User value evaluation method and device

Abstract

The invention provides a user value evaluation method and device, and the method comprises the steps: obtaining M pieces of data information, wherein the M pieces of data information are in one-to-one correspondence with M users; according to the basic information of the ith user, the income information of the ith user and the deposit and loan information of the ith user, a first score of the ith user is determined, and the first score of the ith user is used for indicating the risk level of the ith user; according to the basic information of the ith user and the consumption information of the ith user, a second score of the ith user is determined, and the second score of the ith user is used for indicating the consumption ability of the ith user; and according to the first scores corresponding to the M users and the second scores corresponding to the M users, determining the users whose first scores meet a first preset condition and whose second scores meet a second preset condition in the M users. The method can be applied to conversion of stock users, and conversion efficiency and conversion accuracy are improved.

Description

Technical Field

[0001] The present application relates to the technical field of data analysis, and in particular to a method and device for evaluating user value. Background Art

[0002] At present, competition in various banking businesses is becoming increasingly fierce, and the cost of developing new users remains high. Compared with new users, since existing users have already established certain business dealings with the bank, existing users have higher conversion potential and lower conversion costs when handling new business. This process can also be called the conversion of existing users.

[0003] The conversion of existing stock users mainly depends on the bank's account managers. The account managers conduct integrated analysis based on industry experience and the user's basic registration information, bank assets, counterparty transactions, credit transactions, contract services, equipment usage, financial management and other private banking business situations, and judge the user value based on the analysis results. This method is too subjective, inefficient in screening existing customers, and has a low accuracy rate. Summary of the invention

[0004] The present application provides a user value assessment method and device to solve the problem of low efficiency in screening existing customers.

[0005] In a first aspect, the present application provides a method for evaluating user value, the method comprising:

[0006] Acquire M data information, wherein the M data information corresponds to the M users one by one, wherein the i-th data information includes the basic information of the i-th user, the income information of the i-th user, the deposit and loan information of the i-th user, and the consumption information of the i-th user, and the i-th data information is any one of the M data information;

[0007] Determine a first score of the i-th user according to the basic information of the i-th user, the income information of the i-th user, and the deposit and loan information of the i-th user, wherein the first score of the i-th user is used to indicate the risk level of the i-th user;

[0008] Determine a second score of the i-th user according to the basic information of the i-th user and the consumption information of the i-th user, wherein the second score of the i-th user is used to indicate the consumption capacity of the i-th user;

[0009] According to the first scores respectively corresponding to the M users and the second scores respectively corresponding to the M users, users among the M users whose first scores satisfy a first preset condition and whose second scores satisfy a second preset condition are determined.

[0010] The user value assessment method provided by the present application determines the first score and the second score of each user based on the data information of multiple users obtained, and then determines the users who meet the preset conditions based on the first score and the second score. The first score and the second score are the results of the integrated analysis of the user's basic information, income information, deposit and loan information, and consumption information. The first score is used to indicate the user's risk level, and the second score is used to indicate the user's consumption ability. Therefore, based on the first score and the second score, the user can be evaluated more comprehensively and accurately, which solves the problems of different subjectivity standards of traditional user value assessment, low efficiency in screening existing customers, and low accuracy.

[0011] In a possible design, the deposit and loan information of the i-th user includes a business type and a business amount, wherein the business type includes a deposit and / or a loan.

[0012] In a possible design, determining a user among the M users whose first score satisfies a first preset condition and whose second score satisfies a second preset condition includes:

[0013] Determine a user among the M users whose first score is greater than a first preset threshold and whose second score is greater than a second preset threshold;

[0014] The first score of the i-th user is inversely proportional to the risk level of the i-th user, and the second score of the i-th user is directly proportional to the consumption capacity of the i-th user.

[0015] In one possible design, among the M users whose first scores are greater than the first preset threshold and whose second scores are greater than the second preset threshold, determine the users among the M users whose first scores are greater than a third preset threshold and whose second scores are greater than a fourth preset threshold, and generate a first list; wherein the third preset threshold is greater than the first preset threshold, and the fourth preset threshold is greater than the second preset threshold.

