Local life e-commerce platform queuing order-free rebate analysis system and method

Abstract

The invention relates to a local life e-commerce platform queuing order-free rebate analysis system and method, and relates to the field of rebate analysis, and the system comprises a user data collection module, a data analysis module, a rebate strategy optimization module and a visual display module. The user data acquisition module is used for acquiring behavior data of a user on the platform in real time. And the data analysis module analyzes the user data acquired by the user data acquisition module and identifies the corresponding behavior mode of the user. And the rebate strategy optimization module automatically generates a personalized rebate strategy according to a user behavior mode result analyzed by the data analysis module. And the visual display module is used for displaying the generated rebate strategy and displaying the implementation condition of the rebate strategy. Through mutual cooperation of the modules, adjustment of a rebate order-free strategy can be performed in a targeted manner for different users and stores, and the coverage range of the rebate policy is expanded by adopting a graded rebate mode.

Description

Technical Field

[0001] The present invention relates to the field of rebate analysis, and more particularly to a queuing free order rebate analysis system for local life e-commerce platforms. Background Art

[0002] With the development of Internet technology and the popularity of smart phones, local life e-commerce platforms have gradually emerged. These platforms provide users with convenient local services such as dining, shopping, entertainment, etc. Users can quickly find nearby merchants and make purchases through mobile applications. During peak hours, many merchants face the problem of customers queuing up. This not only affects the customer's consumption experience but also may cause merchants to lose potential customers. Therefore, how to effectively manage the queuing phenomenon and improve customer satisfaction has become an urgent problem for merchants and platforms. To attract customers and increase the consumption frequency, many local life e-commerce platforms have launched free order and rebate activities. These activities can not only effectively reduce the queuing time of customers but also increase the consumption willingness of customers and promote the sales of merchants.

[0003] Traditional free order rebate systems mostly focus on the rebate ratio and the way and speed of user rebate withdrawal, and the adjustment and analysis of the rebate strategy of this application are not comprehensive enough, resulting in a relatively rigid rebate plan, which only targets the users themselves, and the plans for merchants, operators, etc. are not flexible and targeted enough. Summary of the Invention

[0004] Object of the Invention: To provide a queuing free order rebate analysis system for local life e-commerce platforms to solve the above problems existing in the prior art.

[0005] Technical Solution: A queuing free order rebate analysis system for local life e-commerce platforms includes four components: a user data collection module, a data analysis module, a rebate strategy optimization module, and a visualization display module.

[0006] Among them, the user data collection module is used to collect the behavior data of users on the platform in real time, including browsing records, purchase records, queuing duration, and user feedback information;

[0007] The data analysis module analyzes the user data collected by the user data collection module and identifies the corresponding behavior patterns of users, including consumption habits, preferred products, queuing duration, and purchase conversion rate;

[0008] The rebate strategy optimization module automatically generates personalized rebate strategies according to the results of the user behavior patterns analyzed by the data analysis module;

[0009] The visualization display module is used to display the generated rebate strategies and display the implementation status of the rebate strategies.

[0010] In a further embodiment, the specific analysis steps of the data analysis module are as follows:

[0011] S1. Clean and preprocess the collected data, including removing duplicate data, handling missing values and outliers, to ensure the accuracy and integrity of the data;

[0012] S2. Analyze the cleaned and preprocessed data by means of data mining to identify the user's behavior patterns, specifically:

[0013] Identify the user's consumption habits through the user's purchase records and purchase frequencies, including the time, place and amount of purchases, and conduct consumption habit analysis;

[0014] Identify which products the user is more interested in by analyzing the user's browsing records and purchase records, and conduct analysis of preferred products;

[0015] Calculate the purchase conversion rate by analyzing the user's purchase records and browsing records.

[0016] In a further embodiment, the specific analysis steps of the rebate strategy optimization module are as follows:

[0017] T1. Collect data according to the results of various user behavior patterns analyzed by the data analysis module, and perform normalization processing on the collected data information;

[0018] T2. Use data mining techniques to analyze various user behavior patterns, and combine association rule mining and sequential pattern mining to comprehensively analyze various user behavior patterns;

[0019] T3. Generate different free order rebate policies for different store information according to the comprehensive analysis results.

