A method and device for identifying high-value customers

Abstract

This invention provides a method and apparatus for identifying high-value customers, applicable to the field of data processing technology. The method includes: when customer information in a database is updated, acquiring updated customer information with a free insurance identifier from the database; searching for customer attribute information and free insurance information within the updated customer information with the free insurance identifier; calculating the customer's value score based on the customer attribute information and the free insurance information; and determining the customer as a high-value customer if the customer's value score meets the scoring criteria for high-value customers. The apparatus is used to execute the above method. The high-value customer identification method and apparatus provided by this invention can acquire customer information of free insurance customers in real time. Utilizing the unique properties of free insurance, free insurance customers serve as an important source of customer information. By studying the customer information of free insurance customers, the value of customers can be evaluated, thereby identifying high-value customers.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and device for identifying high-value customers. Background Art

[0002] With the rapid development of e-commerce platforms and the advent of the big data era, Internet insurance has developed by leaps and bounds, and the channels for acquiring customers have become more extensive. Therefore, the quality of acquired customers varies. Especially in the face of business diversification, how to acquire customers and verify customer quality is a major test for Internet insurance companies. Summary of the invention

[0003] In view of the problems in the prior art, an embodiment of the present invention provides a method and device for identifying high-value customers, which can at least partially solve the problems in the prior art.

[0004] On the one hand, the present invention proposes a method for identifying high-value customers, comprising: when customer information in a database is updated, obtaining updated customer information with a free insurance identification in the database; searching for customer attribute information and free insurance information in the updated customer information with the free insurance identification; calculating a value score of the customer based on the customer attribute information and the free insurance information; if the customer's value score meets the scoring conditions of a high-value customer, determining that the customer is a high-value customer.

[0005] Optionally, when the customer information in the database is updated, obtaining the updated customer information with the free insurance identification in the database includes: when the customer information in the database is updated, synchronizing the updated customer information with the free insurance identification in the database to the distributed message system cluster; and writing the customer information in the distributed message system cluster into a pre-created customer information table through the batch and stream integrated platform.

[0006] Optionally, searching for customer attribute information and free insurance information in the updated customer information with the free insurance identifier includes: searching for field values ​​of each field in a preset policyholder information table model, an insured information table model, a policy information table model and a claim information table model in the customer information table; generating the policyholder information table, the insured information table, the policy information table and the claim information table of the customer according to the found field values ​​of each field; and obtaining the customer attribute information and free insurance information of the customer in the policyholder information table, the insured information table, the policy information table and the claim information table of the customer.

[0007] Optionally, the free insurance information includes the free insurance payout ratio and / or the free insurance conversion ratio.

[0008] Optionally, the customer attribute information includes at least one of the following: age, gender, occupation, education level, social security information, historical compensation amount, and number of paid products purchased.

[0009] Optionally, calculating the customer's value score based on the customer attribute information and the free insurance information includes: determining the information value of each item of customer attribute information and each item of free insurance information based on the assignment rules of the customer attribute information and the free insurance information; and calculating the customer's value score based on the information value of each item of customer attribute information and each item of free insurance information.

[0010] Optionally, the customer's value score is calculated according to the following customer value score calculation formula:

[0011] y=β 1 x 1 +…+β k x k +β k+1 x k+1 +…β n x n +ε;

[0012] In the formula,

[0013] y is the customer's value score;

[0014] x 1 ,…,x k The information value of each customer attribute information;

[0015] x k+1 ,…,x n The information value of each gift insurance information;

[0016] β 1 ,…,β n is the correction factor;

[0017] ε is the compensation value.

[0018] Optionally, the assignment rule includes:

[0019] For the continuous variables in the customer attribute information and the free insurance information, the actual value of the continuous variable is used as the information value of the continuous variable; and / or

[0020] For the discrete variables in the customer attribute information and the free insurance information, the information value of each discrete variable is calculated according to the following information value calculation formula:

[0021]

[0022] In the formula,

[0023] IVi is the information value of the ith group of the discrete variable;

[0024] #y i is the number of high-value customers in the i-th group of the discrete variable in the customer sample data;

[0025] #y T is the number of all high-value customers in the customer sample data;

[0026] #n i is the number of low-value customers in the ith group of the discrete variable in the customer sample data;

[0027] #n T is the number of all low-value customers in the customer sample data.

