Intelligent shopping point management system and method based on data analysis
By utilizing data analysis-based intelligent shopping points management systems, which employ modules for data cleaning, feature extraction, points generation, and monitoring, the system addresses the limitations of traditional, singular points mechanisms. It enables dynamic points generation and management driven by user consumption characteristics, thereby improving the intelligence and accuracy of points management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- YANTAI WEILAI ELECTRONIC TECH CO LTD
- Filing Date
- 2026-02-09
- Publication Date
- 2026-06-16
AI Technical Summary
Traditional shopping points systems fail to effectively reflect the differences in user consumption value, resulting in a simplistic points distribution mechanism that makes it difficult to achieve dynamic points generation and intelligent management.
The data-driven smart shopping points management system includes modules for data cleaning, feature extraction, points generation, usage management, and points monitoring. It dynamically generates and manages user points, and uses user consumption characteristics and real-time transaction data to calculate and update points.
It enables intelligent management of points during the user's shopping process, dynamically generating and updating points, and accurately calculating points based on user consumption behavior characteristics and real-time transaction data, thereby improving the intelligence and accuracy of points management.
Smart Images
Figure CN122222672A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of intelligent data analysis technology, specifically a smart shopping points management system and method based on data analysis. Background Technology
[0002] Shopping points are a user incentive mechanism set up by merchants or platforms. They are typically accumulated based on user behavior such as shopping, checking in, or participating in activities, and can be used to offset costs, redeem goods, or enjoy preferential services in subsequent purchases. This mechanism quantifies user spending behavior and forms manageable data metrics to maintain user activity and loyalty, and is one of the widely used customer relationship management methods in online shopping malls and offline physical stores.
[0003] Traditional points distribution relies on users' spending amount, that is, the number of points is calculated by multiplying the amount of each transaction by a set coefficient. This easily ignores the different characteristics of users such as spending frequency, product type and user activity level, resulting in a relatively simple points distribution mechanism that is difficult to reflect the true value of users' spending.
[0004] Therefore, this invention proposes a smart shopping points management system and method based on data analysis. Summary of the Invention
[0005] In view of the shortcomings of existing technologies, the purpose of this invention is to provide a smart shopping points management system and method based on data analysis.
[0006] The technical problem to be solved by this invention is:
[0007] How to achieve dynamic generation and intelligent management of points during the user's shopping process.
[0008] To achieve the above objectives, the present invention adopts the following technical solution:
[0009] A data-driven smart shopping points management system includes:
[0010] The data cleaning module is used to detect whether there are any anomalies in the historical user data, and then send the detected historical user data to the feature extraction module.
[0011] The feature extraction module is used to extract the user's consumption behavior features and send the obtained user consumption feature set to the points generation module;
[0012] The points generation module is used to construct the points acquisition formula for users to earn points when making purchases, and to send the obtained points acquisition formula to the user management module and the obtained user's available points balance to the database module.
[0013] The database module is also used to store the store's points redemption ratio and the user's available points balance and send them to the usage management module;
[0014] The data acquisition module is used to collect real-time consumption data when users transact with stores and send it to the usage management module;
[0015] The management module is used to calculate the actual transaction amount and the user's available points balance when the user transacts with the store based on real-time consumption data. The calculated user's available points balance is sent to the database module and the points monitoring module, and the points time set is sent to the points monitoring module.
[0016] The points monitoring module is used to update the user's available points balance based on the points time set, and send the updated available points balance to the database module;
[0017] The database module is also used to update the user's available points balance.
[0018] Furthermore, historical user data includes all users' historical transaction records and user registration time. Historical transaction records include user name, transaction amount when the user transacted with the store, transaction time, product category and store number, as well as whether the product transaction was canceled or completed.
[0019] Furthermore, the detection process of the data cleaning module is as follows:
[0020] For historical user data, detect historical transaction records with the same username; if one historical transaction record is a canceled transaction and the other is a completed transaction, delete the canceled transaction record; if both historical transaction records are canceled transactions, delete the canceled transaction record; if both historical transaction records are completed transactions, do not perform any operation.
