Marketing strategy processing method and device based on customer data

Abstract

The invention provides a marketing strategy processing method and device based on customer data, and the method comprises the steps: building a corresponding multimedia content generation model based on a preset deep learning model, obtaining batch customer data and an image material library, and carrying out the processing of a marketing strategy based on the multimedia content generation model, the customer data and the image material library, generating a corresponding multimedia marketing material, obtaining a marketing strategy for the multimedia marketing material, pushing the multimedia marketing material to a target customer group based on the marketing strategy, constructing a corresponding target customer tendency model based on a preset machine learning algorithm and the customer data, and obtaining a purchase willingness of the target customer group based on the target customer tendency model, and adjusting a marketing strategy of the multimedia marketing material based on the purchase willingness of the target customer group.

Description

Technical Field

[0001] The present application relates to the field of deep learning technology, and more specifically, to a marketing strategy processing method and device based on customer data. Background Art

[0002] With the rapid development of Internet technology, the way companies interact with their customers has undergone profound changes. With diversified channels such as e-commerce, social media, and mobile applications, companies have accumulated unprecedented amounts of customer data, including basic information, transaction records, browsing behavior, social media interactions, and other multi-dimensional information. These data provide companies with valuable resources to gain a deep understanding of customer needs and predict market trends. However, how to efficiently use this data to achieve precision marketing and improve customer experience and satisfaction has become a major challenge facing companies.

[0003] At present, there are many marketing systems based on customer data on the market. Some advanced marketing systems build customer portrait systems by collecting and analyzing customer data. These systems use machine learning algorithms, such as logistic regression and decision trees, to model customer behavior patterns and thus predict customer purchasing tendencies.

[0004] However, most of these marketing systems rely on preset templates to generate marketing materials or manually upload pictures, videos, etc. to generate material libraries, which makes the multimedia content generation monotonous and lacks innovation. At the same time, customer behavior analysis is difficult to deeply explore customer behavior patterns, interest preferences and potential needs, which makes customer behavior analysis insufficient in depth, resulting in a lack of sufficient data support for marketing strategies and difficulty in accurately predicting customers' purchasing intentions. In addition, existing systems often adopt static marketing strategies, which make it difficult to respond to market changes and changes in customer needs in a timely manner, resulting in limited marketing effectiveness. Summary of the invention

[0005] In view of this, the purpose of the present application is to provide a marketing strategy processing method and device based on customer data, which generates multimedia marketing materials through multimedia content generation models, customer data and image materials, and pushes them according to marketing strategies, as well as constructing a target customer preference model based on customer data analysis to obtain the purchase intention of the target customer group, adjust the marketing strategy according to the purchase intention, reduce the dependence on preset templates or manually uploaded material libraries, improve the richness and innovation of multimedia content generation, realize in-depth mining of customer behavior analysis, and improve the depth of customer behavior analysis, thereby improving the accuracy of marketing strategies, and can more accurately predict customer purchase intentions. At the same time, the marketing strategy can be dynamically optimized in a timely manner to improve the marketing effect.

[0006] In a first aspect, an embodiment of the present application provides a marketing strategy processing method based on customer data, the method comprising:

[0007] Building a corresponding multimedia content generation model based on a preset deep learning model, acquiring batches of customer data and image material libraries, and generating corresponding multimedia marketing materials based on the multimedia content generation model, the customer data and the image material library;

[0008] Acquire a marketing strategy for the multimedia marketing material, and push the multimedia marketing material to a target customer group based on the marketing strategy;

[0009] A corresponding target customer tendency model is constructed based on a preset machine learning algorithm and the customer data, the purchase intention of the target customer group is obtained based on the target customer tendency model, and the marketing strategy of the multimedia marketing material is adjusted based on the purchase intention of the target customer group.

[0010] In a possible implementation manner, generating corresponding multimedia marketing materials based on the multimedia content generation model, the customer data, and the image material library includes:

[0011] Based on the multimedia content generation model, generating corresponding marketing material features according to the customer data and the image material library;

[0012] Generate corresponding multimedia marketing materials based on the marketing material features.

[0013] In a possible implementation, before generating corresponding multimedia marketing materials based on the marketing material features, the method further includes:

[0014] Acquire multimedia activity parameters input by a user; wherein the multimedia activity parameters at least include customer tags, marketing themes, and product features;

[0015] The multimedia activity parameters are analyzed, and the configuration parameters of the multimedia content generation model are dynamically adjusted based on the analysis results to obtain the adjusted multimedia content generation model.