[0028] In a second aspect, the present invention proposes a device for identifying high-value customers, comprising: an acquisition module, used to acquire updated customer information with a free insurance identification in the database when customer information in the database is updated; a search module, used to search for customer attribute information and free insurance information in the updated customer information with the free insurance identification; a calculation module, used to calculate the value score of the customer based on the customer attribute information and the free insurance information; and a determination module, used to determine that the customer is a high-value customer if the customer's value score meets the scoring conditions of a high-value customer.

[0029] Optionally, the acquisition module is specifically used to: when customer information in the database is updated, synchronize the updated customer information with the free insurance identification in the database to the distributed message system cluster; and write the customer information in the distributed message system cluster into a pre-created customer information table through the integrated flow and batch platform.

[0030] Optionally, the search module is specifically used to: search for the field values ​​of each field in the preset policyholder information table model, insured information table model, policy information table model and claim information table model in the customer information table; generate the customer's policyholder information table, insured information table, policy information table and claim information table according to the found field values ​​of each field; obtain the customer attribute information and free insurance information of the customer in the customer's policyholder information table, insured information table, policy information table and claim information table.

[0031] Optionally, the free insurance information includes the free insurance payout ratio and / or the free insurance conversion ratio.

[0032] Optionally, the customer attribute information includes at least one of the following: age, gender, occupation, education level, social security information, historical compensation amount, and number of paid products purchased.

[0033] Optionally, the calculation module is specifically used to: determine the information value of each item of customer attribute information and each item of free insurance information according to the assignment rules of the customer attribute information and the free insurance information; and calculate the value score of the customer according to the information value of each item of customer attribute information and each item of free insurance information.

[0034] Optionally, the calculation module calculates the customer's value score according to the following customer value score calculation formula:

[0035] y=β 1 x 1 +…+β k x k +β k+1 x k+1 +…β n x n +ε;

[0036] In the formula,

[0037] y is the customer's value score;

[0038] x 1 ,…,x k The information value of each customer attribute information;

[0039] x k+1 ,…,x n The information value of each gift insurance information;

[0040] β 1 ,…,β n is the correction factor;

[0041] ε is the compensation value.

[0042] Optionally, the assignment rule includes:

[0043] For the continuous variables in the customer attribute information and the free insurance information, the actual value of the continuous variable is used as the information value of the continuous variable; and / or

[0044] For the discrete variables in the customer attribute information and the free insurance information, the information value of each discrete variable is calculated according to the following information value calculation formula:

[0045]

[0046] In the formula,

[0047] IV i is the information value of the ith group of the discrete variable;

[0048] #y iis the number of high-value customers in the i-th group of the discrete variable in the customer sample data;

[0049] #y T is the number of all high-value customers in the customer sample data;

[0050] #n i is the number of low-value customers in the ith group of the discrete variable in the customer sample data;

[0051] #n T is the number of all low-value customers in the customer sample data.

[0052] On the other hand, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the high-value customer identification method described in any of the above embodiments when executing the program.

[0053] In yet another aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for identifying high-value customers described in any of the above embodiments.

[0054] The high-value customer identification method, device and electronic device provided by the embodiments of the present invention can obtain customer information of gift insurance customers in real time, use the unique properties of gift insurance to take gift insurance customers as an important source of customer information, and evaluate the value of customers by studying the customer attribute information of gift insurance customers and gift insurance information, thereby identifying high-value customers. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0056] Figure 1 It is a flowchart of a method for identifying high-value customers provided by an embodiment of the present invention.

[0057] Figure 2 It is a partial flow chart of a method for identifying high-value customers provided by an embodiment of the present invention.

[0058] Figure 3 It is a schematic diagram of a real-time data extraction process provided by an embodiment of the present invention.