[0016] In a possible design, a group label corresponding to the i-th user is determined according to the i-th data information;

[0017] Determining a first score of the i-th user according to the basic information of the i-th user, the income information of the i-th user, and the deposit and loan information of the i-th user includes:

[0018] Determine a first score of the i-th user according to a first coefficient, basic information of the i-th user, income information of the i-th user, and deposit and loan information of the i-th user; the first coefficient is associated with a group label corresponding to the i-th user;

[0019] Determining a second score of the i-th user according to the basic information of the i-th user and the consumption information of the i-th user includes:

[0020] A second score of the i-th user is determined according to the first coefficient, the basic information of the i-th user, and the consumption information of the i-th user.

[0021] It is understandable that users with the same group label generally have similar risk levels and consumption capabilities. Since the first score and the second score of the user in this application are determined based on the first coefficient, and the first coefficient is associated with the group label corresponding to the user, the reliability and accuracy of the first score and the second score of the user in this application are relatively high, which further helps to improve the accuracy of conversion of existing users.

[0022] In a possible design, the basic information of the i-th user includes the work information of the i-th user and / or the provident fund and social security payment information of the i-th user;

[0023] Determining a group label corresponding to the i-th user according to the i-th data information includes:

[0024] The group label corresponding to the i-th user is determined according to the work information of the i-th user and / or the provident fund and social security payment information of the i-th user.

[0025] In a possible design, the basic information of the i-th user further includes the age of the i-th user, and the consumption information of the i-th user includes the average consumption amount and / or the average loan repayment amount;

[0026] Determining a second score of the i-th user according to the basic information of the i-th user and the consumption information of the i-th user includes:

[0027] Determine a second score of the i-th user according to the age of the i-th user and the average consumption amount and / or the average loan repayment amount;

[0028] Wherein, the age of the i-th user is inversely proportional to the second score of the i-th user;

[0029] The average consumption amount and / or average loan repayment amount is directly proportional to the second score of the i-th user.

[0030] In a second aspect, the present application further provides a user value assessment device, the device comprising a transceiver unit and a processing unit:

[0031] The transceiver unit is used to obtain M data information, wherein the M data information corresponds to M users one by one, wherein the i-th data information includes basic information of the i-th user, income information of the i-th user, deposit and loan information of the i-th user, and consumption information of the i-th user, and the i-th data information is any one of the M data information;

[0032] The processing unit is used to determine a first score of the i-th user based on the basic information of the i-th user, the income information of the i-th user and the deposit and loan information of the i-th user, wherein the first score of the i-th user is used to indicate the risk level of the i-th user; to determine a second score of the i-th user based on the basic information of the i-th user and the consumption information of the i-th user, wherein the second score of the i-th user is used to indicate the consumption capacity of the i-th user; and to determine a user among the M users whose first score satisfies a first preset condition and whose second score satisfies a second preset condition based on the first scores corresponding to the M users and the second scores corresponding to the M users.

[0033] In a possible design, the deposit and loan information of the i-th user includes a business type and a business amount, wherein the business type includes a deposit and / or a loan.

[0034] In one possible design, the processing unit is used to determine users among the M users whose first scores satisfy the first preset condition and whose second scores satisfy the second preset condition, and to determine users among the M users whose first scores are greater than the first preset threshold and whose second scores are greater than the second preset threshold, wherein the first score of the i-th user is inversely proportional to the risk level of the i-th user, and the second score of the i-th user is directly proportional to the consumption capacity of the i-th user.

[0035] In one possible design, the processing unit is further used to determine, among the M users whose first scores are greater than the first preset threshold and whose second scores are greater than the second preset threshold, users whose first scores are greater than a third preset threshold and whose second scores are greater than a fourth preset threshold, and generate a first list; wherein the third preset threshold is greater than the first preset threshold, and the fourth preset threshold is greater than the second preset threshold.

[0036] In a possible design, the processing unit is further used to determine the group label corresponding to the ith user based on the ith data information; to determine the first score of the ith user based on the basic information of the ith user, the income information of the ith user and the deposit and loan information of the ith user; to determine the first score of the ith user based on the first coefficient, the basic information of the ith user, the income information of the ith user and the deposit and loan information of the ith user; the first coefficient is associated with the group label corresponding to the ith user; to determine the second score of the ith user based on the basic information of the ith user and the consumption information of the ith user; and to determine the second score of the ith user based on the first coefficient, the basic information of the ith user and the consumption information of the ith user.

