A data processing method and system for a shopping mall

Abstract

The application provides a data processing method and system for a shopping mall, and belongs to the technical field of data processing. The method comprises the following steps: determining the date data of different users that have not performed matching analysis and processing of new user data according to different user data processing methods; determining whether the new user data of users except the to-be-updated user needs to be processed according to the to-be-updated user data and the update data of the user portrait of the to-be-updated user when the update analysis and processing of the user portrait of the to-be-updated user are needed at different dates when the new user data of the different users has not been processed, so that the efficiency of the update processing of the user portrait is improved.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, and in particular relates to a data processing method and system for shopping malls. Background Technology

[0002] To enhance the user shopping experience, existing technical solutions often require targeted product recommendations based on user profile analysis. For example, invention patent application CN202311565494.3, "A Method for Constructing User Profiles in an Online Mall," uses cluster analysis to segment users, providing richer feature information for user profiles, making them more comprehensive and accurate. This allows for the recommendation of products that match users' interests and needs, improving the accuracy of the recommendation system and user satisfaction. However, the following technical problems exist: For different users, the types of products they browse on different dates may change over time and may not match their own user profile, thus causing the user profile to change. Therefore, determining how to analyze the degree of matching between user data and user profile on different dates, and how to quickly identify and process the changed user profile when it changes, has become an urgent technical problem to be solved.

[0003] Therefore, there is an urgent need for a data processing method and system for shopping malls. Summary of the Invention

[0004] To achieve the objectives of this invention, the following technical solution is adopted: Specifically, this application provides a data processing method for an online shopping mall, which includes: S1 determines the data processing method between the user profile and the new user data based on the update date of the user profile of the shopping mall. Based on the data processing method, it determines the matching situation between the user profile and the new user data on different dates. Based on the matching situation, it determines the users whose user profiles are to be updated. S2 determines the dates when different users have not undergone matching analysis and processing of new user data based on different user data processing methods. When it is determined that the user profile of the user to be updated needs to be updated based on the dates when different users have not undergone matching analysis and processing of new user data, proceed to the next step. S3 determines whether the new user data of users other than those to be updated needs to be processed based on the user data to be updated and the updated user profile data of the user to be updated.

[0005] The beneficial effects of this invention are as follows: Based on the update date of user profiles in the shopping mall, the data processing method between user profiles and new user data is determined. This enables the identification of users whose profiles are matched with new user data daily, based on the overall update delay of user profiles in the shopping mall. This not only ensures the efficiency of the overall user profile update process, but also, through adjustments to the data processing method, ensures the efficiency of identifying and processing users with high user profile update needs when their profiles change.

[0006] By considering the dates on which different users have not undergone matching analysis for new user data, it is determined whether user profile update analysis is needed for the users to be updated. This approach takes into account both the differences in the number of dates on which different users have not undergone matching analysis for new user data, leading to differences in the accuracy of the current update identification results, and the differences in the degree of update needs of the users to be updated due to the composition data of the users to be updated. This achieves an assessment of the degree of need for user profile update analysis from both the perspectives of update needs and the accuracy of identification results, ensuring the timeliness of overall user profile update processing, while also avoiding the impact of frequent update analysis processing on the reliability of user profile change identification processing for other users.

[0007] Furthermore, the update date of the user profile is determined based on the parsing results of the user profile's historical update records.

[0008] Furthermore, the newly added user data includes the user's browsing data, purchase data, and search data for different products on different dates.

[0009] Furthermore, the method for determining the data processing method between the user profile and the newly added user data is as follows: Based on the update date of the shopping mall's user profile, determine the interval between the update date and the current date; Based on the interval duration of different users, determine the average interval duration of different users, and use it as the average interval duration. The average interval duration is used to determine the data processing method between the user profile and the new user data.

[0010] Furthermore, determine whether new user data for users other than those awaiting updates requires data processing, specifically including: Based on the user data to be updated, determine the number of users to be updated, and determine the matching ratio factor based on the proportion of the users to be updated among the users who are analyzing and processing the matching between user profiles and new user data; Based on the updated data of the user profile of the user to be updated, identify the user whose user profile has been updated and treat them as the updated user. Based on the matching ratio factor and the number of users who have completed the update, it is determined whether the new user data of users other than those to be updated needs to be processed.

[0011] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the aforementioned data processing method for a shopping mall when running the computer program.

