Commodity recommendation method and system applied to point system

Abstract

The invention discloses a commodity recommendation method and system applied to an integral system, and belongs to the technical field of computer information processing.The commodity recommendation method and system applied to the integral system comprise the following specific steps that firstly, data collection is conducted, acquiring various operation data of a user in an integral system in real time, and when the user acquires an integral, recording an integral acquisition path and quantity; when the user exchanges the commodity, the name of the exchanged commodity, the credits required by the exchange and the exchange time are recorded, and the data are stored in a special database for subsequent analysis and use. Through deep analysis of user data and a personalized recommendation algorithm, commodities meeting requirements and preferences of users can be accurately recommended to the users.

Description

Technical Field

[0001] The present invention belongs to the technical field of computer information processing, and particularly relates to a commodity recommendation method and system applied to an integral system. Background Art

[0002] In the existing integral system, commodity recommendation often lacks pertinence. Usually, it simply recommends according to the popularity of commodities or fixed categories, without fully considering factors such as users' integral usage habits, historical consumption behaviors, and personal preferences. This results in a low matching degree between the recommended commodities and users' actual needs, low interest of users in redeeming commodities with integral, and inability to effectively improve the activity and user stickiness of the integral system. For example, some users may be more inclined to redeem electronic products, but the integral system frequently recommends daily necessities, making it difficult for users to find commodities that meet their needs and reducing the user experience. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to overcome the above-mentioned disadvantages of the prior art and provide a commodity recommendation method and system applied to an integral system.

[0004] The technical solution adopted to solve the above technical problem is: A commodity recommendation method applied to an integral system, including the following specific steps:

[0005] Step 1: Data collection:

[0006] Set up a data collection program on the server side of the integral system to collect various operation data of users in the integral system in real time. When a user obtains integral, record the way and quantity of integral acquisition;

[0007] When a user redeems a commodity, record the name of the redeemed commodity, the integral required for redemption, and the redemption time, and store these data in a special database for subsequent analysis and use;

[0008] Step 2: Data analysis and user portrait establishment;

[0009] Regularly start a data analysis task, use data analysis tools to process and analyze the collected data, extract the key features and behavior patterns of users, and construct a user portrait;

[0010] Step 3: Commodity recommendation:

[0011] When a user logs in to the points system, the system retrieves the user's portrait information from the user portrait database based on the user's ID. Then, the user portrait information is input into the recommendation algorithm module. The recommendation algorithm module filters out a list of recommended products from the product library according to the collaborative filtering algorithm and the content-based recommendation algorithm, and displays the list of recommended products on the user interface. The user clicks to view the product details and perform the redemption operation;

[0012] Step Four: Real-time Update and Optimization:

[0013] During the process of the user using the points system, the system monitors the user's behavior data in real time. When the user has new behaviors such as points acquisition, use, or product browsing, the relevant information in the user portrait database is updated in a timely manner.

[0014] Through the above technical solutions, through in-depth analysis of user data and personalized recommendation algorithms, it is possible to accurately recommend products that meet the user's needs and preferences for the user, greatly improving the matching degree between product recommendations and the user's actual needs, and enabling the user to find the products they are interested in more quickly.

[0015] Furthermore, it includes a data collection module, a data storage module, a data analysis module, a user portrait module, a recommendation algorithm module, and a result display module. The data collection module is responsible for collecting various types of behavior data of the user in the points system in real time and transmitting this data to the data storage module.

[0016] Furthermore, the data storage module uses database technology to structurally store the collected data, ensuring the integrity and security of the data, and facilitating subsequent data query and analysis calls.

[0017] Furthermore, the data analysis module uses data mining and analysis algorithms to deeply process the stored data, extract key user information, and provide data support for user portrait construction and recommendation algorithms. The user portrait module generates a dedicated user portrait for each user according to the data analysis results, integrating the user's basic information, points-related information, and preference tags to form a comprehensive user feature description.

[0018] Furthermore, the recommendation algorithm module combines the collaborative filtering algorithm and the content-based recommendation algorithm, calculates a list of product recommendations suitable for each user according to the user portrait and product information, and the result display module is responsible for presenting the list of product recommendations generated by the recommendation algorithm to the user in an intuitive interface form, facilitating the user to view and select the products they are interested in for points redemption.

