An automatic marketing strategy generation system based on intelligent services

Abstract

The application discloses an automatic marketing strategy generation system based on intelligent service, and relates to the technical field of intelligent marketing.The system comprises a basic template layer, a dynamic adaptation layer, a creative generation layer and a multi-target strategy selection layer.A hierarchical strategy engine is constructed by the basic template layer, the dynamic adaptation layer, the creative generation layer and the multi-target strategy selection layer, thereby breaking through the single strategy generation mode of a traditional fixed template.The basic template layer utilizes an industry marketing knowledge base to provide a standardized strategy generation starting point.The dynamic adaptation layer accesses multi-source heterogeneous data in real time and dynamically corrects strategy parameters, and can quickly respond to market changes.The creative generation layer automatically generates personalized marketing content by means of a multi-modal generation technology.This dynamic layered architecture forms a gradient strategy generation mode from the construction of a basic framework to the real-time parameter adjustment and then to the creative content output, thereby providing a brand-new technical path for marketing strategy generation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent marketing, in particular to an automatic marketing strategy generation system based on intelligent services. BACKGROUND

[0002] In today's competitive business environment, the formulation of marketing strategies plays a crucial role in the survival and development of enterprises. With the rapid development of information technology and the continuous evolution of consumer markets, traditional marketing strategies have become difficult to meet the increasingly complex business needs of enterprises. Enterprises need to dynamically adjust marketing strategies based on real-time market data and consumer behavior to achieve multi-objective balance, such as improving sales, expanding brand awareness, and enhancing user satisfaction, in order to adapt to the rapid changes in the market environment and maintain a competitive advantage. This demand has prompted the urgent need for more intelligent and automated marketing strategy generation systems.

[0003] Currently, the existing related patent technologies have significant shortcomings in strategy generation and evaluation. For example, the classification CN119762145A provides a marketing strategy generation method and system based on big data, which mainly focuses on data collection and simple analysis, but lacks dynamic correction and real-time adaptation functions. It only uses market data and user information to generate fixed strategies, which lacks flexibility in the face of market fluctuations and changes in consumer preferences. The creative content generated is often isolated and not organically integrated with the overall marketing strategy, nor has it undergone rigorous multi-objective optimization evaluation, making it difficult to ensure balanced development of marketing activities in multiple key indicators.

[0004] In summary, the technical bottlenecks of current automatic marketing strategy generation systems are concentrated in the rigid strategy generation mode, the lack of gradient coverage from standardization to personalization, and the inability to meet the diversified marketing needs of enterprises and adapt to differentiated market competition. Therefore, there is an urgent need to build a more adaptive and competitive automatic marketing strategy generation scheme. SUMMARY

[0005] The present application aims to overcome the shortcomings of the prior art and provides an automatic marketing strategy generation system based on intelligent services. It breaks through the single strategy generation mode of traditional fixed templates by constructing a hierarchical strategy engine with a basic template layer, a dynamic adaptation layer, a creative generation layer, and a multi-objective strategy selection layer. The basic template layer uses an industry marketing knowledge base to provide a standardized strategy generation starting point. The dynamic adaptation layer accesses multiple heterogeneous data sources in real time and implements dynamic correction of strategy parameters through differential evolution, enabling rapid response to market changes. The creative generation layer automatically generates personalized marketing content with the help of multi-modal generation technology. This dynamic layered architecture forms a gradient strategy generation mode from basic framework construction to real-time parameter adjustment to creative content output, providing a new technical path and architectural paradigm for marketing strategy generation.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an automatic marketing strategy generation system based on intelligent services, the system comprising: a basic template layer, a dynamic adaptation layer, a creative generation layer, and a multi-objective strategy selection layer;

[0007] The basic template layer collects and organizes general strategy frameworks for various marketing activities in the industry, classifies and labels the collected strategy frameworks, and establishes a basic template library. When the system receives a marketing task, the basic template layer matches and extracts the corresponding general strategy framework from the basic template library based on the basic information of the marketing task, providing a basic framework for strategy generation.

[0008] The dynamic adaptation layer collects multi-source heterogeneous data in real time, including market data, user data, and enterprise data. It analyzes the collected real-time data, explores the patterns of change in the data, and dynamically corrects the parameters in the general strategy framework provided by the basic template layer based on the data analysis results.

