A store recommendation method based on big data exchange
By analyzing user information and store data through big data exchange technology, calculating evaluation coefficients, and accurately recommending stores, this technology solves the problem that user needs and preferences are not deeply analyzed in existing technologies, thereby improving store operating efficiency and user satisfaction.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SUZHOU MAIJIE IND BIG DATA IND RES INST CO LTD
- Filing Date
- 2023-07-31
- Publication Date
- 2026-06-09
Smart Images
Figure CN117150118B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of big data exchange technology, and more specifically to a store recommendation method based on big data exchange. Background Technology
[0002] With the rapid development of the Internet and big data exchange technology, users can experience more intelligent data service models. Big data exchange technology is mainly used in telemarketing. Big data exchange can accurately capture the preferences and needs of different users, provide personalized services, and follow up and promote in a timely manner based on customers' purchase intentions and purchase time, thereby increasing sales rates. It can also promptly identify changes in customer needs and dissatisfaction, and take appropriate measures to solve problems, thereby improving customer satisfaction and loyalty.
[0003] Current technology primarily relies on clicks on shopping platforms to push relevant information, without delving into the needs and preferences of users. Therefore, this analytical approach clearly suffers from at least the following problems:
[0004] Current technology doesn't provide in-depth analysis and understanding of users and stores. This makes it difficult to accurately understand user preferences and shopping habits, hindering the recommendation of relevant products and attracting more user traffic. Consequently, store efficiency decreases, negatively impacting operations and hindering customer retention, thus weakening the store's foundation. Furthermore, neglecting user feedback significantly reduces positive customer impressions. On the other hand, a lack of in-depth understanding of the store prevents it from immediately attracting users, reducing purchase frequency, lowering competitiveness, and ultimately leading to lower operational efficiency and potential losses. Summary of the Invention
[0005] To address the aforementioned technical shortcomings, the purpose of this invention is to provide a store recommendation method based on big data exchange.
[0006] To solve the above technical problems, the present invention adopts the following technical solution: The present invention provides a store recommendation method based on big data exchange, including: Step 1, user information acquisition: by acquiring the basic information of each user on the shopping platform, wherein the basic information of each user on the shopping platform includes the number of times the user uses the shopping platform and the duration of the user's browsing on the shopping platform;
[0007] Step 2: User Information Analysis: By analyzing the basic information of each user on the shopping platform, we can obtain the demand assessment coefficient of each user and determine the demand situation of each user to identify the target users, thus proceeding to Step 3.
[0008] Step 3: User Profile Acquisition: This involves acquiring basic information about each target user's profile, including purchase frequency, product price, repurchase frequency, and positive review frequency for each store.
[0009] Step 4: User Profile Analysis: Based on the basic information of each target user's profile in each store, analyze and obtain the preference evaluation coefficient of each target user in each store, and determine the purchase desire of each target user in each store. If the purchase desire is strong, proceed to Step 5.
[0010] Step 5: User Maintenance Analysis: By analyzing the number of returns and exchanges and the price difference of goods for each target user in each store, we can obtain the evaluation coefficient of each target user in each store, and then proceed to Step 6.
[0011] Step Six: Obtaining Store Information: This involves obtaining basic information about each store on the shopping platform, including the store's level, operating duration, number of followers, store rating, sales volume, and after-sales resolution speed.
[0012] Step 7: Store Information Analysis: By obtaining basic information about each store on the shopping platform, we can then analyze and derive the recommendation evaluation coefficient for each target user in each store, thus obtaining the recommended stores for each target user.
[0013] Preferably, the demand evaluation coefficients of each user on the shopping platform are analyzed to determine the degree of demand for each user. The specific analysis process is as follows:
[0014] Through calculation formula The analysis yielded the demand assessment coefficients for each user on the shopping platform. , where i represents the user's ID. , , These represent the preset weighting factors for the number of times a user uses the shopping platform and the duration of time a user browses the shopping platform. , Let represent the number of times the i-th user uses the shopping platform and the duration of browsing the shopping platform, respectively. , These represent the preset number of times a user uses the shopping platform and the duration of time a user browses the shopping platform, respectively.
[0015] The threshold for evaluating the demand of each user on the shopping platform is compared with the preset threshold for evaluating the demand of users on the shopping platform. If the threshold for evaluating the demand of a user on the shopping platform is less than the preset threshold, the user is considered to have a low demand and will not be considered a target user. If the threshold for evaluating the demand of a user on the shopping platform is greater than the preset threshold, the user is considered to have a high demand and will be considered a target user. Target users are obtained in this way.
