Commodity marketing method and system based on artificial intelligence
By obtaining and analyzing the behavioral data of sales platform users, generating user tags and dynamically adjusting marketing strategies, the problem that traditional marketing methods are difficult to accurately reach the target consumer group is solved, improving the accuracy and efficiency of marketing, and enhancing user participation and conversion to ensure that enterprises can respond flexibly to market changes.
Patent Information
- Application Number
- CN202411506164.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-28
- Publication Date
- 2024-11-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional marketing methods are difficult to accurately reach the target consumer group, have serious waste of resources, poor marketing results, and are difficult to adapt to the needs of diverse users, and are inefficient.
By obtaining the behavioral data of sales platform users, generating user tags, using clustering analysis and correlation analysis, dynamically adjusting marketing templates and strategies, and distributing matching marketing activities in real time.
It significantly improves the accuracy of marketing and resource allocation efficiency, enhances user participation and conversion rates, ensures that enterprises can flexibly respond to market changes and continuously optimize marketing activities.
Smart Images

Figure CN119027165A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of commodity marketing, and in particular to a commodity marketing method and system based on artificial intelligence. Background Art
[0002] In today's highly competitive business environment, product marketing, as a key link for companies to connect with consumers and promote sales growth, is facing unprecedented challenges. Traditional marketing methods often rely on wide-ranging advertising and empirical strategy formulation, which has many shortcomings.
[0003] Traditional marketing methods often rely on extensive advertising and market research, but this method is difficult to accurately reach the target consumer group. Due to the lack of in-depth user data analysis and personalized labeling system, marketing activities can only cover some potential customers, and poor targeting leads to waste of resources and poor marketing results. The market environment and consumer demand are changing at an increasingly rapid pace, but traditional marketing strategies often lag behind in adjustment and are difficult to respond to market changes in a timely manner. Fixed marketing templates and strategies are difficult to adapt to diverse user needs, resulting in poor user experience and reduced conversion rates. Traditional marketing decisions often rely on experience and intuition, lacking scientific data analysis and support. This decision-making method is not only inefficient, but also prone to errors, making it difficult to gain an advantage in the fierce market competition.
[0004] Therefore, it is necessary to provide an artificial intelligence-based commodity marketing method and system to solve the above technical problems. Summary of the invention
[0005] In order to solve the above technical problems, the present invention provides an artificial intelligence-based commodity marketing method and system for solving the problems of poor targeting of traditional marketing methods leading to waste of resources and poor marketing effects, difficulty in adapting to diverse user needs and low efficiency.
[0006] The commodity marketing method based on artificial intelligence provided by the present invention comprises the following steps: Periodically obtain the behavior data of users on the sales platform and generate user tags; Based on the generated user tags, users with similar tags are grouped into one category through cluster analysis method, and representative user tags are identified from each category of user tags; Based on business needs, weights are assigned to each representative user tag, and the priority of the representative user tags is divided; According to the priorities of the representative user tags, a matching marketing template is developed for each priority category through correlation analysis; Set multiple extended marketing strategies for the formulated marketing template, and set a corresponding matching coefficient for each extended strategy; Obtain user behavior data on the sales platform in real time, extract and update user tags, and dynamically assign marketing templates that match their behavior characteristics to users; Based on the set matching coefficient, an extended marketing strategy is selected for the marketing template assigned to the user tag, and a corresponding marketing campaign is executed.
[0007] Preferably, the periodic acquisition of the behavior data of the sales platform users and the generation of user tags specifically include the following steps: Set a fixed time period to collect user behavior data from the sales platform, including but not limited to search data, transaction records, after-sales records and evaluation data; Use data cleaning technology to remove noise and outliers from user behavior data and extract features related to user behavior descriptions; The features related to the extracted user behavior descriptions are identified through association rule mining algorithms to generate multi-dimensional user tags.
[0008] Preferably, the method of classifying users with similar tags into one category based on the generated user tags by a cluster analysis method, and identifying representative user tags from each category of user tags, specifically includes the following steps: According to the similarity of user tags, use any clustering analysis method such as K-means or hierarchical clustering to divide users into different categories; By statistically calculating the frequency of each tag among users of the same category, the tag with the highest frequency is counted from each category of user tags and marked as the representative user tag.