[0012] Other features and advantages will be set forth in the following description, and the objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0013] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0014] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0015] Figure 1 This is a flowchart of a data processing method used in an online shopping mall. Figure 2 This is a flowchart illustrating the method for determining the data processing between user profiles and new user data; Figure 3 This is a flowchart illustrating the method for determining the user profile to be updated within the user data; Figure 4 This is a flowchart for analyzing and processing the user profiles of users who need to be updated. Detailed Implementation

[0016] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0017] Example 1 like Figure 1 As shown, this application provides a data processing method for an online shopping mall, specifically including: S1 determines the data processing method between the user profile and the new user data based on the update date of the user profile of the shopping mall. Based on the data processing method, it determines the matching situation between the user profile and the new user data on different dates. Based on the matching situation, it determines the users whose user profiles are to be updated. S2 determines the dates when different users have not undergone matching analysis and processing of new user data based on different user data processing methods. When it is determined that the user profile of the user to be updated needs to be updated based on the dates when different users have not undergone matching analysis and processing of new user data, proceed to the next step. S3 determines whether the new user data of users other than those to be updated needs to be processed based on the user data to be updated and the updated user profile data of the user to be updated.

[0018] Furthermore, the update date of the user profile is determined based on the parsing results of the user profile's historical update records.

[0019] Furthermore, the newly added user data includes the user's browsing data, purchase data, and search data for different products on different dates.

[0020] Specifically, such as Figure 2 As shown, the method for determining the data processing method between the user profile and the newly added user data is as follows: Based on the update date of the shopping mall's user profile, determine the interval between the update date and the current date; Based on the interval duration of different users, determine the average interval duration of different users, and use it as the average interval duration. The average interval duration is used to determine the data processing method between the user profile and the new user data.

[0021] Specifically, the user profile is determined based on the parsing results of the user's historical user data, specifically the output of the user profile recognition model that uses the historical user data as input. The user profile recognition model is constructed using a neural network-based prediction model or an expert scoring model.

[0022] It is understandable that when the average interval duration is greater than the preset interval duration threshold, it indicates that the timeliness of updating user profiles for different users is difficult to meet the requirements. Therefore, the data processing method for determining the user profile and new user data is as follows: if the user's interval duration is greater than the preset interval duration threshold, as long as the number of products with new user data in the date is greater than the first product quantity threshold, then the matching analysis and processing between user profile and new user data will be performed in the date.

[0023] Additionally, it can be understood that when the interval duration is not greater than a preset interval duration threshold, as long as the number of products with newly added user data in the date is greater than the second product quantity threshold, the matching analysis between user profiles and newly added user data will be performed in the date.

[0024] It should be noted that the first product quantity threshold is less than the second product quantity threshold.

[0025] Specifically, this embodiment constructs a dynamic update decision system based on the global profile freshness. The system aims to intelligently allocate computing resources to ensure the timeliness of user profiles while avoiding unnecessary computational overhead.

[0026] 1. Data foundation and indicator calculation; Data collection: The system records the last update date of each user profile.

[0027] Calculate the individual interval duration: For each user i, calculate the profile update interval T_i (in days): T_i = Current_Date - Last_Update_Date_i; Calculate the global freshness metric: Calculate the average interval duration of all users, i.e., the average interval duration T_avg. This metric reflects the average staleness of the entire user profile set of the online store.

[0028] T_avg = (ΣT_i) / N (N is the total number of users); 2. Update decision-making logic; The system sets a preset interval threshold T_threshold (e.g., 90 days) and executes different update strategies based on the comparison between T_avg and this threshold.

[0029] Scenario A: The overall portrait is outdated (T_avg > T_threshold); Judgment: This indicates that the entire user profile database is severely outdated and urgently needs a large-scale update.

[0030] Strategy: Adopt a lenient update strategy. Individual trigger condition: For users whose interval length is greater than T_threshold, as long as the number of products involved in their newly added user data (such as browsing, favorites, purchases, search, etc.) is greater than N1 (the first product quantity threshold, for example, N1=3) on a certain day, the system will analyze and process the matching between the user's profile and the newly added user data on that day.

[0031] Effect: This strategy lowers the update threshold, allowing even users with only a few new behaviors to trigger profile refresh, aiming to quickly improve the freshness of the entire profile database, while ensuring the efficiency of identification and processing when user profiles of users whose updates are too outdated change.