[0020] In a further embodiment, in step T2, the specific steps of comprehensively analyzing various user behavior patterns by combining association rule mining and sequential pattern mining are as follows:

[0021] T201. Serialize the queuing duration in the user behavior pattern to construct a user queuing duration sequence U id , and associate the store information where the user generates the queuing duration. Its sequence representation is specifically as follows:

[0022] U id =[(t1,d1),(t2,d2),…,(t n ,d n )]

[0023] where t i is the queuing time, di is the queuing duration. At the same time, d i associates the information of the store where it is located;

[0024] T202. Perform sequence pattern mining on the user queuing duration sequence U id as follows:

[0025]

[0026] where T is the database composed of multiple user queuing duration sequences U generated within a predetermined time period, and |D| is the total number of user queuing duration sequences U contained in the database T; id The total number of; id ;

[0027] T203. Set a corresponding threshold MinS and screen the mined sequence S(U id ) as follows:

[0028] S(U id ) ≥ MinS

[0029] When the above conditions are met, the sequence is marked as a frequent sequence;

[0030] T204. Integrate the frequent sequences in each store and mark the store with the most associated times among all frequent sequences;

[0031] T205. Customize corresponding free order rebate strategies according to the number of frequent sequences in each store.

[0032] In a further embodiment, the free order rebate strategy adopts a membership system. Members can enjoy free order rebate subsidies according to a corresponding ratio when queuing for orders on the user platform. When a member applies for a cash withdrawal, a corresponding fee ratio is deducted for each cash withdrawal application, which is collected by the platform and is default empty, that is, there is no fee for cash withdrawal.

[0033] In a further embodiment, the rebate strategy optimization module is a hierarchical system, which is divided into consumer members, stores, shared store clerks, city operators, and platforms;

[0034] The rebate strategy optimization module customizes different rebate and free order strategies according to different level objects as follows:

[0035] The free order amount for consumer members is the order consumption amount × the corresponding store queuing free order ratio;

[0036] The store income is the order consumption amount - (the order consumption amount × the corresponding store queuing free order ratio);

[0037] The order income of the shared store clerk is (the free order amount × the cash withdrawal rate) × the queuing free order commission ratio;

[0038] The order revenue of the city operator is (free order amount × withdrawal fee rate - shared clerk order revenue) × commission ratio of the queue free order operator;

[0039] The platform order revenue is (free order amount × withdrawal fee rate - shared clerk order revenue) - city operator order revenue.

[0040] Beneficial effects: The present invention relates to a system and method for analyzing the free-order rebate for queuing on a local life e-commerce platform, which relates to the field of rebate analysis and includes four components: a user data collection module, a data analysis module, a rebate strategy optimization module, and a visual display module. Among them, the user data collection module is used to collect the user's behavior data on the platform in real time, including browsing records, purchase records, queuing time, and user feedback information. The data analysis module analyzes the user data collected by the user data collection module and identifies the user's corresponding behavior pattern, including consumption habits, preferred products, queuing time, and purchase conversion rate. The rebate strategy optimization module automatically generates a personalized rebate strategy based on the user behavior pattern results analyzed by the data analysis module. The visual display module is used to display the generated rebate strategy and the implementation of the rebate strategy. Through the mutual cooperation between the modules, the present application can adjust the rebate-free-order strategy for different users and stores in a targeted manner, and adopt a graded rebate method to expand the coverage of the rebate policy. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of the overall operation process of the local life e-commerce platform described in the present invention. DETAILED DESCRIPTION

[0042] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features well known in the art are not described.

[0043] The applicant believes that the traditional free-order rebate system focuses more on the rebate ratio and the method and speed of user rebate withdrawal. The adjustment and analysis of the rebate strategy in this application is not comprehensive enough, resulting in a relatively rigid rebate plan that is only targeted at the user itself, and the plan for merchants, operators, etc. is not flexible and targeted enough.

[0044] For this purpose, the applicant designs a queuing free order rebate analysis system for the local life e-commerce platform. Through the mutual cooperation among various modules, it can adjust the rebate and free order strategies targeted at different users and stores, and adopt a hierarchical rebate method to expand the coverage of the rebate policy.

[0045] The queuing free order rebate analysis system for the local life e-commerce platform involved in the present invention mainly includes four components: a user data collection module, a data analysis module, a rebate strategy optimization module, and a visualization display module.