[0009] Preferably, the weight allocation for each representative user tag based on business needs and the priority classification of the representative user tags specifically include the following steps: Comprehensively evaluate different representative user tags based on business needs, and assign corresponding weights according to the comprehensive evaluation scores. Business needs specifically include increasing sales and enhancing user stickiness. According to the result of weight allocation, the representative user tags are divided into different priority categories, where the priority categories include high priority, medium priority and low priority.
[0010] Preferably, the steps of formulating a matching marketing template for each priority category through correlation analysis according to the priorities of the divided representative user tags specifically include the following steps: Design corresponding marketing templates based on user tags and business requirements of each priority category, where the marketing templates include discount information and product recommendations; Use data analysis tools to evaluate the correlation values between marketing templates and representative user tags, and verify the marketing templates based on preset correlation value evaluation thresholds.
[0011] Preferably, the step of setting a plurality of extended marketing strategies for the formulated marketing template and setting a corresponding matching coefficient for each extended strategy specifically includes the following steps: Design multiple extended marketing strategies for each marketing template, including limited-time discounts, member-only discounts, and discounts for purchases above a certain amount; According to the timeliness of the marketing strategy and the acceptance of the historical user group, set the corresponding matching coefficient for each extension strategy.
[0012] Preferably, the real-time acquisition of user behavior data on the sales platform, extracting and updating user tags, and dynamically assigning marketing templates that match the user's behavior characteristics to the user include the following steps: Use real-time data processing technology to continuously monitor changes in user behavior data on the sales platform and extract current user tags; Update user tags in real time based on the user's current behavior data, and perform correlation analysis between the updated user tags and existing marketing templates; Based on the updated user tag and the correlation analysis result, a template that best matches the updated user tag is selected from multiple marketing templates.
[0013] A commodity marketing system based on artificial intelligence, the marketing system comprising: The data acquisition module is used to periodically acquire the behavior data of users on the sales platform and generate user tags; A tag classification module is used to classify users with similar tags into one category based on the generated user tags by clustering analysis method, and identify representative user tags from each category of user tags; A weight allocation module is used to allocate weights to each representative user tag based on business needs and to prioritize the representative user tags; A template definition module is used to formulate a matching marketing template for each priority category based on the priorities of the divided representative user tags through correlation analysis; The strategy definition module is used to set multiple extended marketing strategies for the formulated marketing template and set a corresponding matching coefficient for each extended strategy; The allocation module is used to obtain user behavior data on the sales platform in real time, extract and update user tags, and dynamically allocate marketing templates that match their behavior characteristics to users; The matching module is used to select an extended marketing strategy for the marketing template assigned to the user tag based on a set matching coefficient, and execute a corresponding marketing activity.
[0014] Compared with related technologies, the commodity marketing method and system based on artificial intelligence provided by the present invention has the following beneficial effects: The present invention significantly improves the accuracy of marketing and the efficiency of resource allocation by accurately analyzing user behavior data, implementing cluster analysis and priority sorting. At the same time, it flexibly sets and dynamically adjusts marketing templates and extension strategies, which not only enhances the flexibility of marketing activities, but also greatly improves user participation and conversion rates. This series of measures jointly promotes data-driven decision-making, ensuring that companies can flexibly respond to market changes and continuously optimize marketing activities. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Figure 1 A flowchart of the commodity marketing method based on artificial intelligence of the present invention; Figure 2 This is a system block diagram of the artificial intelligence-based commodity marketing system of the present invention. DETAILED DESCRIPTION
[0016] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes.
[0017] Embodiment 1 like Figure 1 As shown, the commodity marketing method based on artificial intelligence includes the following steps: S100, periodically obtaining the behavior data of users of the sales platform and generating user tags; In the specific implementation process, the specific steps of step S100 are: S101. Set a fixed time period to collect user behavior data from the sales platform, including but not limited to search data, transaction records, after-sales records, and evaluation data; Specifically, set a weekly or monthly cycle to collect user retrieval data from the sales platform: search keywords, browsed product lists, clicked product details pages; transaction records: user purchase records, order details, payment status, etc.; after-sales records: returns, exchanges, complaints and other after-sales behaviors; evaluation data: user evaluation and feedback on purchased products and merchant services.