[0016] In a possible implementation, the building of a corresponding target customer preference model based on a preset machine learning algorithm and the customer data includes:

[0017] Processing the customer data based on a preset data processing method to obtain processed customer data;

[0018] A basic customer propensity model is obtained, and the basic customer propensity model is trained based on the processed customer data and the machine learning algorithm to obtain a target customer propensity model.

[0019] In a possible implementation, the method further includes:

[0020] Based on the processed customer data and the target customer tendency model, corresponding multi-dimensional label information is obtained; wherein the multi-dimensional label information at least includes purchasing habits, interest preferences, and consumption capacity; the label information represents various categories of customer groups;

[0021] Based on the multi-dimensional label information and a preset optimization method, the model parameter configuration of the target customer propensity model is adjusted to obtain an adjusted target customer propensity model; wherein the optimization method includes cross-validation and hyperparameter tuning.

[0022] In a possible implementation, obtaining the purchase intention of the target customer group based on the target customer preference model includes:

[0023] Real-time capture and recording of the target customer group behavior data of the target customer group during the target marketing process; wherein the target marketing process at least includes browsing, clicking, and staying; the target customer group behavior data at least includes the staying time of pictures, videos, and texts, and the click and drag trajectory of the page;

[0024] Based on the target customer group behavior data and the target customer tendency model, the purchase intention of the target customer group is calculated.

[0025] In a possible implementation, the step of calculating the purchase intention of the target customer group based on the target customer group behavior data and the target customer tendency model includes:

[0026] Inputting the target customer group behavior data into the target customer tendency model for analysis to obtain customer characteristics and behavior patterns of the target customer group;

[0027] Based on the customer characteristics and behavior patterns of the target customer group, the purchase intention value of the target customer group is calculated.

[0028] In a second aspect, an embodiment of the present application further provides a marketing strategy processing device based on customer data, the device comprising:

[0029] A generation module, used to build a corresponding multimedia content generation model based on a preset deep learning model, obtain batches of customer data and image material libraries, and generate corresponding multimedia marketing materials based on the multimedia content generation model, the customer data and the image material library;

[0030] A push module, used to obtain a marketing strategy for the multimedia marketing material, and push the multimedia marketing material to a target customer group based on the marketing strategy;

[0031] The first adjustment module is used to build a corresponding target customer tendency model based on a preset machine learning algorithm and the customer data, obtain the purchase intention of the target customer group based on the target customer tendency model, and adjust the marketing strategy of the multimedia marketing material based on the purchase intention of the target customer group.

[0032] In a possible implementation manner, the generating module is specifically used to:

[0033] Based on the multimedia content generation model, generating corresponding marketing material features according to the customer data and the image material library;

[0034] Generate corresponding multimedia marketing materials based on the marketing material features.

[0035] In a possible implementation manner, the marketing strategy processing device based on customer data further includes:

[0036] A first acquisition module is used to acquire multimedia activity parameters input by a user before generating corresponding multimedia marketing materials based on the marketing material features; wherein the multimedia activity parameters at least include customer tags, marketing themes, and product characteristics;

[0037] The analysis module is used to analyze the multimedia activity parameters and dynamically adjust the configuration parameters of the multimedia content generation model based on the analysis results to obtain the adjusted multimedia content generation model.

[0038] In a possible implementation manner, the first adjustment module is specifically configured to:

[0039] Processing the customer data based on a preset data processing method to obtain processed customer data;

[0040] A basic customer propensity model is obtained, and the basic customer propensity model is trained based on the processed customer data and the machine learning algorithm to obtain a target customer propensity model.

[0041] In a possible implementation manner, the marketing strategy processing device based on customer data further includes:

[0042] A second acquisition module is used to obtain corresponding multi-dimensional label information based on the processed customer data and the target customer tendency model; wherein the multi-dimensional label information at least includes purchasing habits, interest preferences, and consumption capacity; and the label information represents various categories of customer groups;

[0043] The second adjustment module is used to adjust the model parameter configuration of the target customer propensity model based on the multi-dimensional label information and a preset optimization method to obtain an adjusted target customer propensity model; wherein the optimization method includes cross-validation and hyperparameter tuning.

[0044] In a possible implementation manner, the first adjustment module is specifically configured to:

[0045] Real-time capture and recording of the target customer group behavior data of the target customer group during the target marketing process; wherein the target marketing process at least includes browsing, clicking, and staying; the target customer group behavior data at least includes the staying time of pictures, videos, and texts, and the click and drag trajectory of the page;

[0046] Based on the target customer group behavior data and the target customer tendency model, the purchase intention of the target customer group is calculated.