[0021] If the transaction time of any historical transaction record in the historical user data is earlier than the user's registration time, the corresponding historical transaction record is determined to be an anomaly in time and is deleted.
[0022] If the transaction time of all historical transaction records in the historical user data is later than the user's registration time, no action will be taken.
[0023] Furthermore, the extraction process of the feature extraction module is as follows:
[0024] Get the transaction amount of the user's transactions with the store in the past three months, add up all the transaction amounts and take the average to calculate the average single transaction amount of the user in the past three months;
[0025] Get the transaction time of the same user and the store in the past three months, subtract the previous transaction time from the next transaction time to calculate the consumption interval between adjacent transaction times, add the consumption intervals between adjacent transaction times and take the average to calculate the average consumption interval of the same user, and take the reciprocal of the average consumption interval to calculate the consumption frequency of the corresponding user.
[0026] Obtain the total number of historical transaction records of the same user in the past three months, as well as the product categories when the same user made purchases. Then, obtain the number of historical transaction records of the user in different product categories and calculate the diversity coefficient of the user in different product categories.
[0027] Obtain the transaction amount of the same user in the first month and the transaction amount in the third month of the past three months. Subtract the transaction amount of the first month from the transaction amount of the third month, and then divide by the transaction amount of the first month to calculate the transaction amount change rate of the corresponding user.
[0028] The average transaction amount, transaction frequency, diversity coefficient, and transaction amount change rate are summarized into a set of user consumption characteristics.
[0029] Furthermore, the working process of the integral generation module is as follows:
[0030] The base points for a user's transactions with the store are calculated based on the user's average transaction amount per transaction.
[0031] Obtain the consumption frequency of all users, sum the consumption frequencies and take the average value to calculate the average consumption frequency of all users. Then divide the user's consumption frequency by the average consumption frequency to calculate the consumption activity coefficient of the corresponding user. Finally, assign the user's first activity score based on the value of the consumption activity coefficient.
[0032] Similarly, the user's second activity score is assigned based on the value corresponding to the user's diversity coefficient, and the user's third activity score BHj is assigned based on the value corresponding to the user's transaction amount change rate.
[0033] Calculate the points earned by the user during interactions with the store;
[0034] The user's available points balance is calculated by summing up the points earned from transactions with the store.
[0035] Furthermore, real-time consumption data includes the real-time transaction amount, the number of points used, and the actual transaction time when a user transacts with a store.
[0036] Furthermore, the calculation process using the management module is as follows:
[0037] Obtain the number of points a user uses when making a transaction with the store; if the user's used points are greater than or equal to their available points balance, then the user's available points balance will be used as the points to be spent in this transaction, and the entire available points balance will be used to deduct the transaction amount; if the user's used points are less than their available points balance, then the available points balance will be subtracted from the used points to calculate the user's remaining points after the transaction with the store, and the used points will be used as the points to be spent in this transaction, and the used points will be used to deduct the transaction amount.
[0038] Obtain the real-time transaction amount when a user transacts with a store and the store's points deduction ratio DK. Calculate the actual transaction amount after the user deducts the transaction amount using points through a formula.
[0039] Obtain the user consumption characteristic set of the corresponding user, calculate the consumption points after the user and the store make a transaction based on the actual transaction amount, and summarize the consumption points and the actual transaction time into the user's consumption point corresponding point time set;
[0040] The user's available points balance is calculated by adding the points earned after a transaction to the remaining points.
[0041] Furthermore, the update process of the points monitoring module is as follows:
[0042] Obtain the actual transaction time from the user's points time set, and use the actual transaction time as a base to add a fixed duration to get the expiration time of the points corresponding to the user's consumption points after the transaction with the store.
[0043] The user's points expiration dates are sorted according to time order, and when the user deducts points from the transaction amount, the points are used in the order of their expiration dates.
