础信息；将所述用户历史消费记录和所述用户基础信息输入预先训练完成的消费意愿分析模型，生成用户消费意愿画像，其中所述消费意愿分析模型基于大量的样本历史消费记录、样本基础信息以及对应匹配的样本消费意愿画像训练得到；分别计算每一预置营销策略与所述用户消费意愿画像之间的策略匹配度；将所述策略匹配度最高的预置营销策略确定的目标营销策略，并执行所述目标营销策略。本申请确保了所选营销策略与用户需求的高度契合，从而提高了营销活动的针对性和有效性，从而提升营销效果。
The present application discloses a marketing strategy execution method and related equipment, the method comprising: obtaining user historical consumption records and user basic information; inputting the user historical consumption records and the user basic information into a pre-trained consumption willingness analysis model to generate a user consumption willingness portrait, 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 portraits; respectively calculating the strategy matching degree between each preset marketing strategy and the user consumption willingness portrait; determining the target marketing strategy with the preset marketing strategy with the highest strategy matching degree, and executing the target marketing strategy. The present application 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.
Description
Technical Field
The present application relates to the field of computers, and more particularly, to a marketing strategy execution method and related devices.
Background
The current e-commerce marketing mode generally follows a mode that after a consumer completes commodity purchasing behavior on an e-commerce platform, a system can automatically trigger a preset marketing strategy. The primary form of these marketing strategies is to push marketing messages to consumers like product recommendations, promotional event information, etc., or to provide merchandise coupons to entice consumers to purchase again. The core goal of such a strategy is to motivate consumers to purchase again by providing additional offers or information, thereby increasing sales and loyalty for the business.
However, it is noted that existing e-commerce marketing schemes tend to employ a unified marketing strategy for different consumers who have placed orders to purchase a particular commodity. This means that consumers receive the same marketing message or coupon regardless of their purchase history, preferences, consumption capabilities, or other personalized features. This approach, while simplifying the marketing process and reducing the operating costs, also limits the flexibility and pertinence of the marketing strategy to a great extent.
The limitation of the unified marketing strategy is that it cannot adequately take into account individual differences and personalized needs of consumers. For example, it may not be attractive to provide low value coupons for consumers who frequently purchase high end products, while they may be more concerned with a more discountable promotional program for price sensitive consumers. Thus, if the enterprise is unable to formulate marketing strategies based on the personalized features of the consumer, the marketing effect may be compromised.
In addition, unified marketing strategies may also lead to consumer dissatisfaction and contradiction. When consumers often receive irrelevant marketing information, poor consumer experience can instead result. This can not only compromise the brand image and consumer relationship of the enterprise, but can also affect the long-term evolution of the enterprise.
Based on the above, the application provides a marketing strategy execution scheme, which can know the demands and the expectations of consumers more accurately, thereby providing a more adaptive marketing strategy.
Disclosure of Invention
In view of the above, the application provides a marketing strategy execution method and related equipment, which ensure that the selected marketing strategy is highly matched with the demands of users, thereby improving the pertinence and the effectiveness of marketing activities and improving the marketing effect.
A marketing strategy execution method, comprising:
Acquiring a user history consumption record and user basic information;
Inputting the user historical consumption record and the user basic information into a pre-trained consumption intention analysis model to generate a user consumption intention portrait, wherein the consumption intention analysis model is obtained by training based on a large number of sample historical consumption records, sample basic information and corresponding matched sample consumption intention portraits;
respectively calculating the policy matching degree between each preset marketing policy and the consumer willingness portraits;
And determining a target marketing strategy according to the preset marketing strategy with the highest strategy matching degree, and executing the target marketing strategy.
Optionally, the consumer intention analysis model comprises a data processing network, an intention analysis network and a portrait construction network;
The data processing network is used for carrying out data cleaning, format conversion and aggregation processing on the input historical consumption records of the users and the basic information of the users to obtain willingness analysis basic data;
the willingness analysis network analyzes the willingness analysis basic data by constructing a gradient decision tree, and determines a preference analysis result and a willingness prediction result;
and the portrayal construction network constructs the consumer willingness portrayal based on the preference analysis result and the willingness prediction result.