[0037] In a possible design, the basic information of the i-th user includes the work information of the i-th user and / or the provident fund and social security payment information of the i-th user;

[0038] The processing unit is used to determine the group label corresponding to the i-th user according to the work information of the i-th user and / or the provident fund and social security payment information of the i-th user when determining the group label corresponding to the i-th user according to the i-th data information.

[0039] In a possible design, the basic information of the i-th user further includes the age of the i-th user, and the consumption information of the i-th user includes the average consumption amount and / or the average loan repayment amount;

[0040] The processing unit is configured to determine the second score of the i-th user according to the age of the i-th user and the average consumption amount and / or the average loan repayment amount when determining the second score of the i-th user according to the basic information of the i-th user and the consumption information of the i-th user;

[0041] Among them, the age of the i-th user is inversely proportional to the second score of the i-th user; the average consumption amount and / or the average loan repayment amount is directly proportional to the second score of the i-th user.

[0042] In a third aspect, the present application also provides a user value assessment device, comprising: one or more processors and one or more memories; wherein the one or more memories store one or more programs, and when the programs are executed by the one or more processors, the device executes a method as described in any one of the above-mentioned first aspects.

[0043] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a program, and when the program is executed on a device, the device executes the method as described in any one of the above-mentioned first aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A flowchart of a user value assessment method provided in an embodiment of the present application;

[0046] Figure 2 A diagram of the system implementation architecture used by the user value assessment method provided in the embodiment of the present application;

[0047] Figure 3 A schematic diagram of the structure of the user value evaluation device provided in the embodiment of the present application Figure 1 ;

[0048] Figure 4 A schematic diagram of the structure of the user value evaluation device provided in the embodiment of the present application Figure 2 . DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0050] The application scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. It is known to those skilled in the art that with the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems. In the description of the present application, unless otherwise specified, the meaning of "multiple" is two or more.

[0051] The above-mentioned reliance on bank account managers to convert existing users still has the following problems:

[0052] 1. User data acquisition is time-consuming and labor-intensive: User data for different businesses exist in multiple business systems of the bank. Therefore, in the process of acquiring user data, account managers need to coordinate and communicate across multiple business systems. At the data implementation level, they need to obtain technical and business support from various business departments, which consumes a lot of manpower and time costs.

[0053] 2. Compliance issues of user data: Customer data includes users’ basic personal information, such as their ID number and address. If relevant security protection measures are not taken for user data, illegal use of user data may occur, leading to user data leakage or unauthorized abuse of relevant user privacy data, seriously affecting users’ trust in the bank.

[0054] 3. Validity of user data: Account managers convert existing users mainly based on historical data from various business systems. If the user has been doing business with the bank for too long or the corresponding business system data has not been updated in real time, for example, the user's registered contact information may become invalid.

[0055] Based on the existing problems in the conversion of existing stock users, this application proposes the following Figure 1 The user value evaluation method shown in FIG. 1 is a system implementation architecture used in the method. Figure 2 As shown, it consists of multiple business systems, network communication servers, data warehouse servers, modeling development servers, and terminal application servers. The business systems include but are not limited to bank counter business systems, mobile banking, WeChat applets, and credit transaction systems. For example, Figure 2 The business system 1 in the example may be a bank counter business system. Figure 2 The business system 2 in the example can be mobile banking. Figure 2 The business system 3 can be a WeChat applet, and this application does not limit this.

[0056] The user value assessment method proposed in this application includes:

[0057] Step 100: Obtain M data information, where the M data information corresponds to the M users one by one, wherein the i-th data information includes the basic information of the i-th user, the income information of the i-th user, the deposit and loan information of the i-th user, and the consumption information of the i-th user, and the i-th data information is any one of the M data information, Figure 2 The network communication server shown obtains M data information from multiple business systems.

[0058] Exemplarily, the basic information of the i-th user includes the i-th user's age, work information and / or the i-th user's provident fund and social security payment information; the i-th user's income information may include salary income, fund income, transfer income, etc., which is not limited in this application; the i-th user's deposit and loan information includes business type and business amount, where the business type includes deposits and / or loans, for example, mortgage business, car loan business; the i-th user's consumption information includes the average consumption amount and / or the average loan repayment amount.