[0009] The creative generation layer uses natural language processing and image generation technology to generate personalized marketing strategies based on the strategy parameters adjusted by the dynamic adaptation layer.

[0010] The multi-objective strategy selection layer is used to set multiple marketing objectives and corresponding weights, and inputs the personalized marketing strategies generated by the creative generation layer into the multi-objective optimization algorithm for comprehensive evaluation and ranking, and outputs the optimal marketing strategy combination.

[0011] Furthermore, the basic template layer includes a strategy framework collection module, a framework classification and annotation module, and a framework matching and extraction module;

[0012] The strategy framework collection module is used to collect and organize the general strategy frameworks for various marketing activities in the industry, including promotional activity strategies, advertising strategies, membership marketing strategies, course sales strategies, and information delivery strategies.

[0013] The framework classification and labeling module classifies and labels the collected general strategy frameworks, and builds multi-dimensional configurable strategy parameters for each strategy framework, including discount level, activity period, and applicable customer group, and establishes a basic template library.

[0014] The framework matching and extraction module is used to match and extract corresponding general strategy frameworks from the basic template library based on the basic information of the marketing task, including industry type, marketing objectives, and product characteristics, as a benchmark for generating personalized marketing strategies.

[0015] Furthermore, the dynamic adaptation layer includes a data acquisition module, a data analysis module, and a parameter correction module;

[0016] The data acquisition module is used to collect multi-source heterogeneous data from the market, users, and enterprises in real time. The market data includes industry trends and market size, the user data includes user behavior data, user profiles, and user feedback, and the enterprise data includes product inventory, sales data, and marketing budget.

[0017] The data analysis module analyzes the collected real-time data and uncovers patterns of change within the data.

[0018] The parameter correction module is used to dynamically correct the parameters in the general strategy framework provided by the basic template layer based on the data analysis results.

[0019] Furthermore, the data analysis module cleans and normalizes the raw data acquired by the data acquisition module, and then processes it according to preset weights. Normalized data By integrating these elements, a multi-dimensional vector comprehensively reflecting the market situation is obtained. and ,in, For the first Normalized vectors of class data, As data type weights, based on the fused data, within a time window T, trend features and fluctuation features are extracted to measure the data's changing patterns. The trend features... The fluctuation characteristics are used to calculate the trend of data changes over time. Used to measure the degree of dispersion of data. For the first Fusion feature values ​​at time step , The mean of time and features;

[0020] The parameter correction module is based on the fusion features output by the data analysis module. Trend and Fluctuation parameters are used to modify the configurable strategy parameters of the basic template layer, with the modification based on a comprehensive marketing effectiveness index. To optimize the objective, calculate the current policy parameters. right sensitivity Used to reflect adjustments The degree of impact on the overall effect is determined by combining trend and volatility characteristics, and configurable strategy parameters are adjusted using an adaptive step size. ,in, For the updated policy parameters, Indicates the first One parameter and , It is the total number of strategy parameters. It is the learning rate, with a value between 0.1 and 0.3, controlling the range of parameter adjustment. The larger the value, the more pronounced the parameter change. It is the trend response coefficient; when the data shows an upward trend... During a downward trend This is used to ensure that the direction of parameter adjustment aligns with the data trend. It is a trend characteristic. It is a fluctuation characteristic, when When the data fluctuates greatly, it indicates that the value should be increased. To make more aggressive parameter adjustments, when When the data fluctuation is small, reduce it. Conservatively adjust the parameters, the C represents conversion rate, which is the percentage of users who complete the target behavior of purchasing or registering out of the total number of visitors; R represents return on investment, which is the ratio of marketing revenue to cost, measuring the profitability of marketing investment; and U represents user complaint rate, which indicates the percentage of users who file a complaint among the total number of users. The target weights are input from the marketing objective setting module of the multi-objective strategy selection layer, reflecting the company's emphasis on different objectives. The updated strategy parameters will then be used to determine the target weights. Feedback is sent to the data analysis module to analyze data trends and fluctuations in the next time window, and to dynamically optimize marketing strategy parameters.

[0021] Furthermore, the creative generation layer includes a text generation module, a multimedia material generation module, and a content fusion and optimization module;

[0022] The text generation module is used to combine natural language processing technology to generate personalized marketing copy based on the strategy parameters corrected by the dynamic adaptation layer and the characteristics of the target audience.