Optionally, the willingness analysis network comprises a feature extraction module, an association relation module, a comprehensive analysis module and a willingness prediction module;
the feature extraction module is used for carrying out feature extraction on the willingness analysis basic data to generate basic information features, consumption behavior features and interest preference features;
The association relation module determines feature association rules among the basic information features, the consumption behavior features and the interest preference features through an association rule mining algorithm;
The comprehensive analysis module builds 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;
and the willingness prediction module predicts the future consumption willingness of the user based on the analysis of the gradient decision tree and generates a willingness prediction result.
Optionally, the feature extraction module comprises a basic information extraction layer, a consumption behavior extraction layer and an interest preference extraction layer;
the basic information extraction layer performs feature extraction on age data, gender data, geographic position data and income level data in the willingness analysis basic data to generate basic information features;
The consumption behavior extraction layer analyzes purchase quantity data, purchase frequency data and consumption amount data in the basic data according to the will to generate consumption behavior characteristics;
and the interest preference extraction layer analyzes browsing behavior data, searching behavior data and social behavior data in the basic data according to the will to generate interest preference characteristics.
Optionally, calculating a policy matching degree between a preset marketing policy and the consumer will portrait comprises:
calculating to obtain a first matching index value by evaluating the target user group coincidence degree between a preset marketing strategy and the user consumption willingness portraits;
Calculating a second matching index value by price sensitive matching of the preset marketing strategy user and the consumer wish portraits;
calculating a third matching index value by evaluating the marketing applicability of a preset marketing strategy to the consumer will portrait;
And integrating the first matching index value, the second matching index value and the third matching index value, and combining preset index weights to calculate and obtain the strategy matching degree between a preset marketing strategy and the consumer wish portrait of the user.
Optionally, the method further comprises:
And if the highest strategy matching degree is smaller than the allowed strategy deviation value, carrying out marketing strategy construction based on the consumer willingness portraits.
A marketing strategy execution device, comprising:
The information acquisition unit is used for acquiring a user history consumption record and user basic information;
The willingness portrait unit is used for inputting the user historical consumption record and the user basic information into a pre-trained consumption willingness analysis model to generate a user consumption willingness portrait, wherein the consumption willingness analysis model is obtained by training based on a large number of sample historical consumption records, sample basic information and corresponding matched sample consumption willingness portraits;
The matching calculation unit is used for calculating the policy matching degree between each preset marketing policy and the consumer wish portraits;
And the strategy determining unit is used for determining the target marketing strategy according to the preset marketing strategy with the highest strategy matching degree and executing the target marketing strategy.
A marketing strategy execution device comprising a memory and a processor;
the memory is used for storing programs;
the processor is configured to execute the program to implement the steps of the marketing strategy execution method according to any one of the above claims.
A readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the steps of the marketing strategy execution method of any of the preceding claims.
A computer program product comprising a computer program which, when run by a processor, performs the steps of the marketing strategy execution method as claimed in any one of the preceding claims.
According to the technical scheme, the marketing strategy execution method and the related equipment provided by the embodiment of the application are characterized in that firstly, the user historical consumption record and the user basic information are acquired, and the user consumption will portrait is generated by inputting the user historical consumption record and the user basic information into a consumption will analysis model which is trained in advance, wherein the consumption will portrait is obtained based on a large number of sample historical consumption records, sample basic information and corresponding matched sample consumption will portrait training. And then, respectively calculating the policy matching degree between each preset marketing policy and the consumer willingness portraits. Because the preset marketing strategy with the highest strategy matching degree is the marketing strategy which is most suitable for the user, the target marketing strategy determined by the preset marketing strategy with the highest strategy matching degree is determined, and the target marketing strategy is executed.
According to the application, through in-depth analysis of the user historical consumption record and the user basic information, the consumption will analysis model which is trained in advance is utilized, so that the user consumption will portrait can be accurately generated. The portrait not only comprehensively reflects the consumption preference, purchasing capability and behavior mode of the user, but also reflects the potential demands and future consumption trend of the user. And then, by calculating the strategy matching degree between each preset marketing strategy and the consumer willingness portraits of the users, the high fit between the selected marketing strategy and the demands of the users is ensured, so that the pertinence and the effectiveness of marketing activities are improved, and the marketing effect is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a marketing strategy execution method disclosed in an embodiment of the present application;
FIG. 2 is a schematic diagram of a consumer intent analysis model according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a marketing strategy execution device according to an embodiment of the present application;
Fig. 4 is a block diagram of a hardware structure of a marketing strategy execution device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The application is operational with numerous general purpose or special purpose computing device environments or configurations. Such as a personal computer, a server computer hand-held or portable device, a tablet device, a multiprocessor device, a distributed computing environment including any of the above devices or devices, and so forth.