[0019] Furthermore, the following specific formula is used for points acquisition:

[0020]

[0021] Among them, I a represents the total points obtained by the user, n represents the number of ways to obtain points, and w i represents the point weight of the i-th way, and a i represents the point value obtained through the i-th way;

[0022] The point level adopts the following specific formula:

[0023] L = f(I t )

[0024] Among them, L represents the point level, and I t represents the total points accumulated by the user, and f is a mapping function that sets different point levels according to different point intervals.

[0025] Through the above technical solutions, the user stickiness of the point system is enhanced. At the same time, personalized product recommendations stimulate users' enthusiasm for participating in point activities, promote the circulation and use of points, and improve the overall activity of the point system.

[0026] Furthermore, the points for recommended products adopt a matching degree formula, which is specifically as follows:

[0027]

[0028] Among them, M represents the matching degree between the recommended product and the user's points, m represents the number of factors affecting the matching degree, and s j represents the weight of the j-th factor, and p j represents the value of the j-th factor. The value is related to the user's point balance and the points required for the product. The smaller the difference between the user's point balance and the points required for the product, the larger the value of p j is.

[0029] The beneficial effects of the present invention are as follows: Through in-depth analysis of user data and personalized recommendation algorithms, the present invention can accurately recommend products that meet the needs and preferences of users, greatly improving the matching degree between product recommendations and users' actual needs, enabling users to find the products they are interested in more quickly, enhancing the enthusiasm and satisfaction of point redemption, thereby enhancing the user stickiness of the point system. At the same time, personalized product recommendations stimulate users' enthusiasm for participating in point activities, promote the circulation and use of points, and improve the overall activity of the point system. Brief Description of the Drawings

[0030] Figure 1 is the method flow chart of the present invention Detailed Embodiments

[0031] To make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0032] As Figure 1 shown, a product recommendation method and system applied to an integral system in this embodiment includes the following specific steps:

[0033] Step 1: Data collection:

[0034] Set up a data collection program on the server side of the integral system to collect various operation data of users in the integral system in real time. When a user obtains points, record the ways and quantities of point acquisition;

[0035] When a user exchanges products, record the names of the exchanged products, the points required for exchange, and the exchange time, and store this data in a dedicated database for subsequent analysis and use;

[0036] Step 2: Data analysis and user portrait establishment;

[0037] Regularly start a data analysis task, use data analysis tools to process and analyze the collected data, extract the key features and behavior patterns of users, and construct user portraits;

[0038] Step 3: Product recommendation:

[0039] When a user logs in to the integral system, the system obtains the user's portrait information from the user portrait database according to the user's ID. Then, input the user portrait information into the recommendation algorithm module. The recommendation algorithm module screens out a recommended product list from the product library according to the collaborative filtering algorithm and the content-based recommendation algorithm, and displays the recommended product list on the user interface. The user clicks to view the product details and perform an exchange operation;

[0040] Step 4: Real-time update and optimization:

[0041] During the process of a user using the integral system, the system monitors the user's behavior data in real time. When the user has new point acquisition, use or product browsing behavior, update the relevant information in the user portrait database in a timely manner. Through in-depth analysis of user data and personalized recommendation algorithms, it is possible to accurately recommend products that meet the user's needs and preferences for the user, greatly improving the matching degree between product recommendation and the user's actual needs, and enabling the user to find the products they are interested in more quickly.

[0042] It includes a data collection module, a data storage module, a data analysis module, a user profile module, a recommendation algorithm module, and a result display module. The data collection module is responsible for collecting various types of behavioral data of users in the points system in real time and transmitting this data to the data storage module.

[0043] The data storage module uses database technology to structurally store the collected data, ensuring the integrity and security of the data, and facilitating subsequent data query and analysis calls.

[0044] The data analysis module uses data mining and analysis algorithms to deeply process the stored data, extract key user information, and provide data support for user profile construction and recommendation algorithms. The user profile module generates a dedicated user profile for each user based on the data analysis results, integrating the user's basic information, points-related information, and preference tags to form a comprehensive description of user characteristics.

[0045] The recommendation algorithm module combines collaborative filtering algorithms and content-based recommendation algorithms. According to the user profile and product information, it calculates a list of product recommendations suitable for each user. The result display module is responsible for presenting the list of product recommendations generated by the recommendation algorithm to the user in an intuitive interface form, facilitating the user to view and select the products of interest for points redemption.