[0059] Figure 4It is a partial flow chart of a method for identifying high-value customers provided by an embodiment of the present invention.

[0060] Figure 5 It is a partial flow chart of a method for identifying high-value customers provided by an embodiment of the present invention.

[0061] Figure 6 It is a schematic diagram of the structure of a high-value customer identification device provided by an embodiment of the present invention.

[0062] Figure 7 It is a schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention. It should be noted that, in the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other arbitrarily.

[0064] The execution subject of the high-value customer identification method provided by the embodiment of the present invention includes but is not limited to a computer.

[0065] Figure 1 FIG. 1 is a flow chart of a method for identifying high-value customers provided by an embodiment of the present invention. Figure 1 As shown, the method for identifying high-value customers provided by the embodiment of the present invention includes:

[0066] S101. When customer information in a database is updated, obtaining updated customer information with a free insurance identification in the database;

[0067] In this step, the database is used to receive data updated by the business department in real time, such as receiving information about customers who receive free insurance in real time; free insurance refers to insurance products given to customers free of charge by insurance companies or insurance agencies. Free insurance is widely recognized by customers due to its outstanding features of free and practical. Therefore, acquiring customers through free insurance is an important means of acquiring customers, and the value evaluation of free insurance customers becomes an important basis for further business development.

[0068] In this embodiment, for each customer who receives free insurance (free insurance customer), the free insurance identifier is included in the customer information of the customer, which is used to mark the customer. When the customer attribute information or insurance information of the free insurance customer is updated in the database, or when a new free insurance customer is added, an operation of obtaining the customer attribute information and insurance information of the free insurance customer updated in the database is triggered. In this way, the free insurance customer data is updated in real time.

[0069] S102, searching for customer attribute information and free insurance information in the updated customer information with the free insurance identification;

[0070] In this step, the customer attribute information refers to the inherent attributes of the customer, and the customer attribute information includes at least one of the following: age, gender, occupation, education level, social security information, historical claim amount, number of paid products purchased, etc.; the gift insurance information refers to information related to the gift insurance, such as the gift insurance claim ratio and / or gift insurance conversion rate, etc.; the gift insurance conversion situation can be determined according to the conversion recognition rules set by the insurance company or insurance agency, for example: if the insured of the gift insurance purchases a policy as the insured 3 months after receiving the gift insurance, the policy is considered to be a gift insurance conversion policy.

[0071] S103, calculating the value score of the customer according to the customer attribute information and the free insurance information;

[0072] In this step, the customer attribute information and insurance information of customers with the free insurance logo can be sorted out, such as the age, gender, social security, historical claim amount, free insurance conversion rate and other information of customers with the free insurance logo, and combined with the underwriting regulations of insurance companies and the China Banking and Insurance Regulatory Commission, a customer value evaluation system can be obtained, and the customer's value score can be calculated based on the customer value evaluation system.

[0073] S104: If the value score of the customer meets the scoring conditions of a high-value customer, the customer is determined to be a high-value customer.

[0074] In this step, the scoring conditions for high-value customers may be preset. For example, when the value score of the customer is higher than a preset threshold, it can be considered that the value score of the customer meets the scoring conditions for high-value customers. For another example, when the value score of the customer is within the scoring range of high-value customers, it can be considered that the value score of the customer meets the scoring conditions for high-value customers.

[0075] The method for identifying high-value customers provided by the embodiment of the present invention can obtain customer information of gift insurance customers in real time, utilize the unique properties of gift insurance, use gift insurance customers as an important source of customer information, and evaluate the value of customers by studying the customer attribute information of gift insurance customers and gift insurance information, thereby identifying high-value customers.

[0076] like Figure 2 As shown, optionally, when the customer information in the database is updated, obtaining the updated customer information with the free insurance identification in the database includes:

[0077] S1011. When the customer information in the database is updated, the updated customer information with the free insurance identification in the database is synchronized to the distributed message system cluster;

[0078] In this step, the distributed messaging system cluster may be a Kafka cluster. Figure 3 As shown, when the customer information in the database is updated, synchronizing the updated customer information with the free insurance identification in the database to the distributed message system cluster can specifically include: collecting the updated customer information with the free insurance identification in the MySQL / Oracle database into Kafka, wherein the Oracle part needs to submit an application to the DBA, and the MySQL part needs to configure the canal into the Kafka cluster.