[0044] The system monitors all user points time sets and user real-time consumption data. When a user does not use points within the expiration period of the points they have consumed, the system subtracts the corresponding consumption points from the user's available points balance to calculate the updated available points balance.
[0045] Secondly, a smart shopping points management method based on data analysis, the method consists of the following steps:
[0046] Step S100: Obtain historical user data for all users, detect abnormal historical transaction records within the historical user data, and determine whether the corresponding historical transaction records need to be modified or deleted based on the detection results.
[0047] Step S200: Extract the consumption characteristics of all users when they transact with stores based on historical user data, and obtain the user consumption characteristic set of the user.
[0048] Step S300: Construct a points acquisition formula for users when making purchases based on the user consumption feature set;
[0049] Step S400: Obtain real-time consumption data when the user transacts with the store; calculate the actual transaction amount and the user's available points balance based on the real-time consumption data to obtain the user's consumption points corresponding to the points time set.
[0050] Step S500: Update the user's available points balance based on the points time set of consumption points.
[0051] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:
[0052] 1. This invention first detects abnormal historical transaction records in historical user data, and determines whether the corresponding historical transaction records need to be modified or deleted based on the detection results. Then, based on the detected historical user data, it extracts the consumption characteristics of all users when they transact with stores, and obtains a set of user consumption characteristics, thereby realizing intelligent extraction of user shopping consumption characteristics.
[0053] 2. This invention constructs a points acquisition formula based on a set of user consumption characteristics to obtain points when a user makes a purchase. At the same time, it calculates the actual transaction amount and the user's available points balance based on real-time consumption data to obtain the points time set corresponding to the user's consumption points. Based on the points time set of consumption points, the user's available points balance is updated. This invention realizes intelligent management of points during the user's shopping process. Attached Figure Description
[0054] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.
[0055] Figure 1 This is an overall system block diagram of the present invention;
[0056] Figure 2 This is a flowchart illustrating the construction of the consumption points formula in this invention;
[0057] Figure 3This is a flowchart of the method of the present invention. Detailed Implementation
[0058] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. 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.
[0059] Example 1: Please refer to Figure 1 and Figure 2 As shown, the technical solution provided by this invention is: a smart shopping points management system based on data analysis. This system obtains a set of user consumption characteristics by detecting and analyzing parameters in the historical user data of all users; then, based on the set of user consumption characteristics, it constructs a points acquisition formula corresponding to the consumption points obtained by the user when interacting with the store; based on the points acquisition formula and the actual transaction amount, it updates the user's available points balance, and sorts the order of use of consumption points according to the points expiration time.
[0060] In this embodiment, the system includes a data acquisition module, a data cleaning module, a feature extraction module, a points generation module, a usage management module, a points monitoring module, and a database module; wherein, the database module is connected to the data cleaning module, the usage management module, and the points monitoring module, and the database module is used to store the historical user data of all users and send the historical user data to the data cleaning module;
[0061] The historical user data specifically includes all users' historical transaction records and user registration time. Historical transaction records include the user's name, the transaction amount, transaction time, product category, and store number, as well as whether the transaction was cancelled or completed. Specifically, only one cancellation and one completion record can exist simultaneously within the same historical transaction record. The store corresponding to the user's transaction can be an online store or a physical store, which can be determined by comparing store numbers. In practice, historical user data is represented in a data table, with a one-to-many relationship between user name and transaction amount, transaction time, product category, and store number.
[0062] For example, the store number of an online store can be represented by XS, and the physical store can be represented by XXI, where i is the number of the offline store, i=1, 2, ..., n, and n is a positive integer;
[0063] Furthermore, the data cleaning module is used to detect whether there are any anomalies in the historical user data. The detection process is as follows:
[0064] Step A101: Detect historical transaction records in the historical user data where the usernames of two historical transaction records are the same;
[0065] If one of two historical transaction records shows a cancelled transaction and the other shows a completed transaction, the cancelled transaction record will be deleted.