[0059] For example, suppose Wang XX works in XXX unit, is 30 years old, has a monthly salary income of 12,000 yuan, a financial management income of 1,000 yuan, a monthly provident fund and social security payment of 2,000 yuan, a monthly consumption amount of 4,000 yuan, and went to the bank counter to apply for a car loan, with a total loan of 100,000 yuan and a monthly loan repayment amount of 2,000 yuan. The data information of this user in the bank counter business system is: ① Basic user information: Name: Wang XX, Age: 35, Work information: XXX unit; ② Income information: 13,000; ③ Deposit and loan information: Business type: car loan, business amount: 100,000; ④ Consumption information: Average consumption amount: 4,000, average loan repayment amount: 2,000.

[0060] Exemplarily, the network communication server sends the acquired user data information to Figure 2 The data warehouse server shown performs pre-processing operations such as data screening and data desensitization on data information.

[0061] Exemplarily, data screening includes introducing time series rules and local outlier factor algorithms to screen data. Specifically, the introduction of time series rules can screen out the latest contact information, work information and other basic information in the user's data information; the use of local outlier factor algorithms can identify abnormal data information points, and then filter the data information containing abnormal data information points; data desensitization refers to desensitizing relevant sensitive information in the data information in accordance with the bank's data management regulations and systems.

[0062] Example 1: Suppose a user previously applied for a car loan at a bank counter, and recently applied for a deposit through the bank's mobile banking. If there is a difference between the user's basic information in the mobile banking and the user's basic information in the bank's counter business system, it means that the user's personal basic information has changed after applying for the car loan. Then, according to the time sequence rule, the user's basic information should be based on the mobile banking.

[0063] Example 2: Suppose that the data information obtained from a certain user shows that the user has applied for a car loan business ①, and the loan amount is 300,000, but the upper limit of the loan amount for the bank's car loan business ① is 200,000. Then the local outlier factor algorithm can identify the loan amount in the data information as an abnormal data information point, and therefore filter the abnormal data information.

[0064] In the above data screening process, the time series rules can ensure that the user's basic information is valid and unique, and the local outlier factor algorithm can filter out abnormal data information to ensure that subsequent steps are based on normal data information, improve efficiency and ensure the reliability of results; data desensitization operations provide protection for the user's relevant privacy information and improve data security.

[0065] The data warehouse server can further determine the user's group label and user portrait based on the preprocessed data information.

[0066] Exemplarily, a user's group label can be determined based on the user's work information and / or the user's provident fund and social security payment information. For example, assuming that the user's provident fund and social security payment has lasted for a long time, the user group label can be set to the provident fund group; assuming that the user's work unit is determined to be a public institution based on the user's work information, the user group label can be set to the public institution group; in addition, if the bank stipulates that a deposit amount greater than 500,000 yuan is a large deposit, then when the user's deposit and loan information includes deposit business and the deposit amount is greater than 500,000, the user group label can be set to the high-quality deposit group.

[0067] Exemplarily, the user portrait can also be determined based on the user's work information and / or the user's provident fund and social security payment information and deposit and loan information. For example, assuming that a user's provident fund and social security payment has lasted for a long time and his or her work unit is a public institution, then the user portrait can be "stable job, good work unit"; if the bank stipulates that a mortgage amount greater than 1 million yuan is a large mortgage, then when the user's deposit and loan information includes mortgage business and the business amount is greater than 1 million, the user portrait can be a "large mortgage user."

[0068] It should be noted that the above is only one possible method for setting user group labels and user portraits provided in this application. It can also be set in other ways according to actual business needs, and this application does not limit this.

[0069] Figure 2 The data warehouse server shown in the figure sends the preprocessed data information as well as the corresponding group label and user portrait of each user to Figure 2 Modeling development server shown.

[0070] Step 110: Determine the first score of the i-th user based on the basic information of the i-th user, the income information of the i-th user, and the deposit and loan information of the i-th user. The first score of the i-th user is used to indicate the risk level of the i-th user. This step is performed in Figure 2 The modeling shown is executed in the development server.

[0071] Exemplarily, when determining the first score of the ith user based on the basic information of the ith user, the income information of the ith user, and the deposit and loan information of the ith user, the first score of the ith user is determined based on the first coefficient, the basic information of the ith user, the income information of the ith user, and the deposit and loan information of the ith user, wherein the first coefficient is associated with the group label corresponding to the ith user.