[0079] S1012. Write the customer information in the distributed message system cluster into a pre-created customer information table through the batch-stream integrated platform.

[0080] In this step, the stream-batch integrated platform can be built based on Flink and Kafka. Figure 3 As shown, the process of writing the customer information in the distributed message system cluster into a pre-created customer information table through the streaming-batch integrated platform may specifically include: 1. Entering the streaming-batch integrated platform, creating a flink kafka table; creating a flink write table in Hive, and authorizing it to the flink user through the streaming-batch integrated platform; 2. Submitting insert in to hive table and select * from kafka table on the streaming-batch integrated platform, the streaming collection task is submitted successfully; 3. The streaming-batch integrated platform automatically collects the updated customer information with the insurance gift identification in the kafka cluster according to the streaming collection task, and writes it into the hive table; 4. Creating a jenkins job, combining the real-time streaming data in Flink with the offline Hive data, and backfilling the Hive data directly in a unified manner through Flink to merge the increments into the historical data (the historical data is stored in the pre-created customer information table), so as to realize real-time data updating.

[0081] like Figure 4 As shown, optionally, searching for customer attribute information and free insurance information in the updated customer information with the free insurance identifier includes:

[0082] S1021. In the customer information table, search for the field value of each field in the preset policyholder information table model, the insured person information table model, the policy information table model, and the claim information table model;

[0083] In this step, the policyholder information table model, the insured person information table model, the policy information table model, and the claim information table model may use the existing form model in the insurance company database, or may be a form model redesigned according to specific needs; wherein the policyholder information table model mainly includes information related to the policyholder, the insured person information table model mainly includes information related to the insured, the policy information table model mainly includes information related to the policy, and the claim information table model mainly includes information related to the claim; for example:

[0084] 1. The policyholder information table model includes the following fields:

[0085]

[0086]

[0087] 2. The insured person information table model includes the following fields:

[0088]

[0089] 3. The policy information table model includes the following fields:

[0090]

[0091]

[0092]

[0093] 4. The claim information table model includes the following fields:

[0094]

[0095]

[0096] S1022, generating the customer's policyholder information table, insured person information table, insurance policy information table and claim settlement information table according to the found field values ​​of each field;

[0097] In this step, after finding the field values ​​of each field in the preset policy information table model in the customer information table, the policy information table of the customer is generated according to the policy information table model; after finding the field values ​​of each field in the preset insured information table model in the customer information table, the insured information table of the customer is generated according to the insured information table model; after finding the field values ​​of each field in the preset policy information table model in the customer information table, the policy information table of the customer is generated according to the policy information table model; after finding the field values ​​of each field in the preset claim information table model in the customer information table, the claim information table of the customer is generated according to the claim information table model.

[0098] S1023. Obtain the customer attribute information and free insurance information of the customer from the customer's policyholder information table, insured person information table, policy information table, and claim information table.

[0099] In this step, the field values ​​of the fields included in the customer attribute information and the free insurance information are searched in the policyholder information table, the insured information table, the policy information table and the claim information table.

[0100] like Figure 5 As shown, optionally, the calculating the value score of the customer according to the customer attribute information and the free insurance information includes:

[0101] S1031. Determine the information value of each item of customer attribute information and each item of free insurance information according to the assignment rules of the customer attribute information and the free insurance information;

[0102] In this step, since the influence of each item of customer attribute information and each item of free insurance information on the customer's value may be different, corresponding assignment rules can be set to assign corresponding information value to each item of customer attribute information and each item of free insurance information of the customer.

[0103] S1032. Calculate the value score of the customer based on the information value of each item of customer attribute information and each item of free insurance information.