[0066] If both historical transaction records are for canceled transactions, delete the historical transaction records for canceled transactions.
[0067] When both historical transaction records show that the goods have been traded, no action is taken.
[0068] Step A102: If the transaction time of any historical transaction record in the historical user data is earlier than the user registration time, the corresponding historical transaction record is determined to be abnormal in time and is deleted.
[0069] If the transaction time of all historical transaction records in the historical user data is later than the user's registration time, no action will be taken.
[0070] The data cleaning module sends the detected historical user data to the feature extraction module.
[0071] Specifically, the feature extraction module is used to extract user consumption behavior features from historical user data. The extraction process is as follows:
[0072] Step B101: Obtain the transaction amount of the user's transactions with the store in the past three months, add up all the transaction amounts and take the average to calculate the average single transaction amount DEj of the user in the past three months, where j is the user's number, j=1,2,...,m, and m is a positive integer;
[0073] Step B102: Obtain the transaction time of the same user and the store in the past three months. Subtract the previous transaction time from the next transaction time to calculate the consumption interval between adjacent transaction times. Sum the consumption intervals between adjacent transaction times and take the average value to calculate the average consumption interval of the same user. Take the reciprocal of the average consumption interval to calculate the consumption frequency XFj of the corresponding user.
[0074] The unit for the consumption interval is days; subtracting adjacent transaction times specifically means subtracting the previous transaction time from the next transaction time.
[0075] Step B103: Obtain the total number of historical transaction records YZj of the same user in the past three months, and the product categories in which the same user made purchases. Then, obtain the number of historical transaction records JSjk of the user in the k-th product category, where k is the product category number, k=1,2,...,o, and o is a positive integer. Finally, calculate the diversity coefficient DXj of the user in different product categories using the Simpson index formula, as follows:
[0076] ;
[0077] It should be noted that the diversity coefficient ranges from [0, 1]. A diversity coefficient close to 1 indicates that the distribution of product categories purchased by users is even, while a diversity coefficient close to 1 indicates that the distribution of product categories purchased by users is uneven.
[0078] Step B104: Obtain the transaction amount of the same user in the first month and the transaction amount in the third month of the past three months. Subtract the transaction amount of the first month from the transaction amount of the third month, and then divide by the transaction amount of the first month to calculate the transaction amount change rate of the corresponding user.
[0079] Step B105: Summarize the average single transaction amount, consumption frequency, diversity coefficient, and transaction amount change rate into a set of user consumption characteristics;
[0080] The feature extraction module sends the user consumption feature set to the points generation module.
[0081] In this embodiment, the points generation module is used to construct a points acquisition formula for users when making purchases based on a set of user consumption characteristics. The construction process is as follows:
[0082] Step C101: Obtain the basic points JFj for the user's transactions with the store based on the user's average single transaction amount;
[0083] For example, the average transaction amount is [0, 1000), the base points are 10; the average transaction amount is [1000, 2000), the base points are 20; the average transaction amount is [2000, 3000), the base points are 30; the average transaction amount is [3000, 4000), the base points are 40; the average transaction amount is [4000, 5000), the base points are 50; the average transaction amount is [5000, +∞), the base points are 100. When the user's average transaction amount is 1200, the user's base points when transacting with the store are 20.
[0084] Step C102: Obtain the consumption frequency of all users, sum the consumption frequencies and take the average value to calculate the average consumption frequency of all users. Then, divide the user's consumption frequency by the average consumption frequency to calculate the consumption activity coefficient of the corresponding user. Then, assign the value of the user's first activity score XHj based on the value of the consumption activity coefficient.
[0085] For example, when the consumption activity coefficient is 1.2, the user's first activity score is 12; when the consumption activity coefficient is 0.8, the user's first activity score is 8.
[0086] In step C103, similarly, the user's second activity score DJj is assigned a value based on the user's diversity coefficient, and the user's third activity score BHj is assigned a value based on the user's transaction amount change rate.