[0032] Scenario B: The overall profile is relatively recent (T_avg <= T_threshold); Judgment: This indicates that the user profile database is generally in an acceptable state, and a more economical and precise update strategy can be adopted. Strategy: Adopt a strict update strategy. Individual trigger condition: For any user, on a given day, the system will only trigger a profile update if the number of products involved in their newly added user data is greater than N2 (the second product quantity threshold, e.g., N2 = 5). Here, N2 > N1. Effect: This strategy raises the update threshold, updating profiles only for users whose behavior is sufficiently active and who have generated a large amount of new data. This effectively saves computing resources and ensures that the updated profiles are based on sufficient data evidence.

[0033] Updating user profiles specifically includes: Data preparation: Merge all historical user data of the user with the new user data to form an updated dataset.

[0034] Model inference: The updated post-dataset is used as input and fed into a pre-trained user profile recognition model (e.g., a Transformer-based deep learning model that can predict user interest tags, purchasing power, life cycle stage, etc. from user behavior sequences).

[0035] Output and storage: The model outputs the latest user profile vector or label set, and the system uses this result to overwrite the old user profile and records the new update date.

[0036] Example of system workflow; Assume that a mall sets T_threshold = 90 days, N1 = 3, N2 = 5.

[0037] Scenario 1: The system calculates and finds that T_avg = 120 days (greater than 90 days), and enters Case A. User A browses 5 different products today. Since 5>N1(3), the system immediately triggers the profile update for User A.

[0038] Scenario 2: After a period of operation, the system calculates and finds that T_avg = 60 days (less than or equal to 90 days), and enters Case B. User B browses 4 products today. Since 4<N2(5), the system will not trigger an update. The next day, User B browses and favorites 12 products. Since 12>N2(5), the system triggers the profile update for User B at this time.

[0039] Beneficial effects: This system realizes adaptive allocation of computing resources. When the profile library is generally outdated, it "casts a wide net" to quickly improve the overall quality; when the overall profiles are relatively new, it "works meticulously" and only responds to high-value user behaviors. This ensures the optimal balance between profile timeliness and system operation efficiency.

[0040] Further, the matching status between the user's user profile and the new user data on different dates is determined according to the matching status between the user profile and the product corresponding to the new user data.

[0041] Specifically, the product corresponding to the new user data is a product on which the user's new user data exists.

[0042] Specifically, as shown in Figure 3 , the method for determining a user to be updated for the user profile among the users is: Based on the matching status, determine the date on which the user's user profile does not match the product corresponding to the new user data, and take it as a profile matching deviation date; Using the profile matching deviation date data, determine whether the user is a user to be updated for the user profile.

[0043] It can be understood that the profile matching deviation date is a date on which the user profile does not match the product with new user data on that date, wherein whether there is a match is determined according to whether the product with new user data is in the preset product library corresponding to the user profile.

[0044] It should be noted that determining whether a user is a user whose profile needs updating based on the date data of the profile matching deviation specifically includes: The matching deviation ratio is determined by the proportion of the dates on which the user profile and new user data are analyzed and processed. If the matching deviation ratio is greater than a preset deviation ratio threshold, then the user is determined to be a user whose user profile needs to be updated.

[0045] This embodiment constructs a dynamic profile update decision system based on the matching deviation ratio. The system intelligently identifies users whose profiles need to be updated first by quantifying the degree of deviation between user behavior and existing profiles.

[0046] 1. Definition of core concepts and data collection; The product library for user profiles: A preset product interest library is maintained for each user. This library is generated based on the user profile recognition model and includes a set of tags such as product categories, brands, and price ranges that the user may be interested in.

[0047] Profile Matching Deviation Date: For a user, if more than a certain percentage (e.g., 30%) of the products involved in their new user data (such as browsing, purchasing, and search history) are not in their preset product database on a certain date during a matching analysis, then that date is marked as a "Profile Matching Deviation Date".

[0048] Data Recording: The system records the date each user performs a matching analysis, and whether that date is marked as a deviation date.

[0049] 2. Calculation of matching deviation ratio; The system calculates a key metric for each user: the Mismatch Deviation Ratio (MDR).

[0050] Formula: MDR = N_mismatch / N_total_analysis; N_mismatch: The total number of days during the most recent statistical period (e.g., the past 30 days) that the user was marked as "profile mismatch date".