[0023] The multimedia material generation module uses image generation technology to generate multimedia marketing materials, including images and videos, that match the marketing theme and the preferences of the target audience.

[0024] The content fusion and optimization module is used to fuse and optimize the generated multimodal content of text, images, and videos to form a complete personalized marketing strategy with multiple marketing contents.

[0025] Furthermore, the text generation module creates targeted text content based on the language habits and interests of different target audiences. The steps are as follows:

[0026] Parameter parsing and audience analysis: The strategy parameters after the dynamic adaptation layer are parsed to extract key information, including product features, marketing goals, and promotional efforts. At the same time, combined with the target audience information of the user profile, the characteristics of the target audience, such as age, gender, region, consumption habits, and interests, are analyzed. Semantic analysis of the target audience is also performed using natural language processing technology.

[0027] Copywriting template selection and adaptation: Based on strategy parameters and target audience characteristics, select a copywriting template from a pre-set copywriting template library. The copywriting template library contains various types of marketing copywriting templates, including product promotion copywriting, promotional activity copywriting, and brand promotion copywriting. Fill the copywriting template with the specific information in the strategy parameters and adapt the expression style of the copywriting to make it conform to the language style of the target audience.

[0028] Copy generation and optimization: Further optimize and generate the adapted copy, learn from historical text data, and optimize the generated copy from three dimensions: grammatical accuracy, semantic coherence, and marketing appeal;

[0029] The multimedia material generation module uses a Generative Adversarial Network (GAN) algorithm to generate images and videos. The GAN consists of a generator and a discriminator. The generator is responsible for generating realistic images, and the discriminator is responsible for determining the authenticity of the generated images. The steps are as follows:

[0030] Input condition setting: Based on the marketing theme and target audience preferences, set the input conditions for image generation, including product appearance features, scene style, and color preferences;

[0031] Image generation by the generator: The generator generates a preliminary image based on the input conditions using a neural network model. The generator learns from image data to generate an image that meets the input conditions.

[0032] Discriminator evaluation and feedback: The discriminator evaluates the image generated by the generator to determine its authenticity. When the discriminator considers the image to be unrealistic, it sends feedback information to the generator. The generator adjusts its generation strategy based on the feedback information and regenerates the image.

[0033] Iterative optimization: Repeat the generation and evaluation process until the discriminator can no longer evaluate the generated image; at this point, the generated image is the marketing image.

[0034] Furthermore, the multi-objective strategy selection layer includes a marketing objective setting module, an evaluation indicator construction module, a multi-objective optimization application module, and a strategy ranking and selection module;

[0035] The marketing goal setting module is used to preset multiple marketing goals based on the company's marketing strategy and actual needs, and supports dynamically expanding goal types to generate goal sets. ,in, Indicates the first One marketing goal, Assign normalized weights to each target ,satisfy ,in, Characterization target Priority in corporate marketing strategy;

[0036] The evaluation index construction module is used to construct corresponding strategy evaluation indicators for each preset marketing objective, forming... Dimensional evaluation index matrix ,in, Indicates the first One goal The next Each sub-indicator For each sub-metric Allocator weights ,satisfy This is used to quantify the contribution of the indicator to its respective objective;

[0037] The multi-objective optimization application module uses a multi-objective optimization algorithm to comprehensively evaluate the various marketing strategies generated and calculate the comprehensive fitness score.

[0038] The strategy ranking and selection module is used to rank the generated marketing strategies based on the evaluation results of the multi-objective optimization algorithm, and generate a strategy priority list.

[0039] Furthermore, the multi-objective optimization application module uses a multi-objective optimization algorithm to optimize the output of the creative generation layer. Personalized marketing strategies are expressed as Each strategy corresponds to a standardized index vector. ,in Representation strategy In the Under the first goal The normalized scores of each indicator are used to calculate the overall fitness score. , For strategy The overall score, For the goal The weight, As an indicator Sub-weights.