[0046] Among them, the user data collection module is used to collect the behavior data of users on the platform in real time, including browsing records, purchase records, queuing duration, and user feedback information, etc. The data analysis module analyzes the user data collected by the user data collection module and identifies the corresponding behavior patterns of users, including consumption habits, preferred products, queuing duration, and purchase conversion rate, etc. The rebate strategy optimization module automatically generates personalized rebate strategies according to the user behavior pattern results analyzed by the data analysis module. The visualization display module is used to display the generated rebate strategies and display the implementation situation of the rebate strategies. During the actual operation process, through the analysis of user consumption habits, targeted push of product information to customers at different times can be carried out, that is, push product discount information, new product information, etc. during the peak order placement period of users. While effectively increasing the exposure of products and preferential policies, it can also effectively promote the order placement probability of products. Through the analysis of users' preferred products, the products to be pushed can be accurately positioned, and products can be accurately pushed to different users. And taking the store as a unit, the preferred products of the users who consume in the store can be classified as a whole, and the products with more consumption types can be placed in prominent positions in the store for the convenience of users to select. Different stores can flexibly adjust the product placement positions according to different data analysis results. This flexible adjustment of product placement positions can also avoid the phenomenon of excessive accumulation of users caused by users wasting time looking for products, resulting in an increase in queuing duration and quantity.

[0047] The specific analysis steps of the data analysis module are as follows:

[0048] First, clean and preprocess the collected data, including removing duplicate data, handling missing values and outliers, to ensure the accuracy and integrity of the data;

[0049] Next, analyze the cleaned and preprocessed data through data mining to identify the behavior patterns of users, specifically:

[0050] Identify the consumption habits of users through their purchase records and purchase frequencies, including the time, place, and amount of purchases, and conduct consumption habit analysis;

[0051] By analyzing the user's browsing records and purchase records, identify which products the user is more interested in and conduct an analysis of preferred products;

[0052] By analyzing the user's purchase records and browsing records, calculate the purchase conversion rate.

[0053] In a further preferred embodiment, when cleaning and preprocessing the collected data, the following steps can be followed:

[0054] 1. Duplicate removal:

[0055] Check whether there are duplicate records in the data. You can use the duplicate removal function of the database or the duplicate removal function of the programming language to determine which field combinations can uniquely identify a record and use this as a basis for duplicate removal.

[0056] 2. Handling missing values:

[0057] Identify the missing values in the data, which can be discovered by using statistical analysis or visualization methods.

[0058] According to the business requirements and data characteristics, select an appropriate method to fill in the missing values, such as filling with the average value, median value, interpolation, etc.

[0059] 3. Handling outliers:

[0060] Determine the outliers in the data, which can be discovered by using statistical analysis, visualization and other methods.

[0061] According to the business requirements and data characteristics, select an appropriate method to handle the outliers, such as removing, replacing with the average value or median value, etc.

[0062] For cases where it is impossible to determine whether it is an outlier, the original data can be retained and special processing can be carried out in subsequent analysis.

[0063] 4. Data type conversion:

[0064] Check the data types of each field in the data to ensure that they match the business requirements and subsequent analysis.

[0065] Perform data type conversion as needed, such as converting strings to numeric types, unifying date and time formats, etc.

[0066] 5. Feature engineering:

[0067] According to the business requirements, perform feature engineering on the data, such as deriving new features, discretizing continuous features, etc.

[0068] Ensure that the newly generated features are relevant to the business objectives and are helpful for subsequent model training and prediction.

[0069] 6. Data normalization:

[0070] Normalize the data, such as standardization, normalization, etc., so that each feature has the same dimension and numerical range.

[0071] Normalization helps to improve the convergence speed and performance of the model.

[0072] 7. Data splitting:

[0073] Divide the cleaned data into a training set, a validation set, and a test set for subsequent model training and evaluation.

[0074] Ensure that the data distributions among the datasets are as similar as possible to avoid data skew.

[0075] Through the above steps, the accuracy, integrity, and availability of the data can be ensured, providing a good foundation for subsequent data analysis.