[0047] In a possible implementation manner, the first adjustment module is specifically configured to:

[0048] Inputting the target customer group behavior data into the target customer tendency model for analysis to obtain customer characteristics and behavior patterns of the target customer group;

[0049] Based on the customer characteristics and behavior patterns of the target customer group, the purchase intention value of the target customer group is calculated.

[0050] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a storage medium and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the marketing strategy processing method based on customer data as described in any one of the first aspects.

[0051] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the marketing strategy processing method based on customer data as described in any one of the first aspects are executed.

[0052] The embodiment of the present application provides a method and device for processing marketing strategies based on customer data, which constructs a corresponding multimedia content generation model based on a preset deep learning model, obtains batches of customer data and image material libraries, and generates corresponding multimedia marketing materials based on the multimedia content generation model, customer data and image material libraries, obtains marketing strategies for multimedia marketing materials, and pushes multimedia marketing materials to target customer groups based on the marketing strategies, constructs corresponding target customer tendency models based on preset machine learning algorithms and customer data, obtains the purchase intention of the target customer group based on the target customer tendency model, and adjusts the marketing strategies of multimedia marketing materials based on the purchase intention of the target customer group. In the present application, multimedia marketing materials are generated through multimedia content generation models, customer data and image materials, and pushed according to marketing strategies, and the purchase intention of the target customer group is obtained based on the target customer tendency model constructed by analyzing customer data, and the marketing strategy is adjusted according to the purchase intention, which reduces the dependence on preset templates or manual uploading to generate material libraries, improves the richness and innovation of multimedia content generation, realizes in-depth mining of customer behavior analysis, improves the depth of customer behavior analysis, thereby improving the accuracy of marketing strategies, and can more accurately predict customer purchase intentions. At the same time, marketing strategies can be dynamically optimized in a timely manner, and marketing effects are improved.

[0053] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 is a flowchart of a marketing strategy processing method based on customer data according to an embodiment of the present application;

[0056] Figure 2 is a flowchart of a marketing strategy processing method based on customer data according to another embodiment of the present application;

[0057] Figure 3 is a flowchart of a marketing strategy processing method based on customer data according to another embodiment of the present application;

[0058] Figure 4 is a flowchart of a marketing strategy processing method based on customer data according to another embodiment of the present application;

[0059] Figure 5 is a structural diagram of a marketing strategy processing device based on customer data according to an embodiment of the present application;

[0060] Figure 6 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0061] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0062] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0063] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0064] With the rapid development of Internet technology, the way companies interact with their customers has undergone profound changes. With diversified channels such as e-commerce, social media, and mobile applications, companies have accumulated unprecedented amounts of customer data, including basic information, transaction records, browsing behavior, social media interactions, and other multi-dimensional information. These data provide companies with valuable resources to gain a deep understanding of customer needs and predict market trends. However, how to efficiently use this data to achieve precision marketing and improve customer experience and satisfaction has become a major challenge facing companies.

[0065] At present, there are many marketing systems based on customer data on the market. Some advanced marketing systems build customer portrait systems by collecting and analyzing customer data. These systems use machine learning algorithms, such as logistic regression and decision trees, to model customer behavior patterns and thus predict customer purchasing tendencies.

[0066] However, most of these marketing systems rely on preset templates to generate marketing materials or manually upload pictures, videos, etc. to generate material libraries, which makes the multimedia content generation monotonous and lacks innovation. At the same time, customer behavior analysis is difficult to deeply explore customer behavior patterns, interest preferences and potential needs, which makes customer behavior analysis insufficient in depth, resulting in a lack of sufficient data support for marketing strategies and difficulty in accurately predicting customers' purchasing intentions. In addition, existing systems often adopt static marketing strategies, which make it difficult to respond to market changes and changes in customer needs in a timely manner, resulting in limited marketing effectiveness.

[0067] To address this problem, the present application provides a method and device for processing a marketing strategy based on customer data, which generates multimedia marketing materials through a multimedia content generation model, customer data and image materials, and pushes them according to the marketing strategy, as well as constructing a target customer preference model based on customer data analysis to obtain the purchasing intention of the target customer group, and adjust the marketing strategy according to the purchasing intention, thereby reducing the reliance on preset templates or manually uploading to generate a material library, improving the richness and innovation of multimedia content generation, achieving in-depth mining of customer behavior analysis, and increasing the depth of customer behavior analysis, thereby improving the accuracy of marketing strategies, and being able to more accurately predict customer purchasing intentions. At the same time, the marketing strategy can be dynamically optimized in a timely manner to improve marketing effectiveness.