[0046] Points acquisition uses the following specific formula:

[0047]

[0048] Where I a represents the total points obtained by the user, n represents the number of ways to obtain points, w i represents the points weight of the i-th way, a i represents the points value obtained through the i-th way;

[0049] The points level uses the following specific formula:

[0050] L = f(I t )

[0051] Where L represents the points level, I t represents the total accumulated points of the user, and f is a mapping function that sets different points levels according to different points intervals, enhancing the user stickiness of the points system. At the same time, personalized product recommendations stimulate the enthusiasm of users to participate in points activities, promote the circulation and use of points, and improve the overall activity of the points system.

[0052] The points for recommended products use a matching degree formula, specifically as follows:

[0053]

[0054] Where M represents the matching degree between the recommended product and the user's points, m represents the number of factors affecting the matching degree, and s j represents the weight of the j-th factor, and p j represents the value of the j-th factor. The value is related to the user's points balance and the points required for the product. The smaller the difference between the user's points balance and the points required for the product, the larger the value of p j is.

[0055] The above is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A commodity recommendation method applied to a points system, characterized in that: The specific steps include: Step 1: Data Collection: A data collection program is set up on the server side of the points system to collect various operation data of users in the points system in real time. When users obtain points, the method and amount of points obtained are recorded; When a user redeems a product, the name of the product, the points required for redemption, and the time of redemption are recorded, and this data is stored in a dedicated database for subsequent analysis; Step 2: Data analysis and user portrait creation; Regularly launch data analysis tasks, use data analysis tools to process and analyze the collected data, extract key features and behavior patterns of users, and build user portraits; Step 3: Product Recommendation: When a user logs in to the points system, the system obtains the user's portrait information from the user portrait database based on the user's ID, and then inputs the user portrait information into the recommendation algorithm module. The recommendation algorithm module selects a list of recommended products from the product library based on the collaborative filtering algorithm and the content-based recommendation algorithm, and displays the recommended product list on the user interface. The user clicks to view the product details and performs redemption operations; Step 4: Real-time update and optimization: When users use the points system, the system monitors the users' behavior data in real time. When users acquire, use or browse new points, the system promptly updates the relevant information in the user portrait database.

2. A commodity recommendation system applied to a points system according to claim 1, characterized in that: It includes data collection module, data storage module, data analysis module, user portrait module, recommendation algorithm module and result display module. The data collection module is responsible for collecting various behavioral data of users in the points system in real time and transmitting these data to the data storage module.

3. A commodity recommendation system applied to a points system according to claim 2, characterized in that: The data storage module uses database technology to perform structured storage of the collected data, ensuring the integrity and security of the data and facilitating subsequent data query and analysis calls.

4. A commodity recommendation system applied to a points system according to claim 3, characterized in that: The data analysis module uses data mining and analysis algorithms to deeply process the stored data, extract key user information, and provide data support for user portrait construction and recommendation algorithms. The user portrait module generates an exclusive user portrait for each user based on the data analysis results, integrating basic user information, points-related information, and preference tags to form a comprehensive user feature description.

5. A commodity recommendation system applied to a points system according to claim 4, characterized in that: The recommendation algorithm module combines the collaborative filtering algorithm and the content-based recommendation algorithm to calculate a product recommendation list suitable for each user based on the user portrait and product information. The result display module is responsible for displaying the product recommendation list generated by the recommendation algorithm to the user in an intuitive interface, making it convenient for users to view and select products of interest for points redemption.

6. A commodity recommendation system applied to a points system according to claim 5, characterized in that: Points are earned using the following specific formula: Among them I a represents the total points obtained by the user, n represents the number of ways to obtain points, and w i represents the integral weight of the ith path, a i represents the integral value obtained through the i-th path; The specific formula for the points level is as follows: L=f(I t ) Where L represents the integral level, I t It represents the total points accumulated by the user. f is a mapping function that sets different points levels according to different points intervals.

7. A commodity recommendation method and system applied to a points system according to claim 6, characterized in that: The recommended product points are calculated using the matching formula, as follows: Where M represents the matching degree between the recommended product and the user's points, m represents the number of factors affecting the matching degree, and s j represents the weight of the jth factor, p j represents the value of the jth factor, which is related to the user's points balance and the points required for the product. The smaller the difference between the user's points balance and the points required for the product, the higher the p j The larger the value.

Images