[0072] Exemplarily, if the user's group tags include a provident fund group, a public institution group, and a high-quality deposit group, it can be assumed that the first coefficient associated with the provident fund group is less than the first coefficient associated with the public institution group and less than the first coefficient associated with the high-quality deposit group.

[0073] The first score can be calculated using but not limited to the following formula:

[0074]

[0075] The formula is designed based on the Risk-Adjusted Return on Capital (RAROC) framework, where Model (Income) is the user's estimated monthly income, which is determined by the estimated average monthly income machine learning model based on the user's income information. Duration is the duration, which can be set to a constant of 1.84. Model (Income) and Duration are multiplied to get the user's expected income level to evaluate the user's debt repayment ability. Asset, Debt, and n are associated with deposit and loan information, which can represent the user's recent debt level. Assuming that a user has handled two businesses, a deposit of 500,000 and a car loan of 100,000, then n is the number of business types included in the deposit and loan information, which is 2. The asset corresponding to the deposit business is 500,000 and the debt is 0. The asset corresponding to the car loan business is 0 and the debt is 100,000. w is the preset weight value, and Model (PD m ) is the user default probability, Model(PD m ) and the user portrait described in step 100. The better the user features, the better the Model (PD m ) value is smaller. For example, assuming that the user profile of user ① is "stable job, good work unit", the user profile of user ② is "large deposit user", and the user profile of user ③ is "large mortgage user", then the Model (PDm ) values ​​are as follows: User ①’s Model (PD m ) value<User②'s Model(PD m ) value<User③'s Model(PD m ) value, the first coefficient may include user default probability (Loss Given Default, LGD), pre-credit limit (Exposure at Default, EAD) and reserved risk threshold (Underwriters Laboratories, UL).

[0076] This step calculates the user's first score based on the user's basic information, income information, and deposit and loan information, and quantifies the user's risk level. The user's first score is inversely proportional to the user's risk level, that is, the larger the first score, the lower the user's risk level; the smaller the first score, the higher the user's risk level.

[0077] Step 120: Determine the second score of the i-th user based on the basic information of the i-th user and the consumption information of the i-th user. The second score of the i-th user is used to indicate the consumption capacity of the i-th user. This step is also performed in Figure 2 The modeling shown is executed in the development server.

[0078] Exemplarily, when determining the second score of the i-th user based on the first coefficient, the basic information of the i-th user and the consumption information of the i-th user, the second score of the i-th user is determined based on the first coefficient, the age of the i-th user, and the average consumption amount and / or the average loan repayment amount.

[0079] The second score is calculated using the following formula:

[0080]

[0081] in, is the average consumption amount in the user's consumption information, EAD is the pre-credit limit, which can be the same as the value of EAD in Score1. The first coefficient also includes the credit card limit utilization rate used_ratio. It represents the user's consumption contribution, Model(trans_rate) is the estimated conversion rate, and the value of Model(trans_rate) is inversely proportional to the user's age, and directly proportional to the user's average consumption amount and average loan repayment amount. That is to say, the older the user is, the smaller the value of Model(trans_rate) is, and the smaller the second score is; the larger the user's average consumption amount or average loan repayment amount is, the larger the value of Model(trans_rate) is, and the larger the second score is; therefore, the second score is inversely proportional to the user's age, and directly proportional to the user's average consumption amount and average loan repayment amount.

[0082] This step calculates the user's second score based on the user's basic information and consumption information, quantifies the user's consumption ability, and the user's second score is directly proportional to the user's consumption ability. That is, the smaller the second score, the weaker the user's consumption ability; the larger the second score, the stronger the user's consumption ability.

[0083] Step 130: Determine, according to the first scores corresponding to the M users and the second scores corresponding to the M users, the users whose first scores satisfy the first preset condition and whose second scores satisfy the second preset condition among the M users.

[0084] Exemplarily, determining a user among M users whose first score satisfies a first preset condition and whose second score satisfies a second preset condition refers to determining a user among M users whose first score is greater than a first preset threshold and whose second score is greater than a second preset threshold.

[0085] If the user's first score is greater than the first preset threshold, it means that the user is a low-risk user; if the user's second score is greater than the second preset threshold, it means that the user is a high-consumption user. Therefore, if the user's first score is greater than the first preset threshold and the second score is greater than the second preset threshold, it means that the user is a low-risk and high-consumption type, and such users can be used as existing user conversion objects.