[0068] Figure 1 FIG. 1 is a flowchart of a marketing strategy processing method based on customer data according to an embodiment of the present application. Figure 1 As shown, the marketing strategy processing method based on customer data in the embodiment of the present application may specifically include:

[0069] S101. Build a corresponding multimedia content generation model based on a preset deep learning model, obtain batches of customer data and image material libraries, and generate corresponding multimedia marketing materials based on the multimedia content generation model, customer data and image material library.

[0070] S102: Obtain a marketing strategy for the multimedia marketing material, and push the multimedia marketing material to the target customer group based on the marketing strategy.

[0071] S103: construct a corresponding target customer propensity model based on a preset machine learning algorithm and customer data, obtain the purchase intention of the target customer group based on the target customer propensity model, and adjust the marketing strategy of the multimedia marketing material based on the purchase intention of the target customer group.

[0072] In the above-mentioned marketing strategy processing method based on customer data, multimedia marketing materials are generated through multimedia content generation models, customer data and image materials, and pushed according to the marketing strategy, and the purchase intention of the target customer group is obtained based on the target customer tendency model constructed by customer data analysis, and the marketing strategy is adjusted according to the purchase intention, which reduces the dependence on preset templates or manually uploaded material libraries, improves the richness and innovation of multimedia content generation, realizes in-depth mining of customer behavior analysis, and improves the depth of customer behavior analysis, thereby improving the accuracy of marketing strategies, and can more accurately predict customer purchase intentions. At the same time, the marketing strategy can be dynamically optimized in a timely manner to improve the marketing effect.

[0073] The above exemplary steps of the embodiment of the present application are described below with reference to specific examples:

[0074] S101, construct a corresponding multimedia content generation model based on a preset deep learning model, obtain batches of customer data and image material libraries, and generate corresponding multimedia marketing materials based on the multimedia content generation model, customer data and image material libraries.

[0075] In the embodiment of the present application, the deep learning model is a pre-set deep learning model, for example, a deep learning model such as a convolutional neural network (CNN) or a generative adversarial network (GAN), the multimedia content generation model is a model for generating multimedia content, that is, a multimedia content generation engine, the customer data is historical customer data, for example, a batch of historical customer data within a preset time, the image material library is a library including multiple image materials, the image material library includes multiple marketing materials that have been pushed, and the generated multimedia marketing materials are personalized, high-quality marketing materials; based on the preset deep learning model, a corresponding multimedia content generation model is constructed, a batch of customer data and an image material library are obtained, and based on the multimedia content generation model, the customer data and the image material library, the corresponding multimedia marketing materials are generated for subsequent processing. It should be noted that the multimedia content generation model generated by the present application is an efficient multimedia content generation engine.

[0076] S102, obtaining a marketing strategy for the multimedia marketing material, and pushing the multimedia marketing material to the target customer group based on the marketing strategy.

[0077] In the embodiment of the present application, the marketing strategy is a strategy for marketing multimedia marketing materials to customers. For the multimedia marketing materials generated in step S101, the marketing strategy corresponding to the multimedia marketing materials is determined, and the multimedia marketing materials are pushed to the target customer group based on the marketing strategy for subsequent processing.

[0078] S103, building a corresponding target customer propensity model based on a preset machine learning algorithm and customer data, obtaining the purchase intention of the target customer group based on the target customer propensity model, and adjusting the marketing strategy of the multimedia marketing material based on the purchase intention of the target customer group.

[0079] In the embodiment of the present application, the machine learning algorithm is a pre-set advanced machine learning algorithm, for example, a gradient boosting tree (GBDT), a neural network (NN) and other machine learning algorithms, and the target customer propensity model is a model for analyzing customer purchasing intention. The corresponding target customer propensity model is constructed according to the machine learning algorithm and the customer data in step S101, and the purchasing intention of the target customer group is obtained based on the target customer propensity model. The marketing strategy of the multimedia marketing material is adjusted based on the purchasing intention of the target customer group, so that the multimedia marketing material can be pushed to the target customer group according to the adjusted marketing strategy.

[0080] It should be noted that the marketing strategy of multimedia marketing materials can be adjusted based on the purchasing intention of the target customer group. This real-time feedback and dynamic adjustment mechanism ensures the targetedness and effectiveness of marketing activities, and improves marketing conversion rate and customer satisfaction.