[0016] Preferably, the preference evaluation coefficients of each target user in each store are analyzed and the purchase desire of each target user in each store is determined. The specific analysis process is as follows:
[0017] Through calculation formula The analysis yielded the preference evaluation coefficients for each target user in each store. f represents the ID of each target user. y represents the store number. , , , , These represent the weighting factors for the preset target user's purchase frequency, product price, repurchase frequency, and positive review frequency, respectively. , , , Let f represent the number of purchases, product price, repurchase frequency, and positive review frequency of the f-th user in the y-th store, respectively. , , , These represent the number of purchases, product price, repurchase frequency, and positive review frequency for the preset target users, respectively.
[0018] The system compares the preference evaluation coefficient threshold of each target user in each store with the preset preference evaluation coefficient threshold of each target user in each store. If the preference evaluation coefficient threshold of a target user in a store is greater than the preset preference evaluation coefficient threshold of a target user in a store, it is determined that the user has a strong desire to buy and a comprehensive recommendation of products based on their preferences is made. If the preference evaluation coefficient threshold of a target user in a store is less than the preset preference evaluation coefficient threshold of a target user in a store, it is determined that the user has a weak desire to buy.
[0019] Preferably, the further analysis yields the evaluation coefficients for each target user in each store, and the specific analysis process is as follows:
[0020] Through calculation formula The analysis yielded the evaluation coefficients for each target user in each store. f represents the ID of each target user. y represents the store number. , , These represent the preset weighting factors for the number of returns / exchanges and the price difference of goods for each target user in each store. , Let f represent the number of returns / exchanges and the price difference of the product for the f-th target user in the y-th store, respectively. , These represent the preset number of returns / exchanges and the price difference of goods for each target user in each store.
[0021] Preferably, the further analysis yields the recommendation evaluation coefficient for each target user in each store, and the specific analysis process is as follows:
[0022] Based on the target user's level and operating time in each store on the shopping platform, the level evaluation coefficient for each target user in each store on the shopping platform is calculated. y represents the store number. ;
[0023] Based on the store ratings and follower counts of each target user on the shopping platform for each store, the store evaluation coefficient for each target user on the shopping platform for each store is calculated. ;
[0024] Based on the sales volume and after-sales resolution speed of each target user on the shopping platform in each store, the store quality evaluation coefficient for each target user on the shopping platform in each store is calculated. ;
[0025] Through calculation formula The analysis yielded the recommendation evaluation coefficients for each target user in each store. , , , , , These represent the weighting factors for the preset store rating evaluation coefficient, store score evaluation coefficient, store good evaluation coefficient, preference evaluation coefficient, and review evaluation coefficient, respectively. , , These represent the preset store rating evaluation coefficient, store evaluation coefficient, and store good evaluation coefficient, respectively. , Let F represent the preference evaluation coefficient and the rating evaluation coefficient of the f-th target user in the y-th store, respectively.
[0026] The recommendation evaluation coefficient threshold for each target user in each store is compared with the preset recommendation evaluation coefficient threshold for each target user in each store. If the recommendation evaluation coefficient threshold for a target user in a store is greater than the preset recommendation evaluation coefficient threshold for each target user in a store, then each target user is selected as a target recommended store. If the recommendation evaluation coefficient threshold for a target user in a store is less than the preset recommendation evaluation coefficient threshold for each target user in a store, then it is not selected as a target recommended store for each target user.
[0027] Preferably, the calculation of the rating coefficients for each target user on the shopping platform in each store is performed as follows:
[0028] Through calculation formula The rating coefficients for each target user on the shopping platform in each store were calculated. , , These represent the weighting factors for the standard store's rating and operating duration, respectively. , Let f represent the target user's level and operating time in the y-th store, respectively. , These represent the standard store level and operating duration, respectively.
[0029] Preferably, the calculation of the store evaluation coefficient for each target user on the shopping platform is performed in each store, and the specific analysis process is as follows:
[0030] Through calculation formula The store evaluation coefficients for each target user on the shopping platform in each store were calculated. , , These represent the standard number of followers and the weighting factors for store ratings, respectively. , Let f represent the number of followers and the store rating of the f-th target user in the y-th store, respectively. , These are represented as standard follower count and store rating, respectively.