[0018] S102, using data cleaning technology to remove noise and outliers from the user's behavior data, and extracting features related to the description of the user's behavior; Specifically, in the user's behavior data, for missing data items, according to the characteristics of the data and business logic, missing value processing can be carried out by filling default values, using mean / median / mode filling and other methods; and for outliers, the standard deviation method in statistics is used to identify outliers and decide whether to eliminate or correct them. After the cleaning process is completed, verify the consistency and standardization of the data format, such as the consistency and standardization of the date format, currency unit, numerical precision, etc.
[0019] S103, identifying features related to the extracted user behavior descriptions through an association rule mining algorithm to generate multi-dimensional user tags; Specifically, the Apriori algorithm and FP-Growth algorithm in the association rule mining algorithm are used to discover the association relationship between data items and identify the patterns and characteristics of user behavior, specifically: based on the user's browsing and purchase records, the user's interest areas and preferred product tags are identified; based on the user's purchase amount, frequency and product category, the user's consumption level and consumption ability tags are evaluated, and the user's login and purchase time are analyzed to determine the user's active time period tags; combined with the user's purchase history, repurchase rate and evaluation data, the user's loyalty to the platform is evaluated.
[0020] For example, by analyzing the user's purchase history and browsing behavior, we can find the association rule that "users who buy product A often also buy product B", and then label such users as "prefer A&B products". Specifically, if the user often browses and buys electronic products, especially high-end smartphones, then the user can be labeled as "electronic product enthusiast", "high-end smartphone user", etc.
[0021] S200, based on the generated user tags, grouping users with similar tags into one category through a cluster analysis method, and identifying representative user tags from each category of user tags; In the specific implementation process, the specific steps of step S200 are: S201, according to the similarity of user tags, using any clustering analysis method such as K-means or hierarchical clustering to divide users into different categories; Specifically, in this embodiment, K-means is used to classify users into different categories. Specifically, first, a cluster number K needs to be pre-set according to business requirements and the distribution of user data. It should be noted that the selection of the K value can be determined by empirical judgment and the Elbow Method. K users are randomly selected as initial cluster centers, and then the distance between each user and each cluster center is calculated. Each user is assigned to the cluster to which the nearest cluster center belongs, and the users are classified into different categories.
[0022] S202, by statistically calculating the frequency of each tag among users of the same category, the tag with the highest frequency is counted from each category of user tags, and marked as a representative user tag; Specifically, for each user in the cluster, the number of occurrences of all their tags is counted. Then, these statistical results are aggregated to the cluster level, and the total frequency of each tag in the cluster is calculated. From the tag frequency statistics of each cluster, the tags with the highest frequency are found. These tags will be regarded as representative user tags of the cluster.
[0023] For example, multiple labels for users are generated, including "electronic product enthusiast", "fashion trend follower", and "high-end consumer", and the K-means clustering method is used to divide the users into three clusters. The label frequency statistics of the first cluster are performed, and it is found that the frequency of the label "electronic product enthusiast" is the highest, far higher than other labels. Therefore, "electronic product enthusiast" is used as the representative user label of the first cluster.
[0024] S300: Based on business requirements, weights are assigned to each representative user tag, and priorities of the representative user tags are divided; In the specific implementation process, the specific steps of step S300 are: S301. Comprehensively evaluate different representative user tags based on business needs, and assign corresponding weights according to the comprehensive evaluation scores, wherein the business needs specifically include increasing sales and enhancing user stickiness; Specifically, based on the needs of increasing transaction frequency or raising average order value, improving user activity, retention rate and loyalty, identify and list all representative user tags collected, analyze the potential correlation between each tag and increasing sales and enhancing user stickiness. For example, "high-frequency buyers" are directly associated with sales growth, while "socially active elements" may indirectly promote sales and enhance user stickiness through word-of-mouth communication. The contribution of each tag in increasing sales and enhancing user stickiness is evaluated by combining quantitative methods, such as historical transaction data and activity statistics, and qualitative methods, such as user feedback and market research. For example, each tag is scored separately in the two dimensions of increasing sales and enhancing user stickiness (out of 10 points), and then the total score or weighted average score is calculated. According to the results of the comprehensive evaluation, each tag is assigned a corresponding weight.