[0040] Compared with existing technologies, this automated marketing strategy generation system based on intelligent services has the following advantages:

[0041] I. The automatic marketing strategy generation system of this invention can significantly improve the accuracy and targeting of marketing strategies. Through a multi-objective strategy selection layer, multiple marketing objectives are quantified, evaluated, and screened. The system can comprehensively consider multiple factors such as sales growth and user satisfaction improvement, avoiding the limitations of focusing on only a single objective in the marketing strategy formulation process. At the same time, combined with a dynamic adaptation layer and a creative generation layer, the system can generate personalized marketing copy, images, and videos in multimodal content based on the characteristics of the target audience and changes in the market environment, making marketing information more in line with the needs and preferences of the target audience. This precise marketing strategy can improve the conversion rate of marketing activities, reduce marketing costs, and bring higher return on investment to enterprises.

[0042] Second, this invention breaks through the traditional single-strategy generation mode of fixed templates by constructing a hierarchical strategy engine consisting of a basic template layer, a dynamic adaptation layer, a creative generation layer, and a multi-objective strategy selection layer. The basic template layer utilizes an industry marketing knowledge base to provide a standardized starting point for strategy generation. The dynamic adaptation layer accesses multi-source heterogeneous data in real time and achieves dynamic correction of strategy parameters through differential evolution, enabling rapid response to market changes. The creative generation layer uses multimodal generation technology to automatically generate personalized marketing content. This dynamic layered architecture, from the construction of the basic framework to the adjustment of real-time parameters and the output of creative content, forms a gradient strategy generation mode, providing a brand-new technical path and architectural paradigm for marketing strategy generation.

[0043] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0045] Figure 1 A flowchart illustrating the operation of an automated marketing strategy generation system based on intelligent services;

[0046] Figure 2 This is a schematic diagram of the components of an automated marketing strategy generation system based on intelligent services. Detailed Implementation

[0047] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0048] Example 1: This example uses the marketing and promotion of the "Digital Operations Specialist" new professional course on a vocational skills training platform to illustrate in detail the working principle of an automated marketing strategy generation system based on intelligent services. Figure 2 As shown, the system comprises a basic template layer, a dynamic adaptation layer, a creative generation layer, and a multi-objective strategy selection layer. The basic template layer constructs a general industry strategy framework; the dynamic adaptation layer collects and analyzes training market data, user characteristics, and enterprise resources in real time; the creative generation layer generates personalized multimodal marketing content; and the multi-objective strategy selection layer enables multi-dimensional strategy evaluation and optimization. This demonstrates the system's ability to generate dynamic and precise strategies from standardized templates in the vocational education field, verifying its effectiveness in improving course enrollment rates, brand awareness, and user satisfaction, and providing a practical model for intelligent marketing in the vocational skills training industry.

[0049] The basic template layer collects and organizes general strategy frameworks for various marketing activities within the industry. It categorizes and labels these frameworks to establish a basic template library. When the system receives a marketing task, the basic template layer matches and extracts the corresponding general strategy framework from the library based on the task's basic information, providing a foundational framework for strategy generation. This includes a strategy framework collection module, a framework classification and labeling module, and a framework matching and extraction module. Through a vocational skills training platform, a "Digital Operations Specialist" course is planned. This course covers core skills such as e-commerce operations, data analysis, and new media marketing, targeting recent graduates and career changers. The strategy framework collection module of the basic template layer collects general strategy frameworks in the vocational skills training field through industry reports, competitor research, and vocational education interviews. These frameworks include: course promotion strategies (e.g., trial classes for lead generation, limited-time offers, referral programs); advertising strategies (e.g., vertical recruitment platform advertising, industry community promotion, KOL (industry blogger / lecturer) collaboration); and membership marketing strategies. The learning system includes a points system, VIP exclusive Q&A, and course bundle discounts; information dissemination strategies include: industry trend white paper releases, free open class live streams, and sharing of student success stories; the framework classification and labeling module categorizes the collected strategy frameworks into three types based on marketing objectives: "course traffic acquisition," "conversion rate improvement," and "user retention and repeat purchase," and configures adjustable parameters for each framework. This example uses the "experience class traffic generation strategy framework" as an example, labeling the applicable customer group (potential users interested in digital operations but without experience), activity cycle, experience class duration, price, and supporting services (free material package, instructor Q&A). After labeling, a basic template library containing strategy frameworks is established, with each framework accompanied by a parameter description document; the framework matching and extraction module filters based on the training task templates. When the platform inputs marketing task information such as: industry type, marketing objective, and product characteristics, the framework matching and extraction module uses keyword matching and semantic analysis to select the core framework from the template library as the basis for generating personalized marketing strategies.