[0081] The customer data-based marketing strategy processing method provided in the embodiment of the present application builds a corresponding multimedia content generation model based on a preset deep learning model, obtains batches of customer data and image material libraries, and generates corresponding multimedia marketing materials based on the multimedia content generation model, customer data and image material libraries, obtains marketing strategies for the multimedia marketing materials, and pushes the multimedia marketing materials to the target customer group based on the marketing strategies, builds a corresponding target customer propensity model based on the preset machine learning algorithm and customer data, obtains the purchase intention of the target customer group based on the target customer propensity model, and adjusts the marketing strategy of the multimedia marketing materials based on the purchase intention of the target customer group. The customer data-based marketing strategy processing method of the present application generates multimedia marketing materials through a multimedia content generation model, customer data and image materials, and pushes them according to the marketing strategy, and constructs a target customer tendency model based on customer data analysis to obtain the purchase intention of the target customer group, and adjusts the marketing strategy according to the purchase intention, thereby reducing the dependence on preset templates or manually uploading to generate a material library, improving the richness and innovation of multimedia content generation, achieving in-depth mining of customer behavior analysis, and improving the depth of customer behavior analysis, thereby improving the accuracy of marketing strategies, and can more accurately predict customer purchase intentions. At the same time, it can timely and dynamically optimize marketing strategies and improve marketing effects.

[0082] Further, such as Figure 2As shown, the step S102 in the above embodiment of “generating corresponding multimedia marketing materials based on the multimedia content generation model, customer data and image material library” may specifically include the following steps:

[0083] S201, based on the multimedia content generation model, corresponding marketing material features are generated according to customer data and image material library.

[0084] In the embodiments of the present application, the marketing material features are the features of the marketing material, and the marketing material features include at least style features, layout features and content features. Based on the multimedia content generation model obtained in the above embodiments, the corresponding marketing material features are generated according to the customer data and image material library in the above embodiments for subsequent processing.

[0085] S202: Generate corresponding multimedia marketing materials based on the marketing material features.

[0086] In the embodiment of the present application, the image material library includes high-quality marketing materials, and corresponding multimedia marketing materials are generated based on the marketing material features in step S201. It should be noted that the multimedia content generation model can automatically learn and imitate the style, layout and content features of high-quality marketing materials from the image material library based on massive historical customer data and the image material library to generate high-quality multimedia marketing materials.

[0087] It should also be noted that the multimedia content generation model includes configuration parameters. Before generating corresponding multimedia marketing materials based on the marketing material features, the multimedia activity parameters input by the user are obtained; the multimedia activity parameters are analyzed, and the configuration parameters of the multimedia content generation model are dynamically adjusted based on the analysis results to obtain the adjusted multimedia content generation model. Among them, the multimedia activity parameters include at least customer tags (age, gender, region, interest preferences, etc.), marketing themes, and product characteristics.

[0088] Therefore, by analyzing the multimedia activity parameters input by these users, the configuration parameters of the multimedia content generation model can be dynamically adjusted to ensure that the generated multimedia marketing materials not only meet the personalized needs of target customers, but also closely revolve around the marketing theme, thereby enhancing the attractiveness and relevance of the content. Figure 3 As shown, the “building a corresponding target customer propensity model based on a preset machine learning algorithm and customer data” in step S103 in the above embodiment may specifically include the following steps:

[0089] S301, processing customer data based on a preset data processing method to obtain processed customer data.

[0090] In the embodiment of the present application, the data processing method at least includes data cleaning, denoising, and feature extraction. The customer data is processed based on the data processing method to obtain processed customer data for subsequent processing.

[0091] Therefore, during the customer preference model training phase, the collected historical customer data undergoes strict preprocessing such as data cleaning, denoising, and feature extraction to ensure data quality.

[0092] S302, obtaining a basic customer propensity model, training the basic customer propensity model based on the processed customer data and a machine learning algorithm, and obtaining a target customer propensity model.

[0093] In the embodiment of the present application, the basic customer propensity model is the customer propensity model to be trained. The basic customer propensity model is trained based on the customer data processed in step S301 and the machine learning algorithm to obtain the target customer propensity model.

[0094] Therefore, the trained target customer preference model can not only accurately predict the customer's purchase intention, but also dynamically adjust and optimize according to changes in customer behavior and the evolution of market trends. This continuous optimization mechanism ensures that the model remains efficient and accurate in a complex and changing market environment.

[0095] Furthermore, based on the processed customer data and the target customer tendency model, corresponding multi-dimensional label information is obtained; based on the multi-dimensional label information and a preset optimization method, the model parameter configuration of the target customer tendency model is adjusted to obtain an adjusted target customer tendency model; wherein, the multi-dimensional label information at least includes purchasing habits, interest preferences, and consumption capacity; the label information represents various categories of customer groups; and the optimization methods include cross-validation and hyperparameter tuning.