[0051] N_total_analysis: The total number of days the system performed "user profile and new user data matching analysis" on this user within the same statistical period.

[0052] 3. Update decision-making logic; The system sets a preset deviation ratio threshold (MDR_threshold), for example, 0.4 (i.e., 40%).

[0053] Decision-making rules: IF MDR > MDR_threshold THEN; The user is identified as a "user whose user profile needs to be updated".

[0054] The system will add the user to a high-priority update queue, and the user profile will be recalculated and refreshed as soon as possible.

[0055] ELSE; The user profile is determined to still reflect the user's current interests well, and there is no need for an urgent update. It can be processed according to the normal cycle.

[0056] 4. System workflow example; Data preparation: User C's historical profile product database contains {"smartphone", "Bluetooth headset", "gaming laptop"}.

[0057] Behavioral monitoring and matching analysis: Date 1: User C's new activity: browsing "smartphones" and "Bluetooth headsets". Analysis results: All items are in stock; this is not a deviation date.

[0058] Date 2: User C's new behavior: browsing "coffee machine" and "air fryer". Analysis result: All items are not in the inventory, marked as a deviation date.

[0059] Date 3: User C's new action: browsed "gaming laptops" and "gaming chairs". Analysis results: "gaming laptops" are in the database, "gaming chairs" are not. If a deviation is defined as 50% of items not being in the database, then this date is marked as a deviation date.

[0060] Calculate MDR: In the last 30 days, the system performed 10 match analyses on user C, of ​​which 3 were marked as deviation dates. Therefore, MDR = 3 / 10 = 0.3.

[0061] Decision: Assuming MDR_threshold = 0.4, since 0.3 < 0.4, the system determines that user C is not a user awaiting update. If user C exhibits abnormal behavior for several consecutive days, causing their MDR to exceed 0.4, they will be immediately marked as a user awaiting update.

[0062] The above technical solution has the following beneficial effects: Accurate identification: By continuously monitoring the matching degree between behavior and profile, it is possible to promptly detect the migration of user interests or the staleness of profiles.

[0063] Resource optimization: It avoids blindly performing regular full updates for all users and concentrates computing resources on the "users waiting to be updated" who need the most updates.

[0064] Keep user profiles up-to-date: Ensure that user profiles can quickly adapt to changes in users' real and latest interests, thereby improving the effectiveness of downstream applications such as personalized recommendations and precision marketing.

[0065] Specifically, such as Figure 4 As shown, the user profile update analysis process for users who need to be updated is determined, specifically including: The date on which the user did not undergo matching analysis of new user data is taken as the unanalyzed date; Based on the composition data of the unanalyzed dates for different users to be updated, determine the analysis bias factors for different users to be updated; Based on the different analytical bias factors of the users to be updated, it is determined whether the user profile of the users to be updated needs to be updated.

[0066] It is understood that the analysis bias factor is determined based on the proportion of unanalyzed dates for the users to be updated.

[0067] It should be noted that if the number of users to be updated is greater than the preset threshold for the number of users to be updated, then it is determined that the user profile update analysis process for the users to be updated needs to be performed because the number of users to be updated is large.

[0068] Furthermore, if the number of users to be updated is not greater than the preset threshold for the number of updated users, it is necessary to further determine the proportion of users among all users who are performing matching analysis between user profiles and new user data, and use this proportion as the matching analysis user ratio. When the matching analysis user ratio is less than the preset threshold for the number of matching analysis users, the proportion of users performing matching analysis is relatively small, and therefore it is determined that the user profiles of the users to be updated need to be updated.

[0069] Additionally, it is understood that when the proportion of users undergoing matching analysis is not less than a preset threshold for the number of users undergoing matching analysis, it is necessary to further determine the analysis deviation factor of the users performing the matching analysis between user profiles and new user data. If the average value of the analysis deviation factor of the users performing the matching analysis between user profiles and new user data is less than a preset deviation factor threshold, it indicates that the reliability of the matching analysis of the users performing the matching analysis between user profiles and new user data is high. Therefore, based on this, it is determined that no update analysis of the user profiles of the users to be updated is required.