The embodiment of the application provides a marketing strategy executing method which can be applied to a platform or application such as online consumption shopping, and can also be applied to various computer terminals or intelligent terminals, wherein an executing main body can be a processor or a server of the computer terminal or the intelligent terminal.
The following technical scheme is presented in the following description, and the specific reference is made to the following.
Fig. 1 is a flowchart of a marketing strategy execution method according to an embodiment of the present application.
As shown in fig. 1, the method may include:
and S1, acquiring a user history consumption record and user basic information.
Specifically, in determining a targeted marketing strategy, it is first necessary to obtain a user history consumption record and user basic information. The historical consumption records comprise detailed information such as the type, price, purchase frequency, time node and the like of the purchased goods, and can intuitively reflect the consumption preference and the purchase habit of the user. Meanwhile, basic information of the user is required to be acquired, the information is actively filled in by the user during registration, the information can be legally acquired by a platform, such as age, gender, occupation, residence and the like, the information is helpful for understanding consumer demands deeply, and firm data support is provided for the follow-up establishment of accurate and effective marketing strategies, so that accurate capture and efficient response to the user demands are realized.
And S2, inputting the historical consumption record of the user and the basic information of the user into a pre-trained consumption intention analysis model to generate a consumption intention portrait of the user.
Specifically, the consumption will analysis model is obtained based on a large number of sample historical consumption records, sample basic information and corresponding matched sample consumption will portrait training. In order to make the analysis model of the consumption will recognize more accurately, the sample data should cover a wide user population, the sample history consumption records comprise detailed consumption records such as purchase history, consumption habit, preference commodity category, etc., and the sample basic information comprises basic information such as age, gender, occupation, income, etc. By further analyzing and learning these sample data, the model is able to identify patterns, trends, and key factors affecting consumption decisions.
When the user's historical consumption record and user base information are entered into the trained consumer intent analysis model, the model parses and evaluates the information. This process includes in-depth analysis of the user's consumption behavior, as well as prediction of future consumer trends of the user. Through analysis and operation, the model can generate a user consumption willingness portrait, which not only details the current consumption preference of the user, but also predicts the future consumption tendency and potential demand of the user.
And S3, respectively calculating the policy matching degree between each preset marketing policy and the consumer wish portrait of the user.
Specifically, calculating the policy matching degree between each preset marketing policy and the consumer will portrait aims at ensuring that the selected marketing policy can fit the actual demands of the user, and realizing accurate marketing. Firstly, a series of marketing strategies can be preset manually, and the marketing strategies can cover different sales promotion modes, price strategies, commodity recommendation algorithms and the like, so that the demands of most users are basically covered, and the diversified demands of different user groups are met. And then, evaluating the matching condition of different marketing strategies and user requirements by calculating the matching degree between each preset marketing strategy and the user portrait one by one. Thereafter the system may filter out the adapted marketing strategy based on the strategy matching and execute the personalized marketing campaign accordingly.
The calculating of the policy matching degree between the preset marketing policy and the consumer will portrait may include:
① And calculating to obtain a first matching index value by evaluating the target user group coincidence degree between a preset marketing strategy and the user consumption willingness portraits.
Specifically, a first match index value is calculated by evaluating a target user population overlap ratio between a preset marketing strategy and a user consumer intent portrayal. The core of this step is to compare the degree of similarity or overlap between the target user population of the marketing strategy and the user population represented by the representation. If the two are highly coincident, the marketing strategy is likely to be attractive to the user, so that a higher first matching index value is obtained.
② And calculating a second matching index value by price sensitive matching of the preset marketing strategy user and the consumer wish portrait.