[0086] If the user's first score is less than the first preset threshold, it means that the user is a high-risk user; if the user's second score is greater than the second preset threshold, it means that the user is a high-spending user. Therefore, if the user's first score is less than the first preset threshold and the second score is greater than the second preset threshold, it means that the user is a high-risk and high-spending type. Such users can also be used as existing user conversion objects, but more stringent review strategies need to be adopted when converting such users.

[0087] If the user's first score is less than the first preset threshold, it means that the user is a high-risk user; if the user's second score is less than the second preset threshold, it means that the user is a low-consumption user. Therefore, if the user's first score is less than the first preset threshold and the second score is less than the second preset threshold, it means that the user is a high-risk, low-consumption type, and such users will not be converted into existing users.

[0088] Furthermore, among the low-risk, high-consumption type users who can be used as the conversion targets of the stock users, the users whose first scores are greater than the third preset threshold and whose second scores are greater than the fourth preset threshold are determined, and a first list is generated, wherein the third preset threshold is greater than the first preset threshold, and the fourth preset threshold is greater than the second preset threshold. The user's first score is greater than the third preset threshold and the second score is greater than the fourth preset threshold, indicating that the user is a user with a higher priority among the low-risk, high-consumption type, and therefore, the user can be adjusted to the front of the first list and the conversion of the stock users can be prioritized.

[0089] For example, assuming that the first preset threshold and the second preset threshold are 30, the third preset threshold and the fourth preset threshold are 70, and there are 4 user data information, the first score and the second score determined according to the respective data information are: User ①: first score: 20, second score: 15; User ②: first score: 15, second score: 15; User ③: first score: 45, second score: 60; User ④: first score: 80, second score: 75. Since the first score of user ①, 20, is less than the first preset threshold of 30 and the second score of user ①, 15, is less than the second preset threshold of 30, user ① belongs to the high-risk low-consumption type. Similarly, it is determined that user ② belongs to the high-risk low-consumption type, user ③ belongs to the medium-risk medium-consumption type, and user ④ belongs to the low-risk high-consumption type. Then, users ① and ② of the high-risk low-consumption type are filtered, and only users ③ and ④ are included in the first list, and user ④ has a higher priority than user ③.

[0090] This step determines the users who meet the preset conditions based on the first and second scores and determines the risk level and consumption level corresponding to the users, and generates a first list. The bank account manager or relevant staff can Figure 2 The terminal application server shown exports the first list and formulates differentiated conversion strategies for users with different risks and consumption levels to improve the conversion success rate.

[0091] In addition, after the conversion service is carried out for users, Figure 2 As shown in the data feedback record, the conversion results can be filled back into the first list. For example, the conversion results can be roughly divided into successful conversions and failed conversions. Then, filling the conversion results back into the first list can avoid repeated conversions for users who have successfully converted, thereby improving the user experience.

[0092] The user value evaluation method provided in the present application calculates a first score and a second score according to the acquired user data information, and evaluates the user value based on the first score and the second score, thereby providing an objective and systematic user value evaluation system. Compared with the manual method of evaluating user value, the user value evaluation method provided in the present application is business-oriented and data-driven, and differentiated conversion plans are formulated for existing users based on the evaluation results, thereby improving the accuracy and success rate of conversion.

[0093] Figure 3 and Figure 4 A schematic diagram of the structure of a possible user value evaluation device provided for an embodiment of the present application. These user value evaluation devices can be used to implement the functions of various servers such as the network communication server, data warehouse server, and modeling analysis server in the above method embodiment, and thus can also achieve the beneficial effects of the above method embodiment.