[0050] The dynamic adaptation layer collects multi-source heterogeneous data in real time, including market data, user data, and enterprise data. It analyzes the collected real-time data to uncover patterns of change. Based on the data analysis results, it dynamically adjusts the parameters in the general strategy framework provided by the basic template layer. This includes a data collection module, a data analysis module, and a parameter adjustment module. The data collection module captures three types of data in real time: market data (professional training industry trends, competitor course pricing, and career change dynamics); user data (target audience behavior data, user profiles, and user feedback); and enterprise data (platform teacher resources, course development progress, and marketing budget). The data is integrated into the data platform through API interfaces, enterprise CRM systems, and manual entry. The data analysis module cleans and normalizes the raw data acquired by the data collection module, and then applies preset weights. Normalized data By integrating these elements, a multi-dimensional vector comprehensively reflecting the market situation is obtained. and ,in, For the first Normalized vectors of class data, As data type weights, based on the fused data, within a time window T, trend features and fluctuation features are extracted to measure the data's changing patterns. The trend features... The fluctuation characteristics are used to calculate the trend of data changes over time. Used to measure the degree of dispersion of data. For the first Fusion feature values ​​at time step , The mean of time and features; the parameter correction module is based on the fused features output by the data analysis module. Trend and Fluctuation parameters are used to modify the configurable strategy parameters of the basic template layer, with the modification based on a comprehensive marketing effectiveness index. To optimize the objective, calculate the current policy parameters. right sensitivity Used to reflect adjustments The degree of impact on the overall effect is determined by combining trend and volatility characteristics, and configurable strategy parameters are adjusted using an adaptive step size. ,in, For the updated policy parameters, Indicates the first One parameter and , It is the total number of strategy parameters. It is the learning rate and its value ranges from 0.1 to 0.3. It is the trend response coefficient; when the data shows an upward trend... During a downward trend , It is a trend characteristic. It is a fluctuation characteristic, the aforementioned C represents conversion rate, which is the percentage of users who complete the target behavior of purchasing or registering out of the total number of visitors; R represents return on investment, which is the ratio of marketing revenue to cost; and U represents user complaint rate, which is the percentage of users who file a complaint out of the total number of visitors. For the target weight, update the policy parameters. Feedback is sent to the data analysis module to analyze data trends and fluctuations in the next time window, and to dynamically optimize marketing strategy parameters.

[0051] The creative generation layer employs natural language processing and image generation technologies to generate personalized marketing strategies based on the strategy parameters adjusted by the dynamic adaptation layer. The creative generation layer includes a text generation module, a multimedia material generation module, and a content fusion optimization module. The text generation module combines natural language processing technology with the strategy parameters corrected by the dynamic adaptation layer and the characteristics of the target audience to generate personalized marketing copy. The steps are as follows:

[0052] Parameter parsing and audience analysis: The strategy parameters after the dynamic adaptation layer are parsed to extract key information, including product features, marketing goals, and promotional efforts. At the same time, combined with the target audience information of the user profile, the characteristics of the target audience, such as age, gender, region, consumption habits, and interests, are analyzed. Semantic analysis of the target audience is also performed using natural language processing technology.

[0053] Copywriting template selection and adaptation: Based on strategy parameters and target audience characteristics, select a copywriting template from a pre-set copywriting template library. The copywriting template library contains various types of marketing copywriting templates, including product promotion copywriting, promotional activity copywriting, and brand promotion copywriting. Fill the copywriting template with the specific information in the strategy parameters and adapt the expression style of the copywriting to make it conform to the language style of the target audience.

[0054] Copy generation and optimization: Further optimize and generate the adapted copy, learn from historical text data, and optimize the generated copy from three dimensions: grammatical accuracy, semantic coherence, and marketing appeal;

[0055] The multimedia material generation module uses a Generative Adversarial Network (GAN) algorithm to generate images and videos. The GAN consists of a generator and a discriminator. The generator is responsible for generating realistic images, and the discriminator is responsible for determining the authenticity of the generated images. The steps are as follows:

[0056] Input condition setting: Based on the marketing theme and target audience preferences, set the input conditions for image generation, including product appearance features, scene style, and color preferences;

[0057] Image generation by the generator: The generator generates a preliminary image based on the input conditions using a neural network model. The generator learns from image data to generate an image that meets the input conditions.