[0076] The specific analysis steps of the rebate strategy optimization module are as follows:

[0077] First, collect data according to the results of various user behavior patterns analyzed by the data analysis module, and normalize the collected data information;

[0078] Next, use data mining techniques to analyze various user behavior patterns, and combine association rule mining and sequential pattern mining to comprehensively analyze various user behavior patterns;

[0079] Finally, generate different free order rebate policies for different store information according to the comprehensive analysis results.

[0080] In the second step, the specific steps for comprehensively analyzing various user behavior patterns by combining association rule mining and sequential pattern mining are as follows:

[0081] First, serialize the queuing duration in the user behavior pattern to construct a user queuing duration sequence U id , and associate the store information where the user generates the queuing duration. Its sequence representation is as follows:

[0082] U id = [(t1, d1), (t2, d2), …, (t n , d n )]

[0083] where t i is the queuing time, d i is the queuing duration. At the same time, d i is associated with the store information;

[0084] Next, for the user queuing duration sequence Uid Perform sequence pattern mining as follows:

[0085]

[0086] Among them, T is a database composed of multiple user queuing duration sequences U generated within a predetermined time period, and |D| is the total number of user queuing duration sequences U contained in database T; id The total number of; id

[0087] Subsequently, set a corresponding threshold MinS and filter the mined sequence S(U id ) as follows:

[0088] S(U id ) ≥ MinS

[0089] When the above conditions are met, the sequence is marked as a frequent sequence;

[0090] Then, integrate the frequent sequences in each store and mark the store with the most associated times among all frequent sequences;

[0091] Finally, customize the corresponding free order rebate strategy according to the number of frequent sequences in each store.

[0092] In a further preferred implementation, timely adjust the store operation mode for the marked store to reduce the user queuing rate in the store and improve the user's shopping experience. At the same time, when a store is marked multiple times in a short period, corresponding operation personnel will be assigned to provide further guidance on the operation of the store to avoid multiple markings of the store.

[0093] The free order rebate strategy adopts a membership system. Members queue for orders on the user platform and enjoy free order rebate subsidies according to a corresponding ratio. When a member applies for a cash withdrawal, a corresponding fee ratio is deducted for each cash withdrawal application, which is collected by the platform and defaults to empty, that is, there is no fee for cash withdrawal.

[0094] The rebate strategy optimization module is a hierarchical system, divided into consumer members, stores, shared store clerks, city operators, and platforms;

[0095] The rebate strategy optimization module customizes different rebate and free order strategies according to different level objects as follows:

[0096] The free order amount for consumer members is the order consumption amount × the corresponding store queuing free order ratio;

[0097] The store income is the order consumption amount - (the order consumption amount × the corresponding store queuing free order ratio);

[0098] ​The shared store clerk order revenue is (the free order amount × the withdrawal rate) × the commission ratio of the queuing free order meeting;

[0099] The urban operator order revenue is (the free order amount × the withdrawal rate - the shared store clerk order revenue) × the commission ratio of the queuing free order operator;

[0100] The platform order revenue is (the free order amount × the withdrawal rate - the shared store clerk order revenue) - the urban operator order revenue.

[0101] In a further preferred embodiment, the queuing free order subsidy ratio: the free order rebate subsidy ratio for the queuing order of "ordinary members" in the "local life" store. The withdrawal rate of ordinary members: the fee ratio deducted for each withdrawal application when "ordinary members" apply for withdrawal, charged by the platform. It is default empty, that is, no fee is charged for withdrawal. The minimum withdrawal amount: the minimum withdrawal amount of "shared shareholders" or "urban operators" cannot be less than 1 yuan. It is recommended to fill in an integer. If not filled in, there is no limit.

[0102] In a further preferred embodiment, the commission revenue of the urban operator store clerk's rights is the rights price × the commission ratio of the store clerk's rights. The commission revenue of the platform store clerk's rights is the rights price - the commission revenue of the store clerk's rights.

[0103] The specific representation of the above queuing free order calculation formula is shown in the following table:

[0104] Table 1: Queuing Free Order Calculation Formula

[0105]

[0106] As described above, although the present invention has been shown and described with reference to specific preferred embodiments, it should not be construed as a limitation of the present invention itself. Various changes in form and detail may be made without departing from the spirit and scope of the present invention defined by the appended claims.