[0031] Preferably, the calculation of the store preference evaluation coefficient for each target user on the shopping platform is performed in each store, and the specific analysis process is as follows:
[0032] Through calculation formula The store satisfaction rating coefficient for each target user on the shopping platform for each store was calculated. , , These represent the weighting factors for standard store sales volume and after-sales resolution speed, respectively. , Let represent the sales volume and after-sales resolution speed of the f-th target user in the y-th store, respectively. , These are respectively represented as the standard store's sales volume and after-sales resolution speed.
[0033] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention provides a store recommendation method based on big data exchange. By analyzing user information, it better understands users' usage of shopping platforms. Through user profile analysis, it better derives the preference evaluation coefficients of each target user in each store. Through user maintenance analysis, it better derives the evaluation coefficients of each target user in each store, and thus better analyzes the recommendation evaluation coefficients of each target user in each store, obtaining recommended stores for each target user. This helps users find stores that better match their desired products. It provides an in-depth analysis of users' shopping preferences and needs, enabling a comprehensive understanding of users and overcoming the shortcomings of current technologies. It allows for a better understanding of user thoughts, thereby improving store purchase rates. It also effectively understands the reasons for user returns and exchanges, allowing for better improvement of the business system, thus better retaining existing customers and attracting new customers. Attached Figure Description
[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0035] Figure 1 This is a schematic diagram of the implementation steps of the method of the present invention. Detailed Implementation
[0036] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0037] Please see Figure 1 As shown, a store recommendation method based on big data exchange includes user information acquisition, user information analysis, user profile acquisition, user profile analysis, user maintenance analysis, store information acquisition, and store information analysis.
[0038] The user information acquisition is connected to user information analysis and user profile acquisition, the user profile analysis is connected to user maintenance analysis and store information acquisition, and the user profile analysis is connected to user maintenance analysis and store information analysis.
[0039] Step 1: Obtaining User Information: This involves obtaining basic information about each user on the shopping platform, including the number of times the user has used the shopping platform and the duration of their browsing time.
[0040] It should be noted that shopping platforms include, but are not limited to, Taobao, Pinduoduo, and JD.com.
[0041] It should also be noted that the basic information of the shopping platform is obtained from the mobile phone's backend records and monitoring.
[0042] Step 2: User Information Analysis: By analyzing the basic information of each user on the shopping platform, we can obtain the demand assessment coefficient of each user and determine the demand situation of each user to identify the target users, thus proceeding to Step 3.
[0043] As an optional implementation method, the analysis yields demand evaluation coefficients for each user on the shopping platform and determines the degree of demand for each user. The specific analysis process is as follows:
[0044] Through calculation formula The analysis yielded the demand assessment coefficients for each user on the shopping platform. , where i represents the user's ID. , , These represent the preset weighting factors for the number of times a user uses the shopping platform and the duration of time a user browses the shopping platform. , Let represent the number of times the i-th user uses the shopping platform and the duration of browsing the shopping platform, respectively. , These represent the preset number of times a user uses the shopping platform and the duration of time a user browses the shopping platform, respectively.
[0045] The threshold for evaluating the demand of each user on the shopping platform is compared with the preset threshold for evaluating the demand of users on the shopping platform. If the threshold for evaluating the demand of a user on the shopping platform is less than the preset threshold, the user is considered to have a low demand and will not be considered a target user. If the threshold for evaluating the demand of a user on the shopping platform is greater than the preset threshold, the user is considered to have a high demand and will be considered a target user. Target users are obtained in this way.
[0046] Step 3: User Profile Acquisition: This involves acquiring basic information about each target user's profile, including purchase frequency, product price, repurchase frequency, and positive review frequency for each store.
[0047] It should be noted that the basic information in the profile was obtained from the purchase records on the shopping platform.
[0048] Step 4: User Profile Analysis: Based on the basic information of each target user's profile in each store, analyze and obtain the preference evaluation coefficient of each target user in each store, and determine the purchase desire of each target user in each store. If the purchase desire is strong, proceed to Step 5.