[0096] Therefore, after preprocessing the data through data cleaning, denoising, feature extraction, etc., we use technical means such as cross-validation and hyperparameter tuning to continuously optimize the parameter configuration of the customer preference model and improve the model's prediction accuracy and generalization ability.

[0097] Further, such as Figure 4 As shown, the step S103 in the above embodiment of “obtaining the purchase intention of the target customer group based on the target customer tendency model” may specifically include the following steps:

[0098] S401, capturing and recording the target customer group behavior data during the target marketing process in real time.

[0099] In an embodiment of the present application, the target marketing process includes at least browsing, clicking, and staying, and the target customer group behavior data includes at least the stay time of pictures, videos, and texts, and the click and drag trajectory of the page. The target customer group behavior data during the target marketing process is captured and recorded in real time for subsequent processing.

[0100] S402, based on the target customer group behavior data and the target customer tendency model, the purchase intention of the target customer group is calculated.

[0101] In the embodiment of the present application, the purchase intention of the target customer group is calculated based on the target customer group behavior data obtained in step S401 and the target customer tendency model in the above embodiment.

[0102] It should be noted that the present application does not impose too many restrictions on the specific method of calculating the purchase intention based on the target customer group behavior data and the target customer tendency model, and it can be set according to actual conditions.

[0103] As a possible implementation method, the target customer group behavior data is input into the target customer propensity model for analysis to obtain the customer characteristics and behavior patterns of the target customer group; based on the customer characteristics and behavior patterns of the target customer group, the purchase intention value of the target customer group is calculated.

[0104] It should be noted that after obtaining the target customer group behavior data, these data are combined with the customer's label information and input into the target customer propensity model for analysis. The model uses the relationship between the learned customer characteristics and behavior patterns to calculate and output the target customer group's willingness to purchase products. This process achieves real-time and accurate prediction of customer purchase intentions, so that through purchase intentions, accurate delivery and continuous optimization of marketing strategies can be achieved.

[0105] Furthermore, the marketing strategy includes push timing. When adjusting the marketing strategy of the multimedia marketing material based on the purchase intention of the target customer group, the tag information of the target customer group is obtained; based on the purchase intention and tag information of the target customer group, the push timing of the multimedia marketing material and the material content of the multimedia marketing material are adjusted in real time.

[0106] Therefore, based on the analysis results of customer purchasing intention, marketing strategies and marketing content can be automatically adjusted. This real-time feedback and dynamic adjustment mechanism ensures the targetedness and effectiveness of marketing activities, and improves marketing conversion rate and customer satisfaction.

[0107] Specifically, in response to the problem that the existing technical solutions are single and lack personalized marketing materials, this application generates multimedia marketing materials through intelligent means. The system can provide highly personalized marketing content based on the unique characteristics and interest preferences of each customer. This personalization not only enhances the attractiveness and relevance of marketing information, but also significantly improves the efficiency and conversion rate of marketing activities. In view of the problem that existing customer behavior analysis models often remain at the surface level and are difficult to deeply explore customers' potential needs and purchasing intentions, this application uses advanced machine learning algorithms and feature engineering technologies to build a high-precision and high-generalization customer propensity model, which can more accurately predict customers' purchasing behavior and provide strong data support for precision marketing. At the same time, this application can capture and analyze customers' behavioral data in the marketing process in real time, and dynamically adjust and optimize marketing strategies accordingly. This real-time feedback and dynamic adjustment mechanism ensures the flexibility and effectiveness of marketing activities and improves market response speed.

[0108] In addition, by providing personalized marketing content and precise marketing strategies, the system can better meet customer needs and expectations, thereby improving customer satisfaction and loyalty. This customer-centric concept helps to build more solid and long-term customer relationships.

[0109] In general, this application realizes the automation and intelligence of the entire process from data collection, analysis, prediction to marketing strategy formulation, which not only reduces labor costs and time costs, but also improves the accuracy and efficiency of marketing decisions.

[0110] It should be noted that the marketing strategy processing method based on customer data of the present application is a multimedia marketing material processing method based on customer data, that is, a customer behavior analysis method based on customer data.