[0070] Furthermore, if the average value of the analysis deviation factor of the user who is performing the matching analysis between the user profile and the new user data is not less than the preset deviation factor threshold, then the analysis demand factor of the user to be updated is determined based on the average value of the analysis deviation factor of different users to be updated and the average value of the proportion of the user to be updated among all users. If the analysis demand factor of the user to be updated is greater than the preset demand factor threshold, then it is determined that the user profile of the user to be updated needs to be updated.

[0071] Additionally, it can be understood that if the analysis demand factor of the user to be updated is not greater than the preset demand factor threshold, then it is determined that no update analysis processing of the user profile of the user to be updated is required.

[0072] Optionally, determine which user profiles need updating and analyze, specifically including: The date on which the user did not undergo matching analysis of new user data is taken as the unanalyzed date; Based on the composition data of the unanalyzed dates for different users to be updated, determine the analysis bias factors for different users to be updated; Based on the average of the analysis deviation factors of different users to be updated and the average proportion of the number of users to be updated among all users, the analysis demand factors of the users to be updated are determined, and based on the analysis demand factors, it is determined whether the user profile update analysis process of the users to be updated needs to be performed.

[0073] Specifically, if the analysis demand factor of the user to be updated is greater than the preset demand factor threshold, for example, 0.2, then it is determined that the user profile of the user to be updated needs to be updated and analyzed.

[0074] Additionally, it can be understood that if the analysis demand factor of the user to be updated is not greater than the preset demand factor threshold, then it is determined that no update analysis processing of the user profile of the user to be updated is required.

[0075] Furthermore, determine whether new user data for users other than those awaiting updates requires data processing, specifically including: Based on the user data to be updated, determine the number of users to be updated, and determine the matching ratio factor based on the proportion of the users to be updated among the users who are analyzing and processing the matching between user profiles and new user data; Based on the updated data of the user profile of the user to be updated, identify the user whose user profile has been updated and treat them as the updated user. Based on the matching ratio factor and the number of users who have completed the update, it is determined whether the new user data of users other than those to be updated needs to be processed.

[0076] Furthermore, when the matching ratio factor is greater than the preset matching ratio factor threshold, the number of users to be updated is large. Therefore, based on this, it is determined that the new user data of users other than those to be updated do not need to be processed.

[0077] Furthermore, when the matching ratio factor is not greater than the preset matching ratio factor threshold, the number of users (excluding users to be updated) who are analyzed and processed for matching between user profiles and new user data is determined. If the number of users (excluding users to be updated) who are analyzed and processed for matching between user profiles and new user data does not meet the requirements, for example, if it is greater than the preset user number threshold, then it is determined that the new user data of users (excluding users to be updated) do not need to be processed.

[0078] Additionally, it is understandable that if the number of users (excluding those awaiting updates) whose user profiles are analyzed and processed to match the new user data meets the requirements, then if the proportion of users whose updates have been completed among those awaiting updates is greater than a preset threshold, then it is determined that all new user data (excluding those awaiting updates) needs to be processed.

[0079] Furthermore, if the proportion of users who have completed the update among the users to be updated is not greater than a preset proportion threshold, then based on the matching deviation proportion of users excluding the users to be updated, if the matching deviation proportion of users excluding the users to be updated is greater than a preset deviation proportion threshold, then it is determined that the new user data of users excluding the users to be updated needs to be processed; and if the matching deviation proportion of users excluding the users to be updated is not greater than a preset deviation proportion threshold, then it is determined that the new user data of users excluding the users to be updated does not need to be processed.

[0080] Specifically, this embodiment constructs a dynamic data processing decision system based on system load and profile quality. The system intelligently decides whether to process new data from a stable user group (excluding users awaiting updates) through multi-level evaluation, thereby achieving optimal allocation of computing resources.

[0081] 1. Calculation of core indicators; Matching scaling factor (M): M = N_pending / N_analyzed; Where N_pending represents the number of users awaiting updates, and N_analyzed represents the total number of users who performed matching analysis within the current period. This factor reflects the current profile update pressure faced by the system.

[0082] User percentage updated (R_updated): R_updated = N_completed / N_pending Where N_completed represents the number of users whose profiles have been updated. This ratio measures the system's progress and efficiency in processing users awaiting updates.

[0083] Stable User Matching Deviation Ratio (MDR_stable): Calculate the average of the matching deviation ratios for all non-updated users to reflect the overall health of the stable user profile.