[0025] S302, according to the result of weight allocation, classify the representative user tags into different priority categories, wherein the priority categories include high priority, medium priority and low priority; Specifically, according to business needs and resource allocation, specific standards for dividing priorities are set. In this embodiment, tags with a total weight score reaching a certain threshold are classified as high priority, slightly lower ones are medium priority, and the rest are low priority. According to the set standards, each tag is classified into a corresponding priority category. In this embodiment, a total weight score ≥ 5 is high priority, 3≤ total weight score <5 is medium priority, and total weight score <3 is low priority.
[0026] S400, according to the priorities of the divided representative user tags, a matching marketing template is formulated for each priority category through correlation analysis; In the specific implementation process, the specific steps of step S400 are: S401. Design corresponding marketing templates according to user tags and business requirements of each priority category, wherein the marketing templates include preferential information and product recommendations; Specifically, for preferential information: for high-frequency buyers, design "member-only discounts", "points exchange" and other preferential treatment; for price-sensitive users, launch "limited-time specials" and "full-discount activities"; for product recommendations: based on the user's purchase history and preferences, intelligently recommend related products; and for socially active people, design content with social attributes, for example, such as "share to win gifts", "friend invitation code", etc., and build preferential information and product recommendations into marketing templates in the form of emails, text messages, APP push or social media messages.
[0027] S402, using a data analysis tool to evaluate the correlation value between the marketing template and the representative user tag, and verifying the marketing template according to a preset correlation value evaluation threshold; Specifically, historical user data, including purchase records, browsing behaviors, interactions, etc., are integrated as the basis for evaluation. Then, Python in existing data analysis tools is used to conduct correlation analysis on keywords, discount information, product recommendations, etc. in the marketing template and user tag features, and one or more evaluation thresholds of correlation values are set as verification basis. Only when the correlation between the marketing template and the specific user tag exceeds this threshold, the marketing template is considered valid.
[0028] S500, setting multiple extended marketing strategies for the formulated marketing template, and setting a corresponding matching coefficient for each extended strategy; In the specific implementation process, the specific steps of step S500 are: S501. Design multiple extended marketing strategies for each marketing template, including limited-time discounts, member-only discounts, and discounts for purchases above a certain amount; Specifically, the design extension strategy includes limited-time discounts: setting limited-time discounts for specific products or services to increase the sense of urgency and attractiveness of purchase; member exclusive: providing members with exclusive discounts or privileges to enhance their sense of belonging and loyalty, an example of which is "member day exclusive, double points + extra discounts"; full-reduction discounts: setting a certain consumption threshold, and enjoying discounts after reaching the threshold to encourage users to increase their purchases.
[0029] S502, according to the timeliness of the marketing strategy and the acceptance of the historical user group, set a corresponding matching coefficient for each extension strategy; Specifically, analyze the timeliness characteristics of each extension strategy, set different weights or coefficients according to the timeliness of the strategy, give higher weights to strategies with strong timeliness, such as limited-time discounts, to quickly attract user attention, and use historical data to analyze user acceptance and feedback on different types of marketing strategies. Then, combine the evaluation results of the two dimensions of timeliness and historical user acceptance, set the final matching coefficient for each extension strategy, and set a different matching coefficient for each extension strategy.
[0030] In this embodiment, for limited-time discounts, a higher matching coefficient of 1.2 is set, indicating that more support is given in terms of resource allocation and promotion efforts; for member-only offers, a moderate matching coefficient of 1.0 is set to maintain a certain promotion strength; for discounts on purchases above a certain amount, a matching coefficient of 1.1 is set to avoid excessive competition and waste of resources.