[0094] like Figure 3 As shown, the user value evaluation device 300 includes a transceiver unit 310 and a processing unit 320. When the user value evaluation device 300 is used to implement Figure 1 In the method embodiment shown, the functions of various servers such as the network communication server, the data warehouse server, and the modeling analysis server are:

[0095] The transceiver unit 310 is used to obtain M data information, where the M data information corresponds to M users one by one, wherein the i-th data information includes basic information of the i-th user, income information of the i-th user, deposit and loan information of the i-th user, and consumption information of the i-th user, and the i-th data information is any one of the M data information;

[0096] The processing unit 320 is used to determine a first score of the i-th user based on the basic information of the i-th user, the income information of the i-th user and the deposit and loan information of the i-th user, wherein the first score of the i-th user is used to indicate the risk level of the i-th user; to determine a second score of the i-th user based on the basic information of the i-th user and the consumption information of the i-th user, wherein the second score of the i-th user is used to indicate the consumption capacity of the i-th user; and to determine users among the M users whose first scores satisfy a first preset condition and whose second scores satisfy a second preset condition based on the first scores corresponding to the M users and the second scores corresponding to the M users.

[0097] In a possible design, the deposit and loan information of the i-th user includes a business type and a business amount, wherein the business type includes a deposit and / or a loan.

[0098] In a possible design, the processing unit 320 is used to determine users among the M users whose first scores satisfy the first preset condition and whose second scores satisfy the second preset condition, and to determine users among the M users whose first scores are greater than the first preset threshold and whose second scores are greater than the second preset threshold; wherein the first score of the i-th user is inversely proportional to the risk level of the i-th user, and the second score of the i-th user is directly proportional to the consumption capacity of the i-th user.

[0099] In one possible design, the processing unit 320 is further used to determine, among the M users whose first scores are greater than the first preset threshold and whose second scores are greater than the second preset threshold, users whose first scores are greater than a third preset threshold and whose second scores are greater than a fourth preset threshold, and generate a first list; wherein the third preset threshold is greater than the first preset threshold, and the fourth preset threshold is greater than the second preset threshold.

[0100] In a possible design, the processing unit 320 is further used to determine the group label corresponding to the ith user based on the ith data information; to determine the first score of the ith user based on the basic information of the ith user, the income information of the ith user and the deposit and loan information of the ith user; to determine the first score of the ith user based on the first coefficient, the basic information of the ith user, the income information of the ith user and the deposit and loan information of the ith user; the first coefficient is associated with the group label corresponding to the ith user; to determine the second score of the ith user based on the basic information of the ith user and the consumption information of the ith user; and to determine the second score of the ith user based on the first coefficient, the basic information of the ith user and the consumption information of the ith user.

[0101] In a possible design, the basic information of the i-th user includes the work information of the i-th user and / or the provident fund and social security payment information of the i-th user;

[0102] The processing unit 320 is used to determine the group label corresponding to the i-th user according to the work information of the i-th user and / or the provident fund and social security payment information of the i-th user when determining the group label corresponding to the i-th user according to the i-th data information.

[0103] In a possible design, the basic information of the i-th user further includes the age of the i-th user, and the consumption information of the i-th user includes the average consumption amount and / or the average loan repayment amount;

[0104] The processing unit 320 is configured to determine the second score of the i-th user according to the age of the i-th user and the average consumption amount and / or the average loan repayment amount when determining the second score of the i-th user according to the basic information of the i-th user and the consumption information of the i-th user;

[0105] Wherein, the age of the i-th user is inversely proportional to the second score of the i-th user;

[0106] The average consumption amount and / or average loan repayment amount is directly proportional to the second score of the i-th user.

[0107] For more detailed description of the transceiver unit 310 and the processing unit 320, please refer to Figure 1 The relevant description in the method embodiment shown is directly obtained and will not be repeated here.

[0108] like Figure 4 As shown, the user value evaluation device 400 includes a processor 410 and an interface circuit 420. The processor 410 and the interface circuit 420 are coupled to each other. It is understood that the interface circuit 420 can be a transceiver or an input-output interface. Optionally, the user value evaluation device 400 may also include a memory 430 for storing instructions executed by the processor 410 or storing input data required by the processor 410 to execute instructions or storing data generated after the processor 410 executes instructions.

[0109] When the user value evaluation device 400 is used to implement Figure 1 When the method is shown, the processor 410 is used to implement the functions of the processing unit 320, and the interface circuit 420 is used to implement the functions of the transceiver unit 310.