Claims

1. A queuing-free order-free rebate analysis system for a local life e-commerce platform, characterized in that Including: A user data collection module, which is used to collect the behavior data of users on the platform in real time, including browsing records, purchase records, queuing duration, and user feedback information; A data analysis module, which analyzes the user data collected by the user data collection module and identifies the corresponding behavior patterns of users, including consumption habits, preferred products, queuing duration, and purchase conversion rate; A rebate strategy optimization module, which automatically generates personalized rebate strategies according to the results of the user behavior patterns analyzed by the data analysis module; A visualization display module, which is used to display the generated rebate strategies and display the implementation status of the rebate strategies.

2. The analysis method of a queuing free order rebate analysis system for a local life e-commerce platform according to claim 1, characterized in that: The specific analysis steps of the data analysis module are: S1. Clean and preprocess the collected data, including removing duplicate data, processing missing values and outliers, to ensure the accuracy and integrity of the data; S2. Analyze the data after cleaning and preprocessing through data mining to identify the behavior patterns of users, specifically: Identify the consumption habits of users through the purchase records and purchase frequencies of users, including the time, place, and amount of purchases, and conduct consumption habit analysis; Identify which products users are more interested in by analyzing the browsing records and purchase records of users, and conduct analysis of preferred products; Calculate the purchase conversion rate by analyzing the purchase records and browsing records of users.

3. The analysis method of a queuing free order rebate analysis system for a local life e-commerce platform according to claim 2, characterized in that: The specific analysis steps of the rebate strategy optimization module are: T1. Collect data according to the results of various user behavior patterns analyzed by the data analysis module, and normalize the collected data information; T2. Use data mining technology to analyze various user behavior patterns, and combine both association rule mining and sequential pattern mining to comprehensively analyze various user behavior patterns; T3. Generate different free order rebate policies for different store information according to the comprehensive analysis results.

4. The analysis method of a queuing free order rebate analysis system for a local life e-commerce platform according to claim 3, characterized in that: In step T2, the specific steps of comprehensively analyzing various user behavior patterns by combining association rule mining and sequential pattern mining are: T201. Serialize the queuing duration in the user behavior pattern to construct a user queuing duration sequence U id , and associate the store information where the user generates the queuing duration. The sequence representation is as follows: U id = [(t1, d1), (t2, d2), …, (t n , d n )] where t i is the queuing time, and d i is the queuing duration. At the same time, d i is associated with the information of the store where it is located; T202. Perform sequence pattern mining on the user queuing duration sequence U id as follows: Among them, T is a database composed of multiple user queuing duration sequences U generated within a predetermined time period, and |D| is the total number of user queuing duration sequences U included in the database T; id id ​​ T203. Set the corresponding threshold MinS and screen the mining sequence S(U id ), as follows: S(U id ) ≥ MinS When the above conditions are met, the sequence is marked as a frequent sequence; T204. Integrate the frequent sequences in each store, and mark the store with the most association times in all frequent sequences; T205. Customize corresponding free order rebate strategies according to the number of frequent sequences in each store.

5. The analysis method of a queuing free order rebate analysis system for a local life e-commerce platform according to claim 4, characterized in that: The free order rebate strategy adopts a membership system. Members queue up orders on the user platform and enjoy free order rebate subsidies according to corresponding ratios. When a member applies for a cash withdrawal, a corresponding fee rate will be deducted for each cash withdrawal application, which is charged by the platform. It is defaulted to be empty, that is, there is no fee for cash withdrawal.

6. A queuing free order rebate analysis system for a local life e-commerce platform according to claim 1, characterized in that: The rebate strategy optimization module is a hierarchical system, which is divided into consumer members, stores, shared clerks, city operators and the platform; The rebate strategy optimization module customizes different rebate free order strategies according to different level objects, specifically as follows: The free order amount for consumer members is the order consumption amount × the corresponding store queuing free order ratio; The store income is the order consumption amount - (the order consumption amount × the corresponding store queuing free order ratio); The order income of the shared clerk is (the free order amount × the cash withdrawal rate) × the queuing free order commission sharing ratio; The order income of the city operator is (the free order amount × the cash withdrawal rate - the order income of the shared clerk) × the queuing free order operator commission sharing ratio; The order income of the platform is (the free order amount × the cash withdrawal rate - the order income of the shared clerk) - the order income of the city operator.

Images