[0087] Among them, the values of the basic integral, the first activity integral, the second activity integral, and the third activity integral are all greater than one. The assignment process of the second activity integral and the third activity integral is the same as the assignment process of the first activity integral.
[0088] Step C104: Calculate the points XJj earned by the user during their interaction with the store using the points calculation formula. The specific formula for earning points is as follows:
[0089] XJj=k1×JFj+k2×XHj+k3×DJj+k4×BHj, where k1, k2, k3 and k4 are fixed weighting coefficients, and the actual values are k1=0.4, k2=0.3, k3=0.2 and k4=0.1.
[0090] It should be noted that in user-store transactions, the average transaction amount per user directly reflects the number of points a user can earn, therefore the average transaction amount per user has the highest weighting coefficient; the consumption activity coefficient directly reflects the frequency of user purchases, therefore the first activity point has the second highest weighting coefficient; the diversity coefficient is used to represent user consumption behavior for different product categories, but a diversity coefficient value close to each other does not necessarily indicate user purchase behavior for products of different values, therefore the second activity point has the third highest weighting coefficient; the transaction amount change rate is used to represent the increase or decrease in user transaction amount, but relying solely on the transaction amount change rate cannot guarantee long-term user purchase behavior, therefore the third activity point has the lowest weighting coefficient.
[0091] Step C105: Sum the points earned by the user when making transactions with the store to calculate the user's available points balance;
[0092] The points generation module sends the points acquisition formula to the usage management module, and at the same time sends the user's available points balance to the database module.
[0093] As a further embodiment, the database module is also used to store the store's points deduction ratio and the user's available points balance, and send the points deduction ratio and available points balance to the usage management module;
[0094] The data acquisition module is used to collect real-time consumption data when users transact with stores and send the real-time consumption data to the usage management module.
[0095] Specifically, real-time consumption data includes the real-time transaction amount, the number of points used, and the actual transaction time when a user transacts with a store.
[0096] In practice, the usage management module is used to calculate the actual transaction amount and the user's available points balance when the user transacts with the store based on real-time consumption data. The calculation process is as follows:
[0097] Step D101: Obtain the number of points used by the user when making transactions with the store;
[0098] If a user's points usage is greater than or equal to their available points balance, then the user's available points balance will be used as the points expenditure for this transaction (ZCj), and all available points balance will be used to deduct the transaction amount.
[0099] If a user's used points are less than their available points balance, the available points balance will be subtracted from the used points to calculate the user's remaining points after the transaction with the store. The used points will be used as the expenditure points for this transaction and will be used to deduct the transaction amount.
[0100] Step D102: Obtain the real-time transaction amount SJj when the user transacts with the store and the store's points deduction ratio DK. Calculate the actual transaction amount JEj after the user deducts the transaction amount using points using the following formula:
[0101] JEj=max(0,SJj-DK×ZCj);
[0102] Step D103: Obtain the user consumption feature set of the corresponding user, calculate the consumption points after the user and the store make a transaction based on the actual transaction amount, and summarize the consumption points and the actual transaction time into the consumption point time set corresponding to the user's consumption points.
[0103] Step D104: Add the points earned by the user after the transaction to the remaining points to calculate the user's available points balance.
[0104] The usage management module sends the user's available points balance to the database module and the points monitoring module. The database module is used to update the user's available points balance and send the points time set to the points monitoring module.
[0105] As a further aspect of this embodiment, the points monitoring module is used to update the user's available points balance based on the points time set. The update process is as follows:
[0106] Step E101: Obtain the actual transaction time from the user's points time set. Based on the actual transaction time, add a fixed duration upwards to obtain the expiration time of the points corresponding to the consumption points after the user's transaction with the store.
[0107] Among them, the expiration time of the points is later than the actual transaction time;
[0108] Step E102: Sort the user's points expiration dates according to time order for all points time sets. When the user deducts the transaction amount, the points are used in order of their expiration dates.