Specifically, a second matching index value is calculated by price sensitive matching of the user preset marketing strategy and the user consumer wish portraits. This step aims to analyze the sensitivity of the user to price variations and whether the price policies in the marketing strategy are consistent with the price expectations of the user. If the price offer or pricing strategy in the marketing strategy can accurately reach the price sensitive point of the user, the second matching index value will be higher.
③ And calculating to obtain a third matching index value by evaluating the marketing applicability of a preset marketing strategy to the consumer will portrait.
Specifically, the marketing suitability of the preset marketing strategy for the consumer will portrayal is evaluated to calculate a third match index value. This step involves taking into account aspects of the content, form, timing, etc. of the marketing strategy to ensure that they are compatible with the characteristics of the consumer preferences, buying habits, etc. in the user representation. If the marketing strategy is able to accurately capture and meet the potential needs of the user, the third match index value will be significantly improved.
④ And integrating the first matching index value, the second matching index value and the third matching index value, and combining preset index weights to calculate and obtain the strategy matching degree between a preset marketing strategy and the consumer wish portrait of the user.
Specifically, the first matching index value, the second matching index value and the third matching index value are integrated, and the preset index weights are combined to calculate the strategy matching degree between the preset marketing strategy and the consumer wish portrait of the user. The matching degree of each dimension can be integrated into a comprehensive index in a weighted average mode, so that the matching degree of the marketing strategy and the user requirement can be comprehensively reflected. The weight setting can be adjusted according to the marketing targets and the market environment of the enterprise, so that the calculation of the strategy matching degree is more reasonable.
And S4, determining a target marketing strategy according to the preset marketing strategy with the highest strategy matching degree, and executing the target marketing strategy.
Specifically, based on the policy matching degree between each preset marketing policy and the consumer will portrait obtained by previous calculation, the system can automatically identify and screen out the policy with the highest matching degree. This step ensures that the selected strategy is able to maximally meet the personalized needs and preferences of the user, thereby improving the pertinence and effectiveness of the marketing campaign.
Once the target marketing strategy is determined, the system will immediately initiate execution flow. This process may include a number of links, such as merchandise recommendations, coupon releases, promotional notifications, etc., depending on the type and content of the target policy. In the execution process, the system can ensure that all marketing messages can be presented in a mode which is most easily accepted and understood by users, such as channels of personalized mail, short message reminding, APP pushing and the like, so as to maximize the participation degree and conversion rate of the users.
Meanwhile, in order to monitor and evaluate the execution effect of the target marketing strategy, the system can collect and analyze feedback data of the user in real time, such as key indexes of click rate, conversion rate, user satisfaction and the like. The data not only can help enterprises to know the response and acceptance of users to marketing strategies in time, but also can provide important references for subsequent strategy optimization and adjustment.
In addition, in the process of formulating and executing the personalized marketing strategy, in order to keep the flexibility and the innovation of the marketing strategy, the application also supports the targeted construction of the marketing strategy, which is specifically as follows:
And if the highest strategy matching degree is smaller than the allowed strategy deviation value, carrying out marketing strategy construction based on the consumer willingness portraits.
Specifically, when the calculated highest policy matching degree is smaller than the preset allowable policy deviation value, this means that even the most matched preset marketing policy cannot reach the desired degree of compliance with the user demand. In this case, the system would in turn perform a completely new marketing strategy construction based on the consumer's wishlist portrayal. The process can fully utilize detailed information in the user portrait, including consumption preference, purchasing habit, potential requirement and the like of the user, and design a marketing strategy which is more fit for the personalized requirement of the user through data analysis and creative planning.
According to the technical scheme, the marketing strategy execution method and the related equipment provided by the embodiment of the application are characterized in that firstly, the user historical consumption record and the user basic information are acquired, and the user consumption will portrait is generated by inputting the user historical consumption record and the user basic information into a consumption will analysis model which is trained in advance, wherein the consumption will portrait is obtained based on a large number of sample historical consumption records, sample basic information and corresponding matched sample consumption will portrait training. And then, respectively calculating the policy matching degree between each preset marketing policy and the consumer willingness portraits. Because the preset marketing strategy with the highest strategy matching degree is the marketing strategy which is most suitable for the user, the target marketing strategy determined by the preset marketing strategy with the highest strategy matching degree is determined, and the target marketing strategy is executed.