[0049] As an optional implementation, the analysis yields the preference evaluation coefficients of each target user in each store and determines the purchase desire of each target user in each store. The specific analysis process is as follows:
[0050] Through calculation formula The analysis yielded the preference evaluation coefficients for each target user in each store. f represents the ID of each target user. y represents the store number. , , , , These represent the weighting factors for the preset target user's purchase frequency, product price, repurchase frequency, and positive review frequency, respectively. , , , Let f represent the number of purchases, product price, repurchase frequency, and positive review frequency of the f-th user in the y-th store, respectively. , , , These represent the number of purchases, product price, repurchase frequency, and positive review frequency for the preset target users, respectively.
[0051] The system compares the preference evaluation coefficient threshold of each target user in each store with the preset preference evaluation coefficient threshold of each target user in each store. If the preference evaluation coefficient threshold of a target user in a store is greater than the preset preference evaluation coefficient threshold of a target user in a store, it is determined that the user has a strong desire to buy and a comprehensive recommendation of products based on their preferences is made. If the preference evaluation coefficient threshold of a target user in a store is less than the preset preference evaluation coefficient threshold of a target user in a store, it is determined that the user has a weak desire to buy.
[0052] Step 5: User Maintenance Analysis: By analyzing the number of returns and exchanges and the price difference of goods for each target user in each store, we can obtain the evaluation coefficient of each target user in each store, and then proceed to Step 6.
[0053] As an optional implementation method, the evaluation coefficients for each target user in each store are further analyzed, and the specific analysis process is as follows:
[0054] Through calculation formula The analysis yielded the evaluation coefficients for each target user in each store. f represents the ID of each target user. y represents the store number. , , These represent the preset weighting factors for the number of returns / exchanges and the price difference of goods for each target user in each store. , Let f represent the number of returns / exchanges and the price difference of the product for the f-th target user in the y-th store, respectively. , These represent the preset number of returns / exchanges and the price difference of goods for each target user in each store.
[0055] Step Six: Obtaining Store Information: This involves obtaining basic information about each store on the shopping platform, including the store's level, operating duration, number of followers, store rating, sales volume, and after-sales resolution speed.
[0056] It should be noted that the basic information of each store is obtained from the shopping platform.
[0057] Step 7: Store Information Analysis: By obtaining basic information about each store on the shopping platform, we can then analyze and derive the recommendation evaluation coefficient for each target user in each store, thus obtaining the recommended stores for each target user.
[0058] As an optional implementation method, the recommendation evaluation coefficient of each target user in each store is further analyzed, and the specific analysis process is as follows:
[0059] Based on the target user's level and operating time in each store on the shopping platform, the level evaluation coefficient for each target user in each store on the shopping platform is calculated. y represents the store number. ;
[0060] Based on the store ratings and follower counts of each target user on the shopping platform for each store, the store evaluation coefficient for each target user on the shopping platform for each store is calculated. ;
[0061] Based on the sales volume and after-sales resolution speed of each target user on the shopping platform in each store, the store quality evaluation coefficient for each target user on the shopping platform in each store is calculated. ;
[0062] Through calculation formula The analysis yielded the recommendation evaluation coefficients for each target user in each store. , , , , , These represent the weighting factors for the preset store rating evaluation coefficient, store score evaluation coefficient, store good evaluation coefficient, preference evaluation coefficient, and review evaluation coefficient, respectively. , , These represent the preset store rating evaluation coefficient, store evaluation coefficient, and store good evaluation coefficient, respectively. , Let F represent the preference evaluation coefficient and the rating evaluation coefficient of the f-th target user in the y-th store, respectively.
[0063] The recommendation evaluation coefficient threshold for each target user in each store is compared with the preset recommendation evaluation coefficient threshold for each target user in each store. If the recommendation evaluation coefficient threshold for a target user in a store is greater than the preset recommendation evaluation coefficient threshold for each target user in a store, then each target user is selected as a target recommended store. If the recommendation evaluation coefficient threshold for a target user in a store is less than the preset recommendation evaluation coefficient threshold for each target user in a store, then it is not selected as a target recommended store for each target user.
[0064] As an optional implementation, the calculation of the rating coefficients for each target user on the shopping platform in each store is as follows:
[0065] Through calculation formula The rating coefficients for each target user on the shopping platform in each store were calculated. , , These represent the weighting factors for the standard store's rating and operating duration, respectively. , Let f represent the target user's level and operating time in the y-th store, respectively. , These represent the standard store level and operating duration, respectively.