[0109] Step E103: Monitor all user points time sets and user real-time consumption data. When a user does not use points within the expiration time of the points corresponding to the consumption points, subtract the corresponding consumption points from the user's available points balance to calculate the updated available points balance.
[0110] In practice, the monitoring interval for monitoring all of a user's points time sets can be one day.
[0111] The usage management module sends the updated available points balance to the database module, which is used to update the user's available points balance.
[0112] Example 2: Figure 3 As shown, based on another concept of the same invention, a smart shopping points management method based on data analysis is proposed, including the following steps:
[0113] Step S100: Obtain historical user data for all users, detect abnormal historical transaction records within the historical user data, and determine whether the corresponding historical transaction records need to be modified or deleted based on the detection results.
[0114] Step S200: Extract the consumption characteristics of all users when they transact with stores based on historical user data, and obtain the user consumption characteristic set of the user.
[0115] Step S300: Construct a points acquisition formula for users when making purchases based on the user consumption feature set;
[0116] Step S400: Obtain real-time consumption data when the user transacts with the store; calculate the actual transaction amount and the user's available points balance based on the real-time consumption data to obtain the user's consumption points corresponding to the points time set.
[0117] Step S500: Update the user's available points balance based on the points time set of consumption points.
[0118] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims
1. A smart shopping points management system based on data analysis, characterized in that: include: The data cleaning module is used to detect whether there are any anomalies in the historical user data, and then send the detected historical user data to the feature extraction module. The feature extraction module is used to extract the user's consumption behavior features and send the obtained user consumption feature set to the points generation module; The points generation module is used to construct the points acquisition formula for users to earn points when making purchases, and to send the obtained points acquisition formula to the user management module and the obtained user's available points balance to the database module. The database module is also used to store the store's points redemption ratio and the user's available points balance and send them to the usage management module; The data acquisition module is used to collect real-time consumption data when users transact with stores and send it to the usage management module; The management module is used to calculate the actual transaction amount and the user's available points balance when the user transacts with the store based on real-time consumption data. The calculated user's available points balance is sent to the database module and the points monitoring module, and the points time set is sent to the points monitoring module. The points monitoring module is used to update the user's available points balance based on the points time set, and send the updated available points balance to the database module; The database module is also used to update the user's available points balance.
2. The intelligent shopping points management system based on data analysis according to claim 1, characterized in that, Historical user data includes all users' historical transaction records and user registration time. Historical transaction records include user name, transaction amount when the user transacted with the store, transaction time, product category and store number, as well as whether the product transaction was canceled or completed.
3. The intelligent shopping points management system based on data analysis according to claim 2, characterized in that, The detection process of the data cleaning module is as follows: For historical user data, detect historical transaction records with the same username; if one historical transaction record is a canceled transaction and the other is a completed transaction, delete the canceled transaction record; if both historical transaction records are canceled transactions, delete the canceled transaction record; if both historical transaction records are completed transactions, do not perform any operation. If the transaction time of any historical transaction record in the historical user data is earlier than the user's registration time, the corresponding historical transaction record is determined to be an anomaly in time and is deleted. If the transaction time of all historical transaction records in the historical user data is later than the user's registration time, no action will be taken.
4. The intelligent shopping points management system based on data analysis according to claim 1, characterized in that, The extraction process of the feature extraction module is as follows: Get the transaction amount of the user's transactions with the store in the past three months, add up all the transaction amounts and take the average to calculate the average single transaction amount of the user in the past three months; Get the transaction time of the same user and the store in the past three months, subtract the previous transaction time from the next transaction time to calculate the consumption interval between adjacent transaction times, add the consumption intervals between adjacent transaction times and take the average to calculate the average consumption interval of the same user, and take the reciprocal of the average consumption interval to calculate the consumption frequency of the corresponding user. Obtain the total number of historical transaction records of the same user in the past three months, as well as the product categories when the same user made purchases. Then, obtain the number of historical transaction records of the user in different product categories and calculate the diversity coefficient of the user in different product categories. Obtain the transaction amount of the same user in the first month and the transaction amount in the third month of the past three months. Subtract the transaction amount of the first month from the transaction amount of the third month, and then divide by the transaction amount of the first month to calculate the transaction amount change rate of the corresponding user. The average transaction amount, transaction frequency, diversity coefficient, and transaction amount change rate are summarized into a set of user consumption characteristics.