According to the application, through in-depth analysis of the user historical consumption record and the user basic information, the consumption will analysis model which is trained in advance is utilized, so that the user consumption will portrait can be accurately generated. The portrait not only comprehensively reflects the consumption preference, purchasing capability and behavior mode of the user, but also reflects the potential demands and future consumption trend of the user. And then, by calculating the strategy matching degree between each preset marketing strategy and the consumer willingness portraits of the users, the high fit between the selected marketing strategy and the demands of the users is ensured, so that the pertinence and the effectiveness of marketing activities are improved, and the marketing effect is improved.
Fig. 2 is a schematic structural diagram of a consumer intent analysis model according to an embodiment of the present application.
In some embodiments of the application, the consumer intent analysis model is described in connection with FIG. 2.
As shown in FIG. 2, the willingness-to-consume analysis model may include, in particular, a data processing network 10, a willingness analysis network 20, and a representation construction network 30.
Data processing network 10:
the data processing network is used for carrying out data cleaning, format conversion and aggregation processing on the input user historical consumption record and the user basic information to obtain willingness analysis basic data.
Specifically, the data processing network serves as a starting point of the whole analysis flow and bears the preprocessing task of the historical consumption record and the basic information of the user. The network removes redundant and error information through data cleaning to ensure data quality, unifies data with different sources and different formats into an analyzable standard format through format conversion, and integrates scattered data into comprehensive analysis basic data through aggregation processing.
Willingness analysis network 20:
And the willingness analysis network analyzes the willingness analysis basic data by constructing a gradient decision tree, and determines a preference analysis result and a willingness prediction result.
Specifically, the willingness analysis network uses a gradient decision tree to conduct deep analysis on the processed basic data. Gradient decision trees are powerful classification and regression tools that automatically learn feature patterns in data and classify and predict consumer preferences based on those patterns. In the network, the gradient decision tree determines the preference analysis result of the user through analysis of basic data, and the analysis result comprises detailed descriptions of the types, brands, price intervals and the like of the favorite products of the user. At the same time, it predicts the consumer's willingness to consume, i.e. the purchasing behavior and consumption trend that the user may produce in a future period of time.
The willingness analysis network 20 further includes a feature extraction module 210, an association relationship module 220, an integrated analysis module 230, and a willingness prediction module 240.
The feature extraction module 210 is configured to perform feature extraction on the willingness analysis basic data, and generate basic information features, consumption behavior features and interest preference features.
The association module 220 determines feature association rules among the basic information features, the consumption behavior features and the interest preference features through an association rule mining algorithm;
The comprehensive analysis module 230 constructs a gradient decision tree and generates a preference analysis result by integrating the basic information feature, the consumption behavior feature, the interest preference feature and the feature association rule;
the willingness prediction module 240 predicts a user's future willingness to consume based on the gradient decision tree analysis, generating a willingness prediction result.
Specifically, the feature extraction module extracts feature information which is vital to consumer intent analysis of the user from the intent analysis basic data, wherein the feature information comprises basic information features, consumption behavior features and interest preference features. The association relation module uses an association rule mining algorithm to conduct deep analysis on basic information features, consumption behavior features and interest preference features to determine feature association rules among the basic information features, consumption behavior features and interest preference features, and the association rules reveal interactions and influences among user features. The comprehensive analysis module further integrates all key features and information on the basis of feature extraction and association relation analysis, and a gradient decision tree is constructed. The gradient decision tree is a powerful machine learning model which can automatically learn and generate decision paths according to the input characteristic data so as to realize accurate classification and prediction of consumer preference. In this module, the gradient decision tree generates detailed preference analysis results by analyzing the integrated feature data, which comprehensively reflect the consumer preferences and potential needs of the user. The willingness prediction module predicts the future consumption willingness of the user based on the analysis result of the gradient decision tree. The method utilizes the prediction capability of the gradient decision tree and combines the historical consumption behavior of the user and the current market environment to generate an accurate willingness prediction result. These predictions include not only information about the type of product, brand, price range, etc. that the user may purchase, but also reflect the user's possible consumption trends and purchasing behavior over a period of time in the future.