[0084] 2. Preset threshold; Preset matching ratio factor threshold (M_threshold): e.g., 0.3; Preset user number threshold (N_threshold): e.g., 5000 people; Preset update completion ratio threshold (R_threshold): e.g., 0.8; Preset stable user deviation threshold (MDR_stable_threshold): e.g., 0.2; 3. System workflow example; Suppose that a certain online shopping mall has the following data during a certain analysis period: The number of users performing match analysis is N_analyzed = 10,000, the number of users pending updates is N_pending = 2,500, the number of users whose updates have been completed is N_completed = 2,000, and the stable user match deviation ratio is MDR_stable = 0.15; Decision-making process: The matching ratio factor M = 2500 / 10000 = 0.25 is calculated, which is less than the threshold of 0.3, so proceed to the next judgment.

[0085] The number of stable users is 10000 - 2500 = 7500, which is greater than the threshold of 5000. Based on the decision-making logic, it is finally determined that new data for stable users does not need to be processed.

[0086] Beneficial effects: Load awareness: When the system is busy processing a large number of users waiting to be updated (high M value) or the number of stable users is too large, it will automatically suspend data processing for stable users and prioritize the completion of core tasks.

[0087] Progress-driven: Only when the processing of users awaiting updates is nearing completion (high R_updated value) will the data processing of stable users be restarted, ensuring that the system's focus remains on this task.

[0088] Quality-oriented: The final decision takes into account the overall health of the stable user group profile (MDR_stable). When resources permit, only groups whose profiles may start to show deviations will be processed to achieve precise resource allocation.

[0089] Through this multi-layered dynamic decision-making mechanism, the system can significantly improve the utilization efficiency of computing resources while ensuring the overall quality of user profiles.

[0090] Example 2 In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the aforementioned data processing method for a shopping mall when running the computer program.

[0091] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0092] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0093] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A data processing method for an online shopping mall, characterized in that, Specifically, it includes: Based on the update date of the user profile of the shopping mall, a data processing method is determined between the user profile and the new user data. Based on the data processing method, the matching situation between the user profile and the new user data on different dates is determined. Based on the matching situation, users whose user profiles are to be updated are identified. The method for determining the data processing method between the user profile and the new user data is as follows: Based on the update date of the shopping mall's user profile, determine the interval between the update date and the current date; Based on the interval duration of different users, determine the average interval duration of different users, and use it as the average interval duration. Using the average interval duration, a data processing method is determined between the user profile and the new user data. When the average interval duration is greater than a preset interval duration threshold, the data processing method between the user profile and the new user data is as follows: If the user's interval duration is greater than the preset interval duration threshold, as long as the number of products with new user data in the date is greater than a first product quantity threshold, then the matching analysis between the user profile and the new user data is performed in the date. Based on different user data processing methods, determine the dates when different users have not undergone matching analysis of new user data. When determining the dates when different users have not undergone matching analysis of new user data and when the user profile of the user to be updated needs to be updated, proceed to the next step. Based on the user data to be updated and the updated user profile data of the user to be updated, determine whether the new user data of users other than the user to be updated needs to be processed. Determine whether new user data (excluding users awaiting updates) requires data processing, specifically including: Based on the user data to be updated, determine the number of users to be updated, and determine the matching ratio factor based on the proportion of the users to be updated among the users who are analyzing and processing the matching between user profiles and new user data; Based on the updated data of the user profile of the user to be updated, identify the user whose user profile has been updated and treat them as the updated user. Based on the matching ratio factor and the number of users who have completed the update, it is determined whether the new user data of users other than those to be updated needs to be processed.

2. The data processing method for an online shopping mall as described in claim 1, characterized in that, The update date of the user profile is determined based on the parsing results of the user profile's historical update records.

3. The data processing method for an online shopping mall as described in claim 1, characterized in that, The newly added user data includes the user's browsing data, purchase data, and search data for different products on different dates.

4. The data processing method for an online shopping mall as described in claim 1, characterized in that, The user profile is determined based on the analysis results of the user's historical user data.

5. The data processing method for an online shopping mall as described in claim 1, characterized in that, The matching results between the user profile and the new user data from different dates are determined based on the matching results between the user profile and the products corresponding to the new user data.

6. The data processing method for an online shopping mall as described in claim 1, characterized in that, The products corresponding to the newly added user data are those for which the user's new user data exists.

7. A computer system, comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it performs a data processing method for a shopping mall as described in any one of claims 1-6.

Images