[0058] Discriminator evaluation and feedback: The discriminator evaluates the image generated by the generator to determine its authenticity. When the discriminator considers the image to be unrealistic, it sends feedback information to the generator. The generator adjusts its generation strategy based on the feedback information and regenerates the image.

[0059] Iterative optimization: Repeat the generation and evaluation process until the discriminator can no longer evaluate the generated image; at this point, the generated image is the marketing image.

[0060] The content fusion and optimization module is used to merge and optimize the generated multimodal content, including text, images, and videos, to form a complete personalized marketing strategy with multiple marketing contents.

[0061] The multi-objective strategy selection layer is used to set multiple marketing objectives and their corresponding weights. The personalized marketing strategies generated by the creative generation layer are input into a multi-objective optimization algorithm for comprehensive evaluation and ranking, outputting the optimal combination of marketing strategies. This includes a marketing objective setting module, an evaluation indicator construction module, a multi-objective optimization application module, and a strategy ranking and selection module. The marketing objective setting module is used to preset multiple marketing objectives based on the company's marketing strategy and actual needs, and supports dynamically expanding objective types to generate objective sets. ,in, Indicates the first One marketing goal, Assign normalized weights to each target ,satisfy ,in, Characterization target Prioritization in corporate marketing strategy; the evaluation indicator construction module is used to build corresponding strategy evaluation indicators for each preset marketing objective, forming... Dimensional evaluation index matrix ,in, Indicates the first One goal The next Each sub-indicator For each sub-metric Allocator weights ,satisfy This is used to quantify the contribution of the indicator to its respective objective, and a multi-objective optimization algorithm is applied to the output of the creative generation layer. Personalized marketing strategies are expressed as Each strategy corresponds to a standardized index vector. ,in Representation strategy In the Under the first goal The normalized scores of each indicator are used to calculate the overall fitness score. , For strategy The overall score, For the goal The weight, As an indicator The sub-weights and strategy ranking selection module rank the generated marketing strategies based on the evaluation results of the multi-objective optimization algorithm, generate a strategy priority list, and use the comprehensive fitness score as the final personalized marketing strategy selection.

[0062] In summary, this embodiment, through the marketing practice of vocational skills training courses, utilizes a dynamic hierarchical strategy generation mechanism to comprehensively collect and analyze market, user, and internal enterprise data. Combined with multi-objective optimization strategy evaluation and selection, it can generate personalized marketing strategies, thereby improving the accuracy and coverage of marketing strategies.

[0063] Example 2: Figure 1 As shown, this embodiment provides a process for formulating personalized marketing strategies through an automated marketing strategy generation system based on intelligent services. The specific steps of this process are as follows:

[0064] Extract general marketing strategy frameworks from industry knowledge bases and establish a basic template library;

[0065] Templates are categorized by industry, target, and product characteristics, and configurable parameters are labeled to form a structured template library;

[0066] Based on the basic information of the input marketing task, the most relevant general strategy framework is retrieved from the template library and used as the basis for generation.

[0067] Real-time collection of market data, user data, and enterprise data;

[0068] Clean the raw data, merge multi-source data according to preset weights, and form a feature vector that comprehensively reflects the market situation;

[0069] Analyze the time trends and fluctuations of integrated data to identify patterns in market changes and dynamic user needs;

[0070] Dynamically adjust the strategy parameters in the template based on market characteristics and marketing performance goals;

[0071] By combining user profiles with real-time behavioral data, we can analyze the target audience's language style and content preferences.

[0072] Based on natural language processing technology, suitable templates are selected from the copywriting template library, strategy parameters are populated, and syntax, semantics, and attractiveness are optimized.

[0073] Using image generation and video production technologies, visual materials are generated based on marketing themes and audience preferences;

[0074] Integrate text, images, and video content to ensure a consistent style and complementary information, forming a complete personalized marketing content package;

[0075] Define multiple marketing objectives and assign priority weights to each objective;

[0076] Establish detailed evaluation indicators for each objective, and clarify the calculation method and sub-weights of the indicators;

[0077] A multi-objective optimization algorithm is used to quantitatively evaluate the multiple marketing strategy proposals generated and calculate the overall fitness score.

[0078] Based on the evaluation results, the options are ranked, the optimal strategy combination is selected, and an executable personalized marketing strategy is output.