[0066] As an optional implementation, the calculation of the store evaluation coefficient for each target user on the shopping platform is as follows:
[0067] Through calculation formula The store evaluation coefficients for each target user on the shopping platform in each store were calculated. , , These represent the standard number of followers and the weighting factors for store ratings, respectively. , Let f represent the number of followers and the store rating of the f-th target user in the y-th store, respectively. , These are represented as standard follower count and store rating, respectively.
[0068] As an optional implementation, the calculation of the store preference evaluation coefficient for each target user on the shopping platform is as follows:
[0069] Through calculation formula The store satisfaction rating coefficient for each target user on the shopping platform for each store was calculated. , , These represent the weighting factors for standard store sales volume and after-sales resolution speed, respectively. , Let represent the sales volume and after-sales resolution speed of the f-th target user in the y-th store, respectively. , These are respectively represented as the standard store's sales volume and after-sales resolution speed.
[0070] This invention provides a store recommendation method based on big data exchange. By analyzing user information, it gains a better understanding of user usage on shopping platforms. Through user profile analysis, it derives the preference evaluation coefficients for each target user in each store. Furthermore, through user maintenance analysis, it obtains the evaluation coefficients for each target user in each store, leading to a better recommendation evaluation coefficient for each target user in each store. This method helps users find stores that better match their desired products. It provides an in-depth analysis of user shopping preferences and needs, offering a comprehensive understanding of users and addressing the shortcomings of current technologies. It allows for a better understanding of user thoughts, thereby improving store purchase rates. Simultaneously, it effectively identifies the reasons for user returns and exchanges, enabling the improvement of the business system to better retain existing customers and attract new ones.
[0071] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.
Claims
1. A store recommendation method based on big data exchange, characterized in that, include: Step 1: Obtaining User Information: This involves obtaining basic information about each user on the shopping platform, including the number of times the user has used the shopping platform and the duration of their browsing time. Step 2: User Information Analysis: By analyzing the basic information of each user on the shopping platform, we can obtain the demand assessment coefficient of each user and determine the demand situation of each user to identify the target users, thus proceeding to Step 3. Step two analyzes and obtains the demand assessment coefficients for each user on the shopping platform, and determines the degree of demand for each user. The specific analysis process is as follows: Through calculation formula The analysis yielded the demand assessment coefficients for each user on the shopping platform. , where i represents the user's ID. , , These represent the preset weighting factors for the number of times a user uses the shopping platform and the duration of time a user browses the shopping platform. , Let represent the number of times the i-th user uses the shopping platform and the duration of browsing the shopping platform, respectively. , These represent the preset number of times a user uses the shopping platform and the duration of time a user browses the shopping platform, respectively. The threshold for evaluating the demand of each user on the shopping platform is compared with the preset threshold for evaluating the demand of users on the shopping platform. If the threshold for evaluating the demand of a user on the shopping platform is less than the preset threshold for evaluating the demand of users on the shopping platform, the user is determined to have a low demand and will not be considered a target user. If the threshold for evaluating the demand of a user on the shopping platform is greater than the preset threshold for evaluating the demand of users on the shopping platform, the user is determined to have a high demand and will be considered a target user. Target users are obtained in this way. Step 3: User Profile Acquisition: This involves acquiring basic information about each target user's profile, including purchase frequency, product price, repurchase frequency, and positive review frequency for each store. Step 4: User Profile Analysis: Based on the basic information of each target user's profile in each store, analyze and obtain the preference evaluation coefficient of each target user in each store, and determine the purchase desire of each target user in each store. If the purchase desire is strong, proceed to Step 5. Step four analyzes and obtains the preference evaluation coefficient of each target user in each store, and determines the purchase desire of each target user in each store. The specific analysis process is as follows: Through calculation formula The analysis yielded the preference evaluation coefficients for each target user in each store. f represents the ID of each target user. y represents the store number. , , , , These represent the weighting factors for the preset target user's purchase frequency, product price, repurchase frequency, and positive review frequency, respectively. , , , Let f represent the number of purchases, product price, repurchase frequency, and positive review frequency of the f-th user in the y-th store, respectively. , , , These represent the number of purchases, product price, repurchase frequency, and positive review frequency for the preset target users, respectively. The preference evaluation coefficient threshold of each target user in each store is compared with the preset preference evaluation coefficient threshold of each target user in each store. If the preference evaluation coefficient threshold of a target user in a store is greater than the preset preference evaluation coefficient threshold of a target