[0104] In this step, the value score of the customer can be evaluated by combining the information value of each customer attribute information and each free insurance information. For example, the average value of the information value of each customer attribute information and the information value of each free insurance information can be used as the value score of the customer.

[0105] Optionally, in the above embodiment, the assignment rule may include:

[0106] For the continuous variables in the customer attribute information and the free insurance information, the actual value of the continuous variable is used as the information value of the continuous variable; and / or

[0107] For the discrete variables in the customer attribute information and the free insurance information, the information value of each discrete variable is calculated according to the following information value calculation formula:

[0108]

[0109] In the formula,

[0110] IV i is the information value of the ith group of the discrete variable;

[0111] #y i is the number of high-value customers in the i-th group of the discrete variable in the customer sample data;

[0112] #y T is the number of all high-value customers in the customer sample data;

[0113] #n i is the number of low-value customers in the ith group of the discrete variable in the customer sample data;

[0114] #n T is the number of all low-value customers in the customer sample data.

[0115] In this embodiment, for example, when the customer attribute information includes age, occupation, education, social security information, historical compensation amount, and number of paid products purchased, the continuous variables and discrete variables in the customer attribute information are shown in the following table:

[0116] Customer attribute information and description:

[0117]

[0118] When the free insurance information includes the free insurance payout ratio and the free insurance conversion rate, the free insurance payout ratio and the free insurance conversion rate can be respectively used as continuous variables.

[0119] For the continuous variables in the customer attribute information and the free insurance information: historical claim amount, number of paid products purchased, free insurance claim ratio, and free insurance conversion rate, the actual value of each continuous variable is used as the information value of the continuous variable.

[0120] For the discrete variables in the customer attribute information and the free insurance information: occupation, age, and education, the information value of each discrete variable is calculated according to the above information value calculation formula. Specifically, taking the customer occupation as an example, as shown in the above table, the customer occupation variable needs to be grouped first to obtain 4 groups of occupations. For the discrete variable of occupation, the information value of the i-th group of the discrete variable is:

[0121]

[0122] in,

[0123] #y i is the number of high-value customers in the ith group of the discrete variable of occupation in the customer sample data;

[0124] #y T is the number of all high-value customers in the customer sample data;

[0125] #n i is the number of low-value customers in the ith group of the discrete variable of occupation in the customer sample data;

[0126] #n T is the number of all low-value customers in the customer sample data.

[0127] The customer sample data is extracted from the historical free insurance customer information database. Which free insurance customers in the customer sample data are high-value customers can be determined based on experience. For example, when the i-th group of the discrete variable occupation is the IT technician group, then #y i It refers to the number of high-value customers who are IT technicians in the customer sample data. T Refers to the number of all high-value customers in the customer sample data, #n i It refers to the number of low-value customers (determined by empirical methods) who are IT technicians in the customer sample data. T Refers to the number of all low-value customers in the customer sample data.

[0128] Optionally, in any of the above embodiments, the customer's value score may be calculated according to the following customer value score calculation formula:

[0129] y=β 1 x 1 +…+β k x k +β k+1 x k+1 +…β n x n +ε;

[0130] In the formula,

[0131] y is the customer's value score;

[0132] x 1 ,…,x k The information value of each customer attribute information;

[0133] x k+1 ,…,xn The information value of each gift insurance information;

[0134] β 1 ,…,β n is the correction factor;

[0135] ε is the compensation value.

[0136] In this embodiment, the correction coefficient is used to correct the size of each information value and to indicate the positive / negative impact of each information on the value score. For example, when the actual value of the continuous variable in the customer attribute information and the insurance gift information is used as the information value of the continuous variable and the information value of the discrete variable in the customer attribute information and the insurance gift information is calculated by the above information value calculation formula, in some cases, the actual value of the continuous variable is very large. For example, for the continuous variable of historical compensation amount, its actual value may range from 0 to several million. At this time, in order to maintain the information value of the continuous variable and the information value of the discrete variable at the same order of magnitude, it is necessary to use a suitable correction coefficient to correct the information value of the continuous variable of historical compensation amount. In addition, since the historical compensation amount is negatively correlated with the value of the customer for the insurance company, the correction coefficient of the continuous variable of historical compensation amount can be negative, such as -1000. In addition, in order to maintain the information value of the continuous variable and the information value of the discrete variable at the same order of magnitude, the correction coefficient of the continuous variable can also adopt a segmented value method, that is, when the discrete variable is in different value ranges, the correction coefficient used is different. Similarly, the same method can be used to set the correction coefficient of each discrete variable.