[0031] S600, real-time acquisition of user behavior data on the sales platform, and dynamic allocation of marketing templates matching the user's behavior characteristics to the user by extracting and updating the user tag; In the specific implementation process, the specific steps of step S600 are: S601. Use real-time data processing technology to continuously monitor changes in user behavior data on the sales platform and extract current user tags; Specifically, various behavioral data of users on the sales platform are captured in real time, and the Apache Kafka tool in stream processing technology is used to process the collected data in real time, remove noise data, clean and format the data, and then analyze the processed data in real time to extract the user's current behavioral characteristics.
[0032] S602: updating user tags in real time according to the user's current behavior data, and performing correlation analysis between the updated user tags and the existing marketing templates; Specifically, based on the user's current behavior data, the user tags are updated in real time, and the updated user tags are analyzed for correlation with each marketing template to evaluate the degree of match between the user tags and the template's target audience.
[0033] S603: Based on the updated user tag and the correlation analysis result, select a template that best matches the updated user tag from multiple marketing templates; S700, based on the set matching coefficient, selecting an extended marketing strategy for the marketing template assigned to the user tag, and executing a corresponding marketing activity; Specifically, according to the matching coefficient set for each extended marketing strategy in step S502 and the marketing template selected by the user tag, a strategy that best matches the current situation is selected from multiple extended marketing strategies. For example, if the marketing template is a clothing promotion for "young and fashionable women" and the current user tag also meets the characteristics of this group, then the extended strategy of "limited-time discount + social media interaction reward" can be selected, because both strategies are more in line with the consumption psychology and social habits of young and fashionable women. According to the selected extended marketing strategy, corresponding marketing activities are carried out, including various links such as event warm-up, formal promotion, user interaction, order processing, and after-sales service.
[0034] Embodiment 2 like Figure 2 As shown, the artificial intelligence-based commodity marketing system applied to the artificial intelligence-based commodity marketing method specifically includes: The data acquisition module is used to periodically acquire the behavior data of users on the sales platform and generate user tags; A tag classification module is used to classify users with similar tags into one category based on the generated user tags by clustering analysis method, and identify representative user tags from each category of user tags; A weight allocation module is used to allocate weights to each representative user tag based on business needs and to prioritize the representative user tags; A template definition module is used to formulate a matching marketing template for each priority category based on the priorities of the divided representative user tags through correlation analysis; The strategy definition module is used to set multiple extended marketing strategies for the formulated marketing template and set a corresponding matching coefficient for each extended strategy; The allocation module is used to obtain user behavior data on the sales platform in real time, extract and update user tags, and dynamically allocate marketing templates that match their behavior characteristics to users; The matching module is used to select an extended marketing strategy for the marketing template assigned to the user tag based on a set matching coefficient, and execute a corresponding marketing activity.
[0035] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0036] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.
[0037] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
Claims
1. A commodity marketing method based on artificial intelligence, characterized in that: The marketing method comprises the following steps: Periodically obtain the behavior data of users on the sales platform and generate user tags; Based on the generated user tags, users with similar tags are grouped into one category through cluster analysis method, and representative user tags are identified from each category of user tags; Based on business needs, weights are assigned to each representative user tag, and the priority of the representative user tags is divided; According to the priorities of the representative user tags, a matching marketing template is developed for each priority category through correlation analysis; Set multiple extended marketing strategies for the formulated marketing template, and set a corresponding matching coefficient for each extended strategy; Obtain user behavior data on the sales platform in real time, extract and update user tags, and dynamically assign marketing templates that match their behavior characteristics to users; Based on the set matching coefficient, an extended marketing strategy is selected for the marketing template assigned to the user tag, and a corresponding marketing campaign is executed.
2. The commodity marketing method based on artificial intelligence according to claim 1, characterized in that: The periodic acquisition of the behavior data of the sales platform users and the generation of user tags specifically include the following steps: Set a fixed time period to collect user behavior data from the sales platform, including but not limited to search data, transaction records, after-sales records and evaluation data; Use data cleaning technology to remove noise and outliers from user behavior data and extract features related to user behavior descriptions; The features related to the extracted user behavior descriptions are identified through association rule mining algorithms to generate multi-dimensional user tags.