Wherein 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;
The basic information extraction layer 211 performs feature extraction on age data, gender data, geographic position data and income level data in the willingness analysis basic data to generate basic information features;
The consumption behavior extraction layer 212 analyzes the purchase quantity data, the purchase frequency data and the consumption amount data in the basic data according to the will to generate consumption behavior characteristics;
the interest preference extraction layer 213 analyzes browsing behavior data, searching behavior data, and social behavior data in the basic data according to the willingness to generate interest preference features.
Specifically, the basic information extraction layer is responsible for processing and analyzing user basic information in willing analysis basic data. It utilizes advanced data processing techniques and algorithms to extract key basic information features from age data, gender data, geographic location data, and revenue level data. The consumption behavior extraction layer is responsible for extracting consumption behavior characteristics from purchasing behavior data of a user. The purchasing habit, the consuming capacity and the consuming trend of the user can be known deeply by analyzing the purchasing quantity data, the purchasing frequency data and the consuming amount data. These consumption behavior features not only reflect the current consumption situation of the user, but also predict the user's future consumption potential and purchase intent. The interest preference extraction layer is responsible for extracting interest preference features from browsing behavior data, search behavior data and social behavior data of the user. By applying the techniques of natural language processing, text mining, social network analysis and the like, the user preference degree of specific products, brands or activities, and interest points and focus hot spots of the user can be accurately captured. These interest preference features are critical to understanding the personalized needs and potential willingness to consume of the user. The feature extraction module can comprehensively and efficiently extract key feature information required by consumer wish analysis through the cooperative work of the basic information extraction layer, the consumption behavior extraction layer and the interest preference extraction layer.
Portrayal construction network 30:
and the portrayal construction network constructs the consumer willingness portrayal based on the preference analysis result and the willingness prediction result.
Specifically, the portrayal construction network constructs the consumer willingness portrayal based on the preference analysis result and the willingness prediction result output by the willingness analysis network. The portrait is an intuitive display of the consumer will of the user, contains information of multiple aspects such as consumer preference, purchasing habit, potential requirement and the like of the user, can convert complex user data into consumer will portrait which is easy to understand and apply through a portrait construction network, and is an important basis for the subsequent marketing strategy formulation and personalized service provision.
The following describes a marketing strategy execution device provided by the embodiment of the present application, and the marketing strategy execution device described below and the marketing strategy execution method described above may be referred to correspondingly.
Referring to fig. 3, fig. 3 is a schematic diagram of a marketing strategy execution device according to an embodiment of the present application.
As shown in fig. 3, the marketing strategy executing apparatus may include:
an information acquisition unit A1 for acquiring a user history consumption record and user basic information;
The willingness portrait unit A2 is used for inputting the user historical consumption record and the user basic information into a pre-trained consumption willingness analysis model to generate a user consumption willingness portrait, wherein the consumption willingness analysis model is obtained by training based on a large number of sample historical consumption records, sample basic information and correspondingly matched sample consumption willingness portraits;
The matching calculation unit A3 is used for calculating the policy matching degree between each preset marketing policy and the consumer wish portraits;
And the strategy determining unit A4 is used for determining the target marketing strategy according to the preset marketing strategy with the highest strategy matching degree and executing the target marketing strategy.
According to the technical scheme, the marketing strategy execution method and the related equipment provided by the embodiment of the application are characterized in that firstly, the user historical consumption record and the user basic information are acquired, and the user consumption will portrait is generated by inputting the user historical consumption record and the user basic information into a consumption will analysis model which is trained in advance, wherein the consumption will portrait is obtained based on a large number of sample historical consumption records, sample basic information and corresponding matched sample consumption will portrait training. And then, respectively calculating the policy matching degree between each preset marketing policy and the consumer willingness portraits. Because the preset marketing strategy with the highest strategy matching degree is the marketing strategy which is most suitable for the user, the target marketing strategy determined by the preset marketing strategy with the highest strategy matching degree is determined, and the target marketing strategy is executed.
According to the application, through in-depth analysis of the user historical consumption record and the user basic information, the consumption will analysis model which is trained in advance is utilized, so that the user consumption will portrait can be accurately generated. The portrait not only comprehensively reflects the consumption preference, purchasing capability and behavior mode of the user, but also reflects the potential demands and future consumption trend of the user. And then, by calculating the strategy matching degree between each preset marketing strategy and the consumer willingness portraits of the users, the high fit between the selected marketing strategy and the demands of the users is ensured, so that the pertinence and the effectiveness of marketing activities are improved, and the marketing effect is improved.