[0110] The division of units in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present application may be integrated into a processor, or may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0111] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0112] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A user value assessment method, characterized in that: The method includes: Acquire M data information, wherein the M data information corresponds to the M users one by one, wherein the i-th data information includes the basic information of the i-th user, the income information of the i-th user, the deposit and loan information of the i-th user, and the consumption information of the i-th user, and the i-th data information is any one of the M data information; Determine a first score of the i-th user according to the basic information of the i-th user, the income information of the i-th user, and the deposit and loan information of the i-th user, wherein the first score of the i-th user is used to indicate the risk level of the i-th user; Determine a second score of the i-th user according to the basic information of the i-th user and the consumption information of the i-th user, wherein the second score of the i-th user is used to indicate the consumption capacity of the i-th user; According to the first scores respectively corresponding to the M users and the second scores respectively corresponding to the M users, users among the M users whose first scores satisfy a first preset condition and whose second scores satisfy a second preset condition are determined.

2. The method according to claim 1, characterized in that The deposit and loan information of the ith user includes a business type and a business amount, wherein the business type includes a deposit and / or a loan.

3. The method according to claim 1, characterized in that Determining a user among the M users whose first score satisfies a first preset condition and whose second score satisfies a second preset condition includes: Determine a user among the M users whose first score is greater than a first preset threshold and whose second score is greater than a second preset threshold; The first score of the i-th user is inversely proportional to the risk level of the i-th user, and the second score of the i-th user is directly proportional to the consumption capacity of the i-th user.

4. The method according to claim 3, characterized in that Also includes: Among the M users whose first scores are greater than the first preset threshold and whose second scores are greater than the second preset threshold, determine the users among the M users whose first scores are greater than the third preset threshold and whose second scores are greater than the fourth preset threshold, and generate a first list; wherein the third preset threshold is greater than the first preset threshold, and the fourth preset threshold is greater than the second preset threshold.

5. The method according to claim 1, characterized in that Also includes: Determine a group label corresponding to the i-th user according to the i-th data information; Determining a first score of the i-th user according to the basic information of the i-th user, the income information of the i-th user, and the deposit and loan information of the i-th user includes: Determine a first score of the i-th user according to a first coefficient, basic information of the i-th user, income information of the i-th user, and deposit and loan information of the i-th user; the first coefficient is associated with a group label corresponding to the i-th user; Determining a second score of the i-th user according to the basic information of the i-th user and the consumption information of the i-th user includes: A second score of the i-th user is determined according to the first coefficient, the basic information of the i-th user, and the consumption information of the i-th user.

6. The method according to claim 5, characterized in that The basic information of the i-th user includes the work information of the i-th user and / or the provident fund and social security payment information of the i-th user; Determining a group label corresponding to the i-th user according to the i-th data information includes: The group label corresponding to the i-th user is determined according to the work information of the i-th user and / or the provident fund and social security payment information of the i-th user.

7. The method according to claim 1, characterized in that The basic information of the i-th user also includes the age of the i-th user, and the consumption information of the i-th user includes the average consumption amount and / or the average loan repayment amount; Determining a second score of the i-th user according to the basic information of the i-th user and the consumption information of the i-th user includes: Determine a second score of the i-th user according to the age of the i-th user and the average consumption amount and / or the average loan repayment amount; Wherein, the age of the i-th user is inversely proportional to the second score of the i-th user; The average consumption amount and / or average loan repayment amount is directly proportional to the second score of the i-th user.

8. A user value assessment device, characterized in that: The device includes: a transceiver unit, configured to obtain M data information, wherein the M data information corresponds to the M users one by one, wherein the i-th data information includes the basic information of the i-th user, the income information of the i-th user, the deposit and loan information of the i-th user, and the consumption information of the i-th user, and the i-th data information is any one of the M data information; A processing unit, configured to determine a first score of the i-th user based on basic information of the i-th user, income information of the i-th user, and deposit and loan information of the i-th user, wherein the first score of the i-th user is used to indicate the risk level of the i-th user; to determine a second score of the i-th user based on the basic information of the i-th user and consumption information of the i-th user, wherein the second score of the i-th user is used to indicate the consumption capacity of the i-th user; and to determine users among the M users whose first scores satisfy a first preset condition and whose second scores satisfy a second preset condition based on first scores corresponding to the M users and second scores corresponding to the M users.

9. A user value assessment device, characterized in that: include: One or more processors and one or more memories; wherein the one or more memories store one or more programs, and when the programs are executed by the one or more processors, the device executes the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The readable storage medium includes a program, and when the program is executed on a device, the device is caused to perform the method according to any one of claims 1 to 7.

Images