[0079] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. An automated marketing strategy generation system based on intelligent services, characterized in that, The system consists of: a basic template layer, a dynamic adaptation layer, a creative generation layer, and a multi-objective strategy selection layer; The basic template layer collects and organizes general strategy frameworks for various marketing activities in the industry, classifies and labels the collected strategy frameworks, and establishes a basic template library. When the system receives a marketing task, the basic template layer matches and extracts the corresponding general strategy framework from the basic template library based on the basic information of the marketing task, providing a basic framework for strategy generation. The dynamic adaptation layer collects multi-source heterogeneous data in real time, including market data, user data, and enterprise data. It analyzes the collected real-time data, explores the patterns of change in the data, and dynamically corrects the parameters in the general strategy framework provided by the basic template layer based on the data analysis results. The dynamic adaptation layer includes a data acquisition module, a data analysis module, and a parameter correction module. The data analysis module cleans and normalizes the raw data acquired by the data acquisition module, and then adjusts the parameters according to preset weights. Normalized data By integrating these elements, a multi-dimensional vector comprehensively reflecting the market situation is obtained. and ,in, For the first Normalized vectors of class data, As data type weights, based on the fused data, within a time window T, trend features and fluctuation features are extracted to measure the data's changing patterns. The trend features... The fluctuation characteristics are used to calculate the trend of data changes over time. Used to measure the degree of dispersion of data. For the first Fusion feature values ​​at time step , The mean of time and features; The parameter correction module is based on the fusion features output by the data analysis module. Trend and Fluctuation parameters are used to modify the configurable strategy parameters of the basic template layer, with the modification based on a comprehensive marketing effectiveness index. To optimize the objective, calculate the current policy parameters. right sensitivity Used to reflect adjustments The degree of impact on the overall effect is determined by combining trend and volatility characteristics, and configurable strategy parameters are adjusted using an adaptive step size. ,in, For the updated policy parameters, Indicates the first One parameter and , It is the total number of strategy parameters. It is the learning rate and its value ranges from 0.1 to 0.

3. It is the trend response coefficient; when the data shows an upward trend... =1, during a downward trend =-1, It is a trend characteristic. It is a fluctuation characteristic, the aforementioned C represents conversion rate, which is the percentage of users who complete the target behavior of purchasing or registering out of the total number of visitors; R represents return on investment, which is the ratio of marketing revenue to cost; and U represents user complaint rate, which is the percentage of users who file a complaint out of the total number of visitors. For the target weight, update the policy parameters. Feedback is sent to the data analysis module to analyze data trends and fluctuations in the next time window and to dynamically optimize marketing strategy parameters; The creative generation layer uses natural language processing and image generation technology to generate personalized marketing strategies based on the strategy parameters adjusted by the dynamic adaptation layer. The multi-objective strategy selection layer is used to set multiple marketing objectives and corresponding weights, and inputs the personalized marketing strategies generated by the creative generation layer into the multi-objective optimization algorithm for comprehensive evaluation and ranking, and outputs the optimal marketing strategy combination.

2. The automated marketing strategy generation system based on intelligent services according to claim 1, characterized in that, The basic template layer includes a strategy framework collection module, a framework classification and annotation module, and a framework matching and extraction module; The strategy framework collection module is used to collect and organize the general strategy frameworks for various marketing activities in the industry, including promotional activity strategies, advertising strategies, membership marketing strategies, course sales strategies, and information delivery strategies. The framework classification and labeling module classifies and labels the collected general strategy frameworks, and builds multi-dimensional configurable strategy parameters for each strategy framework, including discount level, activity period, and applicable customer group, and establishes a basic template library. The framework matching and extraction module is used to match and extract corresponding general strategy frameworks from the basic template library based on the basic information of the marketing task, including industry type, marketing objectives, and product characteristics, as a benchmark for generating personalized marketing strategies.

3. The automated marketing strategy generation system based on intelligent services according to claim 1, characterized in that, The data acquisition module is used to collect multi-source heterogeneous data from the market, users, and enterprises in real time. The market data includes industry trends and market size, the user data includes user behavior data, user profiles, and user feedback, and the enterprise data includes product inventory, sales data, and marketing budget. The data analysis module analyzes the collected real-time data and uncovers patterns of change within the data. The parameter correction module is used to dynamically correct the parameters in the general strategy framework provided by the basic template layer based on the data analysis results.

