A method for generating labels based on user portraits in a credit card system

Abstract

The present invention provides a method for generating labels based on user portraits depicted by a credit card system, and relates to the field of credit card systems. The method for generating labels based on user portraits depicted by a credit card system comprises the following steps: S1. generating corresponding labels based on the overall information recorded in the credit card, wherein the labels are classified into customer status, demographic information, card information, account information, consumption operations, installment operations, cash withdrawal operations, contract behavior, active status, marketing management, and customer value; S2. when a label group is obtained from an internal management page, the labels are divided into unary labels and binary labels. The present invention is aimed at the need to collect basic user information and detect financial transaction behaviors through the credit card system when formulating a reasonable and comprehensive marketing strategy in a credit card system, and to perform big data analysis. A specific, independent label is generated for each user as a marker, which can efficiently and accurately screen vertical populations and find target customers in segmented fields.

Description

Technical Field

[0001] The present invention relates to the technical field of credit card systems, and in particular to a method for generating labels based on user portraits drawn by a credit card system. Background Art

[0002] User portraits refer to labeled user models abstracted from user attributes, preferences, lifestyle habits, behaviors, and other information. In layman's terms, this means labeling users, and labels are highly refined feature identifiers derived from analyzing user information. Labeling allows users to be described using highly generalized, easily understood features, making it easier for people to understand users and facilitating computer processing. User portraits are the modeling of real-world users and should encompass five aspects: goals, methods, organization, standards, and verification. In the internet and e-commerce sectors, user portraits are often used as the foundation for precision marketing and recommendation systems. Their overall functions include precision marketing, user statistics, data mining, service offerings, industry reports, and user research. Summary of the Invention

[0003] (1) Technical problems solved

[0004] In response to the shortcomings of the existing technology, the present invention provides a method for generating labels by depicting user portraits based on the credit card system, which solves the problem of being unable to efficiently and accurately screen vertical groups and find target customers in segmented fields.

[0005] (2) Technical solution

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for generating labels based on user portraits drawn by a credit card system, comprising the following steps:

[0007] S1. Generate corresponding labels based on the information recorded on the credit card. The labels are categorized into customer status, demographic information, card information, account information, consumption operations, installment operations, cash withdrawal operations, contract behavior, active status, marketing management, and customer value.

[0008] S2. When obtaining a tag group from the internal page, classify the tags into unary tags and binary tags;

[0009] S3. After classifying the tag operation type, the unary tags and binary tags are classified into card information, account information, and customer information;

[0010] S4. If the tag is a univariate tag, extract the database data for screening and comparison, and write the users who meet the conditions into the intermediate file. Binary tag data, such as consumption records, is counted every 7 days and written into the intermediate file until all intermediate information for all specified customer groups is processed and written into the intermediate file.

[0011] S5. Use the intermediate file format to perform secondary processing on the customer tag information, write the data of the one-dimensional tag that can directly obtain the result into the final result file, compare and calculate the data of the binary tag with the binary tag configured by the user, and store it in the final result file until all data processing is completed in order to reduce the pressure on the database.

[0012] Preferably, the customer status described in S1 includes whether the customer is a new customer that year, whether the customer is a normal customer, and a large installment identification.

[0013] Preferably, the demographic information in S1 includes gender, age, education level, birthday, and work area, and the consumption operations include the average consumption amount per transaction in the month, the number of consumption transactions in the month, the monthly consumption amount, and the average consumption amount per transaction in the past 7 days.

[0014] Preferably, the one-value tag can directly determine and return only whether, such as whether the customer is a normal customer and gender, and the two-value tag needs to calculate, such as the monthly consumption amount and the average consumption amount per transaction in the past 7 days.

[0015] Preferably, the database in S4 includes a pre-loan system, a mid-loan system, a post-loan system, and a collection system.

[0016] Preferably, the comparative calculation in S5, for example, if the average consumption amount of the configured binary tag in the past 7 days is greater than 30, the number of consumption transactions in the past 7 days and the total consumption amount in the past 7 days are obtained to calculate the result.

[0017] (3) Beneficial effects

[0018] The present invention provides a method for generating labels based on user profiles in a credit card system. This method has the following beneficial effects:

[0019] 1. The present invention aims at the credit card system. When formulating a reasonable and complete marketing strategy, it is necessary to collect basic information of users through the credit card system, detect financial transaction behaviors, conduct big data analysis, and generate specific and independent tags for each user as a mark. It can efficiently and accurately screen vertical groups and find target customers in segmented fields. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0021] Example:

[0022] The embodiment of the present invention provides a method for generating labels based on the user portrait of the credit card system, which includes the following steps: S1. Generate corresponding labels based on the information recorded in the credit card. The labels are classified into customer status, demographic information, card information, account information, consumption operation, installment operation, cash withdrawal operation, contract behavior, active status, marketing management, and customer value. The customer status includes whether it is a new customer of the year, whether it is a normal customer, and the large-amount installment identification. The demographic information includes gender, age, education level, birthday, and work area. The consumption operation includes the average consumption amount of the month, the number of consumption transactions in the month, the consumption amount of the month, and the recent 7 days. Average consumption amount per transaction, S2. When the tag group is obtained from the internal management page, the tags are divided into one-dimensional tags and two-dimensional tags. S3. After classifying the tag operation type, the one-dimensional tags and the two-dimensional tags are classified into card information, account information, and customer information. The one-dimensional tags can directly judge whether to return only whether, such as whether it is a normal customer, gender, and the two-dimensional tags need to calculate the monthly consumption amount and the average consumption amount per transaction in the past 7 days. S4. If it is a one-dimensional tag, extract the database data for screening and comparison, and write the users who meet the conditions into the intermediate file. The data of the two-dimensional tags, such as consumption records, the number of consumption transactions is counted every 7 days and written. The process of processing all the intermediate information of all designated customer groups and users is completed and written into the intermediate file. The database includes the pre-loan system, the loan system, the post-loan system, and the collection system. After the customer's business application is submitted through the channel system, it enters the pre-loan approval link. The pre-loan approval link mainly reviews whether the customer's business application is successful and sends the successful result to the card core for the next step of processing. The key nodes of the pre-loan system process are: anti-fraud strategy, blacklist strategy, credit variable, customer feature review, manual review, and review results. In the process of customers using credit cards, the essence is that the bank keeps The credit card lending process is a dynamic process of granting credit to customers. Therefore, the credit card loan business mainly focuses on credit card limit management and online credit card customer risk screening. After the customer's application for a large-value credit product is approved and the loan is disbursed, it enters the post-loan stage. The post-loan system mainly handles the online risk screening of large-value credit customers. The data platform will screen the list of screened customers according to the large-value credit post-loan risk screening group entry strategy and then push it to the post-loan system. The post-loan system will assign the screening list to the credit personnel for processing. The credit personnel will conduct telephone screening or field visits to the customers based on their risk level and finally register the screening results in the post-delivery system. S5.Secondary processing of customer tag information is performed using an intermediate file format. Data from single-value tags that can directly generate results is written to the final result file. Binary-value tag data is compared and calculated with user-configured binary tags, and stored in the final result file until all data processing is complete. To reduce database pressure, comparative calculations are performed. For example, if the average transaction amount for a configured binary tag over the past seven days is greater than 30, the number of transactions and the total transaction amount over the past seven days are calculated to obtain the result. This system is applicable to credit card systems and credit card-related peripheral systems, such as outbound call systems, telemarketing platforms, and marketing platforms, providing basic data services.

[0023] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for generating labels based on user profiles in a credit card system, characterized by: The following steps are involved: S1. Generate corresponding labels based on the information recorded on the credit card. The labels are categorized into customer status, demographic information, card information, account information, consumption operations, installment operations, cash withdrawal operations, contract behavior, active status, marketing management, and customer value. S2. When obtaining a tag group from the internal page, classify the tags into unary tags and binary tags; S3. After the tag operation type is classified, the one- and two-tags are classified into card information, account information, and customer information; the one-tag can directly determine whether it returns only whether it is a normal customer and gender, and the two-tag needs to calculate the monthly consumption amount and the average consumption amount in the past 7 days; S4. If the tag is a univariate tag, extract the database data for screening and comparison, and write the users who meet the conditions into the intermediate file. The data of the binary tag includes consumption records, and the number of consumption transactions is counted every 7 days and written into the intermediate file until all the intermediate information of all the users in the specified customer group is processed and written into the intermediate file. S5. Perform secondary processing on the customer tag information using the intermediate file format. Write the data of the one-dimensional tags that can directly obtain the results into the final result file. Compare and calculate the data of the binary tags with the binary tags configured by the user and store them in the final result file until all data processing is completed.

2. The method for generating labels based on user portraits in a credit card system according to claim 1, characterized in that: The customer status described in S1 includes whether the customer is a new customer that year, whether the customer is a normal customer, and the large installment payment identifier.

3. The method for generating labels based on user portraits in a credit card system according to claim 1, characterized in that: The demographic information described in S1 includes gender, age, education level, birthday, and work area. The consumption operations include the average consumption amount per transaction in the month, the number of consumption transactions in the month, the monthly consumption amount, and the average consumption amount per transaction in the past 7 days.

4. The method for generating labels based on user portraits in a credit card system according to claim 1, characterized in that: The database described in S4 includes a pre-loan system, a mid-loan system, a post-loan system, and a collection system.

5. The method for generating labels based on user portraits in a credit card system according to claim 1, characterized in that: The comparative calculation described in S5 includes the configured binary tag. If the average consumption amount per transaction in the past 7 days is greater than 30, the number of consumption transactions in the past 7 days and the total consumption amount in the past 7 days are obtained to calculate the result.

6. The method for generating labels based on user portraits in a credit card system according to claim 1, characterized in that: The scope of application is based on the credit card system and credit card-related peripheral systems, including outbound call systems, telemarketing platforms, and marketing platforms, providing basic data services.