[0111] Figure 5 is a flowchart of a marketing strategy processing device based on customer data according to an embodiment of the present application. Figure 5 As shown, the marketing strategy processing device 500 based on customer data in the embodiment of the present application may specifically include:

[0112] The generation module 501 is used to build a corresponding multimedia content generation model based on a preset deep learning model, obtain batches of customer data and image material libraries, and generate corresponding multimedia marketing materials based on the multimedia content generation model, customer data and image material library;

[0113] The push module 502 is used to obtain a marketing strategy for the multimedia marketing material and push the multimedia marketing material to the target customer group based on the marketing strategy;

[0114] The first adjustment module 503 is used to build a corresponding target customer propensity model based on a preset machine learning algorithm and customer data, obtain the purchase intention of the target customer group based on the target customer propensity model, and adjust the marketing strategy of the multimedia marketing material based on the purchase intention of the target customer group.

[0115] In a possible implementation, the generating module is specifically used for:

[0116] Based on the multimedia content generation model, corresponding marketing material features are generated according to customer data and image material library;

[0117] Generate corresponding multimedia marketing materials based on the characteristics of marketing materials.

[0118] In a possible implementation, the marketing strategy processing device based on customer data further includes:

[0119] The first acquisition module is used to acquire multimedia activity parameters input by the user before generating corresponding multimedia marketing materials based on the marketing material features; wherein the multimedia activity parameters at least include customer tags, marketing themes, and product characteristics;

[0120] The analysis module is used to analyze the multimedia activity parameters and dynamically adjust the configuration parameters of the multimedia content generation model based on the analysis results to obtain the adjusted multimedia content generation model.

[0121] In a possible implementation manner, the first adjustment module is specifically configured to:

[0122] Processing the customer data based on a preset data processing method to obtain processed customer data;

[0123] Obtain a basic customer propensity model, train the basic customer propensity model based on the processed customer data and machine learning algorithm, and obtain a target customer propensity model.

[0124] In a possible implementation, the marketing strategy processing device based on customer data further includes:

[0125] The second acquisition module is used to obtain corresponding multi-dimensional label information based on the processed customer data and the target customer tendency model; wherein the multi-dimensional label information at least includes purchasing habits, interest preferences, and consumption capacity; the label information represents various categories of customer groups;

[0126] The second adjustment module is used to adjust the model parameter configuration of the target customer propensity model based on multi-dimensional label information and a preset optimization method to obtain an adjusted target customer propensity model; wherein the optimization method includes cross-validation and hyperparameter tuning.

[0127] In a possible implementation manner, the first adjustment module is specifically configured to:

[0128] Real-time capture and record the target customer group behavior data during the target marketing process; the target marketing process at least includes browsing, clicking, and staying; the target customer group behavior data at least includes the stay time of pictures, videos, and texts, and the click and drag trajectory of the page;

[0129] Based on the target customer group behavior data and the target customer tendency model, the purchase intention of the target customer group is calculated.

[0130] In a possible implementation manner, the first adjustment module is specifically configured to:

[0131] Input the target customer group behavior data into the target customer propensity model for analysis to obtain the customer characteristics and behavior patterns of the target customer group;

[0132] Based on the customer characteristics and behavior patterns of the target customer group, the purchase intention value of the target customer group is calculated.

[0133] The marketing strategy processing device based on customer data provided in the embodiment of the present application builds a corresponding multimedia content generation model based on a preset deep learning model, obtains batches of customer data and image material libraries, and generates corresponding multimedia marketing materials based on the multimedia content generation model, customer data and image material libraries, obtains marketing strategies for the multimedia marketing materials, and pushes the multimedia marketing materials to the target customer group based on the marketing strategies, builds a corresponding target customer propensity model based on the preset machine learning algorithm and customer data, obtains the purchase intention of the target customer group based on the target customer propensity model, and adjusts the marketing strategy of the multimedia marketing materials based on the purchase intention of the target customer group. The customer data-based marketing strategy processing device of the present application generates multimedia marketing materials through multimedia content generation models, customer data and image materials, pushes them according to the marketing strategy, and obtains the purchasing intention of the target customer group based on the target customer tendency model constructed by customer data analysis, and adjusts the marketing strategy according to the purchasing intention, thereby reducing the dependence on preset templates or manually uploading to generate a material library, improving the richness and innovation of multimedia content generation, realizing in-depth mining of customer behavior analysis, and improving the depth of customer behavior analysis, thereby improving the accuracy of marketing strategies, and can more accurately predict customer purchasing intentions. At the same time, it can timely and dynamically optimize marketing strategies and improve marketing effects.

[0134] like Figure 6As shown, an electronic device 600 provided in an embodiment of the present application includes: a processor 601, a memory 602 and a bus, wherein the memory 602 stores machine-readable instructions executable by the processor 601. When the electronic device is running, the processor 601 communicates with the memory 602 through the bus, and the processor 601 executes the machine-readable instructions to perform the steps of the marketing strategy processing method based on customer data as described above.