4. The automated marketing strategy generation system based on intelligent services according to claim 1, characterized in that, The creative generation layer includes a text generation module, a multimedia material generation module, and a content fusion and optimization module; The text generation module is used to combine natural language processing technology to generate personalized marketing copy based on the strategy parameters corrected by the dynamic adaptation layer and the characteristics of the target audience. The multimedia material generation module uses image generation technology to generate multimedia marketing materials, including images and videos, that match the marketing theme and the preferences of the target audience. The content fusion and optimization module is used to fuse and optimize the generated multimodal content of text, images, and videos to form a complete personalized marketing strategy with multiple marketing contents.

5. The automated marketing strategy generation system based on intelligent services according to claim 4, characterized in that, The text generation module creates targeted text content based on the language habits and interests of different target audiences. The steps are as follows: Parameter parsing and audience analysis: The strategy parameters after the dynamic adaptation layer are parsed to extract key information, including product features, marketing goals, and promotional efforts. At the same time, combined with the target audience information of the user profile, the characteristics of the target audience, such as age, gender, region, consumption habits, and interests, are analyzed. Semantic analysis of the target audience is also performed using natural language processing technology. Copywriting template selection and adaptation: Based on strategy parameters and target audience characteristics, select a copywriting template from a pre-set copywriting template library. The copywriting template library contains various types of marketing copywriting templates, including product promotion copywriting, promotional activity copywriting, and brand promotion copywriting. Fill the copywriting template with the specific information in the strategy parameters and adapt the expression style of the copywriting to make it conform to the language style of the target audience. Copy generation and optimization: Further optimize and generate the adapted copy, learn from historical text data, and optimize the generated copy from three dimensions: grammatical accuracy, semantic coherence, and marketing appeal; The multimedia material generation module uses a Generative Adversarial Network (GAN) algorithm to generate images and videos. The GAN consists of a generator and a discriminator. The generator is responsible for generating realistic images, and the discriminator is responsible for determining the authenticity of the generated images. The steps are as follows: Input condition setting: Based on the marketing theme and target audience preferences, set the input conditions for image generation, including product appearance features, scene style, and color preferences; Image generation by the generator: The generator generates a preliminary image based on the input conditions using a neural network model. The generator learns from image data to generate an image that meets the input conditions. Discriminator evaluation and feedback: The discriminator evaluates the image generated by the generator to determine its authenticity. When the discriminator considers the image to be unrealistic, it sends feedback information to the generator. The generator adjusts its generation strategy based on the feedback information and regenerates the image. Iterative optimization: Repeat the generation and evaluation process until the discriminator can no longer evaluate the generated image; at this point, the generated image is the marketing image.

6. The automated marketing strategy generation system based on intelligent services according to claim 1, characterized in that, The multi-objective strategy selection layer includes a marketing objective setting module, an evaluation indicator construction module, a multi-objective optimization application module, and a strategy ranking and selection module; The marketing goal setting module is used to preset multiple marketing goals based on the company's marketing strategy and actual needs, and supports dynamically expanding goal types to generate goal sets. ,in, Indicates the first One marketing goal, Assign normalized weights to each target ,satisfy ,in, Characterization target Priority in corporate marketing strategy; The evaluation index construction module is used to construct corresponding strategy evaluation indicators for each preset marketing objective, forming... Dimensional evaluation index matrix ,in, Indicates the first One goal The next Each sub-indicator For each sub-metric Allocator weights ,satisfy This is used to quantify the contribution of the indicator to its respective objective; The multi-objective optimization application module uses a multi-objective optimization algorithm to comprehensively evaluate the various marketing strategies generated and calculate the comprehensive fitness score. The strategy ranking and selection module is used to rank the generated marketing strategies based on the evaluation results of the multi-objective optimization algorithm, and generate a strategy priority list.

7. The automated marketing strategy generation system based on intelligent services according to claim 6, characterized in that, The multi-objective optimization application module uses a multi-objective optimization algorithm to optimize the output of the creative generation layer. Personalized marketing strategies are expressed as Each strategy corresponds to a standardized index vector. ,in Representation strategy In the Under the first goal The normalized scores of each indicator are used to calculate the overall fitness score. , For strategy The overall score, For the goal The weight, As an indicator Sub-weights.

Images