[0137] The compensation value ε can be understood as the basic value score of the customer, which can be determined based on the customer's credit status in the insurance company, etc. When the customer value score calculation formula is optimized and updated, it is only necessary to update the customer value score calculation formula set in the customer index evaluation system without changing the program, which not only reduces the development cost of the project, but also effectively meets the requirements of management and business for accurate and timely customer value evaluation, improves the development efficiency of the customer index evaluation system, and reduces the risk of frequent code changes to indicator consistency.

[0138] Figure 6 FIG. 1 is a schematic diagram of a high-value customer identification device provided by an embodiment of the present invention. Figure 6As shown, the high-value customer identification device provided by the embodiment of the present invention includes: an acquisition module 21, which is used to acquire updated customer information with a free insurance identification in the database when the customer information in the database is updated; a search module 22, which is used to search for customer attribute information and free insurance information in the updated customer information with the free insurance identification; a calculation module 23, which is used to calculate the value score of the customer based on the customer attribute information and the free insurance information; and a determination module 24, which is used to determine that the customer is a high-value customer if the value score of the customer meets the scoring conditions of the high-value customer.

[0139] The high-value customer identification device provided by the embodiment of the present invention can obtain customer information of gift insurance customers in real time, utilize the unique properties of gift insurance, use gift insurance customers as an important source of customer information, and implement customer value evaluation by studying customer attribute information and gift insurance information of gift insurance customers, thereby identifying high-value customers.

[0140] Optionally, the acquisition module is specifically used to: when customer information in the database is updated, synchronize the updated customer information with the free insurance identification in the database to the distributed message system cluster; and write the customer information in the distributed message system cluster into a pre-created customer information table through the integrated flow and batch platform.

[0141] Optionally, the search module is specifically used to: search for the field values ​​of each field in the preset policyholder information table model, insured information table model, policy information table model and claim information table model in the customer information table; generate the customer's policyholder information table, insured information table, policy information table and claim information table according to the found field values ​​of each field; obtain the customer attribute information and free insurance information of the customer in the customer's policyholder information table, insured information table, policy information table and claim information table.

[0142] Optionally, the free insurance information includes the free insurance payout ratio and / or the free insurance conversion ratio.

[0143] Optionally, the customer attribute information includes at least one of the following: age, gender, occupation, education level, social security information, historical compensation amount, and number of paid products purchased.

[0144] Optionally, the calculation module is specifically used to: determine the information value of each item of customer attribute information and each item of free insurance information according to the assignment rules of the customer attribute information and the free insurance information; and calculate the value score of the customer according to the information value of each item of customer attribute information and each item of free insurance information.

[0145] Optionally, the calculation module calculates the customer's value score according to the following customer value score calculation formula:

[0146] y=β 1 x 1 +…+β k x k +β k+1 x k+1 +…β n x n +ε;

[0147] In the formula,

[0148] y is the customer's value score;

[0149] x 1 ,…,x k The information value of each customer attribute information;

[0150] x k+1 ,…,x n The information value of each gift insurance information;

[0151] β 1 ,…,β n is the correction factor;

[0152] ε is the compensation value.

[0153] Optionally, the assignment rule includes:

[0154] For the continuous variables in the customer attribute information and the free insurance information, the actual value of the continuous variable is used as the information value of the continuous variable; and / or

[0155] For the discrete variables in the customer attribute information and the free insurance information, the information value of each discrete variable is calculated according to the following information value calculation formula:

[0156]

[0157] In the formula,

[0158] IV i is the information value of the ith group of the discrete variable;

[0159] #y i is the number of high-value customers in the i-th group of the discrete variable in the customer sample data;

[0160] #y T is the number of all high-value customers in the customer sample data;

[0161] #n i is the number of low-value customers in the ith group of the discrete variable in the customer sample data;

[0162] #nT is the number of all low-value customers in the customer sample data.