3. The commodity marketing method based on artificial intelligence according to claim 1, characterized in that: Based on the generated user tags, users with similar tags are classified into one category by a cluster analysis method, and representative user tags are identified from each category of user tags, which specifically includes the following steps: According to the similarity of user tags, use any clustering analysis method such as K-means or hierarchical clustering to divide users into different categories; By statistically calculating the frequency of each tag among users of the same category, the tag with the highest frequency is counted from each category of user tags and marked as the representative user tag.
4. The commodity marketing method based on artificial intelligence according to claim 1, characterized in that: The weight allocation for each representative user tag based on the business requirements and the priority classification of the representative user tags specifically include the following steps: Comprehensively evaluate different representative user tags based on business needs, and assign corresponding weights according to the comprehensive evaluation scores. Business needs specifically include increasing sales and enhancing user stickiness. According to the result of weight allocation, the representative user tags are divided into different priority categories, where the priority categories include high priority, medium priority and low priority.
5. The commodity marketing method based on artificial intelligence according to claim 1, characterized in that: According to the priorities of the representative user tags divided, a matching marketing template is formulated for each priority category through correlation analysis, which specifically includes the following steps: Design corresponding marketing templates based on user tags and business requirements of each priority category, where the marketing templates include discount information and product recommendations; Use data analysis tools to evaluate the correlation values between marketing templates and representative user tags, and verify the marketing templates based on preset correlation value evaluation thresholds.
6. The commodity marketing method based on artificial intelligence according to claim 1, characterized in that: The step of setting a plurality of extended marketing strategies for the formulated marketing template and setting a corresponding matching coefficient for each extended strategy specifically includes the following steps: Design multiple extended marketing strategies for each marketing template, including limited-time discounts, member-only discounts, and discounts for purchases above a certain amount; According to the timeliness of the marketing strategy and the acceptance of the historical user group, set the corresponding matching coefficient for each extension strategy.
7. The commodity marketing method based on artificial intelligence according to claim 1, characterized in that: The method of acquiring user behavior data on the sales platform in real time, extracting and updating user tags, and dynamically assigning marketing templates that match the user's behavior characteristics to the user includes the following steps: Use real-time data processing technology to continuously monitor changes in user behavior data on the sales platform and extract current user tags; Update user tags in real time based on the user's current behavior data, and perform correlation analysis between the updated user tags and existing marketing templates; Based on the updated user tag and the correlation analysis result, a template that best matches the updated user tag is selected from multiple marketing templates.
8. An artificial intelligence-based commodity marketing system, applied to the artificial intelligence-based commodity marketing method according to any one of claims 1 to 7, characterized in that: The marketing system includes: The data acquisition module is used to periodically acquire the behavior data of users on the sales platform and generate user tags; A tag classification module is used to classify users with similar tags into one category based on the generated user tags by clustering analysis method, and identify representative user tags from each category of user tags; A weight allocation module is used to allocate weights to each representative user tag based on business needs and to prioritize the representative user tags; A template definition module is used to formulate a matching marketing template for each priority category based on the priorities of the divided representative user tags through correlation analysis; The strategy definition module is used to set multiple extended marketing strategies for the formulated marketing template and set a corresponding matching coefficient for each extended strategy; The allocation module is used to obtain user behavior data on the sales platform in real time, extract and update user tags, and dynamically allocate marketing templates that match their behavior characteristics to users; The matching module is used to select an extended marketing strategy for the marketing template assigned to the user tag based on a set matching coefficient, and execute a corresponding marketing activity.
Citation Information
Patent Citations
Marketing label analysis and extraction method and system for target user portrait
CN109978608A
Customer matching-based network marketing system
CN113421133A
AI robot marketing method and system based on one object and one code, and storable medium
CN113781173A
E-commerce marketing method based on SCRM
CN117726357A
Online marketing strategy recommendation method and system
CN118172091A
Cited By
Data processing method and system for intelligent marketing products
CN119722289A
A data processing method and system for intelligent marketing products
CN119722289B
Marketing problem operation method based on big data technology and related device
CN120317912A
Water supply marketing management method and system based on intelligent water affair
CN120450770A
Crowd value research and judgment method and device based on equipment information and order information
CN121504536A