user in a store, it is determined that the user has a strong desire to buy and a large number of product preferences are comprehensively recommended. If the preference evaluation coefficient threshold of a target user in a store is less than the preset preference evaluation coefficient threshold of a target user in a store, it is determined that the user has a weak desire to buy. Step 5: User Maintenance Analysis: By analyzing the number of returns and exchanges and the price difference of goods for each target user in each store, we can obtain the evaluation coefficient of each target user in each store, and then proceed to Step 6. Step five analyzes and obtains the evaluation coefficients for each target user in each store. The specific analysis process is as follows: Through calculation formula The analysis yielded the evaluation coefficients for each target user in each store. f represents the ID of each target user. y represents the store number. , , These represent the preset weighting factors for the number of returns / exchanges and the price difference of goods for each target user in each store. , Let f represent the number of returns / exchanges and the price difference of the product for the f-th target user in the y-th store, respectively. , These represent the preset number of returns / exchanges and the price difference of goods for each target user in each store; Step Six: Obtaining Store Information: This involves obtaining basic information about each store on the shopping platform, including the store's level, operating duration, number of followers, store rating, sales volume, and after-sales resolution speed. Step 7: Store Information Analysis: By obtaining basic information about each store on the shopping platform, we can then analyze and derive the recommendation evaluation coefficient for each target user in each store, thus obtaining the recommended stores for each target user. Step seven analyzes and obtains the recommendation evaluation coefficient for each target user in each store. The specific analysis process is as follows: Based on the target user's level and operating time in each store on the shopping platform, the level evaluation coefficient for each target user in each store on the shopping platform is calculated. y represents the store number. ; Based on the store ratings and follower counts of each target user on the shopping platform for each store, the store evaluation coefficient for each target user on the shopping platform for each store is calculated. ; Based on the sales volume and after-sales resolution speed of each target user on the shopping platform in each store, the store quality evaluation coefficient for each target user on the shopping platform in each store is calculated. ; Through calculation formula The analysis yielded the recommendation evaluation coefficients for each target user in each store. , , , , , These represent the weighting factors for the preset store rating evaluation coefficient, store score evaluation coefficient, store good evaluation coefficient, preference evaluation coefficient, and review evaluation coefficient, respectively. , , These represent the preset store rating evaluation coefficient, store evaluation coefficient, and store good evaluation coefficient, respectively. , Let F represent the preference evaluation coefficient and the rating evaluation coefficient of the f-th target user in the y-th store, respectively. The recommendation evaluation coefficient threshold for each target user in each store is compared with the preset recommendation evaluation coefficient threshold for each target user in each store. If the recommendation evaluation coefficient threshold for a target user in a store is greater than the preset recommendation evaluation coefficient threshold for each target user in a store, then each target user is selected as a target recommended store. If the recommendation evaluation coefficient threshold for a target user in a store is less than the preset recommendation evaluation coefficient threshold for each target user in a store, then it is not selected as a target recommended store for each target user.
2. The store recommendation method based on big data exchange as described in claim 1, characterized in that, The calculation yields the rating coefficients for each target user on the shopping platform across different stores. The specific analysis process is as follows: Through calculation formula The rating coefficients for each target user on the shopping platform in each store were calculated. , , These represent the weighting factors for the standard store's rating and operating duration, respectively. , Let f represent the target user's level and operating time in the y-th store, respectively. , These represent the standard store level and operating duration, respectively.
3. The store recommendation method based on big data exchange as described in claim 1, characterized in that, The calculation yields the store evaluation coefficient for each target user on the shopping platform for each store. The specific analysis process is as follows: Through calculation formula The store evaluation coefficients for each target user on the shopping platform in each store were calculated. , , These represent the standard number of followers and the weighting factors for store ratings, respectively. , Let f represent the number of followers and the store rating of the f-th target user in the y-th store, respectively. , These are represented as standard follower count and store rating, respectively.
4. The store recommendation method based on big data exchange as described in claim 1, characterized in that, The calculation yields the store preference evaluation coefficient for each target user on the shopping platform for each store. The specific analysis process is as follows: Through calculation formula The store satisfaction rating coefficient for each target user on the shopping platform for each store was calculated. , , These represent the weighting factors for standard store sales volume and after-sales resolution speed, respectively. , Let represent the sales volume and after-sales resolution speed of the f-th target user in the y-th store, respectively. , These are respectively represented as the standard store's sales volume and after-sales resolution speed.