[0163] The embodiments of the device provided by the present invention can be specifically used to execute the processing flow of the above-mentioned method embodiments. Its functions are not described in detail here, and reference can be made to the detailed description of the above-mentioned method embodiments.

[0164] It should be noted that the high-value customer identification method and device provided in the embodiment of the present invention can be used in the field of data processing technology, and can be specifically applied to technical fields such as insurance and finance. The embodiment of the present invention does not limit the application field of the high-value customer identification method and device.

[0165] Figure 7 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention is shown in FIG. Figure 7 As shown, the electronic device may include: a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302 and the memory 303 communicate with each other through the communication bus 304. The processor 301 may call the logic instructions in the memory 303 to execute the method described in any of the above embodiments, for example, including: when the customer information in the database is updated, obtaining the updated customer information with the gift insurance identification in the database; searching for customer attribute information and gift insurance information in the updated customer information with the gift insurance identification; calculating the value score of the customer according to the customer attribute information and the gift insurance information; if the value score of the customer meets the scoring conditions of the high-value customer, determining that the customer is a high-value customer.

[0166] In addition, the logic instructions in the above-mentioned memory 303 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0167] The present embodiment discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the methods provided by the above-mentioned method embodiments, for example, including: when customer information in a database is updated, obtaining updated customer information with a free insurance identification in the database; searching for customer attribute information and free insurance information in the updated customer information with the free insurance identification; calculating the value score of the customer based on the customer attribute information and the free insurance information; if the value score of the customer meets the scoring conditions of a high-value customer, determining that the customer is a high-value customer.

[0168] The present embodiment provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program enables the computer to execute the methods provided by the above-mentioned method embodiments, for example, including: when customer information in a database is updated, obtaining updated customer information with a free insurance identification in the database; searching for customer attribute information and free insurance information in the updated customer information with the free insurance identification; calculating a value score of the customer based on the customer attribute information and free insurance information; and determining that the customer is a high-value customer if the customer's value score meets a scoring condition for a high-value customer.

[0169] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0170] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0171] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0172] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0173] In the description of this specification, the description with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0174] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for identifying high-value customers, characterized in that: include: When the customer information in the database is updated, the updated customer information with the free insurance identification in the database is obtained; Searching for customer attribute information and free insurance information in the updated customer information with the free insurance identifier; Calculate the value score of the customer based on the customer attribute information and the free insurance information; If the customer's value score meets the high-value customer's score conditions, the customer is determined to be a high-value customer; When the customer information in the database is updated, obtaining the updated customer information with the free insurance identification in the database includes: When the customer information in the database is updated, the updated customer information with the free insurance identification in the database is synchronized to the distributed message system cluster; Writing the customer information in the distributed messaging system cluster into a pre-created customer information table through the batch-stream integration platform; When the customer information in the database is updated, synchronizing the updated customer information with the free insurance identification in the database to the distributed message system cluster specifically includes: collecting the updated customer information with the free insurance identification in the MySQL / Oracle database into Kafka, wherein the Oracle part needs to submit an application to the DBA, and the MySQL part needs to configure the canal into the Kafka cluster; The method of writing the customer information in the distributed message system cluster into a pre-created customer information table through the streaming-batch integrated platform specifically includes: entering the streaming-batch integrated platform and creating a flink kafka table; creating a flink write table in Hive and authorizing it to the flink user through the streaming-batch integrated platform; submitting insert in to hive table and select * from kafka table on the streaming-batch integrated platform, and then the streaming collection task is submitted successfully; the streaming-batch integrated platform automatically collects the updated customer information with the free insurance identification in the kafka cluster according to the streaming collection task, and writes it into the hive table; creating a jenkins job, combining the real-time streaming data in Flink with the offline Hive data, and directly backfilling the Hive data in a unified manner through Flink to merge the increments into the historical data to achieve real-time data updating, wherein the historical data is stored in the pre-created customer information table.