Optionally, the consumer intention analysis model comprises a data processing network, an intention analysis network and a portrait construction network;
The data processing network is used for carrying out data cleaning, format conversion and aggregation processing on the input historical consumption records of the users and the basic information of the users to obtain willingness analysis basic data;
the willingness analysis network analyzes the willingness analysis basic data by constructing a gradient decision tree, and determines a preference analysis result and a willingness prediction result;
and the portrayal construction network constructs the consumer willingness portrayal based on the preference analysis result and the willingness prediction result.
Optionally, the willingness analysis network comprises a feature extraction module, an association relation module, a comprehensive analysis module and a willingness prediction module;
the feature extraction module is used for carrying out feature extraction on the willingness analysis basic data to generate basic information features, consumption behavior features and interest preference features;
The association relation module determines feature association rules among the basic information features, the consumption behavior features and the interest preference features through an association rule mining algorithm;
The comprehensive analysis module builds 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;
and the willingness prediction module predicts the future consumption willingness of the user based on the analysis of the gradient decision tree and generates a willingness prediction result.
Optionally, the feature extraction module comprises a basic information extraction layer, a consumption behavior extraction layer and an interest preference extraction layer;
the basic information extraction layer performs feature extraction on age data, gender data, geographic position data and income level data in the willingness analysis basic data to generate basic information features;
The consumption behavior extraction layer analyzes purchase quantity data, purchase frequency data and consumption amount data in the basic data according to the will to generate consumption behavior characteristics;
and the interest preference extraction layer analyzes browsing behavior data, searching behavior data and social behavior data in the basic data according to the will to generate interest preference characteristics.
Optionally, the matching calculation unit may include:
The first matching unit is used for calculating a first matching index value by evaluating the target user group coincidence degree between a preset marketing strategy and the user consumption willingness portraits;
The second matching unit is used for calculating a second matching index value by performing price sensitive matching on the preset marketing strategy user and the consumption willingness portraits;
The third matching unit is used for calculating a third matching index value by evaluating the marketing applicability of a preset marketing strategy to the consumer will portrait;
And the matching integration unit is used for integrating the first matching index value, the second matching index value and the third matching index value, combining preset index weights, and calculating to obtain the strategy matching degree between the preset marketing strategy and the consumer wish portrait of the user.
Optionally, the marketing strategy executing apparatus may further include:
and the strategy construction unit is used for constructing the marketing strategy based on the consumer willingness portrayal under the condition that the highest strategy matching degree is smaller than the allowed strategy deviation value.
The marketing strategy execution device provided by the embodiment of the application can be applied to marketing strategy execution equipment. Fig. 4 shows a block diagram of a hardware structure of a marketing strategy execution device, referring to fig. 4, which 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;
in the embodiment of the 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 complete the communication with each other through the communication bus 4;
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 embodiments of the present invention, etc.;
the memory 3 may comprise a high-speed RAM memory, and may further comprise a non-volatile memory (non-volatile memory) or the like, such as at least one magnetic disk memory;
wherein the memory stores a program, the processor is operable to invoke the program stored in the memory, the program operable to:
Acquiring a user history consumption record and user basic information;
Inputting the user historical consumption record and the user basic information into a pre-trained consumption intention analysis model to generate a user consumption intention portrait, wherein the consumption intention analysis model is obtained by training based on a large number of sample historical consumption records, sample basic information and corresponding matched sample consumption intention portraits;
respectively calculating the policy matching degree between each preset marketing policy and the consumer willingness portraits;
And determining a target marketing strategy according to the preset marketing strategy with the highest strategy matching degree, and executing the target marketing strategy.
Alternatively, the refinement function and the extension function of the program may be described with reference to the above.
The embodiment of the present application also provides a readable storage medium storing a program adapted to be executed by a processor, the program being configured to:
Acquiring a user history consumption record and user basic information;
Inputting the user historical consumption record and the user basic information into a pre-trained consumption intention analysis model to generate a user consumption intention portrait, wherein the consumption intention analysis model is obtained by training based on a large number of sample historical consumption records, sample basic information and corresponding matched sample consumption intention portraits;
respectively calculating the policy matching degree between each preset marketing policy and the consumer willingness portraits;
And determining a target marketing strategy according to the preset marketing strategy with the highest strategy matching degree, and executing the target marketing strategy.