[0135] Specifically, the above-mentioned memory 602 and processor 601 can be general-purpose memories and processors, which are not specifically limited here. When the processor 601 runs the computer program stored in the memory 602, it can execute the above-mentioned marketing strategy processing method based on customer data.

[0136] Corresponding to the above-mentioned marketing strategy processing method based on customer data, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned marketing strategy processing method based on customer data are executed.

[0137] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0138] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, each functional unit in each embodiment of the present application may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0139] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the deployment method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0140] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A marketing strategy processing method based on customer data, characterized in that: The method comprises: Building a corresponding multimedia content generation model based on a preset deep learning model, acquiring batches of customer data and image material libraries, and generating corresponding multimedia marketing materials based on the multimedia content generation model, the customer data and the image material library; Acquire a marketing strategy for the multimedia marketing material, and push the multimedia marketing material to a target customer group based on the marketing strategy; A corresponding target customer tendency model is constructed based on a preset machine learning algorithm and the customer data, the purchase intention of the target customer group is obtained based on the target customer tendency model, and the marketing strategy of the multimedia marketing material is adjusted based on the purchase intention of the target customer group.

2. The method according to claim 1, characterized in that The generating corresponding multimedia marketing materials based on the multimedia content generation model, the customer data and the image material library includes: Based on the multimedia content generation model, generating corresponding marketing material features according to the customer data and the image material library; Generate corresponding multimedia marketing materials based on the marketing material features.

3. The method according to claim 2, characterized in that Before generating corresponding multimedia marketing materials based on the marketing material features, the method further includes: Acquire multimedia activity parameters input by a user; wherein the multimedia activity parameters at least include customer tags, marketing themes, and product features; The multimedia activity parameters are analyzed, and the configuration parameters of the multimedia content generation model are dynamically adjusted based on the analysis results to obtain the adjusted multimedia content generation model.

4. The method according to claim 1, characterized in that: The constructing of a corresponding target customer preference model based on a preset machine learning algorithm and the customer data includes: Processing the customer data based on a preset data processing method to obtain processed customer data; A basic customer propensity model is obtained, and the basic customer propensity model is trained based on the processed customer data and the machine learning algorithm to obtain a target customer propensity model.

5. The method according to claim 4, characterized in that The method further comprises: Based on the processed customer data and the target customer tendency model, corresponding multi-dimensional label information is obtained; wherein the multi-dimensional label information at least includes purchasing habits, interest preferences, and consumption capacity; the label information represents various categories of customer groups; Based on the multi-dimensional label information and a preset optimization method, the model parameter configuration of the target customer propensity model is adjusted to obtain an adjusted target customer propensity model; wherein the optimization method includes cross-validation and hyperparameter tuning.

6. The method according to claim 1, characterized in that The step of obtaining the purchase intention of the target customer group based on the target customer tendency model includes: Real-time capture and recording of the target customer group behavior data of the target customer group during the target marketing process; wherein the target marketing process at least includes browsing, clicking, and staying; the target customer group behavior data at least includes the staying time of pictures, videos, and texts, and the click and drag trajectory of the page; Based on the target customer group behavior data and the target customer tendency model, the purchase intention of the target customer group is calculated.

7. The method according to claim 1, characterized in that The step of calculating the purchase intention of the target customer group based on the target customer group behavior data and the target customer tendency model includes: Inputting the target customer group behavior data into the target customer tendency model for analysis to obtain customer characteristics and behavior patterns of the target customer group; Based on the customer characteristics and behavior patterns of the target customer group, the purchase intention value of the target customer group is calculated.

8. A marketing strategy processing device based on customer data, characterized in that: The device comprises: A generation module, used to build a corresponding multimedia content generation model based on a preset deep learning model, obtain batches of customer data and image material libraries, and generate corresponding multimedia marketing materials based on the multimedia content generation model, the customer data and the image material library; A push module, used to obtain a marketing strategy for the multimedia marketing material, and push the multimedia marketing material to a target customer group based on the marketing strategy; The first adjustment module is used to build a corresponding target customer tendency model based on a preset machine learning algorithm and the customer data, obtain the purchase intention of the target customer group based on the target customer tendency model, and adjust the marketing strategy of the multimedia marketing material based on the purchase intention of the target customer group.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the marketing strategy processing method based on customer data as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the marketing strategy processing method based on customer data as described in any one of claims 1 to 7.

Images