5. The intelligent shopping points management system based on data analysis according to claim 1, characterized in that, The specific working process of the integral generation module is as follows: The base points for a user's transactions with the store are calculated based on the user's average transaction amount per transaction. Obtain the consumption frequency of all users, sum the consumption frequencies and take the average value to calculate the average consumption frequency of all users. Then divide the user's consumption frequency by the average consumption frequency to calculate the consumption activity coefficient of the corresponding user. Finally, assign the user's first activity score based on the value of the consumption activity coefficient. Similarly, the user's second activity score is assigned based on the value corresponding to the user's diversity coefficient, and the user's third activity score BHj is assigned based on the value corresponding to the user's transaction amount change rate. Calculate the points earned by the user during interactions with the store; The user's available points balance is calculated by summing up the points earned from transactions with the store.
6. The intelligent shopping points management system based on data analysis according to claim 1, characterized in that, Real-time consumption data includes the real-time transaction amount, the number of points used, and the actual transaction time when a user transacts with a store.
7. The intelligent shopping points management system based on data analysis according to claim 6, characterized in that, The calculation process using the management module is as follows: Obtain the number of points a user uses when making a transaction with the store; if the user's used points are greater than or equal to their available points balance, then the user's available points balance will be used as the points to be spent in this transaction, and the entire available points balance will be used to deduct the transaction amount; if the user's used points are less than their available points balance, then the available points balance will be subtracted from the used points to calculate the user's remaining points after the transaction with the store, and the used points will be used as the points to be spent in this transaction, and the used points will be used to deduct the transaction amount. Obtain the real-time transaction amount when a user transacts with a store and the store's points deduction ratio DK. Calculate the actual transaction amount after the user deducts the transaction amount using points through a formula. Obtain the user consumption characteristic set of the corresponding user, calculate the consumption points after the user and the store make a transaction based on the actual transaction amount, and summarize the consumption points and the actual transaction time into the user's consumption point corresponding point time set. The user's available points balance is calculated by adding the points earned after a transaction to the remaining points.
8. The intelligent shopping points management system based on data analysis according to claim 7, characterized in that, The update process of the points monitoring module is as follows: Obtain the actual transaction time from the user's points time set, and use the actual transaction time as a base to add a fixed duration to get the expiration time of the points corresponding to the user's consumption points after the transaction with the store. The user's points expiration dates are sorted according to time order, and when the user deducts points from the transaction amount, the points are used in the order of their expiration dates. The system monitors all user points time sets and user real-time consumption data. When a user does not use points within the expiration period of the points they have consumed, the system subtracts the corresponding consumption points from the user's available points balance to calculate the updated available points balance.
9. A smart shopping points management method based on data analysis, characterized in that: The method of the data analysis-based smart shopping points management system according to any one of claims 1-8 includes the following steps: Step S100: Obtain historical user data for all users, detect abnormal historical transaction records within the historical user data, and determine whether the corresponding historical transaction records need to be modified or deleted based on the detection results. Step S200: Extract the consumption characteristics of all users when they transact with stores based on historical user data, and obtain the user consumption characteristic set of the user. Step S300: Construct a points acquisition formula for users when making purchases based on the user consumption feature set; Step S400: Obtain real-time consumption data when the user transacts with the store; calculate the actual transaction amount and the user's available points balance based on the real-time consumption data to obtain the user's consumption points corresponding to the points time set. Step S500: Update the user's available points balance based on the points time set of consumption points.