Alternatively, the refinement function and the extension function of the program may be described with reference to the above.
The embodiment of the application also provides a computer program product, which comprises a computer program, wherein the execution method of the computer program when being executed by a processor is as follows:
Acquiring a user history consumption record and user basic information;
Inputting the user historical consumption record and the user basic information into a pre-trained consumption intention analysis model to generate a user consumption intention portrait, wherein the consumption intention analysis model is obtained by training based on a large number of sample historical consumption records, sample basic information and corresponding matched sample consumption intention portraits;
respectively calculating the policy matching degree between each preset marketing policy and the consumer willingness portraits;
And determining a target marketing strategy according to the preset marketing strategy with the highest strategy matching degree, and executing the target marketing strategy.
Alternatively, the refinement function and the extension function of the program may be described with reference to the above.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411741697.8A CN119558901A (en) | 2024-11-29 | 2024-11-29 | A marketing strategy execution method and related equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411741697.8A CN119558901A (en) | 2024-11-29 | 2024-11-29 | A marketing strategy execution method and related equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119558901A true CN119558901A (en) | 2025-03-04 |
Family
ID=94766456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411741697.8A Pending CN119558901A (en) | 2024-11-29 | 2024-11-29 | A marketing strategy execution method and related equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119558901A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120146893A (en) * | 2025-03-05 | 2025-06-13 | 北京正和思齐数据科技有限公司 | Marketing scenario intelligent training management method, device and storage medium |
-
2024
- 2024-11-29 CN CN202411741697.8A patent/CN119558901A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120146893A (en) * | 2025-03-05 | 2025-06-13 | 北京正和思齐数据科技有限公司 | Marketing scenario intelligent training management method, device and storage medium |
| CN120146893B (en) * | 2025-03-05 | 2025-09-19 | 北京正和思齐数据科技有限公司 | Marketing scene intelligent training management method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109741146B (en) | Product recommendation method, device, equipment and storage medium based on user behaviors | |
| US10430859B2 (en) | System and method of generating a recommendation of a product or service based on inferring a demographic characteristic of a customer | |
| CN113077317B (en) | Item recommendation method, device, equipment and storage medium based on user data | |
| Kim et al. | A deep hybrid learning model for customer repurchase behavior | |
| CN111400613A (en) | Article recommendation method, device, medium and computer equipment | |
| CN114168843A (en) | Search word recommendation method, device and storage medium | |
| WO2020221022A1 (en) | Service object recommendation method | |
| US10713704B2 (en) | System and method for generating output results based on computed relativity measures using relational memory | |
| WO2022151923A1 (en) | Method and apparatus for processing paperwork for goods, electronic device, medium, and program | |
| US20140279251A1 (en) | Search result ranking by brand | |
| US20230186328A1 (en) | Systems and methods for digital shelf display | |
| JP2017027359A (en) | Information processing apparatus, information processing method, and information processing program | |
| CN118710375B (en) | Prefabricated dish recommending method and system | |
| CN119558901A (en) | A marketing strategy execution method and related equipment | |
| WO2022156589A1 (en) | Method and device for determining live broadcast click rate | |
| US11348148B2 (en) | Systems and methods for an intelligent sourcing engine for study participants | |
| US10467654B2 (en) | Forecasting customer channel choice using cross-channel loyalty | |
| Guan et al. | From anticipation to action: Data reveal mobile shopping patterns during a yearly mega sale event in China | |
| CN119311958A (en) | User analysis method, device, equipment and medium based on big model | |
| Wei et al. | Online shopping behavior analysis for smart business using big data analytics and blockchain security | |
| CN110796520A (en) | Commodity recommendation method and device, computing equipment and medium | |
| CN119515507A (en) | A shopping guide strategy optimization method and device | |
| Kalia | Web surfers are web spenders: finding the truth of online shopping | |
| CN111241382A (en) | Data processing method and device, storage medium and electronic equipment | |
| Nurfatiasari et al. | A pilot study of technology adoption: An analysis of consumers' preference on future online grocery service |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |