Intelligent marketing method and system based on user portraits

By building a collection of product labels with user portraits and similar user groups, the problem of insufficient data fragmentation and real-time in intelligent marketing is solved, personalized marketing and dynamic optimization are achieved, and marketing accuracy and user experience are improved.

CN118982384AActive Publication Date: 2024-11-19ZHEJIANG RADIO & TELEVISION NEW MEDIA CO LTD

Patent Information

Application Number
CN202411472131.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-22
Publication Date
2024-11-19
Estimated Expiration
2044-10-22

AI Technical Summary

Technical Problem

The existing intelligent marketing methods have problems such as data fragmentation, insufficient real-time, limited personalization and difficulty in dynamic optimization, resulting in insufficient user profiles and marketing strategies that cannot flexibly respond to market changes.

Method used

By building an initial user portrait, building a product tag collection based on user browsing behavior, determining similar user groups, and updating similar product tag collections in real time to push personalized marketing information, and dynamically adjusting marketing strategies.

Benefits of technology

It improves marketing accuracy, enhances user experience, realizes dynamic optimization of marketing strategies and effective resource allocation, and improves user participation and brand loyalty.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118982384A_ABST
    Figure CN118982384A_ABST
Patent Text Reader

Abstract

The invention provides an intelligent marketing method and system based on a user portrait. Firstly, basic information and browsing behavior data of a user are collected through an authorization protocol, and an initial user portrait is established; furthermore, by comparing the basic information in the user portraits with a preset similar vector, the users with similar characteristics are classified into a similar user group, and a similar commodity label set is shared. And finally, personalized marketing information is pushed according to the similar user group where the user is located, and meanwhile, a commodity label set is dynamically adjusted and optimized according to the feedback of a new online user, so that the continuity and effectiveness of a marketing activity are ensured. The method effectively integrates the user data, optimizes the marketing strategy, and improves the pertinence and conversion rate of advertisements, thereby remarkably improving the user satisfaction and the market competitiveness of enterprises.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of commercial marketing, and in particular to an intelligent marketing method and system based on user portraits. Background Art

[0002] With the rapid development of information technology, especially the application of big data, cloud computing and artificial intelligence technology, digital marketing has become an important core component of modern business. Especially in the field of e-commerce, effective marketing strategies play a vital role in attracting and retaining users. However, traditional marketing strategies often use the same marketing information for all users. This approach ignores the huge differences in interests, needs and behavior patterns among individual users, resulting in low marketing efficiency and user satisfaction.

[0003] Intelligent marketing methods attempt to provide more personalized services by building refined user portraits and using algorithms to predict user behavior. User portraits are models built based on multi-dimensional information such as user personal information, behavioral data, and transaction history. They can reflect user preferences, needs, and potential purchase intentions. By analyzing user portraits, companies can identify the characteristics and needs of different user groups or individuals and achieve precision marketing.

[0004] In the existing technology, intelligent marketing methods usually involve the following key steps: 1. Data collection and processing: Collect users’ personal information, behavioral data, interaction records, etc. through various channels. These data are cleaned and processed to build user portraits.

[0005] 2. User portrait construction: Use the processed data in combination with machine learning or statistical analysis methods to construct a user portrait that reflects user preferences and behavior patterns. This process usually includes steps such as feature selection, model training, and optimization.

[0006] 3. Marketing strategy formulation: Based on user portraits, companies formulate personalized marketing strategies. These strategies may involve product recommendations, advertising, promotional activities, etc.

[0007] 4. Effect evaluation and optimization: By tracking the effects of marketing activities, such as user click-through rate, purchase conversion rate, etc., the effectiveness of marketing strategies can be evaluated, and user portraits and marketing strategies can be optimized based on feedback.

[0008] Although this approach can improve the targeting and efficiency of marketing in many cases, the following problems still exist: 1. Data fragmentation: User data is often scattered in different systems and databases, resulting in information islands. This not only increases the difficulty of data integration, but also affects the integrity and accuracy of user portraits.

[0009] 2. Lack of real-time performance: User behaviors and preferences may change rapidly over time, while the update cycle of user portraits in existing technologies is usually long, which may result in the portrait information no longer being accurate, thus affecting the effectiveness of marketing activities.

[0010] 3. Limited personalization: Although existing technologies attempt to achieve personalized marketing through user profiling, due to the lack of in-depth behavioral analysis and detailed user segmentation, this personalization is often rough and difficult to meet the personalized needs of users.

[0011] 4. Difficulty in dynamic optimization: Existing marketing systems often lack effective mechanisms to adjust marketing strategies in real time to cope with changes in market environment and user behavior, resulting in marketing activities being unable to flexibly respond to new market challenges.

[0012] To address these issues, it is necessary to develop a more efficient, dynamic and accurate intelligent marketing method that can achieve real-time data processing, dynamic user portrait updates and rapid iterative optimization of personalized marketing strategies. Summary of the invention

[0013] In view of the above problems, the purpose of the present invention is to propose an intelligent marketing method based on user portraits, comprising the following steps: S1. Build the initial user portrait: obtain the user's basic information according to the authorization agreement and build the basic information vector; S2. Construct a single-user product tag set based on the browsing behavior of a single user; obtain the product tags involved in the user's browsing behavior according to the authorization protocol, and construct a single-user product tag set; S3, determining similar users based on basic information vectors: according to the predetermined similarity vectors, determining users with similar basic information vectors as a similar user group; S4. Construct a similar user product tag set based on the browsing behavior of similar users; collect statistics on all product tags involved in the browsing behavior of all users in the same similar user group, and construct a similar product tag set in descending order of frequency of occurrence, satisfying: ; in, Indicates A collection of similar product tags for similar user groups; The product label with the highest frequency is , a total of times, and so on, The dimension of the similar product label set; S5. Push marketing information based on the user portrait of the newly-launched user and a collection of similar product tags.

[0014] Furthermore, in step S1, the basic information vector satisfies: ; in, Indicates The basic information vector of each user, is the user serial number; Respectively represent The elements of the basic information vector of each user, is the vector dimension; Respectively represent Elements of a user's browsing behavior information collection, is the collection dimension.

[0015] Furthermore, in step S1, the single-user product tag set satisfies: ; in, Indicates A collection of single-user product tags for each user; Respectively represent The product tags recorded by each user’s browsing behavior, is the collection dimension.

[0016] Furthermore, step S3 specifically includes: S31. Predetermine similarity vectors ,satisfy: ; in, Respectively represent the value ranges of the first element, the second element, and the last element of the basic information vector; S32, all basic information vectors Falling into similar vector The users are identified as a similar user group.

[0017] Furthermore, in step S1, the basic characteristics of the user include at least: gender, age, region, city, personal interest tags, and model of electronic device used.

[0018] Furthermore, in step S2, the user browsing behavior includes at least: the number of pages visited, the dwell time, the visit frequency, the clicked links, the clicked advertisements, the interaction with the interface elements, the search query, the clicked search results, the video watched, the picture browsed, the picture downloaded, the comment, the forwarded sharing, the like, and the favorite.

[0019] Furthermore, step S5 specifically includes: S51. For a newly-launched user, obtain the user's basic information according to the authorization agreement and construct a basic information vector; S52, determining the similar user group to which the new online user belongs; S53, retrieving a similar product tag set corresponding to the similar user group; S54: Push marketing information to the new online user according to the descending order of the product tags in the similar product tag set.

[0020] Furthermore, the user portrait-based intelligent marketing method also includes: S6. Update the similar product tag set according to the browsing behavior of the new online user: obtain the product tags involved in the browsing behavior of the new online user, add them to the similar product tag set of the user group to which the new online user belongs, re-count the frequency of occurrence of each product tag, and update the similar product tag set.

[0021] The present invention also provides an intelligent marketing system based on user portraits, which is used to execute the intelligent marketing method based on user portraits, including: A user information collection module, configured to collect basic information and browsing behavior of the user through an authorization agreement, wherein the basic information includes at least gender, age, region, city, personal interest tags and the model of the electronic device used; A user portrait construction module, configured to construct a user portrait based on the information collected by the user information collection module, wherein the user portrait includes a basic information vector and a behavior information vector; A similar user determination module is configured to compare user basic information vectors according to a preset similarity vector to determine users with similar characteristics and classify them into the same user group; A product tag set building module, configured to build a similar product tag set according to the browsing behavior of users in the similar user group, and the set is sorted from high to low according to the frequency of occurrence of the product tags; A marketing information push module is configured to push personalized marketing information to a new online user based on the user profile of the new online user and the similar product tag set of the similar user group to which the new online user belongs; The data update module is configured to update the corresponding similar product tag set according to the browsing behavior of the newly online user.

[0022] The similar user determination module further includes: a vector comparison unit, used to compare the user's basic information vector with a preset similarity vector; and a user grouping unit, used to classify the user into a corresponding user group according to the comparison result.

[0023] The beneficial effects of the present invention are: 1. Improve marketing accuracy: By building detailed user portraits and building a collection of product tags based on the user's basic information and browsing behavior, it is possible to more accurately identify and reflect the user's specific needs and interests. This approach can significantly improve the targeting of marketing activities and thus increase conversion rates.

[0024] 2. Enhance user experience: By analyzing users' browsing behavior and building similar user groups, the push of marketing information will be more in line with users' actual preferences, reduce irrelevant advertising interference, enhance user experience, and improve user satisfaction and brand loyalty.

[0025] 3. Dynamically optimize marketing strategies: By continuously monitoring the behavior of newly-launched users and using this data to update the product tag sets of similar user groups, marketing strategies can be dynamically adjusted and optimized to maintain the timeliness and relevance of marketing content.

[0026] 4. Promote personalized marketing: The system can customize personalized marketing information based on the unique portrait of each user and the common characteristics of similar user groups, effectively improving user participation and interaction frequency.

[0027] 5. Optimize resource allocation: By accurately determining the similar user groups to which users belong and pushing marketing information in a targeted manner, marketing resources can be allocated more effectively, reducing resource waste and improving the overall ROI (return on investment) of marketing activities.

[0028] 6. Improvement in the profiling method: Compared with the traditional method of pushing information through the browsing behavior of a single user, there is a problem of high randomness. The present invention uses the vector method to calibrate similar groups of people, and uses big data to perform statistics on product labels to determine the common interests of similar groups of people, and then combines the user's own behavior to update the push information, thereby improving the accuracy and basic nature of the push. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a schematic diagram of the method flow of the present invention.

[0030] Figure 2 The figure is a diagram of the running result of an example program code of the method of the present invention. DETAILED DESCRIPTION

[0031] In order to deepen the understanding of the present invention, the present invention will be further described in detail below in conjunction with examples. The examples are only used to explain the present invention and do not constitute a limitation on the protection scope of the present invention.

[0032] Embodiment 1 according to Figure 1 As shown, this embodiment provides an intelligent marketing method based on user portraits, including the following steps: S1. Constructing an initial user portrait: Obtain the user's basic information according to the authorization agreement and construct a basic information vector; the user's basic characteristics include at least: gender, age, region, city, personal interest tags, and electronic device model used; the basic information vector satisfies: ; in, Indicates The basic information vector of each user, is the user serial number; Respectively represent The elements of the basic information vector of each user, is the vector dimension; Respectively represent Elements of a user's browsing behavior information collection, is the collection dimension.

[0033] S2. Construct a single-user product tag set based on the browsing behavior of a single user; obtain the product tags involved in the user's browsing behavior according to the authorization protocol, and construct a single-user product tag set; User browsing behavior at least includes: the number of pages visited, dwell time, visit frequency, link clicks, ad clicks, interface element interactions, search queries, search result clicks, video viewing, image browsing, image downloading, commenting, forwarding, sharing, liking, and collection; the single user product tag set meets the following requirements: ; in, Indicates A collection of single-user product tags for each user; Respectively represent The product tags recorded by each user’s browsing behavior, is the collection dimension.

[0034] S3. Determine similar users based on basic information vectors: According to the predetermined similarity vectors, determine users with similar basic information vectors as a similar user group; specifically, including: S31. Predetermine similarity vectors ,satisfy: ; in, Respectively represent the value ranges of the first element, the second element, and the last element of the basic information vector; S32, all basic information vectors Falling into similar vector The users are identified as a similar user group.

[0035] S4. Construct a similar user product tag set based on the browsing behavior of similar users; collect statistics on all product tags involved in the browsing behavior of all users in the same similar user group, and construct a similar product tag set in descending order of frequency of occurrence, satisfying: ; in, Indicates A collection of similar product tags for similar user groups; The product label with the highest frequency is , a total of times, and so on, The dimension of the similar product label set; S5: Push marketing information based on the user portrait of the newly launched user and the collection of similar product tags; specifically including: S51. For a newly-launched user, obtain the user's basic information according to the authorization agreement and construct a basic information vector; S52, determining the similar user group to which the new online user belongs; S53, retrieving a similar product tag set corresponding to the similar user group; S54: Push marketing information to the new online user according to the descending order of the product tags in the similar product tag set.

[0036] S6. Update the similar product tag set according to the browsing behavior of the new online user: obtain the product tags involved in the browsing behavior of the new online user, add them to the similar product tag set of the user group to which the new online user belongs, re-count the frequency of occurrence of each product tag, and update the similar product tag set.

[0037] Embodiment 2 Suppose an e-commerce website wants to implement an intelligent marketing method based on user portraits. The method aims to improve the relevance and efficiency of advertisements and product recommendations, thereby increasing users' purchase rate.

[0038] Step 1: Build an initial user persona First, collect basic user information to build an initial user profile. Suppose there is a user named Mr. A on the website, and his basic information is as follows: Gender: Male Age: 30 City: City X Personal interest tags: technology, reading, travel Electronic device model used: A certain mobile phone model 12 This information is integrated into a basic information vector:

[0039] Step 2: Build a single-user product tag set based on the browsing behavior of a single user By tracking Mr. A's website activities, we obtained the following browsing behavior data: Number of pages visited: 15; Duration: 120 minutes in total; Visit frequency: 3 times per week on average; Click on the ad: 5 times; Video views: 10 times; Image views: 20 times; Image downloads: 5 times; Comments: 2 times; Collection: 3 times;

[0040] Step 3: Determine similar users based on the basic information vector: For each type of user, we predefine the similarity vector: For example: Age range: [25, 35]; Region: X city; Step 4: Build a similar user product tag set based on the browsing behavior of similar users; Mr. A was classified into a user group with similar age, region and interests. By analyzing the browsing behavior of all members of Mr. A's user group, the following product tags appeared at different frequencies: technology products: 50 times; travel supplies: 30 times; programming books: 20 times.

[0041] The similar product tag collection is:

[0042] Step 5: Marketing information push: When a new user, Ms. B, joins the website, she is classified into the user group of Mr. A based on her basic information. Ms. B's interests also include technology and travel. Based on a set of similar product tags, advertisements and discount information about technology products, travel products, and programming books are pushed to her in order.

[0043] Step 6: Update the similar product tag collection: Ms. B's activities on the website generate new browsing data. She clicks and purchases technology products particularly frequently, so the similar product tag set is updated to: technology products: 55 times; travel supplies: 30 times; programming books: 20 times.

[0044] This embodiment illustrates how to achieve personalized marketing and increase user engagement and purchase intention by dynamically building and updating user portraits and product tag sets for similar user groups.

[0045] For the above embodiment, the present invention provides an exemplary program code: import math from collections import defaultdict # Example User Data users = [ {'id': 1, 'gender': 'M', 'age': 25, 'region': 'East', 'device': 'iPhone', 'browsing': ['Shoes', 'Bags', 'Hats']}, {'id': 2, 'gender': 'F', 'age': 23, 'region': 'West', 'device': 'Android', 'browsing': ['Shoes', 'Jewelry']}, {'id': 3, 'gender': 'M', 'age': 30, 'region': 'East', 'device': 'iPhone', 'browsing': ['Bags', 'Hats']}, {'id': 4, 'gender': 'F', 'age': 22, 'region': 'West', 'device': 'Android', 'browsing': ['Jewelry', 'Shoes']}, ] # S1. Construct basic information vector def build_basic_vector(user): # Gender: 0 for male, 1 for female; Device: 0 for iPhone, 1 for Android gender_value = 0 if user['gender'] == 'M' else 1 device_value = 0 if user['device'] == 'iPhone' else 1 return [gender_value, user['age'], device_value] # S2. Build a single user product tag collection def build_single_user_tags(user): return set(user['browsing']) # Calculate the Euclidean distance between two vectors def calculate_distance(vec1, vec2): return math.sqrt(sum((a - b) ** 2 for a, b in zip(vec1, vec2))) # S3. Determine similar user groups based on basic information vectors def find_similar_users(users, target_user, threshold=5): target_vector = build_basic_vector(target_user) similar_users = [] for user in users: if user['id'] != target_user['id']: # exclude the target user itself user_vector = build_basic_vector(user) # Calculate vector distance (Euclidean distance) distance = calculate_distance(target_vector, user_vector) if distance <threshold: similar_users.append(user) return similar_users # S4. Build a collection of similar user product tags def build_similar_user_tags(similar_users): tag_counts = defaultdict(int) for user in similar_users: for tag in user['browsing']: tag_counts[tag] += 1 # Sort by frequency and return a tag set sorted_tags = sorted(tag_counts.items(), key=lambda x: x[1],reverse=True) return sorted_tags # S5. Push personalized marketing information def push_marketing_info(target_user, similar_tags): print(f"Push the following personalized marketing information to user {target_user['id']}:") for tag, freq in similar_tags: print(f"Recommended products: {tag}, frequency of occurrence: {freq}") # S51. Simulate pushing personalized marketing information to new users def marketing_for_new_user(new_user, users): print(f"--- Build user portrait, user ID: {new_user['id']} ---") # S52. Find similar users similar_users = find_similar_users(users, new_user) if similar_users: print(f"Similar user groups found, total {len(similar_users)} users") # S53. Build a collection of similar product tags similar_tags = build_similar_user_tags(similar_users) # S54. Push personalized marketing information push_marketing_info(new_user, similar_tags) else: print(f"No similar user groups found.") # Verify usage new_user = {'id': 5, 'gender': 'F', 'age': 23, 'region': 'West', 'device': 'Android', 'browsing': []} marketing_for_new_user(new_user, users) The verification results of the program code are as follows Figure 2 As shown, the program exit code is 0, indicating that the program runs correctly without error.

[0046] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An intelligent marketing method based on user portraits, It is characterized in that The following steps are involved: S1. Build the initial user portrait: obtain the user's basic information according to the authorization agreement and build the basic information vector; S2. Construct a single-user product tag set based on the browsing behavior of a single user; obtain the product tags involved in the user's browsing behavior according to the authorization protocol, and construct a single-user product tag set; S3, determining similar users based on basic information vectors: according to the predetermined similarity vectors, determining users with similar basic information vectors as a similar user group; S4. Construct a similar user product tag set based on the browsing behavior of similar users; collect statistics on all product tags involved in the browsing behavior of all users in the same similar user group, and construct a similar product tag set in descending order of frequency of occurrence, satisfying: ; in, Indicates A collection of similar product tags for similar user groups; The product label with the highest frequency is , a total of times, and so on, The dimension of the similar product label set; S5. Push marketing information based on the user portrait of the newly-launched user and a collection of similar product tags.

2. According to the intelligent marketing method based on user portraits according to claim 1, Features: In step S1, the basic information vector satisfies: ; in, Indicates The basic information vector of each user, is the user serial number; Respectively represent The elements of the basic information vector of each user, is the vector dimension; Respectively represent Elements of a user's browsing behavior information collection, is the collection dimension.