2. The method according to claim 1, characterized in that The step of searching for customer attribute information and free insurance information in the updated customer information with the free insurance identification includes: In the customer information table, searching for the field values ​​of each field in the preset policyholder information table model, the insured person information table model, the policy information table model, and the claim information table model; Generate the customer's policyholder information table, insured person information table, policy information table and claim information table according to the found field values ​​of each field; The customer attribute information and free insurance information of the customer are obtained from the customer's policyholder information form, insured person information form, policy information form and claim information form.

3. The method according to claim 1, characterized in that The customer attribute information includes at least one of the following: age, gender, occupation, education level, social security information, historical compensation amount, and number of paid products purchased.

4. The method according to claim 1 or 3, characterized in that: Calculating the customer's value score according to the customer attribute information and the free insurance information includes: According to the assignment rules of customer attribute information and free insurance information, determine the information value of each item of customer attribute information and each item of free insurance information; The value score of the customer is calculated based on the information value of each item of customer attribute information and each item of free insurance information.

5. The method according to claim 4, characterized in that The customer value score is calculated according to the following customer value score calculation formula: y=β1x1+…+β k x k +b k+1 x k+1 +…b n x n +e; In the formula, y is the customer's value score; x1,…,x k The information value of each customer attribute information; x k+1 ,…,x n The information value of each gift insurance information; β1,…,β n is the correction factor; ε is the compensation value.

6. The method according to claim 4, characterized in that The assignment rules include: For the continuous variables in the customer attribute information and the free insurance information, the actual value of the continuous variable is used as the information value of the continuous variable; and / or For the discrete variables in the customer attribute information and the free insurance information, the information value of each discrete variable is calculated according to the following information value calculation formula: In the formula, IV i is the information value of the ith group of the discrete variable; #y i is the number of high-value customers in the i-th group of the discrete variable in the customer sample data; #y T is the number of all high-value customers in the customer sample data; #n i is the number of low-value customers in the ith group of the discrete variable in the customer sample data; #n T is the number of all low-value customers in the customer sample data.

7. A high-value customer identification device, characterized in that: include: An acquisition module, used for acquiring updated customer information with a free insurance identification in the database when the customer information in the database is updated; A search module, used for searching the customer attribute information and the free insurance information in the updated customer information with the free insurance identification; A calculation module, used to calculate the value score of the customer based on the customer attribute information and the free insurance information; A determination module, configured to determine that the customer is a high-value customer if the customer's value score meets the high-value customer's score condition; When the customer information in the database is updated, obtaining the updated customer information with the free insurance identification in the database includes: When the customer information in the database is updated, the updated customer information with the free insurance identification in the database is synchronized to the distributed message system cluster; Writing the customer information in the distributed messaging system cluster into a pre-created customer information table through the batch-stream integration platform; When the customer information in the database is updated, synchronizing the updated customer information with the free insurance identification in the database to the distributed message system cluster specifically includes: collecting the updated customer information with the free insurance identification in the MySQL / Oracle database into Kafka, wherein the Oracle part needs to submit an application to the DBA, and the MySQL part needs to configure the canal into the Kafka cluster; The method of writing the customer information in the distributed message system cluster into a pre-created customer information table through the streaming-batch integrated platform specifically includes: entering the streaming-batch integrated platform and creating a flink kafka table; creating a flink write table in Hive and authorizing it to the flink user through the streaming-batch integrated platform; submitting insert in to hive table and select * from kafka table on the streaming-batch integrated platform, and then the streaming collection task is submitted successfully; the streaming-batch integrated platform automatically collects the updated customer information with the free insurance identification in the kafka cluster according to the streaming collection task, and writes it into the hive table; creating a jenkins job, combining the real-time streaming data in Flink with the offline Hive data, and directly backfilling the Hive data in a unified manner through Flink to merge the increments into the historical data to achieve real-time data updating, wherein the historical data is stored in the pre-created customer information table.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images