3. According to the intelligent marketing method based on user portraits according to claim 1, Features: In step S1, the single-user product tag set satisfies: ; in, Indicates A collection of single-user product tags for each user; Respectively represent The product tags recorded by each user’s browsing behavior, is the collection dimension.

4. According to claim 1, a user portrait-based intelligent marketing method, Features: Step S3 specifically includes: S31. Predetermine similarity vectors ,satisfy: ; in, Respectively represent the value ranges of the first element, the second element, and the last element of the basic information vector; S32, all basic information vectors Falling into similar vector The users are identified as a similar user group.

5. According to claim 1, a user portrait-based intelligent marketing method, Features: In step S1, the basic characteristics of the user include at least: gender, age, region, city, personal interest tags, and the model of the electronic device used.

6. According to claim 1, a user portrait-based intelligent marketing method, Features: In step S2, the user browsing behavior includes at least: the number of pages visited, the dwell time, the visit frequency, the clicked links, the clicked advertisements, the interaction with the interface elements, the search query, the clicked search results, the video watched, the picture browsed, the picture downloaded, the comment, the forwarded sharing, the like, and the favorite.

7. According to claim 1, a user portrait-based intelligent marketing method, Features: Step S5 specifically includes: S51. For a newly-launched user, obtain the user's basic information according to the authorization agreement and construct a basic information vector; S52, determining the similar user group to which the new online user belongs; S53, retrieving a similar product tag set corresponding to the similar user group; S54: Push marketing information to the new online user according to the descending order of the product tags in the similar product tag set.

8. According to claim 1, a user portrait-based intelligent marketing method, It is characterized in that The user portrait-based intelligent marketing method further includes: S6. Update the similar product tag set according to the browsing behavior of the new online user: obtain the product tags involved in the browsing behavior of the new online user, add them to the similar product tag set of the user group to which the new online user belongs, re-count the frequency of occurrence of each product tag, and update the similar product tag set.

9. An intelligent marketing system based on user portrait, used to execute an intelligent marketing method based on user portrait according to any one of claims 1 to 8, It is characterized in that include: A user information collection module, configured to collect basic information and browsing behavior of the user through an authorization agreement, wherein the basic information includes at least gender, age, region, city, personal interest tags and the model of the electronic device used; A user portrait construction module, configured to construct a user portrait based on the information collected by the user information collection module, wherein the user portrait includes a basic information vector and a behavior information vector; A similar user determination module is configured to compare user basic information vectors according to a preset similarity vector to determine users with similar characteristics and classify them into the same user group; A product tag set building module, configured to build a similar product tag set according to the browsing behavior of users in the similar user group, and the set is sorted from high to low according to the frequency of occurrence of the product tags; A marketing information push module is configured to push personalized marketing information to a new online user based on the user profile of the new online user and the similar product tag set of the similar user group to which the new online user belongs; The data update module is configured to update the corresponding similar product tag set according to the browsing behavior of the newly online user.

10. The intelligent marketing system based on user portrait according to claim 9, It is characterized in that The similar user determination module further comprises: a vector comparison unit, used to compare the user's basic information vector with a preset similarity vector; A user grouping unit is used to classify users into corresponding user groups according to the comparison results.

Citation Information

Patent Citations

  • Information push method and apparatus based on similarity degree between users

    CN105095256A

  • Information recommendation method and device, server and storage medium

    CN107784066A

  • Data commodity recommendation method based on edge calculation

    CN110335116A

  • Method for intelligently generating personalized combined promotion scheme and system with method

    CN111652648A

  • Commodity recommendation method, system and device and medium

    CN112070577A

Cited By

  • Portrayal marking method and device based on flow data, and computer equipment

    CN119313985A

  • Product portrait self-adaptive construction method

    CN119784411A

  • User data processing method and device based on user portrait and computer equipment

    CN120822016A

  • Consumption financial sales clue network construction method based on large language model

    CN121836773A